{ "best_metric": 1.8950828313827515, "best_model_checkpoint": "/mnt/proj1/open-28-58/lakoc/LoCo-ASR/experiments/TED_CLM_gpt2_tedlium2/checkpoint-72000", "epoch": 15.0, "global_step": 72405, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2.5e-07, "loss": 6.3048, "step": 5 }, { "epoch": 0.0, "learning_rate": 5e-07, "loss": 6.2151, "step": 10 }, { "epoch": 0.0, "learning_rate": 7.5e-07, "loss": 6.0244, "step": 15 }, { "epoch": 0.0, "learning_rate": 1e-06, "loss": 5.7785, "step": 20 }, { "epoch": 0.01, "learning_rate": 1.25e-06, "loss": 5.5406, "step": 25 }, { "epoch": 0.01, "learning_rate": 1.5e-06, "loss": 5.3438, "step": 30 }, { "epoch": 0.01, "learning_rate": 1.75e-06, "loss": 5.1954, "step": 35 }, { "epoch": 0.01, "learning_rate": 2e-06, "loss": 5.0799, "step": 40 }, { "epoch": 0.01, "learning_rate": 2.25e-06, "loss": 4.9952, "step": 45 }, { "epoch": 0.01, "learning_rate": 2.5e-06, "loss": 4.9318, "step": 50 }, { "epoch": 0.01, "learning_rate": 2.75e-06, "loss": 4.8847, "step": 55 }, { "epoch": 0.01, "learning_rate": 3e-06, "loss": 4.8332, "step": 60 }, { "epoch": 0.01, "learning_rate": 3.25e-06, "loss": 4.7684, "step": 65 }, { "epoch": 0.01, "learning_rate": 3.5e-06, "loss": 4.6907, "step": 70 }, { "epoch": 0.02, "learning_rate": 3.75e-06, "loss": 4.625, "step": 75 }, { "epoch": 0.02, "learning_rate": 4e-06, "loss": 4.5686, "step": 80 }, { "epoch": 0.02, "learning_rate": 4.250000000000001e-06, "loss": 4.5225, "step": 85 }, { "epoch": 0.02, "learning_rate": 4.5e-06, "loss": 4.4793, "step": 90 }, { "epoch": 0.02, "learning_rate": 4.75e-06, "loss": 4.4352, "step": 95 }, { "epoch": 0.02, "learning_rate": 5e-06, "loss": 4.4006, "step": 100 }, { "epoch": 0.02, "learning_rate": 5.2500000000000006e-06, "loss": 4.3665, "step": 105 }, { "epoch": 0.02, "learning_rate": 5.5e-06, "loss": 4.3411, "step": 110 }, { "epoch": 0.02, "learning_rate": 5.75e-06, "loss": 4.3182, "step": 115 }, { "epoch": 0.02, "learning_rate": 6e-06, "loss": 4.2887, "step": 120 }, { "epoch": 0.03, "learning_rate": 6.25e-06, "loss": 4.2693, "step": 125 }, { "epoch": 0.03, "learning_rate": 6.5e-06, "loss": 4.2506, "step": 130 }, { "epoch": 0.03, "learning_rate": 6.75e-06, "loss": 4.2329, "step": 135 }, { "epoch": 0.03, "learning_rate": 7e-06, "loss": 4.2199, "step": 140 }, { "epoch": 0.03, "learning_rate": 7.250000000000001e-06, "loss": 4.2036, "step": 145 }, { "epoch": 0.03, "learning_rate": 7.5e-06, "loss": 4.19, "step": 150 }, { "epoch": 0.03, "learning_rate": 7.75e-06, "loss": 4.1732, "step": 155 }, { "epoch": 0.03, "learning_rate": 8e-06, "loss": 4.1584, "step": 160 }, { "epoch": 0.03, "learning_rate": 8.25e-06, "loss": 4.1444, "step": 165 }, { "epoch": 0.04, "learning_rate": 8.500000000000002e-06, "loss": 4.1255, "step": 170 }, { "epoch": 0.04, "learning_rate": 8.750000000000001e-06, "loss": 4.111, "step": 175 }, { "epoch": 0.04, "learning_rate": 9e-06, "loss": 4.0926, "step": 180 }, { "epoch": 0.04, "learning_rate": 9.25e-06, "loss": 4.0763, "step": 185 }, { "epoch": 0.04, "learning_rate": 9.5e-06, "loss": 4.0577, "step": 190 }, { "epoch": 0.04, "learning_rate": 9.75e-06, "loss": 4.0414, "step": 195 }, { "epoch": 0.04, "learning_rate": 1e-05, "loss": 4.0243, "step": 200 }, { "epoch": 0.04, "learning_rate": 1.025e-05, "loss": 4.0041, "step": 205 }, { "epoch": 0.04, "learning_rate": 1.0500000000000001e-05, "loss": 3.9968, "step": 210 }, { "epoch": 0.04, "learning_rate": 1.0749999999999999e-05, "loss": 3.9743, "step": 215 }, { "epoch": 0.05, "learning_rate": 1.1e-05, "loss": 3.957, "step": 220 }, { "epoch": 0.05, "learning_rate": 1.1249999999999999e-05, "loss": 3.9446, "step": 225 }, { "epoch": 0.05, "learning_rate": 1.15e-05, "loss": 3.9295, "step": 230 }, { "epoch": 0.05, "learning_rate": 1.1750000000000001e-05, "loss": 3.9138, "step": 235 }, { "epoch": 0.05, "learning_rate": 1.2e-05, "loss": 3.8994, "step": 240 }, { "epoch": 0.05, "learning_rate": 1.2250000000000001e-05, "loss": 3.8761, "step": 245 }, { "epoch": 0.05, "learning_rate": 1.25e-05, "loss": 3.8592, "step": 250 }, { "epoch": 0.05, "learning_rate": 1.275e-05, "loss": 3.841, "step": 255 }, { "epoch": 0.05, "learning_rate": 1.3e-05, "loss": 3.8237, "step": 260 }, { "epoch": 0.05, "learning_rate": 1.325e-05, "loss": 3.8146, "step": 265 }, { "epoch": 0.06, "learning_rate": 1.35e-05, "loss": 3.7938, "step": 270 }, { "epoch": 0.06, "learning_rate": 1.375e-05, "loss": 3.7773, "step": 275 }, { "epoch": 0.06, "learning_rate": 1.4e-05, "loss": 3.771, "step": 280 }, { "epoch": 0.06, "learning_rate": 1.425e-05, "loss": 3.7589, "step": 285 }, { "epoch": 0.06, "learning_rate": 1.4500000000000002e-05, "loss": 3.7464, "step": 290 }, { "epoch": 0.06, "learning_rate": 1.475e-05, "loss": 3.7312, "step": 295 }, { "epoch": 0.06, "learning_rate": 1.5e-05, "loss": 3.7245, "step": 300 }, { "epoch": 0.06, "learning_rate": 1.525e-05, "loss": 3.7163, "step": 305 }, { "epoch": 0.06, "learning_rate": 1.55e-05, "loss": 3.7048, "step": 310 }, { "epoch": 0.07, "learning_rate": 1.575e-05, "loss": 3.6935, "step": 315 }, { "epoch": 0.07, "learning_rate": 1.6e-05, "loss": 3.6841, "step": 320 }, { "epoch": 0.07, "learning_rate": 1.6250000000000002e-05, "loss": 3.6823, "step": 325 }, { "epoch": 0.07, "learning_rate": 1.65e-05, "loss": 3.6705, "step": 330 }, { "epoch": 0.07, "learning_rate": 1.675e-05, "loss": 3.6669, "step": 335 }, { "epoch": 0.07, "learning_rate": 1.7000000000000003e-05, "loss": 3.6563, "step": 340 }, { "epoch": 0.07, "learning_rate": 1.7250000000000003e-05, "loss": 3.6524, "step": 345 }, { "epoch": 0.07, "learning_rate": 1.7500000000000002e-05, "loss": 3.649, "step": 350 }, { "epoch": 0.07, "learning_rate": 1.7749999999999998e-05, "loss": 3.6407, "step": 355 }, { "epoch": 0.07, "learning_rate": 1.8e-05, "loss": 3.632, "step": 360 }, { "epoch": 0.08, "learning_rate": 1.825e-05, "loss": 3.6278, "step": 365 }, { "epoch": 0.08, "learning_rate": 1.85e-05, "loss": 3.6167, "step": 370 }, { "epoch": 0.08, "learning_rate": 1.875e-05, "loss": 3.6094, "step": 375 }, { "epoch": 0.08, "learning_rate": 1.9e-05, "loss": 3.6035, "step": 380 }, { "epoch": 0.08, "learning_rate": 1.925e-05, "loss": 3.5965, "step": 385 }, { "epoch": 0.08, "learning_rate": 1.95e-05, "loss": 3.5861, "step": 390 }, { "epoch": 0.08, "learning_rate": 1.975e-05, "loss": 3.5789, "step": 395 }, { "epoch": 0.08, "learning_rate": 2e-05, "loss": 3.5767, "step": 400 }, { "epoch": 0.08, "learning_rate": 2.025e-05, "loss": 3.5747, "step": 405 }, { "epoch": 0.08, "learning_rate": 2.05e-05, "loss": 3.5689, "step": 410 }, { "epoch": 0.09, "learning_rate": 2.0750000000000003e-05, "loss": 3.5589, "step": 415 }, { "epoch": 0.09, "learning_rate": 2.1000000000000002e-05, "loss": 3.5549, "step": 420 }, { "epoch": 0.09, "learning_rate": 2.125e-05, "loss": 3.5479, "step": 425 }, { "epoch": 0.09, "learning_rate": 2.1499999999999997e-05, "loss": 3.541, "step": 430 }, { "epoch": 0.09, "learning_rate": 2.175e-05, "loss": 3.5385, "step": 435 }, { "epoch": 0.09, "learning_rate": 2.2e-05, "loss": 3.5315, "step": 440 }, { "epoch": 0.09, "learning_rate": 2.225e-05, "loss": 3.5353, "step": 445 }, { "epoch": 0.09, "learning_rate": 2.2499999999999998e-05, "loss": 3.5239, "step": 450 }, { "epoch": 0.09, "learning_rate": 2.275e-05, "loss": 3.5248, "step": 455 }, { "epoch": 0.1, "learning_rate": 2.3e-05, "loss": 3.5135, "step": 460 }, { "epoch": 0.1, "learning_rate": 2.325e-05, "loss": 3.516, "step": 465 }, { "epoch": 0.1, "learning_rate": 2.3500000000000002e-05, "loss": 3.5071, "step": 470 }, { "epoch": 0.1, "learning_rate": 2.375e-05, "loss": 3.5085, "step": 475 }, { "epoch": 0.1, "learning_rate": 2.4e-05, "loss": 3.5032, "step": 480 }, { "epoch": 0.1, "learning_rate": 2.425e-05, "loss": 3.4977, "step": 485 }, { "epoch": 0.1, "learning_rate": 2.4500000000000003e-05, "loss": 3.4942, "step": 490 }, { "epoch": 0.1, "learning_rate": 2.4750000000000002e-05, "loss": 3.491, "step": 495 }, { "epoch": 0.1, "learning_rate": 2.5e-05, "loss": 3.4932, "step": 500 }, { "epoch": 0.1, "learning_rate": 2.525e-05, "loss": 3.4812, "step": 505 }, { "epoch": 0.11, "learning_rate": 2.55e-05, "loss": 3.4808, "step": 510 }, { "epoch": 0.11, "learning_rate": 2.575e-05, "loss": 3.4797, "step": 515 }, { "epoch": 0.11, "learning_rate": 2.6e-05, "loss": 3.4764, "step": 520 }, { "epoch": 0.11, "learning_rate": 2.625e-05, "loss": 3.4725, "step": 525 }, { "epoch": 0.11, "learning_rate": 2.65e-05, "loss": 3.4658, "step": 530 }, { "epoch": 0.11, "learning_rate": 2.675e-05, "loss": 3.4622, "step": 535 }, { "epoch": 0.11, "learning_rate": 2.7e-05, "loss": 3.4575, "step": 540 }, { "epoch": 0.11, "learning_rate": 2.725e-05, "loss": 3.4522, "step": 545 }, { "epoch": 0.11, "learning_rate": 2.75e-05, "loss": 3.4513, "step": 550 }, { "epoch": 0.11, "learning_rate": 2.775e-05, "loss": 3.4538, "step": 555 }, { "epoch": 0.12, "learning_rate": 2.8e-05, "loss": 3.4468, "step": 560 }, { "epoch": 0.12, "learning_rate": 2.8250000000000002e-05, "loss": 3.4382, "step": 565 }, { "epoch": 0.12, "learning_rate": 2.85e-05, "loss": 3.43, "step": 570 }, { "epoch": 0.12, "learning_rate": 2.875e-05, "loss": 3.428, "step": 575 }, { "epoch": 0.12, "learning_rate": 2.9000000000000004e-05, "loss": 3.4296, "step": 580 }, { "epoch": 0.12, "learning_rate": 2.9250000000000003e-05, "loss": 3.4218, "step": 585 }, { "epoch": 0.12, "learning_rate": 2.95e-05, "loss": 3.4113, "step": 590 }, { "epoch": 0.12, "learning_rate": 2.9749999999999998e-05, "loss": 3.4118, "step": 595 }, { "epoch": 0.12, "learning_rate": 3e-05, "loss": 3.4028, "step": 600 }, { "epoch": 0.13, "learning_rate": 3.025e-05, "loss": 3.4058, "step": 605 }, { "epoch": 0.13, "learning_rate": 3.05e-05, "loss": 3.4039, "step": 610 }, { "epoch": 0.13, "learning_rate": 3.075e-05, "loss": 3.3928, "step": 615 }, { "epoch": 0.13, "learning_rate": 3.1e-05, "loss": 3.3955, "step": 620 }, { "epoch": 0.13, "learning_rate": 3.125e-05, "loss": 3.3928, "step": 625 }, { "epoch": 0.13, "learning_rate": 3.15e-05, "loss": 3.3835, "step": 630 }, { "epoch": 0.13, "learning_rate": 3.175e-05, "loss": 3.3785, "step": 635 }, { "epoch": 0.13, "learning_rate": 3.2e-05, "loss": 3.3665, "step": 640 }, { "epoch": 0.13, "learning_rate": 3.2250000000000005e-05, "loss": 3.3712, "step": 645 }, { "epoch": 0.13, "learning_rate": 3.2500000000000004e-05, "loss": 3.3605, "step": 650 }, { "epoch": 0.14, "learning_rate": 3.275e-05, "loss": 3.3629, "step": 655 }, { "epoch": 0.14, "learning_rate": 3.3e-05, "loss": 3.3476, "step": 660 }, { "epoch": 0.14, "learning_rate": 3.325e-05, "loss": 3.3402, "step": 665 }, { "epoch": 0.14, "learning_rate": 3.35e-05, "loss": 3.3402, "step": 670 }, { "epoch": 0.14, "learning_rate": 3.375e-05, "loss": 3.3358, "step": 675 }, { "epoch": 0.14, "learning_rate": 3.4000000000000007e-05, "loss": 3.3297, "step": 680 }, { "epoch": 0.14, "learning_rate": 3.4250000000000006e-05, "loss": 3.3264, "step": 685 }, { "epoch": 0.14, "learning_rate": 3.4500000000000005e-05, "loss": 3.3264, "step": 690 }, { "epoch": 0.14, "learning_rate": 3.4750000000000004e-05, "loss": 3.3161, "step": 695 }, { "epoch": 0.15, "learning_rate": 3.5000000000000004e-05, "loss": 3.3132, "step": 700 }, { "epoch": 0.15, "learning_rate": 3.5249999999999996e-05, "loss": 3.3153, "step": 705 }, { "epoch": 0.15, "learning_rate": 3.5499999999999996e-05, "loss": 3.3127, "step": 710 }, { "epoch": 0.15, "learning_rate": 3.5749999999999995e-05, "loss": 3.3051, "step": 715 }, { "epoch": 0.15, "learning_rate": 3.6e-05, "loss": 3.31, "step": 720 }, { "epoch": 0.15, "learning_rate": 3.625e-05, "loss": 3.2996, "step": 725 }, { "epoch": 0.15, "learning_rate": 3.65e-05, "loss": 3.2817, "step": 730 }, { "epoch": 0.15, "learning_rate": 3.675e-05, "loss": 3.283, "step": 735 }, { "epoch": 0.15, "learning_rate": 3.7e-05, "loss": 3.2792, "step": 740 }, { "epoch": 0.15, "learning_rate": 3.725e-05, "loss": 3.2718, "step": 745 }, { "epoch": 0.16, "learning_rate": 3.75e-05, "loss": 3.2678, "step": 750 }, { "epoch": 0.16, "learning_rate": 3.775e-05, "loss": 3.2691, "step": 755 }, { "epoch": 0.16, "learning_rate": 3.8e-05, "loss": 3.2623, "step": 760 }, { "epoch": 0.16, "learning_rate": 3.825e-05, "loss": 3.2508, "step": 765 }, { "epoch": 0.16, "learning_rate": 3.85e-05, "loss": 3.2457, "step": 770 }, { "epoch": 0.16, "learning_rate": 3.875e-05, "loss": 3.2478, "step": 775 }, { "epoch": 0.16, "learning_rate": 3.9e-05, "loss": 3.2352, "step": 780 }, { "epoch": 0.16, "learning_rate": 3.925e-05, "loss": 3.231, "step": 785 }, { "epoch": 0.16, "learning_rate": 3.95e-05, "loss": 3.2234, "step": 790 }, { "epoch": 0.16, "learning_rate": 3.9750000000000004e-05, "loss": 3.2254, "step": 795 }, { "epoch": 0.17, "learning_rate": 4e-05, "loss": 3.2133, "step": 800 }, { "epoch": 0.17, "learning_rate": 4.025e-05, "loss": 3.2055, "step": 805 }, { "epoch": 0.17, "learning_rate": 4.05e-05, "loss": 3.2009, "step": 810 }, { "epoch": 0.17, "learning_rate": 4.075e-05, "loss": 3.1954, "step": 815 }, { "epoch": 0.17, "learning_rate": 4.1e-05, "loss": 3.1867, "step": 820 }, { "epoch": 0.17, "learning_rate": 4.125e-05, "loss": 3.1822, "step": 825 }, { "epoch": 0.17, "learning_rate": 4.1500000000000006e-05, "loss": 3.172, "step": 830 }, { "epoch": 0.17, "learning_rate": 4.1750000000000005e-05, "loss": 3.1766, "step": 835 }, { "epoch": 0.17, "learning_rate": 4.2000000000000004e-05, "loss": 3.1694, "step": 840 }, { "epoch": 0.18, "learning_rate": 4.2250000000000004e-05, "loss": 3.158, "step": 845 }, { "epoch": 0.18, "learning_rate": 4.25e-05, "loss": 3.152, "step": 850 }, { "epoch": 0.18, "learning_rate": 4.275e-05, "loss": 3.1436, "step": 855 }, { "epoch": 0.18, "learning_rate": 4.2999999999999995e-05, "loss": 3.1384, "step": 860 }, { "epoch": 0.18, "learning_rate": 4.325e-05, "loss": 3.1295, "step": 865 }, { "epoch": 0.18, "learning_rate": 4.35e-05, "loss": 3.1285, "step": 870 }, { "epoch": 0.18, "learning_rate": 4.375e-05, "loss": 3.1202, "step": 875 }, { "epoch": 0.18, "learning_rate": 4.4e-05, "loss": 3.115, "step": 880 }, { "epoch": 0.18, "learning_rate": 4.425e-05, "loss": 3.1064, "step": 885 }, { "epoch": 0.18, "learning_rate": 4.45e-05, "loss": 3.0987, "step": 890 }, { "epoch": 0.19, "learning_rate": 4.475e-05, "loss": 3.0917, "step": 895 }, { "epoch": 0.19, "learning_rate": 4.4999999999999996e-05, "loss": 3.0849, "step": 900 }, { "epoch": 0.19, "learning_rate": 4.525e-05, "loss": 3.0816, "step": 905 }, { "epoch": 0.19, "learning_rate": 4.55e-05, "loss": 3.0695, "step": 910 }, { "epoch": 0.19, "learning_rate": 4.575e-05, "loss": 3.0564, "step": 915 }, { "epoch": 0.19, "learning_rate": 4.6e-05, "loss": 3.0573, "step": 920 }, { "epoch": 0.19, "learning_rate": 4.625e-05, "loss": 3.0537, "step": 925 }, { "epoch": 0.19, "learning_rate": 4.65e-05, "loss": 3.0562, "step": 930 }, { "epoch": 0.19, "learning_rate": 4.675e-05, "loss": 3.0416, "step": 935 }, { "epoch": 0.19, "learning_rate": 4.7000000000000004e-05, "loss": 3.0281, "step": 940 }, { "epoch": 0.2, "learning_rate": 4.725e-05, "loss": 3.0244, "step": 945 }, { "epoch": 0.2, "learning_rate": 4.75e-05, "loss": 3.0126, "step": 950 }, { "epoch": 0.2, "learning_rate": 4.775e-05, "loss": 3.0098, "step": 955 }, { "epoch": 0.2, "learning_rate": 4.8e-05, "loss": 2.9975, "step": 960 }, { "epoch": 0.2, "learning_rate": 4.825e-05, "loss": 2.9873, "step": 965 }, { "epoch": 0.2, "learning_rate": 4.85e-05, "loss": 2.9896, "step": 970 }, { "epoch": 0.2, "learning_rate": 4.8750000000000006e-05, "loss": 2.986, "step": 975 }, { "epoch": 0.2, "learning_rate": 4.9000000000000005e-05, "loss": 2.9725, "step": 980 }, { "epoch": 0.2, "learning_rate": 4.9250000000000004e-05, "loss": 2.9644, "step": 985 }, { "epoch": 0.21, "learning_rate": 4.9500000000000004e-05, "loss": 2.957, "step": 990 }, { "epoch": 0.21, "learning_rate": 4.975e-05, "loss": 2.9492, "step": 995 }, { "epoch": 0.21, "learning_rate": 5e-05, "loss": 2.9528, "step": 1000 }, { "epoch": 0.21, "learning_rate": 5.025e-05, "loss": 2.9381, "step": 1005 }, { "epoch": 0.21, "learning_rate": 5.05e-05, "loss": 2.9371, "step": 1010 }, { "epoch": 0.21, "learning_rate": 5.075000000000001e-05, "loss": 2.9292, "step": 1015 }, { "epoch": 0.21, "learning_rate": 5.1e-05, "loss": 2.914, "step": 1020 }, { "epoch": 0.21, "learning_rate": 5.125e-05, "loss": 2.9089, "step": 1025 }, { "epoch": 0.21, "learning_rate": 5.15e-05, "loss": 2.9121, "step": 1030 }, { "epoch": 0.21, "learning_rate": 5.175e-05, "loss": 2.9011, "step": 1035 }, { "epoch": 0.22, "learning_rate": 5.2e-05, "loss": 2.8985, "step": 1040 }, { "epoch": 0.22, "learning_rate": 5.2249999999999996e-05, "loss": 2.8844, "step": 1045 }, { "epoch": 0.22, "learning_rate": 5.25e-05, "loss": 2.8742, "step": 1050 }, { "epoch": 0.22, "learning_rate": 5.275e-05, "loss": 2.8639, "step": 1055 }, { "epoch": 0.22, "learning_rate": 5.3e-05, "loss": 2.8597, "step": 1060 }, { "epoch": 0.22, "learning_rate": 5.325e-05, "loss": 2.8533, "step": 1065 }, { "epoch": 0.22, "learning_rate": 5.35e-05, "loss": 2.8467, "step": 1070 }, { "epoch": 0.22, "learning_rate": 5.375e-05, "loss": 2.8438, "step": 1075 }, { "epoch": 0.22, "learning_rate": 5.4e-05, "loss": 2.836, "step": 1080 }, { "epoch": 0.22, "learning_rate": 5.4250000000000004e-05, "loss": 2.8254, "step": 1085 }, { "epoch": 0.23, "learning_rate": 5.45e-05, "loss": 2.8298, "step": 1090 }, { "epoch": 0.23, "learning_rate": 5.475e-05, "loss": 2.8134, "step": 1095 }, { "epoch": 0.23, "learning_rate": 5.5e-05, "loss": 2.8133, "step": 1100 }, { "epoch": 0.23, "learning_rate": 5.525e-05, "loss": 2.8043, "step": 1105 }, { "epoch": 0.23, "learning_rate": 5.55e-05, "loss": 2.8021, "step": 1110 }, { "epoch": 0.23, "learning_rate": 5.575e-05, "loss": 2.7933, "step": 1115 }, { "epoch": 0.23, "learning_rate": 5.6e-05, "loss": 2.7822, "step": 1120 }, { "epoch": 0.23, "learning_rate": 5.6250000000000005e-05, "loss": 2.7744, "step": 1125 }, { "epoch": 0.23, "learning_rate": 5.6500000000000005e-05, "loss": 2.7714, "step": 1130 }, { "epoch": 0.24, "learning_rate": 5.6750000000000004e-05, "loss": 2.7674, "step": 1135 }, { "epoch": 0.24, "learning_rate": 5.7e-05, "loss": 2.7599, "step": 1140 }, { "epoch": 0.24, "learning_rate": 5.725e-05, "loss": 2.7615, "step": 1145 }, { "epoch": 0.24, "learning_rate": 5.75e-05, "loss": 2.7487, "step": 1150 }, { "epoch": 0.24, "learning_rate": 5.775e-05, "loss": 2.7442, "step": 1155 }, { "epoch": 0.24, "learning_rate": 5.800000000000001e-05, "loss": 2.7396, "step": 1160 }, { "epoch": 0.24, "learning_rate": 5.8250000000000006e-05, "loss": 2.7388, "step": 1165 }, { "epoch": 0.24, "learning_rate": 5.8500000000000006e-05, "loss": 2.7227, "step": 1170 }, { "epoch": 0.24, "learning_rate": 5.875e-05, "loss": 2.7267, "step": 1175 }, { "epoch": 0.24, "learning_rate": 5.9e-05, "loss": 2.716, "step": 1180 }, { "epoch": 0.25, "learning_rate": 5.925e-05, "loss": 2.7087, "step": 1185 }, { "epoch": 0.25, "learning_rate": 5.9499999999999996e-05, "loss": 2.7092, "step": 1190 }, { "epoch": 0.25, "learning_rate": 5.9749999999999995e-05, "loss": 2.7013, "step": 1195 }, { "epoch": 0.25, "learning_rate": 6e-05, "loss": 2.6978, "step": 1200 }, { "epoch": 0.25, "learning_rate": 6.025e-05, "loss": 2.6873, "step": 1205 }, { "epoch": 0.25, "learning_rate": 6.05e-05, "loss": 2.6811, "step": 1210 }, { "epoch": 0.25, "learning_rate": 6.075e-05, "loss": 2.6736, "step": 1215 }, { "epoch": 0.25, "learning_rate": 6.1e-05, "loss": 2.6763, "step": 1220 }, { "epoch": 0.25, "learning_rate": 6.125e-05, "loss": 2.6725, "step": 1225 }, { "epoch": 0.25, "learning_rate": 6.15e-05, "loss": 2.6687, "step": 1230 }, { "epoch": 0.26, "learning_rate": 6.175e-05, "loss": 2.6555, "step": 1235 }, { "epoch": 0.26, "learning_rate": 6.2e-05, "loss": 2.6554, "step": 1240 }, { "epoch": 0.26, "learning_rate": 6.225e-05, "loss": 2.6599, "step": 1245 }, { "epoch": 0.26, "learning_rate": 6.25e-05, "loss": 2.6526, "step": 1250 }, { "epoch": 0.26, "learning_rate": 6.275000000000001e-05, "loss": 2.6531, "step": 1255 }, { "epoch": 0.26, "learning_rate": 6.3e-05, "loss": 2.6423, "step": 1260 }, { "epoch": 0.26, "learning_rate": 6.325e-05, "loss": 2.6409, "step": 1265 }, { "epoch": 0.26, "learning_rate": 6.35e-05, "loss": 2.6376, "step": 1270 }, { "epoch": 0.26, "learning_rate": 6.375e-05, "loss": 2.6327, "step": 1275 }, { "epoch": 0.27, "learning_rate": 6.4e-05, "loss": 2.6298, "step": 1280 }, { "epoch": 0.27, "learning_rate": 6.425e-05, "loss": 2.6211, "step": 1285 }, { "epoch": 0.27, "learning_rate": 6.450000000000001e-05, "loss": 2.624, "step": 1290 }, { "epoch": 0.27, "learning_rate": 6.475e-05, "loss": 2.6132, "step": 1295 }, { "epoch": 0.27, "learning_rate": 6.500000000000001e-05, "loss": 2.6049, "step": 1300 }, { "epoch": 0.27, "learning_rate": 6.525e-05, "loss": 2.6044, "step": 1305 }, { "epoch": 0.27, "learning_rate": 6.55e-05, "loss": 2.5976, "step": 1310 }, { "epoch": 0.27, "learning_rate": 6.575e-05, "loss": 2.5937, "step": 1315 }, { "epoch": 0.27, "learning_rate": 6.6e-05, "loss": 2.5865, "step": 1320 }, { "epoch": 0.27, "learning_rate": 6.625000000000001e-05, "loss": 2.5955, "step": 1325 }, { "epoch": 0.28, "learning_rate": 6.65e-05, "loss": 2.5804, "step": 1330 }, { "epoch": 0.28, "learning_rate": 6.675000000000001e-05, "loss": 2.5918, "step": 1335 }, { "epoch": 0.28, "learning_rate": 6.7e-05, "loss": 2.5744, "step": 1340 }, { "epoch": 0.28, "learning_rate": 6.725000000000001e-05, "loss": 2.5738, "step": 1345 }, { "epoch": 0.28, "learning_rate": 6.75e-05, "loss": 2.5691, "step": 1350 }, { "epoch": 0.28, "learning_rate": 6.775000000000001e-05, "loss": 2.5706, "step": 1355 }, { "epoch": 0.28, "learning_rate": 6.800000000000001e-05, "loss": 2.5693, "step": 1360 }, { "epoch": 0.28, "learning_rate": 6.825e-05, "loss": 2.5652, "step": 1365 }, { "epoch": 0.28, "learning_rate": 6.850000000000001e-05, "loss": 2.5572, "step": 1370 }, { "epoch": 0.28, "learning_rate": 6.875e-05, "loss": 2.5588, "step": 1375 }, { "epoch": 0.29, "learning_rate": 6.900000000000001e-05, "loss": 2.5471, "step": 1380 }, { "epoch": 0.29, "learning_rate": 6.925e-05, "loss": 2.5502, "step": 1385 }, { "epoch": 0.29, "learning_rate": 6.950000000000001e-05, "loss": 2.5402, "step": 1390 }, { "epoch": 0.29, "learning_rate": 6.975e-05, "loss": 2.5514, "step": 1395 }, { "epoch": 0.29, "learning_rate": 7.000000000000001e-05, "loss": 2.5401, "step": 1400 }, { "epoch": 0.29, "learning_rate": 7.025000000000001e-05, "loss": 2.5374, "step": 1405 }, { "epoch": 0.29, "learning_rate": 7.049999999999999e-05, "loss": 2.5316, "step": 1410 }, { "epoch": 0.29, "learning_rate": 7.075e-05, "loss": 2.53, "step": 1415 }, { "epoch": 0.29, "learning_rate": 7.099999999999999e-05, "loss": 2.5301, "step": 1420 }, { "epoch": 0.3, "learning_rate": 7.125e-05, "loss": 2.5259, "step": 1425 }, { "epoch": 0.3, "learning_rate": 7.149999999999999e-05, "loss": 2.5173, "step": 1430 }, { "epoch": 0.3, "learning_rate": 7.175e-05, "loss": 2.5139, "step": 1435 }, { "epoch": 0.3, "learning_rate": 7.2e-05, "loss": 2.5141, "step": 1440 }, { "epoch": 0.3, "learning_rate": 7.225e-05, "loss": 2.5105, "step": 1445 }, { "epoch": 0.3, "learning_rate": 7.25e-05, "loss": 2.5109, "step": 1450 }, { "epoch": 0.3, "learning_rate": 7.274999999999999e-05, "loss": 2.5182, "step": 1455 }, { "epoch": 0.3, "learning_rate": 7.3e-05, "loss": 2.5053, "step": 1460 }, { "epoch": 0.3, "learning_rate": 7.324999999999999e-05, "loss": 2.4979, "step": 1465 }, { "epoch": 0.3, "learning_rate": 7.35e-05, "loss": 2.5046, "step": 1470 }, { "epoch": 0.31, "learning_rate": 7.375e-05, "loss": 2.4992, "step": 1475 }, { "epoch": 0.31, "learning_rate": 7.4e-05, "loss": 2.4926, "step": 1480 }, { "epoch": 0.31, "learning_rate": 7.425e-05, "loss": 2.4907, "step": 1485 }, { "epoch": 0.31, "learning_rate": 7.45e-05, "loss": 2.4912, "step": 1490 }, { "epoch": 0.31, "learning_rate": 7.475e-05, "loss": 2.4852, "step": 1495 }, { "epoch": 0.31, "learning_rate": 7.5e-05, "loss": 2.4848, "step": 1500 }, { "epoch": 0.31, "learning_rate": 7.525e-05, "loss": 2.475, "step": 1505 }, { "epoch": 0.31, "learning_rate": 7.55e-05, "loss": 2.4804, "step": 1510 }, { "epoch": 0.31, "learning_rate": 7.575e-05, "loss": 2.4785, "step": 1515 }, { "epoch": 0.31, "learning_rate": 7.6e-05, "loss": 2.4746, "step": 1520 }, { "epoch": 0.32, "learning_rate": 7.625e-05, "loss": 2.4687, "step": 1525 }, { "epoch": 0.32, "learning_rate": 7.65e-05, "loss": 2.472, "step": 1530 }, { "epoch": 0.32, "learning_rate": 7.675e-05, "loss": 2.4657, "step": 1535 }, { "epoch": 0.32, "learning_rate": 7.7e-05, "loss": 2.4647, "step": 1540 }, { "epoch": 0.32, "learning_rate": 7.725000000000001e-05, "loss": 2.4599, "step": 1545 }, { "epoch": 0.32, "learning_rate": 7.75e-05, "loss": 2.4571, "step": 1550 }, { "epoch": 0.32, "learning_rate": 7.775e-05, "loss": 2.454, "step": 1555 }, { "epoch": 0.32, "learning_rate": 7.8e-05, "loss": 2.4631, "step": 1560 }, { "epoch": 0.32, "learning_rate": 7.825e-05, "loss": 2.4576, "step": 1565 }, { "epoch": 0.33, "learning_rate": 7.85e-05, "loss": 2.4497, "step": 1570 }, { "epoch": 0.33, "learning_rate": 7.875e-05, "loss": 2.4519, "step": 1575 }, { "epoch": 0.33, "learning_rate": 7.9e-05, "loss": 2.4496, "step": 1580 }, { "epoch": 0.33, "learning_rate": 7.925e-05, "loss": 2.439, "step": 1585 }, { "epoch": 0.33, "learning_rate": 7.950000000000001e-05, "loss": 2.4449, "step": 1590 }, { "epoch": 0.33, "learning_rate": 7.975e-05, "loss": 2.4389, "step": 1595 }, { "epoch": 0.33, "learning_rate": 8e-05, "loss": 2.4348, "step": 1600 }, { "epoch": 0.33, "learning_rate": 8.025e-05, "loss": 2.4392, "step": 1605 }, { "epoch": 0.33, "learning_rate": 8.05e-05, "loss": 2.4381, "step": 1610 }, { "epoch": 0.33, "learning_rate": 8.075e-05, "loss": 2.4275, "step": 1615 }, { "epoch": 0.34, "learning_rate": 8.1e-05, "loss": 2.4336, "step": 1620 }, { "epoch": 0.34, "learning_rate": 8.125000000000001e-05, "loss": 2.4262, "step": 1625 }, { "epoch": 0.34, "learning_rate": 8.15e-05, "loss": 2.4249, "step": 1630 }, { "epoch": 0.34, "learning_rate": 8.175000000000001e-05, "loss": 2.4271, "step": 1635 }, { "epoch": 0.34, "learning_rate": 8.2e-05, "loss": 2.4141, "step": 1640 }, { "epoch": 0.34, "learning_rate": 8.225000000000001e-05, "loss": 2.4256, "step": 1645 }, { "epoch": 0.34, "learning_rate": 8.25e-05, "loss": 2.4184, "step": 1650 }, { "epoch": 0.34, "learning_rate": 8.275e-05, "loss": 2.4165, "step": 1655 }, { "epoch": 0.34, "learning_rate": 8.300000000000001e-05, "loss": 2.4169, "step": 1660 }, { "epoch": 0.34, "learning_rate": 8.325e-05, "loss": 2.4111, "step": 1665 }, { "epoch": 0.35, "learning_rate": 8.350000000000001e-05, "loss": 2.4097, "step": 1670 }, { "epoch": 0.35, "learning_rate": 8.375e-05, "loss": 2.4093, "step": 1675 }, { "epoch": 0.35, "learning_rate": 8.400000000000001e-05, "loss": 2.404, "step": 1680 }, { "epoch": 0.35, "learning_rate": 8.425e-05, "loss": 2.404, "step": 1685 }, { "epoch": 0.35, "learning_rate": 8.450000000000001e-05, "loss": 2.4, "step": 1690 }, { "epoch": 0.35, "learning_rate": 8.475000000000001e-05, "loss": 2.4051, "step": 1695 }, { "epoch": 0.35, "learning_rate": 8.5e-05, "loss": 2.4004, "step": 1700 }, { "epoch": 0.35, "learning_rate": 8.525000000000001e-05, "loss": 2.4023, "step": 1705 }, { "epoch": 0.35, "learning_rate": 8.55e-05, "loss": 2.3963, "step": 1710 }, { "epoch": 0.36, "learning_rate": 8.575000000000001e-05, "loss": 2.3951, "step": 1715 }, { "epoch": 0.36, "learning_rate": 8.599999999999999e-05, "loss": 2.3916, "step": 1720 }, { "epoch": 0.36, "learning_rate": 8.625e-05, "loss": 2.3926, "step": 1725 }, { "epoch": 0.36, "learning_rate": 8.65e-05, "loss": 2.3918, "step": 1730 }, { "epoch": 0.36, "learning_rate": 8.675e-05, "loss": 2.3845, "step": 1735 }, { "epoch": 0.36, "learning_rate": 8.7e-05, "loss": 2.3856, "step": 1740 }, { "epoch": 0.36, "learning_rate": 8.724999999999999e-05, "loss": 2.3841, "step": 1745 }, { "epoch": 0.36, "learning_rate": 8.75e-05, "loss": 2.3904, "step": 1750 }, { "epoch": 0.36, "learning_rate": 8.774999999999999e-05, "loss": 2.3796, "step": 1755 }, { "epoch": 0.36, "learning_rate": 8.8e-05, "loss": 2.3841, "step": 1760 }, { "epoch": 0.37, "learning_rate": 8.824999999999999e-05, "loss": 2.374, "step": 1765 }, { "epoch": 0.37, "learning_rate": 8.85e-05, "loss": 2.3747, "step": 1770 }, { "epoch": 0.37, "learning_rate": 8.875e-05, "loss": 2.3766, "step": 1775 }, { "epoch": 0.37, "learning_rate": 8.9e-05, "loss": 2.3751, "step": 1780 }, { "epoch": 0.37, "learning_rate": 8.925e-05, "loss": 2.3717, "step": 1785 }, { "epoch": 0.37, "learning_rate": 8.95e-05, "loss": 2.3713, "step": 1790 }, { "epoch": 0.37, "learning_rate": 8.975e-05, "loss": 2.3788, "step": 1795 }, { "epoch": 0.37, "learning_rate": 8.999999999999999e-05, "loss": 2.369, "step": 1800 }, { "epoch": 0.37, "learning_rate": 9.025e-05, "loss": 2.3608, "step": 1805 }, { "epoch": 0.37, "learning_rate": 9.05e-05, "loss": 2.3687, "step": 1810 }, { "epoch": 0.38, "learning_rate": 9.075e-05, "loss": 2.3635, "step": 1815 }, { "epoch": 0.38, "learning_rate": 9.1e-05, "loss": 2.3644, "step": 1820 }, { "epoch": 0.38, "learning_rate": 9.125e-05, "loss": 2.3672, "step": 1825 }, { "epoch": 0.38, "learning_rate": 9.15e-05, "loss": 2.3619, "step": 1830 }, { "epoch": 0.38, "learning_rate": 9.175e-05, "loss": 2.3511, "step": 1835 }, { "epoch": 0.38, "learning_rate": 9.2e-05, "loss": 2.36, "step": 1840 }, { "epoch": 0.38, "learning_rate": 9.225e-05, "loss": 2.3487, "step": 1845 }, { "epoch": 0.38, "learning_rate": 9.25e-05, "loss": 2.3478, "step": 1850 }, { "epoch": 0.38, "learning_rate": 9.275e-05, "loss": 2.3482, "step": 1855 }, { "epoch": 0.39, "learning_rate": 9.3e-05, "loss": 2.3526, "step": 1860 }, { "epoch": 0.39, "learning_rate": 9.325e-05, "loss": 2.3507, "step": 1865 }, { "epoch": 0.39, "learning_rate": 9.35e-05, "loss": 2.3478, "step": 1870 }, { "epoch": 0.39, "learning_rate": 9.375e-05, "loss": 2.3495, "step": 1875 }, { "epoch": 0.39, "learning_rate": 9.400000000000001e-05, "loss": 2.3384, "step": 1880 }, { "epoch": 0.39, "learning_rate": 9.425e-05, "loss": 2.3435, "step": 1885 }, { "epoch": 0.39, "learning_rate": 9.45e-05, "loss": 2.3371, "step": 1890 }, { "epoch": 0.39, "learning_rate": 9.475e-05, "loss": 2.3437, "step": 1895 }, { "epoch": 0.39, "learning_rate": 9.5e-05, "loss": 2.3433, "step": 1900 }, { "epoch": 0.39, "learning_rate": 9.525e-05, "loss": 2.3405, "step": 1905 }, { "epoch": 0.4, "learning_rate": 9.55e-05, "loss": 2.3366, "step": 1910 }, { "epoch": 0.4, "learning_rate": 9.575000000000001e-05, "loss": 2.3356, "step": 1915 }, { "epoch": 0.4, "learning_rate": 9.6e-05, "loss": 2.3329, "step": 1920 }, { "epoch": 0.4, "learning_rate": 9.625000000000001e-05, "loss": 2.3346, "step": 1925 }, { "epoch": 0.4, "learning_rate": 9.65e-05, "loss": 2.3349, "step": 1930 }, { "epoch": 0.4, "learning_rate": 9.675000000000001e-05, "loss": 2.3329, "step": 1935 }, { "epoch": 0.4, "learning_rate": 9.7e-05, "loss": 2.328, "step": 1940 }, { "epoch": 0.4, "learning_rate": 9.725e-05, "loss": 2.3213, "step": 1945 }, { "epoch": 0.4, "learning_rate": 9.750000000000001e-05, "loss": 2.3271, "step": 1950 }, { "epoch": 0.41, "learning_rate": 9.775e-05, "loss": 2.314, "step": 1955 }, { "epoch": 0.41, "learning_rate": 9.800000000000001e-05, "loss": 2.323, "step": 1960 }, { "epoch": 0.41, "learning_rate": 9.825e-05, "loss": 2.3149, "step": 1965 }, { "epoch": 0.41, "learning_rate": 9.850000000000001e-05, "loss": 2.3167, "step": 1970 }, { "epoch": 0.41, "learning_rate": 9.875e-05, "loss": 2.3133, "step": 1975 }, { "epoch": 0.41, "learning_rate": 9.900000000000001e-05, "loss": 2.3196, "step": 1980 }, { "epoch": 0.41, "learning_rate": 9.925000000000001e-05, "loss": 2.3215, "step": 1985 }, { "epoch": 0.41, "learning_rate": 9.95e-05, "loss": 2.3166, "step": 1990 }, { "epoch": 0.41, "learning_rate": 9.975000000000001e-05, "loss": 2.3185, "step": 1995 }, { "epoch": 0.41, "learning_rate": 0.0001, "loss": 2.3143, "step": 2000 }, { "epoch": 0.42, "learning_rate": 0.00010025000000000001, "loss": 2.3136, "step": 2005 }, { "epoch": 0.42, "learning_rate": 0.0001005, "loss": 2.3062, "step": 2010 }, { "epoch": 0.42, "learning_rate": 0.00010075000000000001, "loss": 2.3114, "step": 2015 }, { "epoch": 0.42, "learning_rate": 0.000101, "loss": 2.3066, "step": 2020 }, { "epoch": 0.42, "learning_rate": 0.00010125000000000001, "loss": 2.3133, "step": 2025 }, { "epoch": 0.42, "learning_rate": 0.00010150000000000001, "loss": 2.3045, "step": 2030 }, { "epoch": 0.42, "learning_rate": 0.00010174999999999999, "loss": 2.3029, "step": 2035 }, { "epoch": 0.42, "learning_rate": 0.000102, "loss": 2.3051, "step": 2040 }, { "epoch": 0.42, "learning_rate": 0.00010224999999999999, "loss": 2.3069, "step": 2045 }, { "epoch": 0.42, "learning_rate": 0.0001025, "loss": 2.3013, "step": 2050 }, { "epoch": 0.43, "learning_rate": 0.00010274999999999999, "loss": 2.2967, "step": 2055 }, { "epoch": 0.43, "learning_rate": 0.000103, "loss": 2.3038, "step": 2060 }, { "epoch": 0.43, "learning_rate": 0.00010325, "loss": 2.2926, "step": 2065 }, { "epoch": 0.43, "learning_rate": 0.0001035, "loss": 2.2983, "step": 2070 }, { "epoch": 0.43, "learning_rate": 0.00010375, "loss": 2.295, "step": 2075 }, { "epoch": 0.43, "learning_rate": 0.000104, "loss": 2.2899, "step": 2080 }, { "epoch": 0.43, "learning_rate": 0.00010425, "loss": 2.2886, "step": 2085 }, { "epoch": 0.43, "learning_rate": 0.00010449999999999999, "loss": 2.2921, "step": 2090 }, { "epoch": 0.43, "learning_rate": 0.00010475, "loss": 2.2799, "step": 2095 }, { "epoch": 0.44, "learning_rate": 0.000105, "loss": 2.2889, "step": 2100 }, { "epoch": 0.44, "learning_rate": 0.00010525, "loss": 2.2953, "step": 2105 }, { "epoch": 0.44, "learning_rate": 0.0001055, "loss": 2.2838, "step": 2110 }, { "epoch": 0.44, "learning_rate": 0.00010575, "loss": 2.2824, "step": 2115 }, { "epoch": 0.44, "learning_rate": 0.000106, "loss": 2.2851, "step": 2120 }, { "epoch": 0.44, "learning_rate": 0.00010625, "loss": 2.285, "step": 2125 }, { "epoch": 0.44, "learning_rate": 0.0001065, "loss": 2.2854, "step": 2130 }, { "epoch": 0.44, "learning_rate": 0.00010675, "loss": 2.2798, "step": 2135 }, { "epoch": 0.44, "learning_rate": 0.000107, "loss": 2.275, "step": 2140 }, { "epoch": 0.44, "learning_rate": 0.00010725, "loss": 2.2812, "step": 2145 }, { "epoch": 0.45, "learning_rate": 0.0001075, "loss": 2.2782, "step": 2150 }, { "epoch": 0.45, "learning_rate": 0.00010775, "loss": 2.2735, "step": 2155 }, { "epoch": 0.45, "learning_rate": 0.000108, "loss": 2.2811, "step": 2160 }, { "epoch": 0.45, "learning_rate": 0.00010825, "loss": 2.2801, "step": 2165 }, { "epoch": 0.45, "learning_rate": 0.00010850000000000001, "loss": 2.2748, "step": 2170 }, { "epoch": 0.45, "learning_rate": 0.00010875, "loss": 2.2715, "step": 2175 }, { "epoch": 0.45, "learning_rate": 0.000109, "loss": 2.274, "step": 2180 }, { "epoch": 0.45, "learning_rate": 0.00010925, "loss": 2.2764, "step": 2185 }, { "epoch": 0.45, "learning_rate": 0.0001095, "loss": 2.2721, "step": 2190 }, { "epoch": 0.45, "learning_rate": 0.00010975, "loss": 2.2701, "step": 2195 }, { "epoch": 0.46, "learning_rate": 0.00011, "loss": 2.2687, "step": 2200 }, { "epoch": 0.46, "learning_rate": 0.00011025, "loss": 2.2648, "step": 2205 }, { "epoch": 0.46, "learning_rate": 0.0001105, "loss": 2.2675, "step": 2210 }, { "epoch": 0.46, "learning_rate": 0.00011075000000000001, "loss": 2.2636, "step": 2215 }, { "epoch": 0.46, "learning_rate": 0.000111, "loss": 2.2621, "step": 2220 }, { "epoch": 0.46, "learning_rate": 0.00011125000000000001, "loss": 2.2574, "step": 2225 }, { "epoch": 0.46, "learning_rate": 0.0001115, "loss": 2.2679, "step": 2230 }, { "epoch": 0.46, "learning_rate": 0.00011175, "loss": 2.2654, "step": 2235 }, { "epoch": 0.46, "learning_rate": 0.000112, "loss": 2.2593, "step": 2240 }, { "epoch": 0.47, "learning_rate": 0.00011225, "loss": 2.2619, "step": 2245 }, { "epoch": 0.47, "learning_rate": 0.00011250000000000001, "loss": 2.2575, "step": 2250 }, { "epoch": 0.47, "learning_rate": 0.00011275, "loss": 2.2547, "step": 2255 }, { "epoch": 0.47, "learning_rate": 0.00011300000000000001, "loss": 2.2569, "step": 2260 }, { "epoch": 0.47, "learning_rate": 0.00011325, "loss": 2.2559, "step": 2265 }, { "epoch": 0.47, "learning_rate": 0.00011350000000000001, "loss": 2.2549, "step": 2270 }, { "epoch": 0.47, "learning_rate": 0.00011375, "loss": 2.2607, "step": 2275 }, { "epoch": 0.47, "learning_rate": 0.000114, "loss": 2.2573, "step": 2280 }, { "epoch": 0.47, "learning_rate": 0.00011425000000000001, "loss": 2.249, "step": 2285 }, { "epoch": 0.47, "learning_rate": 0.0001145, "loss": 2.2462, "step": 2290 }, { "epoch": 0.48, "learning_rate": 0.00011475000000000001, "loss": 2.2498, "step": 2295 }, { "epoch": 0.48, "learning_rate": 0.000115, "loss": 2.2462, "step": 2300 }, { "epoch": 0.48, "learning_rate": 0.00011525000000000001, "loss": 2.2584, "step": 2305 }, { "epoch": 0.48, "learning_rate": 0.0001155, "loss": 2.2468, "step": 2310 }, { "epoch": 0.48, "learning_rate": 0.00011575000000000001, "loss": 2.2424, "step": 2315 }, { "epoch": 0.48, "learning_rate": 0.00011600000000000001, "loss": 2.246, "step": 2320 }, { "epoch": 0.48, "learning_rate": 0.00011625, "loss": 2.2382, "step": 2325 }, { "epoch": 0.48, "learning_rate": 0.00011650000000000001, "loss": 2.2416, "step": 2330 }, { "epoch": 0.48, "learning_rate": 0.00011675, "loss": 2.2554, "step": 2335 }, { "epoch": 0.48, "learning_rate": 0.00011700000000000001, "loss": 2.242, "step": 2340 }, { "epoch": 0.49, "learning_rate": 0.00011724999999999999, "loss": 2.2413, "step": 2345 }, { "epoch": 0.49, "learning_rate": 0.0001175, "loss": 2.24, "step": 2350 }, { "epoch": 0.49, "learning_rate": 0.00011775, "loss": 2.2413, "step": 2355 }, { "epoch": 0.49, "learning_rate": 0.000118, "loss": 2.2377, "step": 2360 }, { "epoch": 0.49, "learning_rate": 0.00011825, "loss": 2.2433, "step": 2365 }, { "epoch": 0.49, "learning_rate": 0.0001185, "loss": 2.2331, "step": 2370 }, { "epoch": 0.49, "learning_rate": 0.00011875, "loss": 2.2405, "step": 2375 }, { "epoch": 0.49, "learning_rate": 0.00011899999999999999, "loss": 2.2377, "step": 2380 }, { "epoch": 0.49, "learning_rate": 0.00011925, "loss": 2.2319, "step": 2385 }, { "epoch": 0.5, "learning_rate": 0.00011949999999999999, "loss": 2.2326, "step": 2390 }, { "epoch": 0.5, "learning_rate": 0.00011975, "loss": 2.2335, "step": 2395 }, { "epoch": 0.5, "learning_rate": 0.00012, "loss": 2.2321, "step": 2400 }, { "epoch": 0.5, "learning_rate": 0.00012025, "loss": 2.2294, "step": 2405 }, { "epoch": 0.5, "learning_rate": 0.0001205, "loss": 2.2324, "step": 2410 }, { "epoch": 0.5, "learning_rate": 0.00012075, "loss": 2.2285, "step": 2415 }, { "epoch": 0.5, "learning_rate": 0.000121, "loss": 2.2251, "step": 2420 }, { "epoch": 0.5, "learning_rate": 0.00012124999999999999, "loss": 2.2256, "step": 2425 }, { "epoch": 0.5, "learning_rate": 0.0001215, "loss": 2.2196, "step": 2430 }, { "epoch": 0.5, "learning_rate": 0.00012175, "loss": 2.2294, "step": 2435 }, { "epoch": 0.51, "learning_rate": 0.000122, "loss": 2.2255, "step": 2440 }, { "epoch": 0.51, "learning_rate": 0.00012225, "loss": 2.2237, "step": 2445 }, { "epoch": 0.51, "learning_rate": 0.0001225, "loss": 2.2269, "step": 2450 }, { "epoch": 0.51, "learning_rate": 0.00012275, "loss": 2.222, "step": 2455 }, { "epoch": 0.51, "learning_rate": 0.000123, "loss": 2.2166, "step": 2460 }, { "epoch": 0.51, "learning_rate": 0.00012325000000000001, "loss": 2.2222, "step": 2465 }, { "epoch": 0.51, "learning_rate": 0.0001235, "loss": 2.2187, "step": 2470 }, { "epoch": 0.51, "learning_rate": 0.00012375, "loss": 2.2193, "step": 2475 }, { "epoch": 0.51, "learning_rate": 0.000124, "loss": 2.2211, "step": 2480 }, { "epoch": 0.51, "learning_rate": 0.00012425, "loss": 2.2226, "step": 2485 }, { "epoch": 0.52, "learning_rate": 0.0001245, "loss": 2.2127, "step": 2490 }, { "epoch": 0.52, "learning_rate": 0.00012475, "loss": 2.2177, "step": 2495 }, { "epoch": 0.52, "learning_rate": 0.000125, "loss": 2.2104, "step": 2500 }, { "epoch": 0.52, "learning_rate": 0.00012525, "loss": 2.219, "step": 2505 }, { "epoch": 0.52, "learning_rate": 0.00012550000000000001, "loss": 2.2171, "step": 2510 }, { "epoch": 0.52, "learning_rate": 0.00012575, "loss": 2.2108, "step": 2515 }, { "epoch": 0.52, "learning_rate": 0.000126, "loss": 2.211, "step": 2520 }, { "epoch": 0.52, "learning_rate": 0.00012625, "loss": 2.214, "step": 2525 }, { "epoch": 0.52, "learning_rate": 0.0001265, "loss": 2.2093, "step": 2530 }, { "epoch": 0.53, "learning_rate": 0.00012675, "loss": 2.2096, "step": 2535 }, { "epoch": 0.53, "learning_rate": 0.000127, "loss": 2.2061, "step": 2540 }, { "epoch": 0.53, "learning_rate": 0.00012725, "loss": 2.2051, "step": 2545 }, { "epoch": 0.53, "learning_rate": 0.0001275, "loss": 2.2076, "step": 2550 }, { "epoch": 0.53, "learning_rate": 0.00012775000000000002, "loss": 2.2109, "step": 2555 }, { "epoch": 0.53, "learning_rate": 0.000128, "loss": 2.2048, "step": 2560 }, { "epoch": 0.53, "learning_rate": 0.00012825, "loss": 2.2072, "step": 2565 }, { "epoch": 0.53, "learning_rate": 0.0001285, "loss": 2.2071, "step": 2570 }, { "epoch": 0.53, "learning_rate": 0.00012875, "loss": 2.202, "step": 2575 }, { "epoch": 0.53, "learning_rate": 0.00012900000000000002, "loss": 2.2043, "step": 2580 }, { "epoch": 0.54, "learning_rate": 0.00012925, "loss": 2.1954, "step": 2585 }, { "epoch": 0.54, "learning_rate": 0.0001295, "loss": 2.1945, "step": 2590 }, { "epoch": 0.54, "learning_rate": 0.00012975, "loss": 2.2013, "step": 2595 }, { "epoch": 0.54, "learning_rate": 0.00013000000000000002, "loss": 2.2011, "step": 2600 }, { "epoch": 0.54, "learning_rate": 0.00013025, "loss": 2.1983, "step": 2605 }, { "epoch": 0.54, "learning_rate": 0.0001305, "loss": 2.1995, "step": 2610 }, { "epoch": 0.54, "learning_rate": 0.00013075, "loss": 2.1969, "step": 2615 }, { "epoch": 0.54, "learning_rate": 0.000131, "loss": 2.197, "step": 2620 }, { "epoch": 0.54, "learning_rate": 0.00013125000000000002, "loss": 2.1933, "step": 2625 }, { "epoch": 0.54, "learning_rate": 0.0001315, "loss": 2.2027, "step": 2630 }, { "epoch": 0.55, "learning_rate": 0.00013175, "loss": 2.1969, "step": 2635 }, { "epoch": 0.55, "learning_rate": 0.000132, "loss": 2.1972, "step": 2640 }, { "epoch": 0.55, "learning_rate": 0.00013225000000000002, "loss": 2.1961, "step": 2645 }, { "epoch": 0.55, "learning_rate": 0.00013250000000000002, "loss": 2.1949, "step": 2650 }, { "epoch": 0.55, "learning_rate": 0.00013275, "loss": 2.1948, "step": 2655 }, { "epoch": 0.55, "learning_rate": 0.000133, "loss": 2.1888, "step": 2660 }, { "epoch": 0.55, "learning_rate": 0.00013325, "loss": 2.1949, "step": 2665 }, { "epoch": 0.55, "learning_rate": 0.00013350000000000002, "loss": 2.1984, "step": 2670 }, { "epoch": 0.55, "learning_rate": 0.00013375, "loss": 2.1874, "step": 2675 }, { "epoch": 0.56, "learning_rate": 0.000134, "loss": 2.1886, "step": 2680 }, { "epoch": 0.56, "learning_rate": 0.00013425, "loss": 2.1891, "step": 2685 }, { "epoch": 0.56, "learning_rate": 0.00013450000000000002, "loss": 2.1843, "step": 2690 }, { "epoch": 0.56, "learning_rate": 0.00013475000000000002, "loss": 2.1836, "step": 2695 }, { "epoch": 0.56, "learning_rate": 0.000135, "loss": 2.1847, "step": 2700 }, { "epoch": 0.56, "learning_rate": 0.00013525, "loss": 2.1847, "step": 2705 }, { "epoch": 0.56, "learning_rate": 0.00013550000000000001, "loss": 2.1822, "step": 2710 }, { "epoch": 0.56, "learning_rate": 0.00013575000000000002, "loss": 2.1811, "step": 2715 }, { "epoch": 0.56, "learning_rate": 0.00013600000000000003, "loss": 2.1864, "step": 2720 }, { "epoch": 0.56, "learning_rate": 0.00013625, "loss": 2.1835, "step": 2725 }, { "epoch": 0.57, "learning_rate": 0.0001365, "loss": 2.1808, "step": 2730 }, { "epoch": 0.57, "learning_rate": 0.00013675000000000002, "loss": 2.1828, "step": 2735 }, { "epoch": 0.57, "learning_rate": 0.00013700000000000002, "loss": 2.1815, "step": 2740 }, { "epoch": 0.57, "learning_rate": 0.00013725, "loss": 2.176, "step": 2745 }, { "epoch": 0.57, "learning_rate": 0.0001375, "loss": 2.1786, "step": 2750 }, { "epoch": 0.57, "learning_rate": 0.00013775000000000001, "loss": 2.1806, "step": 2755 }, { "epoch": 0.57, "learning_rate": 0.00013800000000000002, "loss": 2.1784, "step": 2760 }, { "epoch": 0.57, "learning_rate": 0.00013825000000000003, "loss": 2.1827, "step": 2765 }, { "epoch": 0.57, "learning_rate": 0.0001385, "loss": 2.1863, "step": 2770 }, { "epoch": 0.57, "learning_rate": 0.00013875, "loss": 2.1795, "step": 2775 }, { "epoch": 0.58, "learning_rate": 0.00013900000000000002, "loss": 2.1797, "step": 2780 }, { "epoch": 0.58, "learning_rate": 0.00013925000000000002, "loss": 2.1689, "step": 2785 }, { "epoch": 0.58, "learning_rate": 0.0001395, "loss": 2.1768, "step": 2790 }, { "epoch": 0.58, "learning_rate": 0.00013975, "loss": 2.1781, "step": 2795 }, { "epoch": 0.58, "learning_rate": 0.00014000000000000001, "loss": 2.1698, "step": 2800 }, { "epoch": 0.58, "learning_rate": 0.00014025000000000002, "loss": 2.1797, "step": 2805 }, { "epoch": 0.58, "learning_rate": 0.00014050000000000003, "loss": 2.1739, "step": 2810 }, { "epoch": 0.58, "learning_rate": 0.00014074999999999998, "loss": 2.1675, "step": 2815 }, { "epoch": 0.58, "learning_rate": 0.00014099999999999998, "loss": 2.1858, "step": 2820 }, { "epoch": 0.59, "learning_rate": 0.00014125, "loss": 2.182, "step": 2825 }, { "epoch": 0.59, "learning_rate": 0.0001415, "loss": 2.1713, "step": 2830 }, { "epoch": 0.59, "learning_rate": 0.00014175, "loss": 2.1751, "step": 2835 }, { "epoch": 0.59, "learning_rate": 0.00014199999999999998, "loss": 2.1719, "step": 2840 }, { "epoch": 0.59, "learning_rate": 0.00014225, "loss": 2.1684, "step": 2845 }, { "epoch": 0.59, "learning_rate": 0.0001425, "loss": 2.171, "step": 2850 }, { "epoch": 0.59, "learning_rate": 0.00014275, "loss": 2.1711, "step": 2855 }, { "epoch": 0.59, "learning_rate": 0.00014299999999999998, "loss": 2.168, "step": 2860 }, { "epoch": 0.59, "learning_rate": 0.00014324999999999999, "loss": 2.1702, "step": 2865 }, { "epoch": 0.59, "learning_rate": 0.0001435, "loss": 2.1688, "step": 2870 }, { "epoch": 0.6, "learning_rate": 0.00014375, "loss": 2.1693, "step": 2875 }, { "epoch": 0.6, "learning_rate": 0.000144, "loss": 2.1672, "step": 2880 }, { "epoch": 0.6, "learning_rate": 0.00014424999999999998, "loss": 2.1652, "step": 2885 }, { "epoch": 0.6, "learning_rate": 0.0001445, "loss": 2.1728, "step": 2890 }, { "epoch": 0.6, "learning_rate": 0.00014475, "loss": 2.1682, "step": 2895 }, { "epoch": 0.6, "learning_rate": 0.000145, "loss": 2.1641, "step": 2900 }, { "epoch": 0.6, "learning_rate": 0.00014524999999999998, "loss": 2.1661, "step": 2905 }, { "epoch": 0.6, "learning_rate": 0.00014549999999999999, "loss": 2.1621, "step": 2910 }, { "epoch": 0.6, "learning_rate": 0.00014575, "loss": 2.1655, "step": 2915 }, { "epoch": 0.6, "learning_rate": 0.000146, "loss": 2.1588, "step": 2920 }, { "epoch": 0.61, "learning_rate": 0.00014625, "loss": 2.1584, "step": 2925 }, { "epoch": 0.61, "learning_rate": 0.00014649999999999998, "loss": 2.1606, "step": 2930 }, { "epoch": 0.61, "learning_rate": 0.00014675, "loss": 2.1581, "step": 2935 }, { "epoch": 0.61, "learning_rate": 0.000147, "loss": 2.1582, "step": 2940 }, { "epoch": 0.61, "learning_rate": 0.00014725, "loss": 2.1539, "step": 2945 }, { "epoch": 0.61, "learning_rate": 0.0001475, "loss": 2.1624, "step": 2950 }, { "epoch": 0.61, "learning_rate": 0.00014774999999999999, "loss": 2.1638, "step": 2955 }, { "epoch": 0.61, "learning_rate": 0.000148, "loss": 2.1556, "step": 2960 }, { "epoch": 0.61, "learning_rate": 0.00014825, "loss": 2.1546, "step": 2965 }, { "epoch": 0.62, "learning_rate": 0.0001485, "loss": 2.1697, "step": 2970 }, { "epoch": 0.62, "learning_rate": 0.00014874999999999998, "loss": 2.1545, "step": 2975 }, { "epoch": 0.62, "learning_rate": 0.000149, "loss": 2.1514, "step": 2980 }, { "epoch": 0.62, "learning_rate": 0.00014925, "loss": 2.1522, "step": 2985 }, { "epoch": 0.62, "learning_rate": 0.0001495, "loss": 2.1555, "step": 2990 }, { "epoch": 0.62, "learning_rate": 0.00014975, "loss": 2.1501, "step": 2995 }, { "epoch": 0.62, "learning_rate": 0.00015, "loss": 2.1528, "step": 3000 }, { "epoch": 0.62, "eval_accuracy": 0.45542483660130717, "eval_loss": 2.361211061477661, "eval_runtime": 0.5257, "eval_samples_per_second": 285.324, "eval_steps_per_second": 1.902, "step": 3000 }, { "epoch": 0.62, "learning_rate": 0.00015025, "loss": 2.1596, "step": 3005 }, { "epoch": 0.62, "learning_rate": 0.0001505, "loss": 2.1552, "step": 3010 }, { "epoch": 0.62, "learning_rate": 0.00015075, "loss": 2.1529, "step": 3015 }, { "epoch": 0.63, "learning_rate": 0.000151, "loss": 2.1502, "step": 3020 }, { "epoch": 0.63, "learning_rate": 0.00015125, "loss": 2.1577, "step": 3025 }, { "epoch": 0.63, "learning_rate": 0.0001515, "loss": 2.1507, "step": 3030 }, { "epoch": 0.63, "learning_rate": 0.00015175, "loss": 2.1495, "step": 3035 }, { "epoch": 0.63, "learning_rate": 0.000152, "loss": 2.1466, "step": 3040 }, { "epoch": 0.63, "learning_rate": 0.00015225, "loss": 2.1444, "step": 3045 }, { "epoch": 0.63, "learning_rate": 0.0001525, "loss": 2.1594, "step": 3050 }, { "epoch": 0.63, "learning_rate": 0.00015275, "loss": 2.1478, "step": 3055 }, { "epoch": 0.63, "learning_rate": 0.000153, "loss": 2.1482, "step": 3060 }, { "epoch": 0.63, "learning_rate": 0.00015325, "loss": 2.1477, "step": 3065 }, { "epoch": 0.64, "learning_rate": 0.0001535, "loss": 2.1533, "step": 3070 }, { "epoch": 0.64, "learning_rate": 0.00015375, "loss": 2.1491, "step": 3075 }, { "epoch": 0.64, "learning_rate": 0.000154, "loss": 2.1494, "step": 3080 }, { "epoch": 0.64, "learning_rate": 0.00015425, "loss": 2.1404, "step": 3085 }, { "epoch": 0.64, "learning_rate": 0.00015450000000000001, "loss": 2.1525, "step": 3090 }, { "epoch": 0.64, "learning_rate": 0.00015475, "loss": 2.1431, "step": 3095 }, { "epoch": 0.64, "learning_rate": 0.000155, "loss": 2.1465, "step": 3100 }, { "epoch": 0.64, "learning_rate": 0.00015525, "loss": 2.1412, "step": 3105 }, { "epoch": 0.64, "learning_rate": 0.0001555, "loss": 2.1393, "step": 3110 }, { "epoch": 0.65, "learning_rate": 0.00015575, "loss": 2.1457, "step": 3115 }, { "epoch": 0.65, "learning_rate": 0.000156, "loss": 2.1425, "step": 3120 }, { "epoch": 0.65, "learning_rate": 0.00015625, "loss": 2.1334, "step": 3125 }, { "epoch": 0.65, "learning_rate": 0.0001565, "loss": 2.1394, "step": 3130 }, { "epoch": 0.65, "learning_rate": 0.00015675000000000002, "loss": 2.1341, "step": 3135 }, { "epoch": 0.65, "learning_rate": 0.000157, "loss": 2.1327, "step": 3140 }, { "epoch": 0.65, "learning_rate": 0.00015725, "loss": 2.1477, "step": 3145 }, { "epoch": 0.65, "learning_rate": 0.0001575, "loss": 2.1426, "step": 3150 }, { "epoch": 0.65, "learning_rate": 0.00015775, "loss": 2.1421, "step": 3155 }, { "epoch": 0.65, "learning_rate": 0.000158, "loss": 2.1319, "step": 3160 }, { "epoch": 0.66, "learning_rate": 0.00015825, "loss": 2.1392, "step": 3165 }, { "epoch": 0.66, "learning_rate": 0.0001585, "loss": 2.1417, "step": 3170 }, { "epoch": 0.66, "learning_rate": 0.00015875, "loss": 2.1331, "step": 3175 }, { "epoch": 0.66, "learning_rate": 0.00015900000000000002, "loss": 2.1359, "step": 3180 }, { "epoch": 0.66, "learning_rate": 0.00015925, "loss": 2.1329, "step": 3185 }, { "epoch": 0.66, "learning_rate": 0.0001595, "loss": 2.1371, "step": 3190 }, { "epoch": 0.66, "learning_rate": 0.00015975, "loss": 2.135, "step": 3195 }, { "epoch": 0.66, "learning_rate": 0.00016, "loss": 2.1345, "step": 3200 }, { "epoch": 0.66, "learning_rate": 0.00016025000000000002, "loss": 2.1353, "step": 3205 }, { "epoch": 0.67, "learning_rate": 0.0001605, "loss": 2.1393, "step": 3210 }, { "epoch": 0.67, "learning_rate": 0.00016075, "loss": 2.1364, "step": 3215 }, { "epoch": 0.67, "learning_rate": 0.000161, "loss": 2.124, "step": 3220 }, { "epoch": 0.67, "learning_rate": 0.00016125000000000002, "loss": 2.127, "step": 3225 }, { "epoch": 0.67, "learning_rate": 0.0001615, "loss": 2.135, "step": 3230 }, { "epoch": 0.67, "learning_rate": 0.00016175, "loss": 2.1307, "step": 3235 }, { "epoch": 0.67, "learning_rate": 0.000162, "loss": 2.1286, "step": 3240 }, { "epoch": 0.67, "learning_rate": 0.00016225000000000001, "loss": 2.1314, "step": 3245 }, { "epoch": 0.67, "learning_rate": 0.00016250000000000002, "loss": 2.1247, "step": 3250 }, { "epoch": 0.67, "learning_rate": 0.00016275, "loss": 2.1334, "step": 3255 }, { "epoch": 0.68, "learning_rate": 0.000163, "loss": 2.127, "step": 3260 }, { "epoch": 0.68, "learning_rate": 0.00016325, "loss": 2.1301, "step": 3265 }, { "epoch": 0.68, "learning_rate": 0.00016350000000000002, "loss": 2.1294, "step": 3270 }, { "epoch": 0.68, "learning_rate": 0.00016375000000000002, "loss": 2.1226, "step": 3275 }, { "epoch": 0.68, "learning_rate": 0.000164, "loss": 2.1233, "step": 3280 }, { "epoch": 0.68, "learning_rate": 0.00016425, "loss": 2.1266, "step": 3285 }, { "epoch": 0.68, "learning_rate": 0.00016450000000000001, "loss": 2.1299, "step": 3290 }, { "epoch": 0.68, "learning_rate": 0.00016475000000000002, "loss": 2.1307, "step": 3295 }, { "epoch": 0.68, "learning_rate": 0.000165, "loss": 2.1279, "step": 3300 }, { "epoch": 0.68, "learning_rate": 0.00016525, "loss": 2.134, "step": 3305 }, { "epoch": 0.69, "learning_rate": 0.0001655, "loss": 2.1199, "step": 3310 }, { "epoch": 0.69, "learning_rate": 0.00016575000000000002, "loss": 2.1228, "step": 3315 }, { "epoch": 0.69, "learning_rate": 0.00016600000000000002, "loss": 2.1271, "step": 3320 }, { "epoch": 0.69, "learning_rate": 0.00016625, "loss": 2.1268, "step": 3325 }, { "epoch": 0.69, "learning_rate": 0.0001665, "loss": 2.1232, "step": 3330 }, { "epoch": 0.69, "learning_rate": 0.00016675000000000001, "loss": 2.1186, "step": 3335 }, { "epoch": 0.69, "learning_rate": 0.00016700000000000002, "loss": 2.1218, "step": 3340 }, { "epoch": 0.69, "learning_rate": 0.00016725000000000003, "loss": 2.1238, "step": 3345 }, { "epoch": 0.69, "learning_rate": 0.0001675, "loss": 2.1208, "step": 3350 }, { "epoch": 0.7, "learning_rate": 0.00016775, "loss": 2.1169, "step": 3355 }, { "epoch": 0.7, "learning_rate": 0.00016800000000000002, "loss": 2.1185, "step": 3360 }, { "epoch": 0.7, "learning_rate": 0.00016825000000000002, "loss": 2.1187, "step": 3365 }, { "epoch": 0.7, "learning_rate": 0.0001685, "loss": 2.1299, "step": 3370 }, { "epoch": 0.7, "learning_rate": 0.00016875, "loss": 2.1144, "step": 3375 }, { "epoch": 0.7, "learning_rate": 0.00016900000000000002, "loss": 2.1185, "step": 3380 }, { "epoch": 0.7, "learning_rate": 0.00016925000000000002, "loss": 2.12, "step": 3385 }, { "epoch": 0.7, "learning_rate": 0.00016950000000000003, "loss": 2.114, "step": 3390 }, { "epoch": 0.7, "learning_rate": 0.00016975, "loss": 2.1203, "step": 3395 }, { "epoch": 0.7, "learning_rate": 0.00017, "loss": 2.1173, "step": 3400 }, { "epoch": 0.71, "learning_rate": 0.00017025000000000002, "loss": 2.118, "step": 3405 }, { "epoch": 0.71, "learning_rate": 0.00017050000000000002, "loss": 2.1159, "step": 3410 }, { "epoch": 0.71, "learning_rate": 0.00017075, "loss": 2.115, "step": 3415 }, { "epoch": 0.71, "learning_rate": 0.000171, "loss": 2.117, "step": 3420 }, { "epoch": 0.71, "learning_rate": 0.00017125000000000002, "loss": 2.1144, "step": 3425 }, { "epoch": 0.71, "learning_rate": 0.00017150000000000002, "loss": 2.1152, "step": 3430 }, { "epoch": 0.71, "learning_rate": 0.00017175000000000003, "loss": 2.1137, "step": 3435 }, { "epoch": 0.71, "learning_rate": 0.00017199999999999998, "loss": 2.1135, "step": 3440 }, { "epoch": 0.71, "learning_rate": 0.00017224999999999999, "loss": 2.117, "step": 3445 }, { "epoch": 0.71, "learning_rate": 0.0001725, "loss": 2.1228, "step": 3450 }, { "epoch": 0.72, "learning_rate": 0.00017275, "loss": 2.1066, "step": 3455 }, { "epoch": 0.72, "learning_rate": 0.000173, "loss": 2.1113, "step": 3460 }, { "epoch": 0.72, "learning_rate": 0.00017324999999999998, "loss": 2.1112, "step": 3465 }, { "epoch": 0.72, "learning_rate": 0.0001735, "loss": 2.1073, "step": 3470 }, { "epoch": 0.72, "learning_rate": 0.00017375, "loss": 2.1067, "step": 3475 }, { "epoch": 0.72, "learning_rate": 0.000174, "loss": 2.1176, "step": 3480 }, { "epoch": 0.72, "learning_rate": 0.00017424999999999998, "loss": 2.1155, "step": 3485 }, { "epoch": 0.72, "learning_rate": 0.00017449999999999999, "loss": 2.1101, "step": 3490 }, { "epoch": 0.72, "learning_rate": 0.00017475, "loss": 2.1096, "step": 3495 }, { "epoch": 0.73, "learning_rate": 0.000175, "loss": 2.1066, "step": 3500 }, { "epoch": 0.73, "learning_rate": 0.00017525, "loss": 2.107, "step": 3505 }, { "epoch": 0.73, "learning_rate": 0.00017549999999999998, "loss": 2.112, "step": 3510 }, { "epoch": 0.73, "learning_rate": 0.00017575, "loss": 2.1102, "step": 3515 }, { "epoch": 0.73, "learning_rate": 0.000176, "loss": 2.1085, "step": 3520 }, { "epoch": 0.73, "learning_rate": 0.00017625, "loss": 2.1066, "step": 3525 }, { "epoch": 0.73, "learning_rate": 0.00017649999999999998, "loss": 2.1115, "step": 3530 }, { "epoch": 0.73, "learning_rate": 0.00017675, "loss": 2.1116, "step": 3535 }, { "epoch": 0.73, "learning_rate": 0.000177, "loss": 2.1045, "step": 3540 }, { "epoch": 0.73, "learning_rate": 0.00017725, "loss": 2.1048, "step": 3545 }, { "epoch": 0.74, "learning_rate": 0.0001775, "loss": 2.1035, "step": 3550 }, { "epoch": 0.74, "learning_rate": 0.00017774999999999998, "loss": 2.1065, "step": 3555 }, { "epoch": 0.74, "learning_rate": 0.000178, "loss": 2.1055, "step": 3560 }, { "epoch": 0.74, "learning_rate": 0.00017825, "loss": 2.0986, "step": 3565 }, { "epoch": 0.74, "learning_rate": 0.0001785, "loss": 2.0967, "step": 3570 }, { "epoch": 0.74, "learning_rate": 0.00017875, "loss": 2.0987, "step": 3575 }, { "epoch": 0.74, "learning_rate": 0.000179, "loss": 2.0982, "step": 3580 }, { "epoch": 0.74, "learning_rate": 0.00017925, "loss": 2.1028, "step": 3585 }, { "epoch": 0.74, "learning_rate": 0.0001795, "loss": 2.0998, "step": 3590 }, { "epoch": 0.74, "learning_rate": 0.00017975, "loss": 2.0984, "step": 3595 }, { "epoch": 0.75, "learning_rate": 0.00017999999999999998, "loss": 2.1113, "step": 3600 }, { "epoch": 0.75, "learning_rate": 0.00018025, "loss": 2.1067, "step": 3605 }, { "epoch": 0.75, "learning_rate": 0.0001805, "loss": 2.1061, "step": 3610 }, { "epoch": 0.75, "learning_rate": 0.00018075, "loss": 2.0972, "step": 3615 }, { "epoch": 0.75, "learning_rate": 0.000181, "loss": 2.1025, "step": 3620 }, { "epoch": 0.75, "learning_rate": 0.00018125, "loss": 2.1027, "step": 3625 }, { "epoch": 0.75, "learning_rate": 0.0001815, "loss": 2.1014, "step": 3630 }, { "epoch": 0.75, "learning_rate": 0.00018175, "loss": 2.097, "step": 3635 }, { "epoch": 0.75, "learning_rate": 0.000182, "loss": 2.0931, "step": 3640 }, { "epoch": 0.76, "learning_rate": 0.00018225, "loss": 2.0937, "step": 3645 }, { "epoch": 0.76, "learning_rate": 0.0001825, "loss": 2.097, "step": 3650 }, { "epoch": 0.76, "learning_rate": 0.00018275, "loss": 2.1032, "step": 3655 }, { "epoch": 0.76, "learning_rate": 0.000183, "loss": 2.0994, "step": 3660 }, { "epoch": 0.76, "learning_rate": 0.00018325, "loss": 2.0896, "step": 3665 }, { "epoch": 0.76, "learning_rate": 0.0001835, "loss": 2.0973, "step": 3670 }, { "epoch": 0.76, "learning_rate": 0.00018375, "loss": 2.0958, "step": 3675 }, { "epoch": 0.76, "learning_rate": 0.000184, "loss": 2.0939, "step": 3680 }, { "epoch": 0.76, "learning_rate": 0.00018425, "loss": 2.094, "step": 3685 }, { "epoch": 0.76, "learning_rate": 0.0001845, "loss": 2.0935, "step": 3690 }, { "epoch": 0.77, "learning_rate": 0.00018475, "loss": 2.0861, "step": 3695 }, { "epoch": 0.77, "learning_rate": 0.000185, "loss": 2.093, "step": 3700 }, { "epoch": 0.77, "learning_rate": 0.00018525, "loss": 2.0901, "step": 3705 }, { "epoch": 0.77, "learning_rate": 0.0001855, "loss": 2.089, "step": 3710 }, { "epoch": 0.77, "learning_rate": 0.00018575000000000002, "loss": 2.0935, "step": 3715 }, { "epoch": 0.77, "learning_rate": 0.000186, "loss": 2.0928, "step": 3720 }, { "epoch": 0.77, "learning_rate": 0.00018625, "loss": 2.0822, "step": 3725 }, { "epoch": 0.77, "learning_rate": 0.0001865, "loss": 2.086, "step": 3730 }, { "epoch": 0.77, "learning_rate": 0.00018675, "loss": 2.0925, "step": 3735 }, { "epoch": 0.77, "learning_rate": 0.000187, "loss": 2.0921, "step": 3740 }, { "epoch": 0.78, "learning_rate": 0.00018725, "loss": 2.0902, "step": 3745 }, { "epoch": 0.78, "learning_rate": 0.0001875, "loss": 2.0896, "step": 3750 }, { "epoch": 0.78, "learning_rate": 0.00018775, "loss": 2.0841, "step": 3755 }, { "epoch": 0.78, "learning_rate": 0.00018800000000000002, "loss": 2.0866, "step": 3760 }, { "epoch": 0.78, "learning_rate": 0.00018825, "loss": 2.0981, "step": 3765 }, { "epoch": 0.78, "learning_rate": 0.0001885, "loss": 2.0925, "step": 3770 }, { "epoch": 0.78, "learning_rate": 0.00018875, "loss": 2.083, "step": 3775 }, { "epoch": 0.78, "learning_rate": 0.000189, "loss": 2.0887, "step": 3780 }, { "epoch": 0.78, "learning_rate": 0.00018925, "loss": 2.088, "step": 3785 }, { "epoch": 0.79, "learning_rate": 0.0001895, "loss": 2.0897, "step": 3790 }, { "epoch": 0.79, "learning_rate": 0.00018975, "loss": 2.0861, "step": 3795 }, { "epoch": 0.79, "learning_rate": 0.00019, "loss": 2.0867, "step": 3800 }, { "epoch": 0.79, "learning_rate": 0.00019025000000000002, "loss": 2.0824, "step": 3805 }, { "epoch": 0.79, "learning_rate": 0.0001905, "loss": 2.0893, "step": 3810 }, { "epoch": 0.79, "learning_rate": 0.00019075, "loss": 2.0915, "step": 3815 }, { "epoch": 0.79, "learning_rate": 0.000191, "loss": 2.0866, "step": 3820 }, { "epoch": 0.79, "learning_rate": 0.00019125000000000001, "loss": 2.0898, "step": 3825 }, { "epoch": 0.79, "learning_rate": 0.00019150000000000002, "loss": 2.0843, "step": 3830 }, { "epoch": 0.79, "learning_rate": 0.00019175, "loss": 2.0907, "step": 3835 }, { "epoch": 0.8, "learning_rate": 0.000192, "loss": 2.0883, "step": 3840 }, { "epoch": 0.8, "learning_rate": 0.00019225, "loss": 2.08, "step": 3845 }, { "epoch": 0.8, "learning_rate": 0.00019250000000000002, "loss": 2.0821, "step": 3850 }, { "epoch": 0.8, "learning_rate": 0.00019275, "loss": 2.0786, "step": 3855 }, { "epoch": 0.8, "learning_rate": 0.000193, "loss": 2.0858, "step": 3860 }, { "epoch": 0.8, "learning_rate": 0.00019325, "loss": 2.0803, "step": 3865 }, { "epoch": 0.8, "learning_rate": 0.00019350000000000001, "loss": 2.0808, "step": 3870 }, { "epoch": 0.8, "learning_rate": 0.00019375000000000002, "loss": 2.0812, "step": 3875 }, { "epoch": 0.8, "learning_rate": 0.000194, "loss": 2.0845, "step": 3880 }, { "epoch": 0.8, "learning_rate": 0.00019425, "loss": 2.0771, "step": 3885 }, { "epoch": 0.81, "learning_rate": 0.0001945, "loss": 2.0774, "step": 3890 }, { "epoch": 0.81, "learning_rate": 0.00019475000000000002, "loss": 2.0858, "step": 3895 }, { "epoch": 0.81, "learning_rate": 0.00019500000000000002, "loss": 2.0806, "step": 3900 }, { "epoch": 0.81, "learning_rate": 0.00019525, "loss": 2.0742, "step": 3905 }, { "epoch": 0.81, "learning_rate": 0.0001955, "loss": 2.0888, "step": 3910 }, { "epoch": 0.81, "learning_rate": 0.00019575000000000001, "loss": 2.0841, "step": 3915 }, { "epoch": 0.81, "learning_rate": 0.00019600000000000002, "loss": 2.0823, "step": 3920 }, { "epoch": 0.81, "learning_rate": 0.00019625, "loss": 2.0805, "step": 3925 }, { "epoch": 0.81, "learning_rate": 0.0001965, "loss": 2.0799, "step": 3930 }, { "epoch": 0.82, "learning_rate": 0.00019675, "loss": 2.0746, "step": 3935 }, { "epoch": 0.82, "learning_rate": 0.00019700000000000002, "loss": 2.0727, "step": 3940 }, { "epoch": 0.82, "learning_rate": 0.00019725000000000002, "loss": 2.081, "step": 3945 }, { "epoch": 0.82, "learning_rate": 0.0001975, "loss": 2.0717, "step": 3950 }, { "epoch": 0.82, "learning_rate": 0.00019775, "loss": 2.079, "step": 3955 }, { "epoch": 0.82, "learning_rate": 0.00019800000000000002, "loss": 2.0749, "step": 3960 }, { "epoch": 0.82, "learning_rate": 0.00019825000000000002, "loss": 2.0799, "step": 3965 }, { "epoch": 0.82, "learning_rate": 0.00019850000000000003, "loss": 2.0742, "step": 3970 }, { "epoch": 0.82, "learning_rate": 0.00019875, "loss": 2.0756, "step": 3975 }, { "epoch": 0.82, "learning_rate": 0.000199, "loss": 2.0782, "step": 3980 }, { "epoch": 0.83, "learning_rate": 0.00019925000000000002, "loss": 2.073, "step": 3985 }, { "epoch": 0.83, "learning_rate": 0.00019950000000000002, "loss": 2.0715, "step": 3990 }, { "epoch": 0.83, "learning_rate": 0.00019975, "loss": 2.0823, "step": 3995 }, { "epoch": 0.83, "learning_rate": 0.0002, "loss": 2.0694, "step": 4000 }, { "epoch": 0.83, "learning_rate": 0.00020025000000000002, "loss": 2.0779, "step": 4005 }, { "epoch": 0.83, "learning_rate": 0.00020050000000000002, "loss": 2.0691, "step": 4010 }, { "epoch": 0.83, "learning_rate": 0.00020075000000000003, "loss": 2.072, "step": 4015 }, { "epoch": 0.83, "learning_rate": 0.000201, "loss": 2.07, "step": 4020 }, { "epoch": 0.83, "learning_rate": 0.00020125, "loss": 2.0782, "step": 4025 }, { "epoch": 0.83, "learning_rate": 0.00020150000000000002, "loss": 2.0718, "step": 4030 }, { "epoch": 0.84, "learning_rate": 0.00020175000000000003, "loss": 2.0671, "step": 4035 }, { "epoch": 0.84, "learning_rate": 0.000202, "loss": 2.0701, "step": 4040 }, { "epoch": 0.84, "learning_rate": 0.00020225, "loss": 2.073, "step": 4045 }, { "epoch": 0.84, "learning_rate": 0.00020250000000000002, "loss": 2.078, "step": 4050 }, { "epoch": 0.84, "learning_rate": 0.00020275000000000002, "loss": 2.071, "step": 4055 }, { "epoch": 0.84, "learning_rate": 0.00020300000000000003, "loss": 2.0692, "step": 4060 }, { "epoch": 0.84, "learning_rate": 0.00020324999999999998, "loss": 2.0712, "step": 4065 }, { "epoch": 0.84, "learning_rate": 0.00020349999999999999, "loss": 2.0713, "step": 4070 }, { "epoch": 0.84, "learning_rate": 0.00020375, "loss": 2.0657, "step": 4075 }, { "epoch": 0.85, "learning_rate": 0.000204, "loss": 2.062, "step": 4080 }, { "epoch": 0.85, "learning_rate": 0.00020425, "loss": 2.0608, "step": 4085 }, { "epoch": 0.85, "learning_rate": 0.00020449999999999998, "loss": 2.0704, "step": 4090 }, { "epoch": 0.85, "learning_rate": 0.00020475, "loss": 2.0689, "step": 4095 }, { "epoch": 0.85, "learning_rate": 0.000205, "loss": 2.0658, "step": 4100 }, { "epoch": 0.85, "learning_rate": 0.00020525, "loss": 2.0704, "step": 4105 }, { "epoch": 0.85, "learning_rate": 0.00020549999999999998, "loss": 2.0731, "step": 4110 }, { "epoch": 0.85, "learning_rate": 0.00020575, "loss": 2.0702, "step": 4115 }, { "epoch": 0.85, "learning_rate": 0.000206, "loss": 2.063, "step": 4120 }, { "epoch": 0.85, "learning_rate": 0.00020625, "loss": 2.057, "step": 4125 }, { "epoch": 0.86, "learning_rate": 0.0002065, "loss": 2.0629, "step": 4130 }, { "epoch": 0.86, "learning_rate": 0.00020674999999999998, "loss": 2.0676, "step": 4135 }, { "epoch": 0.86, "learning_rate": 0.000207, "loss": 2.0621, "step": 4140 }, { "epoch": 0.86, "learning_rate": 0.00020725, "loss": 2.0613, "step": 4145 }, { "epoch": 0.86, "learning_rate": 0.0002075, "loss": 2.0578, "step": 4150 }, { "epoch": 0.86, "learning_rate": 0.00020774999999999998, "loss": 2.0667, "step": 4155 }, { "epoch": 0.86, "learning_rate": 0.000208, "loss": 2.0603, "step": 4160 }, { "epoch": 0.86, "learning_rate": 0.00020825, "loss": 2.0599, "step": 4165 }, { "epoch": 0.86, "learning_rate": 0.0002085, "loss": 2.0657, "step": 4170 }, { "epoch": 0.86, "learning_rate": 0.00020875, "loss": 2.0645, "step": 4175 }, { "epoch": 0.87, "learning_rate": 0.00020899999999999998, "loss": 2.0654, "step": 4180 }, { "epoch": 0.87, "learning_rate": 0.00020925, "loss": 2.0593, "step": 4185 }, { "epoch": 0.87, "learning_rate": 0.0002095, "loss": 2.0651, "step": 4190 }, { "epoch": 0.87, "learning_rate": 0.00020975, "loss": 2.0684, "step": 4195 }, { "epoch": 0.87, "learning_rate": 0.00021, "loss": 2.0638, "step": 4200 }, { "epoch": 0.87, "learning_rate": 0.00021025, "loss": 2.0601, "step": 4205 }, { "epoch": 0.87, "learning_rate": 0.0002105, "loss": 2.0565, "step": 4210 }, { "epoch": 0.87, "learning_rate": 0.00021075, "loss": 2.0599, "step": 4215 }, { "epoch": 0.87, "learning_rate": 0.000211, "loss": 2.0609, "step": 4220 }, { "epoch": 0.88, "learning_rate": 0.00021124999999999998, "loss": 2.0564, "step": 4225 }, { "epoch": 0.88, "learning_rate": 0.0002115, "loss": 2.0593, "step": 4230 }, { "epoch": 0.88, "learning_rate": 0.00021175, "loss": 2.0516, "step": 4235 }, { "epoch": 0.88, "learning_rate": 0.000212, "loss": 2.0544, "step": 4240 }, { "epoch": 0.88, "learning_rate": 0.00021225, "loss": 2.0556, "step": 4245 }, { "epoch": 0.88, "learning_rate": 0.0002125, "loss": 2.0563, "step": 4250 }, { "epoch": 0.88, "learning_rate": 0.00021275, "loss": 2.0657, "step": 4255 }, { "epoch": 0.88, "learning_rate": 0.000213, "loss": 2.0635, "step": 4260 }, { "epoch": 0.88, "learning_rate": 0.00021325, "loss": 2.0513, "step": 4265 }, { "epoch": 0.88, "learning_rate": 0.0002135, "loss": 2.0525, "step": 4270 }, { "epoch": 0.89, "learning_rate": 0.00021375, "loss": 2.0532, "step": 4275 }, { "epoch": 0.89, "learning_rate": 0.000214, "loss": 2.0642, "step": 4280 }, { "epoch": 0.89, "learning_rate": 0.00021425, "loss": 2.0529, "step": 4285 }, { "epoch": 0.89, "learning_rate": 0.0002145, "loss": 2.0583, "step": 4290 }, { "epoch": 0.89, "learning_rate": 0.00021475, "loss": 2.0549, "step": 4295 }, { "epoch": 0.89, "learning_rate": 0.000215, "loss": 2.0598, "step": 4300 }, { "epoch": 0.89, "learning_rate": 0.00021525, "loss": 2.058, "step": 4305 }, { "epoch": 0.89, "learning_rate": 0.0002155, "loss": 2.058, "step": 4310 }, { "epoch": 0.89, "learning_rate": 0.00021575, "loss": 2.0528, "step": 4315 }, { "epoch": 0.89, "learning_rate": 0.000216, "loss": 2.0601, "step": 4320 }, { "epoch": 0.9, "learning_rate": 0.00021625, "loss": 2.0573, "step": 4325 }, { "epoch": 0.9, "learning_rate": 0.0002165, "loss": 2.0601, "step": 4330 }, { "epoch": 0.9, "learning_rate": 0.00021675, "loss": 2.0539, "step": 4335 }, { "epoch": 0.9, "learning_rate": 0.00021700000000000002, "loss": 2.0481, "step": 4340 }, { "epoch": 0.9, "learning_rate": 0.00021725, "loss": 2.0513, "step": 4345 }, { "epoch": 0.9, "learning_rate": 0.0002175, "loss": 2.0511, "step": 4350 }, { "epoch": 0.9, "learning_rate": 0.00021775, "loss": 2.0581, "step": 4355 }, { "epoch": 0.9, "learning_rate": 0.000218, "loss": 2.0541, "step": 4360 }, { "epoch": 0.9, "learning_rate": 0.00021825, "loss": 2.0523, "step": 4365 }, { "epoch": 0.91, "learning_rate": 0.0002185, "loss": 2.0477, "step": 4370 }, { "epoch": 0.91, "learning_rate": 0.00021875, "loss": 2.0486, "step": 4375 }, { "epoch": 0.91, "learning_rate": 0.000219, "loss": 2.0569, "step": 4380 }, { "epoch": 0.91, "learning_rate": 0.00021925000000000002, "loss": 2.05, "step": 4385 }, { "epoch": 0.91, "learning_rate": 0.0002195, "loss": 2.0555, "step": 4390 }, { "epoch": 0.91, "learning_rate": 0.00021975, "loss": 2.0491, "step": 4395 }, { "epoch": 0.91, "learning_rate": 0.00022, "loss": 2.0497, "step": 4400 }, { "epoch": 0.91, "learning_rate": 0.00022025000000000001, "loss": 2.0527, "step": 4405 }, { "epoch": 0.91, "learning_rate": 0.0002205, "loss": 2.0483, "step": 4410 }, { "epoch": 0.91, "learning_rate": 0.00022075, "loss": 2.0444, "step": 4415 }, { "epoch": 0.92, "learning_rate": 0.000221, "loss": 2.0445, "step": 4420 }, { "epoch": 0.92, "learning_rate": 0.00022125, "loss": 2.0419, "step": 4425 }, { "epoch": 0.92, "learning_rate": 0.00022150000000000002, "loss": 2.0679, "step": 4430 }, { "epoch": 0.92, "learning_rate": 0.00022175, "loss": 2.0578, "step": 4435 }, { "epoch": 0.92, "learning_rate": 0.000222, "loss": 2.0526, "step": 4440 }, { "epoch": 0.92, "learning_rate": 0.00022225, "loss": 2.0502, "step": 4445 }, { "epoch": 0.92, "learning_rate": 0.00022250000000000001, "loss": 2.0472, "step": 4450 }, { "epoch": 0.92, "learning_rate": 0.00022275000000000002, "loss": 2.0477, "step": 4455 }, { "epoch": 0.92, "learning_rate": 0.000223, "loss": 2.0448, "step": 4460 }, { "epoch": 0.93, "learning_rate": 0.00022325, "loss": 2.0443, "step": 4465 }, { "epoch": 0.93, "learning_rate": 0.0002235, "loss": 2.0531, "step": 4470 }, { "epoch": 0.93, "learning_rate": 0.00022375000000000002, "loss": 2.0443, "step": 4475 }, { "epoch": 0.93, "learning_rate": 0.000224, "loss": 2.0489, "step": 4480 }, { "epoch": 0.93, "learning_rate": 0.00022425, "loss": 2.0508, "step": 4485 }, { "epoch": 0.93, "learning_rate": 0.0002245, "loss": 2.0541, "step": 4490 }, { "epoch": 0.93, "learning_rate": 0.00022475000000000001, "loss": 2.0502, "step": 4495 }, { "epoch": 0.93, "learning_rate": 0.00022500000000000002, "loss": 2.0429, "step": 4500 }, { "epoch": 0.93, "learning_rate": 0.00022525, "loss": 2.042, "step": 4505 }, { "epoch": 0.93, "learning_rate": 0.0002255, "loss": 2.0384, "step": 4510 }, { "epoch": 0.94, "learning_rate": 0.00022575, "loss": 2.0534, "step": 4515 }, { "epoch": 0.94, "learning_rate": 0.00022600000000000002, "loss": 2.0522, "step": 4520 }, { "epoch": 0.94, "learning_rate": 0.00022625000000000002, "loss": 2.0477, "step": 4525 }, { "epoch": 0.94, "learning_rate": 0.0002265, "loss": 2.0493, "step": 4530 }, { "epoch": 0.94, "learning_rate": 0.00022675, "loss": 2.0396, "step": 4535 }, { "epoch": 0.94, "learning_rate": 0.00022700000000000002, "loss": 2.0385, "step": 4540 }, { "epoch": 0.94, "learning_rate": 0.00022725000000000002, "loss": 2.039, "step": 4545 }, { "epoch": 0.94, "learning_rate": 0.0002275, "loss": 2.0415, "step": 4550 }, { "epoch": 0.94, "learning_rate": 0.00022775, "loss": 2.04, "step": 4555 }, { "epoch": 0.94, "learning_rate": 0.000228, "loss": 2.0422, "step": 4560 }, { "epoch": 0.95, "learning_rate": 0.00022825000000000002, "loss": 2.0422, "step": 4565 }, { "epoch": 0.95, "learning_rate": 0.00022850000000000002, "loss": 2.0369, "step": 4570 }, { "epoch": 0.95, "learning_rate": 0.00022875, "loss": 2.0405, "step": 4575 }, { "epoch": 0.95, "learning_rate": 0.000229, "loss": 2.0457, "step": 4580 }, { "epoch": 0.95, "learning_rate": 0.00022925000000000002, "loss": 2.0405, "step": 4585 }, { "epoch": 0.95, "learning_rate": 0.00022950000000000002, "loss": 2.0458, "step": 4590 }, { "epoch": 0.95, "learning_rate": 0.00022975000000000003, "loss": 2.0453, "step": 4595 }, { "epoch": 0.95, "learning_rate": 0.00023, "loss": 2.0383, "step": 4600 }, { "epoch": 0.95, "learning_rate": 0.00023025, "loss": 2.0325, "step": 4605 }, { "epoch": 0.96, "learning_rate": 0.00023050000000000002, "loss": 2.0425, "step": 4610 }, { "epoch": 0.96, "learning_rate": 0.00023075000000000003, "loss": 2.0355, "step": 4615 }, { "epoch": 0.96, "learning_rate": 0.000231, "loss": 2.0395, "step": 4620 }, { "epoch": 0.96, "learning_rate": 0.00023125, "loss": 2.0463, "step": 4625 }, { "epoch": 0.96, "learning_rate": 0.00023150000000000002, "loss": 2.0433, "step": 4630 }, { "epoch": 0.96, "learning_rate": 0.00023175000000000002, "loss": 2.0411, "step": 4635 }, { "epoch": 0.96, "learning_rate": 0.00023200000000000003, "loss": 2.0385, "step": 4640 }, { "epoch": 0.96, "learning_rate": 0.00023225, "loss": 2.04, "step": 4645 }, { "epoch": 0.96, "learning_rate": 0.0002325, "loss": 2.0409, "step": 4650 }, { "epoch": 0.96, "learning_rate": 0.00023275000000000002, "loss": 2.0325, "step": 4655 }, { "epoch": 0.97, "learning_rate": 0.00023300000000000003, "loss": 2.0462, "step": 4660 }, { "epoch": 0.97, "learning_rate": 0.00023325, "loss": 2.0414, "step": 4665 }, { "epoch": 0.97, "learning_rate": 0.0002335, "loss": 2.0335, "step": 4670 }, { "epoch": 0.97, "learning_rate": 0.00023375000000000002, "loss": 2.0312, "step": 4675 }, { "epoch": 0.97, "learning_rate": 0.00023400000000000002, "loss": 2.0302, "step": 4680 }, { "epoch": 0.97, "learning_rate": 0.00023425000000000003, "loss": 2.0291, "step": 4685 }, { "epoch": 0.97, "learning_rate": 0.00023449999999999998, "loss": 2.046, "step": 4690 }, { "epoch": 0.97, "learning_rate": 0.00023475, "loss": 2.0455, "step": 4695 }, { "epoch": 0.97, "learning_rate": 0.000235, "loss": 2.041, "step": 4700 }, { "epoch": 0.97, "learning_rate": 0.00023525, "loss": 2.032, "step": 4705 }, { "epoch": 0.98, "learning_rate": 0.0002355, "loss": 2.029, "step": 4710 }, { "epoch": 0.98, "learning_rate": 0.00023574999999999998, "loss": 2.0311, "step": 4715 }, { "epoch": 0.98, "learning_rate": 0.000236, "loss": 2.044, "step": 4720 }, { "epoch": 0.98, "learning_rate": 0.00023625, "loss": 2.041, "step": 4725 }, { "epoch": 0.98, "learning_rate": 0.0002365, "loss": 2.036, "step": 4730 }, { "epoch": 0.98, "learning_rate": 0.00023674999999999998, "loss": 2.0387, "step": 4735 }, { "epoch": 0.98, "learning_rate": 0.000237, "loss": 2.0304, "step": 4740 }, { "epoch": 0.98, "learning_rate": 0.00023725, "loss": 2.0355, "step": 4745 }, { "epoch": 0.98, "learning_rate": 0.0002375, "loss": 2.0302, "step": 4750 }, { "epoch": 0.99, "learning_rate": 0.00023775, "loss": 2.036, "step": 4755 }, { "epoch": 0.99, "learning_rate": 0.00023799999999999998, "loss": 2.0334, "step": 4760 }, { "epoch": 0.99, "learning_rate": 0.00023825, "loss": 2.0313, "step": 4765 }, { "epoch": 0.99, "learning_rate": 0.0002385, "loss": 2.033, "step": 4770 }, { "epoch": 0.99, "learning_rate": 0.00023875, "loss": 2.0355, "step": 4775 }, { "epoch": 0.99, "learning_rate": 0.00023899999999999998, "loss": 2.0279, "step": 4780 }, { "epoch": 0.99, "learning_rate": 0.00023925, "loss": 2.0374, "step": 4785 }, { "epoch": 0.99, "learning_rate": 0.0002395, "loss": 2.0377, "step": 4790 }, { "epoch": 0.99, "learning_rate": 0.00023975, "loss": 2.0261, "step": 4795 }, { "epoch": 0.99, "learning_rate": 0.00024, "loss": 2.029, "step": 4800 }, { "epoch": 1.0, "learning_rate": 0.00024024999999999999, "loss": 2.0291, "step": 4805 }, { "epoch": 1.0, "learning_rate": 0.0002405, "loss": 2.0291, "step": 4810 }, { "epoch": 1.0, "learning_rate": 0.00024075, "loss": 2.0354, "step": 4815 }, { "epoch": 1.0, "learning_rate": 0.000241, "loss": 2.0301, "step": 4820 }, { "epoch": 1.0, "learning_rate": 0.00024125, "loss": 2.0331, "step": 4825 }, { "epoch": 1.0, "learning_rate": 0.0002415, "loss": 2.0245, "step": 4830 }, { "epoch": 1.0, "learning_rate": 0.00024175, "loss": 2.0262, "step": 4835 }, { "epoch": 1.0, "learning_rate": 0.000242, "loss": 2.0287, "step": 4840 }, { "epoch": 1.0, "learning_rate": 0.00024225, "loss": 2.0272, "step": 4845 }, { "epoch": 1.0, "learning_rate": 0.00024249999999999999, "loss": 2.0237, "step": 4850 }, { "epoch": 1.01, "learning_rate": 0.00024275, "loss": 2.0248, "step": 4855 }, { "epoch": 1.01, "learning_rate": 0.000243, "loss": 2.0215, "step": 4860 }, { "epoch": 1.01, "learning_rate": 0.00024325, "loss": 2.0249, "step": 4865 }, { "epoch": 1.01, "learning_rate": 0.0002435, "loss": 2.0232, "step": 4870 }, { "epoch": 1.01, "learning_rate": 0.00024375, "loss": 2.0261, "step": 4875 }, { "epoch": 1.01, "learning_rate": 0.000244, "loss": 2.0214, "step": 4880 }, { "epoch": 1.01, "learning_rate": 0.00024425, "loss": 2.0217, "step": 4885 }, { "epoch": 1.01, "learning_rate": 0.0002445, "loss": 2.0222, "step": 4890 }, { "epoch": 1.01, "learning_rate": 0.00024475, "loss": 2.0236, "step": 4895 }, { "epoch": 1.02, "learning_rate": 0.000245, "loss": 2.0242, "step": 4900 }, { "epoch": 1.02, "learning_rate": 0.00024525, "loss": 2.0285, "step": 4905 }, { "epoch": 1.02, "learning_rate": 0.0002455, "loss": 2.0262, "step": 4910 }, { "epoch": 1.02, "learning_rate": 0.00024575, "loss": 2.0268, "step": 4915 }, { "epoch": 1.02, "learning_rate": 0.000246, "loss": 2.0229, "step": 4920 }, { "epoch": 1.02, "learning_rate": 0.00024625, "loss": 2.0252, "step": 4925 }, { "epoch": 1.02, "learning_rate": 0.00024650000000000003, "loss": 2.0165, "step": 4930 }, { "epoch": 1.02, "learning_rate": 0.00024675, "loss": 2.0197, "step": 4935 }, { "epoch": 1.02, "learning_rate": 0.000247, "loss": 2.0147, "step": 4940 }, { "epoch": 1.02, "learning_rate": 0.00024725, "loss": 2.0142, "step": 4945 }, { "epoch": 1.03, "learning_rate": 0.0002475, "loss": 2.021, "step": 4950 }, { "epoch": 1.03, "learning_rate": 0.00024775, "loss": 2.0213, "step": 4955 }, { "epoch": 1.03, "learning_rate": 0.000248, "loss": 2.023, "step": 4960 }, { "epoch": 1.03, "learning_rate": 0.00024825, "loss": 2.0213, "step": 4965 }, { "epoch": 1.03, "learning_rate": 0.0002485, "loss": 2.0138, "step": 4970 }, { "epoch": 1.03, "learning_rate": 0.00024875, "loss": 2.0115, "step": 4975 }, { "epoch": 1.03, "learning_rate": 0.000249, "loss": 2.0239, "step": 4980 }, { "epoch": 1.03, "learning_rate": 0.00024925, "loss": 2.0164, "step": 4985 }, { "epoch": 1.03, "learning_rate": 0.0002495, "loss": 2.0187, "step": 4990 }, { "epoch": 1.03, "learning_rate": 0.00024975, "loss": 2.0216, "step": 4995 }, { "epoch": 1.04, "learning_rate": 0.00025, "loss": 2.0177, "step": 5000 }, { "epoch": 1.04, "learning_rate": 0.00025025, "loss": 2.0147, "step": 5005 }, { "epoch": 1.04, "learning_rate": 0.0002505, "loss": 2.019, "step": 5010 }, { "epoch": 1.04, "learning_rate": 0.00025075, "loss": 2.0232, "step": 5015 }, { "epoch": 1.04, "learning_rate": 0.00025100000000000003, "loss": 2.026, "step": 5020 }, { "epoch": 1.04, "learning_rate": 0.00025124999999999995, "loss": 2.0225, "step": 5025 }, { "epoch": 1.04, "learning_rate": 0.0002515, "loss": 2.0193, "step": 5030 }, { "epoch": 1.04, "learning_rate": 0.00025174999999999997, "loss": 2.0213, "step": 5035 }, { "epoch": 1.04, "learning_rate": 0.000252, "loss": 2.0146, "step": 5040 }, { "epoch": 1.05, "learning_rate": 0.00025225, "loss": 2.0237, "step": 5045 }, { "epoch": 1.05, "learning_rate": 0.0002525, "loss": 2.0132, "step": 5050 }, { "epoch": 1.05, "learning_rate": 0.00025275, "loss": 2.0186, "step": 5055 }, { "epoch": 1.05, "learning_rate": 0.000253, "loss": 2.0168, "step": 5060 }, { "epoch": 1.05, "learning_rate": 0.00025325, "loss": 2.0205, "step": 5065 }, { "epoch": 1.05, "learning_rate": 0.0002535, "loss": 2.0159, "step": 5070 }, { "epoch": 1.05, "learning_rate": 0.00025374999999999996, "loss": 2.0108, "step": 5075 }, { "epoch": 1.05, "learning_rate": 0.000254, "loss": 2.0152, "step": 5080 }, { "epoch": 1.05, "learning_rate": 0.00025425, "loss": 2.0215, "step": 5085 }, { "epoch": 1.05, "learning_rate": 0.0002545, "loss": 2.0114, "step": 5090 }, { "epoch": 1.06, "learning_rate": 0.00025475, "loss": 2.0119, "step": 5095 }, { "epoch": 1.06, "learning_rate": 0.000255, "loss": 2.0212, "step": 5100 }, { "epoch": 1.06, "learning_rate": 0.00025525, "loss": 2.0157, "step": 5105 }, { "epoch": 1.06, "learning_rate": 0.00025550000000000003, "loss": 2.0178, "step": 5110 }, { "epoch": 1.06, "learning_rate": 0.00025575, "loss": 2.0095, "step": 5115 }, { "epoch": 1.06, "learning_rate": 0.000256, "loss": 2.0129, "step": 5120 }, { "epoch": 1.06, "learning_rate": 0.00025624999999999997, "loss": 2.0136, "step": 5125 }, { "epoch": 1.06, "learning_rate": 0.0002565, "loss": 2.0179, "step": 5130 }, { "epoch": 1.06, "learning_rate": 0.00025675, "loss": 2.0188, "step": 5135 }, { "epoch": 1.06, "learning_rate": 0.000257, "loss": 2.0158, "step": 5140 }, { "epoch": 1.07, "learning_rate": 0.00025725, "loss": 2.0115, "step": 5145 }, { "epoch": 1.07, "learning_rate": 0.0002575, "loss": 2.0043, "step": 5150 }, { "epoch": 1.07, "learning_rate": 0.00025775, "loss": 2.0083, "step": 5155 }, { "epoch": 1.07, "learning_rate": 0.00025800000000000004, "loss": 2.0065, "step": 5160 }, { "epoch": 1.07, "learning_rate": 0.00025824999999999996, "loss": 2.0303, "step": 5165 }, { "epoch": 1.07, "learning_rate": 0.0002585, "loss": 2.0226, "step": 5170 }, { "epoch": 1.07, "learning_rate": 0.00025875, "loss": 2.0152, "step": 5175 }, { "epoch": 1.07, "learning_rate": 0.000259, "loss": 2.0129, "step": 5180 }, { "epoch": 1.07, "learning_rate": 0.00025925, "loss": 2.0133, "step": 5185 }, { "epoch": 1.08, "learning_rate": 0.0002595, "loss": 2.0116, "step": 5190 }, { "epoch": 1.08, "learning_rate": 0.00025975, "loss": 2.0159, "step": 5195 }, { "epoch": 1.08, "learning_rate": 0.00026000000000000003, "loss": 2.0123, "step": 5200 }, { "epoch": 1.08, "learning_rate": 0.00026025, "loss": 2.0137, "step": 5205 }, { "epoch": 1.08, "learning_rate": 0.0002605, "loss": 2.0073, "step": 5210 }, { "epoch": 1.08, "learning_rate": 0.00026074999999999997, "loss": 2.0115, "step": 5215 }, { "epoch": 1.08, "learning_rate": 0.000261, "loss": 2.0121, "step": 5220 }, { "epoch": 1.08, "learning_rate": 0.00026125, "loss": 2.02, "step": 5225 }, { "epoch": 1.08, "learning_rate": 0.0002615, "loss": 2.0156, "step": 5230 }, { "epoch": 1.08, "learning_rate": 0.00026175, "loss": 2.0066, "step": 5235 }, { "epoch": 1.09, "learning_rate": 0.000262, "loss": 2.0078, "step": 5240 }, { "epoch": 1.09, "learning_rate": 0.00026225, "loss": 2.0086, "step": 5245 }, { "epoch": 1.09, "learning_rate": 0.00026250000000000004, "loss": 2.0231, "step": 5250 }, { "epoch": 1.09, "learning_rate": 0.00026274999999999996, "loss": 2.0229, "step": 5255 }, { "epoch": 1.09, "learning_rate": 0.000263, "loss": 2.0197, "step": 5260 }, { "epoch": 1.09, "learning_rate": 0.00026325, "loss": 2.0138, "step": 5265 }, { "epoch": 1.09, "learning_rate": 0.0002635, "loss": 2.0096, "step": 5270 }, { "epoch": 1.09, "learning_rate": 0.00026375, "loss": 2.0083, "step": 5275 }, { "epoch": 1.09, "learning_rate": 0.000264, "loss": 2.0057, "step": 5280 }, { "epoch": 1.09, "learning_rate": 0.00026425, "loss": 2.0045, "step": 5285 }, { "epoch": 1.1, "learning_rate": 0.00026450000000000003, "loss": 2.0041, "step": 5290 }, { "epoch": 1.1, "learning_rate": 0.00026475, "loss": 2.0076, "step": 5295 }, { "epoch": 1.1, "learning_rate": 0.00026500000000000004, "loss": 2.0126, "step": 5300 }, { "epoch": 1.1, "learning_rate": 0.00026524999999999997, "loss": 2.008, "step": 5305 }, { "epoch": 1.1, "learning_rate": 0.0002655, "loss": 2.0022, "step": 5310 }, { "epoch": 1.1, "learning_rate": 0.00026575, "loss": 2.0003, "step": 5315 }, { "epoch": 1.1, "learning_rate": 0.000266, "loss": 2.005, "step": 5320 }, { "epoch": 1.1, "learning_rate": 0.00026625, "loss": 2.0187, "step": 5325 }, { "epoch": 1.1, "learning_rate": 0.0002665, "loss": 2.0209, "step": 5330 }, { "epoch": 1.11, "learning_rate": 0.00026675, "loss": 2.0194, "step": 5335 }, { "epoch": 1.11, "learning_rate": 0.00026700000000000004, "loss": 2.0054, "step": 5340 }, { "epoch": 1.11, "learning_rate": 0.00026725, "loss": 2.0091, "step": 5345 }, { "epoch": 1.11, "learning_rate": 0.0002675, "loss": 2.0072, "step": 5350 }, { "epoch": 1.11, "learning_rate": 0.00026775, "loss": 2.0109, "step": 5355 }, { "epoch": 1.11, "learning_rate": 0.000268, "loss": 2.0089, "step": 5360 }, { "epoch": 1.11, "learning_rate": 0.00026825, "loss": 2.0153, "step": 5365 }, { "epoch": 1.11, "learning_rate": 0.0002685, "loss": 2.0121, "step": 5370 }, { "epoch": 1.11, "learning_rate": 0.00026875, "loss": 2.0098, "step": 5375 }, { "epoch": 1.11, "learning_rate": 0.00026900000000000003, "loss": 2.0021, "step": 5380 }, { "epoch": 1.12, "learning_rate": 0.00026925, "loss": 2.0002, "step": 5385 }, { "epoch": 1.12, "learning_rate": 0.00026950000000000005, "loss": 2.0117, "step": 5390 }, { "epoch": 1.12, "learning_rate": 0.00026974999999999997, "loss": 2.0055, "step": 5395 }, { "epoch": 1.12, "learning_rate": 0.00027, "loss": 2.0065, "step": 5400 }, { "epoch": 1.12, "learning_rate": 0.00027025, "loss": 2.0093, "step": 5405 }, { "epoch": 1.12, "learning_rate": 0.0002705, "loss": 2.0034, "step": 5410 }, { "epoch": 1.12, "learning_rate": 0.00027075, "loss": 2.0034, "step": 5415 }, { "epoch": 1.12, "learning_rate": 0.00027100000000000003, "loss": 2.002, "step": 5420 }, { "epoch": 1.12, "learning_rate": 0.00027125, "loss": 2.0073, "step": 5425 }, { "epoch": 1.12, "learning_rate": 0.00027150000000000004, "loss": 2.0061, "step": 5430 }, { "epoch": 1.13, "learning_rate": 0.00027175, "loss": 2.0007, "step": 5435 }, { "epoch": 1.13, "learning_rate": 0.00027200000000000005, "loss": 2.0056, "step": 5440 }, { "epoch": 1.13, "learning_rate": 0.00027225, "loss": 2.0038, "step": 5445 }, { "epoch": 1.13, "learning_rate": 0.0002725, "loss": 2.001, "step": 5450 }, { "epoch": 1.13, "learning_rate": 0.00027275, "loss": 1.9973, "step": 5455 }, { "epoch": 1.13, "learning_rate": 0.000273, "loss": 1.9992, "step": 5460 }, { "epoch": 1.13, "learning_rate": 0.00027325, "loss": 2.0009, "step": 5465 }, { "epoch": 1.13, "learning_rate": 0.00027350000000000003, "loss": 1.9976, "step": 5470 }, { "epoch": 1.13, "learning_rate": 0.00027375, "loss": 1.995, "step": 5475 }, { "epoch": 1.14, "learning_rate": 0.00027400000000000005, "loss": 2.0009, "step": 5480 }, { "epoch": 1.14, "learning_rate": 0.00027425, "loss": 2.0143, "step": 5485 }, { "epoch": 1.14, "learning_rate": 0.0002745, "loss": 2.0099, "step": 5490 }, { "epoch": 1.14, "learning_rate": 0.00027475, "loss": 2.007, "step": 5495 }, { "epoch": 1.14, "learning_rate": 0.000275, "loss": 1.9968, "step": 5500 }, { "epoch": 1.14, "learning_rate": 0.00027525, "loss": 1.9988, "step": 5505 }, { "epoch": 1.14, "learning_rate": 0.00027550000000000003, "loss": 1.9963, "step": 5510 }, { "epoch": 1.14, "learning_rate": 0.00027575, "loss": 2.0028, "step": 5515 }, { "epoch": 1.14, "learning_rate": 0.00027600000000000004, "loss": 1.9981, "step": 5520 }, { "epoch": 1.14, "learning_rate": 0.00027625, "loss": 1.9962, "step": 5525 }, { "epoch": 1.15, "learning_rate": 0.00027650000000000005, "loss": 2.0002, "step": 5530 }, { "epoch": 1.15, "learning_rate": 0.00027675, "loss": 2.002, "step": 5535 }, { "epoch": 1.15, "learning_rate": 0.000277, "loss": 1.9919, "step": 5540 }, { "epoch": 1.15, "learning_rate": 0.00027725, "loss": 2.0003, "step": 5545 }, { "epoch": 1.15, "learning_rate": 0.0002775, "loss": 2.0082, "step": 5550 }, { "epoch": 1.15, "learning_rate": 0.00027775, "loss": 2.0011, "step": 5555 }, { "epoch": 1.15, "learning_rate": 0.00027800000000000004, "loss": 2.0029, "step": 5560 }, { "epoch": 1.15, "learning_rate": 0.00027825, "loss": 2.0001, "step": 5565 }, { "epoch": 1.15, "learning_rate": 0.00027850000000000005, "loss": 1.9925, "step": 5570 }, { "epoch": 1.15, "learning_rate": 0.00027875, "loss": 2.0044, "step": 5575 }, { "epoch": 1.16, "learning_rate": 0.000279, "loss": 1.9959, "step": 5580 }, { "epoch": 1.16, "learning_rate": 0.00027925, "loss": 1.9961, "step": 5585 }, { "epoch": 1.16, "learning_rate": 0.0002795, "loss": 1.9943, "step": 5590 }, { "epoch": 1.16, "learning_rate": 0.00027975, "loss": 1.9973, "step": 5595 }, { "epoch": 1.16, "learning_rate": 0.00028000000000000003, "loss": 2.0002, "step": 5600 }, { "epoch": 1.16, "learning_rate": 0.00028025, "loss": 1.9955, "step": 5605 }, { "epoch": 1.16, "learning_rate": 0.00028050000000000004, "loss": 2.0046, "step": 5610 }, { "epoch": 1.16, "learning_rate": 0.00028075, "loss": 2.0028, "step": 5615 }, { "epoch": 1.16, "learning_rate": 0.00028100000000000005, "loss": 1.9933, "step": 5620 }, { "epoch": 1.17, "learning_rate": 0.00028125000000000003, "loss": 2.001, "step": 5625 }, { "epoch": 1.17, "learning_rate": 0.00028149999999999996, "loss": 1.9926, "step": 5630 }, { "epoch": 1.17, "learning_rate": 0.00028175, "loss": 1.9971, "step": 5635 }, { "epoch": 1.17, "learning_rate": 0.00028199999999999997, "loss": 1.9983, "step": 5640 }, { "epoch": 1.17, "learning_rate": 0.00028225, "loss": 1.9914, "step": 5645 }, { "epoch": 1.17, "learning_rate": 0.0002825, "loss": 2.0006, "step": 5650 }, { "epoch": 1.17, "learning_rate": 0.00028275, "loss": 1.9934, "step": 5655 }, { "epoch": 1.17, "learning_rate": 0.000283, "loss": 1.9989, "step": 5660 }, { "epoch": 1.17, "learning_rate": 0.00028325000000000003, "loss": 2.0013, "step": 5665 }, { "epoch": 1.17, "learning_rate": 0.0002835, "loss": 1.9978, "step": 5670 }, { "epoch": 1.18, "learning_rate": 0.00028375, "loss": 1.9955, "step": 5675 }, { "epoch": 1.18, "learning_rate": 0.00028399999999999996, "loss": 1.9921, "step": 5680 }, { "epoch": 1.18, "learning_rate": 0.00028425, "loss": 1.9965, "step": 5685 }, { "epoch": 1.18, "learning_rate": 0.0002845, "loss": 1.9929, "step": 5690 }, { "epoch": 1.18, "learning_rate": 0.00028475, "loss": 2.0082, "step": 5695 }, { "epoch": 1.18, "learning_rate": 0.000285, "loss": 2.0031, "step": 5700 }, { "epoch": 1.18, "learning_rate": 0.00028525, "loss": 1.9928, "step": 5705 }, { "epoch": 1.18, "learning_rate": 0.0002855, "loss": 1.9965, "step": 5710 }, { "epoch": 1.18, "learning_rate": 0.00028575000000000003, "loss": 1.9954, "step": 5715 }, { "epoch": 1.19, "learning_rate": 0.00028599999999999996, "loss": 1.9917, "step": 5720 }, { "epoch": 1.19, "learning_rate": 0.00028625, "loss": 1.9964, "step": 5725 }, { "epoch": 1.19, "learning_rate": 0.00028649999999999997, "loss": 1.9973, "step": 5730 }, { "epoch": 1.19, "learning_rate": 0.00028675, "loss": 1.996, "step": 5735 }, { "epoch": 1.19, "learning_rate": 0.000287, "loss": 1.991, "step": 5740 }, { "epoch": 1.19, "learning_rate": 0.00028725, "loss": 1.989, "step": 5745 }, { "epoch": 1.19, "learning_rate": 0.0002875, "loss": 1.9937, "step": 5750 }, { "epoch": 1.19, "learning_rate": 0.00028775000000000003, "loss": 1.9969, "step": 5755 }, { "epoch": 1.19, "learning_rate": 0.000288, "loss": 1.9956, "step": 5760 }, { "epoch": 1.19, "learning_rate": 0.00028825, "loss": 1.9933, "step": 5765 }, { "epoch": 1.2, "learning_rate": 0.00028849999999999997, "loss": 1.9937, "step": 5770 }, { "epoch": 1.2, "learning_rate": 0.00028875, "loss": 1.9936, "step": 5775 }, { "epoch": 1.2, "learning_rate": 0.000289, "loss": 1.9909, "step": 5780 }, { "epoch": 1.2, "learning_rate": 0.00028925, "loss": 1.9878, "step": 5785 }, { "epoch": 1.2, "learning_rate": 0.0002895, "loss": 1.9899, "step": 5790 }, { "epoch": 1.2, "learning_rate": 0.00028975, "loss": 1.9871, "step": 5795 }, { "epoch": 1.2, "learning_rate": 0.00029, "loss": 1.9957, "step": 5800 }, { "epoch": 1.2, "learning_rate": 0.00029025000000000003, "loss": 1.9894, "step": 5805 }, { "epoch": 1.2, "learning_rate": 0.00029049999999999996, "loss": 1.9932, "step": 5810 }, { "epoch": 1.2, "learning_rate": 0.00029075, "loss": 1.9911, "step": 5815 }, { "epoch": 1.21, "learning_rate": 0.00029099999999999997, "loss": 1.9859, "step": 5820 }, { "epoch": 1.21, "learning_rate": 0.00029125, "loss": 1.986, "step": 5825 }, { "epoch": 1.21, "learning_rate": 0.0002915, "loss": 1.9856, "step": 5830 }, { "epoch": 1.21, "learning_rate": 0.00029175, "loss": 1.9992, "step": 5835 }, { "epoch": 1.21, "learning_rate": 0.000292, "loss": 1.9967, "step": 5840 }, { "epoch": 1.21, "learning_rate": 0.00029225000000000003, "loss": 1.9919, "step": 5845 }, { "epoch": 1.21, "learning_rate": 0.0002925, "loss": 1.9928, "step": 5850 }, { "epoch": 1.21, "learning_rate": 0.00029275000000000004, "loss": 1.989, "step": 5855 }, { "epoch": 1.21, "learning_rate": 0.00029299999999999997, "loss": 1.9926, "step": 5860 }, { "epoch": 1.22, "learning_rate": 0.00029325, "loss": 1.99, "step": 5865 }, { "epoch": 1.22, "learning_rate": 0.0002935, "loss": 1.9894, "step": 5870 }, { "epoch": 1.22, "learning_rate": 0.00029375, "loss": 1.9867, "step": 5875 }, { "epoch": 1.22, "learning_rate": 0.000294, "loss": 1.985, "step": 5880 }, { "epoch": 1.22, "learning_rate": 0.00029425, "loss": 1.9884, "step": 5885 }, { "epoch": 1.22, "learning_rate": 0.0002945, "loss": 1.9957, "step": 5890 }, { "epoch": 1.22, "learning_rate": 0.00029475000000000004, "loss": 1.981, "step": 5895 }, { "epoch": 1.22, "learning_rate": 0.000295, "loss": 1.9886, "step": 5900 }, { "epoch": 1.22, "learning_rate": 0.00029525, "loss": 1.9976, "step": 5905 }, { "epoch": 1.22, "learning_rate": 0.00029549999999999997, "loss": 1.9896, "step": 5910 }, { "epoch": 1.23, "learning_rate": 0.00029575, "loss": 1.9838, "step": 5915 }, { "epoch": 1.23, "learning_rate": 0.000296, "loss": 1.9872, "step": 5920 }, { "epoch": 1.23, "learning_rate": 0.00029625, "loss": 1.9848, "step": 5925 }, { "epoch": 1.23, "learning_rate": 0.0002965, "loss": 1.9806, "step": 5930 }, { "epoch": 1.23, "learning_rate": 0.00029675000000000003, "loss": 1.9935, "step": 5935 }, { "epoch": 1.23, "learning_rate": 0.000297, "loss": 1.982, "step": 5940 }, { "epoch": 1.23, "learning_rate": 0.00029725000000000004, "loss": 1.9835, "step": 5945 }, { "epoch": 1.23, "learning_rate": 0.00029749999999999997, "loss": 1.9816, "step": 5950 }, { "epoch": 1.23, "learning_rate": 0.00029775, "loss": 1.9863, "step": 5955 }, { "epoch": 1.23, "learning_rate": 0.000298, "loss": 1.9859, "step": 5960 }, { "epoch": 1.24, "learning_rate": 0.00029825, "loss": 1.9823, "step": 5965 }, { "epoch": 1.24, "learning_rate": 0.0002985, "loss": 1.9805, "step": 5970 }, { "epoch": 1.24, "learning_rate": 0.00029875, "loss": 1.9847, "step": 5975 }, { "epoch": 1.24, "learning_rate": 0.000299, "loss": 1.9884, "step": 5980 }, { "epoch": 1.24, "learning_rate": 0.00029925000000000004, "loss": 1.9886, "step": 5985 }, { "epoch": 1.24, "learning_rate": 0.0002995, "loss": 1.985, "step": 5990 }, { "epoch": 1.24, "learning_rate": 0.00029975000000000005, "loss": 1.9861, "step": 5995 }, { "epoch": 1.24, "learning_rate": 0.0003, "loss": 1.9797, "step": 6000 }, { "epoch": 1.24, "eval_accuracy": 0.4922875816993464, "eval_loss": 2.2025249004364014, "eval_runtime": 0.6498, "eval_samples_per_second": 230.853, "eval_steps_per_second": 1.539, "step": 6000 }, { "epoch": 1.24, "learning_rate": 0.00030025, "loss": 1.9873, "step": 6005 }, { "epoch": 1.25, "learning_rate": 0.0003005, "loss": 1.9887, "step": 6010 }, { "epoch": 1.25, "learning_rate": 0.00030075, "loss": 1.9817, "step": 6015 }, { "epoch": 1.25, "learning_rate": 0.000301, "loss": 1.984, "step": 6020 }, { "epoch": 1.25, "learning_rate": 0.00030125000000000003, "loss": 1.9791, "step": 6025 }, { "epoch": 1.25, "learning_rate": 0.0003015, "loss": 1.9875, "step": 6030 }, { "epoch": 1.25, "learning_rate": 0.00030175000000000004, "loss": 1.9831, "step": 6035 }, { "epoch": 1.25, "learning_rate": 0.000302, "loss": 1.9819, "step": 6040 }, { "epoch": 1.25, "learning_rate": 0.00030225, "loss": 1.9837, "step": 6045 }, { "epoch": 1.25, "learning_rate": 0.0003025, "loss": 1.9799, "step": 6050 }, { "epoch": 1.25, "learning_rate": 0.00030275, "loss": 1.9894, "step": 6055 }, { "epoch": 1.26, "learning_rate": 0.000303, "loss": 1.9796, "step": 6060 }, { "epoch": 1.26, "learning_rate": 0.00030325, "loss": 1.9848, "step": 6065 }, { "epoch": 1.26, "learning_rate": 0.0003035, "loss": 1.9811, "step": 6070 }, { "epoch": 1.26, "learning_rate": 0.00030375000000000004, "loss": 1.9849, "step": 6075 }, { "epoch": 1.26, "learning_rate": 0.000304, "loss": 1.984, "step": 6080 }, { "epoch": 1.26, "learning_rate": 0.00030425000000000005, "loss": 1.9923, "step": 6085 }, { "epoch": 1.26, "learning_rate": 0.0003045, "loss": 1.9901, "step": 6090 }, { "epoch": 1.26, "learning_rate": 0.00030475, "loss": 1.988, "step": 6095 }, { "epoch": 1.26, "learning_rate": 0.000305, "loss": 1.9866, "step": 6100 }, { "epoch": 1.26, "learning_rate": 0.00030525, "loss": 1.9774, "step": 6105 }, { "epoch": 1.27, "learning_rate": 0.0003055, "loss": 1.9843, "step": 6110 }, { "epoch": 1.27, "learning_rate": 0.00030575000000000003, "loss": 1.9787, "step": 6115 }, { "epoch": 1.27, "learning_rate": 0.000306, "loss": 1.981, "step": 6120 }, { "epoch": 1.27, "learning_rate": 0.00030625000000000004, "loss": 1.9842, "step": 6125 }, { "epoch": 1.27, "learning_rate": 0.0003065, "loss": 1.9863, "step": 6130 }, { "epoch": 1.27, "learning_rate": 0.00030675, "loss": 1.9785, "step": 6135 }, { "epoch": 1.27, "learning_rate": 0.000307, "loss": 1.9767, "step": 6140 }, { "epoch": 1.27, "learning_rate": 0.00030725, "loss": 1.9887, "step": 6145 }, { "epoch": 1.27, "learning_rate": 0.0003075, "loss": 1.9889, "step": 6150 }, { "epoch": 1.28, "learning_rate": 0.00030775, "loss": 1.9873, "step": 6155 }, { "epoch": 1.28, "learning_rate": 0.000308, "loss": 1.9764, "step": 6160 }, { "epoch": 1.28, "learning_rate": 0.00030825000000000004, "loss": 1.9768, "step": 6165 }, { "epoch": 1.28, "learning_rate": 0.0003085, "loss": 1.9765, "step": 6170 }, { "epoch": 1.28, "learning_rate": 0.00030875000000000005, "loss": 1.9789, "step": 6175 }, { "epoch": 1.28, "learning_rate": 0.00030900000000000003, "loss": 1.9787, "step": 6180 }, { "epoch": 1.28, "learning_rate": 0.00030925, "loss": 1.9832, "step": 6185 }, { "epoch": 1.28, "learning_rate": 0.0003095, "loss": 1.9798, "step": 6190 }, { "epoch": 1.28, "learning_rate": 0.00030975, "loss": 1.9736, "step": 6195 }, { "epoch": 1.28, "learning_rate": 0.00031, "loss": 1.9757, "step": 6200 }, { "epoch": 1.29, "learning_rate": 0.00031025000000000003, "loss": 1.9811, "step": 6205 }, { "epoch": 1.29, "learning_rate": 0.0003105, "loss": 1.9795, "step": 6210 }, { "epoch": 1.29, "learning_rate": 0.00031075000000000005, "loss": 1.98, "step": 6215 }, { "epoch": 1.29, "learning_rate": 0.000311, "loss": 1.9701, "step": 6220 }, { "epoch": 1.29, "learning_rate": 0.00031125000000000006, "loss": 1.9754, "step": 6225 }, { "epoch": 1.29, "learning_rate": 0.0003115, "loss": 1.9747, "step": 6230 }, { "epoch": 1.29, "learning_rate": 0.00031175, "loss": 1.9827, "step": 6235 }, { "epoch": 1.29, "learning_rate": 0.000312, "loss": 1.9763, "step": 6240 }, { "epoch": 1.29, "learning_rate": 0.00031225000000000003, "loss": 1.9754, "step": 6245 }, { "epoch": 1.29, "learning_rate": 0.0003125, "loss": 1.9744, "step": 6250 }, { "epoch": 1.3, "learning_rate": 0.00031275, "loss": 1.9723, "step": 6255 }, { "epoch": 1.3, "learning_rate": 0.000313, "loss": 1.9759, "step": 6260 }, { "epoch": 1.3, "learning_rate": 0.00031325, "loss": 1.9775, "step": 6265 }, { "epoch": 1.3, "learning_rate": 0.00031350000000000003, "loss": 1.9743, "step": 6270 }, { "epoch": 1.3, "learning_rate": 0.00031374999999999996, "loss": 1.9749, "step": 6275 }, { "epoch": 1.3, "learning_rate": 0.000314, "loss": 1.9724, "step": 6280 }, { "epoch": 1.3, "learning_rate": 0.00031424999999999997, "loss": 1.9768, "step": 6285 }, { "epoch": 1.3, "learning_rate": 0.0003145, "loss": 1.9686, "step": 6290 }, { "epoch": 1.3, "learning_rate": 0.00031475, "loss": 1.9725, "step": 6295 }, { "epoch": 1.31, "learning_rate": 0.000315, "loss": 1.9735, "step": 6300 }, { "epoch": 1.31, "learning_rate": 0.00031525, "loss": 1.9802, "step": 6305 }, { "epoch": 1.31, "learning_rate": 0.0003155, "loss": 1.9912, "step": 6310 }, { "epoch": 1.31, "learning_rate": 0.00031575, "loss": 1.9847, "step": 6315 }, { "epoch": 1.31, "learning_rate": 0.000316, "loss": 1.985, "step": 6320 }, { "epoch": 1.31, "learning_rate": 0.00031624999999999996, "loss": 1.9776, "step": 6325 }, { "epoch": 1.31, "learning_rate": 0.0003165, "loss": 1.974, "step": 6330 }, { "epoch": 1.31, "learning_rate": 0.00031675, "loss": 1.9737, "step": 6335 }, { "epoch": 1.31, "learning_rate": 0.000317, "loss": 1.9743, "step": 6340 }, { "epoch": 1.31, "learning_rate": 0.00031725, "loss": 1.9787, "step": 6345 }, { "epoch": 1.32, "learning_rate": 0.0003175, "loss": 1.9713, "step": 6350 }, { "epoch": 1.32, "learning_rate": 0.00031775, "loss": 1.9695, "step": 6355 }, { "epoch": 1.32, "learning_rate": 0.00031800000000000003, "loss": 1.9695, "step": 6360 }, { "epoch": 1.32, "learning_rate": 0.00031825, "loss": 1.9798, "step": 6365 }, { "epoch": 1.32, "learning_rate": 0.0003185, "loss": 1.9719, "step": 6370 }, { "epoch": 1.32, "learning_rate": 0.00031874999999999997, "loss": 1.973, "step": 6375 }, { "epoch": 1.32, "learning_rate": 0.000319, "loss": 1.9774, "step": 6380 }, { "epoch": 1.32, "learning_rate": 0.00031925, "loss": 1.9667, "step": 6385 }, { "epoch": 1.32, "learning_rate": 0.0003195, "loss": 1.9681, "step": 6390 }, { "epoch": 1.32, "learning_rate": 0.00031975, "loss": 1.9675, "step": 6395 }, { "epoch": 1.33, "learning_rate": 0.00032, "loss": 1.981, "step": 6400 }, { "epoch": 1.33, "learning_rate": 0.00032025, "loss": 1.9761, "step": 6405 }, { "epoch": 1.33, "learning_rate": 0.00032050000000000004, "loss": 1.9697, "step": 6410 }, { "epoch": 1.33, "learning_rate": 0.00032074999999999996, "loss": 1.9732, "step": 6415 }, { "epoch": 1.33, "learning_rate": 0.000321, "loss": 1.9663, "step": 6420 }, { "epoch": 1.33, "learning_rate": 0.00032125, "loss": 1.9722, "step": 6425 }, { "epoch": 1.33, "learning_rate": 0.0003215, "loss": 1.9727, "step": 6430 }, { "epoch": 1.33, "learning_rate": 0.00032175, "loss": 1.9708, "step": 6435 }, { "epoch": 1.33, "learning_rate": 0.000322, "loss": 1.9658, "step": 6440 }, { "epoch": 1.34, "learning_rate": 0.00032225, "loss": 1.9715, "step": 6445 }, { "epoch": 1.34, "learning_rate": 0.00032250000000000003, "loss": 1.9657, "step": 6450 }, { "epoch": 1.34, "learning_rate": 0.00032275, "loss": 1.968, "step": 6455 }, { "epoch": 1.34, "learning_rate": 0.000323, "loss": 1.9687, "step": 6460 }, { "epoch": 1.34, "learning_rate": 0.00032324999999999997, "loss": 1.9726, "step": 6465 }, { "epoch": 1.34, "learning_rate": 0.0003235, "loss": 1.9699, "step": 6470 }, { "epoch": 1.34, "learning_rate": 0.00032375, "loss": 1.9709, "step": 6475 }, { "epoch": 1.34, "learning_rate": 0.000324, "loss": 1.9683, "step": 6480 }, { "epoch": 1.34, "learning_rate": 0.00032425, "loss": 1.9687, "step": 6485 }, { "epoch": 1.34, "learning_rate": 0.00032450000000000003, "loss": 1.9751, "step": 6490 }, { "epoch": 1.35, "learning_rate": 0.00032475, "loss": 1.9767, "step": 6495 }, { "epoch": 1.35, "learning_rate": 0.00032500000000000004, "loss": 1.9691, "step": 6500 }, { "epoch": 1.35, "learning_rate": 0.00032524999999999996, "loss": 1.9666, "step": 6505 }, { "epoch": 1.35, "learning_rate": 0.0003255, "loss": 1.97, "step": 6510 }, { "epoch": 1.35, "learning_rate": 0.00032575, "loss": 1.9719, "step": 6515 }, { "epoch": 1.35, "learning_rate": 0.000326, "loss": 1.9678, "step": 6520 }, { "epoch": 1.35, "learning_rate": 0.00032625, "loss": 1.9678, "step": 6525 }, { "epoch": 1.35, "learning_rate": 0.0003265, "loss": 1.9693, "step": 6530 }, { "epoch": 1.35, "learning_rate": 0.00032675, "loss": 1.9694, "step": 6535 }, { "epoch": 1.35, "learning_rate": 0.00032700000000000003, "loss": 1.9696, "step": 6540 }, { "epoch": 1.36, "learning_rate": 0.00032725, "loss": 1.9704, "step": 6545 }, { "epoch": 1.36, "learning_rate": 0.00032750000000000005, "loss": 1.9713, "step": 6550 }, { "epoch": 1.36, "learning_rate": 0.00032774999999999997, "loss": 1.97, "step": 6555 }, { "epoch": 1.36, "learning_rate": 0.000328, "loss": 1.972, "step": 6560 }, { "epoch": 1.36, "learning_rate": 0.00032825, "loss": 1.9607, "step": 6565 }, { "epoch": 1.36, "learning_rate": 0.0003285, "loss": 1.9709, "step": 6570 }, { "epoch": 1.36, "learning_rate": 0.00032875, "loss": 1.9732, "step": 6575 }, { "epoch": 1.36, "learning_rate": 0.00032900000000000003, "loss": 1.9698, "step": 6580 }, { "epoch": 1.36, "learning_rate": 0.00032925, "loss": 1.9667, "step": 6585 }, { "epoch": 1.37, "learning_rate": 0.00032950000000000004, "loss": 1.9659, "step": 6590 }, { "epoch": 1.37, "learning_rate": 0.00032975, "loss": 1.969, "step": 6595 }, { "epoch": 1.37, "learning_rate": 0.00033, "loss": 1.9687, "step": 6600 }, { "epoch": 1.37, "learning_rate": 0.00033025, "loss": 1.9732, "step": 6605 }, { "epoch": 1.37, "learning_rate": 0.0003305, "loss": 1.9605, "step": 6610 }, { "epoch": 1.37, "learning_rate": 0.00033075, "loss": 1.9625, "step": 6615 }, { "epoch": 1.37, "learning_rate": 0.000331, "loss": 1.9634, "step": 6620 }, { "epoch": 1.37, "learning_rate": 0.00033125, "loss": 1.9671, "step": 6625 }, { "epoch": 1.37, "learning_rate": 0.00033150000000000003, "loss": 1.9708, "step": 6630 }, { "epoch": 1.37, "learning_rate": 0.00033175, "loss": 1.9747, "step": 6635 }, { "epoch": 1.38, "learning_rate": 0.00033200000000000005, "loss": 1.9646, "step": 6640 }, { "epoch": 1.38, "learning_rate": 0.00033224999999999997, "loss": 1.9718, "step": 6645 }, { "epoch": 1.38, "learning_rate": 0.0003325, "loss": 1.9659, "step": 6650 }, { "epoch": 1.38, "learning_rate": 0.00033275, "loss": 1.9633, "step": 6655 }, { "epoch": 1.38, "learning_rate": 0.000333, "loss": 1.9678, "step": 6660 }, { "epoch": 1.38, "learning_rate": 0.00033325, "loss": 1.967, "step": 6665 }, { "epoch": 1.38, "learning_rate": 0.00033350000000000003, "loss": 1.964, "step": 6670 }, { "epoch": 1.38, "learning_rate": 0.00033375, "loss": 1.9734, "step": 6675 }, { "epoch": 1.38, "learning_rate": 0.00033400000000000004, "loss": 1.9647, "step": 6680 }, { "epoch": 1.38, "learning_rate": 0.00033425, "loss": 1.9673, "step": 6685 }, { "epoch": 1.39, "learning_rate": 0.00033450000000000005, "loss": 1.9619, "step": 6690 }, { "epoch": 1.39, "learning_rate": 0.00033475, "loss": 1.9654, "step": 6695 }, { "epoch": 1.39, "learning_rate": 0.000335, "loss": 1.9685, "step": 6700 }, { "epoch": 1.39, "learning_rate": 0.00033525, "loss": 1.9643, "step": 6705 }, { "epoch": 1.39, "learning_rate": 0.0003355, "loss": 1.9634, "step": 6710 }, { "epoch": 1.39, "learning_rate": 0.00033575, "loss": 1.9611, "step": 6715 }, { "epoch": 1.39, "learning_rate": 0.00033600000000000004, "loss": 1.9652, "step": 6720 }, { "epoch": 1.39, "learning_rate": 0.00033625, "loss": 1.9588, "step": 6725 }, { "epoch": 1.39, "learning_rate": 0.00033650000000000005, "loss": 1.9618, "step": 6730 }, { "epoch": 1.4, "learning_rate": 0.00033675, "loss": 1.9643, "step": 6735 }, { "epoch": 1.4, "learning_rate": 0.000337, "loss": 1.964, "step": 6740 }, { "epoch": 1.4, "learning_rate": 0.00033725, "loss": 1.9636, "step": 6745 }, { "epoch": 1.4, "learning_rate": 0.0003375, "loss": 1.964, "step": 6750 }, { "epoch": 1.4, "learning_rate": 0.00033775, "loss": 1.9632, "step": 6755 }, { "epoch": 1.4, "learning_rate": 0.00033800000000000003, "loss": 1.955, "step": 6760 }, { "epoch": 1.4, "learning_rate": 0.00033825, "loss": 1.9642, "step": 6765 }, { "epoch": 1.4, "learning_rate": 0.00033850000000000004, "loss": 1.9661, "step": 6770 }, { "epoch": 1.4, "learning_rate": 0.00033875, "loss": 1.9636, "step": 6775 }, { "epoch": 1.4, "learning_rate": 0.00033900000000000005, "loss": 1.9666, "step": 6780 }, { "epoch": 1.41, "learning_rate": 0.00033925, "loss": 1.9612, "step": 6785 }, { "epoch": 1.41, "learning_rate": 0.0003395, "loss": 1.962, "step": 6790 }, { "epoch": 1.41, "learning_rate": 0.00033975, "loss": 1.9626, "step": 6795 }, { "epoch": 1.41, "learning_rate": 0.00034, "loss": 1.9621, "step": 6800 }, { "epoch": 1.41, "learning_rate": 0.00034025, "loss": 1.9619, "step": 6805 }, { "epoch": 1.41, "learning_rate": 0.00034050000000000004, "loss": 1.9585, "step": 6810 }, { "epoch": 1.41, "learning_rate": 0.00034075, "loss": 1.9674, "step": 6815 }, { "epoch": 1.41, "learning_rate": 0.00034100000000000005, "loss": 1.9671, "step": 6820 }, { "epoch": 1.41, "learning_rate": 0.00034125000000000003, "loss": 1.9686, "step": 6825 }, { "epoch": 1.41, "learning_rate": 0.0003415, "loss": 1.9705, "step": 6830 }, { "epoch": 1.42, "learning_rate": 0.00034175, "loss": 1.9638, "step": 6835 }, { "epoch": 1.42, "learning_rate": 0.000342, "loss": 1.9624, "step": 6840 }, { "epoch": 1.42, "learning_rate": 0.00034225, "loss": 1.9609, "step": 6845 }, { "epoch": 1.42, "learning_rate": 0.00034250000000000003, "loss": 1.9615, "step": 6850 }, { "epoch": 1.42, "learning_rate": 0.00034275, "loss": 1.9552, "step": 6855 }, { "epoch": 1.42, "learning_rate": 0.00034300000000000004, "loss": 1.9587, "step": 6860 }, { "epoch": 1.42, "learning_rate": 0.00034325, "loss": 1.9586, "step": 6865 }, { "epoch": 1.42, "learning_rate": 0.00034350000000000006, "loss": 1.9641, "step": 6870 }, { "epoch": 1.42, "learning_rate": 0.00034375, "loss": 1.9642, "step": 6875 }, { "epoch": 1.43, "learning_rate": 0.00034399999999999996, "loss": 1.9592, "step": 6880 }, { "epoch": 1.43, "learning_rate": 0.00034425, "loss": 1.9605, "step": 6885 }, { "epoch": 1.43, "learning_rate": 0.00034449999999999997, "loss": 1.9564, "step": 6890 }, { "epoch": 1.43, "learning_rate": 0.00034475, "loss": 1.9605, "step": 6895 }, { "epoch": 1.43, "learning_rate": 0.000345, "loss": 1.9629, "step": 6900 }, { "epoch": 1.43, "learning_rate": 0.00034525, "loss": 1.9601, "step": 6905 }, { "epoch": 1.43, "learning_rate": 0.0003455, "loss": 1.9616, "step": 6910 }, { "epoch": 1.43, "learning_rate": 0.00034575000000000003, "loss": 1.9617, "step": 6915 }, { "epoch": 1.43, "learning_rate": 0.000346, "loss": 1.9656, "step": 6920 }, { "epoch": 1.43, "learning_rate": 0.00034625, "loss": 1.9595, "step": 6925 }, { "epoch": 1.44, "learning_rate": 0.00034649999999999997, "loss": 1.9561, "step": 6930 }, { "epoch": 1.44, "learning_rate": 0.00034675, "loss": 1.9647, "step": 6935 }, { "epoch": 1.44, "learning_rate": 0.000347, "loss": 1.9612, "step": 6940 }, { "epoch": 1.44, "learning_rate": 0.00034725, "loss": 1.9528, "step": 6945 }, { "epoch": 1.44, "learning_rate": 0.0003475, "loss": 1.9555, "step": 6950 }, { "epoch": 1.44, "learning_rate": 0.00034775, "loss": 1.9611, "step": 6955 }, { "epoch": 1.44, "learning_rate": 0.000348, "loss": 1.9598, "step": 6960 }, { "epoch": 1.44, "learning_rate": 0.00034825000000000004, "loss": 1.9609, "step": 6965 }, { "epoch": 1.44, "learning_rate": 0.00034849999999999996, "loss": 1.9693, "step": 6970 }, { "epoch": 1.44, "learning_rate": 0.00034875, "loss": 1.9573, "step": 6975 }, { "epoch": 1.45, "learning_rate": 0.00034899999999999997, "loss": 1.9635, "step": 6980 }, { "epoch": 1.45, "learning_rate": 0.00034925, "loss": 1.9603, "step": 6985 }, { "epoch": 1.45, "learning_rate": 0.0003495, "loss": 1.9601, "step": 6990 }, { "epoch": 1.45, "learning_rate": 0.00034975, "loss": 1.9527, "step": 6995 }, { "epoch": 1.45, "learning_rate": 0.00035, "loss": 1.9668, "step": 7000 }, { "epoch": 1.45, "learning_rate": 0.00035025000000000003, "loss": 1.9595, "step": 7005 }, { "epoch": 1.45, "learning_rate": 0.0003505, "loss": 1.9562, "step": 7010 }, { "epoch": 1.45, "learning_rate": 0.00035075, "loss": 1.9574, "step": 7015 }, { "epoch": 1.45, "learning_rate": 0.00035099999999999997, "loss": 1.9526, "step": 7020 }, { "epoch": 1.46, "learning_rate": 0.00035125, "loss": 1.9596, "step": 7025 }, { "epoch": 1.46, "learning_rate": 0.0003515, "loss": 1.96, "step": 7030 }, { "epoch": 1.46, "learning_rate": 0.00035175, "loss": 1.9602, "step": 7035 }, { "epoch": 1.46, "learning_rate": 0.000352, "loss": 1.9551, "step": 7040 }, { "epoch": 1.46, "learning_rate": 0.00035225, "loss": 1.955, "step": 7045 }, { "epoch": 1.46, "learning_rate": 0.0003525, "loss": 1.958, "step": 7050 }, { "epoch": 1.46, "learning_rate": 0.00035275000000000004, "loss": 1.9568, "step": 7055 }, { "epoch": 1.46, "learning_rate": 0.00035299999999999996, "loss": 1.9611, "step": 7060 }, { "epoch": 1.46, "learning_rate": 0.00035325, "loss": 1.9533, "step": 7065 }, { "epoch": 1.46, "learning_rate": 0.0003535, "loss": 1.9564, "step": 7070 }, { "epoch": 1.47, "learning_rate": 0.00035375, "loss": 1.9551, "step": 7075 }, { "epoch": 1.47, "learning_rate": 0.000354, "loss": 1.9469, "step": 7080 }, { "epoch": 1.47, "learning_rate": 0.00035425, "loss": 1.9735, "step": 7085 }, { "epoch": 1.47, "learning_rate": 0.0003545, "loss": 1.9696, "step": 7090 }, { "epoch": 1.47, "learning_rate": 0.00035475000000000003, "loss": 1.9652, "step": 7095 }, { "epoch": 1.47, "learning_rate": 0.000355, "loss": 1.9584, "step": 7100 }, { "epoch": 1.47, "learning_rate": 0.00035525000000000004, "loss": 1.9589, "step": 7105 }, { "epoch": 1.47, "learning_rate": 0.00035549999999999997, "loss": 1.9559, "step": 7110 }, { "epoch": 1.47, "learning_rate": 0.00035575, "loss": 1.9573, "step": 7115 }, { "epoch": 1.48, "learning_rate": 0.000356, "loss": 1.9556, "step": 7120 }, { "epoch": 1.48, "learning_rate": 0.00035625, "loss": 1.9512, "step": 7125 }, { "epoch": 1.48, "learning_rate": 0.0003565, "loss": 1.9598, "step": 7130 }, { "epoch": 1.48, "learning_rate": 0.00035675, "loss": 1.9542, "step": 7135 }, { "epoch": 1.48, "learning_rate": 0.000357, "loss": 1.9585, "step": 7140 }, { "epoch": 1.48, "learning_rate": 0.00035725000000000004, "loss": 1.9611, "step": 7145 }, { "epoch": 1.48, "learning_rate": 0.0003575, "loss": 1.9544, "step": 7150 }, { "epoch": 1.48, "learning_rate": 0.00035775, "loss": 1.9594, "step": 7155 }, { "epoch": 1.48, "learning_rate": 0.000358, "loss": 1.9495, "step": 7160 }, { "epoch": 1.48, "learning_rate": 0.00035825, "loss": 1.954, "step": 7165 }, { "epoch": 1.49, "learning_rate": 0.0003585, "loss": 1.9537, "step": 7170 }, { "epoch": 1.49, "learning_rate": 0.00035875, "loss": 1.9554, "step": 7175 }, { "epoch": 1.49, "learning_rate": 0.000359, "loss": 1.9539, "step": 7180 }, { "epoch": 1.49, "learning_rate": 0.00035925000000000003, "loss": 1.9554, "step": 7185 }, { "epoch": 1.49, "learning_rate": 0.0003595, "loss": 1.9545, "step": 7190 }, { "epoch": 1.49, "learning_rate": 0.00035975000000000004, "loss": 1.952, "step": 7195 }, { "epoch": 1.49, "learning_rate": 0.00035999999999999997, "loss": 1.9511, "step": 7200 }, { "epoch": 1.49, "learning_rate": 0.00036025, "loss": 1.9508, "step": 7205 }, { "epoch": 1.49, "learning_rate": 0.0003605, "loss": 1.9505, "step": 7210 }, { "epoch": 1.49, "learning_rate": 0.00036075, "loss": 1.9528, "step": 7215 }, { "epoch": 1.5, "learning_rate": 0.000361, "loss": 1.9568, "step": 7220 }, { "epoch": 1.5, "learning_rate": 0.00036125, "loss": 1.9488, "step": 7225 }, { "epoch": 1.5, "learning_rate": 0.0003615, "loss": 1.9519, "step": 7230 }, { "epoch": 1.5, "learning_rate": 0.00036175000000000004, "loss": 1.9535, "step": 7235 }, { "epoch": 1.5, "learning_rate": 0.000362, "loss": 1.9571, "step": 7240 }, { "epoch": 1.5, "learning_rate": 0.00036225000000000005, "loss": 1.9512, "step": 7245 }, { "epoch": 1.5, "learning_rate": 0.0003625, "loss": 1.9516, "step": 7250 }, { "epoch": 1.5, "learning_rate": 0.00036275, "loss": 1.9507, "step": 7255 }, { "epoch": 1.5, "learning_rate": 0.000363, "loss": 1.9534, "step": 7260 }, { "epoch": 1.51, "learning_rate": 0.00036325, "loss": 1.9498, "step": 7265 }, { "epoch": 1.51, "learning_rate": 0.0003635, "loss": 1.9507, "step": 7270 }, { "epoch": 1.51, "learning_rate": 0.00036375000000000003, "loss": 1.9515, "step": 7275 }, { "epoch": 1.51, "learning_rate": 0.000364, "loss": 1.9483, "step": 7280 }, { "epoch": 1.51, "learning_rate": 0.00036425000000000004, "loss": 1.9517, "step": 7285 }, { "epoch": 1.51, "learning_rate": 0.0003645, "loss": 1.9639, "step": 7290 }, { "epoch": 1.51, "learning_rate": 0.00036475, "loss": 1.9684, "step": 7295 }, { "epoch": 1.51, "learning_rate": 0.000365, "loss": 1.9619, "step": 7300 }, { "epoch": 1.51, "learning_rate": 0.00036525, "loss": 1.9557, "step": 7305 }, { "epoch": 1.51, "learning_rate": 0.0003655, "loss": 1.9563, "step": 7310 }, { "epoch": 1.52, "learning_rate": 0.00036575, "loss": 1.9478, "step": 7315 }, { "epoch": 1.52, "learning_rate": 0.000366, "loss": 1.9498, "step": 7320 }, { "epoch": 1.52, "learning_rate": 0.00036625000000000004, "loss": 1.9538, "step": 7325 }, { "epoch": 1.52, "learning_rate": 0.0003665, "loss": 1.9539, "step": 7330 }, { "epoch": 1.52, "learning_rate": 0.00036675000000000005, "loss": 1.9487, "step": 7335 }, { "epoch": 1.52, "learning_rate": 0.000367, "loss": 1.9486, "step": 7340 }, { "epoch": 1.52, "learning_rate": 0.00036725, "loss": 1.9447, "step": 7345 }, { "epoch": 1.52, "learning_rate": 0.0003675, "loss": 1.9461, "step": 7350 }, { "epoch": 1.52, "learning_rate": 0.00036775, "loss": 1.9479, "step": 7355 }, { "epoch": 1.52, "learning_rate": 0.000368, "loss": 1.9539, "step": 7360 }, { "epoch": 1.53, "learning_rate": 0.00036825000000000003, "loss": 1.9596, "step": 7365 }, { "epoch": 1.53, "learning_rate": 0.0003685, "loss": 1.9584, "step": 7370 }, { "epoch": 1.53, "learning_rate": 0.00036875000000000005, "loss": 1.9514, "step": 7375 }, { "epoch": 1.53, "learning_rate": 0.000369, "loss": 1.9546, "step": 7380 }, { "epoch": 1.53, "learning_rate": 0.00036925, "loss": 1.9478, "step": 7385 }, { "epoch": 1.53, "learning_rate": 0.0003695, "loss": 1.9514, "step": 7390 }, { "epoch": 1.53, "learning_rate": 0.00036975, "loss": 1.9524, "step": 7395 }, { "epoch": 1.53, "learning_rate": 0.00037, "loss": 1.9467, "step": 7400 }, { "epoch": 1.53, "learning_rate": 0.00037025000000000003, "loss": 1.9446, "step": 7405 }, { "epoch": 1.54, "learning_rate": 0.0003705, "loss": 1.944, "step": 7410 }, { "epoch": 1.54, "learning_rate": 0.00037075000000000004, "loss": 1.9466, "step": 7415 }, { "epoch": 1.54, "learning_rate": 0.000371, "loss": 1.9533, "step": 7420 }, { "epoch": 1.54, "learning_rate": 0.00037125000000000005, "loss": 1.9494, "step": 7425 }, { "epoch": 1.54, "learning_rate": 0.00037150000000000003, "loss": 1.9471, "step": 7430 }, { "epoch": 1.54, "learning_rate": 0.00037175, "loss": 1.9458, "step": 7435 }, { "epoch": 1.54, "learning_rate": 0.000372, "loss": 1.9455, "step": 7440 }, { "epoch": 1.54, "learning_rate": 0.00037225, "loss": 1.9455, "step": 7445 }, { "epoch": 1.54, "learning_rate": 0.0003725, "loss": 1.9514, "step": 7450 }, { "epoch": 1.54, "learning_rate": 0.00037275000000000003, "loss": 1.9467, "step": 7455 }, { "epoch": 1.55, "learning_rate": 0.000373, "loss": 1.9494, "step": 7460 }, { "epoch": 1.55, "learning_rate": 0.00037325000000000005, "loss": 1.9448, "step": 7465 }, { "epoch": 1.55, "learning_rate": 0.0003735, "loss": 1.9435, "step": 7470 }, { "epoch": 1.55, "learning_rate": 0.00037375000000000006, "loss": 1.9435, "step": 7475 }, { "epoch": 1.55, "learning_rate": 0.000374, "loss": 1.9477, "step": 7480 }, { "epoch": 1.55, "learning_rate": 0.00037425, "loss": 1.9469, "step": 7485 }, { "epoch": 1.55, "learning_rate": 0.0003745, "loss": 1.9431, "step": 7490 }, { "epoch": 1.55, "learning_rate": 0.00037475000000000003, "loss": 1.9496, "step": 7495 }, { "epoch": 1.55, "learning_rate": 0.000375, "loss": 1.9483, "step": 7500 }, { "epoch": 1.55, "learning_rate": 0.00037525, "loss": 1.949, "step": 7505 }, { "epoch": 1.56, "learning_rate": 0.0003755, "loss": 1.9503, "step": 7510 }, { "epoch": 1.56, "learning_rate": 0.00037575, "loss": 1.9441, "step": 7515 }, { "epoch": 1.56, "learning_rate": 0.00037600000000000003, "loss": 1.9466, "step": 7520 }, { "epoch": 1.56, "learning_rate": 0.00037624999999999996, "loss": 1.9413, "step": 7525 }, { "epoch": 1.56, "learning_rate": 0.0003765, "loss": 1.9441, "step": 7530 }, { "epoch": 1.56, "learning_rate": 0.00037674999999999997, "loss": 1.9454, "step": 7535 }, { "epoch": 1.56, "learning_rate": 0.000377, "loss": 1.9412, "step": 7540 }, { "epoch": 1.56, "learning_rate": 0.00037725, "loss": 1.9461, "step": 7545 }, { "epoch": 1.56, "learning_rate": 0.0003775, "loss": 1.9429, "step": 7550 }, { "epoch": 1.57, "learning_rate": 0.00037775, "loss": 1.9497, "step": 7555 }, { "epoch": 1.57, "learning_rate": 0.000378, "loss": 1.9412, "step": 7560 }, { "epoch": 1.57, "learning_rate": 0.00037825, "loss": 1.9419, "step": 7565 }, { "epoch": 1.57, "learning_rate": 0.0003785, "loss": 1.9456, "step": 7570 }, { "epoch": 1.57, "learning_rate": 0.00037874999999999996, "loss": 1.9486, "step": 7575 }, { "epoch": 1.57, "learning_rate": 0.000379, "loss": 1.9443, "step": 7580 }, { "epoch": 1.57, "learning_rate": 0.00037925, "loss": 1.94, "step": 7585 }, { "epoch": 1.57, "learning_rate": 0.0003795, "loss": 1.9413, "step": 7590 }, { "epoch": 1.57, "learning_rate": 0.00037975, "loss": 1.941, "step": 7595 }, { "epoch": 1.57, "learning_rate": 0.00038, "loss": 1.9429, "step": 7600 }, { "epoch": 1.58, "learning_rate": 0.00038025, "loss": 1.9508, "step": 7605 }, { "epoch": 1.58, "learning_rate": 0.00038050000000000003, "loss": 1.9463, "step": 7610 }, { "epoch": 1.58, "learning_rate": 0.00038075, "loss": 1.9484, "step": 7615 }, { "epoch": 1.58, "learning_rate": 0.000381, "loss": 1.9454, "step": 7620 }, { "epoch": 1.58, "learning_rate": 0.00038124999999999997, "loss": 1.9472, "step": 7625 }, { "epoch": 1.58, "learning_rate": 0.0003815, "loss": 1.9438, "step": 7630 }, { "epoch": 1.58, "learning_rate": 0.00038175, "loss": 1.9377, "step": 7635 }, { "epoch": 1.58, "learning_rate": 0.000382, "loss": 1.9428, "step": 7640 }, { "epoch": 1.58, "learning_rate": 0.00038225, "loss": 1.9612, "step": 7645 }, { "epoch": 1.58, "learning_rate": 0.00038250000000000003, "loss": 1.9533, "step": 7650 }, { "epoch": 1.59, "learning_rate": 0.00038275, "loss": 1.9529, "step": 7655 }, { "epoch": 1.59, "learning_rate": 0.00038300000000000004, "loss": 1.9481, "step": 7660 }, { "epoch": 1.59, "learning_rate": 0.00038324999999999996, "loss": 1.9464, "step": 7665 }, { "epoch": 1.59, "learning_rate": 0.0003835, "loss": 1.9441, "step": 7670 }, { "epoch": 1.59, "learning_rate": 0.00038375, "loss": 1.9427, "step": 7675 }, { "epoch": 1.59, "learning_rate": 0.000384, "loss": 1.9482, "step": 7680 }, { "epoch": 1.59, "learning_rate": 0.00038425, "loss": 1.9438, "step": 7685 }, { "epoch": 1.59, "learning_rate": 0.0003845, "loss": 1.9483, "step": 7690 }, { "epoch": 1.59, "learning_rate": 0.00038475, "loss": 1.9359, "step": 7695 }, { "epoch": 1.6, "learning_rate": 0.00038500000000000003, "loss": 1.9402, "step": 7700 }, { "epoch": 1.6, "learning_rate": 0.00038525, "loss": 1.9442, "step": 7705 }, { "epoch": 1.6, "learning_rate": 0.0003855, "loss": 1.9393, "step": 7710 }, { "epoch": 1.6, "learning_rate": 0.00038574999999999997, "loss": 1.9357, "step": 7715 }, { "epoch": 1.6, "learning_rate": 0.000386, "loss": 1.9433, "step": 7720 }, { "epoch": 1.6, "learning_rate": 0.00038625, "loss": 1.9443, "step": 7725 }, { "epoch": 1.6, "learning_rate": 0.0003865, "loss": 1.9381, "step": 7730 }, { "epoch": 1.6, "learning_rate": 0.00038675, "loss": 1.946, "step": 7735 }, { "epoch": 1.6, "learning_rate": 0.00038700000000000003, "loss": 1.9327, "step": 7740 }, { "epoch": 1.6, "learning_rate": 0.00038725, "loss": 1.9335, "step": 7745 }, { "epoch": 1.61, "learning_rate": 0.00038750000000000004, "loss": 1.9409, "step": 7750 }, { "epoch": 1.61, "learning_rate": 0.00038774999999999997, "loss": 1.9366, "step": 7755 }, { "epoch": 1.61, "learning_rate": 0.000388, "loss": 1.9492, "step": 7760 }, { "epoch": 1.61, "learning_rate": 0.00038825, "loss": 1.9421, "step": 7765 }, { "epoch": 1.61, "learning_rate": 0.0003885, "loss": 1.937, "step": 7770 }, { "epoch": 1.61, "learning_rate": 0.00038875, "loss": 1.935, "step": 7775 }, { "epoch": 1.61, "learning_rate": 0.000389, "loss": 1.9395, "step": 7780 }, { "epoch": 1.61, "learning_rate": 0.00038925, "loss": 1.9416, "step": 7785 }, { "epoch": 1.61, "learning_rate": 0.00038950000000000003, "loss": 1.9371, "step": 7790 }, { "epoch": 1.61, "learning_rate": 0.00038975, "loss": 1.9449, "step": 7795 }, { "epoch": 1.62, "learning_rate": 0.00039000000000000005, "loss": 1.9406, "step": 7800 }, { "epoch": 1.62, "learning_rate": 0.00039024999999999997, "loss": 1.9476, "step": 7805 }, { "epoch": 1.62, "learning_rate": 0.0003905, "loss": 1.9472, "step": 7810 }, { "epoch": 1.62, "learning_rate": 0.00039075, "loss": 1.9359, "step": 7815 }, { "epoch": 1.62, "learning_rate": 0.000391, "loss": 1.9374, "step": 7820 }, { "epoch": 1.62, "learning_rate": 0.00039125, "loss": 1.9423, "step": 7825 }, { "epoch": 1.62, "learning_rate": 0.00039150000000000003, "loss": 1.9416, "step": 7830 }, { "epoch": 1.62, "learning_rate": 0.00039175, "loss": 1.9372, "step": 7835 }, { "epoch": 1.62, "learning_rate": 0.00039200000000000004, "loss": 1.9414, "step": 7840 }, { "epoch": 1.63, "learning_rate": 0.00039225, "loss": 1.9373, "step": 7845 }, { "epoch": 1.63, "learning_rate": 0.0003925, "loss": 1.94, "step": 7850 }, { "epoch": 1.63, "learning_rate": 0.00039275, "loss": 1.9335, "step": 7855 }, { "epoch": 1.63, "learning_rate": 0.000393, "loss": 1.9466, "step": 7860 }, { "epoch": 1.63, "learning_rate": 0.00039325, "loss": 1.9396, "step": 7865 }, { "epoch": 1.63, "learning_rate": 0.0003935, "loss": 1.9418, "step": 7870 }, { "epoch": 1.63, "learning_rate": 0.00039375, "loss": 1.9417, "step": 7875 }, { "epoch": 1.63, "learning_rate": 0.00039400000000000004, "loss": 1.9402, "step": 7880 }, { "epoch": 1.63, "learning_rate": 0.00039425, "loss": 1.9386, "step": 7885 }, { "epoch": 1.63, "learning_rate": 0.00039450000000000005, "loss": 1.9333, "step": 7890 }, { "epoch": 1.64, "learning_rate": 0.00039474999999999997, "loss": 1.9371, "step": 7895 }, { "epoch": 1.64, "learning_rate": 0.000395, "loss": 1.9361, "step": 7900 }, { "epoch": 1.64, "learning_rate": 0.00039525, "loss": 1.9428, "step": 7905 }, { "epoch": 1.64, "learning_rate": 0.0003955, "loss": 1.9372, "step": 7910 }, { "epoch": 1.64, "learning_rate": 0.00039575, "loss": 1.94, "step": 7915 }, { "epoch": 1.64, "learning_rate": 0.00039600000000000003, "loss": 1.939, "step": 7920 }, { "epoch": 1.64, "learning_rate": 0.00039625, "loss": 1.9378, "step": 7925 }, { "epoch": 1.64, "learning_rate": 0.00039650000000000004, "loss": 1.9364, "step": 7930 }, { "epoch": 1.64, "learning_rate": 0.00039675, "loss": 1.9483, "step": 7935 }, { "epoch": 1.64, "learning_rate": 0.00039700000000000005, "loss": 1.9496, "step": 7940 }, { "epoch": 1.65, "learning_rate": 0.00039725, "loss": 1.9462, "step": 7945 }, { "epoch": 1.65, "learning_rate": 0.0003975, "loss": 1.9427, "step": 7950 }, { "epoch": 1.65, "learning_rate": 0.00039775, "loss": 1.9393, "step": 7955 }, { "epoch": 1.65, "learning_rate": 0.000398, "loss": 1.9378, "step": 7960 }, { "epoch": 1.65, "learning_rate": 0.00039825, "loss": 1.9382, "step": 7965 }, { "epoch": 1.65, "learning_rate": 0.00039850000000000004, "loss": 1.945, "step": 7970 }, { "epoch": 1.65, "learning_rate": 0.00039875, "loss": 1.9324, "step": 7975 }, { "epoch": 1.65, "learning_rate": 0.00039900000000000005, "loss": 1.9366, "step": 7980 }, { "epoch": 1.65, "learning_rate": 0.00039925000000000003, "loss": 1.9384, "step": 7985 }, { "epoch": 1.66, "learning_rate": 0.0003995, "loss": 1.9438, "step": 7990 }, { "epoch": 1.66, "learning_rate": 0.00039975, "loss": 1.9387, "step": 7995 }, { "epoch": 1.66, "learning_rate": 0.0004, "loss": 1.9411, "step": 8000 }, { "epoch": 1.66, "learning_rate": 0.00040025, "loss": 1.9299, "step": 8005 }, { "epoch": 1.66, "learning_rate": 0.00040050000000000003, "loss": 1.941, "step": 8010 }, { "epoch": 1.66, "learning_rate": 0.00040075, "loss": 1.9358, "step": 8015 }, { "epoch": 1.66, "learning_rate": 0.00040100000000000004, "loss": 1.9357, "step": 8020 }, { "epoch": 1.66, "learning_rate": 0.00040125, "loss": 1.9437, "step": 8025 }, { "epoch": 1.66, "learning_rate": 0.00040150000000000006, "loss": 1.9363, "step": 8030 }, { "epoch": 1.66, "learning_rate": 0.00040175, "loss": 1.9347, "step": 8035 }, { "epoch": 1.67, "learning_rate": 0.000402, "loss": 1.9404, "step": 8040 }, { "epoch": 1.67, "learning_rate": 0.00040225, "loss": 1.9358, "step": 8045 }, { "epoch": 1.67, "learning_rate": 0.0004025, "loss": 1.9391, "step": 8050 }, { "epoch": 1.67, "learning_rate": 0.00040275, "loss": 1.9312, "step": 8055 }, { "epoch": 1.67, "learning_rate": 0.00040300000000000004, "loss": 1.9394, "step": 8060 }, { "epoch": 1.67, "learning_rate": 0.00040325, "loss": 1.9352, "step": 8065 }, { "epoch": 1.67, "learning_rate": 0.00040350000000000005, "loss": 1.9375, "step": 8070 }, { "epoch": 1.67, "learning_rate": 0.00040375000000000003, "loss": 1.937, "step": 8075 }, { "epoch": 1.67, "learning_rate": 0.000404, "loss": 1.9378, "step": 8080 }, { "epoch": 1.67, "learning_rate": 0.00040425, "loss": 1.9382, "step": 8085 }, { "epoch": 1.68, "learning_rate": 0.0004045, "loss": 1.9389, "step": 8090 }, { "epoch": 1.68, "learning_rate": 0.00040475, "loss": 1.9377, "step": 8095 }, { "epoch": 1.68, "learning_rate": 0.00040500000000000003, "loss": 1.9318, "step": 8100 }, { "epoch": 1.68, "learning_rate": 0.00040525, "loss": 1.9286, "step": 8105 }, { "epoch": 1.68, "learning_rate": 0.00040550000000000004, "loss": 1.9371, "step": 8110 }, { "epoch": 1.68, "learning_rate": 0.00040575, "loss": 1.9347, "step": 8115 }, { "epoch": 1.68, "learning_rate": 0.00040600000000000006, "loss": 1.9329, "step": 8120 }, { "epoch": 1.68, "learning_rate": 0.00040625000000000004, "loss": 1.9354, "step": 8125 }, { "epoch": 1.68, "learning_rate": 0.00040649999999999996, "loss": 1.9318, "step": 8130 }, { "epoch": 1.69, "learning_rate": 0.00040675, "loss": 1.9313, "step": 8135 }, { "epoch": 1.69, "learning_rate": 0.00040699999999999997, "loss": 1.9352, "step": 8140 }, { "epoch": 1.69, "learning_rate": 0.00040725, "loss": 1.9337, "step": 8145 }, { "epoch": 1.69, "learning_rate": 0.0004075, "loss": 1.9361, "step": 8150 }, { "epoch": 1.69, "learning_rate": 0.00040775, "loss": 1.933, "step": 8155 }, { "epoch": 1.69, "learning_rate": 0.000408, "loss": 1.9363, "step": 8160 }, { "epoch": 1.69, "learning_rate": 0.00040825000000000003, "loss": 1.931, "step": 8165 }, { "epoch": 1.69, "learning_rate": 0.0004085, "loss": 1.9285, "step": 8170 }, { "epoch": 1.69, "learning_rate": 0.00040875, "loss": 1.9439, "step": 8175 }, { "epoch": 1.69, "learning_rate": 0.00040899999999999997, "loss": 1.9312, "step": 8180 }, { "epoch": 1.7, "learning_rate": 0.00040925, "loss": 1.9317, "step": 8185 }, { "epoch": 1.7, "learning_rate": 0.0004095, "loss": 1.9331, "step": 8190 }, { "epoch": 1.7, "learning_rate": 0.00040975, "loss": 1.9344, "step": 8195 }, { "epoch": 1.7, "learning_rate": 0.00041, "loss": 1.94, "step": 8200 }, { "epoch": 1.7, "learning_rate": 0.00041025, "loss": 1.9342, "step": 8205 }, { "epoch": 1.7, "learning_rate": 0.0004105, "loss": 1.9318, "step": 8210 }, { "epoch": 1.7, "learning_rate": 0.00041075000000000004, "loss": 1.9381, "step": 8215 }, { "epoch": 1.7, "learning_rate": 0.00041099999999999996, "loss": 1.9317, "step": 8220 }, { "epoch": 1.7, "learning_rate": 0.00041125, "loss": 1.9325, "step": 8225 }, { "epoch": 1.7, "learning_rate": 0.0004115, "loss": 1.9289, "step": 8230 }, { "epoch": 1.71, "learning_rate": 0.00041175, "loss": 1.93, "step": 8235 }, { "epoch": 1.71, "learning_rate": 0.000412, "loss": 1.9372, "step": 8240 }, { "epoch": 1.71, "learning_rate": 0.00041225, "loss": 1.9337, "step": 8245 }, { "epoch": 1.71, "learning_rate": 0.0004125, "loss": 1.9389, "step": 8250 }, { "epoch": 1.71, "learning_rate": 0.00041275000000000003, "loss": 1.9318, "step": 8255 }, { "epoch": 1.71, "learning_rate": 0.000413, "loss": 1.9244, "step": 8260 }, { "epoch": 1.71, "learning_rate": 0.00041325, "loss": 1.926, "step": 8265 }, { "epoch": 1.71, "learning_rate": 0.00041349999999999997, "loss": 1.9372, "step": 8270 }, { "epoch": 1.71, "learning_rate": 0.00041375, "loss": 1.9325, "step": 8275 }, { "epoch": 1.72, "learning_rate": 0.000414, "loss": 1.9335, "step": 8280 }, { "epoch": 1.72, "learning_rate": 0.00041425, "loss": 1.9288, "step": 8285 }, { "epoch": 1.72, "learning_rate": 0.0004145, "loss": 1.9257, "step": 8290 }, { "epoch": 1.72, "learning_rate": 0.00041475, "loss": 1.9329, "step": 8295 }, { "epoch": 1.72, "learning_rate": 0.000415, "loss": 1.933, "step": 8300 }, { "epoch": 1.72, "learning_rate": 0.00041525000000000004, "loss": 1.929, "step": 8305 }, { "epoch": 1.72, "learning_rate": 0.00041549999999999996, "loss": 1.9283, "step": 8310 }, { "epoch": 1.72, "learning_rate": 0.00041575, "loss": 1.9286, "step": 8315 }, { "epoch": 1.72, "learning_rate": 0.000416, "loss": 1.933, "step": 8320 }, { "epoch": 1.72, "learning_rate": 0.00041625, "loss": 1.9223, "step": 8325 }, { "epoch": 1.73, "learning_rate": 0.0004165, "loss": 1.9414, "step": 8330 }, { "epoch": 1.73, "learning_rate": 0.00041675, "loss": 1.9362, "step": 8335 }, { "epoch": 1.73, "learning_rate": 0.000417, "loss": 1.9331, "step": 8340 }, { "epoch": 1.73, "learning_rate": 0.00041725000000000003, "loss": 1.9367, "step": 8345 }, { "epoch": 1.73, "learning_rate": 0.0004175, "loss": 1.9349, "step": 8350 }, { "epoch": 1.73, "learning_rate": 0.00041775000000000004, "loss": 1.9275, "step": 8355 }, { "epoch": 1.73, "learning_rate": 0.00041799999999999997, "loss": 1.9325, "step": 8360 }, { "epoch": 1.73, "learning_rate": 0.00041825, "loss": 1.9283, "step": 8365 }, { "epoch": 1.73, "learning_rate": 0.0004185, "loss": 1.9297, "step": 8370 }, { "epoch": 1.74, "learning_rate": 0.00041875, "loss": 1.9263, "step": 8375 }, { "epoch": 1.74, "learning_rate": 0.000419, "loss": 1.9354, "step": 8380 }, { "epoch": 1.74, "learning_rate": 0.00041925, "loss": 1.9344, "step": 8385 }, { "epoch": 1.74, "learning_rate": 0.0004195, "loss": 1.9283, "step": 8390 }, { "epoch": 1.74, "learning_rate": 0.00041975000000000004, "loss": 1.9233, "step": 8395 }, { "epoch": 1.74, "learning_rate": 0.00042, "loss": 1.9291, "step": 8400 }, { "epoch": 1.74, "learning_rate": 0.00042025, "loss": 1.9344, "step": 8405 }, { "epoch": 1.74, "learning_rate": 0.0004205, "loss": 1.9277, "step": 8410 }, { "epoch": 1.74, "learning_rate": 0.00042075, "loss": 1.9273, "step": 8415 }, { "epoch": 1.74, "learning_rate": 0.000421, "loss": 1.9302, "step": 8420 }, { "epoch": 1.75, "learning_rate": 0.00042125, "loss": 1.9321, "step": 8425 }, { "epoch": 1.75, "learning_rate": 0.0004215, "loss": 1.9302, "step": 8430 }, { "epoch": 1.75, "learning_rate": 0.00042175000000000003, "loss": 1.9306, "step": 8435 }, { "epoch": 1.75, "learning_rate": 0.000422, "loss": 1.9279, "step": 8440 }, { "epoch": 1.75, "learning_rate": 0.00042225000000000005, "loss": 1.9303, "step": 8445 }, { "epoch": 1.75, "learning_rate": 0.00042249999999999997, "loss": 1.9259, "step": 8450 }, { "epoch": 1.75, "learning_rate": 0.00042275, "loss": 1.9248, "step": 8455 }, { "epoch": 1.75, "learning_rate": 0.000423, "loss": 1.9337, "step": 8460 }, { "epoch": 1.75, "learning_rate": 0.00042325, "loss": 1.9279, "step": 8465 }, { "epoch": 1.75, "learning_rate": 0.0004235, "loss": 1.931, "step": 8470 }, { "epoch": 1.76, "learning_rate": 0.00042375000000000003, "loss": 1.9288, "step": 8475 }, { "epoch": 1.76, "learning_rate": 0.000424, "loss": 1.9316, "step": 8480 }, { "epoch": 1.76, "learning_rate": 0.00042425000000000004, "loss": 1.9273, "step": 8485 }, { "epoch": 1.76, "learning_rate": 0.0004245, "loss": 1.9265, "step": 8490 }, { "epoch": 1.76, "learning_rate": 0.00042475000000000005, "loss": 1.9224, "step": 8495 }, { "epoch": 1.76, "learning_rate": 0.000425, "loss": 1.9295, "step": 8500 }, { "epoch": 1.76, "learning_rate": 0.00042525, "loss": 1.9283, "step": 8505 }, { "epoch": 1.76, "learning_rate": 0.0004255, "loss": 1.9305, "step": 8510 }, { "epoch": 1.76, "learning_rate": 0.00042575, "loss": 1.9278, "step": 8515 }, { "epoch": 1.77, "learning_rate": 0.000426, "loss": 1.9242, "step": 8520 }, { "epoch": 1.77, "learning_rate": 0.00042625000000000003, "loss": 1.943, "step": 8525 }, { "epoch": 1.77, "learning_rate": 0.0004265, "loss": 1.933, "step": 8530 }, { "epoch": 1.77, "learning_rate": 0.00042675000000000005, "loss": 1.9275, "step": 8535 }, { "epoch": 1.77, "learning_rate": 0.000427, "loss": 1.928, "step": 8540 }, { "epoch": 1.77, "learning_rate": 0.00042725, "loss": 1.9295, "step": 8545 }, { "epoch": 1.77, "learning_rate": 0.0004275, "loss": 1.9282, "step": 8550 }, { "epoch": 1.77, "learning_rate": 0.00042775, "loss": 1.9258, "step": 8555 }, { "epoch": 1.77, "learning_rate": 0.000428, "loss": 1.9246, "step": 8560 }, { "epoch": 1.77, "learning_rate": 0.00042825000000000003, "loss": 1.9295, "step": 8565 }, { "epoch": 1.78, "learning_rate": 0.0004285, "loss": 1.9258, "step": 8570 }, { "epoch": 1.78, "learning_rate": 0.00042875000000000004, "loss": 1.929, "step": 8575 }, { "epoch": 1.78, "learning_rate": 0.000429, "loss": 1.9278, "step": 8580 }, { "epoch": 1.78, "learning_rate": 0.00042925000000000005, "loss": 1.9247, "step": 8585 }, { "epoch": 1.78, "learning_rate": 0.0004295, "loss": 1.9222, "step": 8590 }, { "epoch": 1.78, "learning_rate": 0.00042975, "loss": 1.9336, "step": 8595 }, { "epoch": 1.78, "learning_rate": 0.00043, "loss": 1.9354, "step": 8600 }, { "epoch": 1.78, "learning_rate": 0.00043025, "loss": 1.9299, "step": 8605 }, { "epoch": 1.78, "learning_rate": 0.0004305, "loss": 1.9295, "step": 8610 }, { "epoch": 1.78, "learning_rate": 0.00043075000000000003, "loss": 1.9255, "step": 8615 }, { "epoch": 1.79, "learning_rate": 0.000431, "loss": 1.9316, "step": 8620 }, { "epoch": 1.79, "learning_rate": 0.00043125000000000005, "loss": 1.9198, "step": 8625 }, { "epoch": 1.79, "learning_rate": 0.0004315, "loss": 1.9253, "step": 8630 }, { "epoch": 1.79, "learning_rate": 0.00043175, "loss": 1.931, "step": 8635 }, { "epoch": 1.79, "learning_rate": 0.000432, "loss": 1.9302, "step": 8640 }, { "epoch": 1.79, "learning_rate": 0.00043225, "loss": 1.9324, "step": 8645 }, { "epoch": 1.79, "learning_rate": 0.0004325, "loss": 1.9245, "step": 8650 }, { "epoch": 1.79, "learning_rate": 0.00043275000000000003, "loss": 1.9186, "step": 8655 }, { "epoch": 1.79, "learning_rate": 0.000433, "loss": 1.9253, "step": 8660 }, { "epoch": 1.8, "learning_rate": 0.00043325000000000004, "loss": 1.9248, "step": 8665 }, { "epoch": 1.8, "learning_rate": 0.0004335, "loss": 1.9218, "step": 8670 }, { "epoch": 1.8, "learning_rate": 0.00043375000000000005, "loss": 1.9271, "step": 8675 }, { "epoch": 1.8, "learning_rate": 0.00043400000000000003, "loss": 1.9256, "step": 8680 }, { "epoch": 1.8, "learning_rate": 0.00043425, "loss": 1.9299, "step": 8685 }, { "epoch": 1.8, "learning_rate": 0.0004345, "loss": 1.9275, "step": 8690 }, { "epoch": 1.8, "learning_rate": 0.00043475, "loss": 1.9226, "step": 8695 }, { "epoch": 1.8, "learning_rate": 0.000435, "loss": 1.926, "step": 8700 }, { "epoch": 1.8, "learning_rate": 0.00043525000000000004, "loss": 1.9292, "step": 8705 }, { "epoch": 1.8, "learning_rate": 0.0004355, "loss": 1.9235, "step": 8710 }, { "epoch": 1.81, "learning_rate": 0.00043575000000000005, "loss": 1.9228, "step": 8715 }, { "epoch": 1.81, "learning_rate": 0.000436, "loss": 1.9221, "step": 8720 }, { "epoch": 1.81, "learning_rate": 0.00043625000000000006, "loss": 1.9283, "step": 8725 }, { "epoch": 1.81, "learning_rate": 0.0004365, "loss": 1.9234, "step": 8730 }, { "epoch": 1.81, "learning_rate": 0.00043675, "loss": 1.9248, "step": 8735 }, { "epoch": 1.81, "learning_rate": 0.000437, "loss": 1.9251, "step": 8740 }, { "epoch": 1.81, "learning_rate": 0.00043725000000000003, "loss": 1.9217, "step": 8745 }, { "epoch": 1.81, "learning_rate": 0.0004375, "loss": 1.9221, "step": 8750 }, { "epoch": 1.81, "learning_rate": 0.00043775, "loss": 1.9205, "step": 8755 }, { "epoch": 1.81, "learning_rate": 0.000438, "loss": 1.9319, "step": 8760 }, { "epoch": 1.82, "learning_rate": 0.00043825, "loss": 1.9272, "step": 8765 }, { "epoch": 1.82, "learning_rate": 0.00043850000000000003, "loss": 1.9281, "step": 8770 }, { "epoch": 1.82, "learning_rate": 0.00043874999999999996, "loss": 1.9254, "step": 8775 }, { "epoch": 1.82, "learning_rate": 0.000439, "loss": 1.9259, "step": 8780 }, { "epoch": 1.82, "learning_rate": 0.00043924999999999997, "loss": 1.9212, "step": 8785 }, { "epoch": 1.82, "learning_rate": 0.0004395, "loss": 1.9192, "step": 8790 }, { "epoch": 1.82, "learning_rate": 0.00043975, "loss": 1.9203, "step": 8795 }, { "epoch": 1.82, "learning_rate": 0.00044, "loss": 1.923, "step": 8800 }, { "epoch": 1.82, "learning_rate": 0.00044025, "loss": 1.9215, "step": 8805 }, { "epoch": 1.83, "learning_rate": 0.00044050000000000003, "loss": 1.9221, "step": 8810 }, { "epoch": 1.83, "learning_rate": 0.00044075, "loss": 1.925, "step": 8815 }, { "epoch": 1.83, "learning_rate": 0.000441, "loss": 1.9259, "step": 8820 }, { "epoch": 1.83, "learning_rate": 0.00044124999999999996, "loss": 1.9174, "step": 8825 }, { "epoch": 1.83, "learning_rate": 0.0004415, "loss": 1.925, "step": 8830 }, { "epoch": 1.83, "learning_rate": 0.00044175, "loss": 1.9191, "step": 8835 }, { "epoch": 1.83, "learning_rate": 0.000442, "loss": 1.9198, "step": 8840 }, { "epoch": 1.83, "learning_rate": 0.00044225, "loss": 1.9202, "step": 8845 }, { "epoch": 1.83, "learning_rate": 0.0004425, "loss": 1.921, "step": 8850 }, { "epoch": 1.83, "learning_rate": 0.00044275, "loss": 1.9274, "step": 8855 }, { "epoch": 1.84, "learning_rate": 0.00044300000000000003, "loss": 1.9263, "step": 8860 }, { "epoch": 1.84, "learning_rate": 0.00044325, "loss": 1.9262, "step": 8865 }, { "epoch": 1.84, "learning_rate": 0.0004435, "loss": 1.9237, "step": 8870 }, { "epoch": 1.84, "learning_rate": 0.00044374999999999997, "loss": 1.9253, "step": 8875 }, { "epoch": 1.84, "learning_rate": 0.000444, "loss": 1.9251, "step": 8880 }, { "epoch": 1.84, "learning_rate": 0.00044425, "loss": 1.9198, "step": 8885 }, { "epoch": 1.84, "learning_rate": 0.0004445, "loss": 1.9183, "step": 8890 }, { "epoch": 1.84, "learning_rate": 0.00044475, "loss": 1.9262, "step": 8895 }, { "epoch": 1.84, "learning_rate": 0.00044500000000000003, "loss": 1.9201, "step": 8900 }, { "epoch": 1.84, "learning_rate": 0.00044525, "loss": 1.9258, "step": 8905 }, { "epoch": 1.85, "learning_rate": 0.00044550000000000004, "loss": 1.9268, "step": 8910 }, { "epoch": 1.85, "learning_rate": 0.00044574999999999997, "loss": 1.9281, "step": 8915 }, { "epoch": 1.85, "learning_rate": 0.000446, "loss": 1.9235, "step": 8920 }, { "epoch": 1.85, "learning_rate": 0.00044625, "loss": 1.9257, "step": 8925 }, { "epoch": 1.85, "learning_rate": 0.0004465, "loss": 1.9247, "step": 8930 }, { "epoch": 1.85, "learning_rate": 0.00044675, "loss": 1.9187, "step": 8935 }, { "epoch": 1.85, "learning_rate": 0.000447, "loss": 1.924, "step": 8940 }, { "epoch": 1.85, "learning_rate": 0.00044725, "loss": 1.9225, "step": 8945 }, { "epoch": 1.85, "learning_rate": 0.00044750000000000004, "loss": 1.9202, "step": 8950 }, { "epoch": 1.86, "learning_rate": 0.00044775, "loss": 1.9179, "step": 8955 }, { "epoch": 1.86, "learning_rate": 0.000448, "loss": 1.9227, "step": 8960 }, { "epoch": 1.86, "learning_rate": 0.00044824999999999997, "loss": 1.9242, "step": 8965 }, { "epoch": 1.86, "learning_rate": 0.0004485, "loss": 1.924, "step": 8970 }, { "epoch": 1.86, "learning_rate": 0.00044875, "loss": 1.9137, "step": 8975 }, { "epoch": 1.86, "learning_rate": 0.000449, "loss": 1.9145, "step": 8980 }, { "epoch": 1.86, "learning_rate": 0.00044925, "loss": 1.9205, "step": 8985 }, { "epoch": 1.86, "learning_rate": 0.00044950000000000003, "loss": 1.923, "step": 8990 }, { "epoch": 1.86, "learning_rate": 0.00044975, "loss": 1.9183, "step": 8995 }, { "epoch": 1.86, "learning_rate": 0.00045000000000000004, "loss": 1.9185, "step": 9000 }, { "epoch": 1.86, "eval_accuracy": 0.5088627450980392, "eval_loss": 2.1189281940460205, "eval_runtime": 0.9498, "eval_samples_per_second": 157.929, "eval_steps_per_second": 1.053, "step": 9000 }, { "epoch": 1.87, "learning_rate": 0.00045024999999999997, "loss": 1.9171, "step": 9005 }, { "epoch": 1.87, "learning_rate": 0.0004505, "loss": 1.918, "step": 9010 }, { "epoch": 1.87, "learning_rate": 0.00045075, "loss": 1.9292, "step": 9015 }, { "epoch": 1.87, "learning_rate": 0.000451, "loss": 1.9153, "step": 9020 }, { "epoch": 1.87, "learning_rate": 0.00045125, "loss": 1.9185, "step": 9025 }, { "epoch": 1.87, "learning_rate": 0.0004515, "loss": 1.9124, "step": 9030 }, { "epoch": 1.87, "learning_rate": 0.00045175, "loss": 1.922, "step": 9035 }, { "epoch": 1.87, "learning_rate": 0.00045200000000000004, "loss": 1.9167, "step": 9040 }, { "epoch": 1.87, "learning_rate": 0.00045225, "loss": 1.9192, "step": 9045 }, { "epoch": 1.87, "learning_rate": 0.00045250000000000005, "loss": 1.9195, "step": 9050 }, { "epoch": 1.88, "learning_rate": 0.00045275, "loss": 1.9183, "step": 9055 }, { "epoch": 1.88, "learning_rate": 0.000453, "loss": 1.9319, "step": 9060 }, { "epoch": 1.88, "learning_rate": 0.00045325, "loss": 1.9279, "step": 9065 }, { "epoch": 1.88, "learning_rate": 0.0004535, "loss": 1.9287, "step": 9070 }, { "epoch": 1.88, "learning_rate": 0.00045375, "loss": 1.923, "step": 9075 }, { "epoch": 1.88, "learning_rate": 0.00045400000000000003, "loss": 1.9177, "step": 9080 }, { "epoch": 1.88, "learning_rate": 0.00045425, "loss": 1.9147, "step": 9085 }, { "epoch": 1.88, "learning_rate": 0.00045450000000000004, "loss": 1.9139, "step": 9090 }, { "epoch": 1.88, "learning_rate": 0.00045475, "loss": 1.9218, "step": 9095 }, { "epoch": 1.89, "learning_rate": 0.000455, "loss": 1.9142, "step": 9100 }, { "epoch": 1.89, "learning_rate": 0.00045525, "loss": 1.9242, "step": 9105 }, { "epoch": 1.89, "learning_rate": 0.0004555, "loss": 1.9163, "step": 9110 }, { "epoch": 1.89, "learning_rate": 0.00045575, "loss": 1.9218, "step": 9115 }, { "epoch": 1.89, "learning_rate": 0.000456, "loss": 1.9165, "step": 9120 }, { "epoch": 1.89, "learning_rate": 0.00045625, "loss": 1.9161, "step": 9125 }, { "epoch": 1.89, "learning_rate": 0.00045650000000000004, "loss": 1.9157, "step": 9130 }, { "epoch": 1.89, "learning_rate": 0.00045675, "loss": 1.9185, "step": 9135 }, { "epoch": 1.89, "learning_rate": 0.00045700000000000005, "loss": 1.9144, "step": 9140 }, { "epoch": 1.89, "learning_rate": 0.00045725, "loss": 1.9182, "step": 9145 }, { "epoch": 1.9, "learning_rate": 0.0004575, "loss": 1.9241, "step": 9150 }, { "epoch": 1.9, "learning_rate": 0.00045775, "loss": 1.9132, "step": 9155 }, { "epoch": 1.9, "learning_rate": 0.000458, "loss": 1.9196, "step": 9160 }, { "epoch": 1.9, "learning_rate": 0.00045825, "loss": 1.9191, "step": 9165 }, { "epoch": 1.9, "learning_rate": 0.00045850000000000003, "loss": 1.9216, "step": 9170 }, { "epoch": 1.9, "learning_rate": 0.00045875, "loss": 1.921, "step": 9175 }, { "epoch": 1.9, "learning_rate": 0.00045900000000000004, "loss": 1.9159, "step": 9180 }, { "epoch": 1.9, "learning_rate": 0.00045925, "loss": 1.9104, "step": 9185 }, { "epoch": 1.9, "learning_rate": 0.00045950000000000006, "loss": 1.921, "step": 9190 }, { "epoch": 1.9, "learning_rate": 0.00045975, "loss": 1.9165, "step": 9195 }, { "epoch": 1.91, "learning_rate": 0.00046, "loss": 1.9154, "step": 9200 }, { "epoch": 1.91, "learning_rate": 0.00046025, "loss": 1.9165, "step": 9205 }, { "epoch": 1.91, "learning_rate": 0.0004605, "loss": 1.9272, "step": 9210 }, { "epoch": 1.91, "learning_rate": 0.00046075, "loss": 1.9197, "step": 9215 }, { "epoch": 1.91, "learning_rate": 0.00046100000000000004, "loss": 1.916, "step": 9220 }, { "epoch": 1.91, "learning_rate": 0.00046125, "loss": 1.9167, "step": 9225 }, { "epoch": 1.91, "learning_rate": 0.00046150000000000005, "loss": 1.9167, "step": 9230 }, { "epoch": 1.91, "learning_rate": 0.00046175000000000003, "loss": 1.9224, "step": 9235 }, { "epoch": 1.91, "learning_rate": 0.000462, "loss": 1.9222, "step": 9240 }, { "epoch": 1.92, "learning_rate": 0.00046225, "loss": 1.9179, "step": 9245 }, { "epoch": 1.92, "learning_rate": 0.0004625, "loss": 1.9173, "step": 9250 }, { "epoch": 1.92, "learning_rate": 0.00046275, "loss": 1.9115, "step": 9255 }, { "epoch": 1.92, "learning_rate": 0.00046300000000000003, "loss": 1.916, "step": 9260 }, { "epoch": 1.92, "learning_rate": 0.00046325, "loss": 1.9191, "step": 9265 }, { "epoch": 1.92, "learning_rate": 0.00046350000000000004, "loss": 1.9153, "step": 9270 }, { "epoch": 1.92, "learning_rate": 0.00046375, "loss": 1.9144, "step": 9275 }, { "epoch": 1.92, "learning_rate": 0.00046400000000000006, "loss": 1.9219, "step": 9280 }, { "epoch": 1.92, "learning_rate": 0.00046425, "loss": 1.9137, "step": 9285 }, { "epoch": 1.92, "learning_rate": 0.0004645, "loss": 1.9133, "step": 9290 }, { "epoch": 1.93, "learning_rate": 0.00046475, "loss": 1.9168, "step": 9295 }, { "epoch": 1.93, "learning_rate": 0.000465, "loss": 1.9164, "step": 9300 }, { "epoch": 1.93, "learning_rate": 0.00046525, "loss": 1.9073, "step": 9305 }, { "epoch": 1.93, "learning_rate": 0.00046550000000000004, "loss": 1.9236, "step": 9310 }, { "epoch": 1.93, "learning_rate": 0.00046575, "loss": 1.9229, "step": 9315 }, { "epoch": 1.93, "learning_rate": 0.00046600000000000005, "loss": 1.9177, "step": 9320 }, { "epoch": 1.93, "learning_rate": 0.00046625000000000003, "loss": 1.9171, "step": 9325 }, { "epoch": 1.93, "learning_rate": 0.0004665, "loss": 1.9157, "step": 9330 }, { "epoch": 1.93, "learning_rate": 0.00046675, "loss": 1.9186, "step": 9335 }, { "epoch": 1.93, "learning_rate": 0.000467, "loss": 1.9206, "step": 9340 }, { "epoch": 1.94, "learning_rate": 0.00046725, "loss": 1.9191, "step": 9345 }, { "epoch": 1.94, "learning_rate": 0.00046750000000000003, "loss": 1.9178, "step": 9350 }, { "epoch": 1.94, "learning_rate": 0.00046775, "loss": 1.9181, "step": 9355 }, { "epoch": 1.94, "learning_rate": 0.00046800000000000005, "loss": 1.9198, "step": 9360 }, { "epoch": 1.94, "learning_rate": 0.00046825, "loss": 1.9188, "step": 9365 }, { "epoch": 1.94, "learning_rate": 0.00046850000000000006, "loss": 1.9113, "step": 9370 }, { "epoch": 1.94, "learning_rate": 0.00046875, "loss": 1.9128, "step": 9375 }, { "epoch": 1.94, "learning_rate": 0.00046899999999999996, "loss": 1.917, "step": 9380 }, { "epoch": 1.94, "learning_rate": 0.00046925, "loss": 1.9165, "step": 9385 }, { "epoch": 1.95, "learning_rate": 0.0004695, "loss": 1.916, "step": 9390 }, { "epoch": 1.95, "learning_rate": 0.00046975, "loss": 1.9194, "step": 9395 }, { "epoch": 1.95, "learning_rate": 0.00047, "loss": 1.9123, "step": 9400 }, { "epoch": 1.95, "learning_rate": 0.00047025, "loss": 1.9177, "step": 9405 }, { "epoch": 1.95, "learning_rate": 0.0004705, "loss": 1.915, "step": 9410 }, { "epoch": 1.95, "learning_rate": 0.00047075000000000003, "loss": 1.9092, "step": 9415 }, { "epoch": 1.95, "learning_rate": 0.000471, "loss": 1.911, "step": 9420 }, { "epoch": 1.95, "learning_rate": 0.00047125, "loss": 1.9118, "step": 9425 }, { "epoch": 1.95, "learning_rate": 0.00047149999999999997, "loss": 1.9124, "step": 9430 }, { "epoch": 1.95, "learning_rate": 0.00047175, "loss": 1.9096, "step": 9435 }, { "epoch": 1.96, "learning_rate": 0.000472, "loss": 1.9207, "step": 9440 }, { "epoch": 1.96, "learning_rate": 0.00047225, "loss": 1.9222, "step": 9445 }, { "epoch": 1.96, "learning_rate": 0.0004725, "loss": 1.9156, "step": 9450 }, { "epoch": 1.96, "learning_rate": 0.00047275, "loss": 1.917, "step": 9455 }, { "epoch": 1.96, "learning_rate": 0.000473, "loss": 1.9198, "step": 9460 }, { "epoch": 1.96, "learning_rate": 0.00047325000000000004, "loss": 1.9139, "step": 9465 }, { "epoch": 1.96, "learning_rate": 0.00047349999999999996, "loss": 1.9154, "step": 9470 }, { "epoch": 1.96, "learning_rate": 0.00047375, "loss": 1.9151, "step": 9475 }, { "epoch": 1.96, "learning_rate": 0.000474, "loss": 1.9123, "step": 9480 }, { "epoch": 1.96, "learning_rate": 0.00047425, "loss": 1.9126, "step": 9485 }, { "epoch": 1.97, "learning_rate": 0.0004745, "loss": 1.9123, "step": 9490 }, { "epoch": 1.97, "learning_rate": 0.00047475, "loss": 1.9124, "step": 9495 }, { "epoch": 1.97, "learning_rate": 0.000475, "loss": 1.9098, "step": 9500 }, { "epoch": 1.97, "learning_rate": 0.00047525000000000003, "loss": 1.9148, "step": 9505 }, { "epoch": 1.97, "learning_rate": 0.0004755, "loss": 1.9127, "step": 9510 }, { "epoch": 1.97, "learning_rate": 0.00047575, "loss": 1.9112, "step": 9515 }, { "epoch": 1.97, "learning_rate": 0.00047599999999999997, "loss": 1.9086, "step": 9520 }, { "epoch": 1.97, "learning_rate": 0.00047625, "loss": 1.9146, "step": 9525 }, { "epoch": 1.97, "learning_rate": 0.0004765, "loss": 1.9102, "step": 9530 }, { "epoch": 1.98, "learning_rate": 0.00047675, "loss": 1.9083, "step": 9535 }, { "epoch": 1.98, "learning_rate": 0.000477, "loss": 1.905, "step": 9540 }, { "epoch": 1.98, "learning_rate": 0.00047725, "loss": 1.9094, "step": 9545 }, { "epoch": 1.98, "learning_rate": 0.0004775, "loss": 1.914, "step": 9550 }, { "epoch": 1.98, "learning_rate": 0.00047775000000000004, "loss": 1.9143, "step": 9555 }, { "epoch": 1.98, "learning_rate": 0.00047799999999999996, "loss": 1.9137, "step": 9560 }, { "epoch": 1.98, "learning_rate": 0.00047825, "loss": 1.9052, "step": 9565 }, { "epoch": 1.98, "learning_rate": 0.0004785, "loss": 1.9152, "step": 9570 }, { "epoch": 1.98, "learning_rate": 0.00047875, "loss": 1.9118, "step": 9575 }, { "epoch": 1.98, "learning_rate": 0.000479, "loss": 1.9049, "step": 9580 }, { "epoch": 1.99, "learning_rate": 0.00047925, "loss": 1.9141, "step": 9585 }, { "epoch": 1.99, "learning_rate": 0.0004795, "loss": 1.9075, "step": 9590 }, { "epoch": 1.99, "learning_rate": 0.00047975000000000003, "loss": 1.9144, "step": 9595 }, { "epoch": 1.99, "learning_rate": 0.00048, "loss": 1.9071, "step": 9600 }, { "epoch": 1.99, "learning_rate": 0.00048025000000000005, "loss": 1.9096, "step": 9605 }, { "epoch": 1.99, "learning_rate": 0.00048049999999999997, "loss": 1.9088, "step": 9610 }, { "epoch": 1.99, "learning_rate": 0.00048075, "loss": 1.9276, "step": 9615 }, { "epoch": 1.99, "learning_rate": 0.000481, "loss": 1.9217, "step": 9620 }, { "epoch": 1.99, "learning_rate": 0.00048125, "loss": 1.9214, "step": 9625 }, { "epoch": 2.0, "learning_rate": 0.0004815, "loss": 1.9157, "step": 9630 }, { "epoch": 2.0, "learning_rate": 0.00048175000000000003, "loss": 1.9092, "step": 9635 }, { "epoch": 2.0, "learning_rate": 0.000482, "loss": 1.9124, "step": 9640 }, { "epoch": 2.0, "learning_rate": 0.00048225000000000004, "loss": 1.9138, "step": 9645 }, { "epoch": 2.0, "learning_rate": 0.0004825, "loss": 1.9113, "step": 9650 }, { "epoch": 2.0, "learning_rate": 0.00048275, "loss": 1.9054, "step": 9655 }, { "epoch": 2.0, "learning_rate": 0.000483, "loss": 1.9018, "step": 9660 }, { "epoch": 2.0, "learning_rate": 0.00048325, "loss": 1.9028, "step": 9665 }, { "epoch": 2.0, "learning_rate": 0.0004835, "loss": 1.9066, "step": 9670 }, { "epoch": 2.0, "learning_rate": 0.00048375, "loss": 1.904, "step": 9675 }, { "epoch": 2.01, "learning_rate": 0.000484, "loss": 1.8992, "step": 9680 }, { "epoch": 2.01, "learning_rate": 0.00048425000000000003, "loss": 1.9039, "step": 9685 }, { "epoch": 2.01, "learning_rate": 0.0004845, "loss": 1.8994, "step": 9690 }, { "epoch": 2.01, "learning_rate": 0.00048475000000000005, "loss": 1.9029, "step": 9695 }, { "epoch": 2.01, "learning_rate": 0.00048499999999999997, "loss": 1.9059, "step": 9700 }, { "epoch": 2.01, "learning_rate": 0.00048525, "loss": 1.9038, "step": 9705 }, { "epoch": 2.01, "learning_rate": 0.0004855, "loss": 1.9031, "step": 9710 }, { "epoch": 2.01, "learning_rate": 0.00048575, "loss": 1.906, "step": 9715 }, { "epoch": 2.01, "learning_rate": 0.000486, "loss": 1.9046, "step": 9720 }, { "epoch": 2.01, "learning_rate": 0.00048625000000000003, "loss": 1.8982, "step": 9725 }, { "epoch": 2.02, "learning_rate": 0.0004865, "loss": 1.9046, "step": 9730 }, { "epoch": 2.02, "learning_rate": 0.00048675000000000004, "loss": 1.9033, "step": 9735 }, { "epoch": 2.02, "learning_rate": 0.000487, "loss": 1.9031, "step": 9740 }, { "epoch": 2.02, "learning_rate": 0.00048725000000000005, "loss": 1.8982, "step": 9745 }, { "epoch": 2.02, "learning_rate": 0.0004875, "loss": 1.9097, "step": 9750 }, { "epoch": 2.02, "learning_rate": 0.00048775, "loss": 1.9026, "step": 9755 }, { "epoch": 2.02, "learning_rate": 0.000488, "loss": 1.9013, "step": 9760 }, { "epoch": 2.02, "learning_rate": 0.00048825, "loss": 1.9096, "step": 9765 }, { "epoch": 2.02, "learning_rate": 0.0004885, "loss": 1.9115, "step": 9770 }, { "epoch": 2.03, "learning_rate": 0.00048875, "loss": 1.9054, "step": 9775 }, { "epoch": 2.03, "learning_rate": 0.000489, "loss": 1.9096, "step": 9780 }, { "epoch": 2.03, "learning_rate": 0.00048925, "loss": 1.9069, "step": 9785 }, { "epoch": 2.03, "learning_rate": 0.0004895, "loss": 1.9069, "step": 9790 }, { "epoch": 2.03, "learning_rate": 0.0004897500000000001, "loss": 1.8942, "step": 9795 }, { "epoch": 2.03, "learning_rate": 0.00049, "loss": 1.9121, "step": 9800 }, { "epoch": 2.03, "learning_rate": 0.00049025, "loss": 1.9038, "step": 9805 }, { "epoch": 2.03, "learning_rate": 0.0004905, "loss": 1.9064, "step": 9810 }, { "epoch": 2.03, "learning_rate": 0.0004907500000000001, "loss": 1.9056, "step": 9815 }, { "epoch": 2.03, "learning_rate": 0.000491, "loss": 1.8997, "step": 9820 }, { "epoch": 2.04, "learning_rate": 0.00049125, "loss": 1.9058, "step": 9825 }, { "epoch": 2.04, "learning_rate": 0.0004915, "loss": 1.9031, "step": 9830 }, { "epoch": 2.04, "learning_rate": 0.00049175, "loss": 1.9044, "step": 9835 }, { "epoch": 2.04, "learning_rate": 0.000492, "loss": 1.9006, "step": 9840 }, { "epoch": 2.04, "learning_rate": 0.0004922500000000001, "loss": 1.9051, "step": 9845 }, { "epoch": 2.04, "learning_rate": 0.0004925, "loss": 1.9085, "step": 9850 }, { "epoch": 2.04, "learning_rate": 0.00049275, "loss": 1.9069, "step": 9855 }, { "epoch": 2.04, "learning_rate": 0.0004930000000000001, "loss": 1.9088, "step": 9860 }, { "epoch": 2.04, "learning_rate": 0.00049325, "loss": 1.9057, "step": 9865 }, { "epoch": 2.04, "learning_rate": 0.0004935, "loss": 1.9051, "step": 9870 }, { "epoch": 2.05, "learning_rate": 0.00049375, "loss": 1.9052, "step": 9875 }, { "epoch": 2.05, "learning_rate": 0.000494, "loss": 1.912, "step": 9880 }, { "epoch": 2.05, "learning_rate": 0.00049425, "loss": 1.9063, "step": 9885 }, { "epoch": 2.05, "learning_rate": 0.0004945, "loss": 1.9042, "step": 9890 }, { "epoch": 2.05, "learning_rate": 0.0004947500000000001, "loss": 1.9015, "step": 9895 }, { "epoch": 2.05, "learning_rate": 0.000495, "loss": 1.9075, "step": 9900 }, { "epoch": 2.05, "learning_rate": 0.00049525, "loss": 1.8996, "step": 9905 }, { "epoch": 2.05, "learning_rate": 0.0004955, "loss": 1.9118, "step": 9910 }, { "epoch": 2.05, "learning_rate": 0.00049575, "loss": 1.9075, "step": 9915 }, { "epoch": 2.06, "learning_rate": 0.000496, "loss": 1.8992, "step": 9920 }, { "epoch": 2.06, "learning_rate": 0.0004962500000000001, "loss": 1.8991, "step": 9925 }, { "epoch": 2.06, "learning_rate": 0.0004965, "loss": 1.9012, "step": 9930 }, { "epoch": 2.06, "learning_rate": 0.00049675, "loss": 1.903, "step": 9935 }, { "epoch": 2.06, "learning_rate": 0.000497, "loss": 1.9069, "step": 9940 }, { "epoch": 2.06, "learning_rate": 0.0004972500000000001, "loss": 1.9166, "step": 9945 }, { "epoch": 2.06, "learning_rate": 0.0004975, "loss": 1.9128, "step": 9950 }, { "epoch": 2.06, "learning_rate": 0.00049775, "loss": 1.905, "step": 9955 }, { "epoch": 2.06, "learning_rate": 0.000498, "loss": 1.9041, "step": 9960 }, { "epoch": 2.06, "learning_rate": 0.00049825, "loss": 1.9051, "step": 9965 }, { "epoch": 2.07, "learning_rate": 0.0004985, "loss": 1.9016, "step": 9970 }, { "epoch": 2.07, "learning_rate": 0.0004987500000000001, "loss": 1.9022, "step": 9975 }, { "epoch": 2.07, "learning_rate": 0.000499, "loss": 1.9025, "step": 9980 }, { "epoch": 2.07, "learning_rate": 0.00049925, "loss": 1.9036, "step": 9985 }, { "epoch": 2.07, "learning_rate": 0.0004995, "loss": 1.9011, "step": 9990 }, { "epoch": 2.07, "learning_rate": 0.0004997500000000001, "loss": 1.9045, "step": 9995 }, { "epoch": 2.07, "learning_rate": 0.0005, "loss": 1.9049, "step": 10000 }, { "epoch": 2.07, "learning_rate": 0.0005002499999999999, "loss": 1.9039, "step": 10005 }, { "epoch": 2.07, "learning_rate": 0.0005005, "loss": 1.9023, "step": 10010 }, { "epoch": 2.07, "learning_rate": 0.00050075, "loss": 1.9024, "step": 10015 }, { "epoch": 2.08, "learning_rate": 0.000501, "loss": 1.9028, "step": 10020 }, { "epoch": 2.08, "learning_rate": 0.00050125, "loss": 1.8958, "step": 10025 }, { "epoch": 2.08, "learning_rate": 0.0005015, "loss": 1.9002, "step": 10030 }, { "epoch": 2.08, "learning_rate": 0.00050175, "loss": 1.9055, "step": 10035 }, { "epoch": 2.08, "learning_rate": 0.0005020000000000001, "loss": 1.9007, "step": 10040 }, { "epoch": 2.08, "learning_rate": 0.00050225, "loss": 1.9057, "step": 10045 }, { "epoch": 2.08, "learning_rate": 0.0005024999999999999, "loss": 1.8992, "step": 10050 }, { "epoch": 2.08, "learning_rate": 0.00050275, "loss": 1.8975, "step": 10055 }, { "epoch": 2.08, "learning_rate": 0.000503, "loss": 1.9154, "step": 10060 }, { "epoch": 2.09, "learning_rate": 0.00050325, "loss": 1.9033, "step": 10065 }, { "epoch": 2.09, "learning_rate": 0.0005034999999999999, "loss": 1.9095, "step": 10070 }, { "epoch": 2.09, "learning_rate": 0.0005037500000000001, "loss": 1.9013, "step": 10075 }, { "epoch": 2.09, "learning_rate": 0.000504, "loss": 1.9059, "step": 10080 }, { "epoch": 2.09, "learning_rate": 0.00050425, "loss": 1.9034, "step": 10085 }, { "epoch": 2.09, "learning_rate": 0.0005045, "loss": 1.9007, "step": 10090 }, { "epoch": 2.09, "learning_rate": 0.00050475, "loss": 1.9059, "step": 10095 }, { "epoch": 2.09, "learning_rate": 0.000505, "loss": 1.9092, "step": 10100 }, { "epoch": 2.09, "learning_rate": 0.00050525, "loss": 1.9017, "step": 10105 }, { "epoch": 2.09, "learning_rate": 0.0005055, "loss": 1.9073, "step": 10110 }, { "epoch": 2.1, "learning_rate": 0.00050575, "loss": 1.9034, "step": 10115 }, { "epoch": 2.1, "learning_rate": 0.000506, "loss": 1.9004, "step": 10120 }, { "epoch": 2.1, "learning_rate": 0.00050625, "loss": 1.9015, "step": 10125 }, { "epoch": 2.1, "learning_rate": 0.0005065, "loss": 1.9022, "step": 10130 }, { "epoch": 2.1, "learning_rate": 0.00050675, "loss": 1.8977, "step": 10135 }, { "epoch": 2.1, "learning_rate": 0.000507, "loss": 1.9016, "step": 10140 }, { "epoch": 2.1, "learning_rate": 0.00050725, "loss": 1.901, "step": 10145 }, { "epoch": 2.1, "learning_rate": 0.0005074999999999999, "loss": 1.8989, "step": 10150 }, { "epoch": 2.1, "learning_rate": 0.0005077500000000001, "loss": 1.8982, "step": 10155 }, { "epoch": 2.1, "learning_rate": 0.000508, "loss": 1.9054, "step": 10160 }, { "epoch": 2.11, "learning_rate": 0.00050825, "loss": 1.9027, "step": 10165 }, { "epoch": 2.11, "learning_rate": 0.0005085, "loss": 1.9025, "step": 10170 }, { "epoch": 2.11, "learning_rate": 0.0005087500000000001, "loss": 1.9032, "step": 10175 }, { "epoch": 2.11, "learning_rate": 0.000509, "loss": 1.8989, "step": 10180 }, { "epoch": 2.11, "learning_rate": 0.0005092499999999999, "loss": 1.8984, "step": 10185 }, { "epoch": 2.11, "learning_rate": 0.0005095, "loss": 1.9, "step": 10190 }, { "epoch": 2.11, "learning_rate": 0.00050975, "loss": 1.8987, "step": 10195 }, { "epoch": 2.11, "learning_rate": 0.00051, "loss": 1.8979, "step": 10200 }, { "epoch": 2.11, "learning_rate": 0.00051025, "loss": 1.9028, "step": 10205 }, { "epoch": 2.12, "learning_rate": 0.0005105, "loss": 1.8956, "step": 10210 }, { "epoch": 2.12, "learning_rate": 0.00051075, "loss": 1.9093, "step": 10215 }, { "epoch": 2.12, "learning_rate": 0.0005110000000000001, "loss": 1.9023, "step": 10220 }, { "epoch": 2.12, "learning_rate": 0.00051125, "loss": 1.9018, "step": 10225 }, { "epoch": 2.12, "learning_rate": 0.0005115, "loss": 1.8958, "step": 10230 }, { "epoch": 2.12, "learning_rate": 0.00051175, "loss": 1.9011, "step": 10235 }, { "epoch": 2.12, "learning_rate": 0.000512, "loss": 1.8973, "step": 10240 }, { "epoch": 2.12, "learning_rate": 0.00051225, "loss": 1.9017, "step": 10245 }, { "epoch": 2.12, "learning_rate": 0.0005124999999999999, "loss": 1.9036, "step": 10250 }, { "epoch": 2.12, "learning_rate": 0.0005127500000000001, "loss": 1.9, "step": 10255 }, { "epoch": 2.13, "learning_rate": 0.000513, "loss": 1.9021, "step": 10260 }, { "epoch": 2.13, "learning_rate": 0.00051325, "loss": 1.8986, "step": 10265 }, { "epoch": 2.13, "learning_rate": 0.0005135, "loss": 1.9, "step": 10270 }, { "epoch": 2.13, "learning_rate": 0.0005137500000000001, "loss": 1.8956, "step": 10275 }, { "epoch": 2.13, "learning_rate": 0.000514, "loss": 1.9028, "step": 10280 }, { "epoch": 2.13, "learning_rate": 0.00051425, "loss": 1.9001, "step": 10285 }, { "epoch": 2.13, "learning_rate": 0.0005145, "loss": 1.9053, "step": 10290 }, { "epoch": 2.13, "learning_rate": 0.00051475, "loss": 1.8991, "step": 10295 }, { "epoch": 2.13, "learning_rate": 0.000515, "loss": 1.899, "step": 10300 }, { "epoch": 2.13, "learning_rate": 0.00051525, "loss": 1.8987, "step": 10305 }, { "epoch": 2.14, "learning_rate": 0.0005155, "loss": 1.9077, "step": 10310 }, { "epoch": 2.14, "learning_rate": 0.00051575, "loss": 1.8993, "step": 10315 }, { "epoch": 2.14, "learning_rate": 0.0005160000000000001, "loss": 1.9074, "step": 10320 }, { "epoch": 2.14, "learning_rate": 0.00051625, "loss": 1.9053, "step": 10325 }, { "epoch": 2.14, "learning_rate": 0.0005164999999999999, "loss": 1.8964, "step": 10330 }, { "epoch": 2.14, "learning_rate": 0.0005167500000000001, "loss": 1.8989, "step": 10335 }, { "epoch": 2.14, "learning_rate": 0.000517, "loss": 1.9022, "step": 10340 }, { "epoch": 2.14, "learning_rate": 0.00051725, "loss": 1.8995, "step": 10345 }, { "epoch": 2.14, "learning_rate": 0.0005175, "loss": 1.9022, "step": 10350 }, { "epoch": 2.15, "learning_rate": 0.0005177500000000001, "loss": 1.8964, "step": 10355 }, { "epoch": 2.15, "learning_rate": 0.000518, "loss": 1.9018, "step": 10360 }, { "epoch": 2.15, "learning_rate": 0.00051825, "loss": 1.8982, "step": 10365 }, { "epoch": 2.15, "learning_rate": 0.0005185, "loss": 1.8969, "step": 10370 }, { "epoch": 2.15, "learning_rate": 0.00051875, "loss": 1.9004, "step": 10375 }, { "epoch": 2.15, "learning_rate": 0.000519, "loss": 1.9011, "step": 10380 }, { "epoch": 2.15, "learning_rate": 0.00051925, "loss": 1.8956, "step": 10385 }, { "epoch": 2.15, "learning_rate": 0.0005195, "loss": 1.8984, "step": 10390 }, { "epoch": 2.15, "learning_rate": 0.00051975, "loss": 1.8971, "step": 10395 }, { "epoch": 2.15, "learning_rate": 0.0005200000000000001, "loss": 1.8996, "step": 10400 }, { "epoch": 2.16, "learning_rate": 0.00052025, "loss": 1.901, "step": 10405 }, { "epoch": 2.16, "learning_rate": 0.0005205, "loss": 1.9014, "step": 10410 }, { "epoch": 2.16, "learning_rate": 0.00052075, "loss": 1.9072, "step": 10415 }, { "epoch": 2.16, "learning_rate": 0.000521, "loss": 1.9067, "step": 10420 }, { "epoch": 2.16, "learning_rate": 0.00052125, "loss": 1.8962, "step": 10425 }, { "epoch": 2.16, "learning_rate": 0.0005214999999999999, "loss": 1.9072, "step": 10430 }, { "epoch": 2.16, "learning_rate": 0.0005217500000000001, "loss": 1.9017, "step": 10435 }, { "epoch": 2.16, "learning_rate": 0.000522, "loss": 1.8944, "step": 10440 }, { "epoch": 2.16, "learning_rate": 0.00052225, "loss": 1.9006, "step": 10445 }, { "epoch": 2.16, "learning_rate": 0.0005225, "loss": 1.8983, "step": 10450 }, { "epoch": 2.17, "learning_rate": 0.0005227500000000001, "loss": 1.8935, "step": 10455 }, { "epoch": 2.17, "learning_rate": 0.000523, "loss": 1.8934, "step": 10460 }, { "epoch": 2.17, "learning_rate": 0.00052325, "loss": 1.8971, "step": 10465 }, { "epoch": 2.17, "learning_rate": 0.0005235, "loss": 1.9004, "step": 10470 }, { "epoch": 2.17, "learning_rate": 0.00052375, "loss": 1.9052, "step": 10475 }, { "epoch": 2.17, "learning_rate": 0.000524, "loss": 1.8955, "step": 10480 }, { "epoch": 2.17, "learning_rate": 0.00052425, "loss": 1.897, "step": 10485 }, { "epoch": 2.17, "learning_rate": 0.0005245, "loss": 1.8962, "step": 10490 }, { "epoch": 2.17, "learning_rate": 0.00052475, "loss": 1.8939, "step": 10495 }, { "epoch": 2.18, "learning_rate": 0.0005250000000000001, "loss": 1.9037, "step": 10500 }, { "epoch": 2.18, "learning_rate": 0.00052525, "loss": 1.9049, "step": 10505 }, { "epoch": 2.18, "learning_rate": 0.0005254999999999999, "loss": 1.8995, "step": 10510 }, { "epoch": 2.18, "learning_rate": 0.0005257500000000001, "loss": 1.8985, "step": 10515 }, { "epoch": 2.18, "learning_rate": 0.000526, "loss": 1.8998, "step": 10520 }, { "epoch": 2.18, "learning_rate": 0.00052625, "loss": 1.8991, "step": 10525 }, { "epoch": 2.18, "learning_rate": 0.0005265, "loss": 1.8968, "step": 10530 }, { "epoch": 2.18, "learning_rate": 0.0005267500000000001, "loss": 1.8974, "step": 10535 }, { "epoch": 2.18, "learning_rate": 0.000527, "loss": 1.9003, "step": 10540 }, { "epoch": 2.18, "learning_rate": 0.00052725, "loss": 1.9083, "step": 10545 }, { "epoch": 2.19, "learning_rate": 0.0005275, "loss": 1.9002, "step": 10550 }, { "epoch": 2.19, "learning_rate": 0.0005277500000000001, "loss": 1.8938, "step": 10555 }, { "epoch": 2.19, "learning_rate": 0.000528, "loss": 1.8996, "step": 10560 }, { "epoch": 2.19, "learning_rate": 0.00052825, "loss": 1.8942, "step": 10565 }, { "epoch": 2.19, "learning_rate": 0.0005285, "loss": 1.8984, "step": 10570 }, { "epoch": 2.19, "learning_rate": 0.00052875, "loss": 1.8926, "step": 10575 }, { "epoch": 2.19, "learning_rate": 0.0005290000000000001, "loss": 1.8973, "step": 10580 }, { "epoch": 2.19, "learning_rate": 0.00052925, "loss": 1.8974, "step": 10585 }, { "epoch": 2.19, "learning_rate": 0.0005295, "loss": 1.9, "step": 10590 }, { "epoch": 2.19, "learning_rate": 0.0005297500000000001, "loss": 1.9082, "step": 10595 }, { "epoch": 2.2, "learning_rate": 0.0005300000000000001, "loss": 1.9038, "step": 10600 }, { "epoch": 2.2, "learning_rate": 0.00053025, "loss": 1.9058, "step": 10605 }, { "epoch": 2.2, "learning_rate": 0.0005304999999999999, "loss": 1.9008, "step": 10610 }, { "epoch": 2.2, "learning_rate": 0.0005307500000000001, "loss": 1.9009, "step": 10615 }, { "epoch": 2.2, "learning_rate": 0.000531, "loss": 1.8983, "step": 10620 }, { "epoch": 2.2, "learning_rate": 0.00053125, "loss": 1.9004, "step": 10625 }, { "epoch": 2.2, "learning_rate": 0.0005315, "loss": 1.8959, "step": 10630 }, { "epoch": 2.2, "learning_rate": 0.00053175, "loss": 1.8941, "step": 10635 }, { "epoch": 2.2, "learning_rate": 0.000532, "loss": 1.8947, "step": 10640 }, { "epoch": 2.21, "learning_rate": 0.0005322500000000001, "loss": 1.8991, "step": 10645 }, { "epoch": 2.21, "learning_rate": 0.0005325, "loss": 1.8971, "step": 10650 }, { "epoch": 2.21, "learning_rate": 0.0005327499999999999, "loss": 1.8996, "step": 10655 }, { "epoch": 2.21, "learning_rate": 0.000533, "loss": 1.8994, "step": 10660 }, { "epoch": 2.21, "learning_rate": 0.00053325, "loss": 1.9, "step": 10665 }, { "epoch": 2.21, "learning_rate": 0.0005335, "loss": 1.8949, "step": 10670 }, { "epoch": 2.21, "learning_rate": 0.0005337499999999999, "loss": 1.8984, "step": 10675 }, { "epoch": 2.21, "learning_rate": 0.0005340000000000001, "loss": 1.8977, "step": 10680 }, { "epoch": 2.21, "learning_rate": 0.00053425, "loss": 1.8947, "step": 10685 }, { "epoch": 2.21, "learning_rate": 0.0005345, "loss": 1.893, "step": 10690 }, { "epoch": 2.22, "learning_rate": 0.00053475, "loss": 1.8945, "step": 10695 }, { "epoch": 2.22, "learning_rate": 0.000535, "loss": 1.8936, "step": 10700 }, { "epoch": 2.22, "learning_rate": 0.00053525, "loss": 1.8962, "step": 10705 }, { "epoch": 2.22, "learning_rate": 0.0005355, "loss": 1.8936, "step": 10710 }, { "epoch": 2.22, "learning_rate": 0.00053575, "loss": 1.903, "step": 10715 }, { "epoch": 2.22, "learning_rate": 0.000536, "loss": 1.8997, "step": 10720 }, { "epoch": 2.22, "learning_rate": 0.00053625, "loss": 1.8947, "step": 10725 }, { "epoch": 2.22, "learning_rate": 0.0005365, "loss": 1.8945, "step": 10730 }, { "epoch": 2.22, "learning_rate": 0.00053675, "loss": 1.8994, "step": 10735 }, { "epoch": 2.22, "learning_rate": 0.000537, "loss": 1.897, "step": 10740 }, { "epoch": 2.23, "learning_rate": 0.00053725, "loss": 1.8982, "step": 10745 }, { "epoch": 2.23, "learning_rate": 0.0005375, "loss": 1.9028, "step": 10750 }, { "epoch": 2.23, "learning_rate": 0.0005377499999999999, "loss": 1.8942, "step": 10755 }, { "epoch": 2.23, "learning_rate": 0.0005380000000000001, "loss": 1.8968, "step": 10760 }, { "epoch": 2.23, "learning_rate": 0.00053825, "loss": 1.8983, "step": 10765 }, { "epoch": 2.23, "learning_rate": 0.0005385, "loss": 1.8968, "step": 10770 }, { "epoch": 2.23, "learning_rate": 0.00053875, "loss": 1.8907, "step": 10775 }, { "epoch": 2.23, "learning_rate": 0.0005390000000000001, "loss": 1.8985, "step": 10780 }, { "epoch": 2.23, "learning_rate": 0.00053925, "loss": 1.8957, "step": 10785 }, { "epoch": 2.24, "learning_rate": 0.0005394999999999999, "loss": 1.8957, "step": 10790 }, { "epoch": 2.24, "learning_rate": 0.00053975, "loss": 1.8953, "step": 10795 }, { "epoch": 2.24, "learning_rate": 0.00054, "loss": 1.8957, "step": 10800 }, { "epoch": 2.24, "learning_rate": 0.00054025, "loss": 1.8947, "step": 10805 }, { "epoch": 2.24, "learning_rate": 0.0005405, "loss": 1.9013, "step": 10810 }, { "epoch": 2.24, "learning_rate": 0.00054075, "loss": 1.9028, "step": 10815 }, { "epoch": 2.24, "learning_rate": 0.000541, "loss": 1.8967, "step": 10820 }, { "epoch": 2.24, "learning_rate": 0.0005412500000000001, "loss": 1.8915, "step": 10825 }, { "epoch": 2.24, "learning_rate": 0.0005415, "loss": 1.8984, "step": 10830 }, { "epoch": 2.24, "learning_rate": 0.0005417499999999999, "loss": 1.8975, "step": 10835 }, { "epoch": 2.25, "learning_rate": 0.0005420000000000001, "loss": 1.8944, "step": 10840 }, { "epoch": 2.25, "learning_rate": 0.00054225, "loss": 1.8911, "step": 10845 }, { "epoch": 2.25, "learning_rate": 0.0005425, "loss": 1.9028, "step": 10850 }, { "epoch": 2.25, "learning_rate": 0.0005427499999999999, "loss": 1.894, "step": 10855 }, { "epoch": 2.25, "learning_rate": 0.0005430000000000001, "loss": 1.8946, "step": 10860 }, { "epoch": 2.25, "learning_rate": 0.00054325, "loss": 1.8927, "step": 10865 }, { "epoch": 2.25, "learning_rate": 0.0005435, "loss": 1.8959, "step": 10870 }, { "epoch": 2.25, "learning_rate": 0.00054375, "loss": 1.8943, "step": 10875 }, { "epoch": 2.25, "learning_rate": 0.0005440000000000001, "loss": 1.8971, "step": 10880 }, { "epoch": 2.26, "learning_rate": 0.00054425, "loss": 1.896, "step": 10885 }, { "epoch": 2.26, "learning_rate": 0.0005445, "loss": 1.8948, "step": 10890 }, { "epoch": 2.26, "learning_rate": 0.00054475, "loss": 1.8916, "step": 10895 }, { "epoch": 2.26, "learning_rate": 0.000545, "loss": 1.8992, "step": 10900 }, { "epoch": 2.26, "learning_rate": 0.00054525, "loss": 1.8928, "step": 10905 }, { "epoch": 2.26, "learning_rate": 0.0005455, "loss": 1.8922, "step": 10910 }, { "epoch": 2.26, "learning_rate": 0.00054575, "loss": 1.8902, "step": 10915 }, { "epoch": 2.26, "learning_rate": 0.000546, "loss": 1.8927, "step": 10920 }, { "epoch": 2.26, "learning_rate": 0.0005462500000000001, "loss": 1.8889, "step": 10925 }, { "epoch": 2.26, "learning_rate": 0.0005465, "loss": 1.895, "step": 10930 }, { "epoch": 2.27, "learning_rate": 0.0005467499999999999, "loss": 1.8933, "step": 10935 }, { "epoch": 2.27, "learning_rate": 0.0005470000000000001, "loss": 1.891, "step": 10940 }, { "epoch": 2.27, "learning_rate": 0.00054725, "loss": 1.8956, "step": 10945 }, { "epoch": 2.27, "learning_rate": 0.0005475, "loss": 1.8969, "step": 10950 }, { "epoch": 2.27, "learning_rate": 0.00054775, "loss": 1.8891, "step": 10955 }, { "epoch": 2.27, "learning_rate": 0.0005480000000000001, "loss": 1.8892, "step": 10960 }, { "epoch": 2.27, "learning_rate": 0.00054825, "loss": 1.892, "step": 10965 }, { "epoch": 2.27, "learning_rate": 0.0005485, "loss": 1.8925, "step": 10970 }, { "epoch": 2.27, "learning_rate": 0.00054875, "loss": 1.8982, "step": 10975 }, { "epoch": 2.27, "learning_rate": 0.000549, "loss": 1.894, "step": 10980 }, { "epoch": 2.28, "learning_rate": 0.00054925, "loss": 1.887, "step": 10985 }, { "epoch": 2.28, "learning_rate": 0.0005495, "loss": 1.8899, "step": 10990 }, { "epoch": 2.28, "learning_rate": 0.00054975, "loss": 1.8908, "step": 10995 }, { "epoch": 2.28, "learning_rate": 0.00055, "loss": 1.8914, "step": 11000 }, { "epoch": 2.28, "learning_rate": 0.0005502500000000001, "loss": 1.9069, "step": 11005 }, { "epoch": 2.28, "learning_rate": 0.0005505, "loss": 1.8887, "step": 11010 }, { "epoch": 2.28, "learning_rate": 0.00055075, "loss": 1.8981, "step": 11015 }, { "epoch": 2.28, "learning_rate": 0.0005510000000000001, "loss": 1.8925, "step": 11020 }, { "epoch": 2.28, "learning_rate": 0.00055125, "loss": 1.8898, "step": 11025 }, { "epoch": 2.29, "learning_rate": 0.0005515, "loss": 1.8872, "step": 11030 }, { "epoch": 2.29, "learning_rate": 0.0005517499999999999, "loss": 1.8967, "step": 11035 }, { "epoch": 2.29, "learning_rate": 0.0005520000000000001, "loss": 1.8901, "step": 11040 }, { "epoch": 2.29, "learning_rate": 0.00055225, "loss": 1.8901, "step": 11045 }, { "epoch": 2.29, "learning_rate": 0.0005525, "loss": 1.8909, "step": 11050 }, { "epoch": 2.29, "learning_rate": 0.00055275, "loss": 1.8946, "step": 11055 }, { "epoch": 2.29, "learning_rate": 0.0005530000000000001, "loss": 1.8893, "step": 11060 }, { "epoch": 2.29, "learning_rate": 0.00055325, "loss": 1.8975, "step": 11065 }, { "epoch": 2.29, "learning_rate": 0.0005535, "loss": 1.8933, "step": 11070 }, { "epoch": 2.29, "learning_rate": 0.00055375, "loss": 1.8908, "step": 11075 }, { "epoch": 2.3, "learning_rate": 0.000554, "loss": 1.887, "step": 11080 }, { "epoch": 2.3, "learning_rate": 0.0005542500000000001, "loss": 1.8918, "step": 11085 }, { "epoch": 2.3, "learning_rate": 0.0005545, "loss": 1.8881, "step": 11090 }, { "epoch": 2.3, "learning_rate": 0.00055475, "loss": 1.8979, "step": 11095 }, { "epoch": 2.3, "learning_rate": 0.000555, "loss": 1.9067, "step": 11100 }, { "epoch": 2.3, "learning_rate": 0.0005552500000000001, "loss": 1.9033, "step": 11105 }, { "epoch": 2.3, "learning_rate": 0.0005555, "loss": 1.8957, "step": 11110 }, { "epoch": 2.3, "learning_rate": 0.0005557499999999999, "loss": 1.8963, "step": 11115 }, { "epoch": 2.3, "learning_rate": 0.0005560000000000001, "loss": 1.8923, "step": 11120 }, { "epoch": 2.3, "learning_rate": 0.00055625, "loss": 1.8941, "step": 11125 }, { "epoch": 2.31, "learning_rate": 0.0005565, "loss": 1.8926, "step": 11130 }, { "epoch": 2.31, "learning_rate": 0.00055675, "loss": 1.8897, "step": 11135 }, { "epoch": 2.31, "learning_rate": 0.0005570000000000001, "loss": 1.8902, "step": 11140 }, { "epoch": 2.31, "learning_rate": 0.00055725, "loss": 1.8859, "step": 11145 }, { "epoch": 2.31, "learning_rate": 0.0005575, "loss": 1.8878, "step": 11150 }, { "epoch": 2.31, "learning_rate": 0.00055775, "loss": 1.8888, "step": 11155 }, { "epoch": 2.31, "learning_rate": 0.000558, "loss": 1.8947, "step": 11160 }, { "epoch": 2.31, "learning_rate": 0.00055825, "loss": 1.8841, "step": 11165 }, { "epoch": 2.31, "learning_rate": 0.0005585, "loss": 1.888, "step": 11170 }, { "epoch": 2.32, "learning_rate": 0.00055875, "loss": 1.887, "step": 11175 }, { "epoch": 2.32, "learning_rate": 0.000559, "loss": 1.892, "step": 11180 }, { "epoch": 2.32, "learning_rate": 0.0005592500000000001, "loss": 1.8881, "step": 11185 }, { "epoch": 2.32, "learning_rate": 0.0005595, "loss": 1.8932, "step": 11190 }, { "epoch": 2.32, "learning_rate": 0.00055975, "loss": 1.8854, "step": 11195 }, { "epoch": 2.32, "learning_rate": 0.0005600000000000001, "loss": 1.8883, "step": 11200 }, { "epoch": 2.32, "learning_rate": 0.00056025, "loss": 1.9052, "step": 11205 }, { "epoch": 2.32, "learning_rate": 0.0005605, "loss": 1.9021, "step": 11210 }, { "epoch": 2.32, "learning_rate": 0.0005607499999999999, "loss": 1.892, "step": 11215 }, { "epoch": 2.32, "learning_rate": 0.0005610000000000001, "loss": 1.8952, "step": 11220 }, { "epoch": 2.33, "learning_rate": 0.00056125, "loss": 1.8896, "step": 11225 }, { "epoch": 2.33, "learning_rate": 0.0005615, "loss": 1.89, "step": 11230 }, { "epoch": 2.33, "learning_rate": 0.00056175, "loss": 1.8907, "step": 11235 }, { "epoch": 2.33, "learning_rate": 0.0005620000000000001, "loss": 1.8942, "step": 11240 }, { "epoch": 2.33, "learning_rate": 0.00056225, "loss": 1.8932, "step": 11245 }, { "epoch": 2.33, "learning_rate": 0.0005625000000000001, "loss": 1.895, "step": 11250 }, { "epoch": 2.33, "learning_rate": 0.00056275, "loss": 1.8937, "step": 11255 }, { "epoch": 2.33, "learning_rate": 0.0005629999999999999, "loss": 1.8901, "step": 11260 }, { "epoch": 2.33, "learning_rate": 0.0005632500000000001, "loss": 1.8918, "step": 11265 }, { "epoch": 2.33, "learning_rate": 0.0005635, "loss": 1.8869, "step": 11270 }, { "epoch": 2.34, "learning_rate": 0.00056375, "loss": 1.892, "step": 11275 }, { "epoch": 2.34, "learning_rate": 0.0005639999999999999, "loss": 1.8872, "step": 11280 }, { "epoch": 2.34, "learning_rate": 0.0005642500000000001, "loss": 1.89, "step": 11285 }, { "epoch": 2.34, "learning_rate": 0.0005645, "loss": 1.8883, "step": 11290 }, { "epoch": 2.34, "learning_rate": 0.00056475, "loss": 1.89, "step": 11295 }, { "epoch": 2.34, "learning_rate": 0.000565, "loss": 1.8901, "step": 11300 }, { "epoch": 2.34, "learning_rate": 0.00056525, "loss": 1.8898, "step": 11305 }, { "epoch": 2.34, "learning_rate": 0.0005655, "loss": 1.8893, "step": 11310 }, { "epoch": 2.34, "learning_rate": 0.00056575, "loss": 1.8946, "step": 11315 }, { "epoch": 2.35, "learning_rate": 0.000566, "loss": 1.8873, "step": 11320 }, { "epoch": 2.35, "learning_rate": 0.00056625, "loss": 1.8907, "step": 11325 }, { "epoch": 2.35, "learning_rate": 0.0005665000000000001, "loss": 1.8802, "step": 11330 }, { "epoch": 2.35, "learning_rate": 0.00056675, "loss": 1.8916, "step": 11335 }, { "epoch": 2.35, "learning_rate": 0.000567, "loss": 1.8874, "step": 11340 }, { "epoch": 2.35, "learning_rate": 0.00056725, "loss": 1.8863, "step": 11345 }, { "epoch": 2.35, "learning_rate": 0.0005675, "loss": 1.8871, "step": 11350 }, { "epoch": 2.35, "learning_rate": 0.00056775, "loss": 1.8899, "step": 11355 }, { "epoch": 2.35, "learning_rate": 0.0005679999999999999, "loss": 1.8895, "step": 11360 }, { "epoch": 2.35, "learning_rate": 0.0005682500000000001, "loss": 1.8872, "step": 11365 }, { "epoch": 2.36, "learning_rate": 0.0005685, "loss": 1.8897, "step": 11370 }, { "epoch": 2.36, "learning_rate": 0.00056875, "loss": 1.8849, "step": 11375 }, { "epoch": 2.36, "learning_rate": 0.000569, "loss": 1.894, "step": 11380 }, { "epoch": 2.36, "learning_rate": 0.0005692500000000001, "loss": 1.8933, "step": 11385 }, { "epoch": 2.36, "learning_rate": 0.0005695, "loss": 1.8918, "step": 11390 }, { "epoch": 2.36, "learning_rate": 0.0005697499999999999, "loss": 1.8857, "step": 11395 }, { "epoch": 2.36, "learning_rate": 0.00057, "loss": 1.8864, "step": 11400 }, { "epoch": 2.36, "learning_rate": 0.00057025, "loss": 1.8875, "step": 11405 }, { "epoch": 2.36, "learning_rate": 0.0005705, "loss": 1.8877, "step": 11410 }, { "epoch": 2.36, "learning_rate": 0.00057075, "loss": 1.8836, "step": 11415 }, { "epoch": 2.37, "learning_rate": 0.000571, "loss": 1.8914, "step": 11420 }, { "epoch": 2.37, "learning_rate": 0.00057125, "loss": 1.9008, "step": 11425 }, { "epoch": 2.37, "learning_rate": 0.0005715000000000001, "loss": 1.8929, "step": 11430 }, { "epoch": 2.37, "learning_rate": 0.00057175, "loss": 1.8871, "step": 11435 }, { "epoch": 2.37, "learning_rate": 0.0005719999999999999, "loss": 1.8873, "step": 11440 }, { "epoch": 2.37, "learning_rate": 0.0005722500000000001, "loss": 1.8888, "step": 11445 }, { "epoch": 2.37, "learning_rate": 0.0005725, "loss": 1.8924, "step": 11450 }, { "epoch": 2.37, "learning_rate": 0.00057275, "loss": 1.8919, "step": 11455 }, { "epoch": 2.37, "learning_rate": 0.0005729999999999999, "loss": 1.8886, "step": 11460 }, { "epoch": 2.38, "learning_rate": 0.0005732500000000001, "loss": 1.8905, "step": 11465 }, { "epoch": 2.38, "learning_rate": 0.0005735, "loss": 1.8901, "step": 11470 }, { "epoch": 2.38, "learning_rate": 0.00057375, "loss": 1.8841, "step": 11475 }, { "epoch": 2.38, "learning_rate": 0.000574, "loss": 1.8938, "step": 11480 }, { "epoch": 2.38, "learning_rate": 0.00057425, "loss": 1.8849, "step": 11485 }, { "epoch": 2.38, "learning_rate": 0.0005745, "loss": 1.8862, "step": 11490 }, { "epoch": 2.38, "learning_rate": 0.00057475, "loss": 1.8888, "step": 11495 }, { "epoch": 2.38, "learning_rate": 0.000575, "loss": 1.8876, "step": 11500 }, { "epoch": 2.38, "learning_rate": 0.00057525, "loss": 1.891, "step": 11505 }, { "epoch": 2.38, "learning_rate": 0.0005755000000000001, "loss": 1.8835, "step": 11510 }, { "epoch": 2.39, "learning_rate": 0.00057575, "loss": 1.8888, "step": 11515 }, { "epoch": 2.39, "learning_rate": 0.000576, "loss": 1.8935, "step": 11520 }, { "epoch": 2.39, "learning_rate": 0.00057625, "loss": 1.8962, "step": 11525 }, { "epoch": 2.39, "learning_rate": 0.0005765, "loss": 1.8932, "step": 11530 }, { "epoch": 2.39, "learning_rate": 0.00057675, "loss": 1.8858, "step": 11535 }, { "epoch": 2.39, "learning_rate": 0.0005769999999999999, "loss": 1.8863, "step": 11540 }, { "epoch": 2.39, "learning_rate": 0.0005772500000000001, "loss": 1.8889, "step": 11545 }, { "epoch": 2.39, "learning_rate": 0.0005775, "loss": 1.8864, "step": 11550 }, { "epoch": 2.39, "learning_rate": 0.00057775, "loss": 1.8887, "step": 11555 }, { "epoch": 2.39, "learning_rate": 0.000578, "loss": 1.887, "step": 11560 }, { "epoch": 2.4, "learning_rate": 0.0005782500000000001, "loss": 1.8831, "step": 11565 }, { "epoch": 2.4, "learning_rate": 0.0005785, "loss": 1.8833, "step": 11570 }, { "epoch": 2.4, "learning_rate": 0.00057875, "loss": 1.8828, "step": 11575 }, { "epoch": 2.4, "learning_rate": 0.000579, "loss": 1.8887, "step": 11580 }, { "epoch": 2.4, "learning_rate": 0.00057925, "loss": 1.8818, "step": 11585 }, { "epoch": 2.4, "learning_rate": 0.0005795, "loss": 1.8823, "step": 11590 }, { "epoch": 2.4, "learning_rate": 0.00057975, "loss": 1.8911, "step": 11595 }, { "epoch": 2.4, "learning_rate": 0.00058, "loss": 1.8862, "step": 11600 }, { "epoch": 2.4, "learning_rate": 0.00058025, "loss": 1.8878, "step": 11605 }, { "epoch": 2.41, "learning_rate": 0.0005805000000000001, "loss": 1.8868, "step": 11610 }, { "epoch": 2.41, "learning_rate": 0.00058075, "loss": 1.8839, "step": 11615 }, { "epoch": 2.41, "learning_rate": 0.0005809999999999999, "loss": 1.8905, "step": 11620 }, { "epoch": 2.41, "learning_rate": 0.0005812500000000001, "loss": 1.8917, "step": 11625 }, { "epoch": 2.41, "learning_rate": 0.0005815, "loss": 1.8839, "step": 11630 }, { "epoch": 2.41, "learning_rate": 0.00058175, "loss": 1.8861, "step": 11635 }, { "epoch": 2.41, "learning_rate": 0.0005819999999999999, "loss": 1.8896, "step": 11640 }, { "epoch": 2.41, "learning_rate": 0.0005822500000000001, "loss": 1.8866, "step": 11645 }, { "epoch": 2.41, "learning_rate": 0.0005825, "loss": 1.8865, "step": 11650 }, { "epoch": 2.41, "learning_rate": 0.00058275, "loss": 1.889, "step": 11655 }, { "epoch": 2.42, "learning_rate": 0.000583, "loss": 1.8867, "step": 11660 }, { "epoch": 2.42, "learning_rate": 0.0005832500000000001, "loss": 1.8871, "step": 11665 }, { "epoch": 2.42, "learning_rate": 0.0005835, "loss": 1.8841, "step": 11670 }, { "epoch": 2.42, "learning_rate": 0.00058375, "loss": 1.8768, "step": 11675 }, { "epoch": 2.42, "learning_rate": 0.000584, "loss": 1.8801, "step": 11680 }, { "epoch": 2.42, "learning_rate": 0.00058425, "loss": 1.8885, "step": 11685 }, { "epoch": 2.42, "learning_rate": 0.0005845000000000001, "loss": 1.8947, "step": 11690 }, { "epoch": 2.42, "learning_rate": 0.00058475, "loss": 1.8966, "step": 11695 }, { "epoch": 2.42, "learning_rate": 0.000585, "loss": 1.8952, "step": 11700 }, { "epoch": 2.42, "learning_rate": 0.00058525, "loss": 1.8883, "step": 11705 }, { "epoch": 2.43, "learning_rate": 0.0005855000000000001, "loss": 1.8836, "step": 11710 }, { "epoch": 2.43, "learning_rate": 0.00058575, "loss": 1.8851, "step": 11715 }, { "epoch": 2.43, "learning_rate": 0.0005859999999999999, "loss": 1.8905, "step": 11720 }, { "epoch": 2.43, "learning_rate": 0.0005862500000000001, "loss": 1.8858, "step": 11725 }, { "epoch": 2.43, "learning_rate": 0.0005865, "loss": 1.8922, "step": 11730 }, { "epoch": 2.43, "learning_rate": 0.00058675, "loss": 1.8891, "step": 11735 }, { "epoch": 2.43, "learning_rate": 0.000587, "loss": 1.886, "step": 11740 }, { "epoch": 2.43, "learning_rate": 0.0005872500000000001, "loss": 1.8852, "step": 11745 }, { "epoch": 2.43, "learning_rate": 0.0005875, "loss": 1.8857, "step": 11750 }, { "epoch": 2.44, "learning_rate": 0.0005877500000000001, "loss": 1.8873, "step": 11755 }, { "epoch": 2.44, "learning_rate": 0.000588, "loss": 1.8852, "step": 11760 }, { "epoch": 2.44, "learning_rate": 0.00058825, "loss": 1.8868, "step": 11765 }, { "epoch": 2.44, "learning_rate": 0.0005885, "loss": 1.8852, "step": 11770 }, { "epoch": 2.44, "learning_rate": 0.00058875, "loss": 1.891, "step": 11775 }, { "epoch": 2.44, "learning_rate": 0.000589, "loss": 1.8896, "step": 11780 }, { "epoch": 2.44, "learning_rate": 0.00058925, "loss": 1.8835, "step": 11785 }, { "epoch": 2.44, "learning_rate": 0.0005895000000000001, "loss": 1.8861, "step": 11790 }, { "epoch": 2.44, "learning_rate": 0.00058975, "loss": 1.8831, "step": 11795 }, { "epoch": 2.44, "learning_rate": 0.00059, "loss": 1.8797, "step": 11800 }, { "epoch": 2.45, "learning_rate": 0.0005902500000000001, "loss": 1.8843, "step": 11805 }, { "epoch": 2.45, "learning_rate": 0.0005905, "loss": 1.8836, "step": 11810 }, { "epoch": 2.45, "learning_rate": 0.00059075, "loss": 1.8837, "step": 11815 }, { "epoch": 2.45, "learning_rate": 0.0005909999999999999, "loss": 1.8919, "step": 11820 }, { "epoch": 2.45, "learning_rate": 0.0005912500000000001, "loss": 1.8991, "step": 11825 }, { "epoch": 2.45, "learning_rate": 0.0005915, "loss": 1.889, "step": 11830 }, { "epoch": 2.45, "learning_rate": 0.00059175, "loss": 1.8848, "step": 11835 }, { "epoch": 2.45, "learning_rate": 0.000592, "loss": 1.8862, "step": 11840 }, { "epoch": 2.45, "learning_rate": 0.0005922500000000001, "loss": 1.8871, "step": 11845 }, { "epoch": 2.45, "learning_rate": 0.0005925, "loss": 1.8801, "step": 11850 }, { "epoch": 2.46, "learning_rate": 0.00059275, "loss": 1.8852, "step": 11855 }, { "epoch": 2.46, "learning_rate": 0.000593, "loss": 1.8791, "step": 11860 }, { "epoch": 2.46, "learning_rate": 0.00059325, "loss": 1.8884, "step": 11865 }, { "epoch": 2.46, "learning_rate": 0.0005935000000000001, "loss": 1.8842, "step": 11870 }, { "epoch": 2.46, "learning_rate": 0.00059375, "loss": 1.8867, "step": 11875 }, { "epoch": 2.46, "learning_rate": 0.000594, "loss": 1.8917, "step": 11880 }, { "epoch": 2.46, "learning_rate": 0.0005942499999999999, "loss": 1.8903, "step": 11885 }, { "epoch": 2.46, "learning_rate": 0.0005945000000000001, "loss": 1.885, "step": 11890 }, { "epoch": 2.46, "learning_rate": 0.00059475, "loss": 1.8815, "step": 11895 }, { "epoch": 2.47, "learning_rate": 0.0005949999999999999, "loss": 1.8844, "step": 11900 }, { "epoch": 2.47, "learning_rate": 0.00059525, "loss": 1.8842, "step": 11905 }, { "epoch": 2.47, "learning_rate": 0.0005955, "loss": 1.8785, "step": 11910 }, { "epoch": 2.47, "learning_rate": 0.00059575, "loss": 1.8869, "step": 11915 }, { "epoch": 2.47, "learning_rate": 0.000596, "loss": 1.8889, "step": 11920 }, { "epoch": 2.47, "learning_rate": 0.00059625, "loss": 1.8878, "step": 11925 }, { "epoch": 2.47, "learning_rate": 0.0005965, "loss": 1.8869, "step": 11930 }, { "epoch": 2.47, "learning_rate": 0.0005967500000000001, "loss": 1.8811, "step": 11935 }, { "epoch": 2.47, "learning_rate": 0.000597, "loss": 1.8834, "step": 11940 }, { "epoch": 2.47, "learning_rate": 0.0005972499999999999, "loss": 1.8877, "step": 11945 }, { "epoch": 2.48, "learning_rate": 0.0005975, "loss": 1.8869, "step": 11950 }, { "epoch": 2.48, "learning_rate": 0.00059775, "loss": 1.887, "step": 11955 }, { "epoch": 2.48, "learning_rate": 0.000598, "loss": 1.8768, "step": 11960 }, { "epoch": 2.48, "learning_rate": 0.0005982499999999999, "loss": 1.8864, "step": 11965 }, { "epoch": 2.48, "learning_rate": 0.0005985000000000001, "loss": 1.8814, "step": 11970 }, { "epoch": 2.48, "learning_rate": 0.00059875, "loss": 1.8845, "step": 11975 }, { "epoch": 2.48, "learning_rate": 0.000599, "loss": 1.8879, "step": 11980 }, { "epoch": 2.48, "learning_rate": 0.00059925, "loss": 1.89, "step": 11985 }, { "epoch": 2.48, "learning_rate": 0.0005995000000000001, "loss": 1.882, "step": 11990 }, { "epoch": 2.48, "learning_rate": 0.00059975, "loss": 1.8843, "step": 11995 }, { "epoch": 2.49, "learning_rate": 0.0006, "loss": 1.8816, "step": 12000 }, { "epoch": 2.49, "eval_accuracy": 0.5167581699346405, "eval_loss": 2.070143699645996, "eval_runtime": 0.4983, "eval_samples_per_second": 301.029, "eval_steps_per_second": 2.007, "step": 12000 }, { "epoch": 2.49, "learning_rate": 0.00060025, "loss": 1.8842, "step": 12005 }, { "epoch": 2.49, "learning_rate": 0.0006005, "loss": 1.8818, "step": 12010 }, { "epoch": 2.49, "learning_rate": 0.00060075, "loss": 1.8826, "step": 12015 }, { "epoch": 2.49, "learning_rate": 0.000601, "loss": 1.884, "step": 12020 }, { "epoch": 2.49, "learning_rate": 0.00060125, "loss": 1.8847, "step": 12025 }, { "epoch": 2.49, "learning_rate": 0.0006015, "loss": 1.8822, "step": 12030 }, { "epoch": 2.49, "learning_rate": 0.0006017500000000001, "loss": 1.8838, "step": 12035 }, { "epoch": 2.49, "learning_rate": 0.000602, "loss": 1.8874, "step": 12040 }, { "epoch": 2.5, "learning_rate": 0.0006022499999999999, "loss": 1.8836, "step": 12045 }, { "epoch": 2.5, "learning_rate": 0.0006025000000000001, "loss": 1.8811, "step": 12050 }, { "epoch": 2.5, "learning_rate": 0.00060275, "loss": 1.8805, "step": 12055 }, { "epoch": 2.5, "learning_rate": 0.000603, "loss": 1.8853, "step": 12060 }, { "epoch": 2.5, "learning_rate": 0.0006032499999999999, "loss": 1.8803, "step": 12065 }, { "epoch": 2.5, "learning_rate": 0.0006035000000000001, "loss": 1.898, "step": 12070 }, { "epoch": 2.5, "learning_rate": 0.00060375, "loss": 1.8895, "step": 12075 }, { "epoch": 2.5, "learning_rate": 0.000604, "loss": 1.891, "step": 12080 }, { "epoch": 2.5, "learning_rate": 0.00060425, "loss": 1.8843, "step": 12085 }, { "epoch": 2.5, "learning_rate": 0.0006045, "loss": 1.8814, "step": 12090 }, { "epoch": 2.51, "learning_rate": 0.00060475, "loss": 1.8807, "step": 12095 }, { "epoch": 2.51, "learning_rate": 0.000605, "loss": 1.8826, "step": 12100 }, { "epoch": 2.51, "learning_rate": 0.00060525, "loss": 1.8852, "step": 12105 }, { "epoch": 2.51, "learning_rate": 0.0006055, "loss": 1.8824, "step": 12110 }, { "epoch": 2.51, "learning_rate": 0.0006057500000000001, "loss": 1.8833, "step": 12115 }, { "epoch": 2.51, "learning_rate": 0.000606, "loss": 1.8854, "step": 12120 }, { "epoch": 2.51, "learning_rate": 0.00060625, "loss": 1.8876, "step": 12125 }, { "epoch": 2.51, "learning_rate": 0.0006065, "loss": 1.8748, "step": 12130 }, { "epoch": 2.51, "learning_rate": 0.00060675, "loss": 1.8771, "step": 12135 }, { "epoch": 2.52, "learning_rate": 0.000607, "loss": 1.8827, "step": 12140 }, { "epoch": 2.52, "learning_rate": 0.0006072499999999999, "loss": 1.8858, "step": 12145 }, { "epoch": 2.52, "learning_rate": 0.0006075000000000001, "loss": 1.8892, "step": 12150 }, { "epoch": 2.52, "learning_rate": 0.00060775, "loss": 1.8871, "step": 12155 }, { "epoch": 2.52, "learning_rate": 0.000608, "loss": 1.8838, "step": 12160 }, { "epoch": 2.52, "learning_rate": 0.00060825, "loss": 1.8793, "step": 12165 }, { "epoch": 2.52, "learning_rate": 0.0006085000000000001, "loss": 1.8801, "step": 12170 }, { "epoch": 2.52, "learning_rate": 0.00060875, "loss": 1.8847, "step": 12175 }, { "epoch": 2.52, "learning_rate": 0.000609, "loss": 1.8806, "step": 12180 }, { "epoch": 2.52, "learning_rate": 0.00060925, "loss": 1.8815, "step": 12185 }, { "epoch": 2.53, "learning_rate": 0.0006095, "loss": 1.8822, "step": 12190 }, { "epoch": 2.53, "learning_rate": 0.00060975, "loss": 1.8861, "step": 12195 }, { "epoch": 2.53, "learning_rate": 0.00061, "loss": 1.8784, "step": 12200 }, { "epoch": 2.53, "learning_rate": 0.00061025, "loss": 1.8829, "step": 12205 }, { "epoch": 2.53, "learning_rate": 0.0006105, "loss": 1.8842, "step": 12210 }, { "epoch": 2.53, "learning_rate": 0.0006107500000000001, "loss": 1.8792, "step": 12215 }, { "epoch": 2.53, "learning_rate": 0.000611, "loss": 1.8805, "step": 12220 }, { "epoch": 2.53, "learning_rate": 0.0006112499999999999, "loss": 1.8755, "step": 12225 }, { "epoch": 2.53, "learning_rate": 0.0006115000000000001, "loss": 1.886, "step": 12230 }, { "epoch": 2.53, "learning_rate": 0.00061175, "loss": 1.8875, "step": 12235 }, { "epoch": 2.54, "learning_rate": 0.000612, "loss": 1.8832, "step": 12240 }, { "epoch": 2.54, "learning_rate": 0.00061225, "loss": 1.8863, "step": 12245 }, { "epoch": 2.54, "learning_rate": 0.0006125000000000001, "loss": 1.8807, "step": 12250 }, { "epoch": 2.54, "learning_rate": 0.00061275, "loss": 1.8835, "step": 12255 }, { "epoch": 2.54, "learning_rate": 0.000613, "loss": 1.8773, "step": 12260 }, { "epoch": 2.54, "learning_rate": 0.00061325, "loss": 1.8823, "step": 12265 }, { "epoch": 2.54, "learning_rate": 0.0006135, "loss": 1.8814, "step": 12270 }, { "epoch": 2.54, "learning_rate": 0.00061375, "loss": 1.8853, "step": 12275 }, { "epoch": 2.54, "learning_rate": 0.000614, "loss": 1.876, "step": 12280 }, { "epoch": 2.55, "learning_rate": 0.00061425, "loss": 1.8777, "step": 12285 }, { "epoch": 2.55, "learning_rate": 0.0006145, "loss": 1.8771, "step": 12290 }, { "epoch": 2.55, "learning_rate": 0.0006147500000000001, "loss": 1.8817, "step": 12295 }, { "epoch": 2.55, "learning_rate": 0.000615, "loss": 1.8792, "step": 12300 }, { "epoch": 2.55, "learning_rate": 0.00061525, "loss": 1.8819, "step": 12305 }, { "epoch": 2.55, "learning_rate": 0.0006155, "loss": 1.8841, "step": 12310 }, { "epoch": 2.55, "learning_rate": 0.0006157500000000001, "loss": 1.8801, "step": 12315 }, { "epoch": 2.55, "learning_rate": 0.000616, "loss": 1.8827, "step": 12320 }, { "epoch": 2.55, "learning_rate": 0.0006162499999999999, "loss": 1.8756, "step": 12325 }, { "epoch": 2.55, "learning_rate": 0.0006165000000000001, "loss": 1.8812, "step": 12330 }, { "epoch": 2.56, "learning_rate": 0.00061675, "loss": 1.8834, "step": 12335 }, { "epoch": 2.56, "learning_rate": 0.000617, "loss": 1.8743, "step": 12340 }, { "epoch": 2.56, "learning_rate": 0.00061725, "loss": 1.8798, "step": 12345 }, { "epoch": 2.56, "learning_rate": 0.0006175000000000001, "loss": 1.8793, "step": 12350 }, { "epoch": 2.56, "learning_rate": 0.00061775, "loss": 1.8848, "step": 12355 }, { "epoch": 2.56, "learning_rate": 0.0006180000000000001, "loss": 1.8797, "step": 12360 }, { "epoch": 2.56, "learning_rate": 0.00061825, "loss": 1.8795, "step": 12365 }, { "epoch": 2.56, "learning_rate": 0.0006185, "loss": 1.8808, "step": 12370 }, { "epoch": 2.56, "learning_rate": 0.00061875, "loss": 1.8812, "step": 12375 }, { "epoch": 2.56, "learning_rate": 0.000619, "loss": 1.873, "step": 12380 }, { "epoch": 2.57, "learning_rate": 0.00061925, "loss": 1.8856, "step": 12385 }, { "epoch": 2.57, "learning_rate": 0.0006195, "loss": 1.8829, "step": 12390 }, { "epoch": 2.57, "learning_rate": 0.0006197500000000001, "loss": 1.8803, "step": 12395 }, { "epoch": 2.57, "learning_rate": 0.00062, "loss": 1.8798, "step": 12400 }, { "epoch": 2.57, "learning_rate": 0.00062025, "loss": 1.8837, "step": 12405 }, { "epoch": 2.57, "learning_rate": 0.0006205000000000001, "loss": 1.8811, "step": 12410 }, { "epoch": 2.57, "learning_rate": 0.00062075, "loss": 1.875, "step": 12415 }, { "epoch": 2.57, "learning_rate": 0.000621, "loss": 1.8797, "step": 12420 }, { "epoch": 2.57, "learning_rate": 0.00062125, "loss": 1.8818, "step": 12425 }, { "epoch": 2.58, "learning_rate": 0.0006215000000000001, "loss": 1.877, "step": 12430 }, { "epoch": 2.58, "learning_rate": 0.00062175, "loss": 1.8787, "step": 12435 }, { "epoch": 2.58, "learning_rate": 0.000622, "loss": 1.8814, "step": 12440 }, { "epoch": 2.58, "learning_rate": 0.00062225, "loss": 1.876, "step": 12445 }, { "epoch": 2.58, "learning_rate": 0.0006225000000000001, "loss": 1.8759, "step": 12450 }, { "epoch": 2.58, "learning_rate": 0.00062275, "loss": 1.8776, "step": 12455 }, { "epoch": 2.58, "learning_rate": 0.000623, "loss": 1.8781, "step": 12460 }, { "epoch": 2.58, "learning_rate": 0.00062325, "loss": 1.881, "step": 12465 }, { "epoch": 2.58, "learning_rate": 0.0006235, "loss": 1.8772, "step": 12470 }, { "epoch": 2.58, "learning_rate": 0.0006237500000000001, "loss": 1.8788, "step": 12475 }, { "epoch": 2.59, "learning_rate": 0.000624, "loss": 1.8799, "step": 12480 }, { "epoch": 2.59, "learning_rate": 0.00062425, "loss": 1.8816, "step": 12485 }, { "epoch": 2.59, "learning_rate": 0.0006245000000000001, "loss": 1.8767, "step": 12490 }, { "epoch": 2.59, "learning_rate": 0.0006247500000000001, "loss": 1.8793, "step": 12495 }, { "epoch": 2.59, "learning_rate": 0.000625, "loss": 1.878, "step": 12500 }, { "epoch": 2.59, "learning_rate": 0.0006252499999999999, "loss": 1.8805, "step": 12505 }, { "epoch": 2.59, "learning_rate": 0.0006255, "loss": 1.8796, "step": 12510 }, { "epoch": 2.59, "learning_rate": 0.00062575, "loss": 1.8777, "step": 12515 }, { "epoch": 2.59, "learning_rate": 0.000626, "loss": 1.8862, "step": 12520 }, { "epoch": 2.59, "learning_rate": 0.00062625, "loss": 1.8822, "step": 12525 }, { "epoch": 2.6, "learning_rate": 0.0006265, "loss": 1.8822, "step": 12530 }, { "epoch": 2.6, "learning_rate": 0.00062675, "loss": 1.8796, "step": 12535 }, { "epoch": 2.6, "learning_rate": 0.0006270000000000001, "loss": 1.8822, "step": 12540 }, { "epoch": 2.6, "learning_rate": 0.00062725, "loss": 1.8816, "step": 12545 }, { "epoch": 2.6, "learning_rate": 0.0006274999999999999, "loss": 1.8825, "step": 12550 }, { "epoch": 2.6, "learning_rate": 0.00062775, "loss": 1.8889, "step": 12555 }, { "epoch": 2.6, "learning_rate": 0.000628, "loss": 1.8937, "step": 12560 }, { "epoch": 2.6, "learning_rate": 0.00062825, "loss": 1.8862, "step": 12565 }, { "epoch": 2.6, "learning_rate": 0.0006284999999999999, "loss": 1.8829, "step": 12570 }, { "epoch": 2.61, "learning_rate": 0.0006287500000000001, "loss": 1.8842, "step": 12575 }, { "epoch": 2.61, "learning_rate": 0.000629, "loss": 1.8792, "step": 12580 }, { "epoch": 2.61, "learning_rate": 0.00062925, "loss": 1.8808, "step": 12585 }, { "epoch": 2.61, "learning_rate": 0.0006295, "loss": 1.8807, "step": 12590 }, { "epoch": 2.61, "learning_rate": 0.00062975, "loss": 1.8775, "step": 12595 }, { "epoch": 2.61, "learning_rate": 0.00063, "loss": 1.8792, "step": 12600 }, { "epoch": 2.61, "learning_rate": 0.00063025, "loss": 1.8819, "step": 12605 }, { "epoch": 2.61, "learning_rate": 0.0006305, "loss": 1.8817, "step": 12610 }, { "epoch": 2.61, "learning_rate": 0.00063075, "loss": 1.8747, "step": 12615 }, { "epoch": 2.61, "learning_rate": 0.000631, "loss": 1.875, "step": 12620 }, { "epoch": 2.62, "learning_rate": 0.00063125, "loss": 1.8759, "step": 12625 }, { "epoch": 2.62, "learning_rate": 0.0006315, "loss": 1.8753, "step": 12630 }, { "epoch": 2.62, "learning_rate": 0.00063175, "loss": 1.8809, "step": 12635 }, { "epoch": 2.62, "learning_rate": 0.000632, "loss": 1.8819, "step": 12640 }, { "epoch": 2.62, "learning_rate": 0.00063225, "loss": 1.8769, "step": 12645 }, { "epoch": 2.62, "learning_rate": 0.0006324999999999999, "loss": 1.8756, "step": 12650 }, { "epoch": 2.62, "learning_rate": 0.0006327500000000001, "loss": 1.8778, "step": 12655 }, { "epoch": 2.62, "learning_rate": 0.000633, "loss": 1.8757, "step": 12660 }, { "epoch": 2.62, "learning_rate": 0.00063325, "loss": 1.8757, "step": 12665 }, { "epoch": 2.62, "learning_rate": 0.0006335, "loss": 1.873, "step": 12670 }, { "epoch": 2.63, "learning_rate": 0.0006337500000000001, "loss": 1.8737, "step": 12675 }, { "epoch": 2.63, "learning_rate": 0.000634, "loss": 1.8722, "step": 12680 }, { "epoch": 2.63, "learning_rate": 0.0006342499999999999, "loss": 1.8804, "step": 12685 }, { "epoch": 2.63, "learning_rate": 0.0006345, "loss": 1.8766, "step": 12690 }, { "epoch": 2.63, "learning_rate": 0.00063475, "loss": 1.876, "step": 12695 }, { "epoch": 2.63, "learning_rate": 0.000635, "loss": 1.8801, "step": 12700 }, { "epoch": 2.63, "learning_rate": 0.00063525, "loss": 1.8713, "step": 12705 }, { "epoch": 2.63, "learning_rate": 0.0006355, "loss": 1.8818, "step": 12710 }, { "epoch": 2.63, "learning_rate": 0.00063575, "loss": 1.8784, "step": 12715 }, { "epoch": 2.64, "learning_rate": 0.0006360000000000001, "loss": 1.8762, "step": 12720 }, { "epoch": 2.64, "learning_rate": 0.00063625, "loss": 1.8801, "step": 12725 }, { "epoch": 2.64, "learning_rate": 0.0006365, "loss": 1.876, "step": 12730 }, { "epoch": 2.64, "learning_rate": 0.0006367500000000001, "loss": 1.8749, "step": 12735 }, { "epoch": 2.64, "learning_rate": 0.000637, "loss": 1.8753, "step": 12740 }, { "epoch": 2.64, "learning_rate": 0.00063725, "loss": 1.8793, "step": 12745 }, { "epoch": 2.64, "learning_rate": 0.0006374999999999999, "loss": 1.8848, "step": 12750 }, { "epoch": 2.64, "learning_rate": 0.0006377500000000001, "loss": 1.88, "step": 12755 }, { "epoch": 2.64, "learning_rate": 0.000638, "loss": 1.8714, "step": 12760 }, { "epoch": 2.64, "learning_rate": 0.00063825, "loss": 1.8719, "step": 12765 }, { "epoch": 2.65, "learning_rate": 0.0006385, "loss": 1.8713, "step": 12770 }, { "epoch": 2.65, "learning_rate": 0.0006387500000000001, "loss": 1.8825, "step": 12775 }, { "epoch": 2.65, "learning_rate": 0.000639, "loss": 1.8746, "step": 12780 }, { "epoch": 2.65, "learning_rate": 0.00063925, "loss": 1.8796, "step": 12785 }, { "epoch": 2.65, "learning_rate": 0.0006395, "loss": 1.8796, "step": 12790 }, { "epoch": 2.65, "learning_rate": 0.00063975, "loss": 1.8787, "step": 12795 }, { "epoch": 2.65, "learning_rate": 0.00064, "loss": 1.8732, "step": 12800 }, { "epoch": 2.65, "learning_rate": 0.00064025, "loss": 1.8729, "step": 12805 }, { "epoch": 2.65, "learning_rate": 0.0006405, "loss": 1.8744, "step": 12810 }, { "epoch": 2.65, "learning_rate": 0.00064075, "loss": 1.873, "step": 12815 }, { "epoch": 2.66, "learning_rate": 0.0006410000000000001, "loss": 1.869, "step": 12820 }, { "epoch": 2.66, "learning_rate": 0.00064125, "loss": 1.8759, "step": 12825 }, { "epoch": 2.66, "learning_rate": 0.0006414999999999999, "loss": 1.876, "step": 12830 }, { "epoch": 2.66, "learning_rate": 0.0006417500000000001, "loss": 1.8802, "step": 12835 }, { "epoch": 2.66, "learning_rate": 0.000642, "loss": 1.8777, "step": 12840 }, { "epoch": 2.66, "learning_rate": 0.00064225, "loss": 1.8737, "step": 12845 }, { "epoch": 2.66, "learning_rate": 0.0006425, "loss": 1.8712, "step": 12850 }, { "epoch": 2.66, "learning_rate": 0.0006427500000000001, "loss": 1.8742, "step": 12855 }, { "epoch": 2.66, "learning_rate": 0.000643, "loss": 1.8783, "step": 12860 }, { "epoch": 2.67, "learning_rate": 0.00064325, "loss": 1.8799, "step": 12865 }, { "epoch": 2.67, "learning_rate": 0.0006435, "loss": 1.8718, "step": 12870 }, { "epoch": 2.67, "learning_rate": 0.00064375, "loss": 1.8709, "step": 12875 }, { "epoch": 2.67, "learning_rate": 0.000644, "loss": 1.8767, "step": 12880 }, { "epoch": 2.67, "learning_rate": 0.00064425, "loss": 1.8834, "step": 12885 }, { "epoch": 2.67, "learning_rate": 0.0006445, "loss": 1.8778, "step": 12890 }, { "epoch": 2.67, "learning_rate": 0.00064475, "loss": 1.8748, "step": 12895 }, { "epoch": 2.67, "learning_rate": 0.0006450000000000001, "loss": 1.8777, "step": 12900 }, { "epoch": 2.67, "learning_rate": 0.00064525, "loss": 1.881, "step": 12905 }, { "epoch": 2.67, "learning_rate": 0.0006455, "loss": 1.8768, "step": 12910 }, { "epoch": 2.68, "learning_rate": 0.0006457500000000001, "loss": 1.8732, "step": 12915 }, { "epoch": 2.68, "learning_rate": 0.000646, "loss": 1.8801, "step": 12920 }, { "epoch": 2.68, "learning_rate": 0.00064625, "loss": 1.8797, "step": 12925 }, { "epoch": 2.68, "learning_rate": 0.0006464999999999999, "loss": 1.8719, "step": 12930 }, { "epoch": 2.68, "learning_rate": 0.0006467500000000001, "loss": 1.8744, "step": 12935 }, { "epoch": 2.68, "learning_rate": 0.000647, "loss": 1.8742, "step": 12940 }, { "epoch": 2.68, "learning_rate": 0.00064725, "loss": 1.8739, "step": 12945 }, { "epoch": 2.68, "learning_rate": 0.0006475, "loss": 1.8768, "step": 12950 }, { "epoch": 2.68, "learning_rate": 0.0006477500000000001, "loss": 1.8761, "step": 12955 }, { "epoch": 2.68, "learning_rate": 0.000648, "loss": 1.8713, "step": 12960 }, { "epoch": 2.69, "learning_rate": 0.00064825, "loss": 1.8748, "step": 12965 }, { "epoch": 2.69, "learning_rate": 0.0006485, "loss": 1.8729, "step": 12970 }, { "epoch": 2.69, "learning_rate": 0.00064875, "loss": 1.8756, "step": 12975 }, { "epoch": 2.69, "learning_rate": 0.0006490000000000001, "loss": 1.8759, "step": 12980 }, { "epoch": 2.69, "learning_rate": 0.00064925, "loss": 1.8833, "step": 12985 }, { "epoch": 2.69, "learning_rate": 0.0006495, "loss": 1.8953, "step": 12990 }, { "epoch": 2.69, "learning_rate": 0.00064975, "loss": 1.8836, "step": 12995 }, { "epoch": 2.69, "learning_rate": 0.0006500000000000001, "loss": 1.885, "step": 13000 }, { "epoch": 2.69, "learning_rate": 0.00065025, "loss": 1.8748, "step": 13005 }, { "epoch": 2.7, "learning_rate": 0.0006504999999999999, "loss": 1.8748, "step": 13010 }, { "epoch": 2.7, "learning_rate": 0.0006507500000000001, "loss": 1.8712, "step": 13015 }, { "epoch": 2.7, "learning_rate": 0.000651, "loss": 1.8703, "step": 13020 }, { "epoch": 2.7, "learning_rate": 0.00065125, "loss": 1.8731, "step": 13025 }, { "epoch": 2.7, "learning_rate": 0.0006515, "loss": 1.8752, "step": 13030 }, { "epoch": 2.7, "learning_rate": 0.0006517500000000001, "loss": 1.8746, "step": 13035 }, { "epoch": 2.7, "learning_rate": 0.000652, "loss": 1.8784, "step": 13040 }, { "epoch": 2.7, "learning_rate": 0.00065225, "loss": 1.8771, "step": 13045 }, { "epoch": 2.7, "learning_rate": 0.0006525, "loss": 1.8752, "step": 13050 }, { "epoch": 2.7, "learning_rate": 0.0006527500000000001, "loss": 1.881, "step": 13055 }, { "epoch": 2.71, "learning_rate": 0.000653, "loss": 1.8726, "step": 13060 }, { "epoch": 2.71, "learning_rate": 0.00065325, "loss": 1.8742, "step": 13065 }, { "epoch": 2.71, "learning_rate": 0.0006535, "loss": 1.8731, "step": 13070 }, { "epoch": 2.71, "learning_rate": 0.00065375, "loss": 1.8748, "step": 13075 }, { "epoch": 2.71, "learning_rate": 0.0006540000000000001, "loss": 1.8766, "step": 13080 }, { "epoch": 2.71, "learning_rate": 0.00065425, "loss": 1.8766, "step": 13085 }, { "epoch": 2.71, "learning_rate": 0.0006545, "loss": 1.8711, "step": 13090 }, { "epoch": 2.71, "learning_rate": 0.0006547500000000001, "loss": 1.8762, "step": 13095 }, { "epoch": 2.71, "learning_rate": 0.0006550000000000001, "loss": 1.8714, "step": 13100 }, { "epoch": 2.71, "learning_rate": 0.00065525, "loss": 1.8721, "step": 13105 }, { "epoch": 2.72, "learning_rate": 0.0006554999999999999, "loss": 1.8687, "step": 13110 }, { "epoch": 2.72, "learning_rate": 0.0006557500000000001, "loss": 1.8726, "step": 13115 }, { "epoch": 2.72, "learning_rate": 0.000656, "loss": 1.8725, "step": 13120 }, { "epoch": 2.72, "learning_rate": 0.00065625, "loss": 1.877, "step": 13125 }, { "epoch": 2.72, "learning_rate": 0.0006565, "loss": 1.8734, "step": 13130 }, { "epoch": 2.72, "learning_rate": 0.00065675, "loss": 1.8738, "step": 13135 }, { "epoch": 2.72, "learning_rate": 0.000657, "loss": 1.8675, "step": 13140 }, { "epoch": 2.72, "learning_rate": 0.0006572500000000001, "loss": 1.8748, "step": 13145 }, { "epoch": 2.72, "learning_rate": 0.0006575, "loss": 1.8753, "step": 13150 }, { "epoch": 2.73, "learning_rate": 0.0006577499999999999, "loss": 1.8734, "step": 13155 }, { "epoch": 2.73, "learning_rate": 0.0006580000000000001, "loss": 1.8738, "step": 13160 }, { "epoch": 2.73, "learning_rate": 0.00065825, "loss": 1.872, "step": 13165 }, { "epoch": 2.73, "learning_rate": 0.0006585, "loss": 1.8741, "step": 13170 }, { "epoch": 2.73, "learning_rate": 0.0006587499999999999, "loss": 1.8754, "step": 13175 }, { "epoch": 2.73, "learning_rate": 0.0006590000000000001, "loss": 1.8671, "step": 13180 }, { "epoch": 2.73, "learning_rate": 0.00065925, "loss": 1.8749, "step": 13185 }, { "epoch": 2.73, "learning_rate": 0.0006595, "loss": 1.8706, "step": 13190 }, { "epoch": 2.73, "learning_rate": 0.00065975, "loss": 1.8741, "step": 13195 }, { "epoch": 2.73, "learning_rate": 0.00066, "loss": 1.8771, "step": 13200 }, { "epoch": 2.74, "learning_rate": 0.00066025, "loss": 1.8679, "step": 13205 }, { "epoch": 2.74, "learning_rate": 0.0006605, "loss": 1.8731, "step": 13210 }, { "epoch": 2.74, "learning_rate": 0.00066075, "loss": 1.8691, "step": 13215 }, { "epoch": 2.74, "learning_rate": 0.000661, "loss": 1.8796, "step": 13220 }, { "epoch": 2.74, "learning_rate": 0.00066125, "loss": 1.8754, "step": 13225 }, { "epoch": 2.74, "learning_rate": 0.0006615, "loss": 1.8749, "step": 13230 }, { "epoch": 2.74, "learning_rate": 0.00066175, "loss": 1.8728, "step": 13235 }, { "epoch": 2.74, "learning_rate": 0.000662, "loss": 1.8696, "step": 13240 }, { "epoch": 2.74, "learning_rate": 0.00066225, "loss": 1.8728, "step": 13245 }, { "epoch": 2.74, "learning_rate": 0.0006625, "loss": 1.8738, "step": 13250 }, { "epoch": 2.75, "learning_rate": 0.0006627499999999999, "loss": 1.8756, "step": 13255 }, { "epoch": 2.75, "learning_rate": 0.0006630000000000001, "loss": 1.8669, "step": 13260 }, { "epoch": 2.75, "learning_rate": 0.00066325, "loss": 1.8791, "step": 13265 }, { "epoch": 2.75, "learning_rate": 0.0006635, "loss": 1.8719, "step": 13270 }, { "epoch": 2.75, "learning_rate": 0.00066375, "loss": 1.8705, "step": 13275 }, { "epoch": 2.75, "learning_rate": 0.0006640000000000001, "loss": 1.8725, "step": 13280 }, { "epoch": 2.75, "learning_rate": 0.00066425, "loss": 1.8692, "step": 13285 }, { "epoch": 2.75, "learning_rate": 0.0006644999999999999, "loss": 1.8695, "step": 13290 }, { "epoch": 2.75, "learning_rate": 0.00066475, "loss": 1.8699, "step": 13295 }, { "epoch": 2.76, "learning_rate": 0.000665, "loss": 1.8732, "step": 13300 }, { "epoch": 2.76, "learning_rate": 0.00066525, "loss": 1.8653, "step": 13305 }, { "epoch": 2.76, "learning_rate": 0.0006655, "loss": 1.8679, "step": 13310 }, { "epoch": 2.76, "learning_rate": 0.00066575, "loss": 1.8766, "step": 13315 }, { "epoch": 2.76, "learning_rate": 0.000666, "loss": 1.873, "step": 13320 }, { "epoch": 2.76, "learning_rate": 0.0006662500000000001, "loss": 1.8685, "step": 13325 }, { "epoch": 2.76, "learning_rate": 0.0006665, "loss": 1.8706, "step": 13330 }, { "epoch": 2.76, "learning_rate": 0.0006667499999999999, "loss": 1.8699, "step": 13335 }, { "epoch": 2.76, "learning_rate": 0.0006670000000000001, "loss": 1.8725, "step": 13340 }, { "epoch": 2.76, "learning_rate": 0.00066725, "loss": 1.8674, "step": 13345 }, { "epoch": 2.77, "learning_rate": 0.0006675, "loss": 1.8703, "step": 13350 }, { "epoch": 2.77, "learning_rate": 0.0006677499999999999, "loss": 1.8719, "step": 13355 }, { "epoch": 2.77, "learning_rate": 0.0006680000000000001, "loss": 1.8711, "step": 13360 }, { "epoch": 2.77, "learning_rate": 0.00066825, "loss": 1.8698, "step": 13365 }, { "epoch": 2.77, "learning_rate": 0.0006685, "loss": 1.8693, "step": 13370 }, { "epoch": 2.77, "learning_rate": 0.00066875, "loss": 1.8709, "step": 13375 }, { "epoch": 2.77, "learning_rate": 0.0006690000000000001, "loss": 1.8695, "step": 13380 }, { "epoch": 2.77, "learning_rate": 0.00066925, "loss": 1.8717, "step": 13385 }, { "epoch": 2.77, "learning_rate": 0.0006695, "loss": 1.8692, "step": 13390 }, { "epoch": 2.78, "learning_rate": 0.00066975, "loss": 1.8729, "step": 13395 }, { "epoch": 2.78, "learning_rate": 0.00067, "loss": 1.8692, "step": 13400 }, { "epoch": 2.78, "learning_rate": 0.0006702500000000001, "loss": 1.8761, "step": 13405 }, { "epoch": 2.78, "learning_rate": 0.0006705, "loss": 1.8717, "step": 13410 }, { "epoch": 2.78, "learning_rate": 0.00067075, "loss": 1.8729, "step": 13415 }, { "epoch": 2.78, "learning_rate": 0.000671, "loss": 1.87, "step": 13420 }, { "epoch": 2.78, "learning_rate": 0.0006712500000000001, "loss": 1.8696, "step": 13425 }, { "epoch": 2.78, "learning_rate": 0.0006715, "loss": 1.8691, "step": 13430 }, { "epoch": 2.78, "learning_rate": 0.0006717499999999999, "loss": 1.8696, "step": 13435 }, { "epoch": 2.78, "learning_rate": 0.0006720000000000001, "loss": 1.8696, "step": 13440 }, { "epoch": 2.79, "learning_rate": 0.00067225, "loss": 1.874, "step": 13445 }, { "epoch": 2.79, "learning_rate": 0.0006725, "loss": 1.8736, "step": 13450 }, { "epoch": 2.79, "learning_rate": 0.00067275, "loss": 1.8711, "step": 13455 }, { "epoch": 2.79, "learning_rate": 0.0006730000000000001, "loss": 1.8696, "step": 13460 }, { "epoch": 2.79, "learning_rate": 0.00067325, "loss": 1.8674, "step": 13465 }, { "epoch": 2.79, "learning_rate": 0.0006735, "loss": 1.8681, "step": 13470 }, { "epoch": 2.79, "learning_rate": 0.00067375, "loss": 1.8712, "step": 13475 }, { "epoch": 2.79, "learning_rate": 0.000674, "loss": 1.8745, "step": 13480 }, { "epoch": 2.79, "learning_rate": 0.00067425, "loss": 1.8718, "step": 13485 }, { "epoch": 2.79, "learning_rate": 0.0006745, "loss": 1.8744, "step": 13490 }, { "epoch": 2.8, "learning_rate": 0.00067475, "loss": 1.8674, "step": 13495 }, { "epoch": 2.8, "learning_rate": 0.000675, "loss": 1.8714, "step": 13500 }, { "epoch": 2.8, "learning_rate": 0.0006752500000000001, "loss": 1.8666, "step": 13505 }, { "epoch": 2.8, "learning_rate": 0.0006755, "loss": 1.8746, "step": 13510 }, { "epoch": 2.8, "learning_rate": 0.00067575, "loss": 1.8765, "step": 13515 }, { "epoch": 2.8, "learning_rate": 0.0006760000000000001, "loss": 1.8691, "step": 13520 }, { "epoch": 2.8, "learning_rate": 0.00067625, "loss": 1.8725, "step": 13525 }, { "epoch": 2.8, "learning_rate": 0.0006765, "loss": 1.8715, "step": 13530 }, { "epoch": 2.8, "learning_rate": 0.0006767499999999999, "loss": 1.8705, "step": 13535 }, { "epoch": 2.81, "learning_rate": 0.0006770000000000001, "loss": 1.8697, "step": 13540 }, { "epoch": 2.81, "learning_rate": 0.00067725, "loss": 1.8743, "step": 13545 }, { "epoch": 2.81, "learning_rate": 0.0006775, "loss": 1.8689, "step": 13550 }, { "epoch": 2.81, "learning_rate": 0.00067775, "loss": 1.8724, "step": 13555 }, { "epoch": 2.81, "learning_rate": 0.0006780000000000001, "loss": 1.8748, "step": 13560 }, { "epoch": 2.81, "learning_rate": 0.00067825, "loss": 1.8697, "step": 13565 }, { "epoch": 2.81, "learning_rate": 0.0006785, "loss": 1.8687, "step": 13570 }, { "epoch": 2.81, "learning_rate": 0.00067875, "loss": 1.8646, "step": 13575 }, { "epoch": 2.81, "learning_rate": 0.000679, "loss": 1.8677, "step": 13580 }, { "epoch": 2.81, "learning_rate": 0.0006792500000000001, "loss": 1.8687, "step": 13585 }, { "epoch": 2.82, "learning_rate": 0.0006795, "loss": 1.8703, "step": 13590 }, { "epoch": 2.82, "learning_rate": 0.00067975, "loss": 1.8718, "step": 13595 }, { "epoch": 2.82, "learning_rate": 0.00068, "loss": 1.8728, "step": 13600 }, { "epoch": 2.82, "learning_rate": 0.0006802500000000001, "loss": 1.8674, "step": 13605 }, { "epoch": 2.82, "learning_rate": 0.0006805, "loss": 1.8777, "step": 13610 }, { "epoch": 2.82, "learning_rate": 0.0006807499999999999, "loss": 1.8692, "step": 13615 }, { "epoch": 2.82, "learning_rate": 0.0006810000000000001, "loss": 1.8671, "step": 13620 }, { "epoch": 2.82, "learning_rate": 0.00068125, "loss": 1.8713, "step": 13625 }, { "epoch": 2.82, "learning_rate": 0.0006815, "loss": 1.8655, "step": 13630 }, { "epoch": 2.82, "learning_rate": 0.00068175, "loss": 1.8649, "step": 13635 }, { "epoch": 2.83, "learning_rate": 0.0006820000000000001, "loss": 1.87, "step": 13640 }, { "epoch": 2.83, "learning_rate": 0.00068225, "loss": 1.8691, "step": 13645 }, { "epoch": 2.83, "learning_rate": 0.0006825000000000001, "loss": 1.8722, "step": 13650 }, { "epoch": 2.83, "learning_rate": 0.00068275, "loss": 1.8701, "step": 13655 }, { "epoch": 2.83, "learning_rate": 0.000683, "loss": 1.8716, "step": 13660 }, { "epoch": 2.83, "learning_rate": 0.00068325, "loss": 1.8725, "step": 13665 }, { "epoch": 2.83, "learning_rate": 0.0006835, "loss": 1.8746, "step": 13670 }, { "epoch": 2.83, "learning_rate": 0.00068375, "loss": 1.8726, "step": 13675 }, { "epoch": 2.83, "learning_rate": 0.000684, "loss": 1.8654, "step": 13680 }, { "epoch": 2.84, "learning_rate": 0.0006842500000000001, "loss": 1.8678, "step": 13685 }, { "epoch": 2.84, "learning_rate": 0.0006845, "loss": 1.8704, "step": 13690 }, { "epoch": 2.84, "learning_rate": 0.00068475, "loss": 1.8647, "step": 13695 }, { "epoch": 2.84, "learning_rate": 0.0006850000000000001, "loss": 1.868, "step": 13700 }, { "epoch": 2.84, "learning_rate": 0.00068525, "loss": 1.868, "step": 13705 }, { "epoch": 2.84, "learning_rate": 0.0006855, "loss": 1.8711, "step": 13710 }, { "epoch": 2.84, "learning_rate": 0.0006857499999999999, "loss": 1.8702, "step": 13715 }, { "epoch": 2.84, "learning_rate": 0.0006860000000000001, "loss": 1.8679, "step": 13720 }, { "epoch": 2.84, "learning_rate": 0.00068625, "loss": 1.8669, "step": 13725 }, { "epoch": 2.84, "learning_rate": 0.0006865, "loss": 1.871, "step": 13730 }, { "epoch": 2.85, "learning_rate": 0.00068675, "loss": 1.8724, "step": 13735 }, { "epoch": 2.85, "learning_rate": 0.0006870000000000001, "loss": 1.8727, "step": 13740 }, { "epoch": 2.85, "learning_rate": 0.00068725, "loss": 1.8742, "step": 13745 }, { "epoch": 2.85, "learning_rate": 0.0006875, "loss": 1.8736, "step": 13750 }, { "epoch": 2.85, "learning_rate": 0.00068775, "loss": 1.8705, "step": 13755 }, { "epoch": 2.85, "learning_rate": 0.0006879999999999999, "loss": 1.8676, "step": 13760 }, { "epoch": 2.85, "learning_rate": 0.0006882500000000001, "loss": 1.8662, "step": 13765 }, { "epoch": 2.85, "learning_rate": 0.0006885, "loss": 1.8678, "step": 13770 }, { "epoch": 2.85, "learning_rate": 0.00068875, "loss": 1.8757, "step": 13775 }, { "epoch": 2.85, "learning_rate": 0.0006889999999999999, "loss": 1.8714, "step": 13780 }, { "epoch": 2.86, "learning_rate": 0.0006892500000000001, "loss": 1.8663, "step": 13785 }, { "epoch": 2.86, "learning_rate": 0.0006895, "loss": 1.8668, "step": 13790 }, { "epoch": 2.86, "learning_rate": 0.00068975, "loss": 1.8668, "step": 13795 }, { "epoch": 2.86, "learning_rate": 0.00069, "loss": 1.869, "step": 13800 }, { "epoch": 2.86, "learning_rate": 0.00069025, "loss": 1.8687, "step": 13805 }, { "epoch": 2.86, "learning_rate": 0.0006905, "loss": 1.8623, "step": 13810 }, { "epoch": 2.86, "learning_rate": 0.00069075, "loss": 1.8661, "step": 13815 }, { "epoch": 2.86, "learning_rate": 0.000691, "loss": 1.8703, "step": 13820 }, { "epoch": 2.86, "learning_rate": 0.00069125, "loss": 1.8653, "step": 13825 }, { "epoch": 2.87, "learning_rate": 0.0006915000000000001, "loss": 1.8704, "step": 13830 }, { "epoch": 2.87, "learning_rate": 0.00069175, "loss": 1.8666, "step": 13835 }, { "epoch": 2.87, "learning_rate": 0.000692, "loss": 1.8728, "step": 13840 }, { "epoch": 2.87, "learning_rate": 0.00069225, "loss": 1.8679, "step": 13845 }, { "epoch": 2.87, "learning_rate": 0.0006925, "loss": 1.8703, "step": 13850 }, { "epoch": 2.87, "learning_rate": 0.00069275, "loss": 1.8673, "step": 13855 }, { "epoch": 2.87, "learning_rate": 0.0006929999999999999, "loss": 1.8625, "step": 13860 }, { "epoch": 2.87, "learning_rate": 0.0006932500000000001, "loss": 1.8651, "step": 13865 }, { "epoch": 2.87, "learning_rate": 0.0006935, "loss": 1.8708, "step": 13870 }, { "epoch": 2.87, "learning_rate": 0.00069375, "loss": 1.8641, "step": 13875 }, { "epoch": 2.88, "learning_rate": 0.000694, "loss": 1.8666, "step": 13880 }, { "epoch": 2.88, "learning_rate": 0.0006942500000000001, "loss": 1.8647, "step": 13885 }, { "epoch": 2.88, "learning_rate": 0.0006945, "loss": 1.866, "step": 13890 }, { "epoch": 2.88, "learning_rate": 0.00069475, "loss": 1.8665, "step": 13895 }, { "epoch": 2.88, "learning_rate": 0.000695, "loss": 1.865, "step": 13900 }, { "epoch": 2.88, "learning_rate": 0.00069525, "loss": 1.8687, "step": 13905 }, { "epoch": 2.88, "learning_rate": 0.0006955, "loss": 1.8634, "step": 13910 }, { "epoch": 2.88, "learning_rate": 0.00069575, "loss": 1.8701, "step": 13915 }, { "epoch": 2.88, "learning_rate": 0.000696, "loss": 1.866, "step": 13920 }, { "epoch": 2.88, "learning_rate": 0.00069625, "loss": 1.8663, "step": 13925 }, { "epoch": 2.89, "learning_rate": 0.0006965000000000001, "loss": 1.8659, "step": 13930 }, { "epoch": 2.89, "learning_rate": 0.00069675, "loss": 1.8709, "step": 13935 }, { "epoch": 2.89, "learning_rate": 0.0006969999999999999, "loss": 1.8699, "step": 13940 }, { "epoch": 2.89, "learning_rate": 0.0006972500000000001, "loss": 1.8634, "step": 13945 }, { "epoch": 2.89, "learning_rate": 0.0006975, "loss": 1.8673, "step": 13950 }, { "epoch": 2.89, "learning_rate": 0.00069775, "loss": 1.8677, "step": 13955 }, { "epoch": 2.89, "learning_rate": 0.0006979999999999999, "loss": 1.8661, "step": 13960 }, { "epoch": 2.89, "learning_rate": 0.0006982500000000001, "loss": 1.8677, "step": 13965 }, { "epoch": 2.89, "learning_rate": 0.0006985, "loss": 1.8683, "step": 13970 }, { "epoch": 2.9, "learning_rate": 0.00069875, "loss": 1.8662, "step": 13975 }, { "epoch": 2.9, "learning_rate": 0.000699, "loss": 1.8599, "step": 13980 }, { "epoch": 2.9, "learning_rate": 0.00069925, "loss": 1.8677, "step": 13985 }, { "epoch": 2.9, "learning_rate": 0.0006995, "loss": 1.8642, "step": 13990 }, { "epoch": 2.9, "learning_rate": 0.00069975, "loss": 1.8725, "step": 13995 }, { "epoch": 2.9, "learning_rate": 0.0007, "loss": 1.8792, "step": 14000 }, { "epoch": 2.9, "learning_rate": 0.00070025, "loss": 1.8798, "step": 14005 }, { "epoch": 2.9, "learning_rate": 0.0007005000000000001, "loss": 1.8739, "step": 14010 }, { "epoch": 2.9, "learning_rate": 0.00070075, "loss": 1.8757, "step": 14015 }, { "epoch": 2.9, "learning_rate": 0.000701, "loss": 1.8658, "step": 14020 }, { "epoch": 2.91, "learning_rate": 0.00070125, "loss": 1.8692, "step": 14025 }, { "epoch": 2.91, "learning_rate": 0.0007015, "loss": 1.866, "step": 14030 }, { "epoch": 2.91, "learning_rate": 0.00070175, "loss": 1.8706, "step": 14035 }, { "epoch": 2.91, "learning_rate": 0.0007019999999999999, "loss": 1.8672, "step": 14040 }, { "epoch": 2.91, "learning_rate": 0.0007022500000000001, "loss": 1.8732, "step": 14045 }, { "epoch": 2.91, "learning_rate": 0.0007025, "loss": 1.865, "step": 14050 }, { "epoch": 2.91, "learning_rate": 0.00070275, "loss": 1.8614, "step": 14055 }, { "epoch": 2.91, "learning_rate": 0.000703, "loss": 1.8611, "step": 14060 }, { "epoch": 2.91, "learning_rate": 0.0007032500000000001, "loss": 1.8652, "step": 14065 }, { "epoch": 2.91, "learning_rate": 0.0007035, "loss": 1.8764, "step": 14070 }, { "epoch": 2.92, "learning_rate": 0.00070375, "loss": 1.8648, "step": 14075 }, { "epoch": 2.92, "learning_rate": 0.000704, "loss": 1.8657, "step": 14080 }, { "epoch": 2.92, "learning_rate": 0.00070425, "loss": 1.8679, "step": 14085 }, { "epoch": 2.92, "learning_rate": 0.0007045, "loss": 1.8752, "step": 14090 }, { "epoch": 2.92, "learning_rate": 0.00070475, "loss": 1.8644, "step": 14095 }, { "epoch": 2.92, "learning_rate": 0.000705, "loss": 1.8641, "step": 14100 }, { "epoch": 2.92, "learning_rate": 0.00070525, "loss": 1.8681, "step": 14105 }, { "epoch": 2.92, "learning_rate": 0.0007055000000000001, "loss": 1.8672, "step": 14110 }, { "epoch": 2.92, "learning_rate": 0.00070575, "loss": 1.8636, "step": 14115 }, { "epoch": 2.93, "learning_rate": 0.0007059999999999999, "loss": 1.8578, "step": 14120 }, { "epoch": 2.93, "learning_rate": 0.0007062500000000001, "loss": 1.8635, "step": 14125 }, { "epoch": 2.93, "learning_rate": 0.0007065, "loss": 1.8623, "step": 14130 }, { "epoch": 2.93, "learning_rate": 0.00070675, "loss": 1.8654, "step": 14135 }, { "epoch": 2.93, "learning_rate": 0.000707, "loss": 1.8635, "step": 14140 }, { "epoch": 2.93, "learning_rate": 0.0007072500000000001, "loss": 1.8671, "step": 14145 }, { "epoch": 2.93, "learning_rate": 0.0007075, "loss": 1.8547, "step": 14150 }, { "epoch": 2.93, "learning_rate": 0.00070775, "loss": 1.8683, "step": 14155 }, { "epoch": 2.93, "learning_rate": 0.000708, "loss": 1.8664, "step": 14160 }, { "epoch": 2.93, "learning_rate": 0.0007082500000000001, "loss": 1.8658, "step": 14165 }, { "epoch": 2.94, "learning_rate": 0.0007085, "loss": 1.865, "step": 14170 }, { "epoch": 2.94, "learning_rate": 0.00070875, "loss": 1.8673, "step": 14175 }, { "epoch": 2.94, "learning_rate": 0.000709, "loss": 1.8706, "step": 14180 }, { "epoch": 2.94, "learning_rate": 0.00070925, "loss": 1.8626, "step": 14185 }, { "epoch": 2.94, "learning_rate": 0.0007095000000000001, "loss": 1.8682, "step": 14190 }, { "epoch": 2.94, "learning_rate": 0.00070975, "loss": 1.8574, "step": 14195 }, { "epoch": 2.94, "learning_rate": 0.00071, "loss": 1.8639, "step": 14200 }, { "epoch": 2.94, "learning_rate": 0.00071025, "loss": 1.8623, "step": 14205 }, { "epoch": 2.94, "learning_rate": 0.0007105000000000001, "loss": 1.8609, "step": 14210 }, { "epoch": 2.94, "learning_rate": 0.00071075, "loss": 1.8674, "step": 14215 }, { "epoch": 2.95, "learning_rate": 0.0007109999999999999, "loss": 1.8651, "step": 14220 }, { "epoch": 2.95, "learning_rate": 0.0007112500000000001, "loss": 1.861, "step": 14225 }, { "epoch": 2.95, "learning_rate": 0.0007115, "loss": 1.8661, "step": 14230 }, { "epoch": 2.95, "learning_rate": 0.00071175, "loss": 1.8722, "step": 14235 }, { "epoch": 2.95, "learning_rate": 0.000712, "loss": 1.8611, "step": 14240 }, { "epoch": 2.95, "learning_rate": 0.0007122500000000001, "loss": 1.8588, "step": 14245 }, { "epoch": 2.95, "learning_rate": 0.0007125, "loss": 1.8625, "step": 14250 }, { "epoch": 2.95, "learning_rate": 0.0007127500000000001, "loss": 1.8659, "step": 14255 }, { "epoch": 2.95, "learning_rate": 0.000713, "loss": 1.8579, "step": 14260 }, { "epoch": 2.96, "learning_rate": 0.00071325, "loss": 1.8632, "step": 14265 }, { "epoch": 2.96, "learning_rate": 0.0007135, "loss": 1.8616, "step": 14270 }, { "epoch": 2.96, "learning_rate": 0.00071375, "loss": 1.874, "step": 14275 }, { "epoch": 2.96, "learning_rate": 0.000714, "loss": 1.8684, "step": 14280 }, { "epoch": 2.96, "learning_rate": 0.00071425, "loss": 1.8707, "step": 14285 }, { "epoch": 2.96, "learning_rate": 0.0007145000000000001, "loss": 1.8686, "step": 14290 }, { "epoch": 2.96, "learning_rate": 0.00071475, "loss": 1.8622, "step": 14295 }, { "epoch": 2.96, "learning_rate": 0.000715, "loss": 1.8611, "step": 14300 }, { "epoch": 2.96, "learning_rate": 0.0007152500000000001, "loss": 1.8637, "step": 14305 }, { "epoch": 2.96, "learning_rate": 0.0007155, "loss": 1.8639, "step": 14310 }, { "epoch": 2.97, "learning_rate": 0.00071575, "loss": 1.8639, "step": 14315 }, { "epoch": 2.97, "learning_rate": 0.000716, "loss": 1.8609, "step": 14320 }, { "epoch": 2.97, "learning_rate": 0.0007162500000000001, "loss": 1.8635, "step": 14325 }, { "epoch": 2.97, "learning_rate": 0.0007165, "loss": 1.8641, "step": 14330 }, { "epoch": 2.97, "learning_rate": 0.00071675, "loss": 1.872, "step": 14335 }, { "epoch": 2.97, "learning_rate": 0.000717, "loss": 1.8625, "step": 14340 }, { "epoch": 2.97, "learning_rate": 0.0007172500000000001, "loss": 1.8651, "step": 14345 }, { "epoch": 2.97, "learning_rate": 0.0007175, "loss": 1.8645, "step": 14350 }, { "epoch": 2.97, "learning_rate": 0.00071775, "loss": 1.862, "step": 14355 }, { "epoch": 2.97, "learning_rate": 0.000718, "loss": 1.8663, "step": 14360 }, { "epoch": 2.98, "learning_rate": 0.00071825, "loss": 1.8616, "step": 14365 }, { "epoch": 2.98, "learning_rate": 0.0007185000000000001, "loss": 1.859, "step": 14370 }, { "epoch": 2.98, "learning_rate": 0.00071875, "loss": 1.8649, "step": 14375 }, { "epoch": 2.98, "learning_rate": 0.000719, "loss": 1.8636, "step": 14380 }, { "epoch": 2.98, "learning_rate": 0.00071925, "loss": 1.866, "step": 14385 }, { "epoch": 2.98, "learning_rate": 0.0007195000000000001, "loss": 1.8614, "step": 14390 }, { "epoch": 2.98, "learning_rate": 0.00071975, "loss": 1.8651, "step": 14395 }, { "epoch": 2.98, "learning_rate": 0.0007199999999999999, "loss": 1.8572, "step": 14400 }, { "epoch": 2.98, "learning_rate": 0.00072025, "loss": 1.8627, "step": 14405 }, { "epoch": 2.99, "learning_rate": 0.0007205, "loss": 1.8573, "step": 14410 }, { "epoch": 2.99, "learning_rate": 0.00072075, "loss": 1.8631, "step": 14415 }, { "epoch": 2.99, "learning_rate": 0.000721, "loss": 1.8636, "step": 14420 }, { "epoch": 2.99, "learning_rate": 0.00072125, "loss": 1.8681, "step": 14425 }, { "epoch": 2.99, "learning_rate": 0.0007215, "loss": 1.8627, "step": 14430 }, { "epoch": 2.99, "learning_rate": 0.0007217500000000001, "loss": 1.8666, "step": 14435 }, { "epoch": 2.99, "learning_rate": 0.000722, "loss": 1.8629, "step": 14440 }, { "epoch": 2.99, "learning_rate": 0.0007222499999999999, "loss": 1.862, "step": 14445 }, { "epoch": 2.99, "learning_rate": 0.0007225, "loss": 1.8633, "step": 14450 }, { "epoch": 2.99, "learning_rate": 0.00072275, "loss": 1.8633, "step": 14455 }, { "epoch": 3.0, "learning_rate": 0.000723, "loss": 1.8674, "step": 14460 }, { "epoch": 3.0, "learning_rate": 0.0007232499999999999, "loss": 1.8639, "step": 14465 }, { "epoch": 3.0, "learning_rate": 0.0007235000000000001, "loss": 1.8608, "step": 14470 }, { "epoch": 3.0, "learning_rate": 0.00072375, "loss": 1.8659, "step": 14475 }, { "epoch": 3.0, "learning_rate": 0.000724, "loss": 1.8688, "step": 14480 }, { "epoch": 3.0, "learning_rate": 0.00072425, "loss": 1.855, "step": 14485 }, { "epoch": 3.0, "learning_rate": 0.0007245000000000001, "loss": 1.8521, "step": 14490 }, { "epoch": 3.0, "learning_rate": 0.00072475, "loss": 1.8558, "step": 14495 }, { "epoch": 3.0, "learning_rate": 0.000725, "loss": 1.8534, "step": 14500 }, { "epoch": 3.0, "learning_rate": 0.00072525, "loss": 1.8553, "step": 14505 }, { "epoch": 3.01, "learning_rate": 0.0007255, "loss": 1.861, "step": 14510 }, { "epoch": 3.01, "learning_rate": 0.00072575, "loss": 1.8588, "step": 14515 }, { "epoch": 3.01, "learning_rate": 0.000726, "loss": 1.8545, "step": 14520 }, { "epoch": 3.01, "learning_rate": 0.00072625, "loss": 1.856, "step": 14525 }, { "epoch": 3.01, "learning_rate": 0.0007265, "loss": 1.8523, "step": 14530 }, { "epoch": 3.01, "learning_rate": 0.0007267500000000001, "loss": 1.8528, "step": 14535 }, { "epoch": 3.01, "learning_rate": 0.000727, "loss": 1.857, "step": 14540 }, { "epoch": 3.01, "learning_rate": 0.0007272499999999999, "loss": 1.8538, "step": 14545 }, { "epoch": 3.01, "learning_rate": 0.0007275000000000001, "loss": 1.8577, "step": 14550 }, { "epoch": 3.02, "learning_rate": 0.00072775, "loss": 1.8546, "step": 14555 }, { "epoch": 3.02, "learning_rate": 0.000728, "loss": 1.8653, "step": 14560 }, { "epoch": 3.02, "learning_rate": 0.00072825, "loss": 1.8593, "step": 14565 }, { "epoch": 3.02, "learning_rate": 0.0007285000000000001, "loss": 1.8595, "step": 14570 }, { "epoch": 3.02, "learning_rate": 0.00072875, "loss": 1.8524, "step": 14575 }, { "epoch": 3.02, "learning_rate": 0.000729, "loss": 1.8602, "step": 14580 }, { "epoch": 3.02, "learning_rate": 0.00072925, "loss": 1.8528, "step": 14585 }, { "epoch": 3.02, "learning_rate": 0.0007295, "loss": 1.8544, "step": 14590 }, { "epoch": 3.02, "learning_rate": 0.00072975, "loss": 1.8577, "step": 14595 }, { "epoch": 3.02, "learning_rate": 0.00073, "loss": 1.8566, "step": 14600 }, { "epoch": 3.03, "learning_rate": 0.00073025, "loss": 1.8536, "step": 14605 }, { "epoch": 3.03, "learning_rate": 0.0007305, "loss": 1.8543, "step": 14610 }, { "epoch": 3.03, "learning_rate": 0.0007307500000000001, "loss": 1.856, "step": 14615 }, { "epoch": 3.03, "learning_rate": 0.000731, "loss": 1.8581, "step": 14620 }, { "epoch": 3.03, "learning_rate": 0.00073125, "loss": 1.8588, "step": 14625 }, { "epoch": 3.03, "learning_rate": 0.0007315, "loss": 1.8582, "step": 14630 }, { "epoch": 3.03, "learning_rate": 0.00073175, "loss": 1.8552, "step": 14635 }, { "epoch": 3.03, "learning_rate": 0.000732, "loss": 1.8579, "step": 14640 }, { "epoch": 3.03, "learning_rate": 0.0007322499999999999, "loss": 1.8554, "step": 14645 }, { "epoch": 3.04, "learning_rate": 0.0007325000000000001, "loss": 1.8572, "step": 14650 }, { "epoch": 3.04, "learning_rate": 0.00073275, "loss": 1.8575, "step": 14655 }, { "epoch": 3.04, "learning_rate": 0.000733, "loss": 1.8549, "step": 14660 }, { "epoch": 3.04, "learning_rate": 0.00073325, "loss": 1.8581, "step": 14665 }, { "epoch": 3.04, "learning_rate": 0.0007335000000000001, "loss": 1.8669, "step": 14670 }, { "epoch": 3.04, "learning_rate": 0.00073375, "loss": 1.864, "step": 14675 }, { "epoch": 3.04, "learning_rate": 0.000734, "loss": 1.8596, "step": 14680 }, { "epoch": 3.04, "learning_rate": 0.00073425, "loss": 1.8561, "step": 14685 }, { "epoch": 3.04, "learning_rate": 0.0007345, "loss": 1.8586, "step": 14690 }, { "epoch": 3.04, "learning_rate": 0.00073475, "loss": 1.8599, "step": 14695 }, { "epoch": 3.05, "learning_rate": 0.000735, "loss": 1.8579, "step": 14700 }, { "epoch": 3.05, "learning_rate": 0.00073525, "loss": 1.8558, "step": 14705 }, { "epoch": 3.05, "learning_rate": 0.0007355, "loss": 1.8565, "step": 14710 }, { "epoch": 3.05, "learning_rate": 0.0007357500000000001, "loss": 1.8557, "step": 14715 }, { "epoch": 3.05, "learning_rate": 0.000736, "loss": 1.853, "step": 14720 }, { "epoch": 3.05, "learning_rate": 0.0007362499999999999, "loss": 1.8591, "step": 14725 }, { "epoch": 3.05, "learning_rate": 0.0007365000000000001, "loss": 1.8554, "step": 14730 }, { "epoch": 3.05, "learning_rate": 0.00073675, "loss": 1.8614, "step": 14735 }, { "epoch": 3.05, "learning_rate": 0.000737, "loss": 1.8592, "step": 14740 }, { "epoch": 3.05, "learning_rate": 0.00073725, "loss": 1.8595, "step": 14745 }, { "epoch": 3.06, "learning_rate": 0.0007375000000000001, "loss": 1.8528, "step": 14750 }, { "epoch": 3.06, "learning_rate": 0.00073775, "loss": 1.852, "step": 14755 }, { "epoch": 3.06, "learning_rate": 0.000738, "loss": 1.854, "step": 14760 }, { "epoch": 3.06, "learning_rate": 0.00073825, "loss": 1.8539, "step": 14765 }, { "epoch": 3.06, "learning_rate": 0.0007385, "loss": 1.8566, "step": 14770 }, { "epoch": 3.06, "learning_rate": 0.00073875, "loss": 1.8593, "step": 14775 }, { "epoch": 3.06, "learning_rate": 0.000739, "loss": 1.8536, "step": 14780 }, { "epoch": 3.06, "learning_rate": 0.00073925, "loss": 1.8553, "step": 14785 }, { "epoch": 3.06, "learning_rate": 0.0007395, "loss": 1.8552, "step": 14790 }, { "epoch": 3.07, "learning_rate": 0.0007397500000000001, "loss": 1.8554, "step": 14795 }, { "epoch": 3.07, "learning_rate": 0.00074, "loss": 1.8549, "step": 14800 }, { "epoch": 3.07, "learning_rate": 0.00074025, "loss": 1.8554, "step": 14805 }, { "epoch": 3.07, "learning_rate": 0.0007405000000000001, "loss": 1.8563, "step": 14810 }, { "epoch": 3.07, "learning_rate": 0.0007407500000000001, "loss": 1.8553, "step": 14815 }, { "epoch": 3.07, "learning_rate": 0.000741, "loss": 1.8578, "step": 14820 }, { "epoch": 3.07, "learning_rate": 0.0007412499999999999, "loss": 1.8602, "step": 14825 }, { "epoch": 3.07, "learning_rate": 0.0007415000000000001, "loss": 1.86, "step": 14830 }, { "epoch": 3.07, "learning_rate": 0.00074175, "loss": 1.8534, "step": 14835 }, { "epoch": 3.07, "learning_rate": 0.000742, "loss": 1.8557, "step": 14840 }, { "epoch": 3.08, "learning_rate": 0.00074225, "loss": 1.856, "step": 14845 }, { "epoch": 3.08, "learning_rate": 0.0007425000000000001, "loss": 1.8566, "step": 14850 }, { "epoch": 3.08, "learning_rate": 0.00074275, "loss": 1.8513, "step": 14855 }, { "epoch": 3.08, "learning_rate": 0.0007430000000000001, "loss": 1.8553, "step": 14860 }, { "epoch": 3.08, "learning_rate": 0.00074325, "loss": 1.8621, "step": 14865 }, { "epoch": 3.08, "learning_rate": 0.0007435, "loss": 1.8529, "step": 14870 }, { "epoch": 3.08, "learning_rate": 0.00074375, "loss": 1.8535, "step": 14875 }, { "epoch": 3.08, "learning_rate": 0.000744, "loss": 1.8587, "step": 14880 }, { "epoch": 3.08, "learning_rate": 0.00074425, "loss": 1.855, "step": 14885 }, { "epoch": 3.08, "learning_rate": 0.0007445, "loss": 1.8545, "step": 14890 }, { "epoch": 3.09, "learning_rate": 0.0007447500000000001, "loss": 1.8544, "step": 14895 }, { "epoch": 3.09, "learning_rate": 0.000745, "loss": 1.8541, "step": 14900 }, { "epoch": 3.09, "learning_rate": 0.00074525, "loss": 1.8523, "step": 14905 }, { "epoch": 3.09, "learning_rate": 0.0007455000000000001, "loss": 1.8582, "step": 14910 }, { "epoch": 3.09, "learning_rate": 0.00074575, "loss": 1.8517, "step": 14915 }, { "epoch": 3.09, "learning_rate": 0.000746, "loss": 1.8573, "step": 14920 }, { "epoch": 3.09, "learning_rate": 0.00074625, "loss": 1.8502, "step": 14925 }, { "epoch": 3.09, "learning_rate": 0.0007465000000000001, "loss": 1.8549, "step": 14930 }, { "epoch": 3.09, "learning_rate": 0.00074675, "loss": 1.8512, "step": 14935 }, { "epoch": 3.1, "learning_rate": 0.000747, "loss": 1.8517, "step": 14940 }, { "epoch": 3.1, "learning_rate": 0.00074725, "loss": 1.8535, "step": 14945 }, { "epoch": 3.1, "learning_rate": 0.0007475000000000001, "loss": 1.8513, "step": 14950 }, { "epoch": 3.1, "learning_rate": 0.00074775, "loss": 1.8523, "step": 14955 }, { "epoch": 3.1, "learning_rate": 0.000748, "loss": 1.8544, "step": 14960 }, { "epoch": 3.1, "learning_rate": 0.00074825, "loss": 1.875, "step": 14965 }, { "epoch": 3.1, "learning_rate": 0.0007485, "loss": 1.8685, "step": 14970 }, { "epoch": 3.1, "learning_rate": 0.0007487500000000001, "loss": 1.8635, "step": 14975 }, { "epoch": 3.1, "learning_rate": 0.000749, "loss": 1.8598, "step": 14980 }, { "epoch": 3.1, "learning_rate": 0.00074925, "loss": 1.8604, "step": 14985 }, { "epoch": 3.11, "learning_rate": 0.0007495000000000001, "loss": 1.8536, "step": 14990 }, { "epoch": 3.11, "learning_rate": 0.0007497500000000001, "loss": 1.8565, "step": 14995 }, { "epoch": 3.11, "learning_rate": 0.00075, "loss": 1.8524, "step": 15000 }, { "epoch": 3.11, "eval_accuracy": 0.5231895424836601, "eval_loss": 2.0396018028259277, "eval_runtime": 0.6523, "eval_samples_per_second": 229.939, "eval_steps_per_second": 1.533, "step": 15000 }, { "epoch": 3.11, "learning_rate": 0.0007502499999999999, "loss": 1.8513, "step": 15005 }, { "epoch": 3.11, "learning_rate": 0.0007505, "loss": 1.8515, "step": 15010 }, { "epoch": 3.11, "learning_rate": 0.00075075, "loss": 1.8619, "step": 15015 }, { "epoch": 3.11, "learning_rate": 0.000751, "loss": 1.8536, "step": 15020 }, { "epoch": 3.11, "learning_rate": 0.00075125, "loss": 1.8531, "step": 15025 }, { "epoch": 3.11, "learning_rate": 0.0007515, "loss": 1.8508, "step": 15030 }, { "epoch": 3.11, "learning_rate": 0.00075175, "loss": 1.8541, "step": 15035 }, { "epoch": 3.12, "learning_rate": 0.0007520000000000001, "loss": 1.8526, "step": 15040 }, { "epoch": 3.12, "learning_rate": 0.00075225, "loss": 1.8553, "step": 15045 }, { "epoch": 3.12, "learning_rate": 0.0007524999999999999, "loss": 1.8557, "step": 15050 }, { "epoch": 3.12, "learning_rate": 0.0007527500000000001, "loss": 1.8537, "step": 15055 }, { "epoch": 3.12, "learning_rate": 0.000753, "loss": 1.8517, "step": 15060 }, { "epoch": 3.12, "learning_rate": 0.00075325, "loss": 1.8507, "step": 15065 }, { "epoch": 3.12, "learning_rate": 0.0007534999999999999, "loss": 1.8572, "step": 15070 }, { "epoch": 3.12, "learning_rate": 0.0007537500000000001, "loss": 1.8535, "step": 15075 }, { "epoch": 3.12, "learning_rate": 0.000754, "loss": 1.8572, "step": 15080 }, { "epoch": 3.13, "learning_rate": 0.00075425, "loss": 1.8534, "step": 15085 }, { "epoch": 3.13, "learning_rate": 0.0007545, "loss": 1.8506, "step": 15090 }, { "epoch": 3.13, "learning_rate": 0.00075475, "loss": 1.8522, "step": 15095 }, { "epoch": 3.13, "learning_rate": 0.000755, "loss": 1.8548, "step": 15100 }, { "epoch": 3.13, "learning_rate": 0.00075525, "loss": 1.8537, "step": 15105 }, { "epoch": 3.13, "learning_rate": 0.0007555, "loss": 1.8516, "step": 15110 }, { "epoch": 3.13, "learning_rate": 0.00075575, "loss": 1.8516, "step": 15115 }, { "epoch": 3.13, "learning_rate": 0.000756, "loss": 1.8549, "step": 15120 }, { "epoch": 3.13, "learning_rate": 0.00075625, "loss": 1.8532, "step": 15125 }, { "epoch": 3.13, "learning_rate": 0.0007565, "loss": 1.8597, "step": 15130 }, { "epoch": 3.14, "learning_rate": 0.00075675, "loss": 1.8594, "step": 15135 }, { "epoch": 3.14, "learning_rate": 0.000757, "loss": 1.8551, "step": 15140 }, { "epoch": 3.14, "learning_rate": 0.00075725, "loss": 1.8575, "step": 15145 }, { "epoch": 3.14, "learning_rate": 0.0007574999999999999, "loss": 1.8477, "step": 15150 }, { "epoch": 3.14, "learning_rate": 0.0007577500000000001, "loss": 1.855, "step": 15155 }, { "epoch": 3.14, "learning_rate": 0.000758, "loss": 1.8509, "step": 15160 }, { "epoch": 3.14, "learning_rate": 0.00075825, "loss": 1.8536, "step": 15165 }, { "epoch": 3.14, "learning_rate": 0.0007585, "loss": 1.8573, "step": 15170 }, { "epoch": 3.14, "learning_rate": 0.0007587500000000001, "loss": 1.854, "step": 15175 }, { "epoch": 3.14, "learning_rate": 0.000759, "loss": 1.848, "step": 15180 }, { "epoch": 3.15, "learning_rate": 0.0007592499999999999, "loss": 1.8482, "step": 15185 }, { "epoch": 3.15, "learning_rate": 0.0007595, "loss": 1.8497, "step": 15190 }, { "epoch": 3.15, "learning_rate": 0.00075975, "loss": 1.8556, "step": 15195 }, { "epoch": 3.15, "learning_rate": 0.00076, "loss": 1.8561, "step": 15200 }, { "epoch": 3.15, "learning_rate": 0.00076025, "loss": 1.859, "step": 15205 }, { "epoch": 3.15, "learning_rate": 0.0007605, "loss": 1.8565, "step": 15210 }, { "epoch": 3.15, "learning_rate": 0.00076075, "loss": 1.8529, "step": 15215 }, { "epoch": 3.15, "learning_rate": 0.0007610000000000001, "loss": 1.8517, "step": 15220 }, { "epoch": 3.15, "learning_rate": 0.00076125, "loss": 1.8509, "step": 15225 }, { "epoch": 3.16, "learning_rate": 0.0007615, "loss": 1.8591, "step": 15230 }, { "epoch": 3.16, "learning_rate": 0.0007617500000000001, "loss": 1.8544, "step": 15235 }, { "epoch": 3.16, "learning_rate": 0.000762, "loss": 1.8549, "step": 15240 }, { "epoch": 3.16, "learning_rate": 0.00076225, "loss": 1.8531, "step": 15245 }, { "epoch": 3.16, "learning_rate": 0.0007624999999999999, "loss": 1.8488, "step": 15250 }, { "epoch": 3.16, "learning_rate": 0.0007627500000000001, "loss": 1.8537, "step": 15255 }, { "epoch": 3.16, "learning_rate": 0.000763, "loss": 1.8543, "step": 15260 }, { "epoch": 3.16, "learning_rate": 0.00076325, "loss": 1.8518, "step": 15265 }, { "epoch": 3.16, "learning_rate": 0.0007635, "loss": 1.8522, "step": 15270 }, { "epoch": 3.16, "learning_rate": 0.0007637500000000001, "loss": 1.8543, "step": 15275 }, { "epoch": 3.17, "learning_rate": 0.000764, "loss": 1.8544, "step": 15280 }, { "epoch": 3.17, "learning_rate": 0.00076425, "loss": 1.8578, "step": 15285 }, { "epoch": 3.17, "learning_rate": 0.0007645, "loss": 1.8538, "step": 15290 }, { "epoch": 3.17, "learning_rate": 0.00076475, "loss": 1.8584, "step": 15295 }, { "epoch": 3.17, "learning_rate": 0.0007650000000000001, "loss": 1.8565, "step": 15300 }, { "epoch": 3.17, "learning_rate": 0.00076525, "loss": 1.8543, "step": 15305 }, { "epoch": 3.17, "learning_rate": 0.0007655, "loss": 1.8487, "step": 15310 }, { "epoch": 3.17, "learning_rate": 0.00076575, "loss": 1.8551, "step": 15315 }, { "epoch": 3.17, "learning_rate": 0.0007660000000000001, "loss": 1.8481, "step": 15320 }, { "epoch": 3.17, "learning_rate": 0.00076625, "loss": 1.8541, "step": 15325 }, { "epoch": 3.18, "learning_rate": 0.0007664999999999999, "loss": 1.8533, "step": 15330 }, { "epoch": 3.18, "learning_rate": 0.0007667500000000001, "loss": 1.8472, "step": 15335 }, { "epoch": 3.18, "learning_rate": 0.000767, "loss": 1.8563, "step": 15340 }, { "epoch": 3.18, "learning_rate": 0.00076725, "loss": 1.8542, "step": 15345 }, { "epoch": 3.18, "learning_rate": 0.0007675, "loss": 1.8524, "step": 15350 }, { "epoch": 3.18, "learning_rate": 0.0007677500000000001, "loss": 1.8568, "step": 15355 }, { "epoch": 3.18, "learning_rate": 0.000768, "loss": 1.853, "step": 15360 }, { "epoch": 3.18, "learning_rate": 0.00076825, "loss": 1.8524, "step": 15365 }, { "epoch": 3.18, "learning_rate": 0.0007685, "loss": 1.8511, "step": 15370 }, { "epoch": 3.19, "learning_rate": 0.00076875, "loss": 1.8547, "step": 15375 }, { "epoch": 3.19, "learning_rate": 0.000769, "loss": 1.8537, "step": 15380 }, { "epoch": 3.19, "learning_rate": 0.00076925, "loss": 1.8523, "step": 15385 }, { "epoch": 3.19, "learning_rate": 0.0007695, "loss": 1.8473, "step": 15390 }, { "epoch": 3.19, "learning_rate": 0.00076975, "loss": 1.8526, "step": 15395 }, { "epoch": 3.19, "learning_rate": 0.0007700000000000001, "loss": 1.8517, "step": 15400 }, { "epoch": 3.19, "learning_rate": 0.00077025, "loss": 1.8572, "step": 15405 }, { "epoch": 3.19, "learning_rate": 0.0007705, "loss": 1.8513, "step": 15410 }, { "epoch": 3.19, "learning_rate": 0.0007707500000000001, "loss": 1.8496, "step": 15415 }, { "epoch": 3.19, "learning_rate": 0.000771, "loss": 1.8528, "step": 15420 }, { "epoch": 3.2, "learning_rate": 0.00077125, "loss": 1.8536, "step": 15425 }, { "epoch": 3.2, "learning_rate": 0.0007714999999999999, "loss": 1.8549, "step": 15430 }, { "epoch": 3.2, "learning_rate": 0.0007717500000000001, "loss": 1.8469, "step": 15435 }, { "epoch": 3.2, "learning_rate": 0.000772, "loss": 1.8527, "step": 15440 }, { "epoch": 3.2, "learning_rate": 0.00077225, "loss": 1.8594, "step": 15445 }, { "epoch": 3.2, "learning_rate": 0.0007725, "loss": 1.8518, "step": 15450 }, { "epoch": 3.2, "learning_rate": 0.0007727500000000001, "loss": 1.8562, "step": 15455 }, { "epoch": 3.2, "learning_rate": 0.000773, "loss": 1.8513, "step": 15460 }, { "epoch": 3.2, "learning_rate": 0.00077325, "loss": 1.8496, "step": 15465 }, { "epoch": 3.2, "learning_rate": 0.0007735, "loss": 1.8516, "step": 15470 }, { "epoch": 3.21, "learning_rate": 0.00077375, "loss": 1.8511, "step": 15475 }, { "epoch": 3.21, "learning_rate": 0.0007740000000000001, "loss": 1.8554, "step": 15480 }, { "epoch": 3.21, "learning_rate": 0.00077425, "loss": 1.8525, "step": 15485 }, { "epoch": 3.21, "learning_rate": 0.0007745, "loss": 1.8536, "step": 15490 }, { "epoch": 3.21, "learning_rate": 0.00077475, "loss": 1.8451, "step": 15495 }, { "epoch": 3.21, "learning_rate": 0.0007750000000000001, "loss": 1.8556, "step": 15500 }, { "epoch": 3.21, "learning_rate": 0.00077525, "loss": 1.8565, "step": 15505 }, { "epoch": 3.21, "learning_rate": 0.0007754999999999999, "loss": 1.8511, "step": 15510 }, { "epoch": 3.21, "learning_rate": 0.0007757500000000001, "loss": 1.8506, "step": 15515 }, { "epoch": 3.22, "learning_rate": 0.000776, "loss": 1.8497, "step": 15520 }, { "epoch": 3.22, "learning_rate": 0.00077625, "loss": 1.853, "step": 15525 }, { "epoch": 3.22, "learning_rate": 0.0007765, "loss": 1.8554, "step": 15530 }, { "epoch": 3.22, "learning_rate": 0.0007767500000000001, "loss": 1.8511, "step": 15535 }, { "epoch": 3.22, "learning_rate": 0.000777, "loss": 1.8522, "step": 15540 }, { "epoch": 3.22, "learning_rate": 0.0007772500000000001, "loss": 1.8451, "step": 15545 }, { "epoch": 3.22, "learning_rate": 0.0007775, "loss": 1.8522, "step": 15550 }, { "epoch": 3.22, "learning_rate": 0.0007777500000000001, "loss": 1.8527, "step": 15555 }, { "epoch": 3.22, "learning_rate": 0.000778, "loss": 1.8496, "step": 15560 }, { "epoch": 3.22, "learning_rate": 0.00077825, "loss": 1.8496, "step": 15565 }, { "epoch": 3.23, "learning_rate": 0.0007785, "loss": 1.8525, "step": 15570 }, { "epoch": 3.23, "learning_rate": 0.00077875, "loss": 1.8539, "step": 15575 }, { "epoch": 3.23, "learning_rate": 0.0007790000000000001, "loss": 1.8552, "step": 15580 }, { "epoch": 3.23, "learning_rate": 0.00077925, "loss": 1.8535, "step": 15585 }, { "epoch": 3.23, "learning_rate": 0.0007795, "loss": 1.8503, "step": 15590 }, { "epoch": 3.23, "learning_rate": 0.0007797500000000001, "loss": 1.851, "step": 15595 }, { "epoch": 3.23, "learning_rate": 0.0007800000000000001, "loss": 1.851, "step": 15600 }, { "epoch": 3.23, "learning_rate": 0.00078025, "loss": 1.8488, "step": 15605 }, { "epoch": 3.23, "learning_rate": 0.0007804999999999999, "loss": 1.845, "step": 15610 }, { "epoch": 3.23, "learning_rate": 0.0007807500000000001, "loss": 1.8504, "step": 15615 }, { "epoch": 3.24, "learning_rate": 0.000781, "loss": 1.8527, "step": 15620 }, { "epoch": 3.24, "learning_rate": 0.00078125, "loss": 1.8473, "step": 15625 }, { "epoch": 3.24, "learning_rate": 0.0007815, "loss": 1.8479, "step": 15630 }, { "epoch": 3.24, "learning_rate": 0.00078175, "loss": 1.851, "step": 15635 }, { "epoch": 3.24, "learning_rate": 0.000782, "loss": 1.8491, "step": 15640 }, { "epoch": 3.24, "learning_rate": 0.0007822500000000001, "loss": 1.848, "step": 15645 }, { "epoch": 3.24, "learning_rate": 0.0007825, "loss": 1.8523, "step": 15650 }, { "epoch": 3.24, "learning_rate": 0.0007827499999999999, "loss": 1.8551, "step": 15655 }, { "epoch": 3.24, "learning_rate": 0.0007830000000000001, "loss": 1.8543, "step": 15660 }, { "epoch": 3.25, "learning_rate": 0.00078325, "loss": 1.8509, "step": 15665 }, { "epoch": 3.25, "learning_rate": 0.0007835, "loss": 1.8726, "step": 15670 }, { "epoch": 3.25, "learning_rate": 0.0007837499999999999, "loss": 1.8661, "step": 15675 }, { "epoch": 3.25, "learning_rate": 0.0007840000000000001, "loss": 1.8655, "step": 15680 }, { "epoch": 3.25, "learning_rate": 0.00078425, "loss": 1.8634, "step": 15685 }, { "epoch": 3.25, "learning_rate": 0.0007845, "loss": 1.8559, "step": 15690 }, { "epoch": 3.25, "learning_rate": 0.00078475, "loss": 1.8552, "step": 15695 }, { "epoch": 3.25, "learning_rate": 0.000785, "loss": 1.8542, "step": 15700 }, { "epoch": 3.25, "learning_rate": 0.00078525, "loss": 1.8597, "step": 15705 }, { "epoch": 3.25, "learning_rate": 0.0007855, "loss": 1.8518, "step": 15710 }, { "epoch": 3.26, "learning_rate": 0.00078575, "loss": 1.8544, "step": 15715 }, { "epoch": 3.26, "learning_rate": 0.000786, "loss": 1.8521, "step": 15720 }, { "epoch": 3.26, "learning_rate": 0.0007862500000000001, "loss": 1.8467, "step": 15725 }, { "epoch": 3.26, "learning_rate": 0.0007865, "loss": 1.8529, "step": 15730 }, { "epoch": 3.26, "learning_rate": 0.00078675, "loss": 1.8526, "step": 15735 }, { "epoch": 3.26, "learning_rate": 0.000787, "loss": 1.8487, "step": 15740 }, { "epoch": 3.26, "learning_rate": 0.00078725, "loss": 1.8515, "step": 15745 }, { "epoch": 3.26, "learning_rate": 0.0007875, "loss": 1.8453, "step": 15750 }, { "epoch": 3.26, "learning_rate": 0.0007877499999999999, "loss": 1.8546, "step": 15755 }, { "epoch": 3.26, "learning_rate": 0.0007880000000000001, "loss": 1.8494, "step": 15760 }, { "epoch": 3.27, "learning_rate": 0.00078825, "loss": 1.854, "step": 15765 }, { "epoch": 3.27, "learning_rate": 0.0007885, "loss": 1.8521, "step": 15770 }, { "epoch": 3.27, "learning_rate": 0.00078875, "loss": 1.8506, "step": 15775 }, { "epoch": 3.27, "learning_rate": 0.0007890000000000001, "loss": 1.8503, "step": 15780 }, { "epoch": 3.27, "learning_rate": 0.00078925, "loss": 1.8513, "step": 15785 }, { "epoch": 3.27, "learning_rate": 0.0007894999999999999, "loss": 1.8486, "step": 15790 }, { "epoch": 3.27, "learning_rate": 0.00078975, "loss": 1.8465, "step": 15795 }, { "epoch": 3.27, "learning_rate": 0.00079, "loss": 1.8508, "step": 15800 }, { "epoch": 3.27, "learning_rate": 0.00079025, "loss": 1.8499, "step": 15805 }, { "epoch": 3.28, "learning_rate": 0.0007905, "loss": 1.8535, "step": 15810 }, { "epoch": 3.28, "learning_rate": 0.00079075, "loss": 1.8482, "step": 15815 }, { "epoch": 3.28, "learning_rate": 0.000791, "loss": 1.8492, "step": 15820 }, { "epoch": 3.28, "learning_rate": 0.0007912500000000001, "loss": 1.8492, "step": 15825 }, { "epoch": 3.28, "learning_rate": 0.0007915, "loss": 1.8492, "step": 15830 }, { "epoch": 3.28, "learning_rate": 0.0007917499999999999, "loss": 1.8546, "step": 15835 }, { "epoch": 3.28, "learning_rate": 0.0007920000000000001, "loss": 1.8476, "step": 15840 }, { "epoch": 3.28, "learning_rate": 0.00079225, "loss": 1.8505, "step": 15845 }, { "epoch": 3.28, "learning_rate": 0.0007925, "loss": 1.8698, "step": 15850 }, { "epoch": 3.28, "learning_rate": 0.0007927499999999999, "loss": 1.8641, "step": 15855 }, { "epoch": 3.29, "learning_rate": 0.0007930000000000001, "loss": 1.8602, "step": 15860 }, { "epoch": 3.29, "learning_rate": 0.00079325, "loss": 1.8574, "step": 15865 }, { "epoch": 3.29, "learning_rate": 0.0007935, "loss": 1.8536, "step": 15870 }, { "epoch": 3.29, "learning_rate": 0.00079375, "loss": 1.8543, "step": 15875 }, { "epoch": 3.29, "learning_rate": 0.0007940000000000001, "loss": 1.8434, "step": 15880 }, { "epoch": 3.29, "learning_rate": 0.00079425, "loss": 1.8528, "step": 15885 }, { "epoch": 3.29, "learning_rate": 0.0007945, "loss": 1.851, "step": 15890 }, { "epoch": 3.29, "learning_rate": 0.00079475, "loss": 1.8654, "step": 15895 }, { "epoch": 3.29, "learning_rate": 0.000795, "loss": 1.8562, "step": 15900 }, { "epoch": 3.3, "learning_rate": 0.0007952500000000001, "loss": 1.8564, "step": 15905 }, { "epoch": 3.3, "learning_rate": 0.0007955, "loss": 1.8546, "step": 15910 }, { "epoch": 3.3, "learning_rate": 0.00079575, "loss": 1.855, "step": 15915 }, { "epoch": 3.3, "learning_rate": 0.000796, "loss": 1.8514, "step": 15920 }, { "epoch": 3.3, "learning_rate": 0.0007962500000000001, "loss": 1.8469, "step": 15925 }, { "epoch": 3.3, "learning_rate": 0.0007965, "loss": 1.8557, "step": 15930 }, { "epoch": 3.3, "learning_rate": 0.0007967499999999999, "loss": 1.8472, "step": 15935 }, { "epoch": 3.3, "learning_rate": 0.0007970000000000001, "loss": 1.8498, "step": 15940 }, { "epoch": 3.3, "learning_rate": 0.00079725, "loss": 1.8578, "step": 15945 }, { "epoch": 3.3, "learning_rate": 0.0007975, "loss": 1.8519, "step": 15950 }, { "epoch": 3.31, "learning_rate": 0.00079775, "loss": 1.8518, "step": 15955 }, { "epoch": 3.31, "learning_rate": 0.0007980000000000001, "loss": 1.8515, "step": 15960 }, { "epoch": 3.31, "learning_rate": 0.00079825, "loss": 1.8522, "step": 15965 }, { "epoch": 3.31, "learning_rate": 0.0007985000000000001, "loss": 1.8506, "step": 15970 }, { "epoch": 3.31, "learning_rate": 0.00079875, "loss": 1.8481, "step": 15975 }, { "epoch": 3.31, "learning_rate": 0.000799, "loss": 1.8454, "step": 15980 }, { "epoch": 3.31, "learning_rate": 0.00079925, "loss": 1.8498, "step": 15985 }, { "epoch": 3.31, "learning_rate": 0.0007995, "loss": 1.8534, "step": 15990 }, { "epoch": 3.31, "learning_rate": 0.00079975, "loss": 1.849, "step": 15995 }, { "epoch": 3.31, "learning_rate": 0.0008, "loss": 1.8485, "step": 16000 }, { "epoch": 3.32, "learning_rate": 0.0008002500000000001, "loss": 1.8466, "step": 16005 }, { "epoch": 3.32, "learning_rate": 0.0008005, "loss": 1.848, "step": 16010 }, { "epoch": 3.32, "learning_rate": 0.00080075, "loss": 1.8466, "step": 16015 }, { "epoch": 3.32, "learning_rate": 0.0008010000000000001, "loss": 1.8408, "step": 16020 }, { "epoch": 3.32, "learning_rate": 0.00080125, "loss": 1.8469, "step": 16025 }, { "epoch": 3.32, "learning_rate": 0.0008015, "loss": 1.8488, "step": 16030 }, { "epoch": 3.32, "learning_rate": 0.0008017499999999999, "loss": 1.8502, "step": 16035 }, { "epoch": 3.32, "learning_rate": 0.0008020000000000001, "loss": 1.8461, "step": 16040 }, { "epoch": 3.32, "learning_rate": 0.00080225, "loss": 1.85, "step": 16045 }, { "epoch": 3.33, "learning_rate": 0.0008025, "loss": 1.8511, "step": 16050 }, { "epoch": 3.33, "learning_rate": 0.00080275, "loss": 1.8484, "step": 16055 }, { "epoch": 3.33, "learning_rate": 0.0008030000000000001, "loss": 1.8495, "step": 16060 }, { "epoch": 3.33, "learning_rate": 0.00080325, "loss": 1.8528, "step": 16065 }, { "epoch": 3.33, "learning_rate": 0.0008035, "loss": 1.8472, "step": 16070 }, { "epoch": 3.33, "learning_rate": 0.00080375, "loss": 1.8499, "step": 16075 }, { "epoch": 3.33, "learning_rate": 0.000804, "loss": 1.8529, "step": 16080 }, { "epoch": 3.33, "learning_rate": 0.0008042500000000001, "loss": 1.8459, "step": 16085 }, { "epoch": 3.33, "learning_rate": 0.0008045, "loss": 1.8529, "step": 16090 }, { "epoch": 3.33, "learning_rate": 0.00080475, "loss": 1.858, "step": 16095 }, { "epoch": 3.34, "learning_rate": 0.000805, "loss": 1.8541, "step": 16100 }, { "epoch": 3.34, "learning_rate": 0.0008052500000000001, "loss": 1.8473, "step": 16105 }, { "epoch": 3.34, "learning_rate": 0.0008055, "loss": 1.8573, "step": 16110 }, { "epoch": 3.34, "learning_rate": 0.0008057499999999999, "loss": 1.8502, "step": 16115 }, { "epoch": 3.34, "learning_rate": 0.0008060000000000001, "loss": 1.8437, "step": 16120 }, { "epoch": 3.34, "learning_rate": 0.00080625, "loss": 1.8548, "step": 16125 }, { "epoch": 3.34, "learning_rate": 0.0008065, "loss": 1.8475, "step": 16130 }, { "epoch": 3.34, "learning_rate": 0.00080675, "loss": 1.8506, "step": 16135 }, { "epoch": 3.34, "learning_rate": 0.0008070000000000001, "loss": 1.85, "step": 16140 }, { "epoch": 3.34, "learning_rate": 0.00080725, "loss": 1.8492, "step": 16145 }, { "epoch": 3.35, "learning_rate": 0.0008075000000000001, "loss": 1.8487, "step": 16150 }, { "epoch": 3.35, "learning_rate": 0.00080775, "loss": 1.8487, "step": 16155 }, { "epoch": 3.35, "learning_rate": 0.000808, "loss": 1.8429, "step": 16160 }, { "epoch": 3.35, "learning_rate": 0.00080825, "loss": 1.8462, "step": 16165 }, { "epoch": 3.35, "learning_rate": 0.0008085, "loss": 1.8483, "step": 16170 }, { "epoch": 3.35, "learning_rate": 0.00080875, "loss": 1.8477, "step": 16175 }, { "epoch": 3.35, "learning_rate": 0.000809, "loss": 1.8463, "step": 16180 }, { "epoch": 3.35, "learning_rate": 0.0008092500000000001, "loss": 1.8471, "step": 16185 }, { "epoch": 3.35, "learning_rate": 0.0008095, "loss": 1.8516, "step": 16190 }, { "epoch": 3.36, "learning_rate": 0.00080975, "loss": 1.8454, "step": 16195 }, { "epoch": 3.36, "learning_rate": 0.0008100000000000001, "loss": 1.8514, "step": 16200 }, { "epoch": 3.36, "learning_rate": 0.00081025, "loss": 1.8441, "step": 16205 }, { "epoch": 3.36, "learning_rate": 0.0008105, "loss": 1.8484, "step": 16210 }, { "epoch": 3.36, "learning_rate": 0.00081075, "loss": 1.8528, "step": 16215 }, { "epoch": 3.36, "learning_rate": 0.0008110000000000001, "loss": 1.8466, "step": 16220 }, { "epoch": 3.36, "learning_rate": 0.00081125, "loss": 1.8483, "step": 16225 }, { "epoch": 3.36, "learning_rate": 0.0008115, "loss": 1.8481, "step": 16230 }, { "epoch": 3.36, "learning_rate": 0.00081175, "loss": 1.847, "step": 16235 }, { "epoch": 3.36, "learning_rate": 0.0008120000000000001, "loss": 1.8508, "step": 16240 }, { "epoch": 3.37, "learning_rate": 0.00081225, "loss": 1.8461, "step": 16245 }, { "epoch": 3.37, "learning_rate": 0.0008125000000000001, "loss": 1.8511, "step": 16250 }, { "epoch": 3.37, "learning_rate": 0.00081275, "loss": 1.8528, "step": 16255 }, { "epoch": 3.37, "learning_rate": 0.0008129999999999999, "loss": 1.8472, "step": 16260 }, { "epoch": 3.37, "learning_rate": 0.0008132500000000001, "loss": 1.8501, "step": 16265 }, { "epoch": 3.37, "learning_rate": 0.0008135, "loss": 1.8492, "step": 16270 }, { "epoch": 3.37, "learning_rate": 0.00081375, "loss": 1.8474, "step": 16275 }, { "epoch": 3.37, "learning_rate": 0.0008139999999999999, "loss": 1.8554, "step": 16280 }, { "epoch": 3.37, "learning_rate": 0.0008142500000000001, "loss": 1.8495, "step": 16285 }, { "epoch": 3.37, "learning_rate": 0.0008145, "loss": 1.8539, "step": 16290 }, { "epoch": 3.38, "learning_rate": 0.00081475, "loss": 1.8523, "step": 16295 }, { "epoch": 3.38, "learning_rate": 0.000815, "loss": 1.8495, "step": 16300 }, { "epoch": 3.38, "learning_rate": 0.00081525, "loss": 1.8459, "step": 16305 }, { "epoch": 3.38, "learning_rate": 0.0008155, "loss": 1.8469, "step": 16310 }, { "epoch": 3.38, "learning_rate": 0.00081575, "loss": 1.8507, "step": 16315 }, { "epoch": 3.38, "learning_rate": 0.000816, "loss": 1.8459, "step": 16320 }, { "epoch": 3.38, "learning_rate": 0.00081625, "loss": 1.8451, "step": 16325 }, { "epoch": 3.38, "learning_rate": 0.0008165000000000001, "loss": 1.8458, "step": 16330 }, { "epoch": 3.38, "learning_rate": 0.00081675, "loss": 1.8503, "step": 16335 }, { "epoch": 3.39, "learning_rate": 0.000817, "loss": 1.8569, "step": 16340 }, { "epoch": 3.39, "learning_rate": 0.00081725, "loss": 1.8534, "step": 16345 }, { "epoch": 3.39, "learning_rate": 0.0008175, "loss": 1.8513, "step": 16350 }, { "epoch": 3.39, "learning_rate": 0.00081775, "loss": 1.8463, "step": 16355 }, { "epoch": 3.39, "learning_rate": 0.0008179999999999999, "loss": 1.8486, "step": 16360 }, { "epoch": 3.39, "learning_rate": 0.0008182500000000001, "loss": 1.8451, "step": 16365 }, { "epoch": 3.39, "learning_rate": 0.0008185, "loss": 1.8509, "step": 16370 }, { "epoch": 3.39, "learning_rate": 0.00081875, "loss": 1.8456, "step": 16375 }, { "epoch": 3.39, "learning_rate": 0.000819, "loss": 1.8482, "step": 16380 }, { "epoch": 3.39, "learning_rate": 0.0008192500000000001, "loss": 1.8502, "step": 16385 }, { "epoch": 3.4, "learning_rate": 0.0008195, "loss": 1.8476, "step": 16390 }, { "epoch": 3.4, "learning_rate": 0.00081975, "loss": 1.8559, "step": 16395 }, { "epoch": 3.4, "learning_rate": 0.00082, "loss": 1.847, "step": 16400 }, { "epoch": 3.4, "learning_rate": 0.00082025, "loss": 1.8468, "step": 16405 }, { "epoch": 3.4, "learning_rate": 0.0008205, "loss": 1.8491, "step": 16410 }, { "epoch": 3.4, "learning_rate": 0.00082075, "loss": 1.8494, "step": 16415 }, { "epoch": 3.4, "learning_rate": 0.000821, "loss": 1.8624, "step": 16420 }, { "epoch": 3.4, "learning_rate": 0.00082125, "loss": 1.8591, "step": 16425 }, { "epoch": 3.4, "learning_rate": 0.0008215000000000001, "loss": 1.8544, "step": 16430 }, { "epoch": 3.4, "learning_rate": 0.00082175, "loss": 1.8506, "step": 16435 }, { "epoch": 3.41, "learning_rate": 0.0008219999999999999, "loss": 1.8484, "step": 16440 }, { "epoch": 3.41, "learning_rate": 0.0008222500000000001, "loss": 1.8452, "step": 16445 }, { "epoch": 3.41, "learning_rate": 0.0008225, "loss": 1.8434, "step": 16450 }, { "epoch": 3.41, "learning_rate": 0.00082275, "loss": 1.8469, "step": 16455 }, { "epoch": 3.41, "learning_rate": 0.000823, "loss": 1.8491, "step": 16460 }, { "epoch": 3.41, "learning_rate": 0.0008232500000000001, "loss": 1.8512, "step": 16465 }, { "epoch": 3.41, "learning_rate": 0.0008235, "loss": 1.8515, "step": 16470 }, { "epoch": 3.41, "learning_rate": 0.00082375, "loss": 1.8516, "step": 16475 }, { "epoch": 3.41, "learning_rate": 0.000824, "loss": 1.845, "step": 16480 }, { "epoch": 3.42, "learning_rate": 0.00082425, "loss": 1.8467, "step": 16485 }, { "epoch": 3.42, "learning_rate": 0.0008245, "loss": 1.8526, "step": 16490 }, { "epoch": 3.42, "learning_rate": 0.00082475, "loss": 1.8509, "step": 16495 }, { "epoch": 3.42, "learning_rate": 0.000825, "loss": 1.8522, "step": 16500 }, { "epoch": 3.42, "learning_rate": 0.00082525, "loss": 1.848, "step": 16505 }, { "epoch": 3.42, "learning_rate": 0.0008255000000000001, "loss": 1.8496, "step": 16510 }, { "epoch": 3.42, "learning_rate": 0.00082575, "loss": 1.8475, "step": 16515 }, { "epoch": 3.42, "learning_rate": 0.000826, "loss": 1.8458, "step": 16520 }, { "epoch": 3.42, "learning_rate": 0.00082625, "loss": 1.8462, "step": 16525 }, { "epoch": 3.42, "learning_rate": 0.0008265, "loss": 1.8476, "step": 16530 }, { "epoch": 3.43, "learning_rate": 0.00082675, "loss": 1.8422, "step": 16535 }, { "epoch": 3.43, "learning_rate": 0.0008269999999999999, "loss": 1.8393, "step": 16540 }, { "epoch": 3.43, "learning_rate": 0.0008272500000000001, "loss": 1.8453, "step": 16545 }, { "epoch": 3.43, "learning_rate": 0.0008275, "loss": 1.8479, "step": 16550 }, { "epoch": 3.43, "learning_rate": 0.00082775, "loss": 1.8485, "step": 16555 }, { "epoch": 3.43, "learning_rate": 0.000828, "loss": 1.8425, "step": 16560 }, { "epoch": 3.43, "learning_rate": 0.0008282500000000001, "loss": 1.8407, "step": 16565 }, { "epoch": 3.43, "learning_rate": 0.0008285, "loss": 1.849, "step": 16570 }, { "epoch": 3.43, "learning_rate": 0.00082875, "loss": 1.839, "step": 16575 }, { "epoch": 3.43, "learning_rate": 0.000829, "loss": 1.8519, "step": 16580 }, { "epoch": 3.44, "learning_rate": 0.00082925, "loss": 1.8499, "step": 16585 }, { "epoch": 3.44, "learning_rate": 0.0008295, "loss": 1.8473, "step": 16590 }, { "epoch": 3.44, "learning_rate": 0.00082975, "loss": 1.8407, "step": 16595 }, { "epoch": 3.44, "learning_rate": 0.00083, "loss": 1.8447, "step": 16600 }, { "epoch": 3.44, "learning_rate": 0.00083025, "loss": 1.8459, "step": 16605 }, { "epoch": 3.44, "learning_rate": 0.0008305000000000001, "loss": 1.8455, "step": 16610 }, { "epoch": 3.44, "learning_rate": 0.00083075, "loss": 1.8438, "step": 16615 }, { "epoch": 3.44, "learning_rate": 0.0008309999999999999, "loss": 1.8504, "step": 16620 }, { "epoch": 3.44, "learning_rate": 0.0008312500000000001, "loss": 1.8437, "step": 16625 }, { "epoch": 3.45, "learning_rate": 0.0008315, "loss": 1.8451, "step": 16630 }, { "epoch": 3.45, "learning_rate": 0.00083175, "loss": 1.8511, "step": 16635 }, { "epoch": 3.45, "learning_rate": 0.000832, "loss": 1.8439, "step": 16640 }, { "epoch": 3.45, "learning_rate": 0.0008322500000000001, "loss": 1.8475, "step": 16645 }, { "epoch": 3.45, "learning_rate": 0.0008325, "loss": 1.8456, "step": 16650 }, { "epoch": 3.45, "learning_rate": 0.00083275, "loss": 1.846, "step": 16655 }, { "epoch": 3.45, "learning_rate": 0.000833, "loss": 1.8477, "step": 16660 }, { "epoch": 3.45, "learning_rate": 0.0008332500000000001, "loss": 1.8462, "step": 16665 }, { "epoch": 3.45, "learning_rate": 0.0008335, "loss": 1.8528, "step": 16670 }, { "epoch": 3.45, "learning_rate": 0.00083375, "loss": 1.8422, "step": 16675 }, { "epoch": 3.46, "learning_rate": 0.000834, "loss": 1.8495, "step": 16680 }, { "epoch": 3.46, "learning_rate": 0.00083425, "loss": 1.8415, "step": 16685 }, { "epoch": 3.46, "learning_rate": 0.0008345000000000001, "loss": 1.8413, "step": 16690 }, { "epoch": 3.46, "learning_rate": 0.00083475, "loss": 1.848, "step": 16695 }, { "epoch": 3.46, "learning_rate": 0.000835, "loss": 1.8443, "step": 16700 }, { "epoch": 3.46, "learning_rate": 0.0008352500000000001, "loss": 1.8489, "step": 16705 }, { "epoch": 3.46, "learning_rate": 0.0008355000000000001, "loss": 1.84, "step": 16710 }, { "epoch": 3.46, "learning_rate": 0.00083575, "loss": 1.8461, "step": 16715 }, { "epoch": 3.46, "learning_rate": 0.0008359999999999999, "loss": 1.8457, "step": 16720 }, { "epoch": 3.46, "learning_rate": 0.0008362500000000001, "loss": 1.8457, "step": 16725 }, { "epoch": 3.47, "learning_rate": 0.0008365, "loss": 1.8458, "step": 16730 }, { "epoch": 3.47, "learning_rate": 0.00083675, "loss": 1.8478, "step": 16735 }, { "epoch": 3.47, "learning_rate": 0.000837, "loss": 1.8461, "step": 16740 }, { "epoch": 3.47, "learning_rate": 0.0008372500000000001, "loss": 1.849, "step": 16745 }, { "epoch": 3.47, "learning_rate": 0.0008375, "loss": 1.8468, "step": 16750 }, { "epoch": 3.47, "learning_rate": 0.0008377500000000001, "loss": 1.8446, "step": 16755 }, { "epoch": 3.47, "learning_rate": 0.000838, "loss": 1.8381, "step": 16760 }, { "epoch": 3.47, "learning_rate": 0.00083825, "loss": 1.8453, "step": 16765 }, { "epoch": 3.47, "learning_rate": 0.0008385, "loss": 1.8443, "step": 16770 }, { "epoch": 3.48, "learning_rate": 0.00083875, "loss": 1.8531, "step": 16775 }, { "epoch": 3.48, "learning_rate": 0.000839, "loss": 1.8694, "step": 16780 }, { "epoch": 3.48, "learning_rate": 0.00083925, "loss": 1.8702, "step": 16785 }, { "epoch": 3.48, "learning_rate": 0.0008395000000000001, "loss": 1.8604, "step": 16790 }, { "epoch": 3.48, "learning_rate": 0.00083975, "loss": 1.8575, "step": 16795 }, { "epoch": 3.48, "learning_rate": 0.00084, "loss": 1.846, "step": 16800 }, { "epoch": 3.48, "learning_rate": 0.0008402500000000001, "loss": 1.8467, "step": 16805 }, { "epoch": 3.48, "learning_rate": 0.0008405, "loss": 1.8523, "step": 16810 }, { "epoch": 3.48, "learning_rate": 0.00084075, "loss": 1.849, "step": 16815 }, { "epoch": 3.48, "learning_rate": 0.000841, "loss": 1.8543, "step": 16820 }, { "epoch": 3.49, "learning_rate": 0.0008412500000000001, "loss": 1.8516, "step": 16825 }, { "epoch": 3.49, "learning_rate": 0.0008415, "loss": 1.8472, "step": 16830 }, { "epoch": 3.49, "learning_rate": 0.00084175, "loss": 1.842, "step": 16835 }, { "epoch": 3.49, "learning_rate": 0.000842, "loss": 1.8408, "step": 16840 }, { "epoch": 3.49, "learning_rate": 0.0008422500000000001, "loss": 1.8416, "step": 16845 }, { "epoch": 3.49, "learning_rate": 0.0008425, "loss": 1.8434, "step": 16850 }, { "epoch": 3.49, "learning_rate": 0.00084275, "loss": 1.8457, "step": 16855 }, { "epoch": 3.49, "learning_rate": 0.000843, "loss": 1.8488, "step": 16860 }, { "epoch": 3.49, "learning_rate": 0.00084325, "loss": 1.8442, "step": 16865 }, { "epoch": 3.49, "learning_rate": 0.0008435000000000001, "loss": 1.8508, "step": 16870 }, { "epoch": 3.5, "learning_rate": 0.00084375, "loss": 1.8558, "step": 16875 }, { "epoch": 3.5, "learning_rate": 0.000844, "loss": 1.8507, "step": 16880 }, { "epoch": 3.5, "learning_rate": 0.00084425, "loss": 1.8489, "step": 16885 }, { "epoch": 3.5, "learning_rate": 0.0008445000000000001, "loss": 1.8432, "step": 16890 }, { "epoch": 3.5, "learning_rate": 0.00084475, "loss": 1.847, "step": 16895 }, { "epoch": 3.5, "learning_rate": 0.0008449999999999999, "loss": 1.8441, "step": 16900 }, { "epoch": 3.5, "learning_rate": 0.00084525, "loss": 1.8413, "step": 16905 }, { "epoch": 3.5, "learning_rate": 0.0008455, "loss": 1.848, "step": 16910 }, { "epoch": 3.5, "learning_rate": 0.00084575, "loss": 1.854, "step": 16915 }, { "epoch": 3.51, "learning_rate": 0.000846, "loss": 1.8477, "step": 16920 }, { "epoch": 3.51, "learning_rate": 0.00084625, "loss": 1.8498, "step": 16925 }, { "epoch": 3.51, "learning_rate": 0.0008465, "loss": 1.8483, "step": 16930 }, { "epoch": 3.51, "learning_rate": 0.0008467500000000001, "loss": 1.8419, "step": 16935 }, { "epoch": 3.51, "learning_rate": 0.000847, "loss": 1.8451, "step": 16940 }, { "epoch": 3.51, "learning_rate": 0.0008472499999999999, "loss": 1.8499, "step": 16945 }, { "epoch": 3.51, "learning_rate": 0.0008475000000000001, "loss": 1.8462, "step": 16950 }, { "epoch": 3.51, "learning_rate": 0.00084775, "loss": 1.8446, "step": 16955 }, { "epoch": 3.51, "learning_rate": 0.000848, "loss": 1.8457, "step": 16960 }, { "epoch": 3.51, "learning_rate": 0.0008482499999999999, "loss": 1.846, "step": 16965 }, { "epoch": 3.52, "learning_rate": 0.0008485000000000001, "loss": 1.8431, "step": 16970 }, { "epoch": 3.52, "learning_rate": 0.00084875, "loss": 1.8471, "step": 16975 }, { "epoch": 3.52, "learning_rate": 0.000849, "loss": 1.8472, "step": 16980 }, { "epoch": 3.52, "learning_rate": 0.00084925, "loss": 1.8454, "step": 16985 }, { "epoch": 3.52, "learning_rate": 0.0008495000000000001, "loss": 1.8447, "step": 16990 }, { "epoch": 3.52, "learning_rate": 0.00084975, "loss": 1.848, "step": 16995 }, { "epoch": 3.52, "learning_rate": 0.00085, "loss": 1.8502, "step": 17000 }, { "epoch": 3.52, "learning_rate": 0.00085025, "loss": 1.8453, "step": 17005 }, { "epoch": 3.52, "learning_rate": 0.0008505, "loss": 1.8483, "step": 17010 }, { "epoch": 3.52, "learning_rate": 0.00085075, "loss": 1.8487, "step": 17015 }, { "epoch": 3.53, "learning_rate": 0.000851, "loss": 1.8414, "step": 17020 }, { "epoch": 3.53, "learning_rate": 0.00085125, "loss": 1.846, "step": 17025 }, { "epoch": 3.53, "learning_rate": 0.0008515, "loss": 1.8461, "step": 17030 }, { "epoch": 3.53, "learning_rate": 0.0008517500000000001, "loss": 1.8418, "step": 17035 }, { "epoch": 3.53, "learning_rate": 0.000852, "loss": 1.8443, "step": 17040 }, { "epoch": 3.53, "learning_rate": 0.0008522499999999999, "loss": 1.8444, "step": 17045 }, { "epoch": 3.53, "learning_rate": 0.0008525000000000001, "loss": 1.8466, "step": 17050 }, { "epoch": 3.53, "learning_rate": 0.00085275, "loss": 1.8472, "step": 17055 }, { "epoch": 3.53, "learning_rate": 0.000853, "loss": 1.841, "step": 17060 }, { "epoch": 3.54, "learning_rate": 0.00085325, "loss": 1.8396, "step": 17065 }, { "epoch": 3.54, "learning_rate": 0.0008535000000000001, "loss": 1.8392, "step": 17070 }, { "epoch": 3.54, "learning_rate": 0.00085375, "loss": 1.8481, "step": 17075 }, { "epoch": 3.54, "learning_rate": 0.000854, "loss": 1.8447, "step": 17080 }, { "epoch": 3.54, "learning_rate": 0.00085425, "loss": 1.8361, "step": 17085 }, { "epoch": 3.54, "learning_rate": 0.0008545, "loss": 1.8462, "step": 17090 }, { "epoch": 3.54, "learning_rate": 0.00085475, "loss": 1.8442, "step": 17095 }, { "epoch": 3.54, "learning_rate": 0.000855, "loss": 1.8449, "step": 17100 }, { "epoch": 3.54, "learning_rate": 0.00085525, "loss": 1.8425, "step": 17105 }, { "epoch": 3.54, "learning_rate": 0.0008555, "loss": 1.8432, "step": 17110 }, { "epoch": 3.55, "learning_rate": 0.0008557500000000001, "loss": 1.8449, "step": 17115 }, { "epoch": 3.55, "learning_rate": 0.000856, "loss": 1.8519, "step": 17120 }, { "epoch": 3.55, "learning_rate": 0.00085625, "loss": 1.8497, "step": 17125 }, { "epoch": 3.55, "learning_rate": 0.0008565000000000001, "loss": 1.8466, "step": 17130 }, { "epoch": 3.55, "learning_rate": 0.00085675, "loss": 1.8481, "step": 17135 }, { "epoch": 3.55, "learning_rate": 0.000857, "loss": 1.8423, "step": 17140 }, { "epoch": 3.55, "learning_rate": 0.0008572499999999999, "loss": 1.8432, "step": 17145 }, { "epoch": 3.55, "learning_rate": 0.0008575000000000001, "loss": 1.8449, "step": 17150 }, { "epoch": 3.55, "learning_rate": 0.00085775, "loss": 1.8428, "step": 17155 }, { "epoch": 3.56, "learning_rate": 0.000858, "loss": 1.8429, "step": 17160 }, { "epoch": 3.56, "learning_rate": 0.00085825, "loss": 1.8467, "step": 17165 }, { "epoch": 3.56, "learning_rate": 0.0008585000000000001, "loss": 1.845, "step": 17170 }, { "epoch": 3.56, "learning_rate": 0.00085875, "loss": 1.843, "step": 17175 }, { "epoch": 3.56, "learning_rate": 0.000859, "loss": 1.8402, "step": 17180 }, { "epoch": 3.56, "learning_rate": 0.00085925, "loss": 1.8397, "step": 17185 }, { "epoch": 3.56, "learning_rate": 0.0008595, "loss": 1.8441, "step": 17190 }, { "epoch": 3.56, "learning_rate": 0.00085975, "loss": 1.8405, "step": 17195 }, { "epoch": 3.56, "learning_rate": 0.00086, "loss": 1.8446, "step": 17200 }, { "epoch": 3.56, "learning_rate": 0.00086025, "loss": 1.8404, "step": 17205 }, { "epoch": 3.57, "learning_rate": 0.0008605, "loss": 1.8465, "step": 17210 }, { "epoch": 3.57, "learning_rate": 0.0008607500000000001, "loss": 1.841, "step": 17215 }, { "epoch": 3.57, "learning_rate": 0.000861, "loss": 1.8374, "step": 17220 }, { "epoch": 3.57, "learning_rate": 0.0008612499999999999, "loss": 1.8444, "step": 17225 }, { "epoch": 3.57, "learning_rate": 0.0008615000000000001, "loss": 1.855, "step": 17230 }, { "epoch": 3.57, "learning_rate": 0.00086175, "loss": 1.8504, "step": 17235 }, { "epoch": 3.57, "learning_rate": 0.000862, "loss": 1.8482, "step": 17240 }, { "epoch": 3.57, "learning_rate": 0.00086225, "loss": 1.8467, "step": 17245 }, { "epoch": 3.57, "learning_rate": 0.0008625000000000001, "loss": 1.847, "step": 17250 }, { "epoch": 3.57, "learning_rate": 0.00086275, "loss": 1.8423, "step": 17255 }, { "epoch": 3.58, "learning_rate": 0.000863, "loss": 1.8383, "step": 17260 }, { "epoch": 3.58, "learning_rate": 0.00086325, "loss": 1.8447, "step": 17265 }, { "epoch": 3.58, "learning_rate": 0.0008635, "loss": 1.843, "step": 17270 }, { "epoch": 3.58, "learning_rate": 0.00086375, "loss": 1.8487, "step": 17275 }, { "epoch": 3.58, "learning_rate": 0.000864, "loss": 1.8469, "step": 17280 }, { "epoch": 3.58, "learning_rate": 0.00086425, "loss": 1.8394, "step": 17285 }, { "epoch": 3.58, "learning_rate": 0.0008645, "loss": 1.8417, "step": 17290 }, { "epoch": 3.58, "learning_rate": 0.0008647500000000001, "loss": 1.8467, "step": 17295 }, { "epoch": 3.58, "learning_rate": 0.000865, "loss": 1.84, "step": 17300 }, { "epoch": 3.59, "learning_rate": 0.00086525, "loss": 1.8426, "step": 17305 }, { "epoch": 3.59, "learning_rate": 0.0008655000000000001, "loss": 1.8522, "step": 17310 }, { "epoch": 3.59, "learning_rate": 0.0008657500000000001, "loss": 1.8471, "step": 17315 }, { "epoch": 3.59, "learning_rate": 0.000866, "loss": 1.8472, "step": 17320 }, { "epoch": 3.59, "learning_rate": 0.0008662499999999999, "loss": 1.8377, "step": 17325 }, { "epoch": 3.59, "learning_rate": 0.0008665000000000001, "loss": 1.8458, "step": 17330 }, { "epoch": 3.59, "learning_rate": 0.00086675, "loss": 1.8455, "step": 17335 }, { "epoch": 3.59, "learning_rate": 0.000867, "loss": 1.8441, "step": 17340 }, { "epoch": 3.59, "learning_rate": 0.00086725, "loss": 1.8432, "step": 17345 }, { "epoch": 3.59, "learning_rate": 0.0008675000000000001, "loss": 1.8389, "step": 17350 }, { "epoch": 3.6, "learning_rate": 0.00086775, "loss": 1.8424, "step": 17355 }, { "epoch": 3.6, "learning_rate": 0.0008680000000000001, "loss": 1.8396, "step": 17360 }, { "epoch": 3.6, "learning_rate": 0.00086825, "loss": 1.8454, "step": 17365 }, { "epoch": 3.6, "learning_rate": 0.0008685, "loss": 1.8412, "step": 17370 }, { "epoch": 3.6, "learning_rate": 0.0008687500000000001, "loss": 1.842, "step": 17375 }, { "epoch": 3.6, "learning_rate": 0.000869, "loss": 1.8405, "step": 17380 }, { "epoch": 3.6, "learning_rate": 0.00086925, "loss": 1.8421, "step": 17385 }, { "epoch": 3.6, "learning_rate": 0.0008695, "loss": 1.8413, "step": 17390 }, { "epoch": 3.6, "learning_rate": 0.0008697500000000001, "loss": 1.8407, "step": 17395 }, { "epoch": 3.6, "learning_rate": 0.00087, "loss": 1.8446, "step": 17400 }, { "epoch": 3.61, "learning_rate": 0.00087025, "loss": 1.842, "step": 17405 }, { "epoch": 3.61, "learning_rate": 0.0008705000000000001, "loss": 1.8387, "step": 17410 }, { "epoch": 3.61, "learning_rate": 0.00087075, "loss": 1.8372, "step": 17415 }, { "epoch": 3.61, "learning_rate": 0.000871, "loss": 1.8446, "step": 17420 }, { "epoch": 3.61, "learning_rate": 0.00087125, "loss": 1.843, "step": 17425 }, { "epoch": 3.61, "learning_rate": 0.0008715000000000001, "loss": 1.8417, "step": 17430 }, { "epoch": 3.61, "learning_rate": 0.00087175, "loss": 1.8394, "step": 17435 }, { "epoch": 3.61, "learning_rate": 0.000872, "loss": 1.8415, "step": 17440 }, { "epoch": 3.61, "learning_rate": 0.00087225, "loss": 1.8448, "step": 17445 }, { "epoch": 3.62, "learning_rate": 0.0008725000000000001, "loss": 1.8395, "step": 17450 }, { "epoch": 3.62, "learning_rate": 0.00087275, "loss": 1.8407, "step": 17455 }, { "epoch": 3.62, "learning_rate": 0.000873, "loss": 1.8422, "step": 17460 }, { "epoch": 3.62, "learning_rate": 0.00087325, "loss": 1.8384, "step": 17465 }, { "epoch": 3.62, "learning_rate": 0.0008735, "loss": 1.8415, "step": 17470 }, { "epoch": 3.62, "learning_rate": 0.0008737500000000001, "loss": 1.846, "step": 17475 }, { "epoch": 3.62, "learning_rate": 0.000874, "loss": 1.8435, "step": 17480 }, { "epoch": 3.62, "learning_rate": 0.00087425, "loss": 1.8437, "step": 17485 }, { "epoch": 3.62, "learning_rate": 0.0008745000000000001, "loss": 1.8399, "step": 17490 }, { "epoch": 3.62, "learning_rate": 0.0008747500000000001, "loss": 1.8425, "step": 17495 }, { "epoch": 3.63, "learning_rate": 0.000875, "loss": 1.8379, "step": 17500 }, { "epoch": 3.63, "learning_rate": 0.0008752499999999999, "loss": 1.8398, "step": 17505 }, { "epoch": 3.63, "learning_rate": 0.0008755, "loss": 1.8356, "step": 17510 }, { "epoch": 3.63, "learning_rate": 0.00087575, "loss": 1.8383, "step": 17515 }, { "epoch": 3.63, "learning_rate": 0.000876, "loss": 1.838, "step": 17520 }, { "epoch": 3.63, "learning_rate": 0.00087625, "loss": 1.8425, "step": 17525 }, { "epoch": 3.63, "learning_rate": 0.0008765, "loss": 1.843, "step": 17530 }, { "epoch": 3.63, "learning_rate": 0.00087675, "loss": 1.8371, "step": 17535 }, { "epoch": 3.63, "learning_rate": 0.0008770000000000001, "loss": 1.8427, "step": 17540 }, { "epoch": 3.63, "learning_rate": 0.00087725, "loss": 1.8392, "step": 17545 }, { "epoch": 3.64, "learning_rate": 0.0008774999999999999, "loss": 1.8378, "step": 17550 }, { "epoch": 3.64, "learning_rate": 0.0008777500000000001, "loss": 1.8474, "step": 17555 }, { "epoch": 3.64, "learning_rate": 0.000878, "loss": 1.8343, "step": 17560 }, { "epoch": 3.64, "learning_rate": 0.00087825, "loss": 1.8359, "step": 17565 }, { "epoch": 3.64, "learning_rate": 0.0008784999999999999, "loss": 1.8422, "step": 17570 }, { "epoch": 3.64, "learning_rate": 0.0008787500000000001, "loss": 1.8422, "step": 17575 }, { "epoch": 3.64, "learning_rate": 0.000879, "loss": 1.8387, "step": 17580 }, { "epoch": 3.64, "learning_rate": 0.00087925, "loss": 1.8381, "step": 17585 }, { "epoch": 3.64, "learning_rate": 0.0008795, "loss": 1.8482, "step": 17590 }, { "epoch": 3.65, "learning_rate": 0.00087975, "loss": 1.8429, "step": 17595 }, { "epoch": 3.65, "learning_rate": 0.00088, "loss": 1.8434, "step": 17600 }, { "epoch": 3.65, "learning_rate": 0.00088025, "loss": 1.8431, "step": 17605 }, { "epoch": 3.65, "learning_rate": 0.0008805, "loss": 1.84, "step": 17610 }, { "epoch": 3.65, "learning_rate": 0.00088075, "loss": 1.8397, "step": 17615 }, { "epoch": 3.65, "learning_rate": 0.0008810000000000001, "loss": 1.8381, "step": 17620 }, { "epoch": 3.65, "learning_rate": 0.00088125, "loss": 1.8432, "step": 17625 }, { "epoch": 3.65, "learning_rate": 0.0008815, "loss": 1.8442, "step": 17630 }, { "epoch": 3.65, "learning_rate": 0.00088175, "loss": 1.8418, "step": 17635 }, { "epoch": 3.65, "learning_rate": 0.000882, "loss": 1.8455, "step": 17640 }, { "epoch": 3.66, "learning_rate": 0.00088225, "loss": 1.8423, "step": 17645 }, { "epoch": 3.66, "learning_rate": 0.0008824999999999999, "loss": 1.8398, "step": 17650 }, { "epoch": 3.66, "learning_rate": 0.0008827500000000001, "loss": 1.8393, "step": 17655 }, { "epoch": 3.66, "learning_rate": 0.000883, "loss": 1.8407, "step": 17660 }, { "epoch": 3.66, "learning_rate": 0.00088325, "loss": 1.8381, "step": 17665 }, { "epoch": 3.66, "learning_rate": 0.0008835, "loss": 1.8394, "step": 17670 }, { "epoch": 3.66, "learning_rate": 0.0008837500000000001, "loss": 1.8422, "step": 17675 }, { "epoch": 3.66, "learning_rate": 0.000884, "loss": 1.842, "step": 17680 }, { "epoch": 3.66, "learning_rate": 0.0008842499999999999, "loss": 1.8434, "step": 17685 }, { "epoch": 3.66, "learning_rate": 0.0008845, "loss": 1.8478, "step": 17690 }, { "epoch": 3.67, "learning_rate": 0.00088475, "loss": 1.8458, "step": 17695 }, { "epoch": 3.67, "learning_rate": 0.000885, "loss": 1.8463, "step": 17700 }, { "epoch": 3.67, "learning_rate": 0.00088525, "loss": 1.8446, "step": 17705 }, { "epoch": 3.67, "learning_rate": 0.0008855, "loss": 1.8423, "step": 17710 }, { "epoch": 3.67, "learning_rate": 0.00088575, "loss": 1.8423, "step": 17715 }, { "epoch": 3.67, "learning_rate": 0.0008860000000000001, "loss": 1.8376, "step": 17720 }, { "epoch": 3.67, "learning_rate": 0.00088625, "loss": 1.8368, "step": 17725 }, { "epoch": 3.67, "learning_rate": 0.0008865, "loss": 1.8389, "step": 17730 }, { "epoch": 3.67, "learning_rate": 0.0008867500000000001, "loss": 1.8439, "step": 17735 }, { "epoch": 3.68, "learning_rate": 0.000887, "loss": 1.8392, "step": 17740 }, { "epoch": 3.68, "learning_rate": 0.00088725, "loss": 1.8384, "step": 17745 }, { "epoch": 3.68, "learning_rate": 0.0008874999999999999, "loss": 1.8495, "step": 17750 }, { "epoch": 3.68, "learning_rate": 0.0008877500000000001, "loss": 1.8494, "step": 17755 }, { "epoch": 3.68, "learning_rate": 0.000888, "loss": 1.8447, "step": 17760 }, { "epoch": 3.68, "learning_rate": 0.00088825, "loss": 1.8431, "step": 17765 }, { "epoch": 3.68, "learning_rate": 0.0008885, "loss": 1.8423, "step": 17770 }, { "epoch": 3.68, "learning_rate": 0.0008887500000000001, "loss": 1.8344, "step": 17775 }, { "epoch": 3.68, "learning_rate": 0.000889, "loss": 1.842, "step": 17780 }, { "epoch": 3.68, "learning_rate": 0.00088925, "loss": 1.8403, "step": 17785 }, { "epoch": 3.69, "learning_rate": 0.0008895, "loss": 1.8398, "step": 17790 }, { "epoch": 3.69, "learning_rate": 0.00088975, "loss": 1.8387, "step": 17795 }, { "epoch": 3.69, "learning_rate": 0.0008900000000000001, "loss": 1.8402, "step": 17800 }, { "epoch": 3.69, "learning_rate": 0.00089025, "loss": 1.8429, "step": 17805 }, { "epoch": 3.69, "learning_rate": 0.0008905, "loss": 1.8406, "step": 17810 }, { "epoch": 3.69, "learning_rate": 0.00089075, "loss": 1.841, "step": 17815 }, { "epoch": 3.69, "learning_rate": 0.0008910000000000001, "loss": 1.8387, "step": 17820 }, { "epoch": 3.69, "learning_rate": 0.00089125, "loss": 1.8403, "step": 17825 }, { "epoch": 3.69, "learning_rate": 0.0008914999999999999, "loss": 1.841, "step": 17830 }, { "epoch": 3.69, "learning_rate": 0.0008917500000000001, "loss": 1.8339, "step": 17835 }, { "epoch": 3.7, "learning_rate": 0.000892, "loss": 1.8415, "step": 17840 }, { "epoch": 3.7, "learning_rate": 0.00089225, "loss": 1.8406, "step": 17845 }, { "epoch": 3.7, "learning_rate": 0.0008925, "loss": 1.8389, "step": 17850 }, { "epoch": 3.7, "learning_rate": 0.0008927500000000001, "loss": 1.8409, "step": 17855 }, { "epoch": 3.7, "learning_rate": 0.000893, "loss": 1.8338, "step": 17860 }, { "epoch": 3.7, "learning_rate": 0.0008932500000000001, "loss": 1.8377, "step": 17865 }, { "epoch": 3.7, "learning_rate": 0.0008935, "loss": 1.8458, "step": 17870 }, { "epoch": 3.7, "learning_rate": 0.00089375, "loss": 1.8459, "step": 17875 }, { "epoch": 3.7, "learning_rate": 0.000894, "loss": 1.8402, "step": 17880 }, { "epoch": 3.71, "learning_rate": 0.00089425, "loss": 1.8362, "step": 17885 }, { "epoch": 3.71, "learning_rate": 0.0008945, "loss": 1.8395, "step": 17890 }, { "epoch": 3.71, "learning_rate": 0.00089475, "loss": 1.8346, "step": 17895 }, { "epoch": 3.71, "learning_rate": 0.0008950000000000001, "loss": 1.8384, "step": 17900 }, { "epoch": 3.71, "learning_rate": 0.00089525, "loss": 1.8382, "step": 17905 }, { "epoch": 3.71, "learning_rate": 0.0008955, "loss": 1.8425, "step": 17910 }, { "epoch": 3.71, "learning_rate": 0.0008957500000000001, "loss": 1.838, "step": 17915 }, { "epoch": 3.71, "learning_rate": 0.000896, "loss": 1.8412, "step": 17920 }, { "epoch": 3.71, "learning_rate": 0.00089625, "loss": 1.837, "step": 17925 }, { "epoch": 3.71, "learning_rate": 0.0008964999999999999, "loss": 1.8372, "step": 17930 }, { "epoch": 3.72, "learning_rate": 0.0008967500000000001, "loss": 1.8406, "step": 17935 }, { "epoch": 3.72, "learning_rate": 0.000897, "loss": 1.8402, "step": 17940 }, { "epoch": 3.72, "learning_rate": 0.00089725, "loss": 1.8453, "step": 17945 }, { "epoch": 3.72, "learning_rate": 0.0008975, "loss": 1.8422, "step": 17950 }, { "epoch": 3.72, "learning_rate": 0.0008977500000000001, "loss": 1.8352, "step": 17955 }, { "epoch": 3.72, "learning_rate": 0.000898, "loss": 1.8435, "step": 17960 }, { "epoch": 3.72, "learning_rate": 0.00089825, "loss": 1.8392, "step": 17965 }, { "epoch": 3.72, "learning_rate": 0.0008985, "loss": 1.8392, "step": 17970 }, { "epoch": 3.72, "learning_rate": 0.00089875, "loss": 1.8372, "step": 17975 }, { "epoch": 3.72, "learning_rate": 0.0008990000000000001, "loss": 1.8376, "step": 17980 }, { "epoch": 3.73, "learning_rate": 0.00089925, "loss": 1.8421, "step": 17985 }, { "epoch": 3.73, "learning_rate": 0.0008995, "loss": 1.8345, "step": 17990 }, { "epoch": 3.73, "learning_rate": 0.00089975, "loss": 1.8354, "step": 17995 }, { "epoch": 3.73, "learning_rate": 0.0009000000000000001, "loss": 1.8388, "step": 18000 }, { "epoch": 3.73, "eval_accuracy": 0.5258562091503268, "eval_loss": 2.0113203525543213, "eval_runtime": 0.7983, "eval_samples_per_second": 187.895, "eval_steps_per_second": 1.253, "step": 18000 }, { "epoch": 3.73, "learning_rate": 0.00090025, "loss": 1.8402, "step": 18005 }, { "epoch": 3.73, "learning_rate": 0.0009004999999999999, "loss": 1.8415, "step": 18010 }, { "epoch": 3.73, "learning_rate": 0.0009007500000000001, "loss": 1.8434, "step": 18015 }, { "epoch": 3.73, "learning_rate": 0.000901, "loss": 1.8422, "step": 18020 }, { "epoch": 3.73, "learning_rate": 0.00090125, "loss": 1.837, "step": 18025 }, { "epoch": 3.74, "learning_rate": 0.0009015, "loss": 1.8358, "step": 18030 }, { "epoch": 3.74, "learning_rate": 0.0009017500000000001, "loss": 1.8389, "step": 18035 }, { "epoch": 3.74, "learning_rate": 0.000902, "loss": 1.8342, "step": 18040 }, { "epoch": 3.74, "learning_rate": 0.0009022500000000001, "loss": 1.8374, "step": 18045 }, { "epoch": 3.74, "learning_rate": 0.0009025, "loss": 1.8357, "step": 18050 }, { "epoch": 3.74, "learning_rate": 0.0009027500000000001, "loss": 1.8382, "step": 18055 }, { "epoch": 3.74, "learning_rate": 0.000903, "loss": 1.8399, "step": 18060 }, { "epoch": 3.74, "learning_rate": 0.00090325, "loss": 1.842, "step": 18065 }, { "epoch": 3.74, "learning_rate": 0.0009035, "loss": 1.8457, "step": 18070 }, { "epoch": 3.74, "learning_rate": 0.00090375, "loss": 1.8419, "step": 18075 }, { "epoch": 3.75, "learning_rate": 0.0009040000000000001, "loss": 1.8376, "step": 18080 }, { "epoch": 3.75, "learning_rate": 0.00090425, "loss": 1.8366, "step": 18085 }, { "epoch": 3.75, "learning_rate": 0.0009045, "loss": 1.842, "step": 18090 }, { "epoch": 3.75, "learning_rate": 0.0009047500000000001, "loss": 1.8394, "step": 18095 }, { "epoch": 3.75, "learning_rate": 0.0009050000000000001, "loss": 1.8326, "step": 18100 }, { "epoch": 3.75, "learning_rate": 0.00090525, "loss": 1.839, "step": 18105 }, { "epoch": 3.75, "learning_rate": 0.0009055, "loss": 1.8369, "step": 18110 }, { "epoch": 3.75, "learning_rate": 0.0009057500000000001, "loss": 1.8396, "step": 18115 }, { "epoch": 3.75, "learning_rate": 0.000906, "loss": 1.8354, "step": 18120 }, { "epoch": 3.75, "learning_rate": 0.00090625, "loss": 1.8408, "step": 18125 }, { "epoch": 3.76, "learning_rate": 0.0009065, "loss": 1.8415, "step": 18130 }, { "epoch": 3.76, "learning_rate": 0.00090675, "loss": 1.8425, "step": 18135 }, { "epoch": 3.76, "learning_rate": 0.000907, "loss": 1.8456, "step": 18140 }, { "epoch": 3.76, "learning_rate": 0.0009072500000000001, "loss": 1.8408, "step": 18145 }, { "epoch": 3.76, "learning_rate": 0.0009075, "loss": 1.8343, "step": 18150 }, { "epoch": 3.76, "learning_rate": 0.0009077499999999999, "loss": 1.834, "step": 18155 }, { "epoch": 3.76, "learning_rate": 0.0009080000000000001, "loss": 1.8469, "step": 18160 }, { "epoch": 3.76, "learning_rate": 0.00090825, "loss": 1.8453, "step": 18165 }, { "epoch": 3.76, "learning_rate": 0.0009085, "loss": 1.8363, "step": 18170 }, { "epoch": 3.77, "learning_rate": 0.0009087499999999999, "loss": 1.8395, "step": 18175 }, { "epoch": 3.77, "learning_rate": 0.0009090000000000001, "loss": 1.8365, "step": 18180 }, { "epoch": 3.77, "learning_rate": 0.00090925, "loss": 1.8367, "step": 18185 }, { "epoch": 3.77, "learning_rate": 0.0009095, "loss": 1.842, "step": 18190 }, { "epoch": 3.77, "learning_rate": 0.00090975, "loss": 1.8366, "step": 18195 }, { "epoch": 3.77, "learning_rate": 0.00091, "loss": 1.8385, "step": 18200 }, { "epoch": 3.77, "learning_rate": 0.00091025, "loss": 1.8389, "step": 18205 }, { "epoch": 3.77, "learning_rate": 0.0009105, "loss": 1.8398, "step": 18210 }, { "epoch": 3.77, "learning_rate": 0.00091075, "loss": 1.8374, "step": 18215 }, { "epoch": 3.77, "learning_rate": 0.000911, "loss": 1.84, "step": 18220 }, { "epoch": 3.78, "learning_rate": 0.0009112500000000001, "loss": 1.8377, "step": 18225 }, { "epoch": 3.78, "learning_rate": 0.0009115, "loss": 1.8339, "step": 18230 }, { "epoch": 3.78, "learning_rate": 0.00091175, "loss": 1.8398, "step": 18235 }, { "epoch": 3.78, "learning_rate": 0.000912, "loss": 1.8349, "step": 18240 }, { "epoch": 3.78, "learning_rate": 0.00091225, "loss": 1.8393, "step": 18245 }, { "epoch": 3.78, "learning_rate": 0.0009125, "loss": 1.8392, "step": 18250 }, { "epoch": 3.78, "learning_rate": 0.0009127499999999999, "loss": 1.8352, "step": 18255 }, { "epoch": 3.78, "learning_rate": 0.0009130000000000001, "loss": 1.8356, "step": 18260 }, { "epoch": 3.78, "learning_rate": 0.00091325, "loss": 1.8421, "step": 18265 }, { "epoch": 3.78, "learning_rate": 0.0009135, "loss": 1.8344, "step": 18270 }, { "epoch": 3.79, "learning_rate": 0.00091375, "loss": 1.8358, "step": 18275 }, { "epoch": 3.79, "learning_rate": 0.0009140000000000001, "loss": 1.84, "step": 18280 }, { "epoch": 3.79, "learning_rate": 0.00091425, "loss": 1.8346, "step": 18285 }, { "epoch": 3.79, "learning_rate": 0.0009145, "loss": 1.8331, "step": 18290 }, { "epoch": 3.79, "learning_rate": 0.00091475, "loss": 1.8429, "step": 18295 }, { "epoch": 3.79, "learning_rate": 0.000915, "loss": 1.8379, "step": 18300 }, { "epoch": 3.79, "learning_rate": 0.00091525, "loss": 1.8404, "step": 18305 }, { "epoch": 3.79, "learning_rate": 0.0009155, "loss": 1.839, "step": 18310 }, { "epoch": 3.79, "learning_rate": 0.00091575, "loss": 1.8391, "step": 18315 }, { "epoch": 3.8, "learning_rate": 0.000916, "loss": 1.8355, "step": 18320 }, { "epoch": 3.8, "learning_rate": 0.0009162500000000001, "loss": 1.8383, "step": 18325 }, { "epoch": 3.8, "learning_rate": 0.0009165, "loss": 1.8352, "step": 18330 }, { "epoch": 3.8, "learning_rate": 0.0009167499999999999, "loss": 1.8449, "step": 18335 }, { "epoch": 3.8, "learning_rate": 0.0009170000000000001, "loss": 1.8444, "step": 18340 }, { "epoch": 3.8, "learning_rate": 0.00091725, "loss": 1.8475, "step": 18345 }, { "epoch": 3.8, "learning_rate": 0.0009175, "loss": 1.8467, "step": 18350 }, { "epoch": 3.8, "learning_rate": 0.00091775, "loss": 1.8461, "step": 18355 }, { "epoch": 3.8, "learning_rate": 0.0009180000000000001, "loss": 1.8415, "step": 18360 }, { "epoch": 3.8, "learning_rate": 0.00091825, "loss": 1.8413, "step": 18365 }, { "epoch": 3.81, "learning_rate": 0.0009185, "loss": 1.8387, "step": 18370 }, { "epoch": 3.81, "learning_rate": 0.00091875, "loss": 1.8351, "step": 18375 }, { "epoch": 3.81, "learning_rate": 0.0009190000000000001, "loss": 1.8352, "step": 18380 }, { "epoch": 3.81, "learning_rate": 0.00091925, "loss": 1.8459, "step": 18385 }, { "epoch": 3.81, "learning_rate": 0.0009195, "loss": 1.8367, "step": 18390 }, { "epoch": 3.81, "learning_rate": 0.00091975, "loss": 1.8359, "step": 18395 }, { "epoch": 3.81, "learning_rate": 0.00092, "loss": 1.8428, "step": 18400 }, { "epoch": 3.81, "learning_rate": 0.0009202500000000001, "loss": 1.8377, "step": 18405 }, { "epoch": 3.81, "learning_rate": 0.0009205, "loss": 1.841, "step": 18410 }, { "epoch": 3.81, "learning_rate": 0.00092075, "loss": 1.8368, "step": 18415 }, { "epoch": 3.82, "learning_rate": 0.000921, "loss": 1.8397, "step": 18420 }, { "epoch": 3.82, "learning_rate": 0.0009212500000000001, "loss": 1.8365, "step": 18425 }, { "epoch": 3.82, "learning_rate": 0.0009215, "loss": 1.8348, "step": 18430 }, { "epoch": 3.82, "learning_rate": 0.0009217499999999999, "loss": 1.8314, "step": 18435 }, { "epoch": 3.82, "learning_rate": 0.0009220000000000001, "loss": 1.8395, "step": 18440 }, { "epoch": 3.82, "learning_rate": 0.00092225, "loss": 1.8398, "step": 18445 }, { "epoch": 3.82, "learning_rate": 0.0009225, "loss": 1.8426, "step": 18450 }, { "epoch": 3.82, "learning_rate": 0.00092275, "loss": 1.8398, "step": 18455 }, { "epoch": 3.82, "learning_rate": 0.0009230000000000001, "loss": 1.8396, "step": 18460 }, { "epoch": 3.83, "learning_rate": 0.00092325, "loss": 1.8389, "step": 18465 }, { "epoch": 3.83, "learning_rate": 0.0009235000000000001, "loss": 1.8405, "step": 18470 }, { "epoch": 3.83, "learning_rate": 0.00092375, "loss": 1.8315, "step": 18475 }, { "epoch": 3.83, "learning_rate": 0.000924, "loss": 1.83, "step": 18480 }, { "epoch": 3.83, "learning_rate": 0.00092425, "loss": 1.841, "step": 18485 }, { "epoch": 3.83, "learning_rate": 0.0009245, "loss": 1.8367, "step": 18490 }, { "epoch": 3.83, "learning_rate": 0.00092475, "loss": 1.8362, "step": 18495 }, { "epoch": 3.83, "learning_rate": 0.000925, "loss": 1.8346, "step": 18500 }, { "epoch": 3.83, "learning_rate": 0.0009252500000000001, "loss": 1.8366, "step": 18505 }, { "epoch": 3.83, "learning_rate": 0.0009255, "loss": 1.8366, "step": 18510 }, { "epoch": 3.84, "learning_rate": 0.00092575, "loss": 1.8329, "step": 18515 }, { "epoch": 3.84, "learning_rate": 0.0009260000000000001, "loss": 1.8423, "step": 18520 }, { "epoch": 3.84, "learning_rate": 0.00092625, "loss": 1.833, "step": 18525 }, { "epoch": 3.84, "learning_rate": 0.0009265, "loss": 1.8436, "step": 18530 }, { "epoch": 3.84, "learning_rate": 0.00092675, "loss": 1.8358, "step": 18535 }, { "epoch": 3.84, "learning_rate": 0.0009270000000000001, "loss": 1.8341, "step": 18540 }, { "epoch": 3.84, "learning_rate": 0.00092725, "loss": 1.8415, "step": 18545 }, { "epoch": 3.84, "learning_rate": 0.0009275, "loss": 1.837, "step": 18550 }, { "epoch": 3.84, "learning_rate": 0.00092775, "loss": 1.8358, "step": 18555 }, { "epoch": 3.85, "learning_rate": 0.0009280000000000001, "loss": 1.8416, "step": 18560 }, { "epoch": 3.85, "learning_rate": 0.00092825, "loss": 1.8379, "step": 18565 }, { "epoch": 3.85, "learning_rate": 0.0009285, "loss": 1.8348, "step": 18570 }, { "epoch": 3.85, "learning_rate": 0.00092875, "loss": 1.8338, "step": 18575 }, { "epoch": 3.85, "learning_rate": 0.000929, "loss": 1.8366, "step": 18580 }, { "epoch": 3.85, "learning_rate": 0.0009292500000000001, "loss": 1.8358, "step": 18585 }, { "epoch": 3.85, "learning_rate": 0.0009295, "loss": 1.8329, "step": 18590 }, { "epoch": 3.85, "learning_rate": 0.00092975, "loss": 1.8339, "step": 18595 }, { "epoch": 3.85, "learning_rate": 0.00093, "loss": 1.8394, "step": 18600 }, { "epoch": 3.85, "learning_rate": 0.0009302500000000001, "loss": 1.8298, "step": 18605 }, { "epoch": 3.86, "learning_rate": 0.0009305, "loss": 1.8498, "step": 18610 }, { "epoch": 3.86, "learning_rate": 0.0009307499999999999, "loss": 1.8523, "step": 18615 }, { "epoch": 3.86, "learning_rate": 0.0009310000000000001, "loss": 1.8504, "step": 18620 }, { "epoch": 3.86, "learning_rate": 0.00093125, "loss": 1.8485, "step": 18625 }, { "epoch": 3.86, "learning_rate": 0.0009315, "loss": 1.8415, "step": 18630 }, { "epoch": 3.86, "learning_rate": 0.00093175, "loss": 1.8419, "step": 18635 }, { "epoch": 3.86, "learning_rate": 0.0009320000000000001, "loss": 1.8336, "step": 18640 }, { "epoch": 3.86, "learning_rate": 0.00093225, "loss": 1.8427, "step": 18645 }, { "epoch": 3.86, "learning_rate": 0.0009325000000000001, "loss": 1.8385, "step": 18650 }, { "epoch": 3.86, "learning_rate": 0.00093275, "loss": 1.8346, "step": 18655 }, { "epoch": 3.87, "learning_rate": 0.000933, "loss": 1.838, "step": 18660 }, { "epoch": 3.87, "learning_rate": 0.00093325, "loss": 1.8362, "step": 18665 }, { "epoch": 3.87, "learning_rate": 0.0009335, "loss": 1.8398, "step": 18670 }, { "epoch": 3.87, "learning_rate": 0.00093375, "loss": 1.8399, "step": 18675 }, { "epoch": 3.87, "learning_rate": 0.000934, "loss": 1.8331, "step": 18680 }, { "epoch": 3.87, "learning_rate": 0.0009342500000000001, "loss": 1.8348, "step": 18685 }, { "epoch": 3.87, "learning_rate": 0.0009345, "loss": 1.8377, "step": 18690 }, { "epoch": 3.87, "learning_rate": 0.00093475, "loss": 1.8377, "step": 18695 }, { "epoch": 3.87, "learning_rate": 0.0009350000000000001, "loss": 1.8363, "step": 18700 }, { "epoch": 3.88, "learning_rate": 0.00093525, "loss": 1.8364, "step": 18705 }, { "epoch": 3.88, "learning_rate": 0.0009355, "loss": 1.8365, "step": 18710 }, { "epoch": 3.88, "learning_rate": 0.00093575, "loss": 1.8368, "step": 18715 }, { "epoch": 3.88, "learning_rate": 0.0009360000000000001, "loss": 1.8368, "step": 18720 }, { "epoch": 3.88, "learning_rate": 0.00093625, "loss": 1.8435, "step": 18725 }, { "epoch": 3.88, "learning_rate": 0.0009365, "loss": 1.837, "step": 18730 }, { "epoch": 3.88, "learning_rate": 0.00093675, "loss": 1.8364, "step": 18735 }, { "epoch": 3.88, "learning_rate": 0.0009370000000000001, "loss": 1.8392, "step": 18740 }, { "epoch": 3.88, "learning_rate": 0.00093725, "loss": 1.8346, "step": 18745 }, { "epoch": 3.88, "learning_rate": 0.0009375, "loss": 1.8371, "step": 18750 }, { "epoch": 3.89, "learning_rate": 0.00093775, "loss": 1.8398, "step": 18755 }, { "epoch": 3.89, "learning_rate": 0.0009379999999999999, "loss": 1.836, "step": 18760 }, { "epoch": 3.89, "learning_rate": 0.0009382500000000001, "loss": 1.8357, "step": 18765 }, { "epoch": 3.89, "learning_rate": 0.0009385, "loss": 1.8335, "step": 18770 }, { "epoch": 3.89, "learning_rate": 0.00093875, "loss": 1.8341, "step": 18775 }, { "epoch": 3.89, "learning_rate": 0.000939, "loss": 1.8296, "step": 18780 }, { "epoch": 3.89, "learning_rate": 0.0009392500000000001, "loss": 1.8325, "step": 18785 }, { "epoch": 3.89, "learning_rate": 0.0009395, "loss": 1.8291, "step": 18790 }, { "epoch": 3.89, "learning_rate": 0.00093975, "loss": 1.8318, "step": 18795 }, { "epoch": 3.89, "learning_rate": 0.00094, "loss": 1.8386, "step": 18800 }, { "epoch": 3.9, "learning_rate": 0.00094025, "loss": 1.853, "step": 18805 }, { "epoch": 3.9, "learning_rate": 0.0009405, "loss": 1.8495, "step": 18810 }, { "epoch": 3.9, "learning_rate": 0.00094075, "loss": 1.842, "step": 18815 }, { "epoch": 3.9, "learning_rate": 0.000941, "loss": 1.8467, "step": 18820 }, { "epoch": 3.9, "learning_rate": 0.00094125, "loss": 1.8368, "step": 18825 }, { "epoch": 3.9, "learning_rate": 0.0009415000000000001, "loss": 1.8336, "step": 18830 }, { "epoch": 3.9, "learning_rate": 0.00094175, "loss": 1.8383, "step": 18835 }, { "epoch": 3.9, "learning_rate": 0.000942, "loss": 1.8384, "step": 18840 }, { "epoch": 3.9, "learning_rate": 0.00094225, "loss": 1.8378, "step": 18845 }, { "epoch": 3.91, "learning_rate": 0.0009425, "loss": 1.8348, "step": 18850 }, { "epoch": 3.91, "learning_rate": 0.00094275, "loss": 1.8411, "step": 18855 }, { "epoch": 3.91, "learning_rate": 0.0009429999999999999, "loss": 1.8363, "step": 18860 }, { "epoch": 3.91, "learning_rate": 0.0009432500000000001, "loss": 1.8418, "step": 18865 }, { "epoch": 3.91, "learning_rate": 0.0009435, "loss": 1.841, "step": 18870 }, { "epoch": 3.91, "learning_rate": 0.00094375, "loss": 1.8331, "step": 18875 }, { "epoch": 3.91, "learning_rate": 0.000944, "loss": 1.8355, "step": 18880 }, { "epoch": 3.91, "learning_rate": 0.0009442500000000001, "loss": 1.8292, "step": 18885 }, { "epoch": 3.91, "learning_rate": 0.0009445, "loss": 1.8362, "step": 18890 }, { "epoch": 3.91, "learning_rate": 0.00094475, "loss": 1.8289, "step": 18895 }, { "epoch": 3.92, "learning_rate": 0.000945, "loss": 1.8324, "step": 18900 }, { "epoch": 3.92, "learning_rate": 0.00094525, "loss": 1.8369, "step": 18905 }, { "epoch": 3.92, "learning_rate": 0.0009455, "loss": 1.8354, "step": 18910 }, { "epoch": 3.92, "learning_rate": 0.00094575, "loss": 1.8301, "step": 18915 }, { "epoch": 3.92, "learning_rate": 0.000946, "loss": 1.8363, "step": 18920 }, { "epoch": 3.92, "learning_rate": 0.00094625, "loss": 1.8343, "step": 18925 }, { "epoch": 3.92, "learning_rate": 0.0009465000000000001, "loss": 1.8354, "step": 18930 }, { "epoch": 3.92, "learning_rate": 0.00094675, "loss": 1.8344, "step": 18935 }, { "epoch": 3.92, "learning_rate": 0.0009469999999999999, "loss": 1.841, "step": 18940 }, { "epoch": 3.92, "learning_rate": 0.0009472500000000001, "loss": 1.8422, "step": 18945 }, { "epoch": 3.93, "learning_rate": 0.0009475, "loss": 1.8313, "step": 18950 }, { "epoch": 3.93, "learning_rate": 0.00094775, "loss": 1.8357, "step": 18955 }, { "epoch": 3.93, "learning_rate": 0.000948, "loss": 1.8373, "step": 18960 }, { "epoch": 3.93, "learning_rate": 0.0009482500000000001, "loss": 1.832, "step": 18965 }, { "epoch": 3.93, "learning_rate": 0.0009485, "loss": 1.8348, "step": 18970 }, { "epoch": 3.93, "learning_rate": 0.00094875, "loss": 1.8361, "step": 18975 }, { "epoch": 3.93, "learning_rate": 0.000949, "loss": 1.8376, "step": 18980 }, { "epoch": 3.93, "learning_rate": 0.00094925, "loss": 1.8403, "step": 18985 }, { "epoch": 3.93, "learning_rate": 0.0009495, "loss": 1.8375, "step": 18990 }, { "epoch": 3.94, "learning_rate": 0.00094975, "loss": 1.8359, "step": 18995 }, { "epoch": 3.94, "learning_rate": 0.00095, "loss": 1.8353, "step": 19000 }, { "epoch": 3.94, "learning_rate": 0.00095025, "loss": 1.8296, "step": 19005 }, { "epoch": 3.94, "learning_rate": 0.0009505000000000001, "loss": 1.8326, "step": 19010 }, { "epoch": 3.94, "learning_rate": 0.00095075, "loss": 1.8352, "step": 19015 }, { "epoch": 3.94, "learning_rate": 0.000951, "loss": 1.8369, "step": 19020 }, { "epoch": 3.94, "learning_rate": 0.0009512500000000001, "loss": 1.8414, "step": 19025 }, { "epoch": 3.94, "learning_rate": 0.0009515, "loss": 1.8314, "step": 19030 }, { "epoch": 3.94, "learning_rate": 0.00095175, "loss": 1.8367, "step": 19035 }, { "epoch": 3.94, "learning_rate": 0.0009519999999999999, "loss": 1.8328, "step": 19040 }, { "epoch": 3.95, "learning_rate": 0.0009522500000000001, "loss": 1.8387, "step": 19045 }, { "epoch": 3.95, "learning_rate": 0.0009525, "loss": 1.8291, "step": 19050 }, { "epoch": 3.95, "learning_rate": 0.00095275, "loss": 1.8335, "step": 19055 }, { "epoch": 3.95, "learning_rate": 0.000953, "loss": 1.8348, "step": 19060 }, { "epoch": 3.95, "learning_rate": 0.0009532500000000001, "loss": 1.8317, "step": 19065 }, { "epoch": 3.95, "learning_rate": 0.0009535, "loss": 1.8484, "step": 19070 }, { "epoch": 3.95, "learning_rate": 0.00095375, "loss": 1.8423, "step": 19075 }, { "epoch": 3.95, "learning_rate": 0.000954, "loss": 1.8427, "step": 19080 }, { "epoch": 3.95, "learning_rate": 0.00095425, "loss": 1.8384, "step": 19085 }, { "epoch": 3.95, "learning_rate": 0.0009545, "loss": 1.8344, "step": 19090 }, { "epoch": 3.96, "learning_rate": 0.00095475, "loss": 1.8384, "step": 19095 }, { "epoch": 3.96, "learning_rate": 0.000955, "loss": 1.8356, "step": 19100 }, { "epoch": 3.96, "learning_rate": 0.00095525, "loss": 1.8331, "step": 19105 }, { "epoch": 3.96, "learning_rate": 0.0009555000000000001, "loss": 1.8381, "step": 19110 }, { "epoch": 3.96, "learning_rate": 0.00095575, "loss": 1.8357, "step": 19115 }, { "epoch": 3.96, "learning_rate": 0.0009559999999999999, "loss": 1.8391, "step": 19120 }, { "epoch": 3.96, "learning_rate": 0.0009562500000000001, "loss": 1.8283, "step": 19125 }, { "epoch": 3.96, "learning_rate": 0.0009565, "loss": 1.8342, "step": 19130 }, { "epoch": 3.96, "learning_rate": 0.00095675, "loss": 1.8388, "step": 19135 }, { "epoch": 3.97, "learning_rate": 0.000957, "loss": 1.8371, "step": 19140 }, { "epoch": 3.97, "learning_rate": 0.0009572500000000001, "loss": 1.8334, "step": 19145 }, { "epoch": 3.97, "learning_rate": 0.0009575, "loss": 1.8335, "step": 19150 }, { "epoch": 3.97, "learning_rate": 0.00095775, "loss": 1.8358, "step": 19155 }, { "epoch": 3.97, "learning_rate": 0.000958, "loss": 1.8314, "step": 19160 }, { "epoch": 3.97, "learning_rate": 0.0009582500000000001, "loss": 1.8318, "step": 19165 }, { "epoch": 3.97, "learning_rate": 0.0009585, "loss": 1.8351, "step": 19170 }, { "epoch": 3.97, "learning_rate": 0.00095875, "loss": 1.8363, "step": 19175 }, { "epoch": 3.97, "learning_rate": 0.000959, "loss": 1.8356, "step": 19180 }, { "epoch": 3.97, "learning_rate": 0.00095925, "loss": 1.8294, "step": 19185 }, { "epoch": 3.98, "learning_rate": 0.0009595000000000001, "loss": 1.8361, "step": 19190 }, { "epoch": 3.98, "learning_rate": 0.00095975, "loss": 1.8372, "step": 19195 }, { "epoch": 3.98, "learning_rate": 0.00096, "loss": 1.8389, "step": 19200 }, { "epoch": 3.98, "learning_rate": 0.0009602500000000001, "loss": 1.8332, "step": 19205 }, { "epoch": 3.98, "learning_rate": 0.0009605000000000001, "loss": 1.8324, "step": 19210 }, { "epoch": 3.98, "learning_rate": 0.00096075, "loss": 1.8301, "step": 19215 }, { "epoch": 3.98, "learning_rate": 0.0009609999999999999, "loss": 1.8355, "step": 19220 }, { "epoch": 3.98, "learning_rate": 0.0009612500000000001, "loss": 1.8306, "step": 19225 }, { "epoch": 3.98, "learning_rate": 0.0009615, "loss": 1.8338, "step": 19230 }, { "epoch": 3.98, "learning_rate": 0.00096175, "loss": 1.8309, "step": 19235 }, { "epoch": 3.99, "learning_rate": 0.000962, "loss": 1.8319, "step": 19240 }, { "epoch": 3.99, "learning_rate": 0.0009622500000000001, "loss": 1.8337, "step": 19245 }, { "epoch": 3.99, "learning_rate": 0.0009625, "loss": 1.8312, "step": 19250 }, { "epoch": 3.99, "learning_rate": 0.0009627500000000001, "loss": 1.8355, "step": 19255 }, { "epoch": 3.99, "learning_rate": 0.000963, "loss": 1.8286, "step": 19260 }, { "epoch": 3.99, "learning_rate": 0.00096325, "loss": 1.8374, "step": 19265 }, { "epoch": 3.99, "learning_rate": 0.0009635000000000001, "loss": 1.8346, "step": 19270 }, { "epoch": 3.99, "learning_rate": 0.00096375, "loss": 1.8348, "step": 19275 }, { "epoch": 3.99, "learning_rate": 0.000964, "loss": 1.845, "step": 19280 }, { "epoch": 4.0, "learning_rate": 0.00096425, "loss": 1.8459, "step": 19285 }, { "epoch": 4.0, "learning_rate": 0.0009645000000000001, "loss": 1.8349, "step": 19290 }, { "epoch": 4.0, "learning_rate": 0.00096475, "loss": 1.8335, "step": 19295 }, { "epoch": 4.0, "learning_rate": 0.000965, "loss": 1.8397, "step": 19300 }, { "epoch": 4.0, "learning_rate": 0.0009652500000000001, "loss": 1.8328, "step": 19305 }, { "epoch": 4.0, "learning_rate": 0.0009655, "loss": 1.8317, "step": 19310 }, { "epoch": 4.0, "learning_rate": 0.00096575, "loss": 1.8261, "step": 19315 }, { "epoch": 4.0, "learning_rate": 0.000966, "loss": 1.8216, "step": 19320 }, { "epoch": 4.0, "learning_rate": 0.0009662500000000001, "loss": 1.8298, "step": 19325 }, { "epoch": 4.0, "learning_rate": 0.0009665, "loss": 1.8331, "step": 19330 }, { "epoch": 4.01, "learning_rate": 0.00096675, "loss": 1.8294, "step": 19335 }, { "epoch": 4.01, "learning_rate": 0.000967, "loss": 1.8325, "step": 19340 }, { "epoch": 4.01, "learning_rate": 0.0009672500000000001, "loss": 1.8232, "step": 19345 }, { "epoch": 4.01, "learning_rate": 0.0009675, "loss": 1.8252, "step": 19350 }, { "epoch": 4.01, "learning_rate": 0.00096775, "loss": 1.8232, "step": 19355 }, { "epoch": 4.01, "learning_rate": 0.000968, "loss": 1.828, "step": 19360 }, { "epoch": 4.01, "learning_rate": 0.00096825, "loss": 1.8322, "step": 19365 }, { "epoch": 4.01, "learning_rate": 0.0009685000000000001, "loss": 1.8249, "step": 19370 }, { "epoch": 4.01, "learning_rate": 0.00096875, "loss": 1.8295, "step": 19375 }, { "epoch": 4.01, "learning_rate": 0.000969, "loss": 1.8218, "step": 19380 }, { "epoch": 4.02, "learning_rate": 0.00096925, "loss": 1.8235, "step": 19385 }, { "epoch": 4.02, "learning_rate": 0.0009695000000000001, "loss": 1.822, "step": 19390 }, { "epoch": 4.02, "learning_rate": 0.00096975, "loss": 1.8247, "step": 19395 }, { "epoch": 4.02, "learning_rate": 0.0009699999999999999, "loss": 1.8216, "step": 19400 }, { "epoch": 4.02, "learning_rate": 0.00097025, "loss": 1.831, "step": 19405 }, { "epoch": 4.02, "learning_rate": 0.0009705, "loss": 1.8259, "step": 19410 }, { "epoch": 4.02, "learning_rate": 0.00097075, "loss": 1.8235, "step": 19415 }, { "epoch": 4.02, "learning_rate": 0.000971, "loss": 1.8263, "step": 19420 }, { "epoch": 4.02, "learning_rate": 0.00097125, "loss": 1.8263, "step": 19425 }, { "epoch": 4.03, "learning_rate": 0.0009715, "loss": 1.8194, "step": 19430 }, { "epoch": 4.03, "learning_rate": 0.0009717500000000001, "loss": 1.8396, "step": 19435 }, { "epoch": 4.03, "learning_rate": 0.000972, "loss": 1.8341, "step": 19440 }, { "epoch": 4.03, "learning_rate": 0.0009722499999999999, "loss": 1.8306, "step": 19445 }, { "epoch": 4.03, "learning_rate": 0.0009725000000000001, "loss": 1.8281, "step": 19450 }, { "epoch": 4.03, "learning_rate": 0.00097275, "loss": 1.8271, "step": 19455 }, { "epoch": 4.03, "learning_rate": 0.000973, "loss": 1.8348, "step": 19460 }, { "epoch": 4.03, "learning_rate": 0.0009732499999999999, "loss": 1.8236, "step": 19465 }, { "epoch": 4.03, "learning_rate": 0.0009735000000000001, "loss": 1.8188, "step": 19470 }, { "epoch": 4.03, "learning_rate": 0.00097375, "loss": 1.8218, "step": 19475 }, { "epoch": 4.04, "learning_rate": 0.000974, "loss": 1.8238, "step": 19480 }, { "epoch": 4.04, "learning_rate": 0.00097425, "loss": 1.8269, "step": 19485 }, { "epoch": 4.04, "learning_rate": 0.0009745000000000001, "loss": 1.8261, "step": 19490 }, { "epoch": 4.04, "learning_rate": 0.00097475, "loss": 1.8294, "step": 19495 }, { "epoch": 4.04, "learning_rate": 0.000975, "loss": 1.8233, "step": 19500 }, { "epoch": 4.04, "learning_rate": 0.00097525, "loss": 1.8299, "step": 19505 }, { "epoch": 4.04, "learning_rate": 0.0009755, "loss": 1.8333, "step": 19510 }, { "epoch": 4.04, "learning_rate": 0.0009757500000000001, "loss": 1.8273, "step": 19515 }, { "epoch": 4.04, "learning_rate": 0.000976, "loss": 1.82, "step": 19520 }, { "epoch": 4.04, "learning_rate": 0.00097625, "loss": 1.8304, "step": 19525 }, { "epoch": 4.05, "learning_rate": 0.0009765, "loss": 1.8327, "step": 19530 }, { "epoch": 4.05, "learning_rate": 0.00097675, "loss": 1.8318, "step": 19535 }, { "epoch": 4.05, "learning_rate": 0.000977, "loss": 1.8341, "step": 19540 }, { "epoch": 4.05, "learning_rate": 0.00097725, "loss": 1.8294, "step": 19545 }, { "epoch": 4.05, "learning_rate": 0.0009775, "loss": 1.8253, "step": 19550 }, { "epoch": 4.05, "learning_rate": 0.00097775, "loss": 1.8277, "step": 19555 }, { "epoch": 4.05, "learning_rate": 0.000978, "loss": 1.835, "step": 19560 }, { "epoch": 4.05, "learning_rate": 0.00097825, "loss": 1.8221, "step": 19565 }, { "epoch": 4.05, "learning_rate": 0.0009785, "loss": 1.8301, "step": 19570 }, { "epoch": 4.06, "learning_rate": 0.00097875, "loss": 1.8262, "step": 19575 }, { "epoch": 4.06, "learning_rate": 0.000979, "loss": 1.8259, "step": 19580 }, { "epoch": 4.06, "learning_rate": 0.0009792499999999999, "loss": 1.8248, "step": 19585 }, { "epoch": 4.06, "learning_rate": 0.0009795000000000001, "loss": 1.8305, "step": 19590 }, { "epoch": 4.06, "learning_rate": 0.00097975, "loss": 1.83, "step": 19595 }, { "epoch": 4.06, "learning_rate": 0.00098, "loss": 1.829, "step": 19600 }, { "epoch": 4.06, "learning_rate": 0.00098025, "loss": 1.8301, "step": 19605 }, { "epoch": 4.06, "learning_rate": 0.0009805, "loss": 1.8261, "step": 19610 }, { "epoch": 4.06, "learning_rate": 0.00098075, "loss": 1.8276, "step": 19615 }, { "epoch": 4.06, "learning_rate": 0.000981, "loss": 1.826, "step": 19620 }, { "epoch": 4.07, "learning_rate": 0.00098125, "loss": 1.8314, "step": 19625 }, { "epoch": 4.07, "learning_rate": 0.0009815000000000002, "loss": 1.832, "step": 19630 }, { "epoch": 4.07, "learning_rate": 0.00098175, "loss": 1.8312, "step": 19635 }, { "epoch": 4.07, "learning_rate": 0.000982, "loss": 1.8217, "step": 19640 }, { "epoch": 4.07, "learning_rate": 0.00098225, "loss": 1.8277, "step": 19645 }, { "epoch": 4.07, "learning_rate": 0.0009825, "loss": 1.8277, "step": 19650 }, { "epoch": 4.07, "learning_rate": 0.0009827500000000001, "loss": 1.8247, "step": 19655 }, { "epoch": 4.07, "learning_rate": 0.000983, "loss": 1.8241, "step": 19660 }, { "epoch": 4.07, "learning_rate": 0.00098325, "loss": 1.8264, "step": 19665 }, { "epoch": 4.07, "learning_rate": 0.0009835, "loss": 1.8256, "step": 19670 }, { "epoch": 4.08, "learning_rate": 0.00098375, "loss": 1.8273, "step": 19675 }, { "epoch": 4.08, "learning_rate": 0.000984, "loss": 1.8278, "step": 19680 }, { "epoch": 4.08, "learning_rate": 0.0009842499999999999, "loss": 1.8332, "step": 19685 }, { "epoch": 4.08, "learning_rate": 0.0009845000000000001, "loss": 1.8268, "step": 19690 }, { "epoch": 4.08, "learning_rate": 0.00098475, "loss": 1.8288, "step": 19695 }, { "epoch": 4.08, "learning_rate": 0.000985, "loss": 1.8233, "step": 19700 }, { "epoch": 4.08, "learning_rate": 0.00098525, "loss": 1.8255, "step": 19705 }, { "epoch": 4.08, "learning_rate": 0.0009855, "loss": 1.8257, "step": 19710 }, { "epoch": 4.08, "learning_rate": 0.00098575, "loss": 1.8246, "step": 19715 }, { "epoch": 4.09, "learning_rate": 0.0009860000000000001, "loss": 1.8259, "step": 19720 }, { "epoch": 4.09, "learning_rate": 0.00098625, "loss": 1.821, "step": 19725 }, { "epoch": 4.09, "learning_rate": 0.0009865, "loss": 1.8302, "step": 19730 }, { "epoch": 4.09, "learning_rate": 0.00098675, "loss": 1.8269, "step": 19735 }, { "epoch": 4.09, "learning_rate": 0.000987, "loss": 1.8273, "step": 19740 }, { "epoch": 4.09, "learning_rate": 0.00098725, "loss": 1.826, "step": 19745 }, { "epoch": 4.09, "learning_rate": 0.0009875, "loss": 1.8308, "step": 19750 }, { "epoch": 4.09, "learning_rate": 0.0009877500000000001, "loss": 1.8266, "step": 19755 }, { "epoch": 4.09, "learning_rate": 0.000988, "loss": 1.8283, "step": 19760 }, { "epoch": 4.09, "learning_rate": 0.00098825, "loss": 1.8278, "step": 19765 }, { "epoch": 4.1, "learning_rate": 0.0009885, "loss": 1.8278, "step": 19770 }, { "epoch": 4.1, "learning_rate": 0.00098875, "loss": 1.8236, "step": 19775 }, { "epoch": 4.1, "learning_rate": 0.000989, "loss": 1.8262, "step": 19780 }, { "epoch": 4.1, "learning_rate": 0.00098925, "loss": 1.8239, "step": 19785 }, { "epoch": 4.1, "learning_rate": 0.0009895000000000001, "loss": 1.8368, "step": 19790 }, { "epoch": 4.1, "learning_rate": 0.00098975, "loss": 1.8367, "step": 19795 }, { "epoch": 4.1, "learning_rate": 0.00099, "loss": 1.8322, "step": 19800 }, { "epoch": 4.1, "learning_rate": 0.00099025, "loss": 1.8286, "step": 19805 }, { "epoch": 4.1, "learning_rate": 0.0009905, "loss": 1.8318, "step": 19810 }, { "epoch": 4.11, "learning_rate": 0.00099075, "loss": 1.8278, "step": 19815 }, { "epoch": 4.11, "learning_rate": 0.000991, "loss": 1.8247, "step": 19820 }, { "epoch": 4.11, "learning_rate": 0.00099125, "loss": 1.8235, "step": 19825 }, { "epoch": 4.11, "learning_rate": 0.0009915, "loss": 1.8262, "step": 19830 }, { "epoch": 4.11, "learning_rate": 0.00099175, "loss": 1.827, "step": 19835 }, { "epoch": 4.11, "learning_rate": 0.000992, "loss": 1.8219, "step": 19840 }, { "epoch": 4.11, "learning_rate": 0.00099225, "loss": 1.8221, "step": 19845 }, { "epoch": 4.11, "learning_rate": 0.0009925000000000001, "loss": 1.8309, "step": 19850 }, { "epoch": 4.11, "learning_rate": 0.0009927500000000001, "loss": 1.827, "step": 19855 }, { "epoch": 4.11, "learning_rate": 0.000993, "loss": 1.8247, "step": 19860 }, { "epoch": 4.12, "learning_rate": 0.00099325, "loss": 1.8197, "step": 19865 }, { "epoch": 4.12, "learning_rate": 0.0009935, "loss": 1.8326, "step": 19870 }, { "epoch": 4.12, "learning_rate": 0.00099375, "loss": 1.8279, "step": 19875 }, { "epoch": 4.12, "learning_rate": 0.000994, "loss": 1.8261, "step": 19880 }, { "epoch": 4.12, "learning_rate": 0.00099425, "loss": 1.8305, "step": 19885 }, { "epoch": 4.12, "learning_rate": 0.0009945000000000002, "loss": 1.8264, "step": 19890 }, { "epoch": 4.12, "learning_rate": 0.00099475, "loss": 1.829, "step": 19895 }, { "epoch": 4.12, "learning_rate": 0.000995, "loss": 1.8294, "step": 19900 }, { "epoch": 4.12, "learning_rate": 0.00099525, "loss": 1.8274, "step": 19905 }, { "epoch": 4.12, "learning_rate": 0.0009955, "loss": 1.8284, "step": 19910 }, { "epoch": 4.13, "learning_rate": 0.00099575, "loss": 1.8271, "step": 19915 }, { "epoch": 4.13, "learning_rate": 0.000996, "loss": 1.8258, "step": 19920 }, { "epoch": 4.13, "learning_rate": 0.00099625, "loss": 1.8229, "step": 19925 }, { "epoch": 4.13, "learning_rate": 0.0009965, "loss": 1.8227, "step": 19930 }, { "epoch": 4.13, "learning_rate": 0.00099675, "loss": 1.829, "step": 19935 }, { "epoch": 4.13, "learning_rate": 0.000997, "loss": 1.8281, "step": 19940 }, { "epoch": 4.13, "learning_rate": 0.00099725, "loss": 1.829, "step": 19945 }, { "epoch": 4.13, "learning_rate": 0.0009975000000000001, "loss": 1.8282, "step": 19950 }, { "epoch": 4.13, "learning_rate": 0.00099775, "loss": 1.829, "step": 19955 }, { "epoch": 4.14, "learning_rate": 0.000998, "loss": 1.8259, "step": 19960 }, { "epoch": 4.14, "learning_rate": 0.00099825, "loss": 1.8242, "step": 19965 }, { "epoch": 4.14, "learning_rate": 0.0009985, "loss": 1.824, "step": 19970 }, { "epoch": 4.14, "learning_rate": 0.00099875, "loss": 1.8267, "step": 19975 }, { "epoch": 4.14, "learning_rate": 0.000999, "loss": 1.8274, "step": 19980 }, { "epoch": 4.14, "learning_rate": 0.00099925, "loss": 1.8231, "step": 19985 }, { "epoch": 4.14, "learning_rate": 0.0009995000000000002, "loss": 1.8244, "step": 19990 }, { "epoch": 4.14, "learning_rate": 0.00099975, "loss": 1.827, "step": 19995 }, { "epoch": 4.14, "learning_rate": 0.001, "loss": 1.8253, "step": 20000 }, { "epoch": 4.14, "learning_rate": 0.0009999045892567504, "loss": 1.8268, "step": 20005 }, { "epoch": 4.15, "learning_rate": 0.0009998091785135006, "loss": 1.8255, "step": 20010 }, { "epoch": 4.15, "learning_rate": 0.000999713767770251, "loss": 1.8261, "step": 20015 }, { "epoch": 4.15, "learning_rate": 0.0009996183570270011, "loss": 1.8262, "step": 20020 }, { "epoch": 4.15, "learning_rate": 0.0009995229462837515, "loss": 1.8244, "step": 20025 }, { "epoch": 4.15, "learning_rate": 0.000999427535540502, "loss": 1.8249, "step": 20030 }, { "epoch": 4.15, "learning_rate": 0.0009993321247972523, "loss": 1.8289, "step": 20035 }, { "epoch": 4.15, "learning_rate": 0.0009992367140540025, "loss": 1.828, "step": 20040 }, { "epoch": 4.15, "learning_rate": 0.0009991413033107529, "loss": 1.8306, "step": 20045 }, { "epoch": 4.15, "learning_rate": 0.000999045892567503, "loss": 1.8196, "step": 20050 }, { "epoch": 4.15, "learning_rate": 0.0009989504818242534, "loss": 1.8185, "step": 20055 }, { "epoch": 4.16, "learning_rate": 0.0009988550710810038, "loss": 1.8261, "step": 20060 }, { "epoch": 4.16, "learning_rate": 0.000998759660337754, "loss": 1.8283, "step": 20065 }, { "epoch": 4.16, "learning_rate": 0.0009986642495945044, "loss": 1.824, "step": 20070 }, { "epoch": 4.16, "learning_rate": 0.0009985688388512548, "loss": 1.8265, "step": 20075 }, { "epoch": 4.16, "learning_rate": 0.000998473428108005, "loss": 1.8239, "step": 20080 }, { "epoch": 4.16, "learning_rate": 0.0009983780173647553, "loss": 1.8203, "step": 20085 }, { "epoch": 4.16, "learning_rate": 0.0009982826066215057, "loss": 1.8239, "step": 20090 }, { "epoch": 4.16, "learning_rate": 0.0009981871958782559, "loss": 1.83, "step": 20095 }, { "epoch": 4.16, "learning_rate": 0.0009980917851350063, "loss": 1.826, "step": 20100 }, { "epoch": 4.17, "learning_rate": 0.0009979963743917564, "loss": 1.8292, "step": 20105 }, { "epoch": 4.17, "learning_rate": 0.0009979009636485068, "loss": 1.8213, "step": 20110 }, { "epoch": 4.17, "learning_rate": 0.0009978055529052572, "loss": 1.8288, "step": 20115 }, { "epoch": 4.17, "learning_rate": 0.0009977101421620076, "loss": 1.8226, "step": 20120 }, { "epoch": 4.17, "learning_rate": 0.0009976147314187578, "loss": 1.8245, "step": 20125 }, { "epoch": 4.17, "learning_rate": 0.0009975193206755082, "loss": 1.8215, "step": 20130 }, { "epoch": 4.17, "learning_rate": 0.0009974239099322583, "loss": 1.8258, "step": 20135 }, { "epoch": 4.17, "learning_rate": 0.0009973284991890087, "loss": 1.8286, "step": 20140 }, { "epoch": 4.17, "learning_rate": 0.000997233088445759, "loss": 1.8228, "step": 20145 }, { "epoch": 4.17, "learning_rate": 0.0009971376777025093, "loss": 1.8172, "step": 20150 }, { "epoch": 4.18, "learning_rate": 0.0009970422669592597, "loss": 1.8199, "step": 20155 }, { "epoch": 4.18, "learning_rate": 0.0009969468562160098, "loss": 1.8262, "step": 20160 }, { "epoch": 4.18, "learning_rate": 0.0009968514454727602, "loss": 1.8284, "step": 20165 }, { "epoch": 4.18, "learning_rate": 0.0009967560347295106, "loss": 1.8218, "step": 20170 }, { "epoch": 4.18, "learning_rate": 0.0009966606239862608, "loss": 1.8349, "step": 20175 }, { "epoch": 4.18, "learning_rate": 0.0009965652132430112, "loss": 1.836, "step": 20180 }, { "epoch": 4.18, "learning_rate": 0.0009964698024997616, "loss": 1.835, "step": 20185 }, { "epoch": 4.18, "learning_rate": 0.0009963743917565117, "loss": 1.8307, "step": 20190 }, { "epoch": 4.18, "learning_rate": 0.0009962789810132621, "loss": 1.8227, "step": 20195 }, { "epoch": 4.18, "learning_rate": 0.0009961835702700123, "loss": 1.829, "step": 20200 }, { "epoch": 4.19, "learning_rate": 0.0009960881595267627, "loss": 1.8255, "step": 20205 }, { "epoch": 4.19, "learning_rate": 0.000995992748783513, "loss": 1.8303, "step": 20210 }, { "epoch": 4.19, "learning_rate": 0.0009958973380402635, "loss": 1.8253, "step": 20215 }, { "epoch": 4.19, "learning_rate": 0.0009958019272970136, "loss": 1.8265, "step": 20220 }, { "epoch": 4.19, "learning_rate": 0.000995706516553764, "loss": 1.8348, "step": 20225 }, { "epoch": 4.19, "learning_rate": 0.0009956111058105142, "loss": 1.8277, "step": 20230 }, { "epoch": 4.19, "learning_rate": 0.0009955156950672646, "loss": 1.8314, "step": 20235 }, { "epoch": 4.19, "learning_rate": 0.000995420284324015, "loss": 1.8259, "step": 20240 }, { "epoch": 4.19, "learning_rate": 0.0009953248735807651, "loss": 1.8294, "step": 20245 }, { "epoch": 4.2, "learning_rate": 0.0009952294628375155, "loss": 1.8252, "step": 20250 }, { "epoch": 4.2, "learning_rate": 0.000995134052094266, "loss": 1.8261, "step": 20255 }, { "epoch": 4.2, "learning_rate": 0.000995038641351016, "loss": 1.8305, "step": 20260 }, { "epoch": 4.2, "learning_rate": 0.0009949432306077665, "loss": 1.8248, "step": 20265 }, { "epoch": 4.2, "learning_rate": 0.0009948478198645169, "loss": 1.8285, "step": 20270 }, { "epoch": 4.2, "learning_rate": 0.000994752409121267, "loss": 1.8256, "step": 20275 }, { "epoch": 4.2, "learning_rate": 0.0009946569983780174, "loss": 1.8257, "step": 20280 }, { "epoch": 4.2, "learning_rate": 0.0009945615876347676, "loss": 1.8256, "step": 20285 }, { "epoch": 4.2, "learning_rate": 0.000994466176891518, "loss": 1.8252, "step": 20290 }, { "epoch": 4.2, "learning_rate": 0.0009943707661482684, "loss": 1.8243, "step": 20295 }, { "epoch": 4.21, "learning_rate": 0.0009942753554050188, "loss": 1.8295, "step": 20300 }, { "epoch": 4.21, "learning_rate": 0.000994179944661769, "loss": 1.8217, "step": 20305 }, { "epoch": 4.21, "learning_rate": 0.0009940845339185193, "loss": 1.8247, "step": 20310 }, { "epoch": 4.21, "learning_rate": 0.0009939891231752695, "loss": 1.8229, "step": 20315 }, { "epoch": 4.21, "learning_rate": 0.0009938937124320199, "loss": 1.8261, "step": 20320 }, { "epoch": 4.21, "learning_rate": 0.0009937983016887703, "loss": 1.8243, "step": 20325 }, { "epoch": 4.21, "learning_rate": 0.0009937028909455204, "loss": 1.8287, "step": 20330 }, { "epoch": 4.21, "learning_rate": 0.0009936074802022708, "loss": 1.8287, "step": 20335 }, { "epoch": 4.21, "learning_rate": 0.000993512069459021, "loss": 1.8252, "step": 20340 }, { "epoch": 4.21, "learning_rate": 0.0009934166587157714, "loss": 1.8268, "step": 20345 }, { "epoch": 4.22, "learning_rate": 0.0009933212479725218, "loss": 1.8222, "step": 20350 }, { "epoch": 4.22, "learning_rate": 0.0009932258372292722, "loss": 1.8183, "step": 20355 }, { "epoch": 4.22, "learning_rate": 0.0009931304264860223, "loss": 1.8193, "step": 20360 }, { "epoch": 4.22, "learning_rate": 0.0009930350157427727, "loss": 1.824, "step": 20365 }, { "epoch": 4.22, "learning_rate": 0.000992939604999523, "loss": 1.8259, "step": 20370 }, { "epoch": 4.22, "learning_rate": 0.0009928441942562733, "loss": 1.8208, "step": 20375 }, { "epoch": 4.22, "learning_rate": 0.0009927487835130235, "loss": 1.829, "step": 20380 }, { "epoch": 4.22, "learning_rate": 0.0009926533727697738, "loss": 1.8268, "step": 20385 }, { "epoch": 4.22, "learning_rate": 0.0009925579620265242, "loss": 1.8247, "step": 20390 }, { "epoch": 4.23, "learning_rate": 0.0009924625512832746, "loss": 1.8228, "step": 20395 }, { "epoch": 4.23, "learning_rate": 0.0009923671405400248, "loss": 1.8242, "step": 20400 }, { "epoch": 4.23, "learning_rate": 0.0009922717297967752, "loss": 1.825, "step": 20405 }, { "epoch": 4.23, "learning_rate": 0.0009921763190535253, "loss": 1.8242, "step": 20410 }, { "epoch": 4.23, "learning_rate": 0.0009920809083102757, "loss": 1.8225, "step": 20415 }, { "epoch": 4.23, "learning_rate": 0.0009919854975670261, "loss": 1.8244, "step": 20420 }, { "epoch": 4.23, "learning_rate": 0.0009918900868237763, "loss": 1.8195, "step": 20425 }, { "epoch": 4.23, "learning_rate": 0.0009917946760805267, "loss": 1.8201, "step": 20430 }, { "epoch": 4.23, "learning_rate": 0.0009916992653372769, "loss": 1.822, "step": 20435 }, { "epoch": 4.23, "learning_rate": 0.0009916038545940275, "loss": 1.8215, "step": 20440 }, { "epoch": 4.24, "learning_rate": 0.0009915084438507776, "loss": 1.8247, "step": 20445 }, { "epoch": 4.24, "learning_rate": 0.000991413033107528, "loss": 1.8252, "step": 20450 }, { "epoch": 4.24, "learning_rate": 0.0009913176223642782, "loss": 1.8218, "step": 20455 }, { "epoch": 4.24, "learning_rate": 0.0009912222116210286, "loss": 1.8206, "step": 20460 }, { "epoch": 4.24, "learning_rate": 0.0009911268008777788, "loss": 1.8229, "step": 20465 }, { "epoch": 4.24, "learning_rate": 0.0009910313901345291, "loss": 1.8241, "step": 20470 }, { "epoch": 4.24, "learning_rate": 0.0009909359793912795, "loss": 1.8175, "step": 20475 }, { "epoch": 4.24, "learning_rate": 0.0009908405686480297, "loss": 1.8233, "step": 20480 }, { "epoch": 4.24, "learning_rate": 0.00099074515790478, "loss": 1.8182, "step": 20485 }, { "epoch": 4.24, "learning_rate": 0.0009906497471615305, "loss": 1.8227, "step": 20490 }, { "epoch": 4.25, "learning_rate": 0.0009905543364182806, "loss": 1.8233, "step": 20495 }, { "epoch": 4.25, "learning_rate": 0.000990458925675031, "loss": 1.821, "step": 20500 }, { "epoch": 4.25, "learning_rate": 0.0009903635149317814, "loss": 1.8255, "step": 20505 }, { "epoch": 4.25, "learning_rate": 0.0009902681041885316, "loss": 1.8244, "step": 20510 }, { "epoch": 4.25, "learning_rate": 0.000990172693445282, "loss": 1.8222, "step": 20515 }, { "epoch": 4.25, "learning_rate": 0.0009900772827020322, "loss": 1.8231, "step": 20520 }, { "epoch": 4.25, "learning_rate": 0.0009899818719587825, "loss": 1.8196, "step": 20525 }, { "epoch": 4.25, "learning_rate": 0.000989886461215533, "loss": 1.8243, "step": 20530 }, { "epoch": 4.25, "learning_rate": 0.0009897910504722833, "loss": 1.8203, "step": 20535 }, { "epoch": 4.26, "learning_rate": 0.0009896956397290335, "loss": 1.8227, "step": 20540 }, { "epoch": 4.26, "learning_rate": 0.0009896002289857839, "loss": 1.8217, "step": 20545 }, { "epoch": 4.26, "learning_rate": 0.000989504818242534, "loss": 1.8252, "step": 20550 }, { "epoch": 4.26, "learning_rate": 0.0009894094074992844, "loss": 1.8217, "step": 20555 }, { "epoch": 4.26, "learning_rate": 0.0009893139967560348, "loss": 1.8253, "step": 20560 }, { "epoch": 4.26, "learning_rate": 0.000989218586012785, "loss": 1.8209, "step": 20565 }, { "epoch": 4.26, "learning_rate": 0.0009891231752695354, "loss": 1.8219, "step": 20570 }, { "epoch": 4.26, "learning_rate": 0.0009890277645262858, "loss": 1.8235, "step": 20575 }, { "epoch": 4.26, "learning_rate": 0.000988932353783036, "loss": 1.8226, "step": 20580 }, { "epoch": 4.26, "learning_rate": 0.0009888369430397863, "loss": 1.8188, "step": 20585 }, { "epoch": 4.27, "learning_rate": 0.0009887415322965367, "loss": 1.823, "step": 20590 }, { "epoch": 4.27, "learning_rate": 0.000988646121553287, "loss": 1.823, "step": 20595 }, { "epoch": 4.27, "learning_rate": 0.0009885507108100373, "loss": 1.8241, "step": 20600 }, { "epoch": 4.27, "learning_rate": 0.0009884553000667875, "loss": 1.8196, "step": 20605 }, { "epoch": 4.27, "learning_rate": 0.0009883598893235378, "loss": 1.8265, "step": 20610 }, { "epoch": 4.27, "learning_rate": 0.000988264478580288, "loss": 1.8232, "step": 20615 }, { "epoch": 4.27, "learning_rate": 0.0009881690678370384, "loss": 1.8191, "step": 20620 }, { "epoch": 4.27, "learning_rate": 0.0009880736570937888, "loss": 1.8188, "step": 20625 }, { "epoch": 4.27, "learning_rate": 0.0009879782463505392, "loss": 1.8194, "step": 20630 }, { "epoch": 4.27, "learning_rate": 0.0009878828356072893, "loss": 1.8192, "step": 20635 }, { "epoch": 4.28, "learning_rate": 0.0009877874248640397, "loss": 1.8205, "step": 20640 }, { "epoch": 4.28, "learning_rate": 0.0009876920141207901, "loss": 1.8289, "step": 20645 }, { "epoch": 4.28, "learning_rate": 0.0009875966033775403, "loss": 1.825, "step": 20650 }, { "epoch": 4.28, "learning_rate": 0.0009875011926342907, "loss": 1.8211, "step": 20655 }, { "epoch": 4.28, "learning_rate": 0.0009874057818910409, "loss": 1.8213, "step": 20660 }, { "epoch": 4.28, "learning_rate": 0.0009873103711477912, "loss": 1.8167, "step": 20665 }, { "epoch": 4.28, "learning_rate": 0.0009872149604045416, "loss": 1.8241, "step": 20670 }, { "epoch": 4.28, "learning_rate": 0.000987119549661292, "loss": 1.8235, "step": 20675 }, { "epoch": 4.28, "learning_rate": 0.0009870241389180422, "loss": 1.8252, "step": 20680 }, { "epoch": 4.29, "learning_rate": 0.0009869287281747926, "loss": 1.8191, "step": 20685 }, { "epoch": 4.29, "learning_rate": 0.0009868333174315428, "loss": 1.8251, "step": 20690 }, { "epoch": 4.29, "learning_rate": 0.0009867379066882931, "loss": 1.8235, "step": 20695 }, { "epoch": 4.29, "learning_rate": 0.0009866424959450433, "loss": 1.8201, "step": 20700 }, { "epoch": 4.29, "learning_rate": 0.0009865470852017937, "loss": 1.8264, "step": 20705 }, { "epoch": 4.29, "learning_rate": 0.000986451674458544, "loss": 1.8246, "step": 20710 }, { "epoch": 4.29, "learning_rate": 0.0009863562637152945, "loss": 1.8225, "step": 20715 }, { "epoch": 4.29, "learning_rate": 0.0009862608529720446, "loss": 1.8217, "step": 20720 }, { "epoch": 4.29, "learning_rate": 0.000986165442228795, "loss": 1.8273, "step": 20725 }, { "epoch": 4.29, "learning_rate": 0.0009860700314855452, "loss": 1.8204, "step": 20730 }, { "epoch": 4.3, "learning_rate": 0.0009859746207422956, "loss": 1.8251, "step": 20735 }, { "epoch": 4.3, "learning_rate": 0.000985879209999046, "loss": 1.82, "step": 20740 }, { "epoch": 4.3, "learning_rate": 0.0009857837992557962, "loss": 1.8275, "step": 20745 }, { "epoch": 4.3, "learning_rate": 0.0009856883885125465, "loss": 1.8242, "step": 20750 }, { "epoch": 4.3, "learning_rate": 0.0009855929777692967, "loss": 1.8296, "step": 20755 }, { "epoch": 4.3, "learning_rate": 0.000985497567026047, "loss": 1.8281, "step": 20760 }, { "epoch": 4.3, "learning_rate": 0.0009854021562827975, "loss": 1.8218, "step": 20765 }, { "epoch": 4.3, "learning_rate": 0.0009853067455395479, "loss": 1.8242, "step": 20770 }, { "epoch": 4.3, "learning_rate": 0.000985211334796298, "loss": 1.8264, "step": 20775 }, { "epoch": 4.3, "learning_rate": 0.0009851159240530484, "loss": 1.8211, "step": 20780 }, { "epoch": 4.31, "learning_rate": 0.0009850205133097986, "loss": 1.8242, "step": 20785 }, { "epoch": 4.31, "learning_rate": 0.000984925102566549, "loss": 1.8242, "step": 20790 }, { "epoch": 4.31, "learning_rate": 0.0009848296918232994, "loss": 1.8218, "step": 20795 }, { "epoch": 4.31, "learning_rate": 0.0009847342810800496, "loss": 1.8196, "step": 20800 }, { "epoch": 4.31, "learning_rate": 0.0009846388703368, "loss": 1.8168, "step": 20805 }, { "epoch": 4.31, "learning_rate": 0.0009845434595935503, "loss": 1.8236, "step": 20810 }, { "epoch": 4.31, "learning_rate": 0.0009844480488503005, "loss": 1.817, "step": 20815 }, { "epoch": 4.31, "learning_rate": 0.000984352638107051, "loss": 1.8172, "step": 20820 }, { "epoch": 4.31, "learning_rate": 0.0009842572273638013, "loss": 1.8214, "step": 20825 }, { "epoch": 4.32, "learning_rate": 0.0009841618166205515, "loss": 1.8221, "step": 20830 }, { "epoch": 4.32, "learning_rate": 0.0009840664058773018, "loss": 1.8239, "step": 20835 }, { "epoch": 4.32, "learning_rate": 0.000983970995134052, "loss": 1.8259, "step": 20840 }, { "epoch": 4.32, "learning_rate": 0.0009838755843908024, "loss": 1.823, "step": 20845 }, { "epoch": 4.32, "learning_rate": 0.0009837801736475528, "loss": 1.8265, "step": 20850 }, { "epoch": 4.32, "learning_rate": 0.0009836847629043032, "loss": 1.8186, "step": 20855 }, { "epoch": 4.32, "learning_rate": 0.0009835893521610533, "loss": 1.819, "step": 20860 }, { "epoch": 4.32, "learning_rate": 0.0009834939414178037, "loss": 1.8238, "step": 20865 }, { "epoch": 4.32, "learning_rate": 0.000983398530674554, "loss": 1.8219, "step": 20870 }, { "epoch": 4.32, "learning_rate": 0.0009833031199313043, "loss": 1.8177, "step": 20875 }, { "epoch": 4.33, "learning_rate": 0.0009832077091880547, "loss": 1.8145, "step": 20880 }, { "epoch": 4.33, "learning_rate": 0.0009831122984448049, "loss": 1.8211, "step": 20885 }, { "epoch": 4.33, "learning_rate": 0.0009830168877015552, "loss": 1.8202, "step": 20890 }, { "epoch": 4.33, "learning_rate": 0.0009829214769583054, "loss": 1.817, "step": 20895 }, { "epoch": 4.33, "learning_rate": 0.0009828260662150558, "loss": 1.8263, "step": 20900 }, { "epoch": 4.33, "learning_rate": 0.0009827306554718062, "loss": 1.8179, "step": 20905 }, { "epoch": 4.33, "learning_rate": 0.0009826352447285566, "loss": 1.8255, "step": 20910 }, { "epoch": 4.33, "learning_rate": 0.0009825398339853068, "loss": 1.8179, "step": 20915 }, { "epoch": 4.33, "learning_rate": 0.0009824444232420571, "loss": 1.8206, "step": 20920 }, { "epoch": 4.33, "learning_rate": 0.0009823490124988073, "loss": 1.8213, "step": 20925 }, { "epoch": 4.34, "learning_rate": 0.0009822536017555577, "loss": 1.8217, "step": 20930 }, { "epoch": 4.34, "learning_rate": 0.0009821581910123079, "loss": 1.8185, "step": 20935 }, { "epoch": 4.34, "learning_rate": 0.0009820627802690583, "loss": 1.8244, "step": 20940 }, { "epoch": 4.34, "learning_rate": 0.0009819673695258086, "loss": 1.8219, "step": 20945 }, { "epoch": 4.34, "learning_rate": 0.000981871958782559, "loss": 1.8214, "step": 20950 }, { "epoch": 4.34, "learning_rate": 0.0009817765480393092, "loss": 1.8191, "step": 20955 }, { "epoch": 4.34, "learning_rate": 0.0009816811372960596, "loss": 1.8174, "step": 20960 }, { "epoch": 4.34, "learning_rate": 0.0009815857265528098, "loss": 1.821, "step": 20965 }, { "epoch": 4.34, "learning_rate": 0.0009814903158095602, "loss": 1.8239, "step": 20970 }, { "epoch": 4.35, "learning_rate": 0.0009813949050663105, "loss": 1.8228, "step": 20975 }, { "epoch": 4.35, "learning_rate": 0.0009812994943230607, "loss": 1.818, "step": 20980 }, { "epoch": 4.35, "learning_rate": 0.000981204083579811, "loss": 1.8187, "step": 20985 }, { "epoch": 4.35, "learning_rate": 0.0009811086728365615, "loss": 1.8203, "step": 20990 }, { "epoch": 4.35, "learning_rate": 0.0009810132620933117, "loss": 1.8242, "step": 20995 }, { "epoch": 4.35, "learning_rate": 0.000980917851350062, "loss": 1.8223, "step": 21000 }, { "epoch": 4.35, "eval_accuracy": 0.530718954248366, "eval_loss": 1.9935251474380493, "eval_runtime": 0.6484, "eval_samples_per_second": 231.329, "eval_steps_per_second": 1.542, "step": 21000 }, { "epoch": 4.35, "learning_rate": 0.0009808224406068124, "loss": 1.8222, "step": 21005 }, { "epoch": 4.35, "learning_rate": 0.0009807270298635626, "loss": 1.8185, "step": 21010 }, { "epoch": 4.35, "learning_rate": 0.000980631619120313, "loss": 1.8235, "step": 21015 }, { "epoch": 4.35, "learning_rate": 0.0009805362083770632, "loss": 1.8222, "step": 21020 }, { "epoch": 4.36, "learning_rate": 0.0009804407976338136, "loss": 1.8172, "step": 21025 }, { "epoch": 4.36, "learning_rate": 0.000980345386890564, "loss": 1.8207, "step": 21030 }, { "epoch": 4.36, "learning_rate": 0.0009802499761473143, "loss": 1.8203, "step": 21035 }, { "epoch": 4.36, "learning_rate": 0.0009801545654040645, "loss": 1.8227, "step": 21040 }, { "epoch": 4.36, "learning_rate": 0.000980059154660815, "loss": 1.8229, "step": 21045 }, { "epoch": 4.36, "learning_rate": 0.000979963743917565, "loss": 1.817, "step": 21050 }, { "epoch": 4.36, "learning_rate": 0.0009798683331743155, "loss": 1.8248, "step": 21055 }, { "epoch": 4.36, "learning_rate": 0.0009797729224310658, "loss": 1.8226, "step": 21060 }, { "epoch": 4.36, "learning_rate": 0.000979677511687816, "loss": 1.8188, "step": 21065 }, { "epoch": 4.37, "learning_rate": 0.0009795821009445664, "loss": 1.8171, "step": 21070 }, { "epoch": 4.37, "learning_rate": 0.0009794866902013166, "loss": 1.8232, "step": 21075 }, { "epoch": 4.37, "learning_rate": 0.000979391279458067, "loss": 1.8202, "step": 21080 }, { "epoch": 4.37, "learning_rate": 0.0009792958687148173, "loss": 1.8193, "step": 21085 }, { "epoch": 4.37, "learning_rate": 0.0009792004579715677, "loss": 1.8178, "step": 21090 }, { "epoch": 4.37, "learning_rate": 0.000979105047228318, "loss": 1.8181, "step": 21095 }, { "epoch": 4.37, "learning_rate": 0.0009790096364850683, "loss": 1.8143, "step": 21100 }, { "epoch": 4.37, "learning_rate": 0.0009789142257418185, "loss": 1.8193, "step": 21105 }, { "epoch": 4.37, "learning_rate": 0.0009788188149985689, "loss": 1.8209, "step": 21110 }, { "epoch": 4.37, "learning_rate": 0.0009787234042553192, "loss": 1.8251, "step": 21115 }, { "epoch": 4.38, "learning_rate": 0.0009786279935120694, "loss": 1.8175, "step": 21120 }, { "epoch": 4.38, "learning_rate": 0.0009785325827688198, "loss": 1.8238, "step": 21125 }, { "epoch": 4.38, "learning_rate": 0.0009784371720255702, "loss": 1.8204, "step": 21130 }, { "epoch": 4.38, "learning_rate": 0.0009783417612823204, "loss": 1.8196, "step": 21135 }, { "epoch": 4.38, "learning_rate": 0.0009782463505390708, "loss": 1.8199, "step": 21140 }, { "epoch": 4.38, "learning_rate": 0.0009781509397958211, "loss": 1.8251, "step": 21145 }, { "epoch": 4.38, "learning_rate": 0.0009780555290525713, "loss": 1.8222, "step": 21150 }, { "epoch": 4.38, "learning_rate": 0.0009779601183093217, "loss": 1.8224, "step": 21155 }, { "epoch": 4.38, "learning_rate": 0.0009778647075660719, "loss": 1.8137, "step": 21160 }, { "epoch": 4.38, "learning_rate": 0.0009777692968228223, "loss": 1.8215, "step": 21165 }, { "epoch": 4.39, "learning_rate": 0.0009776738860795724, "loss": 1.8192, "step": 21170 }, { "epoch": 4.39, "learning_rate": 0.000977578475336323, "loss": 1.8201, "step": 21175 }, { "epoch": 4.39, "learning_rate": 0.0009774830645930732, "loss": 1.8154, "step": 21180 }, { "epoch": 4.39, "learning_rate": 0.0009773876538498236, "loss": 1.8237, "step": 21185 }, { "epoch": 4.39, "learning_rate": 0.0009772922431065738, "loss": 1.819, "step": 21190 }, { "epoch": 4.39, "learning_rate": 0.0009771968323633242, "loss": 1.8134, "step": 21195 }, { "epoch": 4.39, "learning_rate": 0.0009771014216200743, "loss": 1.819, "step": 21200 }, { "epoch": 4.39, "learning_rate": 0.0009770060108768247, "loss": 1.822, "step": 21205 }, { "epoch": 4.39, "learning_rate": 0.000976910600133575, "loss": 1.8235, "step": 21210 }, { "epoch": 4.4, "learning_rate": 0.0009768151893903253, "loss": 1.8164, "step": 21215 }, { "epoch": 4.4, "learning_rate": 0.0009767197786470757, "loss": 1.8236, "step": 21220 }, { "epoch": 4.4, "learning_rate": 0.000976624367903826, "loss": 1.8195, "step": 21225 }, { "epoch": 4.4, "learning_rate": 0.0009765289571605763, "loss": 1.8223, "step": 21230 }, { "epoch": 4.4, "learning_rate": 0.0009764335464173266, "loss": 1.8142, "step": 21235 }, { "epoch": 4.4, "learning_rate": 0.0009763381356740769, "loss": 1.8158, "step": 21240 }, { "epoch": 4.4, "learning_rate": 0.0009762427249308272, "loss": 1.8173, "step": 21245 }, { "epoch": 4.4, "learning_rate": 0.0009761473141875776, "loss": 1.8136, "step": 21250 }, { "epoch": 4.4, "learning_rate": 0.0009760519034443278, "loss": 1.817, "step": 21255 }, { "epoch": 4.4, "learning_rate": 0.0009759564927010781, "loss": 1.819, "step": 21260 }, { "epoch": 4.41, "learning_rate": 0.0009758610819578285, "loss": 1.8202, "step": 21265 }, { "epoch": 4.41, "learning_rate": 0.0009757656712145788, "loss": 1.815, "step": 21270 }, { "epoch": 4.41, "learning_rate": 0.0009756702604713292, "loss": 1.8137, "step": 21275 }, { "epoch": 4.41, "learning_rate": 0.0009755748497280795, "loss": 1.8185, "step": 21280 }, { "epoch": 4.41, "learning_rate": 0.0009754794389848297, "loss": 1.8174, "step": 21285 }, { "epoch": 4.41, "learning_rate": 0.00097538402824158, "loss": 1.8233, "step": 21290 }, { "epoch": 4.41, "learning_rate": 0.0009752886174983303, "loss": 1.8217, "step": 21295 }, { "epoch": 4.41, "learning_rate": 0.0009751932067550806, "loss": 1.8202, "step": 21300 }, { "epoch": 4.41, "learning_rate": 0.000975097796011831, "loss": 1.8232, "step": 21305 }, { "epoch": 4.41, "learning_rate": 0.0009750023852685813, "loss": 1.8154, "step": 21310 }, { "epoch": 4.42, "learning_rate": 0.0009749069745253316, "loss": 1.8174, "step": 21315 }, { "epoch": 4.42, "learning_rate": 0.0009748115637820819, "loss": 1.813, "step": 21320 }, { "epoch": 4.42, "learning_rate": 0.0009747161530388322, "loss": 1.8204, "step": 21325 }, { "epoch": 4.42, "learning_rate": 0.0009746207422955825, "loss": 1.814, "step": 21330 }, { "epoch": 4.42, "learning_rate": 0.0009745253315523329, "loss": 1.8198, "step": 21335 }, { "epoch": 4.42, "learning_rate": 0.0009744299208090831, "loss": 1.8191, "step": 21340 }, { "epoch": 4.42, "learning_rate": 0.0009743345100658334, "loss": 1.8224, "step": 21345 }, { "epoch": 4.42, "learning_rate": 0.0009742390993225837, "loss": 1.8218, "step": 21350 }, { "epoch": 4.42, "learning_rate": 0.0009741436885793341, "loss": 1.8215, "step": 21355 }, { "epoch": 4.43, "learning_rate": 0.0009740482778360844, "loss": 1.8167, "step": 21360 }, { "epoch": 4.43, "learning_rate": 0.0009739528670928348, "loss": 1.8181, "step": 21365 }, { "epoch": 4.43, "learning_rate": 0.000973857456349585, "loss": 1.816, "step": 21370 }, { "epoch": 4.43, "learning_rate": 0.0009737620456063353, "loss": 1.8221, "step": 21375 }, { "epoch": 4.43, "learning_rate": 0.0009736666348630856, "loss": 1.8171, "step": 21380 }, { "epoch": 4.43, "learning_rate": 0.0009735712241198359, "loss": 1.8173, "step": 21385 }, { "epoch": 4.43, "learning_rate": 0.0009734758133765861, "loss": 1.8147, "step": 21390 }, { "epoch": 4.43, "learning_rate": 0.0009733804026333365, "loss": 1.8174, "step": 21395 }, { "epoch": 4.43, "learning_rate": 0.0009732849918900868, "loss": 1.8137, "step": 21400 }, { "epoch": 4.43, "learning_rate": 0.0009731895811468372, "loss": 1.8172, "step": 21405 }, { "epoch": 4.44, "learning_rate": 0.0009730941704035875, "loss": 1.8197, "step": 21410 }, { "epoch": 4.44, "learning_rate": 0.0009729987596603378, "loss": 1.8195, "step": 21415 }, { "epoch": 4.44, "learning_rate": 0.000972903348917088, "loss": 1.8162, "step": 21420 }, { "epoch": 4.44, "learning_rate": 0.0009728079381738384, "loss": 1.8179, "step": 21425 }, { "epoch": 4.44, "learning_rate": 0.0009727125274305887, "loss": 1.8217, "step": 21430 }, { "epoch": 4.44, "learning_rate": 0.000972617116687339, "loss": 1.8247, "step": 21435 }, { "epoch": 4.44, "learning_rate": 0.0009725217059440893, "loss": 1.8187, "step": 21440 }, { "epoch": 4.44, "learning_rate": 0.0009724262952008396, "loss": 1.816, "step": 21445 }, { "epoch": 4.44, "learning_rate": 0.0009723308844575899, "loss": 1.8193, "step": 21450 }, { "epoch": 4.44, "learning_rate": 0.0009722354737143403, "loss": 1.8178, "step": 21455 }, { "epoch": 4.45, "learning_rate": 0.0009721400629710906, "loss": 1.817, "step": 21460 }, { "epoch": 4.45, "learning_rate": 0.0009720446522278409, "loss": 1.8188, "step": 21465 }, { "epoch": 4.45, "learning_rate": 0.0009719492414845912, "loss": 1.8205, "step": 21470 }, { "epoch": 4.45, "learning_rate": 0.0009718538307413414, "loss": 1.8166, "step": 21475 }, { "epoch": 4.45, "learning_rate": 0.0009717584199980917, "loss": 1.8175, "step": 21480 }, { "epoch": 4.45, "learning_rate": 0.0009716630092548421, "loss": 1.8132, "step": 21485 }, { "epoch": 4.45, "learning_rate": 0.0009715675985115924, "loss": 1.8149, "step": 21490 }, { "epoch": 4.45, "learning_rate": 0.0009714721877683428, "loss": 1.8128, "step": 21495 }, { "epoch": 4.45, "learning_rate": 0.0009713767770250931, "loss": 1.8143, "step": 21500 }, { "epoch": 4.46, "learning_rate": 0.0009712813662818433, "loss": 1.8162, "step": 21505 }, { "epoch": 4.46, "learning_rate": 0.0009711859555385937, "loss": 1.8117, "step": 21510 }, { "epoch": 4.46, "learning_rate": 0.000971090544795344, "loss": 1.8183, "step": 21515 }, { "epoch": 4.46, "learning_rate": 0.0009709951340520943, "loss": 1.8212, "step": 21520 }, { "epoch": 4.46, "learning_rate": 0.0009708997233088446, "loss": 1.817, "step": 21525 }, { "epoch": 4.46, "learning_rate": 0.0009708043125655949, "loss": 1.8147, "step": 21530 }, { "epoch": 4.46, "learning_rate": 0.0009707089018223451, "loss": 1.8157, "step": 21535 }, { "epoch": 4.46, "learning_rate": 0.0009706134910790956, "loss": 1.8184, "step": 21540 }, { "epoch": 4.46, "learning_rate": 0.0009705180803358459, "loss": 1.8218, "step": 21545 }, { "epoch": 4.46, "learning_rate": 0.0009704226695925962, "loss": 1.8163, "step": 21550 }, { "epoch": 4.47, "learning_rate": 0.0009703272588493465, "loss": 1.8239, "step": 21555 }, { "epoch": 4.47, "learning_rate": 0.0009702318481060967, "loss": 1.8282, "step": 21560 }, { "epoch": 4.47, "learning_rate": 0.000970136437362847, "loss": 1.8211, "step": 21565 }, { "epoch": 4.47, "learning_rate": 0.0009700410266195974, "loss": 1.8211, "step": 21570 }, { "epoch": 4.47, "learning_rate": 0.0009699456158763477, "loss": 1.8132, "step": 21575 }, { "epoch": 4.47, "learning_rate": 0.000969850205133098, "loss": 1.8186, "step": 21580 }, { "epoch": 4.47, "learning_rate": 0.0009697547943898484, "loss": 1.8145, "step": 21585 }, { "epoch": 4.47, "learning_rate": 0.0009696593836465986, "loss": 1.8145, "step": 21590 }, { "epoch": 4.47, "learning_rate": 0.0009695639729033489, "loss": 1.8154, "step": 21595 }, { "epoch": 4.47, "learning_rate": 0.0009694685621600993, "loss": 1.8137, "step": 21600 }, { "epoch": 4.48, "learning_rate": 0.0009693731514168496, "loss": 1.813, "step": 21605 }, { "epoch": 4.48, "learning_rate": 0.0009692777406735999, "loss": 1.8159, "step": 21610 }, { "epoch": 4.48, "learning_rate": 0.0009691823299303501, "loss": 1.8147, "step": 21615 }, { "epoch": 4.48, "learning_rate": 0.0009690869191871004, "loss": 1.8154, "step": 21620 }, { "epoch": 4.48, "learning_rate": 0.0009689915084438507, "loss": 1.8195, "step": 21625 }, { "epoch": 4.48, "learning_rate": 0.0009688960977006011, "loss": 1.8188, "step": 21630 }, { "epoch": 4.48, "learning_rate": 0.0009688006869573515, "loss": 1.8131, "step": 21635 }, { "epoch": 4.48, "learning_rate": 0.0009687052762141018, "loss": 1.8108, "step": 21640 }, { "epoch": 4.48, "learning_rate": 0.000968609865470852, "loss": 1.8199, "step": 21645 }, { "epoch": 4.49, "learning_rate": 0.0009685144547276023, "loss": 1.821, "step": 21650 }, { "epoch": 4.49, "learning_rate": 0.0009684190439843526, "loss": 1.8178, "step": 21655 }, { "epoch": 4.49, "learning_rate": 0.000968323633241103, "loss": 1.8214, "step": 21660 }, { "epoch": 4.49, "learning_rate": 0.0009682282224978533, "loss": 1.8111, "step": 21665 }, { "epoch": 4.49, "learning_rate": 0.0009681328117546036, "loss": 1.8117, "step": 21670 }, { "epoch": 4.49, "learning_rate": 0.0009680374010113538, "loss": 1.818, "step": 21675 }, { "epoch": 4.49, "learning_rate": 0.0009679419902681042, "loss": 1.819, "step": 21680 }, { "epoch": 4.49, "learning_rate": 0.0009678465795248545, "loss": 1.8179, "step": 21685 }, { "epoch": 4.49, "learning_rate": 0.0009677511687816049, "loss": 1.8217, "step": 21690 }, { "epoch": 4.49, "learning_rate": 0.0009676557580383552, "loss": 1.8159, "step": 21695 }, { "epoch": 4.5, "learning_rate": 0.0009675603472951054, "loss": 1.8171, "step": 21700 }, { "epoch": 4.5, "learning_rate": 0.0009674649365518557, "loss": 1.818, "step": 21705 }, { "epoch": 4.5, "learning_rate": 0.000967369525808606, "loss": 1.8131, "step": 21710 }, { "epoch": 4.5, "learning_rate": 0.0009672741150653564, "loss": 1.8114, "step": 21715 }, { "epoch": 4.5, "learning_rate": 0.0009671787043221067, "loss": 1.8131, "step": 21720 }, { "epoch": 4.5, "learning_rate": 0.0009670832935788571, "loss": 1.8205, "step": 21725 }, { "epoch": 4.5, "learning_rate": 0.0009669878828356073, "loss": 1.8185, "step": 21730 }, { "epoch": 4.5, "learning_rate": 0.0009668924720923576, "loss": 1.8177, "step": 21735 }, { "epoch": 4.5, "learning_rate": 0.0009667970613491079, "loss": 1.8154, "step": 21740 }, { "epoch": 4.5, "learning_rate": 0.0009667016506058583, "loss": 1.8114, "step": 21745 }, { "epoch": 4.51, "learning_rate": 0.0009666062398626086, "loss": 1.8106, "step": 21750 }, { "epoch": 4.51, "learning_rate": 0.0009665108291193589, "loss": 1.8142, "step": 21755 }, { "epoch": 4.51, "learning_rate": 0.0009664154183761091, "loss": 1.815, "step": 21760 }, { "epoch": 4.51, "learning_rate": 0.0009663200076328594, "loss": 1.8202, "step": 21765 }, { "epoch": 4.51, "learning_rate": 0.0009662245968896098, "loss": 1.8159, "step": 21770 }, { "epoch": 4.51, "learning_rate": 0.0009661291861463602, "loss": 1.8207, "step": 21775 }, { "epoch": 4.51, "learning_rate": 0.0009660337754031105, "loss": 1.8162, "step": 21780 }, { "epoch": 4.51, "learning_rate": 0.0009659383646598607, "loss": 1.8162, "step": 21785 }, { "epoch": 4.51, "learning_rate": 0.000965842953916611, "loss": 1.812, "step": 21790 }, { "epoch": 4.52, "learning_rate": 0.0009657475431733613, "loss": 1.8131, "step": 21795 }, { "epoch": 4.52, "learning_rate": 0.0009656521324301116, "loss": 1.8171, "step": 21800 }, { "epoch": 4.52, "learning_rate": 0.000965556721686862, "loss": 1.8166, "step": 21805 }, { "epoch": 4.52, "learning_rate": 0.0009654613109436123, "loss": 1.8172, "step": 21810 }, { "epoch": 4.52, "learning_rate": 0.0009653659002003626, "loss": 1.8157, "step": 21815 }, { "epoch": 4.52, "learning_rate": 0.0009652704894571129, "loss": 1.817, "step": 21820 }, { "epoch": 4.52, "learning_rate": 0.0009651750787138632, "loss": 1.8168, "step": 21825 }, { "epoch": 4.52, "learning_rate": 0.0009650796679706135, "loss": 1.8158, "step": 21830 }, { "epoch": 4.52, "learning_rate": 0.0009649842572273639, "loss": 1.8131, "step": 21835 }, { "epoch": 4.52, "learning_rate": 0.0009648888464841141, "loss": 1.8158, "step": 21840 }, { "epoch": 4.53, "learning_rate": 0.0009647934357408644, "loss": 1.8154, "step": 21845 }, { "epoch": 4.53, "learning_rate": 0.0009646980249976147, "loss": 1.8147, "step": 21850 }, { "epoch": 4.53, "learning_rate": 0.000964602614254365, "loss": 1.8163, "step": 21855 }, { "epoch": 4.53, "learning_rate": 0.0009645072035111153, "loss": 1.8139, "step": 21860 }, { "epoch": 4.53, "learning_rate": 0.0009644117927678658, "loss": 1.8163, "step": 21865 }, { "epoch": 4.53, "learning_rate": 0.000964316382024616, "loss": 1.8162, "step": 21870 }, { "epoch": 4.53, "learning_rate": 0.0009642209712813663, "loss": 1.8138, "step": 21875 }, { "epoch": 4.53, "learning_rate": 0.0009641255605381166, "loss": 1.8139, "step": 21880 }, { "epoch": 4.53, "learning_rate": 0.0009640301497948669, "loss": 1.8148, "step": 21885 }, { "epoch": 4.53, "learning_rate": 0.0009639347390516172, "loss": 1.8117, "step": 21890 }, { "epoch": 4.54, "learning_rate": 0.0009638393283083676, "loss": 1.8157, "step": 21895 }, { "epoch": 4.54, "learning_rate": 0.0009637439175651178, "loss": 1.8171, "step": 21900 }, { "epoch": 4.54, "learning_rate": 0.0009636485068218681, "loss": 1.8163, "step": 21905 }, { "epoch": 4.54, "learning_rate": 0.0009635530960786185, "loss": 1.8167, "step": 21910 }, { "epoch": 4.54, "learning_rate": 0.0009634576853353688, "loss": 1.8191, "step": 21915 }, { "epoch": 4.54, "learning_rate": 0.0009633622745921192, "loss": 1.8173, "step": 21920 }, { "epoch": 4.54, "learning_rate": 0.0009632668638488694, "loss": 1.8201, "step": 21925 }, { "epoch": 4.54, "learning_rate": 0.0009631714531056197, "loss": 1.8155, "step": 21930 }, { "epoch": 4.54, "learning_rate": 0.00096307604236237, "loss": 1.809, "step": 21935 }, { "epoch": 4.55, "learning_rate": 0.0009629806316191203, "loss": 1.8148, "step": 21940 }, { "epoch": 4.55, "learning_rate": 0.0009628852208758706, "loss": 1.8126, "step": 21945 }, { "epoch": 4.55, "learning_rate": 0.000962789810132621, "loss": 1.8142, "step": 21950 }, { "epoch": 4.55, "learning_rate": 0.0009626943993893713, "loss": 1.8169, "step": 21955 }, { "epoch": 4.55, "learning_rate": 0.0009625989886461216, "loss": 1.8173, "step": 21960 }, { "epoch": 4.55, "learning_rate": 0.0009625035779028719, "loss": 1.8151, "step": 21965 }, { "epoch": 4.55, "learning_rate": 0.0009624081671596222, "loss": 1.8101, "step": 21970 }, { "epoch": 4.55, "learning_rate": 0.0009623127564163725, "loss": 1.8155, "step": 21975 }, { "epoch": 4.55, "learning_rate": 0.0009622173456731228, "loss": 1.8158, "step": 21980 }, { "epoch": 4.55, "learning_rate": 0.0009621219349298731, "loss": 1.8098, "step": 21985 }, { "epoch": 4.56, "learning_rate": 0.0009620265241866234, "loss": 1.8196, "step": 21990 }, { "epoch": 4.56, "learning_rate": 0.0009619311134433737, "loss": 1.8138, "step": 21995 }, { "epoch": 4.56, "learning_rate": 0.0009618357027001241, "loss": 1.8122, "step": 22000 }, { "epoch": 4.56, "learning_rate": 0.0009617402919568744, "loss": 1.8142, "step": 22005 }, { "epoch": 4.56, "learning_rate": 0.0009616448812136247, "loss": 1.8117, "step": 22010 }, { "epoch": 4.56, "learning_rate": 0.000961549470470375, "loss": 1.8152, "step": 22015 }, { "epoch": 4.56, "learning_rate": 0.0009614540597271253, "loss": 1.8155, "step": 22020 }, { "epoch": 4.56, "learning_rate": 0.0009613586489838756, "loss": 1.8111, "step": 22025 }, { "epoch": 4.56, "learning_rate": 0.0009612632382406259, "loss": 1.8141, "step": 22030 }, { "epoch": 4.56, "learning_rate": 0.0009611678274973761, "loss": 1.8115, "step": 22035 }, { "epoch": 4.57, "learning_rate": 0.0009610724167541265, "loss": 1.8106, "step": 22040 }, { "epoch": 4.57, "learning_rate": 0.0009609770060108769, "loss": 1.813, "step": 22045 }, { "epoch": 4.57, "learning_rate": 0.0009608815952676272, "loss": 1.8079, "step": 22050 }, { "epoch": 4.57, "learning_rate": 0.0009607861845243775, "loss": 1.814, "step": 22055 }, { "epoch": 4.57, "learning_rate": 0.0009606907737811278, "loss": 1.8129, "step": 22060 }, { "epoch": 4.57, "learning_rate": 0.000960595363037878, "loss": 1.8118, "step": 22065 }, { "epoch": 4.57, "learning_rate": 0.0009604999522946284, "loss": 1.8199, "step": 22070 }, { "epoch": 4.57, "learning_rate": 0.0009604045415513787, "loss": 1.8186, "step": 22075 }, { "epoch": 4.57, "learning_rate": 0.000960309130808129, "loss": 1.8112, "step": 22080 }, { "epoch": 4.58, "learning_rate": 0.0009602137200648793, "loss": 1.8087, "step": 22085 }, { "epoch": 4.58, "learning_rate": 0.0009601183093216297, "loss": 1.8152, "step": 22090 }, { "epoch": 4.58, "learning_rate": 0.0009600228985783799, "loss": 1.8038, "step": 22095 }, { "epoch": 4.58, "learning_rate": 0.0009599274878351303, "loss": 1.8127, "step": 22100 }, { "epoch": 4.58, "learning_rate": 0.0009598320770918806, "loss": 1.813, "step": 22105 }, { "epoch": 4.58, "learning_rate": 0.0009597366663486309, "loss": 1.821, "step": 22110 }, { "epoch": 4.58, "learning_rate": 0.0009596412556053812, "loss": 1.8113, "step": 22115 }, { "epoch": 4.58, "learning_rate": 0.0009595458448621314, "loss": 1.8144, "step": 22120 }, { "epoch": 4.58, "learning_rate": 0.0009594504341188817, "loss": 1.8149, "step": 22125 }, { "epoch": 4.58, "learning_rate": 0.0009593550233756321, "loss": 1.8153, "step": 22130 }, { "epoch": 4.59, "learning_rate": 0.0009592596126323824, "loss": 1.8053, "step": 22135 }, { "epoch": 4.59, "learning_rate": 0.0009591642018891328, "loss": 1.8181, "step": 22140 }, { "epoch": 4.59, "learning_rate": 0.0009590687911458831, "loss": 1.8133, "step": 22145 }, { "epoch": 4.59, "learning_rate": 0.0009589733804026333, "loss": 1.8128, "step": 22150 }, { "epoch": 4.59, "learning_rate": 0.0009588779696593837, "loss": 1.806, "step": 22155 }, { "epoch": 4.59, "learning_rate": 0.000958782558916134, "loss": 1.8094, "step": 22160 }, { "epoch": 4.59, "learning_rate": 0.0009586871481728843, "loss": 1.8111, "step": 22165 }, { "epoch": 4.59, "learning_rate": 0.0009585917374296346, "loss": 1.8124, "step": 22170 }, { "epoch": 4.59, "learning_rate": 0.0009584963266863848, "loss": 1.8121, "step": 22175 }, { "epoch": 4.59, "learning_rate": 0.0009584009159431351, "loss": 1.8035, "step": 22180 }, { "epoch": 4.6, "learning_rate": 0.0009583055051998856, "loss": 1.8082, "step": 22185 }, { "epoch": 4.6, "learning_rate": 0.0009582100944566359, "loss": 1.8149, "step": 22190 }, { "epoch": 4.6, "learning_rate": 0.0009581146837133862, "loss": 1.8164, "step": 22195 }, { "epoch": 4.6, "learning_rate": 0.0009580192729701365, "loss": 1.8155, "step": 22200 }, { "epoch": 4.6, "learning_rate": 0.0009579238622268867, "loss": 1.8147, "step": 22205 }, { "epoch": 4.6, "learning_rate": 0.000957828451483637, "loss": 1.8124, "step": 22210 }, { "epoch": 4.6, "learning_rate": 0.0009577330407403874, "loss": 1.8087, "step": 22215 }, { "epoch": 4.6, "learning_rate": 0.0009576376299971377, "loss": 1.8104, "step": 22220 }, { "epoch": 4.6, "learning_rate": 0.000957542219253888, "loss": 1.8186, "step": 22225 }, { "epoch": 4.61, "learning_rate": 0.0009574468085106384, "loss": 1.8099, "step": 22230 }, { "epoch": 4.61, "learning_rate": 0.0009573513977673886, "loss": 1.8129, "step": 22235 }, { "epoch": 4.61, "learning_rate": 0.0009572559870241389, "loss": 1.8096, "step": 22240 }, { "epoch": 4.61, "learning_rate": 0.0009571605762808893, "loss": 1.815, "step": 22245 }, { "epoch": 4.61, "learning_rate": 0.0009570651655376396, "loss": 1.8079, "step": 22250 }, { "epoch": 4.61, "learning_rate": 0.0009569697547943899, "loss": 1.8158, "step": 22255 }, { "epoch": 4.61, "learning_rate": 0.0009568743440511401, "loss": 1.8152, "step": 22260 }, { "epoch": 4.61, "learning_rate": 0.0009567789333078904, "loss": 1.8153, "step": 22265 }, { "epoch": 4.61, "learning_rate": 0.0009566835225646407, "loss": 1.818, "step": 22270 }, { "epoch": 4.61, "learning_rate": 0.0009565881118213912, "loss": 1.8117, "step": 22275 }, { "epoch": 4.62, "learning_rate": 0.0009564927010781415, "loss": 1.8109, "step": 22280 }, { "epoch": 4.62, "learning_rate": 0.0009563972903348918, "loss": 1.8122, "step": 22285 }, { "epoch": 4.62, "learning_rate": 0.000956301879591642, "loss": 1.816, "step": 22290 }, { "epoch": 4.62, "learning_rate": 0.0009562064688483923, "loss": 1.8107, "step": 22295 }, { "epoch": 4.62, "learning_rate": 0.0009561110581051426, "loss": 1.8098, "step": 22300 }, { "epoch": 4.62, "learning_rate": 0.000956015647361893, "loss": 1.8106, "step": 22305 }, { "epoch": 4.62, "learning_rate": 0.0009559202366186433, "loss": 1.8135, "step": 22310 }, { "epoch": 4.62, "learning_rate": 0.0009558248258753935, "loss": 1.8097, "step": 22315 }, { "epoch": 4.62, "learning_rate": 0.0009557294151321439, "loss": 1.8176, "step": 22320 }, { "epoch": 4.63, "learning_rate": 0.0009556340043888942, "loss": 1.8182, "step": 22325 }, { "epoch": 4.63, "learning_rate": 0.0009555385936456446, "loss": 1.8157, "step": 22330 }, { "epoch": 4.63, "learning_rate": 0.0009554431829023949, "loss": 1.8149, "step": 22335 }, { "epoch": 4.63, "learning_rate": 0.0009553477721591452, "loss": 1.8088, "step": 22340 }, { "epoch": 4.63, "learning_rate": 0.0009552523614158954, "loss": 1.8108, "step": 22345 }, { "epoch": 4.63, "learning_rate": 0.0009551569506726457, "loss": 1.8161, "step": 22350 }, { "epoch": 4.63, "learning_rate": 0.000955061539929396, "loss": 1.8132, "step": 22355 }, { "epoch": 4.63, "learning_rate": 0.0009549661291861464, "loss": 1.8109, "step": 22360 }, { "epoch": 4.63, "learning_rate": 0.0009548707184428967, "loss": 1.8117, "step": 22365 }, { "epoch": 4.63, "learning_rate": 0.0009547753076996471, "loss": 1.8152, "step": 22370 }, { "epoch": 4.64, "learning_rate": 0.0009546798969563973, "loss": 1.8164, "step": 22375 }, { "epoch": 4.64, "learning_rate": 0.0009545844862131476, "loss": 1.8113, "step": 22380 }, { "epoch": 4.64, "learning_rate": 0.0009544890754698979, "loss": 1.8177, "step": 22385 }, { "epoch": 4.64, "learning_rate": 0.0009543936647266483, "loss": 1.8203, "step": 22390 }, { "epoch": 4.64, "learning_rate": 0.0009542982539833986, "loss": 1.8169, "step": 22395 }, { "epoch": 4.64, "learning_rate": 0.0009542028432401488, "loss": 1.8154, "step": 22400 }, { "epoch": 4.64, "learning_rate": 0.0009541074324968991, "loss": 1.8129, "step": 22405 }, { "epoch": 4.64, "learning_rate": 0.0009540120217536494, "loss": 1.8137, "step": 22410 }, { "epoch": 4.64, "learning_rate": 0.0009539166110103998, "loss": 1.8083, "step": 22415 }, { "epoch": 4.64, "learning_rate": 0.0009538212002671502, "loss": 1.8125, "step": 22420 }, { "epoch": 4.65, "learning_rate": 0.0009537257895239005, "loss": 1.8122, "step": 22425 }, { "epoch": 4.65, "learning_rate": 0.0009536303787806507, "loss": 1.8088, "step": 22430 }, { "epoch": 4.65, "learning_rate": 0.000953534968037401, "loss": 1.8162, "step": 22435 }, { "epoch": 4.65, "learning_rate": 0.0009534395572941513, "loss": 1.8177, "step": 22440 }, { "epoch": 4.65, "learning_rate": 0.0009533441465509016, "loss": 1.8068, "step": 22445 }, { "epoch": 4.65, "learning_rate": 0.000953248735807652, "loss": 1.8141, "step": 22450 }, { "epoch": 4.65, "learning_rate": 0.0009531533250644022, "loss": 1.8102, "step": 22455 }, { "epoch": 4.65, "learning_rate": 0.0009530579143211526, "loss": 1.8123, "step": 22460 }, { "epoch": 4.65, "learning_rate": 0.0009529625035779029, "loss": 1.8161, "step": 22465 }, { "epoch": 4.66, "learning_rate": 0.0009528670928346532, "loss": 1.8134, "step": 22470 }, { "epoch": 4.66, "learning_rate": 0.0009527716820914035, "loss": 1.8061, "step": 22475 }, { "epoch": 4.66, "learning_rate": 0.0009526762713481539, "loss": 1.8109, "step": 22480 }, { "epoch": 4.66, "learning_rate": 0.0009525808606049041, "loss": 1.8052, "step": 22485 }, { "epoch": 4.66, "learning_rate": 0.0009524854498616544, "loss": 1.8147, "step": 22490 }, { "epoch": 4.66, "learning_rate": 0.0009523900391184047, "loss": 1.8138, "step": 22495 }, { "epoch": 4.66, "learning_rate": 0.000952294628375155, "loss": 1.8126, "step": 22500 }, { "epoch": 4.66, "learning_rate": 0.0009521992176319054, "loss": 1.8133, "step": 22505 }, { "epoch": 4.66, "learning_rate": 0.0009521038068886558, "loss": 1.8084, "step": 22510 }, { "epoch": 4.66, "learning_rate": 0.000952008396145406, "loss": 1.8091, "step": 22515 }, { "epoch": 4.67, "learning_rate": 0.0009519129854021563, "loss": 1.8117, "step": 22520 }, { "epoch": 4.67, "learning_rate": 0.0009518175746589066, "loss": 1.8106, "step": 22525 }, { "epoch": 4.67, "learning_rate": 0.0009517221639156569, "loss": 1.8126, "step": 22530 }, { "epoch": 4.67, "learning_rate": 0.0009516267531724072, "loss": 1.8085, "step": 22535 }, { "epoch": 4.67, "learning_rate": 0.0009515313424291575, "loss": 1.8129, "step": 22540 }, { "epoch": 4.67, "learning_rate": 0.0009514359316859078, "loss": 1.8113, "step": 22545 }, { "epoch": 4.67, "learning_rate": 0.0009513405209426582, "loss": 1.8083, "step": 22550 }, { "epoch": 4.67, "learning_rate": 0.0009512451101994085, "loss": 1.809, "step": 22555 }, { "epoch": 4.67, "learning_rate": 0.0009511496994561588, "loss": 1.8097, "step": 22560 }, { "epoch": 4.67, "learning_rate": 0.0009510542887129092, "loss": 1.8089, "step": 22565 }, { "epoch": 4.68, "learning_rate": 0.0009509588779696594, "loss": 1.8042, "step": 22570 }, { "epoch": 4.68, "learning_rate": 0.0009508634672264097, "loss": 1.8132, "step": 22575 }, { "epoch": 4.68, "learning_rate": 0.00095076805648316, "loss": 1.8091, "step": 22580 }, { "epoch": 4.68, "learning_rate": 0.0009506726457399103, "loss": 1.81, "step": 22585 }, { "epoch": 4.68, "learning_rate": 0.0009505772349966606, "loss": 1.8076, "step": 22590 }, { "epoch": 4.68, "learning_rate": 0.0009504818242534111, "loss": 1.8109, "step": 22595 }, { "epoch": 4.68, "learning_rate": 0.0009503864135101613, "loss": 1.8116, "step": 22600 }, { "epoch": 4.68, "learning_rate": 0.0009502910027669116, "loss": 1.8119, "step": 22605 }, { "epoch": 4.68, "learning_rate": 0.0009501955920236619, "loss": 1.8093, "step": 22610 }, { "epoch": 4.69, "learning_rate": 0.0009501001812804122, "loss": 1.8173, "step": 22615 }, { "epoch": 4.69, "learning_rate": 0.0009500047705371625, "loss": 1.8103, "step": 22620 }, { "epoch": 4.69, "learning_rate": 0.0009499093597939128, "loss": 1.8142, "step": 22625 }, { "epoch": 4.69, "learning_rate": 0.0009498139490506631, "loss": 1.8124, "step": 22630 }, { "epoch": 4.69, "learning_rate": 0.0009497185383074134, "loss": 1.809, "step": 22635 }, { "epoch": 4.69, "learning_rate": 0.0009496231275641637, "loss": 1.8097, "step": 22640 }, { "epoch": 4.69, "learning_rate": 0.0009495277168209141, "loss": 1.8113, "step": 22645 }, { "epoch": 4.69, "learning_rate": 0.0009494323060776644, "loss": 1.8159, "step": 22650 }, { "epoch": 4.69, "learning_rate": 0.0009493368953344147, "loss": 1.81, "step": 22655 }, { "epoch": 4.69, "learning_rate": 0.000949241484591165, "loss": 1.813, "step": 22660 }, { "epoch": 4.7, "learning_rate": 0.0009491460738479153, "loss": 1.8105, "step": 22665 }, { "epoch": 4.7, "learning_rate": 0.0009490506631046656, "loss": 1.8098, "step": 22670 }, { "epoch": 4.7, "learning_rate": 0.0009489552523614159, "loss": 1.8101, "step": 22675 }, { "epoch": 4.7, "learning_rate": 0.0009488598416181661, "loss": 1.8132, "step": 22680 }, { "epoch": 4.7, "learning_rate": 0.0009487644308749165, "loss": 1.8156, "step": 22685 }, { "epoch": 4.7, "learning_rate": 0.0009486690201316669, "loss": 1.806, "step": 22690 }, { "epoch": 4.7, "learning_rate": 0.0009485736093884172, "loss": 1.8105, "step": 22695 }, { "epoch": 4.7, "learning_rate": 0.0009484781986451675, "loss": 1.8091, "step": 22700 }, { "epoch": 4.7, "learning_rate": 0.0009483827879019178, "loss": 1.8172, "step": 22705 }, { "epoch": 4.7, "learning_rate": 0.000948287377158668, "loss": 1.8094, "step": 22710 }, { "epoch": 4.71, "learning_rate": 0.0009481919664154184, "loss": 1.8093, "step": 22715 }, { "epoch": 4.71, "learning_rate": 0.0009480965556721687, "loss": 1.8095, "step": 22720 }, { "epoch": 4.71, "learning_rate": 0.000948001144928919, "loss": 1.8081, "step": 22725 }, { "epoch": 4.71, "learning_rate": 0.0009479057341856693, "loss": 1.8072, "step": 22730 }, { "epoch": 4.71, "learning_rate": 0.0009478103234424197, "loss": 1.8008, "step": 22735 }, { "epoch": 4.71, "learning_rate": 0.0009477149126991699, "loss": 1.813, "step": 22740 }, { "epoch": 4.71, "learning_rate": 0.0009476195019559203, "loss": 1.8072, "step": 22745 }, { "epoch": 4.71, "learning_rate": 0.0009475240912126706, "loss": 1.8079, "step": 22750 }, { "epoch": 4.71, "learning_rate": 0.0009474286804694209, "loss": 1.8043, "step": 22755 }, { "epoch": 4.72, "learning_rate": 0.0009473332697261712, "loss": 1.8094, "step": 22760 }, { "epoch": 4.72, "learning_rate": 0.0009472378589829214, "loss": 1.8102, "step": 22765 }, { "epoch": 4.72, "learning_rate": 0.0009471424482396718, "loss": 1.8056, "step": 22770 }, { "epoch": 4.72, "learning_rate": 0.0009470470374964221, "loss": 1.8144, "step": 22775 }, { "epoch": 4.72, "learning_rate": 0.0009469516267531725, "loss": 1.8066, "step": 22780 }, { "epoch": 4.72, "learning_rate": 0.0009468562160099228, "loss": 1.8122, "step": 22785 }, { "epoch": 4.72, "learning_rate": 0.000946760805266673, "loss": 1.816, "step": 22790 }, { "epoch": 4.72, "learning_rate": 0.0009466653945234233, "loss": 1.8101, "step": 22795 }, { "epoch": 4.72, "learning_rate": 0.0009465699837801737, "loss": 1.8109, "step": 22800 }, { "epoch": 4.72, "learning_rate": 0.000946474573036924, "loss": 1.8114, "step": 22805 }, { "epoch": 4.73, "learning_rate": 0.0009463791622936743, "loss": 1.8119, "step": 22810 }, { "epoch": 4.73, "learning_rate": 0.0009462837515504246, "loss": 1.8111, "step": 22815 }, { "epoch": 4.73, "learning_rate": 0.0009461883408071748, "loss": 1.8056, "step": 22820 }, { "epoch": 4.73, "learning_rate": 0.0009460929300639252, "loss": 1.8212, "step": 22825 }, { "epoch": 4.73, "learning_rate": 0.0009459975193206756, "loss": 1.8196, "step": 22830 }, { "epoch": 4.73, "learning_rate": 0.0009459021085774259, "loss": 1.8194, "step": 22835 }, { "epoch": 4.73, "learning_rate": 0.0009458066978341762, "loss": 1.8146, "step": 22840 }, { "epoch": 4.73, "learning_rate": 0.0009457112870909265, "loss": 1.8135, "step": 22845 }, { "epoch": 4.73, "learning_rate": 0.0009456158763476767, "loss": 1.8091, "step": 22850 }, { "epoch": 4.73, "learning_rate": 0.000945520465604427, "loss": 1.8092, "step": 22855 }, { "epoch": 4.74, "learning_rate": 0.0009454250548611774, "loss": 1.8124, "step": 22860 }, { "epoch": 4.74, "learning_rate": 0.0009453296441179277, "loss": 1.8111, "step": 22865 }, { "epoch": 4.74, "learning_rate": 0.000945234233374678, "loss": 1.8097, "step": 22870 }, { "epoch": 4.74, "learning_rate": 0.0009451388226314284, "loss": 1.8096, "step": 22875 }, { "epoch": 4.74, "learning_rate": 0.0009450434118881786, "loss": 1.8082, "step": 22880 }, { "epoch": 4.74, "learning_rate": 0.0009449480011449289, "loss": 1.8165, "step": 22885 }, { "epoch": 4.74, "learning_rate": 0.0009448525904016793, "loss": 1.8055, "step": 22890 }, { "epoch": 4.74, "learning_rate": 0.0009447571796584296, "loss": 1.8066, "step": 22895 }, { "epoch": 4.74, "learning_rate": 0.0009446617689151799, "loss": 1.81, "step": 22900 }, { "epoch": 4.75, "learning_rate": 0.0009445663581719301, "loss": 1.8143, "step": 22905 }, { "epoch": 4.75, "learning_rate": 0.0009444709474286804, "loss": 1.81, "step": 22910 }, { "epoch": 4.75, "learning_rate": 0.0009443755366854307, "loss": 1.8101, "step": 22915 }, { "epoch": 4.75, "learning_rate": 0.0009442801259421812, "loss": 1.8055, "step": 22920 }, { "epoch": 4.75, "learning_rate": 0.0009441847151989315, "loss": 1.8069, "step": 22925 }, { "epoch": 4.75, "learning_rate": 0.0009440893044556818, "loss": 1.81, "step": 22930 }, { "epoch": 4.75, "learning_rate": 0.000943993893712432, "loss": 1.8098, "step": 22935 }, { "epoch": 4.75, "learning_rate": 0.0009438984829691823, "loss": 1.8062, "step": 22940 }, { "epoch": 4.75, "learning_rate": 0.0009438030722259326, "loss": 1.8052, "step": 22945 }, { "epoch": 4.75, "learning_rate": 0.000943707661482683, "loss": 1.8059, "step": 22950 }, { "epoch": 4.76, "learning_rate": 0.0009436122507394333, "loss": 1.8121, "step": 22955 }, { "epoch": 4.76, "learning_rate": 0.0009435168399961835, "loss": 1.8045, "step": 22960 }, { "epoch": 4.76, "learning_rate": 0.0009434214292529339, "loss": 1.81, "step": 22965 }, { "epoch": 4.76, "learning_rate": 0.0009433260185096842, "loss": 1.8079, "step": 22970 }, { "epoch": 4.76, "learning_rate": 0.0009432306077664346, "loss": 1.8089, "step": 22975 }, { "epoch": 4.76, "learning_rate": 0.0009431351970231849, "loss": 1.8076, "step": 22980 }, { "epoch": 4.76, "learning_rate": 0.0009430397862799352, "loss": 1.807, "step": 22985 }, { "epoch": 4.76, "learning_rate": 0.0009429443755366854, "loss": 1.8099, "step": 22990 }, { "epoch": 4.76, "learning_rate": 0.0009428489647934357, "loss": 1.809, "step": 22995 }, { "epoch": 4.76, "learning_rate": 0.000942753554050186, "loss": 1.8097, "step": 23000 }, { "epoch": 4.77, "learning_rate": 0.0009426581433069364, "loss": 1.81, "step": 23005 }, { "epoch": 4.77, "learning_rate": 0.0009425627325636868, "loss": 1.8052, "step": 23010 }, { "epoch": 4.77, "learning_rate": 0.000942467321820437, "loss": 1.804, "step": 23015 }, { "epoch": 4.77, "learning_rate": 0.0009423719110771873, "loss": 1.8051, "step": 23020 }, { "epoch": 4.77, "learning_rate": 0.0009422765003339376, "loss": 1.8077, "step": 23025 }, { "epoch": 4.77, "learning_rate": 0.0009421810895906879, "loss": 1.8087, "step": 23030 }, { "epoch": 4.77, "learning_rate": 0.0009420856788474383, "loss": 1.813, "step": 23035 }, { "epoch": 4.77, "learning_rate": 0.0009419902681041886, "loss": 1.8047, "step": 23040 }, { "epoch": 4.77, "learning_rate": 0.0009418948573609388, "loss": 1.8123, "step": 23045 }, { "epoch": 4.78, "learning_rate": 0.0009417994466176891, "loss": 1.81, "step": 23050 }, { "epoch": 4.78, "learning_rate": 0.0009417040358744395, "loss": 1.8132, "step": 23055 }, { "epoch": 4.78, "learning_rate": 0.0009416086251311898, "loss": 1.8075, "step": 23060 }, { "epoch": 4.78, "learning_rate": 0.0009415132143879402, "loss": 1.8049, "step": 23065 }, { "epoch": 4.78, "learning_rate": 0.0009414178036446905, "loss": 1.8123, "step": 23070 }, { "epoch": 4.78, "learning_rate": 0.0009413223929014407, "loss": 1.8121, "step": 23075 }, { "epoch": 4.78, "learning_rate": 0.000941226982158191, "loss": 1.8104, "step": 23080 }, { "epoch": 4.78, "learning_rate": 0.0009411315714149413, "loss": 1.8146, "step": 23085 }, { "epoch": 4.78, "learning_rate": 0.0009410361606716916, "loss": 1.8146, "step": 23090 }, { "epoch": 4.78, "learning_rate": 0.000940940749928442, "loss": 1.8038, "step": 23095 }, { "epoch": 4.79, "learning_rate": 0.0009408453391851922, "loss": 1.8116, "step": 23100 }, { "epoch": 4.79, "learning_rate": 0.0009407499284419426, "loss": 1.8078, "step": 23105 }, { "epoch": 4.79, "learning_rate": 0.0009406545176986929, "loss": 1.8115, "step": 23110 }, { "epoch": 4.79, "learning_rate": 0.0009405591069554432, "loss": 1.8084, "step": 23115 }, { "epoch": 4.79, "learning_rate": 0.0009404636962121935, "loss": 1.8056, "step": 23120 }, { "epoch": 4.79, "learning_rate": 0.0009403682854689439, "loss": 1.8117, "step": 23125 }, { "epoch": 4.79, "learning_rate": 0.0009402728747256941, "loss": 1.8098, "step": 23130 }, { "epoch": 4.79, "learning_rate": 0.0009401774639824444, "loss": 1.812, "step": 23135 }, { "epoch": 4.79, "learning_rate": 0.0009400820532391947, "loss": 1.8089, "step": 23140 }, { "epoch": 4.79, "learning_rate": 0.000939986642495945, "loss": 1.8058, "step": 23145 }, { "epoch": 4.8, "learning_rate": 0.0009398912317526954, "loss": 1.811, "step": 23150 }, { "epoch": 4.8, "learning_rate": 0.0009397958210094458, "loss": 1.8078, "step": 23155 }, { "epoch": 4.8, "learning_rate": 0.000939700410266196, "loss": 1.8088, "step": 23160 }, { "epoch": 4.8, "learning_rate": 0.0009396049995229463, "loss": 1.8025, "step": 23165 }, { "epoch": 4.8, "learning_rate": 0.0009395095887796966, "loss": 1.8081, "step": 23170 }, { "epoch": 4.8, "learning_rate": 0.0009394141780364469, "loss": 1.8082, "step": 23175 }, { "epoch": 4.8, "learning_rate": 0.0009393187672931972, "loss": 1.8079, "step": 23180 }, { "epoch": 4.8, "learning_rate": 0.0009392233565499475, "loss": 1.8069, "step": 23185 }, { "epoch": 4.8, "learning_rate": 0.0009391279458066978, "loss": 1.8044, "step": 23190 }, { "epoch": 4.81, "learning_rate": 0.0009390325350634482, "loss": 1.8087, "step": 23195 }, { "epoch": 4.81, "learning_rate": 0.0009389371243201985, "loss": 1.81, "step": 23200 }, { "epoch": 4.81, "learning_rate": 0.0009388417135769488, "loss": 1.8089, "step": 23205 }, { "epoch": 4.81, "learning_rate": 0.0009387463028336992, "loss": 1.8108, "step": 23210 }, { "epoch": 4.81, "learning_rate": 0.0009386508920904494, "loss": 1.8105, "step": 23215 }, { "epoch": 4.81, "learning_rate": 0.0009385554813471997, "loss": 1.8113, "step": 23220 }, { "epoch": 4.81, "learning_rate": 0.00093846007060395, "loss": 1.8008, "step": 23225 }, { "epoch": 4.81, "learning_rate": 0.0009383646598607003, "loss": 1.8061, "step": 23230 }, { "epoch": 4.81, "learning_rate": 0.0009382692491174506, "loss": 1.8069, "step": 23235 }, { "epoch": 4.81, "learning_rate": 0.000938173838374201, "loss": 1.8086, "step": 23240 }, { "epoch": 4.82, "learning_rate": 0.0009380784276309513, "loss": 1.8046, "step": 23245 }, { "epoch": 4.82, "learning_rate": 0.0009379830168877016, "loss": 1.8081, "step": 23250 }, { "epoch": 4.82, "learning_rate": 0.0009378876061444519, "loss": 1.8043, "step": 23255 }, { "epoch": 4.82, "learning_rate": 0.0009377921954012022, "loss": 1.8086, "step": 23260 }, { "epoch": 4.82, "learning_rate": 0.0009376967846579525, "loss": 1.8131, "step": 23265 }, { "epoch": 4.82, "learning_rate": 0.0009376013739147028, "loss": 1.8052, "step": 23270 }, { "epoch": 4.82, "learning_rate": 0.0009375059631714531, "loss": 1.8139, "step": 23275 }, { "epoch": 4.82, "learning_rate": 0.0009374105524282034, "loss": 1.8103, "step": 23280 }, { "epoch": 4.82, "learning_rate": 0.0009373151416849538, "loss": 1.8085, "step": 23285 }, { "epoch": 4.82, "learning_rate": 0.0009372197309417041, "loss": 1.8065, "step": 23290 }, { "epoch": 4.83, "learning_rate": 0.0009371243201984543, "loss": 1.8051, "step": 23295 }, { "epoch": 4.83, "learning_rate": 0.0009370289094552047, "loss": 1.8074, "step": 23300 }, { "epoch": 4.83, "learning_rate": 0.000936933498711955, "loss": 1.8059, "step": 23305 }, { "epoch": 4.83, "learning_rate": 0.0009368380879687053, "loss": 1.8056, "step": 23310 }, { "epoch": 4.83, "learning_rate": 0.0009367426772254556, "loss": 1.806, "step": 23315 }, { "epoch": 4.83, "learning_rate": 0.0009366472664822059, "loss": 1.8039, "step": 23320 }, { "epoch": 4.83, "learning_rate": 0.0009365518557389561, "loss": 1.8093, "step": 23325 }, { "epoch": 4.83, "learning_rate": 0.0009364564449957066, "loss": 1.8141, "step": 23330 }, { "epoch": 4.83, "learning_rate": 0.0009363610342524569, "loss": 1.8123, "step": 23335 }, { "epoch": 4.84, "learning_rate": 0.0009362656235092072, "loss": 1.81, "step": 23340 }, { "epoch": 4.84, "learning_rate": 0.0009361702127659575, "loss": 1.8076, "step": 23345 }, { "epoch": 4.84, "learning_rate": 0.0009360748020227078, "loss": 1.8085, "step": 23350 }, { "epoch": 4.84, "learning_rate": 0.000935979391279458, "loss": 1.8101, "step": 23355 }, { "epoch": 4.84, "learning_rate": 0.0009358839805362084, "loss": 1.8075, "step": 23360 }, { "epoch": 4.84, "learning_rate": 0.0009357885697929587, "loss": 1.8131, "step": 23365 }, { "epoch": 4.84, "learning_rate": 0.000935693159049709, "loss": 1.811, "step": 23370 }, { "epoch": 4.84, "learning_rate": 0.0009355977483064593, "loss": 1.8076, "step": 23375 }, { "epoch": 4.84, "learning_rate": 0.0009355023375632096, "loss": 1.8066, "step": 23380 }, { "epoch": 4.84, "learning_rate": 0.0009354069268199599, "loss": 1.8067, "step": 23385 }, { "epoch": 4.85, "learning_rate": 0.0009353115160767103, "loss": 1.8016, "step": 23390 }, { "epoch": 4.85, "learning_rate": 0.0009352161053334606, "loss": 1.8061, "step": 23395 }, { "epoch": 4.85, "learning_rate": 0.0009351206945902109, "loss": 1.8026, "step": 23400 }, { "epoch": 4.85, "learning_rate": 0.0009350252838469612, "loss": 1.8046, "step": 23405 }, { "epoch": 4.85, "learning_rate": 0.0009349298731037114, "loss": 1.8026, "step": 23410 }, { "epoch": 4.85, "learning_rate": 0.0009348344623604618, "loss": 1.8041, "step": 23415 }, { "epoch": 4.85, "learning_rate": 0.0009347390516172121, "loss": 1.8051, "step": 23420 }, { "epoch": 4.85, "learning_rate": 0.0009346436408739625, "loss": 1.8057, "step": 23425 }, { "epoch": 4.85, "learning_rate": 0.0009345482301307128, "loss": 1.8068, "step": 23430 }, { "epoch": 4.85, "learning_rate": 0.000934452819387463, "loss": 1.8058, "step": 23435 }, { "epoch": 4.86, "learning_rate": 0.0009343574086442133, "loss": 1.8068, "step": 23440 }, { "epoch": 4.86, "learning_rate": 0.0009342619979009637, "loss": 1.8071, "step": 23445 }, { "epoch": 4.86, "learning_rate": 0.000934166587157714, "loss": 1.8084, "step": 23450 }, { "epoch": 4.86, "learning_rate": 0.0009340711764144643, "loss": 1.807, "step": 23455 }, { "epoch": 4.86, "learning_rate": 0.0009339757656712146, "loss": 1.8071, "step": 23460 }, { "epoch": 4.86, "learning_rate": 0.0009338803549279648, "loss": 1.8072, "step": 23465 }, { "epoch": 4.86, "learning_rate": 0.0009337849441847152, "loss": 1.8028, "step": 23470 }, { "epoch": 4.86, "learning_rate": 0.0009336895334414656, "loss": 1.8066, "step": 23475 }, { "epoch": 4.86, "learning_rate": 0.0009335941226982159, "loss": 1.8048, "step": 23480 }, { "epoch": 4.87, "learning_rate": 0.0009334987119549662, "loss": 1.804, "step": 23485 }, { "epoch": 4.87, "learning_rate": 0.0009334033012117165, "loss": 1.8035, "step": 23490 }, { "epoch": 4.87, "learning_rate": 0.0009333078904684667, "loss": 1.8009, "step": 23495 }, { "epoch": 4.87, "learning_rate": 0.000933212479725217, "loss": 1.8059, "step": 23500 }, { "epoch": 4.87, "learning_rate": 0.0009331170689819674, "loss": 1.8031, "step": 23505 }, { "epoch": 4.87, "learning_rate": 0.0009330216582387177, "loss": 1.8243, "step": 23510 }, { "epoch": 4.87, "learning_rate": 0.0009329262474954681, "loss": 1.8206, "step": 23515 }, { "epoch": 4.87, "learning_rate": 0.0009328308367522183, "loss": 1.8226, "step": 23520 }, { "epoch": 4.87, "learning_rate": 0.0009327354260089686, "loss": 1.8178, "step": 23525 }, { "epoch": 4.87, "learning_rate": 0.0009326400152657189, "loss": 1.8169, "step": 23530 }, { "epoch": 4.88, "learning_rate": 0.0009325446045224693, "loss": 1.8094, "step": 23535 }, { "epoch": 4.88, "learning_rate": 0.0009324491937792196, "loss": 1.8105, "step": 23540 }, { "epoch": 4.88, "learning_rate": 0.0009323537830359699, "loss": 1.8119, "step": 23545 }, { "epoch": 4.88, "learning_rate": 0.0009322583722927201, "loss": 1.8086, "step": 23550 }, { "epoch": 4.88, "learning_rate": 0.0009321629615494704, "loss": 1.8091, "step": 23555 }, { "epoch": 4.88, "learning_rate": 0.0009320675508062208, "loss": 1.8068, "step": 23560 }, { "epoch": 4.88, "learning_rate": 0.0009319721400629712, "loss": 1.8105, "step": 23565 }, { "epoch": 4.88, "learning_rate": 0.0009318767293197215, "loss": 1.8033, "step": 23570 }, { "epoch": 4.88, "learning_rate": 0.0009317813185764718, "loss": 1.8023, "step": 23575 }, { "epoch": 4.89, "learning_rate": 0.000931685907833222, "loss": 1.8076, "step": 23580 }, { "epoch": 4.89, "learning_rate": 0.0009315904970899723, "loss": 1.8085, "step": 23585 }, { "epoch": 4.89, "learning_rate": 0.0009314950863467226, "loss": 1.8083, "step": 23590 }, { "epoch": 4.89, "learning_rate": 0.000931399675603473, "loss": 1.8059, "step": 23595 }, { "epoch": 4.89, "learning_rate": 0.0009313042648602233, "loss": 1.8015, "step": 23600 }, { "epoch": 4.89, "learning_rate": 0.0009312088541169735, "loss": 1.8112, "step": 23605 }, { "epoch": 4.89, "learning_rate": 0.0009311134433737239, "loss": 1.8034, "step": 23610 }, { "epoch": 4.89, "learning_rate": 0.0009310180326304742, "loss": 1.807, "step": 23615 }, { "epoch": 4.89, "learning_rate": 0.0009309226218872246, "loss": 1.8065, "step": 23620 }, { "epoch": 4.89, "learning_rate": 0.0009308272111439749, "loss": 1.8088, "step": 23625 }, { "epoch": 4.9, "learning_rate": 0.0009307318004007252, "loss": 1.8041, "step": 23630 }, { "epoch": 4.9, "learning_rate": 0.0009306363896574754, "loss": 1.8062, "step": 23635 }, { "epoch": 4.9, "learning_rate": 0.0009305409789142257, "loss": 1.8025, "step": 23640 }, { "epoch": 4.9, "learning_rate": 0.000930445568170976, "loss": 1.808, "step": 23645 }, { "epoch": 4.9, "learning_rate": 0.0009303501574277264, "loss": 1.8037, "step": 23650 }, { "epoch": 4.9, "learning_rate": 0.0009302547466844768, "loss": 1.8072, "step": 23655 }, { "epoch": 4.9, "learning_rate": 0.000930159335941227, "loss": 1.8077, "step": 23660 }, { "epoch": 4.9, "learning_rate": 0.0009300639251979773, "loss": 1.8093, "step": 23665 }, { "epoch": 4.9, "learning_rate": 0.0009299685144547276, "loss": 1.8093, "step": 23670 }, { "epoch": 4.9, "learning_rate": 0.0009298731037114779, "loss": 1.8072, "step": 23675 }, { "epoch": 4.91, "learning_rate": 0.0009297776929682283, "loss": 1.8052, "step": 23680 }, { "epoch": 4.91, "learning_rate": 0.0009296822822249786, "loss": 1.805, "step": 23685 }, { "epoch": 4.91, "learning_rate": 0.0009295868714817288, "loss": 1.802, "step": 23690 }, { "epoch": 4.91, "learning_rate": 0.0009294914607384791, "loss": 1.8034, "step": 23695 }, { "epoch": 4.91, "learning_rate": 0.0009293960499952295, "loss": 1.8076, "step": 23700 }, { "epoch": 4.91, "learning_rate": 0.0009293006392519798, "loss": 1.8092, "step": 23705 }, { "epoch": 4.91, "learning_rate": 0.0009292052285087302, "loss": 1.8034, "step": 23710 }, { "epoch": 4.91, "learning_rate": 0.0009291098177654805, "loss": 1.8082, "step": 23715 }, { "epoch": 4.91, "learning_rate": 0.0009290144070222307, "loss": 1.8078, "step": 23720 }, { "epoch": 4.92, "learning_rate": 0.000928918996278981, "loss": 1.8075, "step": 23725 }, { "epoch": 4.92, "learning_rate": 0.0009288235855357313, "loss": 1.8028, "step": 23730 }, { "epoch": 4.92, "learning_rate": 0.0009287281747924816, "loss": 1.8033, "step": 23735 }, { "epoch": 4.92, "learning_rate": 0.000928632764049232, "loss": 1.8045, "step": 23740 }, { "epoch": 4.92, "learning_rate": 0.0009285373533059823, "loss": 1.8018, "step": 23745 }, { "epoch": 4.92, "learning_rate": 0.0009284419425627326, "loss": 1.8096, "step": 23750 }, { "epoch": 4.92, "learning_rate": 0.0009283465318194829, "loss": 1.8066, "step": 23755 }, { "epoch": 4.92, "learning_rate": 0.0009282511210762332, "loss": 1.8027, "step": 23760 }, { "epoch": 4.92, "learning_rate": 0.0009281557103329835, "loss": 1.8118, "step": 23765 }, { "epoch": 4.92, "learning_rate": 0.0009280602995897339, "loss": 1.8025, "step": 23770 }, { "epoch": 4.93, "learning_rate": 0.0009279648888464841, "loss": 1.8099, "step": 23775 }, { "epoch": 4.93, "learning_rate": 0.0009278694781032344, "loss": 1.8021, "step": 23780 }, { "epoch": 4.93, "learning_rate": 0.0009277740673599847, "loss": 1.808, "step": 23785 }, { "epoch": 4.93, "learning_rate": 0.0009276786566167351, "loss": 1.8086, "step": 23790 }, { "epoch": 4.93, "learning_rate": 0.0009275832458734854, "loss": 1.8002, "step": 23795 }, { "epoch": 4.93, "learning_rate": 0.0009274878351302358, "loss": 1.808, "step": 23800 }, { "epoch": 4.93, "learning_rate": 0.000927392424386986, "loss": 1.798, "step": 23805 }, { "epoch": 4.93, "learning_rate": 0.0009272970136437363, "loss": 1.8087, "step": 23810 }, { "epoch": 4.93, "learning_rate": 0.0009272016029004866, "loss": 1.8031, "step": 23815 }, { "epoch": 4.93, "learning_rate": 0.0009271061921572369, "loss": 1.8043, "step": 23820 }, { "epoch": 4.94, "learning_rate": 0.0009270107814139871, "loss": 1.8014, "step": 23825 }, { "epoch": 4.94, "learning_rate": 0.0009269153706707375, "loss": 1.8041, "step": 23830 }, { "epoch": 4.94, "learning_rate": 0.0009268199599274878, "loss": 1.8067, "step": 23835 }, { "epoch": 4.94, "learning_rate": 0.0009267245491842382, "loss": 1.8069, "step": 23840 }, { "epoch": 4.94, "learning_rate": 0.0009266291384409885, "loss": 1.8058, "step": 23845 }, { "epoch": 4.94, "learning_rate": 0.0009265337276977388, "loss": 1.8037, "step": 23850 }, { "epoch": 4.94, "learning_rate": 0.0009264383169544892, "loss": 1.8027, "step": 23855 }, { "epoch": 4.94, "learning_rate": 0.0009263429062112394, "loss": 1.8011, "step": 23860 }, { "epoch": 4.94, "learning_rate": 0.0009262474954679897, "loss": 1.8009, "step": 23865 }, { "epoch": 4.95, "learning_rate": 0.00092615208472474, "loss": 1.8097, "step": 23870 }, { "epoch": 4.95, "learning_rate": 0.0009260566739814903, "loss": 1.7952, "step": 23875 }, { "epoch": 4.95, "learning_rate": 0.0009259612632382406, "loss": 1.8095, "step": 23880 }, { "epoch": 4.95, "learning_rate": 0.000925865852494991, "loss": 1.8064, "step": 23885 }, { "epoch": 4.95, "learning_rate": 0.0009257704417517413, "loss": 1.8064, "step": 23890 }, { "epoch": 4.95, "learning_rate": 0.0009256750310084916, "loss": 1.8073, "step": 23895 }, { "epoch": 4.95, "learning_rate": 0.0009255796202652419, "loss": 1.8069, "step": 23900 }, { "epoch": 4.95, "learning_rate": 0.0009254842095219922, "loss": 1.8041, "step": 23905 }, { "epoch": 4.95, "learning_rate": 0.0009253887987787424, "loss": 1.809, "step": 23910 }, { "epoch": 4.95, "learning_rate": 0.0009252933880354928, "loss": 1.807, "step": 23915 }, { "epoch": 4.96, "learning_rate": 0.0009251979772922431, "loss": 1.7997, "step": 23920 }, { "epoch": 4.96, "learning_rate": 0.0009251025665489934, "loss": 1.8021, "step": 23925 }, { "epoch": 4.96, "learning_rate": 0.0009250071558057438, "loss": 1.813, "step": 23930 }, { "epoch": 4.96, "learning_rate": 0.0009249117450624941, "loss": 1.8064, "step": 23935 }, { "epoch": 4.96, "learning_rate": 0.0009248163343192443, "loss": 1.8021, "step": 23940 }, { "epoch": 4.96, "learning_rate": 0.0009247209235759947, "loss": 1.8076, "step": 23945 }, { "epoch": 4.96, "learning_rate": 0.000924625512832745, "loss": 1.8051, "step": 23950 }, { "epoch": 4.96, "learning_rate": 0.0009245301020894953, "loss": 1.8044, "step": 23955 }, { "epoch": 4.96, "learning_rate": 0.0009244346913462456, "loss": 1.8038, "step": 23960 }, { "epoch": 4.96, "learning_rate": 0.0009243392806029959, "loss": 1.8097, "step": 23965 }, { "epoch": 4.97, "learning_rate": 0.0009242438698597461, "loss": 1.8017, "step": 23970 }, { "epoch": 4.97, "learning_rate": 0.0009241484591164966, "loss": 1.7984, "step": 23975 }, { "epoch": 4.97, "learning_rate": 0.0009240530483732469, "loss": 1.807, "step": 23980 }, { "epoch": 4.97, "learning_rate": 0.0009239576376299972, "loss": 1.8093, "step": 23985 }, { "epoch": 4.97, "learning_rate": 0.0009238622268867475, "loss": 1.804, "step": 23990 }, { "epoch": 4.97, "learning_rate": 0.0009237668161434977, "loss": 1.8026, "step": 23995 }, { "epoch": 4.97, "learning_rate": 0.000923671405400248, "loss": 1.8051, "step": 24000 }, { "epoch": 4.97, "eval_accuracy": 0.533202614379085, "eval_loss": 1.9728877544403076, "eval_runtime": 0.7999, "eval_samples_per_second": 187.53, "eval_steps_per_second": 1.25, "step": 24000 }, { "epoch": 4.97, "learning_rate": 0.0009235759946569984, "loss": 1.8013, "step": 24005 }, { "epoch": 4.97, "learning_rate": 0.0009234805839137487, "loss": 1.8005, "step": 24010 }, { "epoch": 4.98, "learning_rate": 0.000923385173170499, "loss": 1.8032, "step": 24015 }, { "epoch": 4.98, "learning_rate": 0.0009232897624272494, "loss": 1.8029, "step": 24020 }, { "epoch": 4.98, "learning_rate": 0.0009231943516839996, "loss": 1.8025, "step": 24025 }, { "epoch": 4.98, "learning_rate": 0.00092309894094075, "loss": 1.8049, "step": 24030 }, { "epoch": 4.98, "learning_rate": 0.0009230035301975003, "loss": 1.799, "step": 24035 }, { "epoch": 4.98, "learning_rate": 0.0009229081194542506, "loss": 1.8051, "step": 24040 }, { "epoch": 4.98, "learning_rate": 0.0009228127087110009, "loss": 1.8018, "step": 24045 }, { "epoch": 4.98, "learning_rate": 0.0009227172979677511, "loss": 1.8093, "step": 24050 }, { "epoch": 4.98, "learning_rate": 0.0009226218872245014, "loss": 1.7977, "step": 24055 }, { "epoch": 4.98, "learning_rate": 0.0009225264764812518, "loss": 1.8073, "step": 24060 }, { "epoch": 4.99, "learning_rate": 0.0009224310657380022, "loss": 1.807, "step": 24065 }, { "epoch": 4.99, "learning_rate": 0.0009223356549947525, "loss": 1.8069, "step": 24070 }, { "epoch": 4.99, "learning_rate": 0.0009222402442515028, "loss": 1.8035, "step": 24075 }, { "epoch": 4.99, "learning_rate": 0.000922144833508253, "loss": 1.8032, "step": 24080 }, { "epoch": 4.99, "learning_rate": 0.0009220494227650033, "loss": 1.8068, "step": 24085 }, { "epoch": 4.99, "learning_rate": 0.0009219540120217537, "loss": 1.8042, "step": 24090 }, { "epoch": 4.99, "learning_rate": 0.000921858601278504, "loss": 1.8079, "step": 24095 }, { "epoch": 4.99, "learning_rate": 0.0009217631905352543, "loss": 1.8048, "step": 24100 }, { "epoch": 4.99, "learning_rate": 0.0009216677797920046, "loss": 1.8024, "step": 24105 }, { "epoch": 4.99, "learning_rate": 0.0009215723690487548, "loss": 1.8033, "step": 24110 }, { "epoch": 5.0, "learning_rate": 0.0009214769583055052, "loss": 1.8035, "step": 24115 }, { "epoch": 5.0, "learning_rate": 0.0009213815475622556, "loss": 1.8041, "step": 24120 }, { "epoch": 5.0, "learning_rate": 0.0009212861368190059, "loss": 1.8032, "step": 24125 }, { "epoch": 5.0, "learning_rate": 0.0009211907260757562, "loss": 1.8044, "step": 24130 }, { "epoch": 5.0, "learning_rate": 0.0009210953153325064, "loss": 1.8044, "step": 24135 }, { "epoch": 5.0, "learning_rate": 0.0009209999045892567, "loss": 1.7956, "step": 24140 }, { "epoch": 5.0, "learning_rate": 0.000920904493846007, "loss": 1.7925, "step": 24145 }, { "epoch": 5.0, "learning_rate": 0.0009208090831027574, "loss": 1.7911, "step": 24150 }, { "epoch": 5.0, "learning_rate": 0.0009207136723595077, "loss": 1.7959, "step": 24155 }, { "epoch": 5.01, "learning_rate": 0.0009206182616162581, "loss": 1.7933, "step": 24160 }, { "epoch": 5.01, "learning_rate": 0.0009205228508730083, "loss": 1.7914, "step": 24165 }, { "epoch": 5.01, "learning_rate": 0.0009204274401297586, "loss": 1.7917, "step": 24170 }, { "epoch": 5.01, "learning_rate": 0.0009203320293865089, "loss": 1.7898, "step": 24175 }, { "epoch": 5.01, "learning_rate": 0.0009202366186432593, "loss": 1.7945, "step": 24180 }, { "epoch": 5.01, "learning_rate": 0.0009201412079000096, "loss": 1.7867, "step": 24185 }, { "epoch": 5.01, "learning_rate": 0.0009200457971567599, "loss": 1.7937, "step": 24190 }, { "epoch": 5.01, "learning_rate": 0.0009199503864135101, "loss": 1.7961, "step": 24195 }, { "epoch": 5.01, "learning_rate": 0.0009198549756702604, "loss": 1.7911, "step": 24200 }, { "epoch": 5.01, "learning_rate": 0.0009197595649270108, "loss": 1.7922, "step": 24205 }, { "epoch": 5.02, "learning_rate": 0.0009196641541837612, "loss": 1.7905, "step": 24210 }, { "epoch": 5.02, "learning_rate": 0.0009195687434405115, "loss": 1.7955, "step": 24215 }, { "epoch": 5.02, "learning_rate": 0.0009194733326972617, "loss": 1.7951, "step": 24220 }, { "epoch": 5.02, "learning_rate": 0.000919377921954012, "loss": 1.7922, "step": 24225 }, { "epoch": 5.02, "learning_rate": 0.0009192825112107623, "loss": 1.7915, "step": 24230 }, { "epoch": 5.02, "learning_rate": 0.0009191871004675126, "loss": 1.7992, "step": 24235 }, { "epoch": 5.02, "learning_rate": 0.000919091689724263, "loss": 1.7914, "step": 24240 }, { "epoch": 5.02, "learning_rate": 0.0009189962789810133, "loss": 1.7879, "step": 24245 }, { "epoch": 5.02, "learning_rate": 0.0009189008682377636, "loss": 1.7881, "step": 24250 }, { "epoch": 5.02, "learning_rate": 0.0009188054574945139, "loss": 1.7934, "step": 24255 }, { "epoch": 5.03, "learning_rate": 0.0009187100467512642, "loss": 1.7955, "step": 24260 }, { "epoch": 5.03, "learning_rate": 0.0009186146360080146, "loss": 1.7913, "step": 24265 }, { "epoch": 5.03, "learning_rate": 0.0009185192252647649, "loss": 1.7924, "step": 24270 }, { "epoch": 5.03, "learning_rate": 0.0009184238145215151, "loss": 1.7943, "step": 24275 }, { "epoch": 5.03, "learning_rate": 0.0009183284037782654, "loss": 1.7931, "step": 24280 }, { "epoch": 5.03, "learning_rate": 0.0009182329930350157, "loss": 1.7898, "step": 24285 }, { "epoch": 5.03, "learning_rate": 0.000918137582291766, "loss": 1.7898, "step": 24290 }, { "epoch": 5.03, "learning_rate": 0.0009180421715485165, "loss": 1.7923, "step": 24295 }, { "epoch": 5.03, "learning_rate": 0.0009179467608052668, "loss": 1.7944, "step": 24300 }, { "epoch": 5.04, "learning_rate": 0.000917851350062017, "loss": 1.7892, "step": 24305 }, { "epoch": 5.04, "learning_rate": 0.0009177559393187673, "loss": 1.794, "step": 24310 }, { "epoch": 5.04, "learning_rate": 0.0009176605285755176, "loss": 1.7906, "step": 24315 }, { "epoch": 5.04, "learning_rate": 0.0009175651178322679, "loss": 1.7972, "step": 24320 }, { "epoch": 5.04, "learning_rate": 0.0009174697070890183, "loss": 1.7885, "step": 24325 }, { "epoch": 5.04, "learning_rate": 0.0009173742963457686, "loss": 1.7895, "step": 24330 }, { "epoch": 5.04, "learning_rate": 0.0009172788856025188, "loss": 1.7939, "step": 24335 }, { "epoch": 5.04, "learning_rate": 0.0009171834748592691, "loss": 1.7941, "step": 24340 }, { "epoch": 5.04, "learning_rate": 0.0009170880641160195, "loss": 1.7919, "step": 24345 }, { "epoch": 5.04, "learning_rate": 0.0009169926533727698, "loss": 1.7966, "step": 24350 }, { "epoch": 5.05, "learning_rate": 0.0009168972426295202, "loss": 1.8026, "step": 24355 }, { "epoch": 5.05, "learning_rate": 0.0009168018318862704, "loss": 1.7911, "step": 24360 }, { "epoch": 5.05, "learning_rate": 0.0009167064211430207, "loss": 1.7938, "step": 24365 }, { "epoch": 5.05, "learning_rate": 0.000916611010399771, "loss": 1.7945, "step": 24370 }, { "epoch": 5.05, "learning_rate": 0.0009165155996565213, "loss": 1.7962, "step": 24375 }, { "epoch": 5.05, "learning_rate": 0.0009164201889132716, "loss": 1.7948, "step": 24380 }, { "epoch": 5.05, "learning_rate": 0.000916324778170022, "loss": 1.7971, "step": 24385 }, { "epoch": 5.05, "learning_rate": 0.0009162293674267723, "loss": 1.7896, "step": 24390 }, { "epoch": 5.05, "learning_rate": 0.0009161339566835226, "loss": 1.7931, "step": 24395 }, { "epoch": 5.05, "learning_rate": 0.0009160385459402729, "loss": 1.7977, "step": 24400 }, { "epoch": 5.06, "learning_rate": 0.0009159431351970232, "loss": 1.797, "step": 24405 }, { "epoch": 5.06, "learning_rate": 0.0009158477244537735, "loss": 1.7955, "step": 24410 }, { "epoch": 5.06, "learning_rate": 0.0009157523137105238, "loss": 1.7943, "step": 24415 }, { "epoch": 5.06, "learning_rate": 0.0009156569029672741, "loss": 1.7959, "step": 24420 }, { "epoch": 5.06, "learning_rate": 0.0009155614922240244, "loss": 1.7963, "step": 24425 }, { "epoch": 5.06, "learning_rate": 0.0009154660814807747, "loss": 1.7937, "step": 24430 }, { "epoch": 5.06, "learning_rate": 0.0009153706707375251, "loss": 1.792, "step": 24435 }, { "epoch": 5.06, "learning_rate": 0.0009152752599942754, "loss": 1.7929, "step": 24440 }, { "epoch": 5.06, "learning_rate": 0.0009151798492510257, "loss": 1.7968, "step": 24445 }, { "epoch": 5.07, "learning_rate": 0.000915084438507776, "loss": 1.7951, "step": 24450 }, { "epoch": 5.07, "learning_rate": 0.0009149890277645263, "loss": 1.7969, "step": 24455 }, { "epoch": 5.07, "learning_rate": 0.0009148936170212766, "loss": 1.7963, "step": 24460 }, { "epoch": 5.07, "learning_rate": 0.0009147982062780269, "loss": 1.7948, "step": 24465 }, { "epoch": 5.07, "learning_rate": 0.0009147027955347773, "loss": 1.7961, "step": 24470 }, { "epoch": 5.07, "learning_rate": 0.0009146073847915275, "loss": 1.7967, "step": 24475 }, { "epoch": 5.07, "learning_rate": 0.0009145119740482779, "loss": 1.7894, "step": 24480 }, { "epoch": 5.07, "learning_rate": 0.0009144165633050282, "loss": 1.7956, "step": 24485 }, { "epoch": 5.07, "learning_rate": 0.0009143211525617785, "loss": 1.7988, "step": 24490 }, { "epoch": 5.07, "learning_rate": 0.0009142257418185288, "loss": 1.7954, "step": 24495 }, { "epoch": 5.08, "learning_rate": 0.0009141303310752791, "loss": 1.7918, "step": 24500 }, { "epoch": 5.08, "learning_rate": 0.0009140349203320294, "loss": 1.8025, "step": 24505 }, { "epoch": 5.08, "learning_rate": 0.0009139395095887797, "loss": 1.7957, "step": 24510 }, { "epoch": 5.08, "learning_rate": 0.00091384409884553, "loss": 1.7936, "step": 24515 }, { "epoch": 5.08, "learning_rate": 0.0009137486881022803, "loss": 1.7966, "step": 24520 }, { "epoch": 5.08, "learning_rate": 0.0009136532773590307, "loss": 1.7982, "step": 24525 }, { "epoch": 5.08, "learning_rate": 0.000913557866615781, "loss": 1.7987, "step": 24530 }, { "epoch": 5.08, "learning_rate": 0.0009134624558725313, "loss": 1.802, "step": 24535 }, { "epoch": 5.08, "learning_rate": 0.0009133670451292816, "loss": 1.7978, "step": 24540 }, { "epoch": 5.08, "learning_rate": 0.0009132716343860319, "loss": 1.7914, "step": 24545 }, { "epoch": 5.09, "learning_rate": 0.0009131762236427822, "loss": 1.7893, "step": 24550 }, { "epoch": 5.09, "learning_rate": 0.0009130808128995324, "loss": 1.7948, "step": 24555 }, { "epoch": 5.09, "learning_rate": 0.0009129854021562828, "loss": 1.7943, "step": 24560 }, { "epoch": 5.09, "learning_rate": 0.0009128899914130331, "loss": 1.7982, "step": 24565 }, { "epoch": 5.09, "learning_rate": 0.0009127945806697835, "loss": 1.796, "step": 24570 }, { "epoch": 5.09, "learning_rate": 0.0009126991699265338, "loss": 1.7964, "step": 24575 }, { "epoch": 5.09, "learning_rate": 0.0009126037591832841, "loss": 1.7981, "step": 24580 }, { "epoch": 5.09, "learning_rate": 0.0009125083484400343, "loss": 1.7948, "step": 24585 }, { "epoch": 5.09, "learning_rate": 0.0009124129376967847, "loss": 1.7947, "step": 24590 }, { "epoch": 5.1, "learning_rate": 0.000912317526953535, "loss": 1.7934, "step": 24595 }, { "epoch": 5.1, "learning_rate": 0.0009122221162102853, "loss": 1.7982, "step": 24600 }, { "epoch": 5.1, "learning_rate": 0.0009121267054670356, "loss": 1.7942, "step": 24605 }, { "epoch": 5.1, "learning_rate": 0.0009120312947237858, "loss": 1.7906, "step": 24610 }, { "epoch": 5.1, "learning_rate": 0.0009119358839805361, "loss": 1.7897, "step": 24615 }, { "epoch": 5.1, "learning_rate": 0.0009118404732372866, "loss": 1.7972, "step": 24620 }, { "epoch": 5.1, "learning_rate": 0.0009117450624940369, "loss": 1.7927, "step": 24625 }, { "epoch": 5.1, "learning_rate": 0.0009116496517507872, "loss": 1.792, "step": 24630 }, { "epoch": 5.1, "learning_rate": 0.0009115542410075375, "loss": 1.794, "step": 24635 }, { "epoch": 5.1, "learning_rate": 0.0009114588302642877, "loss": 1.7978, "step": 24640 }, { "epoch": 5.11, "learning_rate": 0.000911363419521038, "loss": 1.7972, "step": 24645 }, { "epoch": 5.11, "learning_rate": 0.0009112680087777884, "loss": 1.7925, "step": 24650 }, { "epoch": 5.11, "learning_rate": 0.0009111725980345387, "loss": 1.7958, "step": 24655 }, { "epoch": 5.11, "learning_rate": 0.000911077187291289, "loss": 1.7929, "step": 24660 }, { "epoch": 5.11, "learning_rate": 0.0009109817765480394, "loss": 1.7954, "step": 24665 }, { "epoch": 5.11, "learning_rate": 0.0009108863658047896, "loss": 1.7888, "step": 24670 }, { "epoch": 5.11, "learning_rate": 0.00091079095506154, "loss": 1.7943, "step": 24675 }, { "epoch": 5.11, "learning_rate": 0.0009106955443182903, "loss": 1.7909, "step": 24680 }, { "epoch": 5.11, "learning_rate": 0.0009106001335750406, "loss": 1.7921, "step": 24685 }, { "epoch": 5.11, "learning_rate": 0.0009105047228317909, "loss": 1.7987, "step": 24690 }, { "epoch": 5.12, "learning_rate": 0.0009104093120885411, "loss": 1.7957, "step": 24695 }, { "epoch": 5.12, "learning_rate": 0.0009103139013452914, "loss": 1.8, "step": 24700 }, { "epoch": 5.12, "learning_rate": 0.0009102184906020418, "loss": 1.791, "step": 24705 }, { "epoch": 5.12, "learning_rate": 0.0009101230798587922, "loss": 1.795, "step": 24710 }, { "epoch": 5.12, "learning_rate": 0.0009100276691155425, "loss": 1.7948, "step": 24715 }, { "epoch": 5.12, "learning_rate": 0.0009099322583722928, "loss": 1.7921, "step": 24720 }, { "epoch": 5.12, "learning_rate": 0.000909836847629043, "loss": 1.798, "step": 24725 }, { "epoch": 5.12, "learning_rate": 0.0009097414368857933, "loss": 1.7912, "step": 24730 }, { "epoch": 5.12, "learning_rate": 0.0009096460261425437, "loss": 1.7957, "step": 24735 }, { "epoch": 5.13, "learning_rate": 0.000909550615399294, "loss": 1.7932, "step": 24740 }, { "epoch": 5.13, "learning_rate": 0.0009094552046560443, "loss": 1.7944, "step": 24745 }, { "epoch": 5.13, "learning_rate": 0.0009093597939127945, "loss": 1.7923, "step": 24750 }, { "epoch": 5.13, "learning_rate": 0.0009092643831695449, "loss": 1.8004, "step": 24755 }, { "epoch": 5.13, "learning_rate": 0.0009091689724262952, "loss": 1.7978, "step": 24760 }, { "epoch": 5.13, "learning_rate": 0.0009090735616830456, "loss": 1.8038, "step": 24765 }, { "epoch": 5.13, "learning_rate": 0.0009089781509397959, "loss": 1.8048, "step": 24770 }, { "epoch": 5.13, "learning_rate": 0.0009088827401965462, "loss": 1.7961, "step": 24775 }, { "epoch": 5.13, "learning_rate": 0.0009087873294532964, "loss": 1.7972, "step": 24780 }, { "epoch": 5.13, "learning_rate": 0.0009086919187100467, "loss": 1.7951, "step": 24785 }, { "epoch": 5.14, "learning_rate": 0.000908596507966797, "loss": 1.7939, "step": 24790 }, { "epoch": 5.14, "learning_rate": 0.0009085010972235474, "loss": 1.7959, "step": 24795 }, { "epoch": 5.14, "learning_rate": 0.0009084056864802978, "loss": 1.7943, "step": 24800 }, { "epoch": 5.14, "learning_rate": 0.0009083102757370481, "loss": 1.7978, "step": 24805 }, { "epoch": 5.14, "learning_rate": 0.0009082148649937983, "loss": 1.7975, "step": 24810 }, { "epoch": 5.14, "learning_rate": 0.0009081194542505486, "loss": 1.7917, "step": 24815 }, { "epoch": 5.14, "learning_rate": 0.0009080240435072989, "loss": 1.7882, "step": 24820 }, { "epoch": 5.14, "learning_rate": 0.0009079286327640493, "loss": 1.7949, "step": 24825 }, { "epoch": 5.14, "learning_rate": 0.0009078332220207996, "loss": 1.7943, "step": 24830 }, { "epoch": 5.15, "learning_rate": 0.0009077378112775498, "loss": 1.7945, "step": 24835 }, { "epoch": 5.15, "learning_rate": 0.0009076424005343001, "loss": 1.7931, "step": 24840 }, { "epoch": 5.15, "learning_rate": 0.0009075469897910504, "loss": 1.7991, "step": 24845 }, { "epoch": 5.15, "learning_rate": 0.0009074515790478008, "loss": 1.7918, "step": 24850 }, { "epoch": 5.15, "learning_rate": 0.0009073561683045512, "loss": 1.7957, "step": 24855 }, { "epoch": 5.15, "learning_rate": 0.0009072607575613015, "loss": 1.7967, "step": 24860 }, { "epoch": 5.15, "learning_rate": 0.0009071653468180517, "loss": 1.7948, "step": 24865 }, { "epoch": 5.15, "learning_rate": 0.000907069936074802, "loss": 1.7902, "step": 24870 }, { "epoch": 5.15, "learning_rate": 0.0009069745253315523, "loss": 1.7977, "step": 24875 }, { "epoch": 5.15, "learning_rate": 0.0009068791145883026, "loss": 1.7929, "step": 24880 }, { "epoch": 5.16, "learning_rate": 0.000906783703845053, "loss": 1.7857, "step": 24885 }, { "epoch": 5.16, "learning_rate": 0.0009066882931018032, "loss": 1.7923, "step": 24890 }, { "epoch": 5.16, "learning_rate": 0.0009065928823585536, "loss": 1.7935, "step": 24895 }, { "epoch": 5.16, "learning_rate": 0.0009064974716153039, "loss": 1.796, "step": 24900 }, { "epoch": 5.16, "learning_rate": 0.0009064020608720542, "loss": 1.7973, "step": 24905 }, { "epoch": 5.16, "learning_rate": 0.0009063066501288046, "loss": 1.7916, "step": 24910 }, { "epoch": 5.16, "learning_rate": 0.0009062112393855549, "loss": 1.7898, "step": 24915 }, { "epoch": 5.16, "learning_rate": 0.0009061158286423051, "loss": 1.7944, "step": 24920 }, { "epoch": 5.16, "learning_rate": 0.0009060204178990554, "loss": 1.7946, "step": 24925 }, { "epoch": 5.16, "learning_rate": 0.0009059250071558057, "loss": 1.7923, "step": 24930 }, { "epoch": 5.17, "learning_rate": 0.000905829596412556, "loss": 1.7903, "step": 24935 }, { "epoch": 5.17, "learning_rate": 0.0009057341856693065, "loss": 1.7948, "step": 24940 }, { "epoch": 5.17, "learning_rate": 0.0009056387749260568, "loss": 1.7968, "step": 24945 }, { "epoch": 5.17, "learning_rate": 0.000905543364182807, "loss": 1.7965, "step": 24950 }, { "epoch": 5.17, "learning_rate": 0.0009054479534395573, "loss": 1.7934, "step": 24955 }, { "epoch": 5.17, "learning_rate": 0.0009053525426963076, "loss": 1.7964, "step": 24960 }, { "epoch": 5.17, "learning_rate": 0.0009052571319530579, "loss": 1.7922, "step": 24965 }, { "epoch": 5.17, "learning_rate": 0.0009051617212098083, "loss": 1.7977, "step": 24970 }, { "epoch": 5.17, "learning_rate": 0.0009050663104665585, "loss": 1.7969, "step": 24975 }, { "epoch": 5.18, "learning_rate": 0.0009049708997233088, "loss": 1.7936, "step": 24980 }, { "epoch": 5.18, "learning_rate": 0.0009048754889800592, "loss": 1.7956, "step": 24985 }, { "epoch": 5.18, "learning_rate": 0.0009047800782368095, "loss": 1.7963, "step": 24990 }, { "epoch": 5.18, "learning_rate": 0.0009046846674935598, "loss": 1.7936, "step": 24995 }, { "epoch": 5.18, "learning_rate": 0.0009045892567503102, "loss": 1.7945, "step": 25000 }, { "epoch": 5.18, "learning_rate": 0.0009044938460070604, "loss": 1.7938, "step": 25005 }, { "epoch": 5.18, "learning_rate": 0.0009043984352638107, "loss": 1.7953, "step": 25010 }, { "epoch": 5.18, "learning_rate": 0.000904303024520561, "loss": 1.7976, "step": 25015 }, { "epoch": 5.18, "learning_rate": 0.0009042076137773113, "loss": 1.7917, "step": 25020 }, { "epoch": 5.18, "learning_rate": 0.0009041122030340616, "loss": 1.7949, "step": 25025 }, { "epoch": 5.19, "learning_rate": 0.0009040167922908121, "loss": 1.7942, "step": 25030 }, { "epoch": 5.19, "learning_rate": 0.0009039213815475623, "loss": 1.7903, "step": 25035 }, { "epoch": 5.19, "learning_rate": 0.0009038259708043126, "loss": 1.791, "step": 25040 }, { "epoch": 5.19, "learning_rate": 0.0009037305600610629, "loss": 1.7961, "step": 25045 }, { "epoch": 5.19, "learning_rate": 0.0009036351493178132, "loss": 1.7913, "step": 25050 }, { "epoch": 5.19, "learning_rate": 0.0009035397385745635, "loss": 1.789, "step": 25055 }, { "epoch": 5.19, "learning_rate": 0.0009034443278313138, "loss": 1.7925, "step": 25060 }, { "epoch": 5.19, "learning_rate": 0.0009033489170880641, "loss": 1.798, "step": 25065 }, { "epoch": 5.19, "learning_rate": 0.0009032535063448144, "loss": 1.7964, "step": 25070 }, { "epoch": 5.19, "learning_rate": 0.0009031580956015647, "loss": 1.793, "step": 25075 }, { "epoch": 5.2, "learning_rate": 0.0009030626848583151, "loss": 1.7931, "step": 25080 }, { "epoch": 5.2, "learning_rate": 0.0009029672741150655, "loss": 1.7958, "step": 25085 }, { "epoch": 5.2, "learning_rate": 0.0009028718633718157, "loss": 1.7941, "step": 25090 }, { "epoch": 5.2, "learning_rate": 0.000902776452628566, "loss": 1.8003, "step": 25095 }, { "epoch": 5.2, "learning_rate": 0.0009026810418853163, "loss": 1.7992, "step": 25100 }, { "epoch": 5.2, "learning_rate": 0.0009025856311420666, "loss": 1.7928, "step": 25105 }, { "epoch": 5.2, "learning_rate": 0.0009024902203988169, "loss": 1.7965, "step": 25110 }, { "epoch": 5.2, "learning_rate": 0.0009023948096555672, "loss": 1.7955, "step": 25115 }, { "epoch": 5.2, "learning_rate": 0.0009022993989123175, "loss": 1.7973, "step": 25120 }, { "epoch": 5.21, "learning_rate": 0.0009022039881690679, "loss": 1.7945, "step": 25125 }, { "epoch": 5.21, "learning_rate": 0.0009021085774258182, "loss": 1.7915, "step": 25130 }, { "epoch": 5.21, "learning_rate": 0.0009020131666825685, "loss": 1.7957, "step": 25135 }, { "epoch": 5.21, "learning_rate": 0.0009019177559393188, "loss": 1.7845, "step": 25140 }, { "epoch": 5.21, "learning_rate": 0.0009018223451960691, "loss": 1.7954, "step": 25145 }, { "epoch": 5.21, "learning_rate": 0.0009017269344528194, "loss": 1.7923, "step": 25150 }, { "epoch": 5.21, "learning_rate": 0.0009016315237095697, "loss": 1.7925, "step": 25155 }, { "epoch": 5.21, "learning_rate": 0.00090153611296632, "loss": 1.7927, "step": 25160 }, { "epoch": 5.21, "learning_rate": 0.0009014407022230703, "loss": 1.7935, "step": 25165 }, { "epoch": 5.21, "learning_rate": 0.0009013452914798207, "loss": 1.7974, "step": 25170 }, { "epoch": 5.22, "learning_rate": 0.000901249880736571, "loss": 1.7918, "step": 25175 }, { "epoch": 5.22, "learning_rate": 0.0009011544699933213, "loss": 1.791, "step": 25180 }, { "epoch": 5.22, "learning_rate": 0.0009010590592500716, "loss": 1.792, "step": 25185 }, { "epoch": 5.22, "learning_rate": 0.0009009636485068219, "loss": 1.7917, "step": 25190 }, { "epoch": 5.22, "learning_rate": 0.0009008682377635722, "loss": 1.795, "step": 25195 }, { "epoch": 5.22, "learning_rate": 0.0009007728270203224, "loss": 1.7947, "step": 25200 }, { "epoch": 5.22, "learning_rate": 0.0009006774162770728, "loss": 1.7933, "step": 25205 }, { "epoch": 5.22, "learning_rate": 0.0009005820055338231, "loss": 1.7923, "step": 25210 }, { "epoch": 5.22, "learning_rate": 0.0009004865947905735, "loss": 1.7925, "step": 25215 }, { "epoch": 5.22, "learning_rate": 0.0009003911840473238, "loss": 1.7898, "step": 25220 }, { "epoch": 5.23, "learning_rate": 0.000900295773304074, "loss": 1.7951, "step": 25225 }, { "epoch": 5.23, "learning_rate": 0.0009002003625608243, "loss": 1.7946, "step": 25230 }, { "epoch": 5.23, "learning_rate": 0.0009001049518175747, "loss": 1.7958, "step": 25235 }, { "epoch": 5.23, "learning_rate": 0.000900009541074325, "loss": 1.7958, "step": 25240 }, { "epoch": 5.23, "learning_rate": 0.0008999141303310753, "loss": 1.7946, "step": 25245 }, { "epoch": 5.23, "learning_rate": 0.0008998187195878256, "loss": 1.7966, "step": 25250 }, { "epoch": 5.23, "learning_rate": 0.0008997233088445758, "loss": 1.7974, "step": 25255 }, { "epoch": 5.23, "learning_rate": 0.0008996278981013262, "loss": 1.7919, "step": 25260 }, { "epoch": 5.23, "learning_rate": 0.0008995324873580766, "loss": 1.7916, "step": 25265 }, { "epoch": 5.24, "learning_rate": 0.0008994370766148269, "loss": 1.7919, "step": 25270 }, { "epoch": 5.24, "learning_rate": 0.0008993416658715772, "loss": 1.7906, "step": 25275 }, { "epoch": 5.24, "learning_rate": 0.0008992462551283275, "loss": 1.7919, "step": 25280 }, { "epoch": 5.24, "learning_rate": 0.0008991508443850777, "loss": 1.7964, "step": 25285 }, { "epoch": 5.24, "learning_rate": 0.000899055433641828, "loss": 1.7954, "step": 25290 }, { "epoch": 5.24, "learning_rate": 0.0008989600228985784, "loss": 1.7935, "step": 25295 }, { "epoch": 5.24, "learning_rate": 0.0008988646121553287, "loss": 1.7951, "step": 25300 }, { "epoch": 5.24, "learning_rate": 0.0008987692014120791, "loss": 1.7893, "step": 25305 }, { "epoch": 5.24, "learning_rate": 0.0008986737906688294, "loss": 1.792, "step": 25310 }, { "epoch": 5.24, "learning_rate": 0.0008985783799255796, "loss": 1.7916, "step": 25315 }, { "epoch": 5.25, "learning_rate": 0.00089848296918233, "loss": 1.7949, "step": 25320 }, { "epoch": 5.25, "learning_rate": 0.0008983875584390803, "loss": 1.7899, "step": 25325 }, { "epoch": 5.25, "learning_rate": 0.0008982921476958306, "loss": 1.7956, "step": 25330 }, { "epoch": 5.25, "learning_rate": 0.0008981967369525809, "loss": 1.791, "step": 25335 }, { "epoch": 5.25, "learning_rate": 0.0008981013262093311, "loss": 1.7967, "step": 25340 }, { "epoch": 5.25, "learning_rate": 0.0008980059154660814, "loss": 1.7907, "step": 25345 }, { "epoch": 5.25, "learning_rate": 0.0008979105047228318, "loss": 1.7924, "step": 25350 }, { "epoch": 5.25, "learning_rate": 0.0008978150939795822, "loss": 1.7913, "step": 25355 }, { "epoch": 5.25, "learning_rate": 0.0008977196832363325, "loss": 1.7877, "step": 25360 }, { "epoch": 5.25, "learning_rate": 0.0008976242724930828, "loss": 1.7949, "step": 25365 }, { "epoch": 5.26, "learning_rate": 0.000897528861749833, "loss": 1.7962, "step": 25370 }, { "epoch": 5.26, "learning_rate": 0.0008974334510065833, "loss": 1.7932, "step": 25375 }, { "epoch": 5.26, "learning_rate": 0.0008973380402633337, "loss": 1.799, "step": 25380 }, { "epoch": 5.26, "learning_rate": 0.000897242629520084, "loss": 1.794, "step": 25385 }, { "epoch": 5.26, "learning_rate": 0.0008971472187768343, "loss": 1.7891, "step": 25390 }, { "epoch": 5.26, "learning_rate": 0.0008970518080335845, "loss": 1.7949, "step": 25395 }, { "epoch": 5.26, "learning_rate": 0.0008969563972903349, "loss": 1.7965, "step": 25400 }, { "epoch": 5.26, "learning_rate": 0.0008968609865470852, "loss": 1.7897, "step": 25405 }, { "epoch": 5.26, "learning_rate": 0.0008967655758038356, "loss": 1.7881, "step": 25410 }, { "epoch": 5.27, "learning_rate": 0.0008966701650605859, "loss": 1.7942, "step": 25415 }, { "epoch": 5.27, "learning_rate": 0.0008965747543173362, "loss": 1.7926, "step": 25420 }, { "epoch": 5.27, "learning_rate": 0.0008964793435740864, "loss": 1.7966, "step": 25425 }, { "epoch": 5.27, "learning_rate": 0.0008963839328308367, "loss": 1.7933, "step": 25430 }, { "epoch": 5.27, "learning_rate": 0.000896288522087587, "loss": 1.795, "step": 25435 }, { "epoch": 5.27, "learning_rate": 0.0008961931113443374, "loss": 1.7904, "step": 25440 }, { "epoch": 5.27, "learning_rate": 0.0008960977006010878, "loss": 1.7917, "step": 25445 }, { "epoch": 5.27, "learning_rate": 0.000896002289857838, "loss": 1.7899, "step": 25450 }, { "epoch": 5.27, "learning_rate": 0.0008959068791145883, "loss": 1.7931, "step": 25455 }, { "epoch": 5.27, "learning_rate": 0.0008958114683713386, "loss": 1.7924, "step": 25460 }, { "epoch": 5.28, "learning_rate": 0.0008957160576280889, "loss": 1.7942, "step": 25465 }, { "epoch": 5.28, "learning_rate": 0.0008956206468848393, "loss": 1.7919, "step": 25470 }, { "epoch": 5.28, "learning_rate": 0.0008955252361415896, "loss": 1.7916, "step": 25475 }, { "epoch": 5.28, "learning_rate": 0.0008954298253983398, "loss": 1.7876, "step": 25480 }, { "epoch": 5.28, "learning_rate": 0.0008953344146550901, "loss": 1.7897, "step": 25485 }, { "epoch": 5.28, "learning_rate": 0.0008952390039118405, "loss": 1.792, "step": 25490 }, { "epoch": 5.28, "learning_rate": 0.0008951435931685908, "loss": 1.7899, "step": 25495 }, { "epoch": 5.28, "learning_rate": 0.0008950481824253412, "loss": 1.7873, "step": 25500 }, { "epoch": 5.28, "learning_rate": 0.0008949527716820915, "loss": 1.7902, "step": 25505 }, { "epoch": 5.28, "learning_rate": 0.0008948573609388417, "loss": 1.7909, "step": 25510 }, { "epoch": 5.29, "learning_rate": 0.000894761950195592, "loss": 1.7957, "step": 25515 }, { "epoch": 5.29, "learning_rate": 0.0008946665394523423, "loss": 1.7917, "step": 25520 }, { "epoch": 5.29, "learning_rate": 0.0008945711287090926, "loss": 1.7884, "step": 25525 }, { "epoch": 5.29, "learning_rate": 0.000894475717965843, "loss": 1.7953, "step": 25530 }, { "epoch": 5.29, "learning_rate": 0.0008943803072225934, "loss": 1.7918, "step": 25535 }, { "epoch": 5.29, "learning_rate": 0.0008942848964793436, "loss": 1.7941, "step": 25540 }, { "epoch": 5.29, "learning_rate": 0.0008941894857360939, "loss": 1.7953, "step": 25545 }, { "epoch": 5.29, "learning_rate": 0.0008940940749928442, "loss": 1.7967, "step": 25550 }, { "epoch": 5.29, "learning_rate": 0.0008939986642495946, "loss": 1.7922, "step": 25555 }, { "epoch": 5.3, "learning_rate": 0.0008939032535063449, "loss": 1.7907, "step": 25560 }, { "epoch": 5.3, "learning_rate": 0.0008938078427630951, "loss": 1.79, "step": 25565 }, { "epoch": 5.3, "learning_rate": 0.0008937124320198454, "loss": 1.7928, "step": 25570 }, { "epoch": 5.3, "learning_rate": 0.0008936170212765957, "loss": 1.7922, "step": 25575 }, { "epoch": 5.3, "learning_rate": 0.000893521610533346, "loss": 1.7924, "step": 25580 }, { "epoch": 5.3, "learning_rate": 0.0008934261997900965, "loss": 1.7874, "step": 25585 }, { "epoch": 5.3, "learning_rate": 0.0008933307890468468, "loss": 1.7943, "step": 25590 }, { "epoch": 5.3, "learning_rate": 0.000893235378303597, "loss": 1.7904, "step": 25595 }, { "epoch": 5.3, "learning_rate": 0.0008931399675603473, "loss": 1.7943, "step": 25600 }, { "epoch": 5.3, "learning_rate": 0.0008930445568170976, "loss": 1.7875, "step": 25605 }, { "epoch": 5.31, "learning_rate": 0.0008929491460738479, "loss": 1.7883, "step": 25610 }, { "epoch": 5.31, "learning_rate": 0.0008928537353305983, "loss": 1.7902, "step": 25615 }, { "epoch": 5.31, "learning_rate": 0.0008927583245873485, "loss": 1.7941, "step": 25620 }, { "epoch": 5.31, "learning_rate": 0.0008926629138440988, "loss": 1.7898, "step": 25625 }, { "epoch": 5.31, "learning_rate": 0.0008925675031008492, "loss": 1.7926, "step": 25630 }, { "epoch": 5.31, "learning_rate": 0.0008924720923575995, "loss": 1.7965, "step": 25635 }, { "epoch": 5.31, "learning_rate": 0.0008923766816143498, "loss": 1.7907, "step": 25640 }, { "epoch": 5.31, "learning_rate": 0.0008922812708711002, "loss": 1.7905, "step": 25645 }, { "epoch": 5.31, "learning_rate": 0.0008921858601278504, "loss": 1.7921, "step": 25650 }, { "epoch": 5.31, "learning_rate": 0.0008920904493846007, "loss": 1.7942, "step": 25655 }, { "epoch": 5.32, "learning_rate": 0.000891995038641351, "loss": 1.7926, "step": 25660 }, { "epoch": 5.32, "learning_rate": 0.0008918996278981013, "loss": 1.7985, "step": 25665 }, { "epoch": 5.32, "learning_rate": 0.0008918042171548516, "loss": 1.7928, "step": 25670 }, { "epoch": 5.32, "learning_rate": 0.000891708806411602, "loss": 1.7947, "step": 25675 }, { "epoch": 5.32, "learning_rate": 0.0008916133956683523, "loss": 1.7912, "step": 25680 }, { "epoch": 5.32, "learning_rate": 0.0008915179849251026, "loss": 1.7926, "step": 25685 }, { "epoch": 5.32, "learning_rate": 0.0008914225741818529, "loss": 1.7902, "step": 25690 }, { "epoch": 5.32, "learning_rate": 0.0008913271634386032, "loss": 1.7932, "step": 25695 }, { "epoch": 5.32, "learning_rate": 0.0008912317526953535, "loss": 1.7941, "step": 25700 }, { "epoch": 5.33, "learning_rate": 0.0008911363419521038, "loss": 1.7919, "step": 25705 }, { "epoch": 5.33, "learning_rate": 0.0008910409312088541, "loss": 1.7911, "step": 25710 }, { "epoch": 5.33, "learning_rate": 0.0008909455204656044, "loss": 1.7977, "step": 25715 }, { "epoch": 5.33, "learning_rate": 0.0008908501097223548, "loss": 1.7894, "step": 25720 }, { "epoch": 5.33, "learning_rate": 0.0008907546989791051, "loss": 1.7893, "step": 25725 }, { "epoch": 5.33, "learning_rate": 0.0008906592882358555, "loss": 1.7936, "step": 25730 }, { "epoch": 5.33, "learning_rate": 0.0008905638774926057, "loss": 1.7956, "step": 25735 }, { "epoch": 5.33, "learning_rate": 0.000890468466749356, "loss": 1.7969, "step": 25740 }, { "epoch": 5.33, "learning_rate": 0.0008903730560061063, "loss": 1.7957, "step": 25745 }, { "epoch": 5.33, "learning_rate": 0.0008902776452628566, "loss": 1.7928, "step": 25750 }, { "epoch": 5.34, "learning_rate": 0.0008901822345196069, "loss": 1.7926, "step": 25755 }, { "epoch": 5.34, "learning_rate": 0.0008900868237763572, "loss": 1.7917, "step": 25760 }, { "epoch": 5.34, "learning_rate": 0.0008899914130331076, "loss": 1.7943, "step": 25765 }, { "epoch": 5.34, "learning_rate": 0.0008898960022898579, "loss": 1.7906, "step": 25770 }, { "epoch": 5.34, "learning_rate": 0.0008898005915466082, "loss": 1.7937, "step": 25775 }, { "epoch": 5.34, "learning_rate": 0.0008897051808033585, "loss": 1.7911, "step": 25780 }, { "epoch": 5.34, "learning_rate": 0.0008896097700601088, "loss": 1.7906, "step": 25785 }, { "epoch": 5.34, "learning_rate": 0.0008895143593168591, "loss": 1.8011, "step": 25790 }, { "epoch": 5.34, "learning_rate": 0.0008894189485736094, "loss": 1.7931, "step": 25795 }, { "epoch": 5.34, "learning_rate": 0.0008893235378303597, "loss": 1.794, "step": 25800 }, { "epoch": 5.35, "learning_rate": 0.00088922812708711, "loss": 1.7822, "step": 25805 }, { "epoch": 5.35, "learning_rate": 0.0008891327163438603, "loss": 1.7931, "step": 25810 }, { "epoch": 5.35, "learning_rate": 0.0008890373056006106, "loss": 1.7915, "step": 25815 }, { "epoch": 5.35, "learning_rate": 0.000888941894857361, "loss": 1.7882, "step": 25820 }, { "epoch": 5.35, "learning_rate": 0.0008888464841141113, "loss": 1.7894, "step": 25825 }, { "epoch": 5.35, "learning_rate": 0.0008887510733708616, "loss": 1.7941, "step": 25830 }, { "epoch": 5.35, "learning_rate": 0.0008886556626276119, "loss": 1.7888, "step": 25835 }, { "epoch": 5.35, "learning_rate": 0.0008885602518843622, "loss": 1.7903, "step": 25840 }, { "epoch": 5.35, "learning_rate": 0.0008884648411411124, "loss": 1.7908, "step": 25845 }, { "epoch": 5.36, "learning_rate": 0.0008883694303978628, "loss": 1.7919, "step": 25850 }, { "epoch": 5.36, "learning_rate": 0.0008882740196546131, "loss": 1.7899, "step": 25855 }, { "epoch": 5.36, "learning_rate": 0.0008881786089113635, "loss": 1.7907, "step": 25860 }, { "epoch": 5.36, "learning_rate": 0.0008880831981681138, "loss": 1.7955, "step": 25865 }, { "epoch": 5.36, "learning_rate": 0.000887987787424864, "loss": 1.7896, "step": 25870 }, { "epoch": 5.36, "learning_rate": 0.0008878923766816143, "loss": 1.793, "step": 25875 }, { "epoch": 5.36, "learning_rate": 0.0008877969659383647, "loss": 1.7907, "step": 25880 }, { "epoch": 5.36, "learning_rate": 0.000887701555195115, "loss": 1.7854, "step": 25885 }, { "epoch": 5.36, "learning_rate": 0.0008876061444518653, "loss": 1.7908, "step": 25890 }, { "epoch": 5.36, "learning_rate": 0.0008875107337086156, "loss": 1.7939, "step": 25895 }, { "epoch": 5.37, "learning_rate": 0.0008874153229653658, "loss": 1.7893, "step": 25900 }, { "epoch": 5.37, "learning_rate": 0.0008873199122221162, "loss": 1.7925, "step": 25905 }, { "epoch": 5.37, "learning_rate": 0.0008872245014788666, "loss": 1.7888, "step": 25910 }, { "epoch": 5.37, "learning_rate": 0.0008871290907356169, "loss": 1.7915, "step": 25915 }, { "epoch": 5.37, "learning_rate": 0.0008870336799923672, "loss": 1.7884, "step": 25920 }, { "epoch": 5.37, "learning_rate": 0.0008869382692491175, "loss": 1.7953, "step": 25925 }, { "epoch": 5.37, "learning_rate": 0.0008868428585058677, "loss": 1.7911, "step": 25930 }, { "epoch": 5.37, "learning_rate": 0.000886747447762618, "loss": 1.7967, "step": 25935 }, { "epoch": 5.37, "learning_rate": 0.0008866520370193684, "loss": 1.7948, "step": 25940 }, { "epoch": 5.37, "learning_rate": 0.0008865566262761187, "loss": 1.7938, "step": 25945 }, { "epoch": 5.38, "learning_rate": 0.0008864612155328691, "loss": 1.7944, "step": 25950 }, { "epoch": 5.38, "learning_rate": 0.0008863658047896193, "loss": 1.7917, "step": 25955 }, { "epoch": 5.38, "learning_rate": 0.0008862703940463696, "loss": 1.7916, "step": 25960 }, { "epoch": 5.38, "learning_rate": 0.00088617498330312, "loss": 1.7922, "step": 25965 }, { "epoch": 5.38, "learning_rate": 0.0008860795725598703, "loss": 1.7928, "step": 25970 }, { "epoch": 5.38, "learning_rate": 0.0008859841618166206, "loss": 1.7961, "step": 25975 }, { "epoch": 5.38, "learning_rate": 0.0008858887510733709, "loss": 1.7942, "step": 25980 }, { "epoch": 5.38, "learning_rate": 0.0008857933403301211, "loss": 1.7888, "step": 25985 }, { "epoch": 5.38, "learning_rate": 0.0008856979295868714, "loss": 1.797, "step": 25990 }, { "epoch": 5.39, "learning_rate": 0.0008856025188436219, "loss": 1.785, "step": 25995 }, { "epoch": 5.39, "learning_rate": 0.0008855071081003722, "loss": 1.7911, "step": 26000 }, { "epoch": 5.39, "learning_rate": 0.0008854116973571225, "loss": 1.7922, "step": 26005 }, { "epoch": 5.39, "learning_rate": 0.0008853162866138728, "loss": 1.7944, "step": 26010 }, { "epoch": 5.39, "learning_rate": 0.000885220875870623, "loss": 1.7927, "step": 26015 }, { "epoch": 5.39, "learning_rate": 0.0008851254651273733, "loss": 1.7869, "step": 26020 }, { "epoch": 5.39, "learning_rate": 0.0008850300543841237, "loss": 1.7969, "step": 26025 }, { "epoch": 5.39, "learning_rate": 0.000884934643640874, "loss": 1.7863, "step": 26030 }, { "epoch": 5.39, "learning_rate": 0.0008848392328976243, "loss": 1.7964, "step": 26035 }, { "epoch": 5.39, "learning_rate": 0.0008847438221543746, "loss": 1.7919, "step": 26040 }, { "epoch": 5.4, "learning_rate": 0.0008846484114111249, "loss": 1.7961, "step": 26045 }, { "epoch": 5.4, "learning_rate": 0.0008845530006678752, "loss": 1.7896, "step": 26050 }, { "epoch": 5.4, "learning_rate": 0.0008844575899246256, "loss": 1.7868, "step": 26055 }, { "epoch": 5.4, "learning_rate": 0.0008843621791813759, "loss": 1.7951, "step": 26060 }, { "epoch": 5.4, "learning_rate": 0.0008842667684381262, "loss": 1.7896, "step": 26065 }, { "epoch": 5.4, "learning_rate": 0.0008841713576948764, "loss": 1.7934, "step": 26070 }, { "epoch": 5.4, "learning_rate": 0.0008840759469516267, "loss": 1.7915, "step": 26075 }, { "epoch": 5.4, "learning_rate": 0.000883980536208377, "loss": 1.7931, "step": 26080 }, { "epoch": 5.4, "learning_rate": 0.0008838851254651274, "loss": 1.7927, "step": 26085 }, { "epoch": 5.41, "learning_rate": 0.0008837897147218778, "loss": 1.7902, "step": 26090 }, { "epoch": 5.41, "learning_rate": 0.000883694303978628, "loss": 1.7889, "step": 26095 }, { "epoch": 5.41, "learning_rate": 0.0008835988932353783, "loss": 1.7925, "step": 26100 }, { "epoch": 5.41, "learning_rate": 0.0008835034824921286, "loss": 1.7883, "step": 26105 }, { "epoch": 5.41, "learning_rate": 0.0008834080717488789, "loss": 1.7929, "step": 26110 }, { "epoch": 5.41, "learning_rate": 0.0008833126610056293, "loss": 1.7925, "step": 26115 }, { "epoch": 5.41, "learning_rate": 0.0008832172502623796, "loss": 1.7865, "step": 26120 }, { "epoch": 5.41, "learning_rate": 0.0008831218395191298, "loss": 1.7935, "step": 26125 }, { "epoch": 5.41, "learning_rate": 0.0008830264287758801, "loss": 1.7966, "step": 26130 }, { "epoch": 5.41, "learning_rate": 0.0008829310180326305, "loss": 1.7911, "step": 26135 }, { "epoch": 5.42, "learning_rate": 0.0008828356072893808, "loss": 1.7921, "step": 26140 }, { "epoch": 5.42, "learning_rate": 0.0008827401965461312, "loss": 1.7921, "step": 26145 }, { "epoch": 5.42, "learning_rate": 0.0008826447858028815, "loss": 1.7915, "step": 26150 }, { "epoch": 5.42, "learning_rate": 0.0008825493750596317, "loss": 1.7924, "step": 26155 }, { "epoch": 5.42, "learning_rate": 0.000882453964316382, "loss": 1.785, "step": 26160 }, { "epoch": 5.42, "learning_rate": 0.0008823585535731323, "loss": 1.7889, "step": 26165 }, { "epoch": 5.42, "learning_rate": 0.0008822631428298827, "loss": 1.7923, "step": 26170 }, { "epoch": 5.42, "learning_rate": 0.000882167732086633, "loss": 1.7884, "step": 26175 }, { "epoch": 5.42, "learning_rate": 0.0008820723213433833, "loss": 1.79, "step": 26180 }, { "epoch": 5.42, "learning_rate": 0.0008819769106001336, "loss": 1.7905, "step": 26185 }, { "epoch": 5.43, "learning_rate": 0.0008818814998568839, "loss": 1.7931, "step": 26190 }, { "epoch": 5.43, "learning_rate": 0.0008817860891136342, "loss": 1.7912, "step": 26195 }, { "epoch": 5.43, "learning_rate": 0.0008816906783703846, "loss": 1.792, "step": 26200 }, { "epoch": 5.43, "learning_rate": 0.0008815952676271349, "loss": 1.788, "step": 26205 }, { "epoch": 5.43, "learning_rate": 0.0008814998568838851, "loss": 1.7928, "step": 26210 }, { "epoch": 5.43, "learning_rate": 0.0008814044461406354, "loss": 1.7921, "step": 26215 }, { "epoch": 5.43, "learning_rate": 0.0008813090353973857, "loss": 1.7891, "step": 26220 }, { "epoch": 5.43, "learning_rate": 0.0008812136246541361, "loss": 1.7854, "step": 26225 }, { "epoch": 5.43, "learning_rate": 0.0008811182139108865, "loss": 1.7957, "step": 26230 }, { "epoch": 5.44, "learning_rate": 0.0008810228031676368, "loss": 1.7908, "step": 26235 }, { "epoch": 5.44, "learning_rate": 0.000880927392424387, "loss": 1.7893, "step": 26240 }, { "epoch": 5.44, "learning_rate": 0.0008808319816811373, "loss": 1.7897, "step": 26245 }, { "epoch": 5.44, "learning_rate": 0.0008807365709378876, "loss": 1.7908, "step": 26250 }, { "epoch": 5.44, "learning_rate": 0.0008806411601946379, "loss": 1.7882, "step": 26255 }, { "epoch": 5.44, "learning_rate": 0.0008805457494513883, "loss": 1.7914, "step": 26260 }, { "epoch": 5.44, "learning_rate": 0.0008804503387081385, "loss": 1.7886, "step": 26265 }, { "epoch": 5.44, "learning_rate": 0.0008803549279648889, "loss": 1.7885, "step": 26270 }, { "epoch": 5.44, "learning_rate": 0.0008802595172216392, "loss": 1.7912, "step": 26275 }, { "epoch": 5.44, "learning_rate": 0.0008801641064783895, "loss": 1.7896, "step": 26280 }, { "epoch": 5.45, "learning_rate": 0.0008800686957351398, "loss": 1.7905, "step": 26285 }, { "epoch": 5.45, "learning_rate": 0.0008799732849918902, "loss": 1.7857, "step": 26290 }, { "epoch": 5.45, "learning_rate": 0.0008798778742486404, "loss": 1.7901, "step": 26295 }, { "epoch": 5.45, "learning_rate": 0.0008797824635053907, "loss": 1.7901, "step": 26300 }, { "epoch": 5.45, "learning_rate": 0.000879687052762141, "loss": 1.7955, "step": 26305 }, { "epoch": 5.45, "learning_rate": 0.0008795916420188913, "loss": 1.7843, "step": 26310 }, { "epoch": 5.45, "learning_rate": 0.0008794962312756416, "loss": 1.7888, "step": 26315 }, { "epoch": 5.45, "learning_rate": 0.000879400820532392, "loss": 1.7879, "step": 26320 }, { "epoch": 5.45, "learning_rate": 0.0008793054097891423, "loss": 1.7912, "step": 26325 }, { "epoch": 5.45, "learning_rate": 0.0008792099990458926, "loss": 1.7912, "step": 26330 }, { "epoch": 5.46, "learning_rate": 0.0008791145883026429, "loss": 1.7888, "step": 26335 }, { "epoch": 5.46, "learning_rate": 0.0008790191775593932, "loss": 1.7918, "step": 26340 }, { "epoch": 5.46, "learning_rate": 0.0008789237668161434, "loss": 1.7969, "step": 26345 }, { "epoch": 5.46, "learning_rate": 0.0008788283560728938, "loss": 1.7904, "step": 26350 }, { "epoch": 5.46, "learning_rate": 0.0008787329453296441, "loss": 1.787, "step": 26355 }, { "epoch": 5.46, "learning_rate": 0.0008786375345863944, "loss": 1.7909, "step": 26360 }, { "epoch": 5.46, "learning_rate": 0.0008785421238431448, "loss": 1.7876, "step": 26365 }, { "epoch": 5.46, "learning_rate": 0.0008784467130998951, "loss": 1.7919, "step": 26370 }, { "epoch": 5.46, "learning_rate": 0.0008783513023566455, "loss": 1.7899, "step": 26375 }, { "epoch": 5.47, "learning_rate": 0.0008782558916133957, "loss": 1.7916, "step": 26380 }, { "epoch": 5.47, "learning_rate": 0.000878160480870146, "loss": 1.7978, "step": 26385 }, { "epoch": 5.47, "learning_rate": 0.0008780650701268963, "loss": 1.7895, "step": 26390 }, { "epoch": 5.47, "learning_rate": 0.0008779696593836466, "loss": 1.7912, "step": 26395 }, { "epoch": 5.47, "learning_rate": 0.0008778742486403969, "loss": 1.7878, "step": 26400 }, { "epoch": 5.47, "learning_rate": 0.0008777788378971472, "loss": 1.7907, "step": 26405 }, { "epoch": 5.47, "learning_rate": 0.0008776834271538976, "loss": 1.7876, "step": 26410 }, { "epoch": 5.47, "learning_rate": 0.0008775880164106479, "loss": 1.7931, "step": 26415 }, { "epoch": 5.47, "learning_rate": 0.0008774926056673982, "loss": 1.787, "step": 26420 }, { "epoch": 5.47, "learning_rate": 0.0008773971949241485, "loss": 1.7919, "step": 26425 }, { "epoch": 5.48, "learning_rate": 0.0008773017841808987, "loss": 1.7881, "step": 26430 }, { "epoch": 5.48, "learning_rate": 0.0008772063734376491, "loss": 1.7892, "step": 26435 }, { "epoch": 5.48, "learning_rate": 0.0008771109626943994, "loss": 1.7886, "step": 26440 }, { "epoch": 5.48, "learning_rate": 0.0008770155519511497, "loss": 1.7892, "step": 26445 }, { "epoch": 5.48, "learning_rate": 0.0008769201412079, "loss": 1.7935, "step": 26450 }, { "epoch": 5.48, "learning_rate": 0.0008768247304646504, "loss": 1.7927, "step": 26455 }, { "epoch": 5.48, "learning_rate": 0.0008767293197214006, "loss": 1.7903, "step": 26460 }, { "epoch": 5.48, "learning_rate": 0.000876633908978151, "loss": 1.7897, "step": 26465 }, { "epoch": 5.48, "learning_rate": 0.0008765384982349013, "loss": 1.7989, "step": 26470 }, { "epoch": 5.48, "learning_rate": 0.0008764430874916516, "loss": 1.7932, "step": 26475 }, { "epoch": 5.49, "learning_rate": 0.0008763476767484019, "loss": 1.7843, "step": 26480 }, { "epoch": 5.49, "learning_rate": 0.0008762522660051521, "loss": 1.7897, "step": 26485 }, { "epoch": 5.49, "learning_rate": 0.0008761568552619024, "loss": 1.7928, "step": 26490 }, { "epoch": 5.49, "learning_rate": 0.0008760614445186528, "loss": 1.7902, "step": 26495 }, { "epoch": 5.49, "learning_rate": 0.0008759660337754032, "loss": 1.7929, "step": 26500 }, { "epoch": 5.49, "learning_rate": 0.0008758706230321535, "loss": 1.7895, "step": 26505 }, { "epoch": 5.49, "learning_rate": 0.0008757752122889038, "loss": 1.788, "step": 26510 }, { "epoch": 5.49, "learning_rate": 0.000875679801545654, "loss": 1.794, "step": 26515 }, { "epoch": 5.49, "learning_rate": 0.0008755843908024043, "loss": 1.7912, "step": 26520 }, { "epoch": 5.5, "learning_rate": 0.0008754889800591547, "loss": 1.794, "step": 26525 }, { "epoch": 5.5, "learning_rate": 0.000875393569315905, "loss": 1.7917, "step": 26530 }, { "epoch": 5.5, "learning_rate": 0.0008752981585726553, "loss": 1.7844, "step": 26535 }, { "epoch": 5.5, "learning_rate": 0.0008752027478294056, "loss": 1.7863, "step": 26540 }, { "epoch": 5.5, "learning_rate": 0.0008751073370861559, "loss": 1.7851, "step": 26545 }, { "epoch": 5.5, "learning_rate": 0.0008750119263429062, "loss": 1.7846, "step": 26550 }, { "epoch": 5.5, "learning_rate": 0.0008749165155996566, "loss": 1.7823, "step": 26555 }, { "epoch": 5.5, "learning_rate": 0.0008748211048564069, "loss": 1.7917, "step": 26560 }, { "epoch": 5.5, "learning_rate": 0.0008747256941131572, "loss": 1.791, "step": 26565 }, { "epoch": 5.5, "learning_rate": 0.0008746302833699074, "loss": 1.806, "step": 26570 }, { "epoch": 5.51, "learning_rate": 0.0008745348726266577, "loss": 1.7973, "step": 26575 }, { "epoch": 5.51, "learning_rate": 0.000874439461883408, "loss": 1.7921, "step": 26580 }, { "epoch": 5.51, "learning_rate": 0.0008743440511401584, "loss": 1.7937, "step": 26585 }, { "epoch": 5.51, "learning_rate": 0.0008742486403969087, "loss": 1.7881, "step": 26590 }, { "epoch": 5.51, "learning_rate": 0.0008741532296536591, "loss": 1.7903, "step": 26595 }, { "epoch": 5.51, "learning_rate": 0.0008740578189104093, "loss": 1.7835, "step": 26600 }, { "epoch": 5.51, "learning_rate": 0.0008739624081671596, "loss": 1.7917, "step": 26605 }, { "epoch": 5.51, "learning_rate": 0.00087386699742391, "loss": 1.7864, "step": 26610 }, { "epoch": 5.51, "learning_rate": 0.0008737715866806603, "loss": 1.788, "step": 26615 }, { "epoch": 5.51, "learning_rate": 0.0008736761759374106, "loss": 1.7843, "step": 26620 }, { "epoch": 5.52, "learning_rate": 0.0008735807651941609, "loss": 1.7949, "step": 26625 }, { "epoch": 5.52, "learning_rate": 0.0008734853544509111, "loss": 1.7917, "step": 26630 }, { "epoch": 5.52, "learning_rate": 0.0008733899437076614, "loss": 1.7878, "step": 26635 }, { "epoch": 5.52, "learning_rate": 0.0008732945329644119, "loss": 1.7897, "step": 26640 }, { "epoch": 5.52, "learning_rate": 0.0008731991222211622, "loss": 1.7903, "step": 26645 }, { "epoch": 5.52, "learning_rate": 0.0008731037114779125, "loss": 1.7885, "step": 26650 }, { "epoch": 5.52, "learning_rate": 0.0008730083007346627, "loss": 1.7841, "step": 26655 }, { "epoch": 5.52, "learning_rate": 0.000872912889991413, "loss": 1.789, "step": 26660 }, { "epoch": 5.52, "learning_rate": 0.0008728174792481633, "loss": 1.7875, "step": 26665 }, { "epoch": 5.53, "learning_rate": 0.0008727220685049137, "loss": 1.791, "step": 26670 }, { "epoch": 5.53, "learning_rate": 0.000872626657761664, "loss": 1.7939, "step": 26675 }, { "epoch": 5.53, "learning_rate": 0.0008725312470184143, "loss": 1.79, "step": 26680 }, { "epoch": 5.53, "learning_rate": 0.0008724358362751646, "loss": 1.7832, "step": 26685 }, { "epoch": 5.53, "learning_rate": 0.0008723404255319149, "loss": 1.7899, "step": 26690 }, { "epoch": 5.53, "learning_rate": 0.0008722450147886652, "loss": 1.786, "step": 26695 }, { "epoch": 5.53, "learning_rate": 0.0008721496040454156, "loss": 1.7878, "step": 26700 }, { "epoch": 5.53, "learning_rate": 0.0008720541933021659, "loss": 1.7865, "step": 26705 }, { "epoch": 5.53, "learning_rate": 0.0008719587825589161, "loss": 1.787, "step": 26710 }, { "epoch": 5.53, "learning_rate": 0.0008718633718156664, "loss": 1.7893, "step": 26715 }, { "epoch": 5.54, "learning_rate": 0.0008717679610724167, "loss": 1.7898, "step": 26720 }, { "epoch": 5.54, "learning_rate": 0.000871672550329167, "loss": 1.7898, "step": 26725 }, { "epoch": 5.54, "learning_rate": 0.0008715771395859175, "loss": 1.784, "step": 26730 }, { "epoch": 5.54, "learning_rate": 0.0008714817288426678, "loss": 1.7834, "step": 26735 }, { "epoch": 5.54, "learning_rate": 0.000871386318099418, "loss": 1.7851, "step": 26740 }, { "epoch": 5.54, "learning_rate": 0.0008712909073561683, "loss": 1.793, "step": 26745 }, { "epoch": 5.54, "learning_rate": 0.0008711954966129186, "loss": 1.7886, "step": 26750 }, { "epoch": 5.54, "learning_rate": 0.0008711000858696689, "loss": 1.7944, "step": 26755 }, { "epoch": 5.54, "learning_rate": 0.0008710046751264193, "loss": 1.7934, "step": 26760 }, { "epoch": 5.54, "learning_rate": 0.0008709092643831696, "loss": 1.7936, "step": 26765 }, { "epoch": 5.55, "learning_rate": 0.0008708138536399198, "loss": 1.7888, "step": 26770 }, { "epoch": 5.55, "learning_rate": 0.0008707184428966702, "loss": 1.794, "step": 26775 }, { "epoch": 5.55, "learning_rate": 0.0008706230321534205, "loss": 1.7884, "step": 26780 }, { "epoch": 5.55, "learning_rate": 0.0008705276214101709, "loss": 1.7855, "step": 26785 }, { "epoch": 5.55, "learning_rate": 0.0008704322106669212, "loss": 1.7908, "step": 26790 }, { "epoch": 5.55, "learning_rate": 0.0008703367999236714, "loss": 1.7897, "step": 26795 }, { "epoch": 5.55, "learning_rate": 0.0008702413891804217, "loss": 1.7909, "step": 26800 }, { "epoch": 5.55, "learning_rate": 0.000870145978437172, "loss": 1.7877, "step": 26805 }, { "epoch": 5.55, "learning_rate": 0.0008700505676939223, "loss": 1.7947, "step": 26810 }, { "epoch": 5.56, "learning_rate": 0.0008699551569506727, "loss": 1.7871, "step": 26815 }, { "epoch": 5.56, "learning_rate": 0.000869859746207423, "loss": 1.7868, "step": 26820 }, { "epoch": 5.56, "learning_rate": 0.0008697643354641733, "loss": 1.7907, "step": 26825 }, { "epoch": 5.56, "learning_rate": 0.0008696689247209236, "loss": 1.7884, "step": 26830 }, { "epoch": 5.56, "learning_rate": 0.0008695735139776739, "loss": 1.7825, "step": 26835 }, { "epoch": 5.56, "learning_rate": 0.0008694781032344242, "loss": 1.7867, "step": 26840 }, { "epoch": 5.56, "learning_rate": 0.0008693826924911746, "loss": 1.7875, "step": 26845 }, { "epoch": 5.56, "learning_rate": 0.0008692872817479248, "loss": 1.7838, "step": 26850 }, { "epoch": 5.56, "learning_rate": 0.0008691918710046751, "loss": 1.79, "step": 26855 }, { "epoch": 5.56, "learning_rate": 0.0008690964602614254, "loss": 1.7906, "step": 26860 }, { "epoch": 5.57, "learning_rate": 0.0008690010495181757, "loss": 1.7895, "step": 26865 }, { "epoch": 5.57, "learning_rate": 0.0008689056387749261, "loss": 1.7924, "step": 26870 }, { "epoch": 5.57, "learning_rate": 0.0008688102280316765, "loss": 1.7847, "step": 26875 }, { "epoch": 5.57, "learning_rate": 0.0008687148172884267, "loss": 1.792, "step": 26880 }, { "epoch": 5.57, "learning_rate": 0.000868619406545177, "loss": 1.7877, "step": 26885 }, { "epoch": 5.57, "learning_rate": 0.0008685239958019273, "loss": 1.7845, "step": 26890 }, { "epoch": 5.57, "learning_rate": 0.0008684285850586776, "loss": 1.7863, "step": 26895 }, { "epoch": 5.57, "learning_rate": 0.0008683331743154279, "loss": 1.7896, "step": 26900 }, { "epoch": 5.57, "learning_rate": 0.0008682377635721783, "loss": 1.7889, "step": 26905 }, { "epoch": 5.57, "learning_rate": 0.0008681423528289285, "loss": 1.7896, "step": 26910 }, { "epoch": 5.58, "learning_rate": 0.0008680469420856789, "loss": 1.7876, "step": 26915 }, { "epoch": 5.58, "learning_rate": 0.0008679515313424292, "loss": 1.7866, "step": 26920 }, { "epoch": 5.58, "learning_rate": 0.0008678561205991795, "loss": 1.7876, "step": 26925 }, { "epoch": 5.58, "learning_rate": 0.0008677607098559298, "loss": 1.7909, "step": 26930 }, { "epoch": 5.58, "learning_rate": 0.0008676652991126801, "loss": 1.7914, "step": 26935 }, { "epoch": 5.58, "learning_rate": 0.0008675698883694304, "loss": 1.7883, "step": 26940 }, { "epoch": 5.58, "learning_rate": 0.0008674744776261807, "loss": 1.7888, "step": 26945 }, { "epoch": 5.58, "learning_rate": 0.000867379066882931, "loss": 1.7839, "step": 26950 }, { "epoch": 5.58, "learning_rate": 0.0008672836561396813, "loss": 1.7915, "step": 26955 }, { "epoch": 5.59, "learning_rate": 0.0008671882453964317, "loss": 1.7909, "step": 26960 }, { "epoch": 5.59, "learning_rate": 0.000867092834653182, "loss": 1.7911, "step": 26965 }, { "epoch": 5.59, "learning_rate": 0.0008669974239099323, "loss": 1.7875, "step": 26970 }, { "epoch": 5.59, "learning_rate": 0.0008669020131666826, "loss": 1.7894, "step": 26975 }, { "epoch": 5.59, "learning_rate": 0.0008668066024234329, "loss": 1.7904, "step": 26980 }, { "epoch": 5.59, "learning_rate": 0.0008667111916801832, "loss": 1.7894, "step": 26985 }, { "epoch": 5.59, "learning_rate": 0.0008666157809369334, "loss": 1.7916, "step": 26990 }, { "epoch": 5.59, "learning_rate": 0.0008665203701936838, "loss": 1.7833, "step": 26995 }, { "epoch": 5.59, "learning_rate": 0.0008664249594504341, "loss": 1.7875, "step": 27000 }, { "epoch": 5.59, "eval_accuracy": 0.5343790849673202, "eval_loss": 1.9587690830230713, "eval_runtime": 0.5009, "eval_samples_per_second": 299.455, "eval_steps_per_second": 1.996, "step": 27000 }, { "epoch": 5.59, "learning_rate": 0.0008663295487071845, "loss": 1.7854, "step": 27005 }, { "epoch": 5.6, "learning_rate": 0.0008662341379639348, "loss": 1.7829, "step": 27010 }, { "epoch": 5.6, "learning_rate": 0.0008661387272206851, "loss": 1.7886, "step": 27015 }, { "epoch": 5.6, "learning_rate": 0.0008660433164774354, "loss": 1.7892, "step": 27020 }, { "epoch": 5.6, "learning_rate": 0.0008659479057341857, "loss": 1.7895, "step": 27025 }, { "epoch": 5.6, "learning_rate": 0.000865852494990936, "loss": 1.7881, "step": 27030 }, { "epoch": 5.6, "learning_rate": 0.0008657570842476863, "loss": 1.7836, "step": 27035 }, { "epoch": 5.6, "learning_rate": 0.0008656616735044366, "loss": 1.7858, "step": 27040 }, { "epoch": 5.6, "learning_rate": 0.0008655662627611868, "loss": 1.7896, "step": 27045 }, { "epoch": 5.6, "learning_rate": 0.0008654708520179372, "loss": 1.7869, "step": 27050 }, { "epoch": 5.6, "learning_rate": 0.0008653754412746876, "loss": 1.7798, "step": 27055 }, { "epoch": 5.61, "learning_rate": 0.0008652800305314379, "loss": 1.7836, "step": 27060 }, { "epoch": 5.61, "learning_rate": 0.0008651846197881882, "loss": 1.7811, "step": 27065 }, { "epoch": 5.61, "learning_rate": 0.0008650892090449385, "loss": 1.7925, "step": 27070 }, { "epoch": 5.61, "learning_rate": 0.0008649937983016887, "loss": 1.7925, "step": 27075 }, { "epoch": 5.61, "learning_rate": 0.0008648983875584391, "loss": 1.7932, "step": 27080 }, { "epoch": 5.61, "learning_rate": 0.0008648029768151894, "loss": 1.7864, "step": 27085 }, { "epoch": 5.61, "learning_rate": 0.0008647075660719397, "loss": 1.7896, "step": 27090 }, { "epoch": 5.61, "learning_rate": 0.00086461215532869, "loss": 1.786, "step": 27095 }, { "epoch": 5.61, "learning_rate": 0.0008645167445854404, "loss": 1.7854, "step": 27100 }, { "epoch": 5.62, "learning_rate": 0.0008644213338421906, "loss": 1.788, "step": 27105 }, { "epoch": 5.62, "learning_rate": 0.000864325923098941, "loss": 1.783, "step": 27110 }, { "epoch": 5.62, "learning_rate": 0.0008642305123556913, "loss": 1.784, "step": 27115 }, { "epoch": 5.62, "learning_rate": 0.0008641351016124416, "loss": 1.7841, "step": 27120 }, { "epoch": 5.62, "learning_rate": 0.0008640396908691919, "loss": 1.7849, "step": 27125 }, { "epoch": 5.62, "learning_rate": 0.0008639442801259421, "loss": 1.7888, "step": 27130 }, { "epoch": 5.62, "learning_rate": 0.0008638488693826924, "loss": 1.7879, "step": 27135 }, { "epoch": 5.62, "learning_rate": 0.0008637534586394428, "loss": 1.7839, "step": 27140 }, { "epoch": 5.62, "learning_rate": 0.0008636580478961932, "loss": 1.7883, "step": 27145 }, { "epoch": 5.62, "learning_rate": 0.0008635626371529435, "loss": 1.7915, "step": 27150 }, { "epoch": 5.63, "learning_rate": 0.0008634672264096938, "loss": 1.7834, "step": 27155 }, { "epoch": 5.63, "learning_rate": 0.000863371815666444, "loss": 1.7859, "step": 27160 }, { "epoch": 5.63, "learning_rate": 0.0008632764049231943, "loss": 1.7845, "step": 27165 }, { "epoch": 5.63, "learning_rate": 0.0008631809941799447, "loss": 1.7881, "step": 27170 }, { "epoch": 5.63, "learning_rate": 0.000863085583436695, "loss": 1.7827, "step": 27175 }, { "epoch": 5.63, "learning_rate": 0.0008629901726934453, "loss": 1.7827, "step": 27180 }, { "epoch": 5.63, "learning_rate": 0.0008628947619501955, "loss": 1.7821, "step": 27185 }, { "epoch": 5.63, "learning_rate": 0.0008627993512069459, "loss": 1.7887, "step": 27190 }, { "epoch": 5.63, "learning_rate": 0.0008627039404636962, "loss": 1.7861, "step": 27195 }, { "epoch": 5.63, "learning_rate": 0.0008626085297204466, "loss": 1.7859, "step": 27200 }, { "epoch": 5.64, "learning_rate": 0.0008625131189771969, "loss": 1.7868, "step": 27205 }, { "epoch": 5.64, "learning_rate": 0.0008624177082339472, "loss": 1.7894, "step": 27210 }, { "epoch": 5.64, "learning_rate": 0.0008623222974906974, "loss": 1.7893, "step": 27215 }, { "epoch": 5.64, "learning_rate": 0.0008622268867474477, "loss": 1.7852, "step": 27220 }, { "epoch": 5.64, "learning_rate": 0.0008621314760041981, "loss": 1.7933, "step": 27225 }, { "epoch": 5.64, "learning_rate": 0.0008620360652609484, "loss": 1.7835, "step": 27230 }, { "epoch": 5.64, "learning_rate": 0.0008619406545176988, "loss": 1.7908, "step": 27235 }, { "epoch": 5.64, "learning_rate": 0.0008618452437744491, "loss": 1.7833, "step": 27240 }, { "epoch": 5.64, "learning_rate": 0.0008617498330311993, "loss": 1.7824, "step": 27245 }, { "epoch": 5.65, "learning_rate": 0.0008616544222879496, "loss": 1.784, "step": 27250 }, { "epoch": 5.65, "learning_rate": 0.0008615590115447, "loss": 1.7873, "step": 27255 }, { "epoch": 5.65, "learning_rate": 0.0008614636008014503, "loss": 1.7848, "step": 27260 }, { "epoch": 5.65, "learning_rate": 0.0008613681900582006, "loss": 1.7881, "step": 27265 }, { "epoch": 5.65, "learning_rate": 0.0008612727793149508, "loss": 1.7881, "step": 27270 }, { "epoch": 5.65, "learning_rate": 0.0008611773685717011, "loss": 1.7837, "step": 27275 }, { "epoch": 5.65, "learning_rate": 0.0008610819578284515, "loss": 1.7878, "step": 27280 }, { "epoch": 5.65, "learning_rate": 0.0008609865470852019, "loss": 1.7818, "step": 27285 }, { "epoch": 5.65, "learning_rate": 0.0008608911363419522, "loss": 1.7824, "step": 27290 }, { "epoch": 5.65, "learning_rate": 0.0008607957255987025, "loss": 1.7878, "step": 27295 }, { "epoch": 5.66, "learning_rate": 0.0008607003148554527, "loss": 1.7861, "step": 27300 }, { "epoch": 5.66, "learning_rate": 0.000860604904112203, "loss": 1.7843, "step": 27305 }, { "epoch": 5.66, "learning_rate": 0.0008605094933689533, "loss": 1.7879, "step": 27310 }, { "epoch": 5.66, "learning_rate": 0.0008604140826257037, "loss": 1.7935, "step": 27315 }, { "epoch": 5.66, "learning_rate": 0.000860318671882454, "loss": 1.7906, "step": 27320 }, { "epoch": 5.66, "learning_rate": 0.0008602232611392042, "loss": 1.7885, "step": 27325 }, { "epoch": 5.66, "learning_rate": 0.0008601278503959546, "loss": 1.7851, "step": 27330 }, { "epoch": 5.66, "learning_rate": 0.0008600324396527049, "loss": 1.7856, "step": 27335 }, { "epoch": 5.66, "learning_rate": 0.0008599370289094552, "loss": 1.7832, "step": 27340 }, { "epoch": 5.67, "learning_rate": 0.0008598416181662056, "loss": 1.7843, "step": 27345 }, { "epoch": 5.67, "learning_rate": 0.0008597462074229559, "loss": 1.7873, "step": 27350 }, { "epoch": 5.67, "learning_rate": 0.0008596507966797061, "loss": 1.7859, "step": 27355 }, { "epoch": 5.67, "learning_rate": 0.0008595553859364564, "loss": 1.7912, "step": 27360 }, { "epoch": 5.67, "learning_rate": 0.0008594599751932067, "loss": 1.7854, "step": 27365 }, { "epoch": 5.67, "learning_rate": 0.000859364564449957, "loss": 1.7858, "step": 27370 }, { "epoch": 5.67, "learning_rate": 0.0008592691537067075, "loss": 1.7826, "step": 27375 }, { "epoch": 5.67, "learning_rate": 0.0008591737429634578, "loss": 1.7882, "step": 27380 }, { "epoch": 5.67, "learning_rate": 0.000859078332220208, "loss": 1.7854, "step": 27385 }, { "epoch": 5.67, "learning_rate": 0.0008589829214769583, "loss": 1.784, "step": 27390 }, { "epoch": 5.68, "learning_rate": 0.0008588875107337086, "loss": 1.7881, "step": 27395 }, { "epoch": 5.68, "learning_rate": 0.0008587920999904589, "loss": 1.7815, "step": 27400 }, { "epoch": 5.68, "learning_rate": 0.0008586966892472093, "loss": 1.7875, "step": 27405 }, { "epoch": 5.68, "learning_rate": 0.0008586012785039595, "loss": 1.7863, "step": 27410 }, { "epoch": 5.68, "learning_rate": 0.0008585058677607098, "loss": 1.7813, "step": 27415 }, { "epoch": 5.68, "learning_rate": 0.0008584104570174602, "loss": 1.7861, "step": 27420 }, { "epoch": 5.68, "learning_rate": 0.0008583150462742105, "loss": 1.7854, "step": 27425 }, { "epoch": 5.68, "learning_rate": 0.0008582196355309609, "loss": 1.7854, "step": 27430 }, { "epoch": 5.68, "learning_rate": 0.0008581242247877112, "loss": 1.7843, "step": 27435 }, { "epoch": 5.68, "learning_rate": 0.0008580288140444614, "loss": 1.7877, "step": 27440 }, { "epoch": 5.69, "learning_rate": 0.0008579334033012117, "loss": 1.7853, "step": 27445 }, { "epoch": 5.69, "learning_rate": 0.000857837992557962, "loss": 1.7851, "step": 27450 }, { "epoch": 5.69, "learning_rate": 0.0008577425818147123, "loss": 1.7799, "step": 27455 }, { "epoch": 5.69, "learning_rate": 0.0008576471710714627, "loss": 1.7836, "step": 27460 }, { "epoch": 5.69, "learning_rate": 0.0008575517603282131, "loss": 1.7862, "step": 27465 }, { "epoch": 5.69, "learning_rate": 0.0008574563495849633, "loss": 1.7875, "step": 27470 }, { "epoch": 5.69, "learning_rate": 0.0008573609388417136, "loss": 1.7885, "step": 27475 }, { "epoch": 5.69, "learning_rate": 0.0008572655280984639, "loss": 1.7864, "step": 27480 }, { "epoch": 5.69, "learning_rate": 0.0008571701173552142, "loss": 1.7887, "step": 27485 }, { "epoch": 5.7, "learning_rate": 0.0008570747066119646, "loss": 1.7867, "step": 27490 }, { "epoch": 5.7, "learning_rate": 0.0008569792958687148, "loss": 1.7853, "step": 27495 }, { "epoch": 5.7, "learning_rate": 0.0008568838851254651, "loss": 1.7908, "step": 27500 }, { "epoch": 5.7, "learning_rate": 0.0008567884743822154, "loss": 1.7916, "step": 27505 }, { "epoch": 5.7, "learning_rate": 0.0008566930636389658, "loss": 1.7838, "step": 27510 }, { "epoch": 5.7, "learning_rate": 0.0008565976528957161, "loss": 1.783, "step": 27515 }, { "epoch": 5.7, "learning_rate": 0.0008565022421524665, "loss": 1.7882, "step": 27520 }, { "epoch": 5.7, "learning_rate": 0.0008564068314092167, "loss": 1.7823, "step": 27525 }, { "epoch": 5.7, "learning_rate": 0.000856311420665967, "loss": 1.788, "step": 27530 }, { "epoch": 5.7, "learning_rate": 0.0008562160099227173, "loss": 1.7883, "step": 27535 }, { "epoch": 5.71, "learning_rate": 0.0008561205991794676, "loss": 1.7859, "step": 27540 }, { "epoch": 5.71, "learning_rate": 0.0008560251884362179, "loss": 1.7874, "step": 27545 }, { "epoch": 5.71, "learning_rate": 0.0008559297776929682, "loss": 1.7894, "step": 27550 }, { "epoch": 5.71, "learning_rate": 0.0008558343669497185, "loss": 1.7894, "step": 27555 }, { "epoch": 5.71, "learning_rate": 0.0008557389562064689, "loss": 1.788, "step": 27560 }, { "epoch": 5.71, "learning_rate": 0.0008556435454632192, "loss": 1.7868, "step": 27565 }, { "epoch": 5.71, "learning_rate": 0.0008555481347199695, "loss": 1.7872, "step": 27570 }, { "epoch": 5.71, "learning_rate": 0.0008554527239767198, "loss": 1.7837, "step": 27575 }, { "epoch": 5.71, "learning_rate": 0.0008553573132334701, "loss": 1.7853, "step": 27580 }, { "epoch": 5.71, "learning_rate": 0.0008552619024902204, "loss": 1.7867, "step": 27585 }, { "epoch": 5.72, "learning_rate": 0.0008551664917469707, "loss": 1.7871, "step": 27590 }, { "epoch": 5.72, "learning_rate": 0.000855071081003721, "loss": 1.7844, "step": 27595 }, { "epoch": 5.72, "learning_rate": 0.0008549756702604713, "loss": 1.7827, "step": 27600 }, { "epoch": 5.72, "learning_rate": 0.0008548802595172217, "loss": 1.7887, "step": 27605 }, { "epoch": 5.72, "learning_rate": 0.000854784848773972, "loss": 1.7832, "step": 27610 }, { "epoch": 5.72, "learning_rate": 0.0008546894380307223, "loss": 1.7815, "step": 27615 }, { "epoch": 5.72, "learning_rate": 0.0008545940272874726, "loss": 1.79, "step": 27620 }, { "epoch": 5.72, "learning_rate": 0.0008544986165442229, "loss": 1.7865, "step": 27625 }, { "epoch": 5.72, "learning_rate": 0.0008544032058009732, "loss": 1.7933, "step": 27630 }, { "epoch": 5.73, "learning_rate": 0.0008543077950577234, "loss": 1.7902, "step": 27635 }, { "epoch": 5.73, "learning_rate": 0.0008542123843144738, "loss": 1.7866, "step": 27640 }, { "epoch": 5.73, "learning_rate": 0.0008541169735712241, "loss": 1.7976, "step": 27645 }, { "epoch": 5.73, "learning_rate": 0.0008540215628279745, "loss": 1.7915, "step": 27650 }, { "epoch": 5.73, "learning_rate": 0.0008539261520847248, "loss": 1.7883, "step": 27655 }, { "epoch": 5.73, "learning_rate": 0.000853830741341475, "loss": 1.786, "step": 27660 }, { "epoch": 5.73, "learning_rate": 0.0008537353305982254, "loss": 1.7847, "step": 27665 }, { "epoch": 5.73, "learning_rate": 0.0008536399198549757, "loss": 1.7872, "step": 27670 }, { "epoch": 5.73, "learning_rate": 0.000853544509111726, "loss": 1.7824, "step": 27675 }, { "epoch": 5.73, "learning_rate": 0.0008534490983684763, "loss": 1.7858, "step": 27680 }, { "epoch": 5.74, "learning_rate": 0.0008533536876252266, "loss": 1.7821, "step": 27685 }, { "epoch": 5.74, "learning_rate": 0.0008532582768819768, "loss": 1.7817, "step": 27690 }, { "epoch": 5.74, "learning_rate": 0.0008531628661387273, "loss": 1.7816, "step": 27695 }, { "epoch": 5.74, "learning_rate": 0.0008530674553954776, "loss": 1.7879, "step": 27700 }, { "epoch": 5.74, "learning_rate": 0.0008529720446522279, "loss": 1.7833, "step": 27705 }, { "epoch": 5.74, "learning_rate": 0.0008528766339089782, "loss": 1.7846, "step": 27710 }, { "epoch": 5.74, "learning_rate": 0.0008527812231657285, "loss": 1.7898, "step": 27715 }, { "epoch": 5.74, "learning_rate": 0.0008526858124224787, "loss": 1.7877, "step": 27720 }, { "epoch": 5.74, "learning_rate": 0.0008525904016792291, "loss": 1.7859, "step": 27725 }, { "epoch": 5.74, "learning_rate": 0.0008524949909359794, "loss": 1.7859, "step": 27730 }, { "epoch": 5.75, "learning_rate": 0.0008523995801927297, "loss": 1.7824, "step": 27735 }, { "epoch": 5.75, "learning_rate": 0.0008523041694494801, "loss": 1.7863, "step": 27740 }, { "epoch": 5.75, "learning_rate": 0.0008522087587062304, "loss": 1.7834, "step": 27745 }, { "epoch": 5.75, "learning_rate": 0.0008521133479629806, "loss": 1.7844, "step": 27750 }, { "epoch": 5.75, "learning_rate": 0.000852017937219731, "loss": 1.7896, "step": 27755 }, { "epoch": 5.75, "learning_rate": 0.0008519225264764813, "loss": 1.783, "step": 27760 }, { "epoch": 5.75, "learning_rate": 0.0008518271157332316, "loss": 1.7872, "step": 27765 }, { "epoch": 5.75, "learning_rate": 0.0008517317049899819, "loss": 1.7871, "step": 27770 }, { "epoch": 5.75, "learning_rate": 0.0008516362942467321, "loss": 1.7823, "step": 27775 }, { "epoch": 5.76, "learning_rate": 0.0008515408835034824, "loss": 1.7837, "step": 27780 }, { "epoch": 5.76, "learning_rate": 0.0008514454727602329, "loss": 1.7814, "step": 27785 }, { "epoch": 5.76, "learning_rate": 0.0008513500620169832, "loss": 1.7856, "step": 27790 }, { "epoch": 5.76, "learning_rate": 0.0008512546512737335, "loss": 1.7857, "step": 27795 }, { "epoch": 5.76, "learning_rate": 0.0008511592405304838, "loss": 1.7855, "step": 27800 }, { "epoch": 5.76, "learning_rate": 0.000851063829787234, "loss": 1.784, "step": 27805 }, { "epoch": 5.76, "learning_rate": 0.0008509684190439843, "loss": 1.784, "step": 27810 }, { "epoch": 5.76, "learning_rate": 0.0008508730083007347, "loss": 1.7827, "step": 27815 }, { "epoch": 5.76, "learning_rate": 0.000850777597557485, "loss": 1.7859, "step": 27820 }, { "epoch": 5.76, "learning_rate": 0.0008506821868142353, "loss": 1.7851, "step": 27825 }, { "epoch": 5.77, "learning_rate": 0.0008505867760709855, "loss": 1.7848, "step": 27830 }, { "epoch": 5.77, "learning_rate": 0.0008504913653277359, "loss": 1.7851, "step": 27835 }, { "epoch": 5.77, "learning_rate": 0.0008503959545844862, "loss": 1.7882, "step": 27840 }, { "epoch": 5.77, "learning_rate": 0.0008503005438412366, "loss": 1.7834, "step": 27845 }, { "epoch": 5.77, "learning_rate": 0.0008502051330979869, "loss": 1.7873, "step": 27850 }, { "epoch": 5.77, "learning_rate": 0.0008501097223547372, "loss": 1.7833, "step": 27855 }, { "epoch": 5.77, "learning_rate": 0.0008500143116114874, "loss": 1.7894, "step": 27860 }, { "epoch": 5.77, "learning_rate": 0.0008499189008682377, "loss": 1.7824, "step": 27865 }, { "epoch": 5.77, "learning_rate": 0.0008498234901249881, "loss": 1.7828, "step": 27870 }, { "epoch": 5.77, "learning_rate": 0.0008497280793817384, "loss": 1.7845, "step": 27875 }, { "epoch": 5.78, "learning_rate": 0.0008496326686384888, "loss": 1.7792, "step": 27880 }, { "epoch": 5.78, "learning_rate": 0.000849537257895239, "loss": 1.7828, "step": 27885 }, { "epoch": 5.78, "learning_rate": 0.0008494418471519893, "loss": 1.7855, "step": 27890 }, { "epoch": 5.78, "learning_rate": 0.0008493464364087396, "loss": 1.7846, "step": 27895 }, { "epoch": 5.78, "learning_rate": 0.00084925102566549, "loss": 1.782, "step": 27900 }, { "epoch": 5.78, "learning_rate": 0.0008491556149222403, "loss": 1.7832, "step": 27905 }, { "epoch": 5.78, "learning_rate": 0.0008490602041789906, "loss": 1.7908, "step": 27910 }, { "epoch": 5.78, "learning_rate": 0.0008489647934357408, "loss": 1.7857, "step": 27915 }, { "epoch": 5.78, "learning_rate": 0.0008488693826924911, "loss": 1.7838, "step": 27920 }, { "epoch": 5.79, "learning_rate": 0.0008487739719492415, "loss": 1.7908, "step": 27925 }, { "epoch": 5.79, "learning_rate": 0.0008486785612059919, "loss": 1.7813, "step": 27930 }, { "epoch": 5.79, "learning_rate": 0.0008485831504627422, "loss": 1.7856, "step": 27935 }, { "epoch": 5.79, "learning_rate": 0.0008484877397194925, "loss": 1.7842, "step": 27940 }, { "epoch": 5.79, "learning_rate": 0.0008483923289762427, "loss": 1.7847, "step": 27945 }, { "epoch": 5.79, "learning_rate": 0.000848296918232993, "loss": 1.7816, "step": 27950 }, { "epoch": 5.79, "learning_rate": 0.0008482015074897433, "loss": 1.7851, "step": 27955 }, { "epoch": 5.79, "learning_rate": 0.0008481060967464937, "loss": 1.7845, "step": 27960 }, { "epoch": 5.79, "learning_rate": 0.000848010686003244, "loss": 1.7836, "step": 27965 }, { "epoch": 5.79, "learning_rate": 0.0008479152752599944, "loss": 1.7849, "step": 27970 }, { "epoch": 5.8, "learning_rate": 0.0008478198645167446, "loss": 1.7868, "step": 27975 }, { "epoch": 5.8, "learning_rate": 0.0008477244537734949, "loss": 1.7837, "step": 27980 }, { "epoch": 5.8, "learning_rate": 0.0008476290430302452, "loss": 1.78, "step": 27985 }, { "epoch": 5.8, "learning_rate": 0.0008475336322869956, "loss": 1.7778, "step": 27990 }, { "epoch": 5.8, "learning_rate": 0.0008474382215437459, "loss": 1.7775, "step": 27995 }, { "epoch": 5.8, "learning_rate": 0.0008473428108004961, "loss": 1.7852, "step": 28000 }, { "epoch": 5.8, "learning_rate": 0.0008472474000572464, "loss": 1.7819, "step": 28005 }, { "epoch": 5.8, "learning_rate": 0.0008471519893139967, "loss": 1.7864, "step": 28010 }, { "epoch": 5.8, "learning_rate": 0.0008470565785707471, "loss": 1.7855, "step": 28015 }, { "epoch": 5.8, "learning_rate": 0.0008469611678274975, "loss": 1.7857, "step": 28020 }, { "epoch": 5.81, "learning_rate": 0.0008468657570842478, "loss": 1.7789, "step": 28025 }, { "epoch": 5.81, "learning_rate": 0.000846770346340998, "loss": 1.7881, "step": 28030 }, { "epoch": 5.81, "learning_rate": 0.0008466749355977483, "loss": 1.7873, "step": 28035 }, { "epoch": 5.81, "learning_rate": 0.0008465795248544986, "loss": 1.7815, "step": 28040 }, { "epoch": 5.81, "learning_rate": 0.0008464841141112489, "loss": 1.785, "step": 28045 }, { "epoch": 5.81, "learning_rate": 0.0008463887033679993, "loss": 1.7847, "step": 28050 }, { "epoch": 5.81, "learning_rate": 0.0008462932926247495, "loss": 1.7819, "step": 28055 }, { "epoch": 5.81, "learning_rate": 0.0008461978818814998, "loss": 1.7876, "step": 28060 }, { "epoch": 5.81, "learning_rate": 0.0008461024711382502, "loss": 1.7847, "step": 28065 }, { "epoch": 5.82, "learning_rate": 0.0008460070603950005, "loss": 1.7905, "step": 28070 }, { "epoch": 5.82, "learning_rate": 0.0008459116496517509, "loss": 1.7867, "step": 28075 }, { "epoch": 5.82, "learning_rate": 0.0008458162389085012, "loss": 1.7873, "step": 28080 }, { "epoch": 5.82, "learning_rate": 0.0008457208281652514, "loss": 1.7838, "step": 28085 }, { "epoch": 5.82, "learning_rate": 0.0008456254174220017, "loss": 1.7835, "step": 28090 }, { "epoch": 5.82, "learning_rate": 0.000845530006678752, "loss": 1.7814, "step": 28095 }, { "epoch": 5.82, "learning_rate": 0.0008454345959355023, "loss": 1.7889, "step": 28100 }, { "epoch": 5.82, "learning_rate": 0.0008453391851922527, "loss": 1.7812, "step": 28105 }, { "epoch": 5.82, "learning_rate": 0.000845243774449003, "loss": 1.7761, "step": 28110 }, { "epoch": 5.82, "learning_rate": 0.0008451483637057533, "loss": 1.785, "step": 28115 }, { "epoch": 5.83, "learning_rate": 0.0008450529529625036, "loss": 1.782, "step": 28120 }, { "epoch": 5.83, "learning_rate": 0.0008449575422192539, "loss": 1.789, "step": 28125 }, { "epoch": 5.83, "learning_rate": 0.0008448621314760042, "loss": 1.7819, "step": 28130 }, { "epoch": 5.83, "learning_rate": 0.0008447667207327546, "loss": 1.7881, "step": 28135 }, { "epoch": 5.83, "learning_rate": 0.0008446713099895048, "loss": 1.7866, "step": 28140 }, { "epoch": 5.83, "learning_rate": 0.0008445758992462551, "loss": 1.7854, "step": 28145 }, { "epoch": 5.83, "learning_rate": 0.0008444804885030054, "loss": 1.7831, "step": 28150 }, { "epoch": 5.83, "learning_rate": 0.0008443850777597558, "loss": 1.781, "step": 28155 }, { "epoch": 5.83, "learning_rate": 0.0008442896670165061, "loss": 1.7908, "step": 28160 }, { "epoch": 5.83, "learning_rate": 0.0008441942562732565, "loss": 1.7868, "step": 28165 }, { "epoch": 5.84, "learning_rate": 0.0008440988455300067, "loss": 1.7882, "step": 28170 }, { "epoch": 5.84, "learning_rate": 0.000844003434786757, "loss": 1.7874, "step": 28175 }, { "epoch": 5.84, "learning_rate": 0.0008439080240435073, "loss": 1.784, "step": 28180 }, { "epoch": 5.84, "learning_rate": 0.0008438126133002576, "loss": 1.7856, "step": 28185 }, { "epoch": 5.84, "learning_rate": 0.0008437172025570079, "loss": 1.783, "step": 28190 }, { "epoch": 5.84, "learning_rate": 0.0008436217918137582, "loss": 1.7827, "step": 28195 }, { "epoch": 5.84, "learning_rate": 0.0008435263810705086, "loss": 1.7775, "step": 28200 }, { "epoch": 5.84, "learning_rate": 0.0008434309703272589, "loss": 1.7819, "step": 28205 }, { "epoch": 5.84, "learning_rate": 0.0008433355595840092, "loss": 1.7818, "step": 28210 }, { "epoch": 5.85, "learning_rate": 0.0008432401488407595, "loss": 1.7867, "step": 28215 }, { "epoch": 5.85, "learning_rate": 0.0008431447380975098, "loss": 1.7786, "step": 28220 }, { "epoch": 5.85, "learning_rate": 0.0008430493273542601, "loss": 1.7866, "step": 28225 }, { "epoch": 5.85, "learning_rate": 0.0008429539166110104, "loss": 1.7836, "step": 28230 }, { "epoch": 5.85, "learning_rate": 0.0008428585058677607, "loss": 1.7837, "step": 28235 }, { "epoch": 5.85, "learning_rate": 0.000842763095124511, "loss": 1.7816, "step": 28240 }, { "epoch": 5.85, "learning_rate": 0.0008426676843812614, "loss": 1.7768, "step": 28245 }, { "epoch": 5.85, "learning_rate": 0.0008425722736380116, "loss": 1.7815, "step": 28250 }, { "epoch": 5.85, "learning_rate": 0.000842476862894762, "loss": 1.7876, "step": 28255 }, { "epoch": 5.85, "learning_rate": 0.0008423814521515123, "loss": 1.7809, "step": 28260 }, { "epoch": 5.86, "learning_rate": 0.0008422860414082626, "loss": 1.779, "step": 28265 }, { "epoch": 5.86, "learning_rate": 0.0008421906306650129, "loss": 1.7844, "step": 28270 }, { "epoch": 5.86, "learning_rate": 0.0008420952199217632, "loss": 1.7878, "step": 28275 }, { "epoch": 5.86, "learning_rate": 0.0008419998091785134, "loss": 1.7789, "step": 28280 }, { "epoch": 5.86, "learning_rate": 0.0008419043984352638, "loss": 1.7842, "step": 28285 }, { "epoch": 5.86, "learning_rate": 0.0008418089876920141, "loss": 1.7795, "step": 28290 }, { "epoch": 5.86, "learning_rate": 0.0008417135769487645, "loss": 1.7836, "step": 28295 }, { "epoch": 5.86, "learning_rate": 0.0008416181662055148, "loss": 1.7855, "step": 28300 }, { "epoch": 5.86, "learning_rate": 0.000841522755462265, "loss": 1.7783, "step": 28305 }, { "epoch": 5.86, "learning_rate": 0.0008414273447190154, "loss": 1.7815, "step": 28310 }, { "epoch": 5.87, "learning_rate": 0.0008413319339757657, "loss": 1.7823, "step": 28315 }, { "epoch": 5.87, "learning_rate": 0.000841236523232516, "loss": 1.7806, "step": 28320 }, { "epoch": 5.87, "learning_rate": 0.0008411411124892663, "loss": 1.7806, "step": 28325 }, { "epoch": 5.87, "learning_rate": 0.0008410457017460166, "loss": 1.7878, "step": 28330 }, { "epoch": 5.87, "learning_rate": 0.0008409502910027668, "loss": 1.7838, "step": 28335 }, { "epoch": 5.87, "learning_rate": 0.0008408548802595173, "loss": 1.7826, "step": 28340 }, { "epoch": 5.87, "learning_rate": 0.0008407594695162676, "loss": 1.7927, "step": 28345 }, { "epoch": 5.87, "learning_rate": 0.0008406640587730179, "loss": 1.7829, "step": 28350 }, { "epoch": 5.87, "learning_rate": 0.0008405686480297682, "loss": 1.7884, "step": 28355 }, { "epoch": 5.88, "learning_rate": 0.0008404732372865185, "loss": 1.7819, "step": 28360 }, { "epoch": 5.88, "learning_rate": 0.0008403778265432687, "loss": 1.7794, "step": 28365 }, { "epoch": 5.88, "learning_rate": 0.0008402824158000191, "loss": 1.7893, "step": 28370 }, { "epoch": 5.88, "learning_rate": 0.0008401870050567694, "loss": 1.7868, "step": 28375 }, { "epoch": 5.88, "learning_rate": 0.0008400915943135197, "loss": 1.7816, "step": 28380 }, { "epoch": 5.88, "learning_rate": 0.0008399961835702701, "loss": 1.7888, "step": 28385 }, { "epoch": 5.88, "learning_rate": 0.0008399007728270203, "loss": 1.783, "step": 28390 }, { "epoch": 5.88, "learning_rate": 0.0008398053620837706, "loss": 1.7841, "step": 28395 }, { "epoch": 5.88, "learning_rate": 0.000839709951340521, "loss": 1.7806, "step": 28400 }, { "epoch": 5.88, "learning_rate": 0.0008396145405972713, "loss": 1.7833, "step": 28405 }, { "epoch": 5.89, "learning_rate": 0.0008395191298540216, "loss": 1.7843, "step": 28410 }, { "epoch": 5.89, "learning_rate": 0.0008394237191107719, "loss": 1.7843, "step": 28415 }, { "epoch": 5.89, "learning_rate": 0.0008393283083675221, "loss": 1.7882, "step": 28420 }, { "epoch": 5.89, "learning_rate": 0.0008392328976242724, "loss": 1.7812, "step": 28425 }, { "epoch": 5.89, "learning_rate": 0.0008391374868810229, "loss": 1.7825, "step": 28430 }, { "epoch": 5.89, "learning_rate": 0.0008390420761377732, "loss": 1.785, "step": 28435 }, { "epoch": 5.89, "learning_rate": 0.0008389466653945235, "loss": 1.7842, "step": 28440 }, { "epoch": 5.89, "learning_rate": 0.0008388512546512738, "loss": 1.7807, "step": 28445 }, { "epoch": 5.89, "learning_rate": 0.000838755843908024, "loss": 1.7847, "step": 28450 }, { "epoch": 5.89, "learning_rate": 0.0008386604331647743, "loss": 1.7833, "step": 28455 }, { "epoch": 5.9, "learning_rate": 0.0008385650224215247, "loss": 1.7883, "step": 28460 }, { "epoch": 5.9, "learning_rate": 0.000838469611678275, "loss": 1.7846, "step": 28465 }, { "epoch": 5.9, "learning_rate": 0.0008383742009350253, "loss": 1.7811, "step": 28470 }, { "epoch": 5.9, "learning_rate": 0.0008382787901917756, "loss": 1.7844, "step": 28475 }, { "epoch": 5.9, "learning_rate": 0.0008381833794485259, "loss": 1.7874, "step": 28480 }, { "epoch": 5.9, "learning_rate": 0.0008380879687052763, "loss": 1.783, "step": 28485 }, { "epoch": 5.9, "learning_rate": 0.0008379925579620266, "loss": 1.7873, "step": 28490 }, { "epoch": 5.9, "learning_rate": 0.0008378971472187769, "loss": 1.7813, "step": 28495 }, { "epoch": 5.9, "learning_rate": 0.0008378017364755272, "loss": 1.7825, "step": 28500 }, { "epoch": 5.91, "learning_rate": 0.0008377063257322774, "loss": 1.7865, "step": 28505 }, { "epoch": 5.91, "learning_rate": 0.0008376109149890277, "loss": 1.7848, "step": 28510 }, { "epoch": 5.91, "learning_rate": 0.0008375155042457781, "loss": 1.7772, "step": 28515 }, { "epoch": 5.91, "learning_rate": 0.0008374200935025285, "loss": 1.7833, "step": 28520 }, { "epoch": 5.91, "learning_rate": 0.0008373246827592788, "loss": 1.788, "step": 28525 }, { "epoch": 5.91, "learning_rate": 0.000837229272016029, "loss": 1.7791, "step": 28530 }, { "epoch": 5.91, "learning_rate": 0.0008371338612727793, "loss": 1.7829, "step": 28535 }, { "epoch": 5.91, "learning_rate": 0.0008370384505295296, "loss": 1.7869, "step": 28540 }, { "epoch": 5.91, "learning_rate": 0.00083694303978628, "loss": 1.7813, "step": 28545 }, { "epoch": 5.91, "learning_rate": 0.0008368476290430303, "loss": 1.7808, "step": 28550 }, { "epoch": 5.92, "learning_rate": 0.0008367522182997806, "loss": 1.7796, "step": 28555 }, { "epoch": 5.92, "learning_rate": 0.0008366568075565308, "loss": 1.791, "step": 28560 }, { "epoch": 5.92, "learning_rate": 0.0008365613968132811, "loss": 1.7807, "step": 28565 }, { "epoch": 5.92, "learning_rate": 0.0008364659860700315, "loss": 1.7891, "step": 28570 }, { "epoch": 5.92, "learning_rate": 0.0008363705753267819, "loss": 1.7844, "step": 28575 }, { "epoch": 5.92, "learning_rate": 0.0008362751645835322, "loss": 1.7772, "step": 28580 }, { "epoch": 5.92, "learning_rate": 0.0008361797538402825, "loss": 1.783, "step": 28585 }, { "epoch": 5.92, "learning_rate": 0.0008360843430970327, "loss": 1.7819, "step": 28590 }, { "epoch": 5.92, "learning_rate": 0.000835988932353783, "loss": 1.7843, "step": 28595 }, { "epoch": 5.93, "learning_rate": 0.0008358935216105333, "loss": 1.7835, "step": 28600 }, { "epoch": 5.93, "learning_rate": 0.0008357981108672837, "loss": 1.7833, "step": 28605 }, { "epoch": 5.93, "learning_rate": 0.000835702700124034, "loss": 1.7867, "step": 28610 }, { "epoch": 5.93, "learning_rate": 0.0008356072893807843, "loss": 1.7855, "step": 28615 }, { "epoch": 5.93, "learning_rate": 0.0008355118786375346, "loss": 1.779, "step": 28620 }, { "epoch": 5.93, "learning_rate": 0.0008354164678942849, "loss": 1.7824, "step": 28625 }, { "epoch": 5.93, "learning_rate": 0.0008353210571510352, "loss": 1.7824, "step": 28630 }, { "epoch": 5.93, "learning_rate": 0.0008352256464077856, "loss": 1.7781, "step": 28635 }, { "epoch": 5.93, "learning_rate": 0.0008351302356645359, "loss": 1.7825, "step": 28640 }, { "epoch": 5.93, "learning_rate": 0.0008350348249212861, "loss": 1.7813, "step": 28645 }, { "epoch": 5.94, "learning_rate": 0.0008349394141780364, "loss": 1.7807, "step": 28650 }, { "epoch": 5.94, "learning_rate": 0.0008348440034347867, "loss": 1.7843, "step": 28655 }, { "epoch": 5.94, "learning_rate": 0.0008347485926915371, "loss": 1.784, "step": 28660 }, { "epoch": 5.94, "learning_rate": 0.0008346531819482875, "loss": 1.7805, "step": 28665 }, { "epoch": 5.94, "learning_rate": 0.0008345577712050378, "loss": 1.7837, "step": 28670 }, { "epoch": 5.94, "learning_rate": 0.000834462360461788, "loss": 1.782, "step": 28675 }, { "epoch": 5.94, "learning_rate": 0.0008343669497185383, "loss": 1.7858, "step": 28680 }, { "epoch": 5.94, "learning_rate": 0.0008342715389752886, "loss": 1.7838, "step": 28685 }, { "epoch": 5.94, "learning_rate": 0.0008341761282320389, "loss": 1.7826, "step": 28690 }, { "epoch": 5.94, "learning_rate": 0.0008340807174887893, "loss": 1.7828, "step": 28695 }, { "epoch": 5.95, "learning_rate": 0.0008339853067455395, "loss": 1.784, "step": 28700 }, { "epoch": 5.95, "learning_rate": 0.0008338898960022899, "loss": 1.787, "step": 28705 }, { "epoch": 5.95, "learning_rate": 0.0008337944852590402, "loss": 1.7818, "step": 28710 }, { "epoch": 5.95, "learning_rate": 0.0008336990745157905, "loss": 1.7824, "step": 28715 }, { "epoch": 5.95, "learning_rate": 0.0008336036637725409, "loss": 1.7824, "step": 28720 }, { "epoch": 5.95, "learning_rate": 0.0008335082530292912, "loss": 1.7856, "step": 28725 }, { "epoch": 5.95, "learning_rate": 0.0008334128422860414, "loss": 1.7786, "step": 28730 }, { "epoch": 5.95, "learning_rate": 0.0008333174315427917, "loss": 1.7786, "step": 28735 }, { "epoch": 5.95, "learning_rate": 0.000833222020799542, "loss": 1.7806, "step": 28740 }, { "epoch": 5.96, "learning_rate": 0.0008331266100562923, "loss": 1.7872, "step": 28745 }, { "epoch": 5.96, "learning_rate": 0.0008330311993130428, "loss": 1.789, "step": 28750 }, { "epoch": 5.96, "learning_rate": 0.000832935788569793, "loss": 1.7853, "step": 28755 }, { "epoch": 5.96, "learning_rate": 0.0008328403778265433, "loss": 1.7777, "step": 28760 }, { "epoch": 5.96, "learning_rate": 0.0008327449670832936, "loss": 1.7799, "step": 28765 }, { "epoch": 5.96, "learning_rate": 0.0008326495563400439, "loss": 1.7867, "step": 28770 }, { "epoch": 5.96, "learning_rate": 0.0008325541455967942, "loss": 1.7808, "step": 28775 }, { "epoch": 5.96, "learning_rate": 0.0008324587348535446, "loss": 1.7852, "step": 28780 }, { "epoch": 5.96, "learning_rate": 0.0008323633241102948, "loss": 1.7776, "step": 28785 }, { "epoch": 5.96, "learning_rate": 0.0008322679133670451, "loss": 1.7836, "step": 28790 }, { "epoch": 5.97, "learning_rate": 0.0008321725026237954, "loss": 1.781, "step": 28795 }, { "epoch": 5.97, "learning_rate": 0.0008320770918805458, "loss": 1.7854, "step": 28800 }, { "epoch": 5.97, "learning_rate": 0.0008319816811372961, "loss": 1.78, "step": 28805 }, { "epoch": 5.97, "learning_rate": 0.0008318862703940465, "loss": 1.7791, "step": 28810 }, { "epoch": 5.97, "learning_rate": 0.0008317908596507967, "loss": 1.7867, "step": 28815 }, { "epoch": 5.97, "learning_rate": 0.000831695448907547, "loss": 1.7812, "step": 28820 }, { "epoch": 5.97, "learning_rate": 0.0008316000381642973, "loss": 1.7866, "step": 28825 }, { "epoch": 5.97, "learning_rate": 0.0008315046274210476, "loss": 1.7822, "step": 28830 }, { "epoch": 5.97, "learning_rate": 0.0008314092166777979, "loss": 1.7827, "step": 28835 }, { "epoch": 5.97, "learning_rate": 0.0008313138059345482, "loss": 1.7778, "step": 28840 }, { "epoch": 5.98, "learning_rate": 0.0008312183951912986, "loss": 1.7793, "step": 28845 }, { "epoch": 5.98, "learning_rate": 0.0008311229844480489, "loss": 1.7816, "step": 28850 }, { "epoch": 5.98, "learning_rate": 0.0008310275737047992, "loss": 1.7859, "step": 28855 }, { "epoch": 5.98, "learning_rate": 0.0008309321629615495, "loss": 1.782, "step": 28860 }, { "epoch": 5.98, "learning_rate": 0.0008308367522182997, "loss": 1.7781, "step": 28865 }, { "epoch": 5.98, "learning_rate": 0.0008307413414750501, "loss": 1.7803, "step": 28870 }, { "epoch": 5.98, "learning_rate": 0.0008306459307318004, "loss": 1.7883, "step": 28875 }, { "epoch": 5.98, "learning_rate": 0.0008305505199885507, "loss": 1.7796, "step": 28880 }, { "epoch": 5.98, "learning_rate": 0.000830455109245301, "loss": 1.7822, "step": 28885 }, { "epoch": 5.99, "learning_rate": 0.0008303596985020514, "loss": 1.778, "step": 28890 }, { "epoch": 5.99, "learning_rate": 0.0008302642877588016, "loss": 1.7827, "step": 28895 }, { "epoch": 5.99, "learning_rate": 0.000830168877015552, "loss": 1.7843, "step": 28900 }, { "epoch": 5.99, "learning_rate": 0.0008300734662723023, "loss": 1.7818, "step": 28905 }, { "epoch": 5.99, "learning_rate": 0.0008299780555290526, "loss": 1.7788, "step": 28910 }, { "epoch": 5.99, "learning_rate": 0.0008298826447858029, "loss": 1.7813, "step": 28915 }, { "epoch": 5.99, "learning_rate": 0.0008297872340425531, "loss": 1.7802, "step": 28920 }, { "epoch": 5.99, "learning_rate": 0.0008296918232993035, "loss": 1.7801, "step": 28925 }, { "epoch": 5.99, "learning_rate": 0.0008295964125560538, "loss": 1.7826, "step": 28930 }, { "epoch": 5.99, "learning_rate": 0.0008295010018128042, "loss": 1.784, "step": 28935 }, { "epoch": 6.0, "learning_rate": 0.0008294055910695545, "loss": 1.7891, "step": 28940 }, { "epoch": 6.0, "learning_rate": 0.0008293101803263048, "loss": 1.779, "step": 28945 }, { "epoch": 6.0, "learning_rate": 0.000829214769583055, "loss": 1.7833, "step": 28950 }, { "epoch": 6.0, "learning_rate": 0.0008291193588398054, "loss": 1.7757, "step": 28955 }, { "epoch": 6.0, "learning_rate": 0.0008290239480965557, "loss": 1.7851, "step": 28960 }, { "epoch": 6.0, "learning_rate": 0.000828928537353306, "loss": 1.7756, "step": 28965 }, { "epoch": 6.0, "learning_rate": 0.0008288331266100563, "loss": 1.7758, "step": 28970 }, { "epoch": 6.0, "learning_rate": 0.0008287377158668066, "loss": 1.7691, "step": 28975 }, { "epoch": 6.0, "learning_rate": 0.0008286423051235569, "loss": 1.7703, "step": 28980 }, { "epoch": 6.0, "learning_rate": 0.0008285468943803073, "loss": 1.7666, "step": 28985 }, { "epoch": 6.01, "learning_rate": 0.0008284514836370576, "loss": 1.7718, "step": 28990 }, { "epoch": 6.01, "learning_rate": 0.0008283560728938079, "loss": 1.7708, "step": 28995 }, { "epoch": 6.01, "learning_rate": 0.0008282606621505582, "loss": 1.7685, "step": 29000 }, { "epoch": 6.01, "learning_rate": 0.0008281652514073084, "loss": 1.7672, "step": 29005 }, { "epoch": 6.01, "learning_rate": 0.0008280698406640587, "loss": 1.7718, "step": 29010 }, { "epoch": 6.01, "learning_rate": 0.0008279744299208091, "loss": 1.7717, "step": 29015 }, { "epoch": 6.01, "learning_rate": 0.0008278790191775594, "loss": 1.7679, "step": 29020 }, { "epoch": 6.01, "learning_rate": 0.0008277836084343097, "loss": 1.7702, "step": 29025 }, { "epoch": 6.01, "learning_rate": 0.0008276881976910601, "loss": 1.7706, "step": 29030 }, { "epoch": 6.02, "learning_rate": 0.0008275927869478103, "loss": 1.7658, "step": 29035 }, { "epoch": 6.02, "learning_rate": 0.0008274973762045606, "loss": 1.7673, "step": 29040 }, { "epoch": 6.02, "learning_rate": 0.000827401965461311, "loss": 1.7722, "step": 29045 }, { "epoch": 6.02, "learning_rate": 0.0008273065547180613, "loss": 1.7703, "step": 29050 }, { "epoch": 6.02, "learning_rate": 0.0008272111439748116, "loss": 1.7696, "step": 29055 }, { "epoch": 6.02, "learning_rate": 0.0008271157332315619, "loss": 1.7697, "step": 29060 }, { "epoch": 6.02, "learning_rate": 0.0008270203224883121, "loss": 1.7719, "step": 29065 }, { "epoch": 6.02, "learning_rate": 0.0008269249117450624, "loss": 1.7718, "step": 29070 }, { "epoch": 6.02, "learning_rate": 0.0008268295010018129, "loss": 1.7723, "step": 29075 }, { "epoch": 6.02, "learning_rate": 0.0008267340902585632, "loss": 1.7694, "step": 29080 }, { "epoch": 6.03, "learning_rate": 0.0008266386795153135, "loss": 1.7858, "step": 29085 }, { "epoch": 6.03, "learning_rate": 0.0008265432687720637, "loss": 1.7857, "step": 29090 }, { "epoch": 6.03, "learning_rate": 0.000826447858028814, "loss": 1.7788, "step": 29095 }, { "epoch": 6.03, "learning_rate": 0.0008263524472855643, "loss": 1.768, "step": 29100 }, { "epoch": 6.03, "learning_rate": 0.0008262570365423147, "loss": 1.777, "step": 29105 }, { "epoch": 6.03, "learning_rate": 0.000826161625799065, "loss": 1.769, "step": 29110 }, { "epoch": 6.03, "learning_rate": 0.0008260662150558153, "loss": 1.7767, "step": 29115 }, { "epoch": 6.03, "learning_rate": 0.0008259708043125656, "loss": 1.7725, "step": 29120 }, { "epoch": 6.03, "learning_rate": 0.0008258753935693159, "loss": 1.7805, "step": 29125 }, { "epoch": 6.03, "learning_rate": 0.0008257799828260663, "loss": 1.77, "step": 29130 }, { "epoch": 6.04, "learning_rate": 0.0008256845720828166, "loss": 1.7761, "step": 29135 }, { "epoch": 6.04, "learning_rate": 0.0008255891613395669, "loss": 1.7756, "step": 29140 }, { "epoch": 6.04, "learning_rate": 0.0008254937505963171, "loss": 1.779, "step": 29145 }, { "epoch": 6.04, "learning_rate": 0.0008253983398530674, "loss": 1.7687, "step": 29150 }, { "epoch": 6.04, "learning_rate": 0.0008253029291098177, "loss": 1.7745, "step": 29155 }, { "epoch": 6.04, "learning_rate": 0.0008252075183665681, "loss": 1.7699, "step": 29160 }, { "epoch": 6.04, "learning_rate": 0.0008251121076233185, "loss": 1.7728, "step": 29165 }, { "epoch": 6.04, "learning_rate": 0.0008250166968800688, "loss": 1.7709, "step": 29170 }, { "epoch": 6.04, "learning_rate": 0.000824921286136819, "loss": 1.7717, "step": 29175 }, { "epoch": 6.05, "learning_rate": 0.0008248258753935693, "loss": 1.7778, "step": 29180 }, { "epoch": 6.05, "learning_rate": 0.0008247304646503196, "loss": 1.7747, "step": 29185 }, { "epoch": 6.05, "learning_rate": 0.00082463505390707, "loss": 1.7731, "step": 29190 }, { "epoch": 6.05, "learning_rate": 0.0008245396431638203, "loss": 1.7708, "step": 29195 }, { "epoch": 6.05, "learning_rate": 0.0008244442324205706, "loss": 1.7755, "step": 29200 }, { "epoch": 6.05, "learning_rate": 0.0008243488216773208, "loss": 1.7722, "step": 29205 }, { "epoch": 6.05, "learning_rate": 0.0008242534109340712, "loss": 1.7717, "step": 29210 }, { "epoch": 6.05, "learning_rate": 0.0008241580001908215, "loss": 1.774, "step": 29215 }, { "epoch": 6.05, "learning_rate": 0.0008240625894475719, "loss": 1.7712, "step": 29220 }, { "epoch": 6.05, "learning_rate": 0.0008239671787043222, "loss": 1.7756, "step": 29225 }, { "epoch": 6.06, "learning_rate": 0.0008238717679610724, "loss": 1.769, "step": 29230 }, { "epoch": 6.06, "learning_rate": 0.0008237763572178227, "loss": 1.7735, "step": 29235 }, { "epoch": 6.06, "learning_rate": 0.000823680946474573, "loss": 1.7758, "step": 29240 }, { "epoch": 6.06, "learning_rate": 0.0008235855357313233, "loss": 1.7696, "step": 29245 }, { "epoch": 6.06, "learning_rate": 0.0008234901249880737, "loss": 1.7746, "step": 29250 }, { "epoch": 6.06, "learning_rate": 0.0008233947142448241, "loss": 1.7707, "step": 29255 }, { "epoch": 6.06, "learning_rate": 0.0008232993035015743, "loss": 1.7745, "step": 29260 }, { "epoch": 6.06, "learning_rate": 0.0008232038927583246, "loss": 1.7694, "step": 29265 }, { "epoch": 6.06, "learning_rate": 0.0008231084820150749, "loss": 1.7769, "step": 29270 }, { "epoch": 6.06, "learning_rate": 0.0008230130712718252, "loss": 1.7719, "step": 29275 }, { "epoch": 6.07, "learning_rate": 0.0008229176605285756, "loss": 1.7706, "step": 29280 }, { "epoch": 6.07, "learning_rate": 0.0008228222497853258, "loss": 1.7756, "step": 29285 }, { "epoch": 6.07, "learning_rate": 0.0008227268390420761, "loss": 1.7759, "step": 29290 }, { "epoch": 6.07, "learning_rate": 0.0008226314282988264, "loss": 1.7765, "step": 29295 }, { "epoch": 6.07, "learning_rate": 0.0008225360175555767, "loss": 1.7661, "step": 29300 }, { "epoch": 6.07, "learning_rate": 0.0008224406068123271, "loss": 1.7693, "step": 29305 }, { "epoch": 6.07, "learning_rate": 0.0008223451960690775, "loss": 1.7742, "step": 29310 }, { "epoch": 6.07, "learning_rate": 0.0008222497853258277, "loss": 1.7744, "step": 29315 }, { "epoch": 6.07, "learning_rate": 0.000822154374582578, "loss": 1.7754, "step": 29320 }, { "epoch": 6.08, "learning_rate": 0.0008220589638393283, "loss": 1.7746, "step": 29325 }, { "epoch": 6.08, "learning_rate": 0.0008219635530960786, "loss": 1.7782, "step": 29330 }, { "epoch": 6.08, "learning_rate": 0.0008218681423528289, "loss": 1.7711, "step": 29335 }, { "epoch": 6.08, "learning_rate": 0.0008217727316095793, "loss": 1.7739, "step": 29340 }, { "epoch": 6.08, "learning_rate": 0.0008216773208663295, "loss": 1.7722, "step": 29345 }, { "epoch": 6.08, "learning_rate": 0.0008215819101230799, "loss": 1.7771, "step": 29350 }, { "epoch": 6.08, "learning_rate": 0.0008214864993798302, "loss": 1.7757, "step": 29355 }, { "epoch": 6.08, "learning_rate": 0.0008213910886365805, "loss": 1.7748, "step": 29360 }, { "epoch": 6.08, "learning_rate": 0.0008212956778933309, "loss": 1.7761, "step": 29365 }, { "epoch": 6.08, "learning_rate": 0.0008212002671500811, "loss": 1.7747, "step": 29370 }, { "epoch": 6.09, "learning_rate": 0.0008211048564068314, "loss": 1.7768, "step": 29375 }, { "epoch": 6.09, "learning_rate": 0.0008210094456635817, "loss": 1.7697, "step": 29380 }, { "epoch": 6.09, "learning_rate": 0.000820914034920332, "loss": 1.7752, "step": 29385 }, { "epoch": 6.09, "learning_rate": 0.0008208186241770823, "loss": 1.7738, "step": 29390 }, { "epoch": 6.09, "learning_rate": 0.0008207232134338328, "loss": 1.7721, "step": 29395 }, { "epoch": 6.09, "learning_rate": 0.000820627802690583, "loss": 1.7717, "step": 29400 }, { "epoch": 6.09, "learning_rate": 0.0008205323919473333, "loss": 1.778, "step": 29405 }, { "epoch": 6.09, "learning_rate": 0.0008204369812040836, "loss": 1.7726, "step": 29410 }, { "epoch": 6.09, "learning_rate": 0.0008203415704608339, "loss": 1.7734, "step": 29415 }, { "epoch": 6.09, "learning_rate": 0.0008202461597175842, "loss": 1.7761, "step": 29420 }, { "epoch": 6.1, "learning_rate": 0.0008201507489743346, "loss": 1.7788, "step": 29425 }, { "epoch": 6.1, "learning_rate": 0.0008200553382310848, "loss": 1.7679, "step": 29430 }, { "epoch": 6.1, "learning_rate": 0.0008199599274878351, "loss": 1.7745, "step": 29435 }, { "epoch": 6.1, "learning_rate": 0.0008198645167445855, "loss": 1.7752, "step": 29440 }, { "epoch": 6.1, "learning_rate": 0.0008197691060013358, "loss": 1.7738, "step": 29445 }, { "epoch": 6.1, "learning_rate": 0.0008196736952580861, "loss": 1.7717, "step": 29450 }, { "epoch": 6.1, "learning_rate": 0.0008195782845148364, "loss": 1.7741, "step": 29455 }, { "epoch": 6.1, "learning_rate": 0.0008194828737715867, "loss": 1.7767, "step": 29460 }, { "epoch": 6.1, "learning_rate": 0.000819387463028337, "loss": 1.7705, "step": 29465 }, { "epoch": 6.11, "learning_rate": 0.0008192920522850873, "loss": 1.7742, "step": 29470 }, { "epoch": 6.11, "learning_rate": 0.0008191966415418376, "loss": 1.7643, "step": 29475 }, { "epoch": 6.11, "learning_rate": 0.0008191012307985878, "loss": 1.7756, "step": 29480 }, { "epoch": 6.11, "learning_rate": 0.0008190058200553383, "loss": 1.7704, "step": 29485 }, { "epoch": 6.11, "learning_rate": 0.0008189104093120886, "loss": 1.771, "step": 29490 }, { "epoch": 6.11, "learning_rate": 0.0008188149985688389, "loss": 1.7721, "step": 29495 }, { "epoch": 6.11, "learning_rate": 0.0008187195878255892, "loss": 1.7785, "step": 29500 }, { "epoch": 6.11, "learning_rate": 0.0008186241770823395, "loss": 1.7744, "step": 29505 }, { "epoch": 6.11, "learning_rate": 0.0008185287663390897, "loss": 1.7714, "step": 29510 }, { "epoch": 6.11, "learning_rate": 0.0008184333555958401, "loss": 1.776, "step": 29515 }, { "epoch": 6.12, "learning_rate": 0.0008183379448525904, "loss": 1.7725, "step": 29520 }, { "epoch": 6.12, "learning_rate": 0.0008182425341093407, "loss": 1.7655, "step": 29525 }, { "epoch": 6.12, "learning_rate": 0.000818147123366091, "loss": 1.7787, "step": 29530 }, { "epoch": 6.12, "learning_rate": 0.0008180517126228414, "loss": 1.7729, "step": 29535 }, { "epoch": 6.12, "learning_rate": 0.0008179563018795917, "loss": 1.776, "step": 29540 }, { "epoch": 6.12, "learning_rate": 0.000817860891136342, "loss": 1.7677, "step": 29545 }, { "epoch": 6.12, "learning_rate": 0.0008177654803930923, "loss": 1.7782, "step": 29550 }, { "epoch": 6.12, "learning_rate": 0.0008176700696498426, "loss": 1.7733, "step": 29555 }, { "epoch": 6.12, "learning_rate": 0.0008175746589065929, "loss": 1.7793, "step": 29560 }, { "epoch": 6.12, "learning_rate": 0.0008174792481633431, "loss": 1.775, "step": 29565 }, { "epoch": 6.13, "learning_rate": 0.0008173838374200935, "loss": 1.7719, "step": 29570 }, { "epoch": 6.13, "learning_rate": 0.0008172884266768438, "loss": 1.7743, "step": 29575 }, { "epoch": 6.13, "learning_rate": 0.0008171930159335942, "loss": 1.7663, "step": 29580 }, { "epoch": 6.13, "learning_rate": 0.0008170976051903445, "loss": 1.7721, "step": 29585 }, { "epoch": 6.13, "learning_rate": 0.0008170021944470948, "loss": 1.7785, "step": 29590 }, { "epoch": 6.13, "learning_rate": 0.000816906783703845, "loss": 1.773, "step": 29595 }, { "epoch": 6.13, "learning_rate": 0.0008168113729605954, "loss": 1.7732, "step": 29600 }, { "epoch": 6.13, "learning_rate": 0.0008167159622173457, "loss": 1.7722, "step": 29605 }, { "epoch": 6.13, "learning_rate": 0.000816620551474096, "loss": 1.7834, "step": 29610 }, { "epoch": 6.14, "learning_rate": 0.0008165251407308463, "loss": 1.7747, "step": 29615 }, { "epoch": 6.14, "learning_rate": 0.0008164297299875965, "loss": 1.7739, "step": 29620 }, { "epoch": 6.14, "learning_rate": 0.0008163343192443469, "loss": 1.7763, "step": 29625 }, { "epoch": 6.14, "learning_rate": 0.0008162389085010973, "loss": 1.7743, "step": 29630 }, { "epoch": 6.14, "learning_rate": 0.0008161434977578476, "loss": 1.7777, "step": 29635 }, { "epoch": 6.14, "learning_rate": 0.0008160480870145979, "loss": 1.7757, "step": 29640 }, { "epoch": 6.14, "learning_rate": 0.0008159526762713482, "loss": 1.7727, "step": 29645 }, { "epoch": 6.14, "learning_rate": 0.0008158572655280984, "loss": 1.7671, "step": 29650 }, { "epoch": 6.14, "learning_rate": 0.0008157618547848487, "loss": 1.7729, "step": 29655 }, { "epoch": 6.14, "learning_rate": 0.0008156664440415991, "loss": 1.7743, "step": 29660 }, { "epoch": 6.15, "learning_rate": 0.0008155710332983494, "loss": 1.7737, "step": 29665 }, { "epoch": 6.15, "learning_rate": 0.0008154756225550998, "loss": 1.7696, "step": 29670 }, { "epoch": 6.15, "learning_rate": 0.0008153802118118501, "loss": 1.7709, "step": 29675 }, { "epoch": 6.15, "learning_rate": 0.0008152848010686003, "loss": 1.7722, "step": 29680 }, { "epoch": 6.15, "learning_rate": 0.0008151893903253506, "loss": 1.7767, "step": 29685 }, { "epoch": 6.15, "learning_rate": 0.000815093979582101, "loss": 1.785, "step": 29690 }, { "epoch": 6.15, "learning_rate": 0.0008149985688388513, "loss": 1.7795, "step": 29695 }, { "epoch": 6.15, "learning_rate": 0.0008149031580956016, "loss": 1.7787, "step": 29700 }, { "epoch": 6.15, "learning_rate": 0.0008148077473523518, "loss": 1.7767, "step": 29705 }, { "epoch": 6.15, "learning_rate": 0.0008147123366091021, "loss": 1.7757, "step": 29710 }, { "epoch": 6.16, "learning_rate": 0.0008146169258658525, "loss": 1.7762, "step": 29715 }, { "epoch": 6.16, "learning_rate": 0.0008145215151226029, "loss": 1.7778, "step": 29720 }, { "epoch": 6.16, "learning_rate": 0.0008144261043793532, "loss": 1.7681, "step": 29725 }, { "epoch": 6.16, "learning_rate": 0.0008143306936361035, "loss": 1.7781, "step": 29730 }, { "epoch": 6.16, "learning_rate": 0.0008142352828928537, "loss": 1.7703, "step": 29735 }, { "epoch": 6.16, "learning_rate": 0.000814139872149604, "loss": 1.7725, "step": 29740 }, { "epoch": 6.16, "learning_rate": 0.0008140444614063543, "loss": 1.7721, "step": 29745 }, { "epoch": 6.16, "learning_rate": 0.0008139490506631047, "loss": 1.773, "step": 29750 }, { "epoch": 6.16, "learning_rate": 0.000813853639919855, "loss": 1.7695, "step": 29755 }, { "epoch": 6.17, "learning_rate": 0.0008137582291766054, "loss": 1.7728, "step": 29760 }, { "epoch": 6.17, "learning_rate": 0.0008136628184333556, "loss": 1.772, "step": 29765 }, { "epoch": 6.17, "learning_rate": 0.0008135674076901059, "loss": 1.773, "step": 29770 }, { "epoch": 6.17, "learning_rate": 0.0008134719969468563, "loss": 1.7724, "step": 29775 }, { "epoch": 6.17, "learning_rate": 0.0008133765862036066, "loss": 1.7724, "step": 29780 }, { "epoch": 6.17, "learning_rate": 0.0008132811754603569, "loss": 1.7787, "step": 29785 }, { "epoch": 6.17, "learning_rate": 0.0008131857647171071, "loss": 1.7765, "step": 29790 }, { "epoch": 6.17, "learning_rate": 0.0008130903539738574, "loss": 1.774, "step": 29795 }, { "epoch": 6.17, "learning_rate": 0.0008129949432306077, "loss": 1.7799, "step": 29800 }, { "epoch": 6.17, "learning_rate": 0.0008128995324873581, "loss": 1.7745, "step": 29805 }, { "epoch": 6.18, "learning_rate": 0.0008128041217441085, "loss": 1.7702, "step": 29810 }, { "epoch": 6.18, "learning_rate": 0.0008127087110008588, "loss": 1.777, "step": 29815 }, { "epoch": 6.18, "learning_rate": 0.000812613300257609, "loss": 1.7754, "step": 29820 }, { "epoch": 6.18, "learning_rate": 0.0008125178895143593, "loss": 1.7763, "step": 29825 }, { "epoch": 6.18, "learning_rate": 0.0008124224787711096, "loss": 1.7762, "step": 29830 }, { "epoch": 6.18, "learning_rate": 0.00081232706802786, "loss": 1.7697, "step": 29835 }, { "epoch": 6.18, "learning_rate": 0.0008122316572846103, "loss": 1.7747, "step": 29840 }, { "epoch": 6.18, "learning_rate": 0.0008121362465413605, "loss": 1.7784, "step": 29845 }, { "epoch": 6.18, "learning_rate": 0.0008120408357981108, "loss": 1.7765, "step": 29850 }, { "epoch": 6.19, "learning_rate": 0.0008119454250548612, "loss": 1.775, "step": 29855 }, { "epoch": 6.19, "learning_rate": 0.0008118500143116115, "loss": 1.7766, "step": 29860 }, { "epoch": 6.19, "learning_rate": 0.0008117546035683619, "loss": 1.7727, "step": 29865 }, { "epoch": 6.19, "learning_rate": 0.0008116591928251122, "loss": 1.7736, "step": 29870 }, { "epoch": 6.19, "learning_rate": 0.0008115637820818624, "loss": 1.7692, "step": 29875 }, { "epoch": 6.19, "learning_rate": 0.0008114683713386127, "loss": 1.7666, "step": 29880 }, { "epoch": 6.19, "learning_rate": 0.000811372960595363, "loss": 1.7719, "step": 29885 }, { "epoch": 6.19, "learning_rate": 0.0008112775498521133, "loss": 1.7702, "step": 29890 }, { "epoch": 6.19, "learning_rate": 0.0008111821391088637, "loss": 1.7709, "step": 29895 }, { "epoch": 6.19, "learning_rate": 0.0008110867283656141, "loss": 1.7769, "step": 29900 }, { "epoch": 6.2, "learning_rate": 0.0008109913176223643, "loss": 1.7712, "step": 29905 }, { "epoch": 6.2, "learning_rate": 0.0008108959068791146, "loss": 1.7718, "step": 29910 }, { "epoch": 6.2, "learning_rate": 0.0008108004961358649, "loss": 1.7708, "step": 29915 }, { "epoch": 6.2, "learning_rate": 0.0008107050853926152, "loss": 1.779, "step": 29920 }, { "epoch": 6.2, "learning_rate": 0.0008106096746493656, "loss": 1.7728, "step": 29925 }, { "epoch": 6.2, "learning_rate": 0.0008105142639061158, "loss": 1.7771, "step": 29930 }, { "epoch": 6.2, "learning_rate": 0.0008104188531628661, "loss": 1.7804, "step": 29935 }, { "epoch": 6.2, "learning_rate": 0.0008103234424196164, "loss": 1.7716, "step": 29940 }, { "epoch": 6.2, "learning_rate": 0.0008102280316763668, "loss": 1.7776, "step": 29945 }, { "epoch": 6.2, "learning_rate": 0.0008101326209331171, "loss": 1.772, "step": 29950 }, { "epoch": 6.21, "learning_rate": 0.0008100372101898675, "loss": 1.773, "step": 29955 }, { "epoch": 6.21, "learning_rate": 0.0008099417994466177, "loss": 1.7715, "step": 29960 }, { "epoch": 6.21, "learning_rate": 0.000809846388703368, "loss": 1.7757, "step": 29965 }, { "epoch": 6.21, "learning_rate": 0.0008097509779601183, "loss": 1.7671, "step": 29970 }, { "epoch": 6.21, "learning_rate": 0.0008096555672168686, "loss": 1.7708, "step": 29975 }, { "epoch": 6.21, "learning_rate": 0.0008095601564736189, "loss": 1.7732, "step": 29980 }, { "epoch": 6.21, "learning_rate": 0.0008094647457303692, "loss": 1.771, "step": 29985 }, { "epoch": 6.21, "learning_rate": 0.0008093693349871196, "loss": 1.7749, "step": 29990 }, { "epoch": 6.21, "learning_rate": 0.0008092739242438699, "loss": 1.7732, "step": 29995 }, { "epoch": 6.22, "learning_rate": 0.0008091785135006202, "loss": 1.7709, "step": 30000 }, { "epoch": 6.22, "eval_accuracy": 0.5369411764705883, "eval_loss": 1.9441477060317993, "eval_runtime": 0.8019, "eval_samples_per_second": 187.056, "eval_steps_per_second": 1.247, "step": 30000 }, { "epoch": 6.22, "learning_rate": 0.0008090831027573705, "loss": 1.773, "step": 30005 }, { "epoch": 6.22, "learning_rate": 0.0008089876920141209, "loss": 1.772, "step": 30010 }, { "epoch": 6.22, "learning_rate": 0.0008088922812708711, "loss": 1.7734, "step": 30015 }, { "epoch": 6.22, "learning_rate": 0.0008087968705276214, "loss": 1.7731, "step": 30020 }, { "epoch": 6.22, "learning_rate": 0.0008087014597843717, "loss": 1.7738, "step": 30025 }, { "epoch": 6.22, "learning_rate": 0.000808606049041122, "loss": 1.7712, "step": 30030 }, { "epoch": 6.22, "learning_rate": 0.0008085106382978723, "loss": 1.775, "step": 30035 }, { "epoch": 6.22, "learning_rate": 0.0008084152275546228, "loss": 1.7752, "step": 30040 }, { "epoch": 6.22, "learning_rate": 0.000808319816811373, "loss": 1.7787, "step": 30045 }, { "epoch": 6.23, "learning_rate": 0.0008082244060681233, "loss": 1.7713, "step": 30050 }, { "epoch": 6.23, "learning_rate": 0.0008081289953248736, "loss": 1.7723, "step": 30055 }, { "epoch": 6.23, "learning_rate": 0.0008080335845816239, "loss": 1.7747, "step": 30060 }, { "epoch": 6.23, "learning_rate": 0.0008079381738383742, "loss": 1.7752, "step": 30065 }, { "epoch": 6.23, "learning_rate": 0.0008078427630951245, "loss": 1.771, "step": 30070 }, { "epoch": 6.23, "learning_rate": 0.0008077473523518748, "loss": 1.7736, "step": 30075 }, { "epoch": 6.23, "learning_rate": 0.0008076519416086251, "loss": 1.7683, "step": 30080 }, { "epoch": 6.23, "learning_rate": 0.0008075565308653755, "loss": 1.7739, "step": 30085 }, { "epoch": 6.23, "learning_rate": 0.0008074611201221258, "loss": 1.7718, "step": 30090 }, { "epoch": 6.23, "learning_rate": 0.000807365709378876, "loss": 1.7752, "step": 30095 }, { "epoch": 6.24, "learning_rate": 0.0008072702986356264, "loss": 1.775, "step": 30100 }, { "epoch": 6.24, "learning_rate": 0.0008071748878923767, "loss": 1.7704, "step": 30105 }, { "epoch": 6.24, "learning_rate": 0.000807079477149127, "loss": 1.7787, "step": 30110 }, { "epoch": 6.24, "learning_rate": 0.0008069840664058773, "loss": 1.7704, "step": 30115 }, { "epoch": 6.24, "learning_rate": 0.0008068886556626276, "loss": 1.7758, "step": 30120 }, { "epoch": 6.24, "learning_rate": 0.0008067932449193778, "loss": 1.7742, "step": 30125 }, { "epoch": 6.24, "learning_rate": 0.0008066978341761283, "loss": 1.7707, "step": 30130 }, { "epoch": 6.24, "learning_rate": 0.0008066024234328786, "loss": 1.775, "step": 30135 }, { "epoch": 6.24, "learning_rate": 0.0008065070126896289, "loss": 1.7702, "step": 30140 }, { "epoch": 6.25, "learning_rate": 0.0008064116019463792, "loss": 1.7709, "step": 30145 }, { "epoch": 6.25, "learning_rate": 0.0008063161912031295, "loss": 1.7749, "step": 30150 }, { "epoch": 6.25, "learning_rate": 0.0008062207804598797, "loss": 1.7707, "step": 30155 }, { "epoch": 6.25, "learning_rate": 0.0008061253697166301, "loss": 1.7719, "step": 30160 }, { "epoch": 6.25, "learning_rate": 0.0008060299589733804, "loss": 1.772, "step": 30165 }, { "epoch": 6.25, "learning_rate": 0.0008059345482301307, "loss": 1.7724, "step": 30170 }, { "epoch": 6.25, "learning_rate": 0.0008058391374868811, "loss": 1.774, "step": 30175 }, { "epoch": 6.25, "learning_rate": 0.0008057437267436314, "loss": 1.7727, "step": 30180 }, { "epoch": 6.25, "learning_rate": 0.0008056483160003817, "loss": 1.7746, "step": 30185 }, { "epoch": 6.25, "learning_rate": 0.000805552905257132, "loss": 1.7727, "step": 30190 }, { "epoch": 6.26, "learning_rate": 0.0008054574945138823, "loss": 1.7742, "step": 30195 }, { "epoch": 6.26, "learning_rate": 0.0008053620837706326, "loss": 1.7719, "step": 30200 }, { "epoch": 6.26, "learning_rate": 0.0008052666730273829, "loss": 1.7745, "step": 30205 }, { "epoch": 6.26, "learning_rate": 0.0008051712622841331, "loss": 1.7739, "step": 30210 }, { "epoch": 6.26, "learning_rate": 0.0008050758515408835, "loss": 1.7702, "step": 30215 }, { "epoch": 6.26, "learning_rate": 0.0008049804407976339, "loss": 1.7717, "step": 30220 }, { "epoch": 6.26, "learning_rate": 0.0008048850300543842, "loss": 1.7687, "step": 30225 }, { "epoch": 6.26, "learning_rate": 0.0008047896193111345, "loss": 1.773, "step": 30230 }, { "epoch": 6.26, "learning_rate": 0.0008046942085678848, "loss": 1.7782, "step": 30235 }, { "epoch": 6.26, "learning_rate": 0.000804598797824635, "loss": 1.7702, "step": 30240 }, { "epoch": 6.27, "learning_rate": 0.0008045033870813854, "loss": 1.7683, "step": 30245 }, { "epoch": 6.27, "learning_rate": 0.0008044079763381357, "loss": 1.7718, "step": 30250 }, { "epoch": 6.27, "learning_rate": 0.000804312565594886, "loss": 1.7726, "step": 30255 }, { "epoch": 6.27, "learning_rate": 0.0008042171548516363, "loss": 1.7697, "step": 30260 }, { "epoch": 6.27, "learning_rate": 0.0008041217441083865, "loss": 1.773, "step": 30265 }, { "epoch": 6.27, "learning_rate": 0.0008040263333651369, "loss": 1.7724, "step": 30270 }, { "epoch": 6.27, "learning_rate": 0.0008039309226218873, "loss": 1.7727, "step": 30275 }, { "epoch": 6.27, "learning_rate": 0.0008038355118786376, "loss": 1.7714, "step": 30280 }, { "epoch": 6.27, "learning_rate": 0.0008037401011353879, "loss": 1.7733, "step": 30285 }, { "epoch": 6.28, "learning_rate": 0.0008036446903921382, "loss": 1.7713, "step": 30290 }, { "epoch": 6.28, "learning_rate": 0.0008035492796488884, "loss": 1.7739, "step": 30295 }, { "epoch": 6.28, "learning_rate": 0.0008034538689056387, "loss": 1.7782, "step": 30300 }, { "epoch": 6.28, "learning_rate": 0.0008033584581623891, "loss": 1.7727, "step": 30305 }, { "epoch": 6.28, "learning_rate": 0.0008032630474191394, "loss": 1.7789, "step": 30310 }, { "epoch": 6.28, "learning_rate": 0.0008031676366758898, "loss": 1.7691, "step": 30315 }, { "epoch": 6.28, "learning_rate": 0.00080307222593264, "loss": 1.7707, "step": 30320 }, { "epoch": 6.28, "learning_rate": 0.0008029768151893903, "loss": 1.7681, "step": 30325 }, { "epoch": 6.28, "learning_rate": 0.0008028814044461406, "loss": 1.7727, "step": 30330 }, { "epoch": 6.28, "learning_rate": 0.000802785993702891, "loss": 1.7735, "step": 30335 }, { "epoch": 6.29, "learning_rate": 0.0008026905829596413, "loss": 1.7711, "step": 30340 }, { "epoch": 6.29, "learning_rate": 0.0008025951722163916, "loss": 1.7754, "step": 30345 }, { "epoch": 6.29, "learning_rate": 0.0008024997614731418, "loss": 1.7725, "step": 30350 }, { "epoch": 6.29, "learning_rate": 0.0008024043507298921, "loss": 1.7754, "step": 30355 }, { "epoch": 6.29, "learning_rate": 0.0008023089399866425, "loss": 1.7718, "step": 30360 }, { "epoch": 6.29, "learning_rate": 0.0008022135292433929, "loss": 1.7791, "step": 30365 }, { "epoch": 6.29, "learning_rate": 0.0008021181185001432, "loss": 1.7754, "step": 30370 }, { "epoch": 6.29, "learning_rate": 0.0008020227077568935, "loss": 1.7755, "step": 30375 }, { "epoch": 6.29, "learning_rate": 0.0008019272970136437, "loss": 1.7693, "step": 30380 }, { "epoch": 6.29, "learning_rate": 0.000801831886270394, "loss": 1.7701, "step": 30385 }, { "epoch": 6.3, "learning_rate": 0.0008017364755271443, "loss": 1.7739, "step": 30390 }, { "epoch": 6.3, "learning_rate": 0.0008016410647838947, "loss": 1.7775, "step": 30395 }, { "epoch": 6.3, "learning_rate": 0.000801545654040645, "loss": 1.7712, "step": 30400 }, { "epoch": 6.3, "learning_rate": 0.0008014502432973954, "loss": 1.7748, "step": 30405 }, { "epoch": 6.3, "learning_rate": 0.0008013548325541456, "loss": 1.7674, "step": 30410 }, { "epoch": 6.3, "learning_rate": 0.0008012594218108959, "loss": 1.7687, "step": 30415 }, { "epoch": 6.3, "learning_rate": 0.0008011640110676463, "loss": 1.7756, "step": 30420 }, { "epoch": 6.3, "learning_rate": 0.0008010686003243966, "loss": 1.7698, "step": 30425 }, { "epoch": 6.3, "learning_rate": 0.0008009731895811469, "loss": 1.7684, "step": 30430 }, { "epoch": 6.31, "learning_rate": 0.0008008777788378971, "loss": 1.7708, "step": 30435 }, { "epoch": 6.31, "learning_rate": 0.0008007823680946474, "loss": 1.768, "step": 30440 }, { "epoch": 6.31, "learning_rate": 0.0008006869573513977, "loss": 1.7695, "step": 30445 }, { "epoch": 6.31, "learning_rate": 0.0008005915466081482, "loss": 1.768, "step": 30450 }, { "epoch": 6.31, "learning_rate": 0.0008004961358648985, "loss": 1.777, "step": 30455 }, { "epoch": 6.31, "learning_rate": 0.0008004007251216488, "loss": 1.7772, "step": 30460 }, { "epoch": 6.31, "learning_rate": 0.000800305314378399, "loss": 1.7718, "step": 30465 }, { "epoch": 6.31, "learning_rate": 0.0008002099036351493, "loss": 1.7737, "step": 30470 }, { "epoch": 6.31, "learning_rate": 0.0008001144928918996, "loss": 1.7706, "step": 30475 }, { "epoch": 6.31, "learning_rate": 0.00080001908214865, "loss": 1.7739, "step": 30480 }, { "epoch": 6.32, "learning_rate": 0.0007999236714054003, "loss": 1.7755, "step": 30485 }, { "epoch": 6.32, "learning_rate": 0.0007998282606621505, "loss": 1.7737, "step": 30490 }, { "epoch": 6.32, "learning_rate": 0.0007997328499189009, "loss": 1.7717, "step": 30495 }, { "epoch": 6.32, "learning_rate": 0.0007996374391756512, "loss": 1.7696, "step": 30500 }, { "epoch": 6.32, "learning_rate": 0.0007995420284324015, "loss": 1.7701, "step": 30505 }, { "epoch": 6.32, "learning_rate": 0.0007994466176891519, "loss": 1.7746, "step": 30510 }, { "epoch": 6.32, "learning_rate": 0.0007993512069459022, "loss": 1.7759, "step": 30515 }, { "epoch": 6.32, "learning_rate": 0.0007992557962026524, "loss": 1.7705, "step": 30520 }, { "epoch": 6.32, "learning_rate": 0.0007991603854594027, "loss": 1.7731, "step": 30525 }, { "epoch": 6.32, "learning_rate": 0.000799064974716153, "loss": 1.7753, "step": 30530 }, { "epoch": 6.33, "learning_rate": 0.0007989695639729033, "loss": 1.7692, "step": 30535 }, { "epoch": 6.33, "learning_rate": 0.0007988741532296537, "loss": 1.7723, "step": 30540 }, { "epoch": 6.33, "learning_rate": 0.000798778742486404, "loss": 1.7787, "step": 30545 }, { "epoch": 6.33, "learning_rate": 0.0007986833317431543, "loss": 1.7728, "step": 30550 }, { "epoch": 6.33, "learning_rate": 0.0007985879209999046, "loss": 1.7722, "step": 30555 }, { "epoch": 6.33, "learning_rate": 0.0007984925102566549, "loss": 1.7757, "step": 30560 }, { "epoch": 6.33, "learning_rate": 0.0007983970995134052, "loss": 1.7761, "step": 30565 }, { "epoch": 6.33, "learning_rate": 0.0007983016887701556, "loss": 1.771, "step": 30570 }, { "epoch": 6.33, "learning_rate": 0.0007982062780269058, "loss": 1.7793, "step": 30575 }, { "epoch": 6.34, "learning_rate": 0.0007981108672836561, "loss": 1.7761, "step": 30580 }, { "epoch": 6.34, "learning_rate": 0.0007980154565404064, "loss": 1.7743, "step": 30585 }, { "epoch": 6.34, "learning_rate": 0.0007979200457971568, "loss": 1.7773, "step": 30590 }, { "epoch": 6.34, "learning_rate": 0.0007978246350539071, "loss": 1.7708, "step": 30595 }, { "epoch": 6.34, "learning_rate": 0.0007977292243106575, "loss": 1.771, "step": 30600 }, { "epoch": 6.34, "learning_rate": 0.0007976338135674077, "loss": 1.7768, "step": 30605 }, { "epoch": 6.34, "learning_rate": 0.000797538402824158, "loss": 1.7702, "step": 30610 }, { "epoch": 6.34, "learning_rate": 0.0007974429920809083, "loss": 1.766, "step": 30615 }, { "epoch": 6.34, "learning_rate": 0.0007973475813376586, "loss": 1.771, "step": 30620 }, { "epoch": 6.34, "learning_rate": 0.000797252170594409, "loss": 1.7692, "step": 30625 }, { "epoch": 6.35, "learning_rate": 0.0007971567598511592, "loss": 1.7722, "step": 30630 }, { "epoch": 6.35, "learning_rate": 0.0007970613491079096, "loss": 1.774, "step": 30635 }, { "epoch": 6.35, "learning_rate": 0.0007969659383646599, "loss": 1.7786, "step": 30640 }, { "epoch": 6.35, "learning_rate": 0.0007968705276214102, "loss": 1.7682, "step": 30645 }, { "epoch": 6.35, "learning_rate": 0.0007967751168781605, "loss": 1.7743, "step": 30650 }, { "epoch": 6.35, "learning_rate": 0.0007966797061349109, "loss": 1.774, "step": 30655 }, { "epoch": 6.35, "learning_rate": 0.0007965842953916611, "loss": 1.7761, "step": 30660 }, { "epoch": 6.35, "learning_rate": 0.0007964888846484114, "loss": 1.7719, "step": 30665 }, { "epoch": 6.35, "learning_rate": 0.0007963934739051617, "loss": 1.7748, "step": 30670 }, { "epoch": 6.35, "learning_rate": 0.000796298063161912, "loss": 1.7751, "step": 30675 }, { "epoch": 6.36, "learning_rate": 0.0007962026524186624, "loss": 1.7733, "step": 30680 }, { "epoch": 6.36, "learning_rate": 0.0007961072416754128, "loss": 1.7735, "step": 30685 }, { "epoch": 6.36, "learning_rate": 0.000796011830932163, "loss": 1.7731, "step": 30690 }, { "epoch": 6.36, "learning_rate": 0.0007959164201889133, "loss": 1.7728, "step": 30695 }, { "epoch": 6.36, "learning_rate": 0.0007958210094456636, "loss": 1.7711, "step": 30700 }, { "epoch": 6.36, "learning_rate": 0.0007957255987024139, "loss": 1.7737, "step": 30705 }, { "epoch": 6.36, "learning_rate": 0.0007956301879591642, "loss": 1.7731, "step": 30710 }, { "epoch": 6.36, "learning_rate": 0.0007955347772159145, "loss": 1.776, "step": 30715 }, { "epoch": 6.36, "learning_rate": 0.0007954393664726648, "loss": 1.7736, "step": 30720 }, { "epoch": 6.37, "learning_rate": 0.0007953439557294152, "loss": 1.775, "step": 30725 }, { "epoch": 6.37, "learning_rate": 0.0007952485449861655, "loss": 1.7665, "step": 30730 }, { "epoch": 6.37, "learning_rate": 0.0007951531342429158, "loss": 1.7715, "step": 30735 }, { "epoch": 6.37, "learning_rate": 0.000795057723499666, "loss": 1.7721, "step": 30740 }, { "epoch": 6.37, "learning_rate": 0.0007949623127564164, "loss": 1.7704, "step": 30745 }, { "epoch": 6.37, "learning_rate": 0.0007948669020131667, "loss": 1.7713, "step": 30750 }, { "epoch": 6.37, "learning_rate": 0.000794771491269917, "loss": 1.7725, "step": 30755 }, { "epoch": 6.37, "learning_rate": 0.0007946760805266673, "loss": 1.7782, "step": 30760 }, { "epoch": 6.37, "learning_rate": 0.0007945806697834176, "loss": 1.7669, "step": 30765 }, { "epoch": 6.37, "learning_rate": 0.0007944852590401678, "loss": 1.7691, "step": 30770 }, { "epoch": 6.38, "learning_rate": 0.0007943898482969183, "loss": 1.7721, "step": 30775 }, { "epoch": 6.38, "learning_rate": 0.0007942944375536686, "loss": 1.7726, "step": 30780 }, { "epoch": 6.38, "learning_rate": 0.0007941990268104189, "loss": 1.7768, "step": 30785 }, { "epoch": 6.38, "learning_rate": 0.0007941036160671692, "loss": 1.7707, "step": 30790 }, { "epoch": 6.38, "learning_rate": 0.0007940082053239195, "loss": 1.7683, "step": 30795 }, { "epoch": 6.38, "learning_rate": 0.0007939127945806697, "loss": 1.774, "step": 30800 }, { "epoch": 6.38, "learning_rate": 0.0007938173838374201, "loss": 1.7689, "step": 30805 }, { "epoch": 6.38, "learning_rate": 0.0007937219730941704, "loss": 1.7735, "step": 30810 }, { "epoch": 6.38, "learning_rate": 0.0007936265623509207, "loss": 1.7725, "step": 30815 }, { "epoch": 6.38, "learning_rate": 0.0007935311516076711, "loss": 1.7701, "step": 30820 }, { "epoch": 6.39, "learning_rate": 0.0007934357408644213, "loss": 1.7682, "step": 30825 }, { "epoch": 6.39, "learning_rate": 0.0007933403301211717, "loss": 1.7747, "step": 30830 }, { "epoch": 6.39, "learning_rate": 0.000793244919377922, "loss": 1.7762, "step": 30835 }, { "epoch": 6.39, "learning_rate": 0.0007931495086346723, "loss": 1.7706, "step": 30840 }, { "epoch": 6.39, "learning_rate": 0.0007930540978914226, "loss": 1.7704, "step": 30845 }, { "epoch": 6.39, "learning_rate": 0.0007929586871481729, "loss": 1.7702, "step": 30850 }, { "epoch": 6.39, "learning_rate": 0.0007928632764049231, "loss": 1.7748, "step": 30855 }, { "epoch": 6.39, "learning_rate": 0.0007927678656616735, "loss": 1.774, "step": 30860 }, { "epoch": 6.39, "learning_rate": 0.0007926724549184239, "loss": 1.7701, "step": 30865 }, { "epoch": 6.4, "learning_rate": 0.0007925770441751742, "loss": 1.7733, "step": 30870 }, { "epoch": 6.4, "learning_rate": 0.0007924816334319245, "loss": 1.7763, "step": 30875 }, { "epoch": 6.4, "learning_rate": 0.0007923862226886748, "loss": 1.774, "step": 30880 }, { "epoch": 6.4, "learning_rate": 0.000792290811945425, "loss": 1.778, "step": 30885 }, { "epoch": 6.4, "learning_rate": 0.0007921954012021754, "loss": 1.7747, "step": 30890 }, { "epoch": 6.4, "learning_rate": 0.0007920999904589257, "loss": 1.7749, "step": 30895 }, { "epoch": 6.4, "learning_rate": 0.000792004579715676, "loss": 1.7749, "step": 30900 }, { "epoch": 6.4, "learning_rate": 0.0007919091689724263, "loss": 1.7731, "step": 30905 }, { "epoch": 6.4, "learning_rate": 0.0007918137582291766, "loss": 1.7698, "step": 30910 }, { "epoch": 6.4, "learning_rate": 0.0007917183474859269, "loss": 1.7672, "step": 30915 }, { "epoch": 6.41, "learning_rate": 0.0007916229367426773, "loss": 1.7735, "step": 30920 }, { "epoch": 6.41, "learning_rate": 0.0007915275259994276, "loss": 1.7737, "step": 30925 }, { "epoch": 6.41, "learning_rate": 0.0007914321152561779, "loss": 1.7739, "step": 30930 }, { "epoch": 6.41, "learning_rate": 0.0007913367045129282, "loss": 1.7765, "step": 30935 }, { "epoch": 6.41, "learning_rate": 0.0007912412937696784, "loss": 1.7693, "step": 30940 }, { "epoch": 6.41, "learning_rate": 0.0007911458830264287, "loss": 1.7707, "step": 30945 }, { "epoch": 6.41, "learning_rate": 0.0007910504722831791, "loss": 1.7716, "step": 30950 }, { "epoch": 6.41, "learning_rate": 0.0007909550615399295, "loss": 1.775, "step": 30955 }, { "epoch": 6.41, "learning_rate": 0.0007908596507966798, "loss": 1.7737, "step": 30960 }, { "epoch": 6.41, "learning_rate": 0.00079076424005343, "loss": 1.7735, "step": 30965 }, { "epoch": 6.42, "learning_rate": 0.0007906688293101803, "loss": 1.771, "step": 30970 }, { "epoch": 6.42, "learning_rate": 0.0007905734185669306, "loss": 1.7716, "step": 30975 }, { "epoch": 6.42, "learning_rate": 0.000790478007823681, "loss": 1.7731, "step": 30980 }, { "epoch": 6.42, "learning_rate": 0.0007903825970804313, "loss": 1.7745, "step": 30985 }, { "epoch": 6.42, "learning_rate": 0.0007902871863371816, "loss": 1.7693, "step": 30990 }, { "epoch": 6.42, "learning_rate": 0.0007901917755939318, "loss": 1.766, "step": 30995 }, { "epoch": 6.42, "learning_rate": 0.0007900963648506822, "loss": 1.7735, "step": 31000 }, { "epoch": 6.42, "learning_rate": 0.0007900009541074325, "loss": 1.7712, "step": 31005 }, { "epoch": 6.42, "learning_rate": 0.0007899055433641829, "loss": 1.7647, "step": 31010 }, { "epoch": 6.43, "learning_rate": 0.0007898101326209332, "loss": 1.7689, "step": 31015 }, { "epoch": 6.43, "learning_rate": 0.0007897147218776835, "loss": 1.7693, "step": 31020 }, { "epoch": 6.43, "learning_rate": 0.0007896193111344337, "loss": 1.7703, "step": 31025 }, { "epoch": 6.43, "learning_rate": 0.000789523900391184, "loss": 1.77, "step": 31030 }, { "epoch": 6.43, "learning_rate": 0.0007894284896479343, "loss": 1.7744, "step": 31035 }, { "epoch": 6.43, "learning_rate": 0.0007893330789046847, "loss": 1.7707, "step": 31040 }, { "epoch": 6.43, "learning_rate": 0.000789237668161435, "loss": 1.7726, "step": 31045 }, { "epoch": 6.43, "learning_rate": 0.0007891422574181853, "loss": 1.7785, "step": 31050 }, { "epoch": 6.43, "learning_rate": 0.0007890468466749356, "loss": 1.7675, "step": 31055 }, { "epoch": 6.43, "learning_rate": 0.0007889514359316859, "loss": 1.7723, "step": 31060 }, { "epoch": 6.44, "learning_rate": 0.0007888560251884363, "loss": 1.7723, "step": 31065 }, { "epoch": 6.44, "learning_rate": 0.0007887606144451866, "loss": 1.7702, "step": 31070 }, { "epoch": 6.44, "learning_rate": 0.0007886652037019369, "loss": 1.7796, "step": 31075 }, { "epoch": 6.44, "learning_rate": 0.0007885697929586871, "loss": 1.7762, "step": 31080 }, { "epoch": 6.44, "learning_rate": 0.0007884743822154374, "loss": 1.7751, "step": 31085 }, { "epoch": 6.44, "learning_rate": 0.0007883789714721877, "loss": 1.7749, "step": 31090 }, { "epoch": 6.44, "learning_rate": 0.0007882835607289382, "loss": 1.7694, "step": 31095 }, { "epoch": 6.44, "learning_rate": 0.0007881881499856885, "loss": 1.774, "step": 31100 }, { "epoch": 6.44, "learning_rate": 0.0007880927392424388, "loss": 1.7701, "step": 31105 }, { "epoch": 6.44, "learning_rate": 0.000787997328499189, "loss": 1.7692, "step": 31110 }, { "epoch": 6.45, "learning_rate": 0.0007879019177559393, "loss": 1.7721, "step": 31115 }, { "epoch": 6.45, "learning_rate": 0.0007878065070126896, "loss": 1.7685, "step": 31120 }, { "epoch": 6.45, "learning_rate": 0.00078771109626944, "loss": 1.7696, "step": 31125 }, { "epoch": 6.45, "learning_rate": 0.0007876156855261903, "loss": 1.7687, "step": 31130 }, { "epoch": 6.45, "learning_rate": 0.0007875202747829405, "loss": 1.7687, "step": 31135 }, { "epoch": 6.45, "learning_rate": 0.0007874248640396909, "loss": 1.7757, "step": 31140 }, { "epoch": 6.45, "learning_rate": 0.0007873294532964412, "loss": 1.7728, "step": 31145 }, { "epoch": 6.45, "learning_rate": 0.0007872340425531915, "loss": 1.7728, "step": 31150 }, { "epoch": 6.45, "learning_rate": 0.0007871386318099419, "loss": 1.7637, "step": 31155 }, { "epoch": 6.46, "learning_rate": 0.0007870432210666922, "loss": 1.7712, "step": 31160 }, { "epoch": 6.46, "learning_rate": 0.0007869478103234424, "loss": 1.7682, "step": 31165 }, { "epoch": 6.46, "learning_rate": 0.0007868523995801927, "loss": 1.7644, "step": 31170 }, { "epoch": 6.46, "learning_rate": 0.000786756988836943, "loss": 1.7756, "step": 31175 }, { "epoch": 6.46, "learning_rate": 0.0007866615780936933, "loss": 1.7655, "step": 31180 }, { "epoch": 6.46, "learning_rate": 0.0007865661673504438, "loss": 1.7771, "step": 31185 }, { "epoch": 6.46, "learning_rate": 0.000786470756607194, "loss": 1.7757, "step": 31190 }, { "epoch": 6.46, "learning_rate": 0.0007863753458639443, "loss": 1.7711, "step": 31195 }, { "epoch": 6.46, "learning_rate": 0.0007862799351206946, "loss": 1.7711, "step": 31200 }, { "epoch": 6.46, "learning_rate": 0.0007861845243774449, "loss": 1.7691, "step": 31205 }, { "epoch": 6.47, "learning_rate": 0.0007860891136341952, "loss": 1.7722, "step": 31210 }, { "epoch": 6.47, "learning_rate": 0.0007859937028909456, "loss": 1.7758, "step": 31215 }, { "epoch": 6.47, "learning_rate": 0.0007858982921476958, "loss": 1.7686, "step": 31220 }, { "epoch": 6.47, "learning_rate": 0.0007858028814044461, "loss": 1.7753, "step": 31225 }, { "epoch": 6.47, "learning_rate": 0.0007857074706611965, "loss": 1.7685, "step": 31230 }, { "epoch": 6.47, "learning_rate": 0.0007856120599179468, "loss": 1.7764, "step": 31235 }, { "epoch": 6.47, "learning_rate": 0.0007855166491746972, "loss": 1.7702, "step": 31240 }, { "epoch": 6.47, "learning_rate": 0.0007854212384314475, "loss": 1.7694, "step": 31245 }, { "epoch": 6.47, "learning_rate": 0.0007853258276881977, "loss": 1.7722, "step": 31250 }, { "epoch": 6.48, "learning_rate": 0.000785230416944948, "loss": 1.776, "step": 31255 }, { "epoch": 6.48, "learning_rate": 0.0007851350062016983, "loss": 1.7748, "step": 31260 }, { "epoch": 6.48, "learning_rate": 0.0007850395954584486, "loss": 1.7757, "step": 31265 }, { "epoch": 6.48, "learning_rate": 0.000784944184715199, "loss": 1.7698, "step": 31270 }, { "epoch": 6.48, "learning_rate": 0.0007848487739719492, "loss": 1.7707, "step": 31275 }, { "epoch": 6.48, "learning_rate": 0.0007847533632286996, "loss": 1.7713, "step": 31280 }, { "epoch": 6.48, "learning_rate": 0.0007846579524854499, "loss": 1.7727, "step": 31285 }, { "epoch": 6.48, "learning_rate": 0.0007845625417422002, "loss": 1.7748, "step": 31290 }, { "epoch": 6.48, "learning_rate": 0.0007844671309989505, "loss": 1.7672, "step": 31295 }, { "epoch": 6.48, "learning_rate": 0.0007843717202557009, "loss": 1.7703, "step": 31300 }, { "epoch": 6.49, "learning_rate": 0.0007842763095124511, "loss": 1.7665, "step": 31305 }, { "epoch": 6.49, "learning_rate": 0.0007841808987692014, "loss": 1.7727, "step": 31310 }, { "epoch": 6.49, "learning_rate": 0.0007840854880259517, "loss": 1.7712, "step": 31315 }, { "epoch": 6.49, "learning_rate": 0.000783990077282702, "loss": 1.769, "step": 31320 }, { "epoch": 6.49, "learning_rate": 0.0007838946665394524, "loss": 1.7696, "step": 31325 }, { "epoch": 6.49, "learning_rate": 0.0007837992557962027, "loss": 1.7708, "step": 31330 }, { "epoch": 6.49, "learning_rate": 0.000783703845052953, "loss": 1.7701, "step": 31335 }, { "epoch": 6.49, "learning_rate": 0.0007836084343097033, "loss": 1.7706, "step": 31340 }, { "epoch": 6.49, "learning_rate": 0.0007835130235664536, "loss": 1.7695, "step": 31345 }, { "epoch": 6.49, "learning_rate": 0.0007834176128232039, "loss": 1.7741, "step": 31350 }, { "epoch": 6.5, "learning_rate": 0.0007833222020799541, "loss": 1.7731, "step": 31355 }, { "epoch": 6.5, "learning_rate": 0.0007832267913367045, "loss": 1.7743, "step": 31360 }, { "epoch": 6.5, "learning_rate": 0.0007831313805934548, "loss": 1.7773, "step": 31365 }, { "epoch": 6.5, "learning_rate": 0.0007830359698502052, "loss": 1.7679, "step": 31370 }, { "epoch": 6.5, "learning_rate": 0.0007829405591069555, "loss": 1.7702, "step": 31375 }, { "epoch": 6.5, "learning_rate": 0.0007828451483637058, "loss": 1.7727, "step": 31380 }, { "epoch": 6.5, "learning_rate": 0.000782749737620456, "loss": 1.7699, "step": 31385 }, { "epoch": 6.5, "learning_rate": 0.0007826543268772064, "loss": 1.771, "step": 31390 }, { "epoch": 6.5, "learning_rate": 0.0007825589161339567, "loss": 1.7676, "step": 31395 }, { "epoch": 6.51, "learning_rate": 0.000782463505390707, "loss": 1.77, "step": 31400 }, { "epoch": 6.51, "learning_rate": 0.0007823680946474573, "loss": 1.7729, "step": 31405 }, { "epoch": 6.51, "learning_rate": 0.0007822726839042076, "loss": 1.7707, "step": 31410 }, { "epoch": 6.51, "learning_rate": 0.0007821772731609579, "loss": 1.7753, "step": 31415 }, { "epoch": 6.51, "learning_rate": 0.0007820818624177083, "loss": 1.7757, "step": 31420 }, { "epoch": 6.51, "learning_rate": 0.0007819864516744586, "loss": 1.7715, "step": 31425 }, { "epoch": 6.51, "learning_rate": 0.0007818910409312089, "loss": 1.7645, "step": 31430 }, { "epoch": 6.51, "learning_rate": 0.0007817956301879592, "loss": 1.7723, "step": 31435 }, { "epoch": 6.51, "learning_rate": 0.0007817002194447094, "loss": 1.7708, "step": 31440 }, { "epoch": 6.51, "learning_rate": 0.0007816048087014597, "loss": 1.765, "step": 31445 }, { "epoch": 6.52, "learning_rate": 0.0007815093979582101, "loss": 1.7709, "step": 31450 }, { "epoch": 6.52, "learning_rate": 0.0007814139872149604, "loss": 1.7666, "step": 31455 }, { "epoch": 6.52, "learning_rate": 0.0007813185764717108, "loss": 1.7699, "step": 31460 }, { "epoch": 6.52, "learning_rate": 0.0007812231657284611, "loss": 1.7654, "step": 31465 }, { "epoch": 6.52, "learning_rate": 0.0007811277549852113, "loss": 1.7656, "step": 31470 }, { "epoch": 6.52, "learning_rate": 0.0007810323442419617, "loss": 1.7724, "step": 31475 }, { "epoch": 6.52, "learning_rate": 0.000780936933498712, "loss": 1.7681, "step": 31480 }, { "epoch": 6.52, "learning_rate": 0.0007808415227554623, "loss": 1.767, "step": 31485 }, { "epoch": 6.52, "learning_rate": 0.0007807461120122126, "loss": 1.7696, "step": 31490 }, { "epoch": 6.52, "learning_rate": 0.0007806507012689629, "loss": 1.7718, "step": 31495 }, { "epoch": 6.53, "learning_rate": 0.0007805552905257131, "loss": 1.7665, "step": 31500 }, { "epoch": 6.53, "learning_rate": 0.0007804598797824635, "loss": 1.7742, "step": 31505 }, { "epoch": 6.53, "learning_rate": 0.0007803644690392139, "loss": 1.7686, "step": 31510 }, { "epoch": 6.53, "learning_rate": 0.0007802690582959642, "loss": 1.7708, "step": 31515 }, { "epoch": 6.53, "learning_rate": 0.0007801736475527145, "loss": 1.7682, "step": 31520 }, { "epoch": 6.53, "learning_rate": 0.0007800782368094647, "loss": 1.771, "step": 31525 }, { "epoch": 6.53, "learning_rate": 0.000779982826066215, "loss": 1.7753, "step": 31530 }, { "epoch": 6.53, "learning_rate": 0.0007798874153229654, "loss": 1.7685, "step": 31535 }, { "epoch": 6.53, "learning_rate": 0.0007797920045797157, "loss": 1.7726, "step": 31540 }, { "epoch": 6.54, "learning_rate": 0.000779696593836466, "loss": 1.7702, "step": 31545 }, { "epoch": 6.54, "learning_rate": 0.0007796011830932163, "loss": 1.7714, "step": 31550 }, { "epoch": 6.54, "learning_rate": 0.0007795057723499666, "loss": 1.772, "step": 31555 }, { "epoch": 6.54, "learning_rate": 0.0007794103616067169, "loss": 1.7681, "step": 31560 }, { "epoch": 6.54, "learning_rate": 0.0007793149508634673, "loss": 1.7638, "step": 31565 }, { "epoch": 6.54, "learning_rate": 0.0007792195401202176, "loss": 1.7732, "step": 31570 }, { "epoch": 6.54, "learning_rate": 0.0007791241293769679, "loss": 1.7759, "step": 31575 }, { "epoch": 6.54, "learning_rate": 0.0007790287186337181, "loss": 1.7689, "step": 31580 }, { "epoch": 6.54, "learning_rate": 0.0007789333078904684, "loss": 1.7731, "step": 31585 }, { "epoch": 6.54, "learning_rate": 0.0007788378971472187, "loss": 1.7718, "step": 31590 }, { "epoch": 6.55, "learning_rate": 0.0007787424864039691, "loss": 1.7697, "step": 31595 }, { "epoch": 6.55, "learning_rate": 0.0007786470756607195, "loss": 1.7689, "step": 31600 }, { "epoch": 6.55, "learning_rate": 0.0007785516649174698, "loss": 1.7699, "step": 31605 }, { "epoch": 6.55, "learning_rate": 0.00077845625417422, "loss": 1.7697, "step": 31610 }, { "epoch": 6.55, "learning_rate": 0.0007783608434309703, "loss": 1.7696, "step": 31615 }, { "epoch": 6.55, "learning_rate": 0.0007782654326877206, "loss": 1.7735, "step": 31620 }, { "epoch": 6.55, "learning_rate": 0.000778170021944471, "loss": 1.7713, "step": 31625 }, { "epoch": 6.55, "learning_rate": 0.0007780746112012213, "loss": 1.7692, "step": 31630 }, { "epoch": 6.55, "learning_rate": 0.0007779792004579716, "loss": 1.7647, "step": 31635 }, { "epoch": 6.55, "learning_rate": 0.0007778837897147218, "loss": 1.7675, "step": 31640 }, { "epoch": 6.56, "learning_rate": 0.0007777883789714722, "loss": 1.7707, "step": 31645 }, { "epoch": 6.56, "learning_rate": 0.0007776929682282225, "loss": 1.7685, "step": 31650 }, { "epoch": 6.56, "learning_rate": 0.0007775975574849729, "loss": 1.7727, "step": 31655 }, { "epoch": 6.56, "learning_rate": 0.0007775021467417232, "loss": 1.7729, "step": 31660 }, { "epoch": 6.56, "learning_rate": 0.0007774067359984734, "loss": 1.7714, "step": 31665 }, { "epoch": 6.56, "learning_rate": 0.0007773113252552237, "loss": 1.7661, "step": 31670 }, { "epoch": 6.56, "learning_rate": 0.000777215914511974, "loss": 1.7682, "step": 31675 }, { "epoch": 6.56, "learning_rate": 0.0007771205037687244, "loss": 1.7703, "step": 31680 }, { "epoch": 6.56, "learning_rate": 0.0007770250930254747, "loss": 1.7726, "step": 31685 }, { "epoch": 6.57, "learning_rate": 0.0007769296822822251, "loss": 1.7694, "step": 31690 }, { "epoch": 6.57, "learning_rate": 0.0007768342715389753, "loss": 1.7693, "step": 31695 }, { "epoch": 6.57, "learning_rate": 0.0007767388607957256, "loss": 1.7747, "step": 31700 }, { "epoch": 6.57, "learning_rate": 0.0007766434500524759, "loss": 1.7686, "step": 31705 }, { "epoch": 6.57, "learning_rate": 0.0007765480393092263, "loss": 1.7675, "step": 31710 }, { "epoch": 6.57, "learning_rate": 0.0007764526285659766, "loss": 1.7659, "step": 31715 }, { "epoch": 6.57, "learning_rate": 0.0007763572178227268, "loss": 1.7715, "step": 31720 }, { "epoch": 6.57, "learning_rate": 0.0007762618070794771, "loss": 1.7671, "step": 31725 }, { "epoch": 6.57, "learning_rate": 0.0007761663963362274, "loss": 1.771, "step": 31730 }, { "epoch": 6.57, "learning_rate": 0.0007760709855929778, "loss": 1.7706, "step": 31735 }, { "epoch": 6.58, "learning_rate": 0.0007759755748497282, "loss": 1.77, "step": 31740 }, { "epoch": 6.58, "learning_rate": 0.0007758801641064785, "loss": 1.7653, "step": 31745 }, { "epoch": 6.58, "learning_rate": 0.0007757847533632287, "loss": 1.7683, "step": 31750 }, { "epoch": 6.58, "learning_rate": 0.000775689342619979, "loss": 1.7726, "step": 31755 }, { "epoch": 6.58, "learning_rate": 0.0007755939318767293, "loss": 1.7707, "step": 31760 }, { "epoch": 6.58, "learning_rate": 0.0007754985211334796, "loss": 1.7701, "step": 31765 }, { "epoch": 6.58, "learning_rate": 0.00077540311039023, "loss": 1.7708, "step": 31770 }, { "epoch": 6.58, "learning_rate": 0.0007753076996469803, "loss": 1.7673, "step": 31775 }, { "epoch": 6.58, "learning_rate": 0.0007752122889037305, "loss": 1.7735, "step": 31780 }, { "epoch": 6.58, "learning_rate": 0.0007751168781604809, "loss": 1.7712, "step": 31785 }, { "epoch": 6.59, "learning_rate": 0.0007750214674172312, "loss": 1.7714, "step": 31790 }, { "epoch": 6.59, "learning_rate": 0.0007749260566739815, "loss": 1.768, "step": 31795 }, { "epoch": 6.59, "learning_rate": 0.0007748306459307319, "loss": 1.7683, "step": 31800 }, { "epoch": 6.59, "learning_rate": 0.0007747352351874821, "loss": 1.7708, "step": 31805 }, { "epoch": 6.59, "learning_rate": 0.0007746398244442324, "loss": 1.7728, "step": 31810 }, { "epoch": 6.59, "learning_rate": 0.0007745444137009827, "loss": 1.7653, "step": 31815 }, { "epoch": 6.59, "learning_rate": 0.000774449002957733, "loss": 1.7736, "step": 31820 }, { "epoch": 6.59, "learning_rate": 0.0007743535922144833, "loss": 1.7694, "step": 31825 }, { "epoch": 6.59, "learning_rate": 0.0007742581814712338, "loss": 1.7708, "step": 31830 }, { "epoch": 6.6, "learning_rate": 0.000774162770727984, "loss": 1.7698, "step": 31835 }, { "epoch": 6.6, "learning_rate": 0.0007740673599847343, "loss": 1.7679, "step": 31840 }, { "epoch": 6.6, "learning_rate": 0.0007739719492414846, "loss": 1.7717, "step": 31845 }, { "epoch": 6.6, "learning_rate": 0.0007738765384982349, "loss": 1.7729, "step": 31850 }, { "epoch": 6.6, "learning_rate": 0.0007737811277549852, "loss": 1.7694, "step": 31855 }, { "epoch": 6.6, "learning_rate": 0.0007736857170117356, "loss": 1.7724, "step": 31860 }, { "epoch": 6.6, "learning_rate": 0.0007735903062684858, "loss": 1.7704, "step": 31865 }, { "epoch": 6.6, "learning_rate": 0.0007734948955252361, "loss": 1.7686, "step": 31870 }, { "epoch": 6.6, "learning_rate": 0.0007733994847819865, "loss": 1.7651, "step": 31875 }, { "epoch": 6.6, "learning_rate": 0.0007733040740387368, "loss": 1.769, "step": 31880 }, { "epoch": 6.61, "learning_rate": 0.0007732086632954872, "loss": 1.7724, "step": 31885 }, { "epoch": 6.61, "learning_rate": 0.0007731132525522374, "loss": 1.765, "step": 31890 }, { "epoch": 6.61, "learning_rate": 0.0007730178418089877, "loss": 1.7684, "step": 31895 }, { "epoch": 6.61, "learning_rate": 0.000772922431065738, "loss": 1.771, "step": 31900 }, { "epoch": 6.61, "learning_rate": 0.0007728270203224883, "loss": 1.7733, "step": 31905 }, { "epoch": 6.61, "learning_rate": 0.0007727316095792386, "loss": 1.7685, "step": 31910 }, { "epoch": 6.61, "learning_rate": 0.000772636198835989, "loss": 1.7736, "step": 31915 }, { "epoch": 6.61, "learning_rate": 0.0007725407880927393, "loss": 1.769, "step": 31920 }, { "epoch": 6.61, "learning_rate": 0.0007724453773494896, "loss": 1.7711, "step": 31925 }, { "epoch": 6.61, "learning_rate": 0.0007723499666062399, "loss": 1.7676, "step": 31930 }, { "epoch": 6.62, "learning_rate": 0.0007722545558629902, "loss": 1.7732, "step": 31935 }, { "epoch": 6.62, "learning_rate": 0.0007721591451197405, "loss": 1.7702, "step": 31940 }, { "epoch": 6.62, "learning_rate": 0.0007720637343764908, "loss": 1.7728, "step": 31945 }, { "epoch": 6.62, "learning_rate": 0.0007719683236332411, "loss": 1.7655, "step": 31950 }, { "epoch": 6.62, "learning_rate": 0.0007718729128899914, "loss": 1.7681, "step": 31955 }, { "epoch": 6.62, "learning_rate": 0.0007717775021467417, "loss": 1.7675, "step": 31960 }, { "epoch": 6.62, "learning_rate": 0.0007716820914034921, "loss": 1.7719, "step": 31965 }, { "epoch": 6.62, "learning_rate": 0.0007715866806602424, "loss": 1.7663, "step": 31970 }, { "epoch": 6.62, "learning_rate": 0.0007714912699169927, "loss": 1.7685, "step": 31975 }, { "epoch": 6.63, "learning_rate": 0.000771395859173743, "loss": 1.7633, "step": 31980 }, { "epoch": 6.63, "learning_rate": 0.0007713004484304933, "loss": 1.7708, "step": 31985 }, { "epoch": 6.63, "learning_rate": 0.0007712050376872436, "loss": 1.7706, "step": 31990 }, { "epoch": 6.63, "learning_rate": 0.0007711096269439939, "loss": 1.7657, "step": 31995 }, { "epoch": 6.63, "learning_rate": 0.0007710142162007441, "loss": 1.7671, "step": 32000 }, { "epoch": 6.63, "learning_rate": 0.0007709188054574945, "loss": 1.7696, "step": 32005 }, { "epoch": 6.63, "learning_rate": 0.0007708233947142448, "loss": 1.7664, "step": 32010 }, { "epoch": 6.63, "learning_rate": 0.0007707279839709952, "loss": 1.7739, "step": 32015 }, { "epoch": 6.63, "learning_rate": 0.0007706325732277455, "loss": 1.7693, "step": 32020 }, { "epoch": 6.63, "learning_rate": 0.0007705371624844958, "loss": 1.769, "step": 32025 }, { "epoch": 6.64, "learning_rate": 0.000770441751741246, "loss": 1.77, "step": 32030 }, { "epoch": 6.64, "learning_rate": 0.0007703463409979964, "loss": 1.7703, "step": 32035 }, { "epoch": 6.64, "learning_rate": 0.0007702509302547467, "loss": 1.7694, "step": 32040 }, { "epoch": 6.64, "learning_rate": 0.000770155519511497, "loss": 1.7705, "step": 32045 }, { "epoch": 6.64, "learning_rate": 0.0007700601087682473, "loss": 1.7696, "step": 32050 }, { "epoch": 6.64, "learning_rate": 0.0007699646980249975, "loss": 1.7664, "step": 32055 }, { "epoch": 6.64, "learning_rate": 0.0007698692872817479, "loss": 1.7682, "step": 32060 }, { "epoch": 6.64, "learning_rate": 0.0007697738765384983, "loss": 1.768, "step": 32065 }, { "epoch": 6.64, "learning_rate": 0.0007696784657952486, "loss": 1.7712, "step": 32070 }, { "epoch": 6.64, "learning_rate": 0.0007695830550519989, "loss": 1.7703, "step": 32075 }, { "epoch": 6.65, "learning_rate": 0.0007694876443087492, "loss": 1.7728, "step": 32080 }, { "epoch": 6.65, "learning_rate": 0.0007693922335654994, "loss": 1.7662, "step": 32085 }, { "epoch": 6.65, "learning_rate": 0.0007692968228222497, "loss": 1.7699, "step": 32090 }, { "epoch": 6.65, "learning_rate": 0.0007692014120790001, "loss": 1.7698, "step": 32095 }, { "epoch": 6.65, "learning_rate": 0.0007691060013357504, "loss": 1.7687, "step": 32100 }, { "epoch": 6.65, "learning_rate": 0.0007690105905925008, "loss": 1.7696, "step": 32105 }, { "epoch": 6.65, "learning_rate": 0.0007689151798492511, "loss": 1.7659, "step": 32110 }, { "epoch": 6.65, "learning_rate": 0.0007688197691060013, "loss": 1.7686, "step": 32115 }, { "epoch": 6.65, "learning_rate": 0.0007687243583627517, "loss": 1.7695, "step": 32120 }, { "epoch": 6.66, "learning_rate": 0.000768628947619502, "loss": 1.7673, "step": 32125 }, { "epoch": 6.66, "learning_rate": 0.0007685335368762523, "loss": 1.7705, "step": 32130 }, { "epoch": 6.66, "learning_rate": 0.0007684381261330026, "loss": 1.7643, "step": 32135 }, { "epoch": 6.66, "learning_rate": 0.0007683427153897528, "loss": 1.7728, "step": 32140 }, { "epoch": 6.66, "learning_rate": 0.0007682473046465031, "loss": 1.7724, "step": 32145 }, { "epoch": 6.66, "learning_rate": 0.0007681518939032536, "loss": 1.767, "step": 32150 }, { "epoch": 6.66, "learning_rate": 0.0007680564831600039, "loss": 1.7658, "step": 32155 }, { "epoch": 6.66, "learning_rate": 0.0007679610724167542, "loss": 1.7697, "step": 32160 }, { "epoch": 6.66, "learning_rate": 0.0007678656616735045, "loss": 1.7723, "step": 32165 }, { "epoch": 6.66, "learning_rate": 0.0007677702509302547, "loss": 1.7669, "step": 32170 }, { "epoch": 6.67, "learning_rate": 0.000767674840187005, "loss": 1.7656, "step": 32175 }, { "epoch": 6.67, "learning_rate": 0.0007675794294437554, "loss": 1.7737, "step": 32180 }, { "epoch": 6.67, "learning_rate": 0.0007674840187005057, "loss": 1.767, "step": 32185 }, { "epoch": 6.67, "learning_rate": 0.000767388607957256, "loss": 1.7694, "step": 32190 }, { "epoch": 6.67, "learning_rate": 0.0007672931972140064, "loss": 1.7722, "step": 32195 }, { "epoch": 6.67, "learning_rate": 0.0007671977864707566, "loss": 1.7722, "step": 32200 }, { "epoch": 6.67, "learning_rate": 0.0007671023757275069, "loss": 1.7632, "step": 32205 }, { "epoch": 6.67, "learning_rate": 0.0007670069649842573, "loss": 1.7714, "step": 32210 }, { "epoch": 6.67, "learning_rate": 0.0007669115542410076, "loss": 1.7678, "step": 32215 }, { "epoch": 6.67, "learning_rate": 0.0007668161434977579, "loss": 1.7705, "step": 32220 }, { "epoch": 6.68, "learning_rate": 0.0007667207327545081, "loss": 1.7703, "step": 32225 }, { "epoch": 6.68, "learning_rate": 0.0007666253220112584, "loss": 1.7657, "step": 32230 }, { "epoch": 6.68, "learning_rate": 0.0007665299112680087, "loss": 1.7711, "step": 32235 }, { "epoch": 6.68, "learning_rate": 0.0007664345005247591, "loss": 1.7666, "step": 32240 }, { "epoch": 6.68, "learning_rate": 0.0007663390897815095, "loss": 1.7686, "step": 32245 }, { "epoch": 6.68, "learning_rate": 0.0007662436790382598, "loss": 1.7657, "step": 32250 }, { "epoch": 6.68, "learning_rate": 0.00076614826829501, "loss": 1.7717, "step": 32255 }, { "epoch": 6.68, "learning_rate": 0.0007660528575517603, "loss": 1.7591, "step": 32260 }, { "epoch": 6.68, "learning_rate": 0.0007659574468085106, "loss": 1.7695, "step": 32265 }, { "epoch": 6.69, "learning_rate": 0.000765862036065261, "loss": 1.7672, "step": 32270 }, { "epoch": 6.69, "learning_rate": 0.0007657666253220113, "loss": 1.77, "step": 32275 }, { "epoch": 6.69, "learning_rate": 0.0007656712145787615, "loss": 1.7645, "step": 32280 }, { "epoch": 6.69, "learning_rate": 0.0007655758038355118, "loss": 1.7701, "step": 32285 }, { "epoch": 6.69, "learning_rate": 0.0007654803930922622, "loss": 1.7622, "step": 32290 }, { "epoch": 6.69, "learning_rate": 0.0007653849823490125, "loss": 1.77, "step": 32295 }, { "epoch": 6.69, "learning_rate": 0.0007652895716057629, "loss": 1.7715, "step": 32300 }, { "epoch": 6.69, "learning_rate": 0.0007651941608625132, "loss": 1.7693, "step": 32305 }, { "epoch": 6.69, "learning_rate": 0.0007650987501192634, "loss": 1.7655, "step": 32310 }, { "epoch": 6.69, "learning_rate": 0.0007650033393760137, "loss": 1.773, "step": 32315 }, { "epoch": 6.7, "learning_rate": 0.000764907928632764, "loss": 1.7686, "step": 32320 }, { "epoch": 6.7, "learning_rate": 0.0007648125178895144, "loss": 1.7653, "step": 32325 }, { "epoch": 6.7, "learning_rate": 0.0007647171071462647, "loss": 1.7636, "step": 32330 }, { "epoch": 6.7, "learning_rate": 0.0007646216964030151, "loss": 1.7743, "step": 32335 }, { "epoch": 6.7, "learning_rate": 0.0007645262856597653, "loss": 1.769, "step": 32340 }, { "epoch": 6.7, "learning_rate": 0.0007644308749165156, "loss": 1.7712, "step": 32345 }, { "epoch": 6.7, "learning_rate": 0.0007643354641732659, "loss": 1.7728, "step": 32350 }, { "epoch": 6.7, "learning_rate": 0.0007642400534300163, "loss": 1.7651, "step": 32355 }, { "epoch": 6.7, "learning_rate": 0.0007641446426867666, "loss": 1.7711, "step": 32360 }, { "epoch": 6.7, "learning_rate": 0.0007640492319435168, "loss": 1.7695, "step": 32365 }, { "epoch": 6.71, "learning_rate": 0.0007639538212002671, "loss": 1.7668, "step": 32370 }, { "epoch": 6.71, "learning_rate": 0.0007638584104570174, "loss": 1.7687, "step": 32375 }, { "epoch": 6.71, "learning_rate": 0.0007637629997137678, "loss": 1.7728, "step": 32380 }, { "epoch": 6.71, "learning_rate": 0.0007636675889705182, "loss": 1.7757, "step": 32385 }, { "epoch": 6.71, "learning_rate": 0.0007635721782272685, "loss": 1.7667, "step": 32390 }, { "epoch": 6.71, "learning_rate": 0.0007634767674840187, "loss": 1.7697, "step": 32395 }, { "epoch": 6.71, "learning_rate": 0.000763381356740769, "loss": 1.7683, "step": 32400 }, { "epoch": 6.71, "learning_rate": 0.0007632859459975193, "loss": 1.7665, "step": 32405 }, { "epoch": 6.71, "learning_rate": 0.0007631905352542696, "loss": 1.7686, "step": 32410 }, { "epoch": 6.72, "learning_rate": 0.00076309512451102, "loss": 1.7714, "step": 32415 }, { "epoch": 6.72, "learning_rate": 0.0007629997137677702, "loss": 1.7651, "step": 32420 }, { "epoch": 6.72, "learning_rate": 0.0007629043030245206, "loss": 1.7666, "step": 32425 }, { "epoch": 6.72, "learning_rate": 0.0007628088922812709, "loss": 1.7721, "step": 32430 }, { "epoch": 6.72, "learning_rate": 0.0007627134815380212, "loss": 1.7681, "step": 32435 }, { "epoch": 6.72, "learning_rate": 0.0007626180707947715, "loss": 1.7686, "step": 32440 }, { "epoch": 6.72, "learning_rate": 0.0007625226600515219, "loss": 1.7637, "step": 32445 }, { "epoch": 6.72, "learning_rate": 0.0007624272493082721, "loss": 1.7705, "step": 32450 }, { "epoch": 6.72, "learning_rate": 0.0007623318385650224, "loss": 1.77, "step": 32455 }, { "epoch": 6.72, "learning_rate": 0.0007622364278217727, "loss": 1.7737, "step": 32460 }, { "epoch": 6.73, "learning_rate": 0.000762141017078523, "loss": 1.7674, "step": 32465 }, { "epoch": 6.73, "learning_rate": 0.0007620456063352734, "loss": 1.7689, "step": 32470 }, { "epoch": 6.73, "learning_rate": 0.0007619501955920238, "loss": 1.7758, "step": 32475 }, { "epoch": 6.73, "learning_rate": 0.000761854784848774, "loss": 1.7686, "step": 32480 }, { "epoch": 6.73, "learning_rate": 0.0007617593741055243, "loss": 1.7677, "step": 32485 }, { "epoch": 6.73, "learning_rate": 0.0007616639633622746, "loss": 1.7645, "step": 32490 }, { "epoch": 6.73, "learning_rate": 0.0007615685526190249, "loss": 1.7635, "step": 32495 }, { "epoch": 6.73, "learning_rate": 0.0007614731418757752, "loss": 1.7671, "step": 32500 }, { "epoch": 6.73, "learning_rate": 0.0007613777311325255, "loss": 1.7657, "step": 32505 }, { "epoch": 6.74, "learning_rate": 0.0007612823203892758, "loss": 1.7721, "step": 32510 }, { "epoch": 6.74, "learning_rate": 0.0007611869096460261, "loss": 1.7711, "step": 32515 }, { "epoch": 6.74, "learning_rate": 0.0007610914989027765, "loss": 1.7702, "step": 32520 }, { "epoch": 6.74, "learning_rate": 0.0007609960881595268, "loss": 1.7696, "step": 32525 }, { "epoch": 6.74, "learning_rate": 0.0007609006774162772, "loss": 1.7678, "step": 32530 }, { "epoch": 6.74, "learning_rate": 0.0007608052666730274, "loss": 1.7658, "step": 32535 }, { "epoch": 6.74, "learning_rate": 0.0007607098559297777, "loss": 1.767, "step": 32540 }, { "epoch": 6.74, "learning_rate": 0.000760614445186528, "loss": 1.7662, "step": 32545 }, { "epoch": 6.74, "learning_rate": 0.0007605190344432783, "loss": 1.7686, "step": 32550 }, { "epoch": 6.74, "learning_rate": 0.0007604236237000286, "loss": 1.7656, "step": 32555 }, { "epoch": 6.75, "learning_rate": 0.000760328212956779, "loss": 1.7693, "step": 32560 }, { "epoch": 6.75, "learning_rate": 0.0007602328022135293, "loss": 1.7678, "step": 32565 }, { "epoch": 6.75, "learning_rate": 0.0007601373914702796, "loss": 1.7693, "step": 32570 }, { "epoch": 6.75, "learning_rate": 0.0007600419807270299, "loss": 1.7718, "step": 32575 }, { "epoch": 6.75, "learning_rate": 0.0007599465699837802, "loss": 1.7623, "step": 32580 }, { "epoch": 6.75, "learning_rate": 0.0007598511592405305, "loss": 1.7677, "step": 32585 }, { "epoch": 6.75, "learning_rate": 0.0007597557484972808, "loss": 1.7654, "step": 32590 }, { "epoch": 6.75, "learning_rate": 0.0007596603377540311, "loss": 1.7644, "step": 32595 }, { "epoch": 6.75, "learning_rate": 0.0007595649270107814, "loss": 1.7704, "step": 32600 }, { "epoch": 6.75, "learning_rate": 0.0007594695162675317, "loss": 1.769, "step": 32605 }, { "epoch": 6.76, "learning_rate": 0.0007593741055242821, "loss": 1.7687, "step": 32610 }, { "epoch": 6.76, "learning_rate": 0.0007592786947810324, "loss": 1.7646, "step": 32615 }, { "epoch": 6.76, "learning_rate": 0.0007591832840377827, "loss": 1.7647, "step": 32620 }, { "epoch": 6.76, "learning_rate": 0.000759087873294533, "loss": 1.7664, "step": 32625 }, { "epoch": 6.76, "learning_rate": 0.0007589924625512833, "loss": 1.766, "step": 32630 }, { "epoch": 6.76, "learning_rate": 0.0007588970518080336, "loss": 1.7665, "step": 32635 }, { "epoch": 6.76, "learning_rate": 0.0007588016410647839, "loss": 1.769, "step": 32640 }, { "epoch": 6.76, "learning_rate": 0.0007587062303215341, "loss": 1.7626, "step": 32645 }, { "epoch": 6.76, "learning_rate": 0.0007586108195782845, "loss": 1.771, "step": 32650 }, { "epoch": 6.77, "learning_rate": 0.0007585154088350349, "loss": 1.7692, "step": 32655 }, { "epoch": 6.77, "learning_rate": 0.0007584199980917852, "loss": 1.7651, "step": 32660 }, { "epoch": 6.77, "learning_rate": 0.0007583245873485355, "loss": 1.7676, "step": 32665 }, { "epoch": 6.77, "learning_rate": 0.0007582291766052858, "loss": 1.7617, "step": 32670 }, { "epoch": 6.77, "learning_rate": 0.000758133765862036, "loss": 1.7667, "step": 32675 }, { "epoch": 6.77, "learning_rate": 0.0007580383551187864, "loss": 1.7604, "step": 32680 }, { "epoch": 6.77, "learning_rate": 0.0007579429443755367, "loss": 1.768, "step": 32685 }, { "epoch": 6.77, "learning_rate": 0.000757847533632287, "loss": 1.7677, "step": 32690 }, { "epoch": 6.77, "learning_rate": 0.0007577521228890373, "loss": 1.7642, "step": 32695 }, { "epoch": 6.77, "learning_rate": 0.0007576567121457877, "loss": 1.7638, "step": 32700 }, { "epoch": 6.78, "learning_rate": 0.0007575613014025379, "loss": 1.7729, "step": 32705 }, { "epoch": 6.78, "learning_rate": 0.0007574658906592883, "loss": 1.7672, "step": 32710 }, { "epoch": 6.78, "learning_rate": 0.0007573704799160386, "loss": 1.7696, "step": 32715 }, { "epoch": 6.78, "learning_rate": 0.0007572750691727889, "loss": 1.7721, "step": 32720 }, { "epoch": 6.78, "learning_rate": 0.0007571796584295392, "loss": 1.7676, "step": 32725 }, { "epoch": 6.78, "learning_rate": 0.0007570842476862894, "loss": 1.7714, "step": 32730 }, { "epoch": 6.78, "learning_rate": 0.0007569888369430397, "loss": 1.7683, "step": 32735 }, { "epoch": 6.78, "learning_rate": 0.0007568934261997901, "loss": 1.7685, "step": 32740 }, { "epoch": 6.78, "learning_rate": 0.0007567980154565404, "loss": 1.773, "step": 32745 }, { "epoch": 6.78, "learning_rate": 0.0007567026047132908, "loss": 1.7676, "step": 32750 }, { "epoch": 6.79, "learning_rate": 0.000756607193970041, "loss": 1.7703, "step": 32755 }, { "epoch": 6.79, "learning_rate": 0.0007565117832267913, "loss": 1.7703, "step": 32760 }, { "epoch": 6.79, "learning_rate": 0.0007564163724835417, "loss": 1.7619, "step": 32765 }, { "epoch": 6.79, "learning_rate": 0.000756320961740292, "loss": 1.771, "step": 32770 }, { "epoch": 6.79, "learning_rate": 0.0007562255509970423, "loss": 1.7691, "step": 32775 }, { "epoch": 6.79, "learning_rate": 0.0007561301402537926, "loss": 1.7647, "step": 32780 }, { "epoch": 6.79, "learning_rate": 0.0007560347295105428, "loss": 1.7612, "step": 32785 }, { "epoch": 6.79, "learning_rate": 0.0007559393187672931, "loss": 1.7658, "step": 32790 }, { "epoch": 6.79, "learning_rate": 0.0007558439080240436, "loss": 1.7636, "step": 32795 }, { "epoch": 6.8, "learning_rate": 0.0007557484972807939, "loss": 1.768, "step": 32800 }, { "epoch": 6.8, "learning_rate": 0.0007556530865375442, "loss": 1.7719, "step": 32805 }, { "epoch": 6.8, "learning_rate": 0.0007555576757942945, "loss": 1.7639, "step": 32810 }, { "epoch": 6.8, "learning_rate": 0.0007554622650510447, "loss": 1.7707, "step": 32815 }, { "epoch": 6.8, "learning_rate": 0.000755366854307795, "loss": 1.7703, "step": 32820 }, { "epoch": 6.8, "learning_rate": 0.0007552714435645454, "loss": 1.7703, "step": 32825 }, { "epoch": 6.8, "learning_rate": 0.0007551760328212957, "loss": 1.7675, "step": 32830 }, { "epoch": 6.8, "learning_rate": 0.000755080622078046, "loss": 1.7682, "step": 32835 }, { "epoch": 6.8, "learning_rate": 0.0007549852113347964, "loss": 1.7635, "step": 32840 }, { "epoch": 6.8, "learning_rate": 0.0007548898005915466, "loss": 1.7651, "step": 32845 }, { "epoch": 6.81, "learning_rate": 0.0007547943898482969, "loss": 1.7665, "step": 32850 }, { "epoch": 6.81, "learning_rate": 0.0007546989791050473, "loss": 1.7678, "step": 32855 }, { "epoch": 6.81, "learning_rate": 0.0007546035683617976, "loss": 1.7688, "step": 32860 }, { "epoch": 6.81, "learning_rate": 0.0007545081576185479, "loss": 1.7649, "step": 32865 }, { "epoch": 6.81, "learning_rate": 0.0007544127468752981, "loss": 1.7709, "step": 32870 }, { "epoch": 6.81, "learning_rate": 0.0007543173361320484, "loss": 1.7674, "step": 32875 }, { "epoch": 6.81, "learning_rate": 0.0007542219253887987, "loss": 1.7661, "step": 32880 }, { "epoch": 6.81, "learning_rate": 0.0007541265146455492, "loss": 1.765, "step": 32885 }, { "epoch": 6.81, "learning_rate": 0.0007540311039022995, "loss": 1.7677, "step": 32890 }, { "epoch": 6.81, "learning_rate": 0.0007539356931590498, "loss": 1.7668, "step": 32895 }, { "epoch": 6.82, "learning_rate": 0.0007538402824158, "loss": 1.7672, "step": 32900 }, { "epoch": 6.82, "learning_rate": 0.0007537448716725503, "loss": 1.7641, "step": 32905 }, { "epoch": 6.82, "learning_rate": 0.0007536494609293006, "loss": 1.7672, "step": 32910 }, { "epoch": 6.82, "learning_rate": 0.000753554050186051, "loss": 1.7646, "step": 32915 }, { "epoch": 6.82, "learning_rate": 0.0007534586394428013, "loss": 1.7633, "step": 32920 }, { "epoch": 6.82, "learning_rate": 0.0007533632286995515, "loss": 1.7608, "step": 32925 }, { "epoch": 6.82, "learning_rate": 0.0007532678179563019, "loss": 1.7684, "step": 32930 }, { "epoch": 6.82, "learning_rate": 0.0007531724072130522, "loss": 1.7669, "step": 32935 }, { "epoch": 6.82, "learning_rate": 0.0007530769964698026, "loss": 1.7637, "step": 32940 }, { "epoch": 6.83, "learning_rate": 0.0007529815857265529, "loss": 1.7666, "step": 32945 }, { "epoch": 6.83, "learning_rate": 0.0007528861749833032, "loss": 1.7646, "step": 32950 }, { "epoch": 6.83, "learning_rate": 0.0007527907642400534, "loss": 1.7638, "step": 32955 }, { "epoch": 6.83, "learning_rate": 0.0007526953534968037, "loss": 1.769, "step": 32960 }, { "epoch": 6.83, "learning_rate": 0.000752599942753554, "loss": 1.7722, "step": 32965 }, { "epoch": 6.83, "learning_rate": 0.0007525045320103044, "loss": 1.7632, "step": 32970 }, { "epoch": 6.83, "learning_rate": 0.0007524091212670548, "loss": 1.7638, "step": 32975 }, { "epoch": 6.83, "learning_rate": 0.000752313710523805, "loss": 1.7611, "step": 32980 }, { "epoch": 6.83, "learning_rate": 0.0007522182997805553, "loss": 1.7678, "step": 32985 }, { "epoch": 6.83, "learning_rate": 0.0007521228890373056, "loss": 1.7626, "step": 32990 }, { "epoch": 6.84, "learning_rate": 0.0007520274782940559, "loss": 1.7626, "step": 32995 }, { "epoch": 6.84, "learning_rate": 0.0007519320675508063, "loss": 1.7643, "step": 33000 }, { "epoch": 6.84, "eval_accuracy": 0.5381176470588235, "eval_loss": 1.9461110830307007, "eval_runtime": 0.9482, "eval_samples_per_second": 158.194, "eval_steps_per_second": 1.055, "step": 33000 }, { "epoch": 6.84, "learning_rate": 0.0007518366568075566, "loss": 1.7644, "step": 33005 }, { "epoch": 6.84, "learning_rate": 0.0007517412460643068, "loss": 1.7664, "step": 33010 }, { "epoch": 6.84, "learning_rate": 0.0007516458353210571, "loss": 1.7647, "step": 33015 }, { "epoch": 6.84, "learning_rate": 0.0007515504245778074, "loss": 1.7677, "step": 33020 }, { "epoch": 6.84, "learning_rate": 0.0007514550138345578, "loss": 1.7668, "step": 33025 }, { "epoch": 6.84, "learning_rate": 0.0007513596030913082, "loss": 1.7627, "step": 33030 }, { "epoch": 6.84, "learning_rate": 0.0007512641923480585, "loss": 1.7665, "step": 33035 }, { "epoch": 6.84, "learning_rate": 0.0007511687816048087, "loss": 1.7627, "step": 33040 }, { "epoch": 6.85, "learning_rate": 0.000751073370861559, "loss": 1.7697, "step": 33045 }, { "epoch": 6.85, "learning_rate": 0.0007509779601183093, "loss": 1.7756, "step": 33050 }, { "epoch": 6.85, "learning_rate": 0.0007508825493750596, "loss": 1.7664, "step": 33055 }, { "epoch": 6.85, "learning_rate": 0.00075078713863181, "loss": 1.7729, "step": 33060 }, { "epoch": 6.85, "learning_rate": 0.0007506917278885602, "loss": 1.7687, "step": 33065 }, { "epoch": 6.85, "learning_rate": 0.0007505963171453106, "loss": 1.7672, "step": 33070 }, { "epoch": 6.85, "learning_rate": 0.0007505009064020609, "loss": 1.766, "step": 33075 }, { "epoch": 6.85, "learning_rate": 0.0007504054956588112, "loss": 1.766, "step": 33080 }, { "epoch": 6.85, "learning_rate": 0.0007503100849155615, "loss": 1.7644, "step": 33085 }, { "epoch": 6.86, "learning_rate": 0.0007502146741723119, "loss": 1.7671, "step": 33090 }, { "epoch": 6.86, "learning_rate": 0.0007501192634290621, "loss": 1.7656, "step": 33095 }, { "epoch": 6.86, "learning_rate": 0.0007500238526858124, "loss": 1.7666, "step": 33100 }, { "epoch": 6.86, "learning_rate": 0.0007499284419425627, "loss": 1.764, "step": 33105 }, { "epoch": 6.86, "learning_rate": 0.000749833031199313, "loss": 1.7684, "step": 33110 }, { "epoch": 6.86, "learning_rate": 0.0007497376204560634, "loss": 1.7668, "step": 33115 }, { "epoch": 6.86, "learning_rate": 0.0007496422097128138, "loss": 1.7642, "step": 33120 }, { "epoch": 6.86, "learning_rate": 0.000749546798969564, "loss": 1.7675, "step": 33125 }, { "epoch": 6.86, "learning_rate": 0.0007494513882263143, "loss": 1.7681, "step": 33130 }, { "epoch": 6.86, "learning_rate": 0.0007493559774830646, "loss": 1.7605, "step": 33135 }, { "epoch": 6.87, "learning_rate": 0.0007492605667398149, "loss": 1.7649, "step": 33140 }, { "epoch": 6.87, "learning_rate": 0.0007491651559965652, "loss": 1.7688, "step": 33145 }, { "epoch": 6.87, "learning_rate": 0.0007490697452533155, "loss": 1.768, "step": 33150 }, { "epoch": 6.87, "learning_rate": 0.0007489743345100658, "loss": 1.7653, "step": 33155 }, { "epoch": 6.87, "learning_rate": 0.0007488789237668162, "loss": 1.7683, "step": 33160 }, { "epoch": 6.87, "learning_rate": 0.0007487835130235665, "loss": 1.7669, "step": 33165 }, { "epoch": 6.87, "learning_rate": 0.0007486881022803168, "loss": 1.7662, "step": 33170 }, { "epoch": 6.87, "learning_rate": 0.0007485926915370672, "loss": 1.7653, "step": 33175 }, { "epoch": 6.87, "learning_rate": 0.0007484972807938174, "loss": 1.773, "step": 33180 }, { "epoch": 6.87, "learning_rate": 0.0007484018700505677, "loss": 1.7682, "step": 33185 }, { "epoch": 6.88, "learning_rate": 0.000748306459307318, "loss": 1.7648, "step": 33190 }, { "epoch": 6.88, "learning_rate": 0.0007482110485640683, "loss": 1.7679, "step": 33195 }, { "epoch": 6.88, "learning_rate": 0.0007481156378208186, "loss": 1.7681, "step": 33200 }, { "epoch": 6.88, "learning_rate": 0.000748020227077569, "loss": 1.7638, "step": 33205 }, { "epoch": 6.88, "learning_rate": 0.0007479248163343193, "loss": 1.7638, "step": 33210 }, { "epoch": 6.88, "learning_rate": 0.0007478294055910696, "loss": 1.7668, "step": 33215 }, { "epoch": 6.88, "learning_rate": 0.0007477339948478199, "loss": 1.769, "step": 33220 }, { "epoch": 6.88, "learning_rate": 0.0007476385841045702, "loss": 1.7652, "step": 33225 }, { "epoch": 6.88, "learning_rate": 0.0007475431733613205, "loss": 1.77, "step": 33230 }, { "epoch": 6.89, "learning_rate": 0.0007474477626180708, "loss": 1.7659, "step": 33235 }, { "epoch": 6.89, "learning_rate": 0.0007473523518748211, "loss": 1.7671, "step": 33240 }, { "epoch": 6.89, "learning_rate": 0.0007472569411315714, "loss": 1.7646, "step": 33245 }, { "epoch": 6.89, "learning_rate": 0.0007471615303883217, "loss": 1.7708, "step": 33250 }, { "epoch": 6.89, "learning_rate": 0.0007470661196450721, "loss": 1.766, "step": 33255 }, { "epoch": 6.89, "learning_rate": 0.0007469707089018223, "loss": 1.7631, "step": 33260 }, { "epoch": 6.89, "learning_rate": 0.0007468752981585727, "loss": 1.7693, "step": 33265 }, { "epoch": 6.89, "learning_rate": 0.000746779887415323, "loss": 1.7663, "step": 33270 }, { "epoch": 6.89, "learning_rate": 0.0007466844766720733, "loss": 1.765, "step": 33275 }, { "epoch": 6.89, "learning_rate": 0.0007465890659288236, "loss": 1.7648, "step": 33280 }, { "epoch": 6.9, "learning_rate": 0.0007464936551855739, "loss": 1.7612, "step": 33285 }, { "epoch": 6.9, "learning_rate": 0.0007463982444423241, "loss": 1.7628, "step": 33290 }, { "epoch": 6.9, "learning_rate": 0.0007463028336990745, "loss": 1.7657, "step": 33295 }, { "epoch": 6.9, "learning_rate": 0.0007462074229558249, "loss": 1.7639, "step": 33300 }, { "epoch": 6.9, "learning_rate": 0.0007461120122125752, "loss": 1.7646, "step": 33305 }, { "epoch": 6.9, "learning_rate": 0.0007460166014693255, "loss": 1.7653, "step": 33310 }, { "epoch": 6.9, "learning_rate": 0.0007459211907260758, "loss": 1.763, "step": 33315 }, { "epoch": 6.9, "learning_rate": 0.000745825779982826, "loss": 1.7714, "step": 33320 }, { "epoch": 6.9, "learning_rate": 0.0007457303692395764, "loss": 1.7678, "step": 33325 }, { "epoch": 6.9, "learning_rate": 0.0007456349584963267, "loss": 1.7643, "step": 33330 }, { "epoch": 6.91, "learning_rate": 0.000745539547753077, "loss": 1.7645, "step": 33335 }, { "epoch": 6.91, "learning_rate": 0.0007454441370098273, "loss": 1.7681, "step": 33340 }, { "epoch": 6.91, "learning_rate": 0.0007453487262665776, "loss": 1.7659, "step": 33345 }, { "epoch": 6.91, "learning_rate": 0.0007452533155233279, "loss": 1.7678, "step": 33350 }, { "epoch": 6.91, "learning_rate": 0.0007451579047800783, "loss": 1.7668, "step": 33355 }, { "epoch": 6.91, "learning_rate": 0.0007450624940368286, "loss": 1.7626, "step": 33360 }, { "epoch": 6.91, "learning_rate": 0.0007449670832935789, "loss": 1.7671, "step": 33365 }, { "epoch": 6.91, "learning_rate": 0.0007448716725503292, "loss": 1.7639, "step": 33370 }, { "epoch": 6.91, "learning_rate": 0.0007447762618070794, "loss": 1.769, "step": 33375 }, { "epoch": 6.92, "learning_rate": 0.0007446808510638298, "loss": 1.7667, "step": 33380 }, { "epoch": 6.92, "learning_rate": 0.0007445854403205801, "loss": 1.7691, "step": 33385 }, { "epoch": 6.92, "learning_rate": 0.0007444900295773305, "loss": 1.7681, "step": 33390 }, { "epoch": 6.92, "learning_rate": 0.0007443946188340808, "loss": 1.7632, "step": 33395 }, { "epoch": 6.92, "learning_rate": 0.000744299208090831, "loss": 1.7661, "step": 33400 }, { "epoch": 6.92, "learning_rate": 0.0007442037973475813, "loss": 1.7683, "step": 33405 }, { "epoch": 6.92, "learning_rate": 0.0007441083866043317, "loss": 1.7719, "step": 33410 }, { "epoch": 6.92, "learning_rate": 0.000744012975861082, "loss": 1.7664, "step": 33415 }, { "epoch": 6.92, "learning_rate": 0.0007439175651178323, "loss": 1.77, "step": 33420 }, { "epoch": 6.92, "learning_rate": 0.0007438221543745826, "loss": 1.7713, "step": 33425 }, { "epoch": 6.93, "learning_rate": 0.0007437267436313328, "loss": 1.7624, "step": 33430 }, { "epoch": 6.93, "learning_rate": 0.0007436313328880832, "loss": 1.7695, "step": 33435 }, { "epoch": 6.93, "learning_rate": 0.0007435359221448336, "loss": 1.7671, "step": 33440 }, { "epoch": 6.93, "learning_rate": 0.0007434405114015839, "loss": 1.7717, "step": 33445 }, { "epoch": 6.93, "learning_rate": 0.0007433451006583342, "loss": 1.7666, "step": 33450 }, { "epoch": 6.93, "learning_rate": 0.0007432496899150845, "loss": 1.7687, "step": 33455 }, { "epoch": 6.93, "learning_rate": 0.0007431542791718347, "loss": 1.7672, "step": 33460 }, { "epoch": 6.93, "learning_rate": 0.000743058868428585, "loss": 1.7694, "step": 33465 }, { "epoch": 6.93, "learning_rate": 0.0007429634576853354, "loss": 1.7652, "step": 33470 }, { "epoch": 6.93, "learning_rate": 0.0007428680469420857, "loss": 1.7617, "step": 33475 }, { "epoch": 6.94, "learning_rate": 0.000742772636198836, "loss": 1.7594, "step": 33480 }, { "epoch": 6.94, "learning_rate": 0.0007426772254555863, "loss": 1.7641, "step": 33485 }, { "epoch": 6.94, "learning_rate": 0.0007425818147123366, "loss": 1.766, "step": 33490 }, { "epoch": 6.94, "learning_rate": 0.0007424864039690869, "loss": 1.7636, "step": 33495 }, { "epoch": 6.94, "learning_rate": 0.0007423909932258373, "loss": 1.7621, "step": 33500 }, { "epoch": 6.94, "learning_rate": 0.0007422955824825876, "loss": 1.7587, "step": 33505 }, { "epoch": 6.94, "learning_rate": 0.0007422001717393379, "loss": 1.7706, "step": 33510 }, { "epoch": 6.94, "learning_rate": 0.0007421047609960881, "loss": 1.7656, "step": 33515 }, { "epoch": 6.94, "learning_rate": 0.0007420093502528384, "loss": 1.7649, "step": 33520 }, { "epoch": 6.95, "learning_rate": 0.0007419139395095887, "loss": 1.7642, "step": 33525 }, { "epoch": 6.95, "learning_rate": 0.0007418185287663392, "loss": 1.7673, "step": 33530 }, { "epoch": 6.95, "learning_rate": 0.0007417231180230895, "loss": 1.7713, "step": 33535 }, { "epoch": 6.95, "learning_rate": 0.0007416277072798398, "loss": 1.7668, "step": 33540 }, { "epoch": 6.95, "learning_rate": 0.00074153229653659, "loss": 1.7592, "step": 33545 }, { "epoch": 6.95, "learning_rate": 0.0007414368857933403, "loss": 1.7648, "step": 33550 }, { "epoch": 6.95, "learning_rate": 0.0007413414750500906, "loss": 1.7622, "step": 33555 }, { "epoch": 6.95, "learning_rate": 0.000741246064306841, "loss": 1.7651, "step": 33560 }, { "epoch": 6.95, "learning_rate": 0.0007411506535635913, "loss": 1.7667, "step": 33565 }, { "epoch": 6.95, "learning_rate": 0.0007410552428203415, "loss": 1.7694, "step": 33570 }, { "epoch": 6.96, "learning_rate": 0.0007409598320770919, "loss": 1.7732, "step": 33575 }, { "epoch": 6.96, "learning_rate": 0.0007408644213338422, "loss": 1.7733, "step": 33580 }, { "epoch": 6.96, "learning_rate": 0.0007407690105905926, "loss": 1.7646, "step": 33585 }, { "epoch": 6.96, "learning_rate": 0.0007406735998473429, "loss": 1.7702, "step": 33590 }, { "epoch": 6.96, "learning_rate": 0.0007405781891040932, "loss": 1.7649, "step": 33595 }, { "epoch": 6.96, "learning_rate": 0.0007404827783608434, "loss": 1.7646, "step": 33600 }, { "epoch": 6.96, "learning_rate": 0.0007403873676175937, "loss": 1.7667, "step": 33605 }, { "epoch": 6.96, "learning_rate": 0.000740291956874344, "loss": 1.7637, "step": 33610 }, { "epoch": 6.96, "learning_rate": 0.0007401965461310944, "loss": 1.7648, "step": 33615 }, { "epoch": 6.96, "learning_rate": 0.0007401011353878448, "loss": 1.7645, "step": 33620 }, { "epoch": 6.97, "learning_rate": 0.000740005724644595, "loss": 1.7633, "step": 33625 }, { "epoch": 6.97, "learning_rate": 0.0007399103139013453, "loss": 1.7674, "step": 33630 }, { "epoch": 6.97, "learning_rate": 0.0007398149031580956, "loss": 1.7625, "step": 33635 }, { "epoch": 6.97, "learning_rate": 0.0007397194924148459, "loss": 1.7656, "step": 33640 }, { "epoch": 6.97, "learning_rate": 0.0007396240816715963, "loss": 1.7665, "step": 33645 }, { "epoch": 6.97, "learning_rate": 0.0007395286709283466, "loss": 1.7659, "step": 33650 }, { "epoch": 6.97, "learning_rate": 0.0007394332601850968, "loss": 1.7666, "step": 33655 }, { "epoch": 6.97, "learning_rate": 0.0007393378494418471, "loss": 1.7616, "step": 33660 }, { "epoch": 6.97, "learning_rate": 0.0007392424386985975, "loss": 1.7656, "step": 33665 }, { "epoch": 6.98, "learning_rate": 0.0007391470279553478, "loss": 1.7719, "step": 33670 }, { "epoch": 6.98, "learning_rate": 0.0007390516172120982, "loss": 1.7629, "step": 33675 }, { "epoch": 6.98, "learning_rate": 0.0007389562064688485, "loss": 1.7707, "step": 33680 }, { "epoch": 6.98, "learning_rate": 0.0007388607957255987, "loss": 1.7688, "step": 33685 }, { "epoch": 6.98, "learning_rate": 0.000738765384982349, "loss": 1.7612, "step": 33690 }, { "epoch": 6.98, "learning_rate": 0.0007386699742390993, "loss": 1.7614, "step": 33695 }, { "epoch": 6.98, "learning_rate": 0.0007385745634958496, "loss": 1.7635, "step": 33700 }, { "epoch": 6.98, "learning_rate": 0.0007384791527526, "loss": 1.7683, "step": 33705 }, { "epoch": 6.98, "learning_rate": 0.0007383837420093503, "loss": 1.7675, "step": 33710 }, { "epoch": 6.98, "learning_rate": 0.0007382883312661006, "loss": 1.7626, "step": 33715 }, { "epoch": 6.99, "learning_rate": 0.0007381929205228509, "loss": 1.7683, "step": 33720 }, { "epoch": 6.99, "learning_rate": 0.0007380975097796012, "loss": 1.7638, "step": 33725 }, { "epoch": 6.99, "learning_rate": 0.0007380020990363515, "loss": 1.7697, "step": 33730 }, { "epoch": 6.99, "learning_rate": 0.0007379066882931019, "loss": 1.7619, "step": 33735 }, { "epoch": 6.99, "learning_rate": 0.0007378112775498521, "loss": 1.768, "step": 33740 }, { "epoch": 6.99, "learning_rate": 0.0007377158668066024, "loss": 1.7614, "step": 33745 }, { "epoch": 6.99, "learning_rate": 0.0007376204560633527, "loss": 1.7679, "step": 33750 }, { "epoch": 6.99, "learning_rate": 0.000737525045320103, "loss": 1.7653, "step": 33755 }, { "epoch": 6.99, "learning_rate": 0.0007374296345768534, "loss": 1.7642, "step": 33760 }, { "epoch": 7.0, "learning_rate": 0.0007373342238336037, "loss": 1.7675, "step": 33765 }, { "epoch": 7.0, "learning_rate": 0.000737238813090354, "loss": 1.7661, "step": 33770 }, { "epoch": 7.0, "learning_rate": 0.0007371434023471043, "loss": 1.7646, "step": 33775 }, { "epoch": 7.0, "learning_rate": 0.0007370479916038546, "loss": 1.7651, "step": 33780 }, { "epoch": 7.0, "learning_rate": 0.0007369525808606049, "loss": 1.7635, "step": 33785 }, { "epoch": 7.0, "learning_rate": 0.0007368571701173551, "loss": 1.7659, "step": 33790 }, { "epoch": 7.0, "learning_rate": 0.0007367617593741055, "loss": 1.7516, "step": 33795 }, { "epoch": 7.0, "learning_rate": 0.0007366663486308558, "loss": 1.7565, "step": 33800 }, { "epoch": 7.0, "learning_rate": 0.0007365709378876062, "loss": 1.7566, "step": 33805 }, { "epoch": 7.0, "learning_rate": 0.0007364755271443565, "loss": 1.756, "step": 33810 }, { "epoch": 7.01, "learning_rate": 0.0007363801164011068, "loss": 1.762, "step": 33815 }, { "epoch": 7.01, "learning_rate": 0.0007362847056578572, "loss": 1.7591, "step": 33820 }, { "epoch": 7.01, "learning_rate": 0.0007361892949146074, "loss": 1.7541, "step": 33825 }, { "epoch": 7.01, "learning_rate": 0.0007360938841713577, "loss": 1.7571, "step": 33830 }, { "epoch": 7.01, "learning_rate": 0.000735998473428108, "loss": 1.7539, "step": 33835 }, { "epoch": 7.01, "learning_rate": 0.0007359030626848583, "loss": 1.7578, "step": 33840 }, { "epoch": 7.01, "learning_rate": 0.0007358076519416086, "loss": 1.7579, "step": 33845 }, { "epoch": 7.01, "learning_rate": 0.000735712241198359, "loss": 1.7493, "step": 33850 }, { "epoch": 7.01, "learning_rate": 0.0007356168304551093, "loss": 1.7635, "step": 33855 }, { "epoch": 7.01, "learning_rate": 0.0007355214197118596, "loss": 1.7537, "step": 33860 }, { "epoch": 7.02, "learning_rate": 0.0007354260089686099, "loss": 1.7575, "step": 33865 }, { "epoch": 7.02, "learning_rate": 0.0007353305982253602, "loss": 1.7531, "step": 33870 }, { "epoch": 7.02, "learning_rate": 0.0007352351874821104, "loss": 1.7526, "step": 33875 }, { "epoch": 7.02, "learning_rate": 0.0007351397767388608, "loss": 1.7591, "step": 33880 }, { "epoch": 7.02, "learning_rate": 0.0007350443659956111, "loss": 1.7585, "step": 33885 }, { "epoch": 7.02, "learning_rate": 0.0007349489552523614, "loss": 1.7601, "step": 33890 }, { "epoch": 7.02, "learning_rate": 0.0007348535445091118, "loss": 1.7557, "step": 33895 }, { "epoch": 7.02, "learning_rate": 0.0007347581337658621, "loss": 1.7549, "step": 33900 }, { "epoch": 7.02, "learning_rate": 0.0007346627230226123, "loss": 1.7575, "step": 33905 }, { "epoch": 7.03, "learning_rate": 0.0007345673122793627, "loss": 1.7574, "step": 33910 }, { "epoch": 7.03, "learning_rate": 0.000734471901536113, "loss": 1.7568, "step": 33915 }, { "epoch": 7.03, "learning_rate": 0.0007343764907928633, "loss": 1.7569, "step": 33920 }, { "epoch": 7.03, "learning_rate": 0.0007342810800496136, "loss": 1.7587, "step": 33925 }, { "epoch": 7.03, "learning_rate": 0.0007341856693063639, "loss": 1.7623, "step": 33930 }, { "epoch": 7.03, "learning_rate": 0.0007340902585631141, "loss": 1.7617, "step": 33935 }, { "epoch": 7.03, "learning_rate": 0.0007339948478198646, "loss": 1.7546, "step": 33940 }, { "epoch": 7.03, "learning_rate": 0.0007338994370766149, "loss": 1.7568, "step": 33945 }, { "epoch": 7.03, "learning_rate": 0.0007338040263333652, "loss": 1.7596, "step": 33950 }, { "epoch": 7.03, "learning_rate": 0.0007337086155901155, "loss": 1.7589, "step": 33955 }, { "epoch": 7.04, "learning_rate": 0.0007336132048468657, "loss": 1.7545, "step": 33960 }, { "epoch": 7.04, "learning_rate": 0.000733517794103616, "loss": 1.7512, "step": 33965 }, { "epoch": 7.04, "learning_rate": 0.0007334223833603664, "loss": 1.7534, "step": 33970 }, { "epoch": 7.04, "learning_rate": 0.0007333269726171167, "loss": 1.7516, "step": 33975 }, { "epoch": 7.04, "learning_rate": 0.000733231561873867, "loss": 1.758, "step": 33980 }, { "epoch": 7.04, "learning_rate": 0.0007331361511306173, "loss": 1.7524, "step": 33985 }, { "epoch": 7.04, "learning_rate": 0.0007330407403873676, "loss": 1.7599, "step": 33990 }, { "epoch": 7.04, "learning_rate": 0.000732945329644118, "loss": 1.7527, "step": 33995 }, { "epoch": 7.04, "learning_rate": 0.0007328499189008683, "loss": 1.7577, "step": 34000 }, { "epoch": 7.04, "learning_rate": 0.0007327545081576186, "loss": 1.7594, "step": 34005 }, { "epoch": 7.05, "learning_rate": 0.0007326590974143689, "loss": 1.7539, "step": 34010 }, { "epoch": 7.05, "learning_rate": 0.0007325636866711191, "loss": 1.7615, "step": 34015 }, { "epoch": 7.05, "learning_rate": 0.0007324682759278694, "loss": 1.755, "step": 34020 }, { "epoch": 7.05, "learning_rate": 0.0007323728651846198, "loss": 1.7556, "step": 34025 }, { "epoch": 7.05, "learning_rate": 0.0007322774544413701, "loss": 1.7552, "step": 34030 }, { "epoch": 7.05, "learning_rate": 0.0007321820436981205, "loss": 1.7594, "step": 34035 }, { "epoch": 7.05, "learning_rate": 0.0007320866329548708, "loss": 1.7579, "step": 34040 }, { "epoch": 7.05, "learning_rate": 0.000731991222211621, "loss": 1.7586, "step": 34045 }, { "epoch": 7.05, "learning_rate": 0.0007318958114683713, "loss": 1.7572, "step": 34050 }, { "epoch": 7.06, "learning_rate": 0.0007318004007251217, "loss": 1.7559, "step": 34055 }, { "epoch": 7.06, "learning_rate": 0.000731704989981872, "loss": 1.7566, "step": 34060 }, { "epoch": 7.06, "learning_rate": 0.0007316095792386223, "loss": 1.7511, "step": 34065 }, { "epoch": 7.06, "learning_rate": 0.0007315141684953726, "loss": 1.7569, "step": 34070 }, { "epoch": 7.06, "learning_rate": 0.0007314187577521228, "loss": 1.7538, "step": 34075 }, { "epoch": 7.06, "learning_rate": 0.0007313233470088732, "loss": 1.7498, "step": 34080 }, { "epoch": 7.06, "learning_rate": 0.0007312279362656236, "loss": 1.7585, "step": 34085 }, { "epoch": 7.06, "learning_rate": 0.0007311325255223739, "loss": 1.7607, "step": 34090 }, { "epoch": 7.06, "learning_rate": 0.0007310371147791242, "loss": 1.7567, "step": 34095 }, { "epoch": 7.06, "learning_rate": 0.0007309417040358744, "loss": 1.752, "step": 34100 }, { "epoch": 7.07, "learning_rate": 0.0007308462932926247, "loss": 1.7546, "step": 34105 }, { "epoch": 7.07, "learning_rate": 0.000730750882549375, "loss": 1.7578, "step": 34110 }, { "epoch": 7.07, "learning_rate": 0.0007306554718061254, "loss": 1.7557, "step": 34115 }, { "epoch": 7.07, "learning_rate": 0.0007305600610628757, "loss": 1.7558, "step": 34120 }, { "epoch": 7.07, "learning_rate": 0.0007304646503196261, "loss": 1.7572, "step": 34125 }, { "epoch": 7.07, "learning_rate": 0.0007303692395763763, "loss": 1.7576, "step": 34130 }, { "epoch": 7.07, "learning_rate": 0.0007302738288331266, "loss": 1.7572, "step": 34135 }, { "epoch": 7.07, "learning_rate": 0.0007301784180898769, "loss": 1.7558, "step": 34140 }, { "epoch": 7.07, "learning_rate": 0.0007300830073466273, "loss": 1.7545, "step": 34145 }, { "epoch": 7.07, "learning_rate": 0.0007299875966033776, "loss": 1.7563, "step": 34150 }, { "epoch": 7.08, "learning_rate": 0.0007298921858601278, "loss": 1.7511, "step": 34155 }, { "epoch": 7.08, "learning_rate": 0.0007297967751168781, "loss": 1.7549, "step": 34160 }, { "epoch": 7.08, "learning_rate": 0.0007297013643736284, "loss": 1.7564, "step": 34165 }, { "epoch": 7.08, "learning_rate": 0.0007296059536303788, "loss": 1.7579, "step": 34170 }, { "epoch": 7.08, "learning_rate": 0.0007295105428871292, "loss": 1.7521, "step": 34175 }, { "epoch": 7.08, "learning_rate": 0.0007294151321438795, "loss": 1.7637, "step": 34180 }, { "epoch": 7.08, "learning_rate": 0.0007293197214006297, "loss": 1.7537, "step": 34185 }, { "epoch": 7.08, "learning_rate": 0.00072922431065738, "loss": 1.7555, "step": 34190 }, { "epoch": 7.08, "learning_rate": 0.0007291288999141303, "loss": 1.7591, "step": 34195 }, { "epoch": 7.09, "learning_rate": 0.0007290334891708806, "loss": 1.7656, "step": 34200 }, { "epoch": 7.09, "learning_rate": 0.000728938078427631, "loss": 1.7655, "step": 34205 }, { "epoch": 7.09, "learning_rate": 0.0007288426676843813, "loss": 1.7655, "step": 34210 }, { "epoch": 7.09, "learning_rate": 0.0007287472569411315, "loss": 1.7632, "step": 34215 }, { "epoch": 7.09, "learning_rate": 0.0007286518461978819, "loss": 1.7648, "step": 34220 }, { "epoch": 7.09, "learning_rate": 0.0007285564354546322, "loss": 1.7592, "step": 34225 }, { "epoch": 7.09, "learning_rate": 0.0007284610247113826, "loss": 1.7574, "step": 34230 }, { "epoch": 7.09, "learning_rate": 0.0007283656139681329, "loss": 1.76, "step": 34235 }, { "epoch": 7.09, "learning_rate": 0.0007282702032248831, "loss": 1.7549, "step": 34240 }, { "epoch": 7.09, "learning_rate": 0.0007281747924816334, "loss": 1.7559, "step": 34245 }, { "epoch": 7.1, "learning_rate": 0.0007280793817383837, "loss": 1.7587, "step": 34250 }, { "epoch": 7.1, "learning_rate": 0.000727983970995134, "loss": 1.7623, "step": 34255 }, { "epoch": 7.1, "learning_rate": 0.0007278885602518844, "loss": 1.7537, "step": 34260 }, { "epoch": 7.1, "learning_rate": 0.0007277931495086348, "loss": 1.7576, "step": 34265 }, { "epoch": 7.1, "learning_rate": 0.000727697738765385, "loss": 1.7595, "step": 34270 }, { "epoch": 7.1, "learning_rate": 0.0007276023280221353, "loss": 1.7608, "step": 34275 }, { "epoch": 7.1, "learning_rate": 0.0007275069172788856, "loss": 1.7547, "step": 34280 }, { "epoch": 7.1, "learning_rate": 0.0007274115065356359, "loss": 1.7548, "step": 34285 }, { "epoch": 7.1, "learning_rate": 0.0007273160957923863, "loss": 1.7547, "step": 34290 }, { "epoch": 7.1, "learning_rate": 0.0007272206850491366, "loss": 1.7577, "step": 34295 }, { "epoch": 7.11, "learning_rate": 0.0007271252743058868, "loss": 1.7602, "step": 34300 }, { "epoch": 7.11, "learning_rate": 0.0007270298635626371, "loss": 1.7597, "step": 34305 }, { "epoch": 7.11, "learning_rate": 0.0007269344528193875, "loss": 1.7577, "step": 34310 }, { "epoch": 7.11, "learning_rate": 0.0007268390420761378, "loss": 1.753, "step": 34315 }, { "epoch": 7.11, "learning_rate": 0.0007267436313328882, "loss": 1.7591, "step": 34320 }, { "epoch": 7.11, "learning_rate": 0.0007266482205896384, "loss": 1.7615, "step": 34325 }, { "epoch": 7.11, "learning_rate": 0.0007265528098463887, "loss": 1.7576, "step": 34330 }, { "epoch": 7.11, "learning_rate": 0.000726457399103139, "loss": 1.7585, "step": 34335 }, { "epoch": 7.11, "learning_rate": 0.0007263619883598893, "loss": 1.7559, "step": 34340 }, { "epoch": 7.12, "learning_rate": 0.0007262665776166396, "loss": 1.761, "step": 34345 }, { "epoch": 7.12, "learning_rate": 0.00072617116687339, "loss": 1.7551, "step": 34350 }, { "epoch": 7.12, "learning_rate": 0.0007260757561301403, "loss": 1.7571, "step": 34355 }, { "epoch": 7.12, "learning_rate": 0.0007259803453868906, "loss": 1.7576, "step": 34360 }, { "epoch": 7.12, "learning_rate": 0.0007258849346436409, "loss": 1.7561, "step": 34365 }, { "epoch": 7.12, "learning_rate": 0.0007257895239003912, "loss": 1.7562, "step": 34370 }, { "epoch": 7.12, "learning_rate": 0.0007256941131571415, "loss": 1.7511, "step": 34375 }, { "epoch": 7.12, "learning_rate": 0.0007255987024138918, "loss": 1.761, "step": 34380 }, { "epoch": 7.12, "learning_rate": 0.0007255032916706421, "loss": 1.7574, "step": 34385 }, { "epoch": 7.12, "learning_rate": 0.0007254078809273924, "loss": 1.7507, "step": 34390 }, { "epoch": 7.13, "learning_rate": 0.0007253124701841427, "loss": 1.7588, "step": 34395 }, { "epoch": 7.13, "learning_rate": 0.0007252170594408931, "loss": 1.7575, "step": 34400 }, { "epoch": 7.13, "learning_rate": 0.0007251216486976434, "loss": 1.7582, "step": 34405 }, { "epoch": 7.13, "learning_rate": 0.0007250262379543937, "loss": 1.7519, "step": 34410 }, { "epoch": 7.13, "learning_rate": 0.000724930827211144, "loss": 1.7584, "step": 34415 }, { "epoch": 7.13, "learning_rate": 0.0007248354164678943, "loss": 1.7576, "step": 34420 }, { "epoch": 7.13, "learning_rate": 0.0007247400057246446, "loss": 1.757, "step": 34425 }, { "epoch": 7.13, "learning_rate": 0.0007246445949813949, "loss": 1.7584, "step": 34430 }, { "epoch": 7.13, "learning_rate": 0.0007245491842381451, "loss": 1.7572, "step": 34435 }, { "epoch": 7.13, "learning_rate": 0.0007244537734948955, "loss": 1.7534, "step": 34440 }, { "epoch": 7.14, "learning_rate": 0.0007243583627516459, "loss": 1.7604, "step": 34445 }, { "epoch": 7.14, "learning_rate": 0.0007242629520083962, "loss": 1.7573, "step": 34450 }, { "epoch": 7.14, "learning_rate": 0.0007241675412651465, "loss": 1.7549, "step": 34455 }, { "epoch": 7.14, "learning_rate": 0.0007240721305218968, "loss": 1.7605, "step": 34460 }, { "epoch": 7.14, "learning_rate": 0.0007239767197786471, "loss": 1.7583, "step": 34465 }, { "epoch": 7.14, "learning_rate": 0.0007238813090353974, "loss": 1.7563, "step": 34470 }, { "epoch": 7.14, "learning_rate": 0.0007237858982921477, "loss": 1.7627, "step": 34475 }, { "epoch": 7.14, "learning_rate": 0.000723690487548898, "loss": 1.757, "step": 34480 }, { "epoch": 7.14, "learning_rate": 0.0007235950768056483, "loss": 1.7589, "step": 34485 }, { "epoch": 7.15, "learning_rate": 0.0007234996660623985, "loss": 1.7532, "step": 34490 }, { "epoch": 7.15, "learning_rate": 0.000723404255319149, "loss": 1.7603, "step": 34495 }, { "epoch": 7.15, "learning_rate": 0.0007233088445758993, "loss": 1.7544, "step": 34500 }, { "epoch": 7.15, "learning_rate": 0.0007232134338326496, "loss": 1.7572, "step": 34505 }, { "epoch": 7.15, "learning_rate": 0.0007231180230893999, "loss": 1.7545, "step": 34510 }, { "epoch": 7.15, "learning_rate": 0.0007230226123461502, "loss": 1.7608, "step": 34515 }, { "epoch": 7.15, "learning_rate": 0.0007229272016029004, "loss": 1.7634, "step": 34520 }, { "epoch": 7.15, "learning_rate": 0.0007228317908596508, "loss": 1.7557, "step": 34525 }, { "epoch": 7.15, "learning_rate": 0.0007227363801164011, "loss": 1.7551, "step": 34530 }, { "epoch": 7.15, "learning_rate": 0.0007226409693731514, "loss": 1.7619, "step": 34535 }, { "epoch": 7.16, "learning_rate": 0.0007225455586299018, "loss": 1.7592, "step": 34540 }, { "epoch": 7.16, "learning_rate": 0.0007224501478866521, "loss": 1.7575, "step": 34545 }, { "epoch": 7.16, "learning_rate": 0.0007223547371434023, "loss": 1.7643, "step": 34550 }, { "epoch": 7.16, "learning_rate": 0.0007222593264001527, "loss": 1.7591, "step": 34555 }, { "epoch": 7.16, "learning_rate": 0.000722163915656903, "loss": 1.7637, "step": 34560 }, { "epoch": 7.16, "learning_rate": 0.0007220685049136533, "loss": 1.7553, "step": 34565 }, { "epoch": 7.16, "learning_rate": 0.0007219730941704036, "loss": 1.7581, "step": 34570 }, { "epoch": 7.16, "learning_rate": 0.0007218776834271538, "loss": 1.7568, "step": 34575 }, { "epoch": 7.16, "learning_rate": 0.0007217822726839041, "loss": 1.7564, "step": 34580 }, { "epoch": 7.16, "learning_rate": 0.0007216868619406546, "loss": 1.7508, "step": 34585 }, { "epoch": 7.17, "learning_rate": 0.0007215914511974049, "loss": 1.7617, "step": 34590 }, { "epoch": 7.17, "learning_rate": 0.0007214960404541552, "loss": 1.7575, "step": 34595 }, { "epoch": 7.17, "learning_rate": 0.0007214006297109055, "loss": 1.7574, "step": 34600 }, { "epoch": 7.17, "learning_rate": 0.0007213052189676557, "loss": 1.7561, "step": 34605 }, { "epoch": 7.17, "learning_rate": 0.000721209808224406, "loss": 1.7546, "step": 34610 }, { "epoch": 7.17, "learning_rate": 0.0007211143974811564, "loss": 1.7577, "step": 34615 }, { "epoch": 7.17, "learning_rate": 0.0007210189867379067, "loss": 1.7558, "step": 34620 }, { "epoch": 7.17, "learning_rate": 0.000720923575994657, "loss": 1.7589, "step": 34625 }, { "epoch": 7.17, "learning_rate": 0.0007208281652514074, "loss": 1.7594, "step": 34630 }, { "epoch": 7.18, "learning_rate": 0.0007207327545081576, "loss": 1.7579, "step": 34635 }, { "epoch": 7.18, "learning_rate": 0.000720637343764908, "loss": 1.7594, "step": 34640 }, { "epoch": 7.18, "learning_rate": 0.0007205419330216583, "loss": 1.7587, "step": 34645 }, { "epoch": 7.18, "learning_rate": 0.0007204465222784086, "loss": 1.7585, "step": 34650 }, { "epoch": 7.18, "learning_rate": 0.0007203511115351589, "loss": 1.7515, "step": 34655 }, { "epoch": 7.18, "learning_rate": 0.0007202557007919091, "loss": 1.7644, "step": 34660 }, { "epoch": 7.18, "learning_rate": 0.0007201602900486594, "loss": 1.7595, "step": 34665 }, { "epoch": 7.18, "learning_rate": 0.0007200648793054098, "loss": 1.7586, "step": 34670 }, { "epoch": 7.18, "learning_rate": 0.0007199694685621602, "loss": 1.7564, "step": 34675 }, { "epoch": 7.18, "learning_rate": 0.0007198740578189105, "loss": 1.7611, "step": 34680 }, { "epoch": 7.19, "learning_rate": 0.0007197786470756608, "loss": 1.7566, "step": 34685 }, { "epoch": 7.19, "learning_rate": 0.000719683236332411, "loss": 1.7576, "step": 34690 }, { "epoch": 7.19, "learning_rate": 0.0007195878255891613, "loss": 1.7563, "step": 34695 }, { "epoch": 7.19, "learning_rate": 0.0007194924148459117, "loss": 1.761, "step": 34700 }, { "epoch": 7.19, "learning_rate": 0.000719397004102662, "loss": 1.7589, "step": 34705 }, { "epoch": 7.19, "learning_rate": 0.0007193015933594123, "loss": 1.756, "step": 34710 }, { "epoch": 7.19, "learning_rate": 0.0007192061826161625, "loss": 1.7572, "step": 34715 }, { "epoch": 7.19, "learning_rate": 0.0007191107718729128, "loss": 1.753, "step": 34720 }, { "epoch": 7.19, "learning_rate": 0.0007190153611296632, "loss": 1.7612, "step": 34725 }, { "epoch": 7.19, "learning_rate": 0.0007189199503864136, "loss": 1.7604, "step": 34730 }, { "epoch": 7.2, "learning_rate": 0.0007188245396431639, "loss": 1.758, "step": 34735 }, { "epoch": 7.2, "learning_rate": 0.0007187291288999142, "loss": 1.7552, "step": 34740 }, { "epoch": 7.2, "learning_rate": 0.0007186337181566644, "loss": 1.7576, "step": 34745 }, { "epoch": 7.2, "learning_rate": 0.0007185383074134147, "loss": 1.753, "step": 34750 }, { "epoch": 7.2, "learning_rate": 0.000718442896670165, "loss": 1.7592, "step": 34755 }, { "epoch": 7.2, "learning_rate": 0.0007183474859269154, "loss": 1.7546, "step": 34760 }, { "epoch": 7.2, "learning_rate": 0.0007182520751836657, "loss": 1.7615, "step": 34765 }, { "epoch": 7.2, "learning_rate": 0.0007181566644404161, "loss": 1.7591, "step": 34770 }, { "epoch": 7.2, "learning_rate": 0.0007180612536971663, "loss": 1.7582, "step": 34775 }, { "epoch": 7.21, "learning_rate": 0.0007179658429539166, "loss": 1.7635, "step": 34780 }, { "epoch": 7.21, "learning_rate": 0.0007178704322106669, "loss": 1.7601, "step": 34785 }, { "epoch": 7.21, "learning_rate": 0.0007177750214674173, "loss": 1.7529, "step": 34790 }, { "epoch": 7.21, "learning_rate": 0.0007176796107241676, "loss": 1.7577, "step": 34795 }, { "epoch": 7.21, "learning_rate": 0.0007175841999809178, "loss": 1.7548, "step": 34800 }, { "epoch": 7.21, "learning_rate": 0.0007174887892376681, "loss": 1.7549, "step": 34805 }, { "epoch": 7.21, "learning_rate": 0.0007173933784944184, "loss": 1.7576, "step": 34810 }, { "epoch": 7.21, "learning_rate": 0.0007172979677511688, "loss": 1.7596, "step": 34815 }, { "epoch": 7.21, "learning_rate": 0.0007172025570079192, "loss": 1.7605, "step": 34820 }, { "epoch": 7.21, "learning_rate": 0.0007171071462646695, "loss": 1.7574, "step": 34825 }, { "epoch": 7.22, "learning_rate": 0.0007170117355214197, "loss": 1.7559, "step": 34830 }, { "epoch": 7.22, "learning_rate": 0.00071691632477817, "loss": 1.7575, "step": 34835 }, { "epoch": 7.22, "learning_rate": 0.0007168209140349203, "loss": 1.756, "step": 34840 }, { "epoch": 7.22, "learning_rate": 0.0007167255032916706, "loss": 1.7581, "step": 34845 }, { "epoch": 7.22, "learning_rate": 0.000716630092548421, "loss": 1.7599, "step": 34850 }, { "epoch": 7.22, "learning_rate": 0.0007165346818051712, "loss": 1.7563, "step": 34855 }, { "epoch": 7.22, "learning_rate": 0.0007164392710619216, "loss": 1.7532, "step": 34860 }, { "epoch": 7.22, "learning_rate": 0.0007163438603186719, "loss": 1.761, "step": 34865 }, { "epoch": 7.22, "learning_rate": 0.0007162484495754222, "loss": 1.757, "step": 34870 }, { "epoch": 7.22, "learning_rate": 0.0007161530388321726, "loss": 1.7629, "step": 34875 }, { "epoch": 7.23, "learning_rate": 0.0007160576280889229, "loss": 1.7599, "step": 34880 }, { "epoch": 7.23, "learning_rate": 0.0007159622173456731, "loss": 1.761, "step": 34885 }, { "epoch": 7.23, "learning_rate": 0.0007158668066024234, "loss": 1.7587, "step": 34890 }, { "epoch": 7.23, "learning_rate": 0.0007157713958591737, "loss": 1.754, "step": 34895 }, { "epoch": 7.23, "learning_rate": 0.000715675985115924, "loss": 1.7533, "step": 34900 }, { "epoch": 7.23, "learning_rate": 0.0007155805743726745, "loss": 1.7565, "step": 34905 }, { "epoch": 7.23, "learning_rate": 0.0007154851636294248, "loss": 1.7574, "step": 34910 }, { "epoch": 7.23, "learning_rate": 0.000715389752886175, "loss": 1.7515, "step": 34915 }, { "epoch": 7.23, "learning_rate": 0.0007152943421429253, "loss": 1.7596, "step": 34920 }, { "epoch": 7.24, "learning_rate": 0.0007151989313996756, "loss": 1.7588, "step": 34925 }, { "epoch": 7.24, "learning_rate": 0.0007151035206564259, "loss": 1.7596, "step": 34930 }, { "epoch": 7.24, "learning_rate": 0.0007150081099131763, "loss": 1.7594, "step": 34935 }, { "epoch": 7.24, "learning_rate": 0.0007149126991699265, "loss": 1.7582, "step": 34940 }, { "epoch": 7.24, "learning_rate": 0.0007148172884266768, "loss": 1.7585, "step": 34945 }, { "epoch": 7.24, "learning_rate": 0.0007147218776834272, "loss": 1.7553, "step": 34950 }, { "epoch": 7.24, "learning_rate": 0.0007146264669401775, "loss": 1.7624, "step": 34955 }, { "epoch": 7.24, "learning_rate": 0.0007145310561969278, "loss": 1.7554, "step": 34960 }, { "epoch": 7.24, "learning_rate": 0.0007144356454536782, "loss": 1.7647, "step": 34965 }, { "epoch": 7.24, "learning_rate": 0.0007143402347104284, "loss": 1.7604, "step": 34970 }, { "epoch": 7.25, "learning_rate": 0.0007142448239671787, "loss": 1.7609, "step": 34975 }, { "epoch": 7.25, "learning_rate": 0.000714149413223929, "loss": 1.7614, "step": 34980 }, { "epoch": 7.25, "learning_rate": 0.0007140540024806793, "loss": 1.7568, "step": 34985 }, { "epoch": 7.25, "learning_rate": 0.0007139585917374296, "loss": 1.7579, "step": 34990 }, { "epoch": 7.25, "learning_rate": 0.00071386318099418, "loss": 1.7556, "step": 34995 }, { "epoch": 7.25, "learning_rate": 0.0007137677702509303, "loss": 1.7662, "step": 35000 }, { "epoch": 7.25, "learning_rate": 0.0007136723595076806, "loss": 1.7627, "step": 35005 }, { "epoch": 7.25, "learning_rate": 0.0007135769487644309, "loss": 1.7599, "step": 35010 }, { "epoch": 7.25, "learning_rate": 0.0007134815380211812, "loss": 1.7546, "step": 35015 }, { "epoch": 7.26, "learning_rate": 0.0007133861272779315, "loss": 1.7587, "step": 35020 }, { "epoch": 7.26, "learning_rate": 0.0007132907165346818, "loss": 1.7592, "step": 35025 }, { "epoch": 7.26, "learning_rate": 0.0007131953057914321, "loss": 1.7554, "step": 35030 }, { "epoch": 7.26, "learning_rate": 0.0007130998950481824, "loss": 1.7592, "step": 35035 }, { "epoch": 7.26, "learning_rate": 0.0007130044843049327, "loss": 1.7591, "step": 35040 }, { "epoch": 7.26, "learning_rate": 0.0007129090735616831, "loss": 1.7608, "step": 35045 }, { "epoch": 7.26, "learning_rate": 0.0007128136628184334, "loss": 1.7565, "step": 35050 }, { "epoch": 7.26, "learning_rate": 0.0007127182520751837, "loss": 1.7571, "step": 35055 }, { "epoch": 7.26, "learning_rate": 0.000712622841331934, "loss": 1.759, "step": 35060 }, { "epoch": 7.26, "learning_rate": 0.0007125274305886843, "loss": 1.7558, "step": 35065 }, { "epoch": 7.27, "learning_rate": 0.0007124320198454346, "loss": 1.754, "step": 35070 }, { "epoch": 7.27, "learning_rate": 0.0007123366091021849, "loss": 1.7603, "step": 35075 }, { "epoch": 7.27, "learning_rate": 0.0007122411983589352, "loss": 1.7564, "step": 35080 }, { "epoch": 7.27, "learning_rate": 0.0007121457876156855, "loss": 1.7593, "step": 35085 }, { "epoch": 7.27, "learning_rate": 0.0007120503768724359, "loss": 1.7519, "step": 35090 }, { "epoch": 7.27, "learning_rate": 0.0007119549661291862, "loss": 1.7569, "step": 35095 }, { "epoch": 7.27, "learning_rate": 0.0007118595553859365, "loss": 1.758, "step": 35100 }, { "epoch": 7.27, "learning_rate": 0.0007117641446426868, "loss": 1.759, "step": 35105 }, { "epoch": 7.27, "learning_rate": 0.0007116687338994371, "loss": 1.7566, "step": 35110 }, { "epoch": 7.27, "learning_rate": 0.0007115733231561874, "loss": 1.7535, "step": 35115 }, { "epoch": 7.28, "learning_rate": 0.0007114779124129377, "loss": 1.7641, "step": 35120 }, { "epoch": 7.28, "learning_rate": 0.000711382501669688, "loss": 1.7536, "step": 35125 }, { "epoch": 7.28, "learning_rate": 0.0007112870909264383, "loss": 1.7632, "step": 35130 }, { "epoch": 7.28, "learning_rate": 0.0007111916801831887, "loss": 1.7534, "step": 35135 }, { "epoch": 7.28, "learning_rate": 0.000711096269439939, "loss": 1.7565, "step": 35140 }, { "epoch": 7.28, "learning_rate": 0.0007110008586966893, "loss": 1.7602, "step": 35145 }, { "epoch": 7.28, "learning_rate": 0.0007109054479534396, "loss": 1.7545, "step": 35150 }, { "epoch": 7.28, "learning_rate": 0.0007108100372101899, "loss": 1.7598, "step": 35155 }, { "epoch": 7.28, "learning_rate": 0.0007107146264669402, "loss": 1.7578, "step": 35160 }, { "epoch": 7.29, "learning_rate": 0.0007106192157236904, "loss": 1.7549, "step": 35165 }, { "epoch": 7.29, "learning_rate": 0.0007105238049804408, "loss": 1.7542, "step": 35170 }, { "epoch": 7.29, "learning_rate": 0.0007104283942371911, "loss": 1.7578, "step": 35175 }, { "epoch": 7.29, "learning_rate": 0.0007103329834939415, "loss": 1.7586, "step": 35180 }, { "epoch": 7.29, "learning_rate": 0.0007102375727506918, "loss": 1.7586, "step": 35185 }, { "epoch": 7.29, "learning_rate": 0.000710142162007442, "loss": 1.7542, "step": 35190 }, { "epoch": 7.29, "learning_rate": 0.0007100467512641923, "loss": 1.7578, "step": 35195 }, { "epoch": 7.29, "learning_rate": 0.0007099513405209427, "loss": 1.7614, "step": 35200 }, { "epoch": 7.29, "learning_rate": 0.000709855929777693, "loss": 1.753, "step": 35205 }, { "epoch": 7.29, "learning_rate": 0.0007097605190344433, "loss": 1.7564, "step": 35210 }, { "epoch": 7.3, "learning_rate": 0.0007096651082911936, "loss": 1.7624, "step": 35215 }, { "epoch": 7.3, "learning_rate": 0.0007095696975479438, "loss": 1.7604, "step": 35220 }, { "epoch": 7.3, "learning_rate": 0.0007094742868046941, "loss": 1.757, "step": 35225 }, { "epoch": 7.3, "learning_rate": 0.0007093788760614446, "loss": 1.7596, "step": 35230 }, { "epoch": 7.3, "learning_rate": 0.0007092834653181949, "loss": 1.76, "step": 35235 }, { "epoch": 7.3, "learning_rate": 0.0007091880545749452, "loss": 1.7532, "step": 35240 }, { "epoch": 7.3, "learning_rate": 0.0007090926438316955, "loss": 1.7516, "step": 35245 }, { "epoch": 7.3, "learning_rate": 0.0007089972330884457, "loss": 1.755, "step": 35250 }, { "epoch": 7.3, "learning_rate": 0.000708901822345196, "loss": 1.7581, "step": 35255 }, { "epoch": 7.3, "learning_rate": 0.0007088064116019464, "loss": 1.7606, "step": 35260 }, { "epoch": 7.31, "learning_rate": 0.0007087110008586967, "loss": 1.7555, "step": 35265 }, { "epoch": 7.31, "learning_rate": 0.000708615590115447, "loss": 1.7593, "step": 35270 }, { "epoch": 7.31, "learning_rate": 0.0007085201793721974, "loss": 1.7566, "step": 35275 }, { "epoch": 7.31, "learning_rate": 0.0007084247686289476, "loss": 1.7528, "step": 35280 }, { "epoch": 7.31, "learning_rate": 0.000708329357885698, "loss": 1.7599, "step": 35285 }, { "epoch": 7.31, "learning_rate": 0.0007082339471424483, "loss": 1.7561, "step": 35290 }, { "epoch": 7.31, "learning_rate": 0.0007081385363991986, "loss": 1.7597, "step": 35295 }, { "epoch": 7.31, "learning_rate": 0.0007080431256559489, "loss": 1.756, "step": 35300 }, { "epoch": 7.31, "learning_rate": 0.0007079477149126991, "loss": 1.76, "step": 35305 }, { "epoch": 7.32, "learning_rate": 0.0007078523041694494, "loss": 1.7621, "step": 35310 }, { "epoch": 7.32, "learning_rate": 0.0007077568934261998, "loss": 1.7599, "step": 35315 }, { "epoch": 7.32, "learning_rate": 0.0007076614826829502, "loss": 1.7575, "step": 35320 }, { "epoch": 7.32, "learning_rate": 0.0007075660719397005, "loss": 1.7572, "step": 35325 }, { "epoch": 7.32, "learning_rate": 0.0007074706611964508, "loss": 1.7553, "step": 35330 }, { "epoch": 7.32, "learning_rate": 0.000707375250453201, "loss": 1.7584, "step": 35335 }, { "epoch": 7.32, "learning_rate": 0.0007072798397099513, "loss": 1.7529, "step": 35340 }, { "epoch": 7.32, "learning_rate": 0.0007071844289667017, "loss": 1.7605, "step": 35345 }, { "epoch": 7.32, "learning_rate": 0.000707089018223452, "loss": 1.7592, "step": 35350 }, { "epoch": 7.32, "learning_rate": 0.0007069936074802023, "loss": 1.758, "step": 35355 }, { "epoch": 7.33, "learning_rate": 0.0007068981967369525, "loss": 1.7572, "step": 35360 }, { "epoch": 7.33, "learning_rate": 0.0007068027859937029, "loss": 1.7629, "step": 35365 }, { "epoch": 7.33, "learning_rate": 0.0007067073752504532, "loss": 1.7596, "step": 35370 }, { "epoch": 7.33, "learning_rate": 0.0007066119645072036, "loss": 1.7606, "step": 35375 }, { "epoch": 7.33, "learning_rate": 0.0007065165537639539, "loss": 1.7653, "step": 35380 }, { "epoch": 7.33, "learning_rate": 0.0007064211430207042, "loss": 1.7589, "step": 35385 }, { "epoch": 7.33, "learning_rate": 0.0007063257322774544, "loss": 1.7572, "step": 35390 }, { "epoch": 7.33, "learning_rate": 0.0007062303215342047, "loss": 1.7555, "step": 35395 }, { "epoch": 7.33, "learning_rate": 0.000706134910790955, "loss": 1.7582, "step": 35400 }, { "epoch": 7.33, "learning_rate": 0.0007060395000477054, "loss": 1.7583, "step": 35405 }, { "epoch": 7.34, "learning_rate": 0.0007059440893044558, "loss": 1.7586, "step": 35410 }, { "epoch": 7.34, "learning_rate": 0.000705848678561206, "loss": 1.7552, "step": 35415 }, { "epoch": 7.34, "learning_rate": 0.0007057532678179563, "loss": 1.7614, "step": 35420 }, { "epoch": 7.34, "learning_rate": 0.0007056578570747066, "loss": 1.7611, "step": 35425 }, { "epoch": 7.34, "learning_rate": 0.0007055624463314569, "loss": 1.7596, "step": 35430 }, { "epoch": 7.34, "learning_rate": 0.0007054670355882073, "loss": 1.7603, "step": 35435 }, { "epoch": 7.34, "learning_rate": 0.0007053716248449576, "loss": 1.7549, "step": 35440 }, { "epoch": 7.34, "learning_rate": 0.0007052762141017078, "loss": 1.7629, "step": 35445 }, { "epoch": 7.34, "learning_rate": 0.0007051808033584581, "loss": 1.7567, "step": 35450 }, { "epoch": 7.35, "learning_rate": 0.0007050853926152084, "loss": 1.7586, "step": 35455 }, { "epoch": 7.35, "learning_rate": 0.0007049899818719588, "loss": 1.7604, "step": 35460 }, { "epoch": 7.35, "learning_rate": 0.0007048945711287092, "loss": 1.7597, "step": 35465 }, { "epoch": 7.35, "learning_rate": 0.0007047991603854595, "loss": 1.7564, "step": 35470 }, { "epoch": 7.35, "learning_rate": 0.0007047037496422097, "loss": 1.7549, "step": 35475 }, { "epoch": 7.35, "learning_rate": 0.00070460833889896, "loss": 1.7552, "step": 35480 }, { "epoch": 7.35, "learning_rate": 0.0007045129281557103, "loss": 1.7574, "step": 35485 }, { "epoch": 7.35, "learning_rate": 0.0007044175174124606, "loss": 1.7562, "step": 35490 }, { "epoch": 7.35, "learning_rate": 0.000704322106669211, "loss": 1.7512, "step": 35495 }, { "epoch": 7.35, "learning_rate": 0.0007042266959259612, "loss": 1.7549, "step": 35500 }, { "epoch": 7.36, "learning_rate": 0.0007041312851827116, "loss": 1.76, "step": 35505 }, { "epoch": 7.36, "learning_rate": 0.0007040358744394619, "loss": 1.7558, "step": 35510 }, { "epoch": 7.36, "learning_rate": 0.0007039404636962122, "loss": 1.7624, "step": 35515 }, { "epoch": 7.36, "learning_rate": 0.0007038450529529626, "loss": 1.7521, "step": 35520 }, { "epoch": 7.36, "learning_rate": 0.0007037496422097129, "loss": 1.7581, "step": 35525 }, { "epoch": 7.36, "learning_rate": 0.0007036542314664631, "loss": 1.7557, "step": 35530 }, { "epoch": 7.36, "learning_rate": 0.0007035588207232134, "loss": 1.7592, "step": 35535 }, { "epoch": 7.36, "learning_rate": 0.0007034634099799637, "loss": 1.7587, "step": 35540 }, { "epoch": 7.36, "learning_rate": 0.000703367999236714, "loss": 1.7595, "step": 35545 }, { "epoch": 7.36, "learning_rate": 0.0007032725884934645, "loss": 1.7597, "step": 35550 }, { "epoch": 7.37, "learning_rate": 0.0007031771777502148, "loss": 1.7544, "step": 35555 }, { "epoch": 7.37, "learning_rate": 0.000703081767006965, "loss": 1.7602, "step": 35560 }, { "epoch": 7.37, "learning_rate": 0.0007029863562637153, "loss": 1.7534, "step": 35565 }, { "epoch": 7.37, "learning_rate": 0.0007028909455204656, "loss": 1.7597, "step": 35570 }, { "epoch": 7.37, "learning_rate": 0.0007027955347772159, "loss": 1.7554, "step": 35575 }, { "epoch": 7.37, "learning_rate": 0.0007027001240339663, "loss": 1.754, "step": 35580 }, { "epoch": 7.37, "learning_rate": 0.0007026047132907165, "loss": 1.7587, "step": 35585 }, { "epoch": 7.37, "learning_rate": 0.0007025093025474668, "loss": 1.7541, "step": 35590 }, { "epoch": 7.37, "learning_rate": 0.0007024138918042172, "loss": 1.7543, "step": 35595 }, { "epoch": 7.38, "learning_rate": 0.0007023184810609675, "loss": 1.7623, "step": 35600 }, { "epoch": 7.38, "learning_rate": 0.0007022230703177178, "loss": 1.7558, "step": 35605 }, { "epoch": 7.38, "learning_rate": 0.0007021276595744682, "loss": 1.7594, "step": 35610 }, { "epoch": 7.38, "learning_rate": 0.0007020322488312184, "loss": 1.7586, "step": 35615 }, { "epoch": 7.38, "learning_rate": 0.0007019368380879687, "loss": 1.7641, "step": 35620 }, { "epoch": 7.38, "learning_rate": 0.000701841427344719, "loss": 1.7649, "step": 35625 }, { "epoch": 7.38, "learning_rate": 0.0007017460166014693, "loss": 1.758, "step": 35630 }, { "epoch": 7.38, "learning_rate": 0.0007016506058582196, "loss": 1.7577, "step": 35635 }, { "epoch": 7.38, "learning_rate": 0.00070155519511497, "loss": 1.7579, "step": 35640 }, { "epoch": 7.38, "learning_rate": 0.0007014597843717203, "loss": 1.7554, "step": 35645 }, { "epoch": 7.39, "learning_rate": 0.0007013643736284706, "loss": 1.7601, "step": 35650 }, { "epoch": 7.39, "learning_rate": 0.0007012689628852209, "loss": 1.7555, "step": 35655 }, { "epoch": 7.39, "learning_rate": 0.0007011735521419712, "loss": 1.762, "step": 35660 }, { "epoch": 7.39, "learning_rate": 0.0007010781413987215, "loss": 1.7563, "step": 35665 }, { "epoch": 7.39, "learning_rate": 0.0007009827306554718, "loss": 1.7599, "step": 35670 }, { "epoch": 7.39, "learning_rate": 0.0007008873199122221, "loss": 1.7534, "step": 35675 }, { "epoch": 7.39, "learning_rate": 0.0007007919091689724, "loss": 1.7577, "step": 35680 }, { "epoch": 7.39, "learning_rate": 0.0007006964984257228, "loss": 1.7541, "step": 35685 }, { "epoch": 7.39, "learning_rate": 0.0007006010876824731, "loss": 1.7581, "step": 35690 }, { "epoch": 7.39, "learning_rate": 0.0007005056769392235, "loss": 1.7592, "step": 35695 }, { "epoch": 7.4, "learning_rate": 0.0007004102661959737, "loss": 1.7553, "step": 35700 }, { "epoch": 7.4, "learning_rate": 0.000700314855452724, "loss": 1.7482, "step": 35705 }, { "epoch": 7.4, "learning_rate": 0.0007002194447094743, "loss": 1.7542, "step": 35710 }, { "epoch": 7.4, "learning_rate": 0.0007001240339662246, "loss": 1.7582, "step": 35715 }, { "epoch": 7.4, "learning_rate": 0.0007000286232229749, "loss": 1.7526, "step": 35720 }, { "epoch": 7.4, "learning_rate": 0.0006999332124797252, "loss": 1.7557, "step": 35725 }, { "epoch": 7.4, "learning_rate": 0.0006998378017364755, "loss": 1.7616, "step": 35730 }, { "epoch": 7.4, "learning_rate": 0.0006997423909932259, "loss": 1.7567, "step": 35735 }, { "epoch": 7.4, "learning_rate": 0.0006996469802499762, "loss": 1.755, "step": 35740 }, { "epoch": 7.41, "learning_rate": 0.0006995515695067265, "loss": 1.7563, "step": 35745 }, { "epoch": 7.41, "learning_rate": 0.0006994561587634768, "loss": 1.7584, "step": 35750 }, { "epoch": 7.41, "learning_rate": 0.0006993607480202271, "loss": 1.7488, "step": 35755 }, { "epoch": 7.41, "learning_rate": 0.0006992653372769774, "loss": 1.7599, "step": 35760 }, { "epoch": 7.41, "learning_rate": 0.0006991699265337277, "loss": 1.7589, "step": 35765 }, { "epoch": 7.41, "learning_rate": 0.000699074515790478, "loss": 1.7557, "step": 35770 }, { "epoch": 7.41, "learning_rate": 0.0006989791050472283, "loss": 1.7539, "step": 35775 }, { "epoch": 7.41, "learning_rate": 0.0006988836943039786, "loss": 1.7592, "step": 35780 }, { "epoch": 7.41, "learning_rate": 0.000698788283560729, "loss": 1.7545, "step": 35785 }, { "epoch": 7.41, "learning_rate": 0.0006986928728174793, "loss": 1.7572, "step": 35790 }, { "epoch": 7.42, "learning_rate": 0.0006985974620742296, "loss": 1.7582, "step": 35795 }, { "epoch": 7.42, "learning_rate": 0.0006985020513309799, "loss": 1.7608, "step": 35800 }, { "epoch": 7.42, "learning_rate": 0.0006984066405877302, "loss": 1.7567, "step": 35805 }, { "epoch": 7.42, "learning_rate": 0.0006983112298444804, "loss": 1.7577, "step": 35810 }, { "epoch": 7.42, "learning_rate": 0.0006982158191012308, "loss": 1.7612, "step": 35815 }, { "epoch": 7.42, "learning_rate": 0.0006981204083579811, "loss": 1.7599, "step": 35820 }, { "epoch": 7.42, "learning_rate": 0.0006980249976147315, "loss": 1.7548, "step": 35825 }, { "epoch": 7.42, "learning_rate": 0.0006979295868714818, "loss": 1.7556, "step": 35830 }, { "epoch": 7.42, "learning_rate": 0.000697834176128232, "loss": 1.7578, "step": 35835 }, { "epoch": 7.42, "learning_rate": 0.0006977387653849823, "loss": 1.7633, "step": 35840 }, { "epoch": 7.43, "learning_rate": 0.0006976433546417327, "loss": 1.7586, "step": 35845 }, { "epoch": 7.43, "learning_rate": 0.000697547943898483, "loss": 1.7551, "step": 35850 }, { "epoch": 7.43, "learning_rate": 0.0006974525331552333, "loss": 1.7534, "step": 35855 }, { "epoch": 7.43, "learning_rate": 0.0006973571224119836, "loss": 1.7615, "step": 35860 }, { "epoch": 7.43, "learning_rate": 0.0006972617116687338, "loss": 1.7514, "step": 35865 }, { "epoch": 7.43, "learning_rate": 0.0006971663009254842, "loss": 1.7568, "step": 35870 }, { "epoch": 7.43, "learning_rate": 0.0006970708901822346, "loss": 1.7582, "step": 35875 }, { "epoch": 7.43, "learning_rate": 0.0006969754794389849, "loss": 1.7611, "step": 35880 }, { "epoch": 7.43, "learning_rate": 0.0006968800686957352, "loss": 1.7587, "step": 35885 }, { "epoch": 7.44, "learning_rate": 0.0006967846579524855, "loss": 1.7567, "step": 35890 }, { "epoch": 7.44, "learning_rate": 0.0006966892472092357, "loss": 1.7614, "step": 35895 }, { "epoch": 7.44, "learning_rate": 0.000696593836465986, "loss": 1.7577, "step": 35900 }, { "epoch": 7.44, "learning_rate": 0.0006964984257227364, "loss": 1.7601, "step": 35905 }, { "epoch": 7.44, "learning_rate": 0.0006964030149794867, "loss": 1.7576, "step": 35910 }, { "epoch": 7.44, "learning_rate": 0.0006963076042362371, "loss": 1.7563, "step": 35915 }, { "epoch": 7.44, "learning_rate": 0.0006962121934929873, "loss": 1.7538, "step": 35920 }, { "epoch": 7.44, "learning_rate": 0.0006961167827497376, "loss": 1.7609, "step": 35925 }, { "epoch": 7.44, "learning_rate": 0.000696021372006488, "loss": 1.756, "step": 35930 }, { "epoch": 7.44, "learning_rate": 0.0006959259612632383, "loss": 1.753, "step": 35935 }, { "epoch": 7.45, "learning_rate": 0.0006958305505199886, "loss": 1.7575, "step": 35940 }, { "epoch": 7.45, "learning_rate": 0.0006957351397767389, "loss": 1.754, "step": 35945 }, { "epoch": 7.45, "learning_rate": 0.0006956397290334891, "loss": 1.7532, "step": 35950 }, { "epoch": 7.45, "learning_rate": 0.0006955443182902394, "loss": 1.7565, "step": 35955 }, { "epoch": 7.45, "learning_rate": 0.0006954489075469898, "loss": 1.7587, "step": 35960 }, { "epoch": 7.45, "learning_rate": 0.0006953534968037402, "loss": 1.7576, "step": 35965 }, { "epoch": 7.45, "learning_rate": 0.0006952580860604905, "loss": 1.7587, "step": 35970 }, { "epoch": 7.45, "learning_rate": 0.0006951626753172408, "loss": 1.7581, "step": 35975 }, { "epoch": 7.45, "learning_rate": 0.000695067264573991, "loss": 1.7547, "step": 35980 }, { "epoch": 7.45, "learning_rate": 0.0006949718538307413, "loss": 1.7547, "step": 35985 }, { "epoch": 7.46, "learning_rate": 0.0006948764430874917, "loss": 1.7632, "step": 35990 }, { "epoch": 7.46, "learning_rate": 0.000694781032344242, "loss": 1.7601, "step": 35995 }, { "epoch": 7.46, "learning_rate": 0.0006946856216009923, "loss": 1.7567, "step": 36000 }, { "epoch": 7.46, "eval_accuracy": 0.5395032679738562, "eval_loss": 1.94707190990448, "eval_runtime": 0.9511, "eval_samples_per_second": 157.704, "eval_steps_per_second": 1.051, "step": 36000 }, { "epoch": 7.46, "learning_rate": 0.0006945902108577425, "loss": 1.7548, "step": 36005 }, { "epoch": 7.46, "learning_rate": 0.0006944948001144929, "loss": 1.7548, "step": 36010 }, { "epoch": 7.46, "learning_rate": 0.0006943993893712432, "loss": 1.7559, "step": 36015 }, { "epoch": 7.46, "learning_rate": 0.0006943039786279936, "loss": 1.7588, "step": 36020 }, { "epoch": 7.46, "learning_rate": 0.0006942085678847439, "loss": 1.7559, "step": 36025 }, { "epoch": 7.46, "learning_rate": 0.0006941131571414942, "loss": 1.7609, "step": 36030 }, { "epoch": 7.47, "learning_rate": 0.0006940177463982444, "loss": 1.7558, "step": 36035 }, { "epoch": 7.47, "learning_rate": 0.0006939223356549947, "loss": 1.7572, "step": 36040 }, { "epoch": 7.47, "learning_rate": 0.000693826924911745, "loss": 1.7578, "step": 36045 }, { "epoch": 7.47, "learning_rate": 0.0006937315141684954, "loss": 1.7596, "step": 36050 }, { "epoch": 7.47, "learning_rate": 0.0006936361034252458, "loss": 1.758, "step": 36055 }, { "epoch": 7.47, "learning_rate": 0.000693540692681996, "loss": 1.7553, "step": 36060 }, { "epoch": 7.47, "learning_rate": 0.0006934452819387463, "loss": 1.7576, "step": 36065 }, { "epoch": 7.47, "learning_rate": 0.0006933498711954966, "loss": 1.7608, "step": 36070 }, { "epoch": 7.47, "learning_rate": 0.0006932544604522469, "loss": 1.7536, "step": 36075 }, { "epoch": 7.47, "learning_rate": 0.0006931590497089973, "loss": 1.7563, "step": 36080 }, { "epoch": 7.48, "learning_rate": 0.0006930636389657476, "loss": 1.7553, "step": 36085 }, { "epoch": 7.48, "learning_rate": 0.0006929682282224978, "loss": 1.753, "step": 36090 }, { "epoch": 7.48, "learning_rate": 0.0006928728174792481, "loss": 1.7547, "step": 36095 }, { "epoch": 7.48, "learning_rate": 0.0006927774067359985, "loss": 1.7545, "step": 36100 }, { "epoch": 7.48, "learning_rate": 0.0006926819959927488, "loss": 1.755, "step": 36105 }, { "epoch": 7.48, "learning_rate": 0.0006925865852494992, "loss": 1.7546, "step": 36110 }, { "epoch": 7.48, "learning_rate": 0.0006924911745062495, "loss": 1.7575, "step": 36115 }, { "epoch": 7.48, "learning_rate": 0.0006923957637629997, "loss": 1.7542, "step": 36120 }, { "epoch": 7.48, "learning_rate": 0.00069230035301975, "loss": 1.7531, "step": 36125 }, { "epoch": 7.48, "learning_rate": 0.0006922049422765003, "loss": 1.7528, "step": 36130 }, { "epoch": 7.49, "learning_rate": 0.0006921095315332507, "loss": 1.7566, "step": 36135 }, { "epoch": 7.49, "learning_rate": 0.000692014120790001, "loss": 1.7557, "step": 36140 }, { "epoch": 7.49, "learning_rate": 0.0006919187100467513, "loss": 1.7623, "step": 36145 }, { "epoch": 7.49, "learning_rate": 0.0006918232993035016, "loss": 1.7591, "step": 36150 }, { "epoch": 7.49, "learning_rate": 0.0006917278885602519, "loss": 1.7601, "step": 36155 }, { "epoch": 7.49, "learning_rate": 0.0006916324778170022, "loss": 1.7581, "step": 36160 }, { "epoch": 7.49, "learning_rate": 0.0006915370670737526, "loss": 1.7505, "step": 36165 }, { "epoch": 7.49, "learning_rate": 0.0006914416563305029, "loss": 1.7582, "step": 36170 }, { "epoch": 7.49, "learning_rate": 0.0006913462455872531, "loss": 1.7519, "step": 36175 }, { "epoch": 7.5, "learning_rate": 0.0006912508348440034, "loss": 1.7532, "step": 36180 }, { "epoch": 7.5, "learning_rate": 0.0006911554241007537, "loss": 1.7525, "step": 36185 }, { "epoch": 7.5, "learning_rate": 0.0006910600133575041, "loss": 1.7542, "step": 36190 }, { "epoch": 7.5, "learning_rate": 0.0006909646026142545, "loss": 1.7573, "step": 36195 }, { "epoch": 7.5, "learning_rate": 0.0006908691918710047, "loss": 1.7597, "step": 36200 }, { "epoch": 7.5, "learning_rate": 0.000690773781127755, "loss": 1.7549, "step": 36205 }, { "epoch": 7.5, "learning_rate": 0.0006906783703845053, "loss": 1.7575, "step": 36210 }, { "epoch": 7.5, "learning_rate": 0.0006905829596412556, "loss": 1.7497, "step": 36215 }, { "epoch": 7.5, "learning_rate": 0.0006904875488980059, "loss": 1.7564, "step": 36220 }, { "epoch": 7.5, "learning_rate": 0.0006903921381547563, "loss": 1.7561, "step": 36225 }, { "epoch": 7.51, "learning_rate": 0.0006902967274115065, "loss": 1.751, "step": 36230 }, { "epoch": 7.51, "learning_rate": 0.0006902013166682568, "loss": 1.7609, "step": 36235 }, { "epoch": 7.51, "learning_rate": 0.0006901059059250072, "loss": 1.7602, "step": 36240 }, { "epoch": 7.51, "learning_rate": 0.0006900104951817575, "loss": 1.7533, "step": 36245 }, { "epoch": 7.51, "learning_rate": 0.0006899150844385078, "loss": 1.7609, "step": 36250 }, { "epoch": 7.51, "learning_rate": 0.0006898196736952582, "loss": 1.7608, "step": 36255 }, { "epoch": 7.51, "learning_rate": 0.0006897242629520084, "loss": 1.7571, "step": 36260 }, { "epoch": 7.51, "learning_rate": 0.0006896288522087587, "loss": 1.7519, "step": 36265 }, { "epoch": 7.51, "learning_rate": 0.000689533441465509, "loss": 1.759, "step": 36270 }, { "epoch": 7.52, "learning_rate": 0.0006894380307222593, "loss": 1.7568, "step": 36275 }, { "epoch": 7.52, "learning_rate": 0.0006893426199790096, "loss": 1.7531, "step": 36280 }, { "epoch": 7.52, "learning_rate": 0.00068924720923576, "loss": 1.7557, "step": 36285 }, { "epoch": 7.52, "learning_rate": 0.0006891517984925103, "loss": 1.7576, "step": 36290 }, { "epoch": 7.52, "learning_rate": 0.0006890563877492606, "loss": 1.7511, "step": 36295 }, { "epoch": 7.52, "learning_rate": 0.0006889609770060109, "loss": 1.7535, "step": 36300 }, { "epoch": 7.52, "learning_rate": 0.0006888655662627612, "loss": 1.7589, "step": 36305 }, { "epoch": 7.52, "learning_rate": 0.0006887701555195114, "loss": 1.753, "step": 36310 }, { "epoch": 7.52, "learning_rate": 0.0006886747447762618, "loss": 1.7545, "step": 36315 }, { "epoch": 7.52, "learning_rate": 0.0006885793340330121, "loss": 1.7569, "step": 36320 }, { "epoch": 7.53, "learning_rate": 0.0006884839232897624, "loss": 1.7592, "step": 36325 }, { "epoch": 7.53, "learning_rate": 0.0006883885125465128, "loss": 1.7573, "step": 36330 }, { "epoch": 7.53, "learning_rate": 0.0006882931018032631, "loss": 1.7566, "step": 36335 }, { "epoch": 7.53, "learning_rate": 0.0006881976910600135, "loss": 1.7603, "step": 36340 }, { "epoch": 7.53, "learning_rate": 0.0006881022803167637, "loss": 1.7586, "step": 36345 }, { "epoch": 7.53, "learning_rate": 0.000688006869573514, "loss": 1.7603, "step": 36350 }, { "epoch": 7.53, "learning_rate": 0.0006879114588302643, "loss": 1.7558, "step": 36355 }, { "epoch": 7.53, "learning_rate": 0.0006878160480870146, "loss": 1.7522, "step": 36360 }, { "epoch": 7.53, "learning_rate": 0.0006877206373437649, "loss": 1.7519, "step": 36365 }, { "epoch": 7.53, "learning_rate": 0.0006876252266005152, "loss": 1.7548, "step": 36370 }, { "epoch": 7.54, "learning_rate": 0.0006875298158572656, "loss": 1.759, "step": 36375 }, { "epoch": 7.54, "learning_rate": 0.0006874344051140159, "loss": 1.7545, "step": 36380 }, { "epoch": 7.54, "learning_rate": 0.0006873389943707662, "loss": 1.7542, "step": 36385 }, { "epoch": 7.54, "learning_rate": 0.0006872435836275165, "loss": 1.7561, "step": 36390 }, { "epoch": 7.54, "learning_rate": 0.0006871481728842667, "loss": 1.7505, "step": 36395 }, { "epoch": 7.54, "learning_rate": 0.0006870527621410171, "loss": 1.7549, "step": 36400 }, { "epoch": 7.54, "learning_rate": 0.0006869573513977674, "loss": 1.7563, "step": 36405 }, { "epoch": 7.54, "learning_rate": 0.0006868619406545177, "loss": 1.7553, "step": 36410 }, { "epoch": 7.54, "learning_rate": 0.000686766529911268, "loss": 1.765, "step": 36415 }, { "epoch": 7.55, "learning_rate": 0.0006866711191680184, "loss": 1.7578, "step": 36420 }, { "epoch": 7.55, "learning_rate": 0.0006865757084247686, "loss": 1.752, "step": 36425 }, { "epoch": 7.55, "learning_rate": 0.000686480297681519, "loss": 1.7526, "step": 36430 }, { "epoch": 7.55, "learning_rate": 0.0006863848869382693, "loss": 1.7609, "step": 36435 }, { "epoch": 7.55, "learning_rate": 0.0006862894761950196, "loss": 1.7592, "step": 36440 }, { "epoch": 7.55, "learning_rate": 0.0006861940654517699, "loss": 1.7583, "step": 36445 }, { "epoch": 7.55, "learning_rate": 0.0006860986547085201, "loss": 1.7567, "step": 36450 }, { "epoch": 7.55, "learning_rate": 0.0006860032439652704, "loss": 1.7613, "step": 36455 }, { "epoch": 7.55, "learning_rate": 0.0006859078332220208, "loss": 1.7583, "step": 36460 }, { "epoch": 7.55, "learning_rate": 0.0006858124224787711, "loss": 1.756, "step": 36465 }, { "epoch": 7.56, "learning_rate": 0.0006857170117355215, "loss": 1.755, "step": 36470 }, { "epoch": 7.56, "learning_rate": 0.0006856216009922718, "loss": 1.7637, "step": 36475 }, { "epoch": 7.56, "learning_rate": 0.000685526190249022, "loss": 1.753, "step": 36480 }, { "epoch": 7.56, "learning_rate": 0.0006854307795057723, "loss": 1.7566, "step": 36485 }, { "epoch": 7.56, "learning_rate": 0.0006853353687625227, "loss": 1.7537, "step": 36490 }, { "epoch": 7.56, "learning_rate": 0.000685239958019273, "loss": 1.7615, "step": 36495 }, { "epoch": 7.56, "learning_rate": 0.0006851445472760233, "loss": 1.7505, "step": 36500 }, { "epoch": 7.56, "learning_rate": 0.0006850491365327736, "loss": 1.7577, "step": 36505 }, { "epoch": 7.56, "learning_rate": 0.0006849537257895238, "loss": 1.7525, "step": 36510 }, { "epoch": 7.56, "learning_rate": 0.0006848583150462742, "loss": 1.755, "step": 36515 }, { "epoch": 7.57, "learning_rate": 0.0006847629043030246, "loss": 1.7562, "step": 36520 }, { "epoch": 7.57, "learning_rate": 0.0006846674935597749, "loss": 1.7582, "step": 36525 }, { "epoch": 7.57, "learning_rate": 0.0006845720828165252, "loss": 1.7548, "step": 36530 }, { "epoch": 7.57, "learning_rate": 0.0006844766720732754, "loss": 1.7583, "step": 36535 }, { "epoch": 7.57, "learning_rate": 0.0006843812613300257, "loss": 1.752, "step": 36540 }, { "epoch": 7.57, "learning_rate": 0.000684285850586776, "loss": 1.7589, "step": 36545 }, { "epoch": 7.57, "learning_rate": 0.0006841904398435264, "loss": 1.7567, "step": 36550 }, { "epoch": 7.57, "learning_rate": 0.0006840950291002767, "loss": 1.7564, "step": 36555 }, { "epoch": 7.57, "learning_rate": 0.0006839996183570271, "loss": 1.7529, "step": 36560 }, { "epoch": 7.58, "learning_rate": 0.0006839042076137773, "loss": 1.7544, "step": 36565 }, { "epoch": 7.58, "learning_rate": 0.0006838087968705276, "loss": 1.7541, "step": 36570 }, { "epoch": 7.58, "learning_rate": 0.000683713386127278, "loss": 1.7542, "step": 36575 }, { "epoch": 7.58, "learning_rate": 0.0006836179753840283, "loss": 1.7555, "step": 36580 }, { "epoch": 7.58, "learning_rate": 0.0006835225646407786, "loss": 1.7575, "step": 36585 }, { "epoch": 7.58, "learning_rate": 0.0006834271538975288, "loss": 1.7571, "step": 36590 }, { "epoch": 7.58, "learning_rate": 0.0006833317431542791, "loss": 1.7559, "step": 36595 }, { "epoch": 7.58, "learning_rate": 0.0006832363324110294, "loss": 1.7544, "step": 36600 }, { "epoch": 7.58, "learning_rate": 0.0006831409216677799, "loss": 1.7552, "step": 36605 }, { "epoch": 7.58, "learning_rate": 0.0006830455109245302, "loss": 1.756, "step": 36610 }, { "epoch": 7.59, "learning_rate": 0.0006829501001812805, "loss": 1.7515, "step": 36615 }, { "epoch": 7.59, "learning_rate": 0.0006828546894380307, "loss": 1.7534, "step": 36620 }, { "epoch": 7.59, "learning_rate": 0.000682759278694781, "loss": 1.7569, "step": 36625 }, { "epoch": 7.59, "learning_rate": 0.0006826638679515313, "loss": 1.7556, "step": 36630 }, { "epoch": 7.59, "learning_rate": 0.0006825684572082817, "loss": 1.7553, "step": 36635 }, { "epoch": 7.59, "learning_rate": 0.000682473046465032, "loss": 1.7587, "step": 36640 }, { "epoch": 7.59, "learning_rate": 0.0006823776357217823, "loss": 1.7561, "step": 36645 }, { "epoch": 7.59, "learning_rate": 0.0006822822249785326, "loss": 1.7545, "step": 36650 }, { "epoch": 7.59, "learning_rate": 0.0006821868142352829, "loss": 1.7596, "step": 36655 }, { "epoch": 7.59, "learning_rate": 0.0006820914034920332, "loss": 1.7514, "step": 36660 }, { "epoch": 7.6, "learning_rate": 0.0006819959927487836, "loss": 1.7616, "step": 36665 }, { "epoch": 7.6, "learning_rate": 0.0006819005820055339, "loss": 1.7535, "step": 36670 }, { "epoch": 7.6, "learning_rate": 0.0006818051712622841, "loss": 1.7599, "step": 36675 }, { "epoch": 7.6, "learning_rate": 0.0006817097605190344, "loss": 1.7595, "step": 36680 }, { "epoch": 7.6, "learning_rate": 0.0006816143497757847, "loss": 1.7591, "step": 36685 }, { "epoch": 7.6, "learning_rate": 0.000681518939032535, "loss": 1.7544, "step": 36690 }, { "epoch": 7.6, "learning_rate": 0.0006814235282892854, "loss": 1.7547, "step": 36695 }, { "epoch": 7.6, "learning_rate": 0.0006813281175460358, "loss": 1.7534, "step": 36700 }, { "epoch": 7.6, "learning_rate": 0.000681232706802786, "loss": 1.7547, "step": 36705 }, { "epoch": 7.61, "learning_rate": 0.0006811372960595363, "loss": 1.7523, "step": 36710 }, { "epoch": 7.61, "learning_rate": 0.0006810418853162866, "loss": 1.7484, "step": 36715 }, { "epoch": 7.61, "learning_rate": 0.0006809464745730369, "loss": 1.7572, "step": 36720 }, { "epoch": 7.61, "learning_rate": 0.0006808510638297873, "loss": 1.7566, "step": 36725 }, { "epoch": 7.61, "learning_rate": 0.0006807556530865376, "loss": 1.7498, "step": 36730 }, { "epoch": 7.61, "learning_rate": 0.0006806602423432878, "loss": 1.7565, "step": 36735 }, { "epoch": 7.61, "learning_rate": 0.0006805648316000381, "loss": 1.7601, "step": 36740 }, { "epoch": 7.61, "learning_rate": 0.0006804694208567885, "loss": 1.7584, "step": 36745 }, { "epoch": 7.61, "learning_rate": 0.0006803740101135388, "loss": 1.7562, "step": 36750 }, { "epoch": 7.61, "learning_rate": 0.0006802785993702892, "loss": 1.7568, "step": 36755 }, { "epoch": 7.62, "learning_rate": 0.0006801831886270394, "loss": 1.761, "step": 36760 }, { "epoch": 7.62, "learning_rate": 0.0006800877778837897, "loss": 1.7507, "step": 36765 }, { "epoch": 7.62, "learning_rate": 0.00067999236714054, "loss": 1.7551, "step": 36770 }, { "epoch": 7.62, "learning_rate": 0.0006798969563972903, "loss": 1.7589, "step": 36775 }, { "epoch": 7.62, "learning_rate": 0.0006798015456540407, "loss": 1.7555, "step": 36780 }, { "epoch": 7.62, "learning_rate": 0.000679706134910791, "loss": 1.7548, "step": 36785 }, { "epoch": 7.62, "learning_rate": 0.0006796107241675413, "loss": 1.7581, "step": 36790 }, { "epoch": 7.62, "learning_rate": 0.0006795153134242916, "loss": 1.7585, "step": 36795 }, { "epoch": 7.62, "learning_rate": 0.0006794199026810419, "loss": 1.7573, "step": 36800 }, { "epoch": 7.62, "learning_rate": 0.0006793244919377922, "loss": 1.7587, "step": 36805 }, { "epoch": 7.63, "learning_rate": 0.0006792290811945426, "loss": 1.7544, "step": 36810 }, { "epoch": 7.63, "learning_rate": 0.0006791336704512928, "loss": 1.7544, "step": 36815 }, { "epoch": 7.63, "learning_rate": 0.0006790382597080431, "loss": 1.7553, "step": 36820 }, { "epoch": 7.63, "learning_rate": 0.0006789428489647934, "loss": 1.7528, "step": 36825 }, { "epoch": 7.63, "learning_rate": 0.0006788474382215437, "loss": 1.7545, "step": 36830 }, { "epoch": 7.63, "learning_rate": 0.0006787520274782941, "loss": 1.7444, "step": 36835 }, { "epoch": 7.63, "learning_rate": 0.0006786566167350445, "loss": 1.7589, "step": 36840 }, { "epoch": 7.63, "learning_rate": 0.0006785612059917947, "loss": 1.7546, "step": 36845 }, { "epoch": 7.63, "learning_rate": 0.000678465795248545, "loss": 1.7563, "step": 36850 }, { "epoch": 7.64, "learning_rate": 0.0006783703845052953, "loss": 1.7544, "step": 36855 }, { "epoch": 7.64, "learning_rate": 0.0006782749737620456, "loss": 1.7565, "step": 36860 }, { "epoch": 7.64, "learning_rate": 0.0006781795630187959, "loss": 1.7533, "step": 36865 }, { "epoch": 7.64, "learning_rate": 0.0006780841522755463, "loss": 1.7571, "step": 36870 }, { "epoch": 7.64, "learning_rate": 0.0006779887415322965, "loss": 1.7602, "step": 36875 }, { "epoch": 7.64, "learning_rate": 0.0006778933307890469, "loss": 1.7516, "step": 36880 }, { "epoch": 7.64, "learning_rate": 0.0006777979200457972, "loss": 1.7498, "step": 36885 }, { "epoch": 7.64, "learning_rate": 0.0006777025093025475, "loss": 1.7495, "step": 36890 }, { "epoch": 7.64, "learning_rate": 0.0006776070985592978, "loss": 1.7523, "step": 36895 }, { "epoch": 7.64, "learning_rate": 0.0006775116878160481, "loss": 1.7527, "step": 36900 }, { "epoch": 7.65, "learning_rate": 0.0006774162770727984, "loss": 1.7539, "step": 36905 }, { "epoch": 7.65, "learning_rate": 0.0006773208663295487, "loss": 1.7543, "step": 36910 }, { "epoch": 7.65, "learning_rate": 0.000677225455586299, "loss": 1.7569, "step": 36915 }, { "epoch": 7.65, "learning_rate": 0.0006771300448430493, "loss": 1.7553, "step": 36920 }, { "epoch": 7.65, "learning_rate": 0.0006770346340997997, "loss": 1.761, "step": 36925 }, { "epoch": 7.65, "learning_rate": 0.00067693922335655, "loss": 1.7532, "step": 36930 }, { "epoch": 7.65, "learning_rate": 0.0006768438126133003, "loss": 1.7568, "step": 36935 }, { "epoch": 7.65, "learning_rate": 0.0006767484018700506, "loss": 1.7596, "step": 36940 }, { "epoch": 7.65, "learning_rate": 0.0006766529911268009, "loss": 1.7575, "step": 36945 }, { "epoch": 7.65, "learning_rate": 0.0006765575803835512, "loss": 1.7513, "step": 36950 }, { "epoch": 7.66, "learning_rate": 0.0006764621696403014, "loss": 1.7576, "step": 36955 }, { "epoch": 7.66, "learning_rate": 0.0006763667588970518, "loss": 1.7599, "step": 36960 }, { "epoch": 7.66, "learning_rate": 0.0006762713481538021, "loss": 1.7515, "step": 36965 }, { "epoch": 7.66, "learning_rate": 0.0006761759374105524, "loss": 1.7553, "step": 36970 }, { "epoch": 7.66, "learning_rate": 0.0006760805266673028, "loss": 1.7611, "step": 36975 }, { "epoch": 7.66, "learning_rate": 0.0006759851159240531, "loss": 1.7567, "step": 36980 }, { "epoch": 7.66, "learning_rate": 0.0006758897051808034, "loss": 1.7577, "step": 36985 }, { "epoch": 7.66, "learning_rate": 0.0006757942944375537, "loss": 1.7566, "step": 36990 }, { "epoch": 7.66, "learning_rate": 0.000675698883694304, "loss": 1.755, "step": 36995 }, { "epoch": 7.67, "learning_rate": 0.0006756034729510543, "loss": 1.755, "step": 37000 }, { "epoch": 7.67, "learning_rate": 0.0006755080622078046, "loss": 1.7561, "step": 37005 }, { "epoch": 7.67, "learning_rate": 0.0006754126514645548, "loss": 1.7508, "step": 37010 }, { "epoch": 7.67, "learning_rate": 0.0006753172407213052, "loss": 1.751, "step": 37015 }, { "epoch": 7.67, "learning_rate": 0.0006752218299780556, "loss": 1.7534, "step": 37020 }, { "epoch": 7.67, "learning_rate": 0.0006751264192348059, "loss": 1.7574, "step": 37025 }, { "epoch": 7.67, "learning_rate": 0.0006750310084915562, "loss": 1.7496, "step": 37030 }, { "epoch": 7.67, "learning_rate": 0.0006749355977483065, "loss": 1.7487, "step": 37035 }, { "epoch": 7.67, "learning_rate": 0.0006748401870050567, "loss": 1.756, "step": 37040 }, { "epoch": 7.67, "learning_rate": 0.0006747447762618071, "loss": 1.7546, "step": 37045 }, { "epoch": 7.68, "learning_rate": 0.0006746493655185574, "loss": 1.7558, "step": 37050 }, { "epoch": 7.68, "learning_rate": 0.0006745539547753077, "loss": 1.7532, "step": 37055 }, { "epoch": 7.68, "learning_rate": 0.000674458544032058, "loss": 1.7516, "step": 37060 }, { "epoch": 7.68, "learning_rate": 0.0006743631332888084, "loss": 1.7529, "step": 37065 }, { "epoch": 7.68, "learning_rate": 0.0006742677225455586, "loss": 1.7577, "step": 37070 }, { "epoch": 7.68, "learning_rate": 0.000674172311802309, "loss": 1.7579, "step": 37075 }, { "epoch": 7.68, "learning_rate": 0.0006740769010590593, "loss": 1.7602, "step": 37080 }, { "epoch": 7.68, "learning_rate": 0.0006739814903158096, "loss": 1.7559, "step": 37085 }, { "epoch": 7.68, "learning_rate": 0.0006738860795725599, "loss": 1.7556, "step": 37090 }, { "epoch": 7.68, "learning_rate": 0.0006737906688293101, "loss": 1.7569, "step": 37095 }, { "epoch": 7.69, "learning_rate": 0.0006736952580860604, "loss": 1.7623, "step": 37100 }, { "epoch": 7.69, "learning_rate": 0.0006735998473428108, "loss": 1.7604, "step": 37105 }, { "epoch": 7.69, "learning_rate": 0.0006735044365995612, "loss": 1.7593, "step": 37110 }, { "epoch": 7.69, "learning_rate": 0.0006734090258563115, "loss": 1.7456, "step": 37115 }, { "epoch": 7.69, "learning_rate": 0.0006733136151130618, "loss": 1.755, "step": 37120 }, { "epoch": 7.69, "learning_rate": 0.000673218204369812, "loss": 1.7548, "step": 37125 }, { "epoch": 7.69, "learning_rate": 0.0006731227936265623, "loss": 1.761, "step": 37130 }, { "epoch": 7.69, "learning_rate": 0.0006730273828833127, "loss": 1.7545, "step": 37135 }, { "epoch": 7.69, "learning_rate": 0.000672931972140063, "loss": 1.7564, "step": 37140 }, { "epoch": 7.7, "learning_rate": 0.0006728365613968133, "loss": 1.7499, "step": 37145 }, { "epoch": 7.7, "learning_rate": 0.0006727411506535635, "loss": 1.7551, "step": 37150 }, { "epoch": 7.7, "learning_rate": 0.0006726457399103139, "loss": 1.761, "step": 37155 }, { "epoch": 7.7, "learning_rate": 0.0006725503291670642, "loss": 1.7534, "step": 37160 }, { "epoch": 7.7, "learning_rate": 0.0006724549184238146, "loss": 1.7522, "step": 37165 }, { "epoch": 7.7, "learning_rate": 0.0006723595076805649, "loss": 1.753, "step": 37170 }, { "epoch": 7.7, "learning_rate": 0.0006722640969373152, "loss": 1.7539, "step": 37175 }, { "epoch": 7.7, "learning_rate": 0.0006721686861940654, "loss": 1.7562, "step": 37180 }, { "epoch": 7.7, "learning_rate": 0.0006720732754508157, "loss": 1.7601, "step": 37185 }, { "epoch": 7.7, "learning_rate": 0.000671977864707566, "loss": 1.7509, "step": 37190 }, { "epoch": 7.71, "learning_rate": 0.0006718824539643164, "loss": 1.752, "step": 37195 }, { "epoch": 7.71, "learning_rate": 0.0006717870432210667, "loss": 1.7569, "step": 37200 }, { "epoch": 7.71, "learning_rate": 0.0006716916324778171, "loss": 1.7527, "step": 37205 }, { "epoch": 7.71, "learning_rate": 0.0006715962217345673, "loss": 1.7532, "step": 37210 }, { "epoch": 7.71, "learning_rate": 0.0006715008109913176, "loss": 1.7562, "step": 37215 }, { "epoch": 7.71, "learning_rate": 0.000671405400248068, "loss": 1.7535, "step": 37220 }, { "epoch": 7.71, "learning_rate": 0.0006713099895048183, "loss": 1.7589, "step": 37225 }, { "epoch": 7.71, "learning_rate": 0.0006712145787615686, "loss": 1.7543, "step": 37230 }, { "epoch": 7.71, "learning_rate": 0.0006711191680183188, "loss": 1.756, "step": 37235 }, { "epoch": 7.71, "learning_rate": 0.0006710237572750691, "loss": 1.7564, "step": 37240 }, { "epoch": 7.72, "learning_rate": 0.0006709283465318194, "loss": 1.7618, "step": 37245 }, { "epoch": 7.72, "learning_rate": 0.0006708329357885699, "loss": 1.7522, "step": 37250 }, { "epoch": 7.72, "learning_rate": 0.0006707375250453202, "loss": 1.754, "step": 37255 }, { "epoch": 7.72, "learning_rate": 0.0006706421143020705, "loss": 1.7549, "step": 37260 }, { "epoch": 7.72, "learning_rate": 0.0006705467035588207, "loss": 1.7606, "step": 37265 }, { "epoch": 7.72, "learning_rate": 0.000670451292815571, "loss": 1.7588, "step": 37270 }, { "epoch": 7.72, "learning_rate": 0.0006703558820723213, "loss": 1.7525, "step": 37275 }, { "epoch": 7.72, "learning_rate": 0.0006702604713290717, "loss": 1.7546, "step": 37280 }, { "epoch": 7.72, "learning_rate": 0.000670165060585822, "loss": 1.7579, "step": 37285 }, { "epoch": 7.73, "learning_rate": 0.0006700696498425722, "loss": 1.756, "step": 37290 }, { "epoch": 7.73, "learning_rate": 0.0006699742390993226, "loss": 1.7549, "step": 37295 }, { "epoch": 7.73, "learning_rate": 0.0006698788283560729, "loss": 1.7585, "step": 37300 }, { "epoch": 7.73, "learning_rate": 0.0006697834176128232, "loss": 1.7523, "step": 37305 }, { "epoch": 7.73, "learning_rate": 0.0006696880068695736, "loss": 1.7528, "step": 37310 }, { "epoch": 7.73, "learning_rate": 0.0006695925961263239, "loss": 1.7587, "step": 37315 }, { "epoch": 7.73, "learning_rate": 0.0006694971853830741, "loss": 1.7532, "step": 37320 }, { "epoch": 7.73, "learning_rate": 0.0006694017746398244, "loss": 1.7554, "step": 37325 }, { "epoch": 7.73, "learning_rate": 0.0006693063638965747, "loss": 1.7529, "step": 37330 }, { "epoch": 7.73, "learning_rate": 0.000669210953153325, "loss": 1.746, "step": 37335 }, { "epoch": 7.74, "learning_rate": 0.0006691155424100755, "loss": 1.7492, "step": 37340 }, { "epoch": 7.74, "learning_rate": 0.0006690201316668258, "loss": 1.7529, "step": 37345 }, { "epoch": 7.74, "learning_rate": 0.000668924720923576, "loss": 1.755, "step": 37350 }, { "epoch": 7.74, "learning_rate": 0.0006688293101803263, "loss": 1.757, "step": 37355 }, { "epoch": 7.74, "learning_rate": 0.0006687338994370766, "loss": 1.7545, "step": 37360 }, { "epoch": 7.74, "learning_rate": 0.0006686384886938269, "loss": 1.748, "step": 37365 }, { "epoch": 7.74, "learning_rate": 0.0006685430779505773, "loss": 1.7541, "step": 37370 }, { "epoch": 7.74, "learning_rate": 0.0006684476672073275, "loss": 1.7545, "step": 37375 }, { "epoch": 7.74, "learning_rate": 0.0006683522564640778, "loss": 1.7634, "step": 37380 }, { "epoch": 7.74, "learning_rate": 0.0006682568457208282, "loss": 1.7489, "step": 37385 }, { "epoch": 7.75, "learning_rate": 0.0006681614349775785, "loss": 1.76, "step": 37390 }, { "epoch": 7.75, "learning_rate": 0.0006680660242343289, "loss": 1.7558, "step": 37395 }, { "epoch": 7.75, "learning_rate": 0.0006679706134910792, "loss": 1.7568, "step": 37400 }, { "epoch": 7.75, "learning_rate": 0.0006678752027478294, "loss": 1.7504, "step": 37405 }, { "epoch": 7.75, "learning_rate": 0.0006677797920045797, "loss": 1.7597, "step": 37410 }, { "epoch": 7.75, "learning_rate": 0.00066768438126133, "loss": 1.7559, "step": 37415 }, { "epoch": 7.75, "learning_rate": 0.0006675889705180803, "loss": 1.7607, "step": 37420 }, { "epoch": 7.75, "learning_rate": 0.0006674935597748307, "loss": 1.7522, "step": 37425 }, { "epoch": 7.75, "learning_rate": 0.000667398149031581, "loss": 1.7549, "step": 37430 }, { "epoch": 7.76, "learning_rate": 0.0006673027382883313, "loss": 1.7525, "step": 37435 }, { "epoch": 7.76, "learning_rate": 0.0006672073275450816, "loss": 1.7473, "step": 37440 }, { "epoch": 7.76, "learning_rate": 0.0006671119168018319, "loss": 1.7516, "step": 37445 }, { "epoch": 7.76, "learning_rate": 0.0006670165060585822, "loss": 1.7547, "step": 37450 }, { "epoch": 7.76, "learning_rate": 0.0006669210953153326, "loss": 1.7567, "step": 37455 }, { "epoch": 7.76, "learning_rate": 0.0006668256845720828, "loss": 1.7566, "step": 37460 }, { "epoch": 7.76, "learning_rate": 0.0006667302738288331, "loss": 1.7543, "step": 37465 }, { "epoch": 7.76, "learning_rate": 0.0006666348630855834, "loss": 1.7536, "step": 37470 }, { "epoch": 7.76, "learning_rate": 0.0006665394523423337, "loss": 1.7563, "step": 37475 }, { "epoch": 7.76, "learning_rate": 0.0006664440415990841, "loss": 1.7551, "step": 37480 }, { "epoch": 7.77, "learning_rate": 0.0006663486308558345, "loss": 1.7501, "step": 37485 }, { "epoch": 7.77, "learning_rate": 0.0006662532201125847, "loss": 1.7565, "step": 37490 }, { "epoch": 7.77, "learning_rate": 0.000666157809369335, "loss": 1.7544, "step": 37495 }, { "epoch": 7.77, "learning_rate": 0.0006660623986260853, "loss": 1.7552, "step": 37500 }, { "epoch": 7.77, "learning_rate": 0.0006659669878828356, "loss": 1.7549, "step": 37505 }, { "epoch": 7.77, "learning_rate": 0.0006658715771395859, "loss": 1.7583, "step": 37510 }, { "epoch": 7.77, "learning_rate": 0.0006657761663963362, "loss": 1.7482, "step": 37515 }, { "epoch": 7.77, "learning_rate": 0.0006656807556530865, "loss": 1.7559, "step": 37520 }, { "epoch": 7.77, "learning_rate": 0.0006655853449098369, "loss": 1.7476, "step": 37525 }, { "epoch": 7.78, "learning_rate": 0.0006654899341665872, "loss": 1.7548, "step": 37530 }, { "epoch": 7.78, "learning_rate": 0.0006653945234233375, "loss": 1.7596, "step": 37535 }, { "epoch": 7.78, "learning_rate": 0.0006652991126800878, "loss": 1.7567, "step": 37540 }, { "epoch": 7.78, "learning_rate": 0.0006652037019368381, "loss": 1.7566, "step": 37545 }, { "epoch": 7.78, "learning_rate": 0.0006651082911935884, "loss": 1.7553, "step": 37550 }, { "epoch": 7.78, "learning_rate": 0.0006650128804503387, "loss": 1.7558, "step": 37555 }, { "epoch": 7.78, "learning_rate": 0.000664917469707089, "loss": 1.758, "step": 37560 }, { "epoch": 7.78, "learning_rate": 0.0006648220589638393, "loss": 1.7542, "step": 37565 }, { "epoch": 7.78, "learning_rate": 0.0006647266482205897, "loss": 1.7545, "step": 37570 }, { "epoch": 7.78, "learning_rate": 0.00066463123747734, "loss": 1.7565, "step": 37575 }, { "epoch": 7.79, "learning_rate": 0.0006645358267340903, "loss": 1.755, "step": 37580 }, { "epoch": 7.79, "learning_rate": 0.0006644404159908406, "loss": 1.7565, "step": 37585 }, { "epoch": 7.79, "learning_rate": 0.0006643450052475909, "loss": 1.753, "step": 37590 }, { "epoch": 7.79, "learning_rate": 0.0006642495945043412, "loss": 1.7533, "step": 37595 }, { "epoch": 7.79, "learning_rate": 0.0006641541837610914, "loss": 1.7524, "step": 37600 }, { "epoch": 7.79, "learning_rate": 0.0006640587730178418, "loss": 1.7587, "step": 37605 }, { "epoch": 7.79, "learning_rate": 0.0006639633622745921, "loss": 1.7554, "step": 37610 }, { "epoch": 7.79, "learning_rate": 0.0006638679515313425, "loss": 1.7548, "step": 37615 }, { "epoch": 7.79, "learning_rate": 0.0006637725407880928, "loss": 1.7522, "step": 37620 }, { "epoch": 7.79, "learning_rate": 0.000663677130044843, "loss": 1.7504, "step": 37625 }, { "epoch": 7.8, "learning_rate": 0.0006635817193015934, "loss": 1.7507, "step": 37630 }, { "epoch": 7.8, "learning_rate": 0.0006634863085583437, "loss": 1.7578, "step": 37635 }, { "epoch": 7.8, "learning_rate": 0.000663390897815094, "loss": 1.7636, "step": 37640 }, { "epoch": 7.8, "learning_rate": 0.0006632954870718443, "loss": 1.7571, "step": 37645 }, { "epoch": 7.8, "learning_rate": 0.0006632000763285946, "loss": 1.7551, "step": 37650 }, { "epoch": 7.8, "learning_rate": 0.0006631046655853448, "loss": 1.7555, "step": 37655 }, { "epoch": 7.8, "learning_rate": 0.0006630092548420953, "loss": 1.7543, "step": 37660 }, { "epoch": 7.8, "learning_rate": 0.0006629138440988456, "loss": 1.7561, "step": 37665 }, { "epoch": 7.8, "learning_rate": 0.0006628184333555959, "loss": 1.7584, "step": 37670 }, { "epoch": 7.81, "learning_rate": 0.0006627230226123462, "loss": 1.7514, "step": 37675 }, { "epoch": 7.81, "learning_rate": 0.0006626276118690965, "loss": 1.7542, "step": 37680 }, { "epoch": 7.81, "learning_rate": 0.0006625322011258467, "loss": 1.7548, "step": 37685 }, { "epoch": 7.81, "learning_rate": 0.0006624367903825971, "loss": 1.7503, "step": 37690 }, { "epoch": 7.81, "learning_rate": 0.0006623413796393474, "loss": 1.754, "step": 37695 }, { "epoch": 7.81, "learning_rate": 0.0006622459688960977, "loss": 1.7488, "step": 37700 }, { "epoch": 7.81, "learning_rate": 0.000662150558152848, "loss": 1.7548, "step": 37705 }, { "epoch": 7.81, "learning_rate": 0.0006620551474095984, "loss": 1.7511, "step": 37710 }, { "epoch": 7.81, "learning_rate": 0.0006619597366663486, "loss": 1.7522, "step": 37715 }, { "epoch": 7.81, "learning_rate": 0.000661864325923099, "loss": 1.7516, "step": 37720 }, { "epoch": 7.82, "learning_rate": 0.0006617689151798493, "loss": 1.7588, "step": 37725 }, { "epoch": 7.82, "learning_rate": 0.0006616735044365996, "loss": 1.7503, "step": 37730 }, { "epoch": 7.82, "learning_rate": 0.0006615780936933499, "loss": 1.7519, "step": 37735 }, { "epoch": 7.82, "learning_rate": 0.0006614826829501001, "loss": 1.7544, "step": 37740 }, { "epoch": 7.82, "learning_rate": 0.0006613872722068504, "loss": 1.7532, "step": 37745 }, { "epoch": 7.82, "learning_rate": 0.0006612918614636008, "loss": 1.7564, "step": 37750 }, { "epoch": 7.82, "learning_rate": 0.0006611964507203512, "loss": 1.7518, "step": 37755 }, { "epoch": 7.82, "learning_rate": 0.0006611010399771015, "loss": 1.7497, "step": 37760 }, { "epoch": 7.82, "learning_rate": 0.0006610056292338518, "loss": 1.7555, "step": 37765 }, { "epoch": 7.82, "learning_rate": 0.000660910218490602, "loss": 1.7571, "step": 37770 }, { "epoch": 7.83, "learning_rate": 0.0006608148077473523, "loss": 1.7527, "step": 37775 }, { "epoch": 7.83, "learning_rate": 0.0006607193970041027, "loss": 1.7509, "step": 37780 }, { "epoch": 7.83, "learning_rate": 0.000660623986260853, "loss": 1.7492, "step": 37785 }, { "epoch": 7.83, "learning_rate": 0.0006605285755176033, "loss": 1.7604, "step": 37790 }, { "epoch": 7.83, "learning_rate": 0.0006604331647743535, "loss": 1.7532, "step": 37795 }, { "epoch": 7.83, "learning_rate": 0.0006603377540311039, "loss": 1.7533, "step": 37800 }, { "epoch": 7.83, "learning_rate": 0.0006602423432878542, "loss": 1.7594, "step": 37805 }, { "epoch": 7.83, "learning_rate": 0.0006601469325446046, "loss": 1.75, "step": 37810 }, { "epoch": 7.83, "learning_rate": 0.0006600515218013549, "loss": 1.7528, "step": 37815 }, { "epoch": 7.84, "learning_rate": 0.0006599561110581052, "loss": 1.7565, "step": 37820 }, { "epoch": 7.84, "learning_rate": 0.0006598607003148554, "loss": 1.7507, "step": 37825 }, { "epoch": 7.84, "learning_rate": 0.0006597652895716057, "loss": 1.7545, "step": 37830 }, { "epoch": 7.84, "learning_rate": 0.0006596698788283561, "loss": 1.7609, "step": 37835 }, { "epoch": 7.84, "learning_rate": 0.0006595744680851064, "loss": 1.7558, "step": 37840 }, { "epoch": 7.84, "learning_rate": 0.0006594790573418568, "loss": 1.7522, "step": 37845 }, { "epoch": 7.84, "learning_rate": 0.000659383646598607, "loss": 1.7543, "step": 37850 }, { "epoch": 7.84, "learning_rate": 0.0006592882358553573, "loss": 1.7535, "step": 37855 }, { "epoch": 7.84, "learning_rate": 0.0006591928251121076, "loss": 1.7555, "step": 37860 }, { "epoch": 7.84, "learning_rate": 0.000659097414368858, "loss": 1.7562, "step": 37865 }, { "epoch": 7.85, "learning_rate": 0.0006590020036256083, "loss": 1.7571, "step": 37870 }, { "epoch": 7.85, "learning_rate": 0.0006589065928823586, "loss": 1.7526, "step": 37875 }, { "epoch": 7.85, "learning_rate": 0.0006588111821391088, "loss": 1.7555, "step": 37880 }, { "epoch": 7.85, "learning_rate": 0.0006587157713958591, "loss": 1.7534, "step": 37885 }, { "epoch": 7.85, "learning_rate": 0.0006586203606526095, "loss": 1.7541, "step": 37890 }, { "epoch": 7.85, "learning_rate": 0.0006585249499093599, "loss": 1.7546, "step": 37895 }, { "epoch": 7.85, "learning_rate": 0.0006584295391661102, "loss": 1.7492, "step": 37900 }, { "epoch": 7.85, "learning_rate": 0.0006583341284228605, "loss": 1.7546, "step": 37905 }, { "epoch": 7.85, "learning_rate": 0.0006582387176796107, "loss": 1.7551, "step": 37910 }, { "epoch": 7.85, "learning_rate": 0.000658143306936361, "loss": 1.7557, "step": 37915 }, { "epoch": 7.86, "learning_rate": 0.0006580478961931113, "loss": 1.752, "step": 37920 }, { "epoch": 7.86, "learning_rate": 0.0006579524854498617, "loss": 1.7553, "step": 37925 }, { "epoch": 7.86, "learning_rate": 0.000657857074706612, "loss": 1.7547, "step": 37930 }, { "epoch": 7.86, "learning_rate": 0.0006577616639633622, "loss": 1.7543, "step": 37935 }, { "epoch": 7.86, "learning_rate": 0.0006576662532201126, "loss": 1.7545, "step": 37940 }, { "epoch": 7.86, "learning_rate": 0.0006575708424768629, "loss": 1.7538, "step": 37945 }, { "epoch": 7.86, "learning_rate": 0.0006574754317336132, "loss": 1.7493, "step": 37950 }, { "epoch": 7.86, "learning_rate": 0.0006573800209903636, "loss": 1.7566, "step": 37955 }, { "epoch": 7.86, "learning_rate": 0.0006572846102471139, "loss": 1.7579, "step": 37960 }, { "epoch": 7.87, "learning_rate": 0.0006571891995038641, "loss": 1.7517, "step": 37965 }, { "epoch": 7.87, "learning_rate": 0.0006570937887606144, "loss": 1.7538, "step": 37970 }, { "epoch": 7.87, "learning_rate": 0.0006569983780173647, "loss": 1.7538, "step": 37975 }, { "epoch": 7.87, "learning_rate": 0.000656902967274115, "loss": 1.756, "step": 37980 }, { "epoch": 7.87, "learning_rate": 0.0006568075565308655, "loss": 1.7539, "step": 37985 }, { "epoch": 7.87, "learning_rate": 0.0006567121457876158, "loss": 1.7529, "step": 37990 }, { "epoch": 7.87, "learning_rate": 0.000656616735044366, "loss": 1.756, "step": 37995 }, { "epoch": 7.87, "learning_rate": 0.0006565213243011163, "loss": 1.7569, "step": 38000 }, { "epoch": 7.87, "learning_rate": 0.0006564259135578666, "loss": 1.7549, "step": 38005 }, { "epoch": 7.87, "learning_rate": 0.0006563305028146169, "loss": 1.7497, "step": 38010 }, { "epoch": 7.88, "learning_rate": 0.0006562350920713673, "loss": 1.7563, "step": 38015 }, { "epoch": 7.88, "learning_rate": 0.0006561396813281175, "loss": 1.7565, "step": 38020 }, { "epoch": 7.88, "learning_rate": 0.0006560442705848678, "loss": 1.7544, "step": 38025 }, { "epoch": 7.88, "learning_rate": 0.0006559488598416182, "loss": 1.7567, "step": 38030 }, { "epoch": 7.88, "learning_rate": 0.0006558534490983685, "loss": 1.7551, "step": 38035 }, { "epoch": 7.88, "learning_rate": 0.0006557580383551189, "loss": 1.7509, "step": 38040 }, { "epoch": 7.88, "learning_rate": 0.0006556626276118692, "loss": 1.7498, "step": 38045 }, { "epoch": 7.88, "learning_rate": 0.0006555672168686194, "loss": 1.7573, "step": 38050 }, { "epoch": 7.88, "learning_rate": 0.0006554718061253697, "loss": 1.7537, "step": 38055 }, { "epoch": 7.88, "learning_rate": 0.00065537639538212, "loss": 1.7546, "step": 38060 }, { "epoch": 7.89, "learning_rate": 0.0006552809846388703, "loss": 1.7565, "step": 38065 }, { "epoch": 7.89, "learning_rate": 0.0006551855738956207, "loss": 1.7539, "step": 38070 }, { "epoch": 7.89, "learning_rate": 0.000655090163152371, "loss": 1.7561, "step": 38075 }, { "epoch": 7.89, "learning_rate": 0.0006549947524091213, "loss": 1.7507, "step": 38080 }, { "epoch": 7.89, "learning_rate": 0.0006548993416658716, "loss": 1.7527, "step": 38085 }, { "epoch": 7.89, "learning_rate": 0.0006548039309226219, "loss": 1.7498, "step": 38090 }, { "epoch": 7.89, "learning_rate": 0.0006547085201793722, "loss": 1.7554, "step": 38095 }, { "epoch": 7.89, "learning_rate": 0.0006546131094361226, "loss": 1.7522, "step": 38100 }, { "epoch": 7.89, "learning_rate": 0.0006545176986928728, "loss": 1.756, "step": 38105 }, { "epoch": 7.9, "learning_rate": 0.0006544222879496231, "loss": 1.7533, "step": 38110 }, { "epoch": 7.9, "learning_rate": 0.0006543268772063734, "loss": 1.7559, "step": 38115 }, { "epoch": 7.9, "learning_rate": 0.0006542314664631238, "loss": 1.7512, "step": 38120 }, { "epoch": 7.9, "learning_rate": 0.0006541360557198741, "loss": 1.752, "step": 38125 }, { "epoch": 7.9, "learning_rate": 0.0006540406449766245, "loss": 1.7545, "step": 38130 }, { "epoch": 7.9, "learning_rate": 0.0006539452342333747, "loss": 1.7528, "step": 38135 }, { "epoch": 7.9, "learning_rate": 0.000653849823490125, "loss": 1.7541, "step": 38140 }, { "epoch": 7.9, "learning_rate": 0.0006537544127468753, "loss": 1.7583, "step": 38145 }, { "epoch": 7.9, "learning_rate": 0.0006536590020036256, "loss": 1.7556, "step": 38150 }, { "epoch": 7.9, "learning_rate": 0.0006535635912603759, "loss": 1.7539, "step": 38155 }, { "epoch": 7.91, "learning_rate": 0.0006534681805171262, "loss": 1.7557, "step": 38160 }, { "epoch": 7.91, "learning_rate": 0.0006533727697738766, "loss": 1.7559, "step": 38165 }, { "epoch": 7.91, "learning_rate": 0.0006532773590306269, "loss": 1.7541, "step": 38170 }, { "epoch": 7.91, "learning_rate": 0.0006531819482873772, "loss": 1.755, "step": 38175 }, { "epoch": 7.91, "learning_rate": 0.0006530865375441275, "loss": 1.7508, "step": 38180 }, { "epoch": 7.91, "learning_rate": 0.0006529911268008778, "loss": 1.754, "step": 38185 }, { "epoch": 7.91, "learning_rate": 0.0006528957160576281, "loss": 1.749, "step": 38190 }, { "epoch": 7.91, "learning_rate": 0.0006528003053143784, "loss": 1.7578, "step": 38195 }, { "epoch": 7.91, "learning_rate": 0.0006527048945711287, "loss": 1.752, "step": 38200 }, { "epoch": 7.91, "learning_rate": 0.000652609483827879, "loss": 1.7552, "step": 38205 }, { "epoch": 7.92, "learning_rate": 0.0006525140730846293, "loss": 1.7566, "step": 38210 }, { "epoch": 7.92, "learning_rate": 0.0006524186623413796, "loss": 1.7523, "step": 38215 }, { "epoch": 7.92, "learning_rate": 0.00065232325159813, "loss": 1.7583, "step": 38220 }, { "epoch": 7.92, "learning_rate": 0.0006522278408548803, "loss": 1.7594, "step": 38225 }, { "epoch": 7.92, "learning_rate": 0.0006521324301116306, "loss": 1.7471, "step": 38230 }, { "epoch": 7.92, "learning_rate": 0.0006520370193683809, "loss": 1.754, "step": 38235 }, { "epoch": 7.92, "learning_rate": 0.0006519416086251312, "loss": 1.7537, "step": 38240 }, { "epoch": 7.92, "learning_rate": 0.0006518461978818814, "loss": 1.755, "step": 38245 }, { "epoch": 7.92, "learning_rate": 0.0006517507871386318, "loss": 1.7505, "step": 38250 }, { "epoch": 7.93, "learning_rate": 0.0006516553763953821, "loss": 1.7512, "step": 38255 }, { "epoch": 7.93, "learning_rate": 0.0006515599656521325, "loss": 1.7511, "step": 38260 }, { "epoch": 7.93, "learning_rate": 0.0006514645549088828, "loss": 1.7538, "step": 38265 }, { "epoch": 7.93, "learning_rate": 0.000651369144165633, "loss": 1.7551, "step": 38270 }, { "epoch": 7.93, "learning_rate": 0.0006512737334223834, "loss": 1.7473, "step": 38275 }, { "epoch": 7.93, "learning_rate": 0.0006511783226791337, "loss": 1.7539, "step": 38280 }, { "epoch": 7.93, "learning_rate": 0.000651082911935884, "loss": 1.7544, "step": 38285 }, { "epoch": 7.93, "learning_rate": 0.0006509875011926343, "loss": 1.7482, "step": 38290 }, { "epoch": 7.93, "learning_rate": 0.0006508920904493846, "loss": 1.7517, "step": 38295 }, { "epoch": 7.93, "learning_rate": 0.0006507966797061348, "loss": 1.754, "step": 38300 }, { "epoch": 7.94, "learning_rate": 0.0006507012689628853, "loss": 1.7511, "step": 38305 }, { "epoch": 7.94, "learning_rate": 0.0006506058582196356, "loss": 1.7586, "step": 38310 }, { "epoch": 7.94, "learning_rate": 0.0006505104474763859, "loss": 1.7523, "step": 38315 }, { "epoch": 7.94, "learning_rate": 0.0006504150367331362, "loss": 1.7581, "step": 38320 }, { "epoch": 7.94, "learning_rate": 0.0006503196259898865, "loss": 1.7517, "step": 38325 }, { "epoch": 7.94, "learning_rate": 0.0006502242152466367, "loss": 1.756, "step": 38330 }, { "epoch": 7.94, "learning_rate": 0.0006501288045033871, "loss": 1.7531, "step": 38335 }, { "epoch": 7.94, "learning_rate": 0.0006500333937601374, "loss": 1.7498, "step": 38340 }, { "epoch": 7.94, "learning_rate": 0.0006499379830168877, "loss": 1.7567, "step": 38345 }, { "epoch": 7.94, "learning_rate": 0.0006498425722736381, "loss": 1.7567, "step": 38350 }, { "epoch": 7.95, "learning_rate": 0.0006497471615303883, "loss": 1.7475, "step": 38355 }, { "epoch": 7.95, "learning_rate": 0.0006496517507871386, "loss": 1.7564, "step": 38360 }, { "epoch": 7.95, "learning_rate": 0.000649556340043889, "loss": 1.7517, "step": 38365 }, { "epoch": 7.95, "learning_rate": 0.0006494609293006393, "loss": 1.7576, "step": 38370 }, { "epoch": 7.95, "learning_rate": 0.0006493655185573896, "loss": 1.755, "step": 38375 }, { "epoch": 7.95, "learning_rate": 0.0006492701078141399, "loss": 1.7439, "step": 38380 }, { "epoch": 7.95, "learning_rate": 0.0006491746970708901, "loss": 1.7508, "step": 38385 }, { "epoch": 7.95, "learning_rate": 0.0006490792863276404, "loss": 1.7509, "step": 38390 }, { "epoch": 7.95, "learning_rate": 0.0006489838755843909, "loss": 1.7511, "step": 38395 }, { "epoch": 7.96, "learning_rate": 0.0006488884648411412, "loss": 1.7502, "step": 38400 }, { "epoch": 7.96, "learning_rate": 0.0006487930540978915, "loss": 1.7552, "step": 38405 }, { "epoch": 7.96, "learning_rate": 0.0006486976433546418, "loss": 1.7512, "step": 38410 }, { "epoch": 7.96, "learning_rate": 0.000648602232611392, "loss": 1.7538, "step": 38415 }, { "epoch": 7.96, "learning_rate": 0.0006485068218681423, "loss": 1.7567, "step": 38420 }, { "epoch": 7.96, "learning_rate": 0.0006484114111248927, "loss": 1.7495, "step": 38425 }, { "epoch": 7.96, "learning_rate": 0.000648316000381643, "loss": 1.7572, "step": 38430 }, { "epoch": 7.96, "learning_rate": 0.0006482205896383933, "loss": 1.7584, "step": 38435 }, { "epoch": 7.96, "learning_rate": 0.0006481251788951435, "loss": 1.7544, "step": 38440 }, { "epoch": 7.96, "learning_rate": 0.0006480297681518939, "loss": 1.7538, "step": 38445 }, { "epoch": 7.97, "learning_rate": 0.0006479343574086443, "loss": 1.7525, "step": 38450 }, { "epoch": 7.97, "learning_rate": 0.0006478389466653946, "loss": 1.7515, "step": 38455 }, { "epoch": 7.97, "learning_rate": 0.0006477435359221449, "loss": 1.7579, "step": 38460 }, { "epoch": 7.97, "learning_rate": 0.0006476481251788952, "loss": 1.7572, "step": 38465 }, { "epoch": 7.97, "learning_rate": 0.0006475527144356454, "loss": 1.7546, "step": 38470 }, { "epoch": 7.97, "learning_rate": 0.0006474573036923957, "loss": 1.7565, "step": 38475 }, { "epoch": 7.97, "learning_rate": 0.0006473618929491461, "loss": 1.752, "step": 38480 }, { "epoch": 7.97, "learning_rate": 0.0006472664822058964, "loss": 1.7585, "step": 38485 }, { "epoch": 7.97, "learning_rate": 0.0006471710714626468, "loss": 1.7531, "step": 38490 }, { "epoch": 7.97, "learning_rate": 0.000647075660719397, "loss": 1.7489, "step": 38495 }, { "epoch": 7.98, "learning_rate": 0.0006469802499761473, "loss": 1.7548, "step": 38500 }, { "epoch": 7.98, "learning_rate": 0.0006468848392328976, "loss": 1.7485, "step": 38505 }, { "epoch": 7.98, "learning_rate": 0.000646789428489648, "loss": 1.7509, "step": 38510 }, { "epoch": 7.98, "learning_rate": 0.0006466940177463983, "loss": 1.751, "step": 38515 }, { "epoch": 7.98, "learning_rate": 0.0006465986070031486, "loss": 1.7543, "step": 38520 }, { "epoch": 7.98, "learning_rate": 0.0006465031962598988, "loss": 1.7589, "step": 38525 }, { "epoch": 7.98, "learning_rate": 0.0006464077855166491, "loss": 1.753, "step": 38530 }, { "epoch": 7.98, "learning_rate": 0.0006463123747733995, "loss": 1.7515, "step": 38535 }, { "epoch": 7.98, "learning_rate": 0.0006462169640301499, "loss": 1.7511, "step": 38540 }, { "epoch": 7.99, "learning_rate": 0.0006461215532869002, "loss": 1.7521, "step": 38545 }, { "epoch": 7.99, "learning_rate": 0.0006460261425436505, "loss": 1.7503, "step": 38550 }, { "epoch": 7.99, "learning_rate": 0.0006459307318004007, "loss": 1.7538, "step": 38555 }, { "epoch": 7.99, "learning_rate": 0.000645835321057151, "loss": 1.7507, "step": 38560 }, { "epoch": 7.99, "learning_rate": 0.0006457399103139013, "loss": 1.7549, "step": 38565 }, { "epoch": 7.99, "learning_rate": 0.0006456444995706517, "loss": 1.7527, "step": 38570 }, { "epoch": 7.99, "learning_rate": 0.000645549088827402, "loss": 1.7494, "step": 38575 }, { "epoch": 7.99, "learning_rate": 0.0006454536780841523, "loss": 1.7458, "step": 38580 }, { "epoch": 7.99, "learning_rate": 0.0006453582673409026, "loss": 1.7522, "step": 38585 }, { "epoch": 7.99, "learning_rate": 0.0006452628565976529, "loss": 1.7502, "step": 38590 }, { "epoch": 8.0, "learning_rate": 0.0006451674458544032, "loss": 1.7566, "step": 38595 }, { "epoch": 8.0, "learning_rate": 0.0006450720351111536, "loss": 1.7564, "step": 38600 }, { "epoch": 8.0, "learning_rate": 0.0006449766243679039, "loss": 1.7565, "step": 38605 }, { "epoch": 8.0, "learning_rate": 0.0006448812136246541, "loss": 1.7509, "step": 38610 }, { "epoch": 8.0, "learning_rate": 0.0006447858028814044, "loss": 1.7566, "step": 38615 }, { "epoch": 8.0, "learning_rate": 0.0006446903921381547, "loss": 1.7469, "step": 38620 }, { "epoch": 8.0, "learning_rate": 0.0006445949813949051, "loss": 1.746, "step": 38625 }, { "epoch": 8.0, "learning_rate": 0.0006444995706516555, "loss": 1.7438, "step": 38630 }, { "epoch": 8.0, "learning_rate": 0.0006444041599084057, "loss": 1.74, "step": 38635 }, { "epoch": 8.0, "learning_rate": 0.000644308749165156, "loss": 1.7438, "step": 38640 }, { "epoch": 8.01, "learning_rate": 0.0006442133384219063, "loss": 1.7424, "step": 38645 }, { "epoch": 8.01, "learning_rate": 0.0006441179276786566, "loss": 1.7422, "step": 38650 }, { "epoch": 8.01, "learning_rate": 0.0006440225169354069, "loss": 1.7417, "step": 38655 }, { "epoch": 8.01, "learning_rate": 0.0006439271061921573, "loss": 1.7438, "step": 38660 }, { "epoch": 8.01, "learning_rate": 0.0006438316954489075, "loss": 1.7497, "step": 38665 }, { "epoch": 8.01, "learning_rate": 0.0006437362847056578, "loss": 1.743, "step": 38670 }, { "epoch": 8.01, "learning_rate": 0.0006436408739624082, "loss": 1.7458, "step": 38675 }, { "epoch": 8.01, "learning_rate": 0.0006435454632191585, "loss": 1.7436, "step": 38680 }, { "epoch": 8.01, "learning_rate": 0.0006434500524759089, "loss": 1.742, "step": 38685 }, { "epoch": 8.02, "learning_rate": 0.0006433546417326592, "loss": 1.7362, "step": 38690 }, { "epoch": 8.02, "learning_rate": 0.0006432592309894094, "loss": 1.7438, "step": 38695 }, { "epoch": 8.02, "learning_rate": 0.0006431638202461597, "loss": 1.7444, "step": 38700 }, { "epoch": 8.02, "learning_rate": 0.00064306840950291, "loss": 1.7424, "step": 38705 }, { "epoch": 8.02, "learning_rate": 0.0006429729987596603, "loss": 1.7468, "step": 38710 }, { "epoch": 8.02, "learning_rate": 0.0006428775880164107, "loss": 1.7432, "step": 38715 }, { "epoch": 8.02, "learning_rate": 0.000642782177273161, "loss": 1.7378, "step": 38720 }, { "epoch": 8.02, "learning_rate": 0.0006426867665299113, "loss": 1.7426, "step": 38725 }, { "epoch": 8.02, "learning_rate": 0.0006425913557866616, "loss": 1.7445, "step": 38730 }, { "epoch": 8.02, "learning_rate": 0.0006424959450434119, "loss": 1.7443, "step": 38735 }, { "epoch": 8.03, "learning_rate": 0.0006424005343001622, "loss": 1.7405, "step": 38740 }, { "epoch": 8.03, "learning_rate": 0.0006423051235569126, "loss": 1.7445, "step": 38745 }, { "epoch": 8.03, "learning_rate": 0.0006422097128136628, "loss": 1.7473, "step": 38750 }, { "epoch": 8.03, "learning_rate": 0.0006421143020704131, "loss": 1.7462, "step": 38755 }, { "epoch": 8.03, "learning_rate": 0.0006420188913271634, "loss": 1.7442, "step": 38760 }, { "epoch": 8.03, "learning_rate": 0.0006419234805839138, "loss": 1.745, "step": 38765 }, { "epoch": 8.03, "learning_rate": 0.0006418280698406641, "loss": 1.7458, "step": 38770 }, { "epoch": 8.03, "learning_rate": 0.0006417326590974145, "loss": 1.7451, "step": 38775 }, { "epoch": 8.03, "learning_rate": 0.0006416372483541647, "loss": 1.7475, "step": 38780 }, { "epoch": 8.04, "learning_rate": 0.000641541837610915, "loss": 1.7441, "step": 38785 }, { "epoch": 8.04, "learning_rate": 0.0006414464268676653, "loss": 1.7475, "step": 38790 }, { "epoch": 8.04, "learning_rate": 0.0006413510161244156, "loss": 1.7485, "step": 38795 }, { "epoch": 8.04, "learning_rate": 0.0006412556053811658, "loss": 1.7443, "step": 38800 }, { "epoch": 8.04, "learning_rate": 0.0006411601946379162, "loss": 1.7398, "step": 38805 }, { "epoch": 8.04, "learning_rate": 0.0006410647838946666, "loss": 1.7428, "step": 38810 }, { "epoch": 8.04, "learning_rate": 0.0006409693731514169, "loss": 1.7447, "step": 38815 }, { "epoch": 8.04, "learning_rate": 0.0006408739624081672, "loss": 1.7417, "step": 38820 }, { "epoch": 8.04, "learning_rate": 0.0006407785516649175, "loss": 1.7403, "step": 38825 }, { "epoch": 8.04, "learning_rate": 0.0006406831409216677, "loss": 1.7425, "step": 38830 }, { "epoch": 8.05, "learning_rate": 0.0006405877301784181, "loss": 1.7456, "step": 38835 }, { "epoch": 8.05, "learning_rate": 0.0006404923194351684, "loss": 1.7403, "step": 38840 }, { "epoch": 8.05, "learning_rate": 0.0006403969086919187, "loss": 1.7393, "step": 38845 }, { "epoch": 8.05, "learning_rate": 0.000640301497948669, "loss": 1.747, "step": 38850 }, { "epoch": 8.05, "learning_rate": 0.0006402060872054194, "loss": 1.7447, "step": 38855 }, { "epoch": 8.05, "learning_rate": 0.0006401106764621696, "loss": 1.7394, "step": 38860 }, { "epoch": 8.05, "learning_rate": 0.00064001526571892, "loss": 1.7488, "step": 38865 }, { "epoch": 8.05, "learning_rate": 0.0006399198549756703, "loss": 1.7465, "step": 38870 }, { "epoch": 8.05, "learning_rate": 0.0006398244442324206, "loss": 1.7428, "step": 38875 }, { "epoch": 8.05, "learning_rate": 0.0006397290334891709, "loss": 1.7413, "step": 38880 }, { "epoch": 8.06, "learning_rate": 0.0006396336227459211, "loss": 1.7411, "step": 38885 }, { "epoch": 8.06, "learning_rate": 0.0006395382120026714, "loss": 1.743, "step": 38890 }, { "epoch": 8.06, "learning_rate": 0.0006394428012594218, "loss": 1.7417, "step": 38895 }, { "epoch": 8.06, "learning_rate": 0.0006393473905161722, "loss": 1.7447, "step": 38900 }, { "epoch": 8.06, "learning_rate": 0.0006392519797729225, "loss": 1.7449, "step": 38905 }, { "epoch": 8.06, "learning_rate": 0.0006391565690296728, "loss": 1.7449, "step": 38910 }, { "epoch": 8.06, "learning_rate": 0.000639061158286423, "loss": 1.7453, "step": 38915 }, { "epoch": 8.06, "learning_rate": 0.0006389657475431734, "loss": 1.7494, "step": 38920 }, { "epoch": 8.06, "learning_rate": 0.0006388703367999237, "loss": 1.7475, "step": 38925 }, { "epoch": 8.07, "learning_rate": 0.000638774926056674, "loss": 1.7455, "step": 38930 }, { "epoch": 8.07, "learning_rate": 0.0006386795153134243, "loss": 1.7408, "step": 38935 }, { "epoch": 8.07, "learning_rate": 0.0006385841045701746, "loss": 1.7417, "step": 38940 }, { "epoch": 8.07, "learning_rate": 0.0006384886938269248, "loss": 1.7444, "step": 38945 }, { "epoch": 8.07, "learning_rate": 0.0006383932830836753, "loss": 1.7401, "step": 38950 }, { "epoch": 8.07, "learning_rate": 0.0006382978723404256, "loss": 1.7457, "step": 38955 }, { "epoch": 8.07, "learning_rate": 0.0006382024615971759, "loss": 1.747, "step": 38960 }, { "epoch": 8.07, "learning_rate": 0.0006381070508539262, "loss": 1.7448, "step": 38965 }, { "epoch": 8.07, "learning_rate": 0.0006380116401106764, "loss": 1.7434, "step": 38970 }, { "epoch": 8.07, "learning_rate": 0.0006379162293674267, "loss": 1.7464, "step": 38975 }, { "epoch": 8.08, "learning_rate": 0.0006378208186241771, "loss": 1.7431, "step": 38980 }, { "epoch": 8.08, "learning_rate": 0.0006377254078809274, "loss": 1.7418, "step": 38985 }, { "epoch": 8.08, "learning_rate": 0.0006376299971376777, "loss": 1.745, "step": 38990 }, { "epoch": 8.08, "learning_rate": 0.0006375345863944281, "loss": 1.7458, "step": 38995 }, { "epoch": 8.08, "learning_rate": 0.0006374391756511783, "loss": 1.7482, "step": 39000 }, { "epoch": 8.08, "eval_accuracy": 0.5412287581699347, "eval_loss": 1.930657148361206, "eval_runtime": 0.9787, "eval_samples_per_second": 153.268, "eval_steps_per_second": 1.022, "step": 39000 }, { "epoch": 8.08, "learning_rate": 0.0006373437649079286, "loss": 1.7462, "step": 39005 }, { "epoch": 8.08, "learning_rate": 0.000637248354164679, "loss": 1.7453, "step": 39010 }, { "epoch": 8.08, "learning_rate": 0.0006371529434214293, "loss": 1.7438, "step": 39015 }, { "epoch": 8.08, "learning_rate": 0.0006370575326781796, "loss": 1.7424, "step": 39020 }, { "epoch": 8.08, "learning_rate": 0.0006369621219349298, "loss": 1.7457, "step": 39025 }, { "epoch": 8.09, "learning_rate": 0.0006368667111916801, "loss": 1.7424, "step": 39030 }, { "epoch": 8.09, "learning_rate": 0.0006367713004484304, "loss": 1.7421, "step": 39035 }, { "epoch": 8.09, "learning_rate": 0.0006366758897051809, "loss": 1.7473, "step": 39040 }, { "epoch": 8.09, "learning_rate": 0.0006365804789619312, "loss": 1.7444, "step": 39045 }, { "epoch": 8.09, "learning_rate": 0.0006364850682186815, "loss": 1.7446, "step": 39050 }, { "epoch": 8.09, "learning_rate": 0.0006363896574754317, "loss": 1.7464, "step": 39055 }, { "epoch": 8.09, "learning_rate": 0.000636294246732182, "loss": 1.7409, "step": 39060 }, { "epoch": 8.09, "learning_rate": 0.0006361988359889323, "loss": 1.7467, "step": 39065 }, { "epoch": 8.09, "learning_rate": 0.0006361034252456827, "loss": 1.7423, "step": 39070 }, { "epoch": 8.1, "learning_rate": 0.000636008014502433, "loss": 1.7429, "step": 39075 }, { "epoch": 8.1, "learning_rate": 0.0006359126037591833, "loss": 1.745, "step": 39080 }, { "epoch": 8.1, "learning_rate": 0.0006358171930159336, "loss": 1.7471, "step": 39085 }, { "epoch": 8.1, "learning_rate": 0.0006357217822726839, "loss": 1.7452, "step": 39090 }, { "epoch": 8.1, "learning_rate": 0.0006356263715294343, "loss": 1.743, "step": 39095 }, { "epoch": 8.1, "learning_rate": 0.0006355309607861846, "loss": 1.7479, "step": 39100 }, { "epoch": 8.1, "learning_rate": 0.0006354355500429349, "loss": 1.7483, "step": 39105 }, { "epoch": 8.1, "learning_rate": 0.0006353401392996851, "loss": 1.7445, "step": 39110 }, { "epoch": 8.1, "learning_rate": 0.0006352447285564354, "loss": 1.7494, "step": 39115 }, { "epoch": 8.1, "learning_rate": 0.0006351493178131857, "loss": 1.7491, "step": 39120 }, { "epoch": 8.11, "learning_rate": 0.0006350539070699361, "loss": 1.7445, "step": 39125 }, { "epoch": 8.11, "learning_rate": 0.0006349584963266865, "loss": 1.7476, "step": 39130 }, { "epoch": 8.11, "learning_rate": 0.0006348630855834368, "loss": 1.744, "step": 39135 }, { "epoch": 8.11, "learning_rate": 0.000634767674840187, "loss": 1.7425, "step": 39140 }, { "epoch": 8.11, "learning_rate": 0.0006346722640969373, "loss": 1.7421, "step": 39145 }, { "epoch": 8.11, "learning_rate": 0.0006345768533536876, "loss": 1.7462, "step": 39150 }, { "epoch": 8.11, "learning_rate": 0.000634481442610438, "loss": 1.7472, "step": 39155 }, { "epoch": 8.11, "learning_rate": 0.0006343860318671883, "loss": 1.7421, "step": 39160 }, { "epoch": 8.11, "learning_rate": 0.0006342906211239386, "loss": 1.7486, "step": 39165 }, { "epoch": 8.11, "learning_rate": 0.0006341952103806888, "loss": 1.7505, "step": 39170 }, { "epoch": 8.12, "learning_rate": 0.0006340997996374391, "loss": 1.7441, "step": 39175 }, { "epoch": 8.12, "learning_rate": 0.0006340043888941895, "loss": 1.7436, "step": 39180 }, { "epoch": 8.12, "learning_rate": 0.0006339089781509399, "loss": 1.7484, "step": 39185 }, { "epoch": 8.12, "learning_rate": 0.0006338135674076902, "loss": 1.7456, "step": 39190 }, { "epoch": 8.12, "learning_rate": 0.0006337181566644404, "loss": 1.7487, "step": 39195 }, { "epoch": 8.12, "learning_rate": 0.0006336227459211907, "loss": 1.7439, "step": 39200 }, { "epoch": 8.12, "learning_rate": 0.000633527335177941, "loss": 1.7443, "step": 39205 }, { "epoch": 8.12, "learning_rate": 0.0006334319244346913, "loss": 1.7482, "step": 39210 }, { "epoch": 8.12, "learning_rate": 0.0006333365136914417, "loss": 1.7429, "step": 39215 }, { "epoch": 8.13, "learning_rate": 0.000633241102948192, "loss": 1.7452, "step": 39220 }, { "epoch": 8.13, "learning_rate": 0.0006331456922049423, "loss": 1.7458, "step": 39225 }, { "epoch": 8.13, "learning_rate": 0.0006330502814616926, "loss": 1.7427, "step": 39230 }, { "epoch": 8.13, "learning_rate": 0.0006329548707184429, "loss": 1.7447, "step": 39235 }, { "epoch": 8.13, "learning_rate": 0.0006328594599751932, "loss": 1.743, "step": 39240 }, { "epoch": 8.13, "learning_rate": 0.0006327640492319436, "loss": 1.7442, "step": 39245 }, { "epoch": 8.13, "learning_rate": 0.0006326686384886938, "loss": 1.7493, "step": 39250 }, { "epoch": 8.13, "learning_rate": 0.0006325732277454441, "loss": 1.7435, "step": 39255 }, { "epoch": 8.13, "learning_rate": 0.0006324778170021944, "loss": 1.7424, "step": 39260 }, { "epoch": 8.13, "learning_rate": 0.0006323824062589447, "loss": 1.7461, "step": 39265 }, { "epoch": 8.14, "learning_rate": 0.0006322869955156951, "loss": 1.7478, "step": 39270 }, { "epoch": 8.14, "learning_rate": 0.0006321915847724455, "loss": 1.7468, "step": 39275 }, { "epoch": 8.14, "learning_rate": 0.0006320961740291957, "loss": 1.745, "step": 39280 }, { "epoch": 8.14, "learning_rate": 0.000632000763285946, "loss": 1.7458, "step": 39285 }, { "epoch": 8.14, "learning_rate": 0.0006319053525426963, "loss": 1.7445, "step": 39290 }, { "epoch": 8.14, "learning_rate": 0.0006318099417994466, "loss": 1.7454, "step": 39295 }, { "epoch": 8.14, "learning_rate": 0.0006317145310561969, "loss": 1.7462, "step": 39300 }, { "epoch": 8.14, "learning_rate": 0.0006316191203129473, "loss": 1.7457, "step": 39305 }, { "epoch": 8.14, "learning_rate": 0.0006315237095696975, "loss": 1.7434, "step": 39310 }, { "epoch": 8.14, "learning_rate": 0.0006314282988264479, "loss": 1.7432, "step": 39315 }, { "epoch": 8.15, "learning_rate": 0.0006313328880831982, "loss": 1.7436, "step": 39320 }, { "epoch": 8.15, "learning_rate": 0.0006312374773399485, "loss": 1.7465, "step": 39325 }, { "epoch": 8.15, "learning_rate": 0.0006311420665966989, "loss": 1.7422, "step": 39330 }, { "epoch": 8.15, "learning_rate": 0.0006310466558534491, "loss": 1.7471, "step": 39335 }, { "epoch": 8.15, "learning_rate": 0.0006309512451101994, "loss": 1.7405, "step": 39340 }, { "epoch": 8.15, "learning_rate": 0.0006308558343669497, "loss": 1.7437, "step": 39345 }, { "epoch": 8.15, "learning_rate": 0.0006307604236237, "loss": 1.7485, "step": 39350 }, { "epoch": 8.15, "learning_rate": 0.0006306650128804503, "loss": 1.7466, "step": 39355 }, { "epoch": 8.15, "learning_rate": 0.0006305696021372008, "loss": 1.7448, "step": 39360 }, { "epoch": 8.16, "learning_rate": 0.000630474191393951, "loss": 1.7434, "step": 39365 }, { "epoch": 8.16, "learning_rate": 0.0006303787806507013, "loss": 1.7441, "step": 39370 }, { "epoch": 8.16, "learning_rate": 0.0006302833699074516, "loss": 1.7417, "step": 39375 }, { "epoch": 8.16, "learning_rate": 0.0006301879591642019, "loss": 1.7428, "step": 39380 }, { "epoch": 8.16, "learning_rate": 0.0006300925484209522, "loss": 1.7517, "step": 39385 }, { "epoch": 8.16, "learning_rate": 0.0006299971376777026, "loss": 1.7416, "step": 39390 }, { "epoch": 8.16, "learning_rate": 0.0006299017269344528, "loss": 1.7449, "step": 39395 }, { "epoch": 8.16, "learning_rate": 0.0006298063161912031, "loss": 1.7447, "step": 39400 }, { "epoch": 8.16, "learning_rate": 0.0006297109054479534, "loss": 1.7448, "step": 39405 }, { "epoch": 8.16, "learning_rate": 0.0006296154947047038, "loss": 1.7455, "step": 39410 }, { "epoch": 8.17, "learning_rate": 0.0006295200839614541, "loss": 1.7469, "step": 39415 }, { "epoch": 8.17, "learning_rate": 0.0006294246732182044, "loss": 1.7418, "step": 39420 }, { "epoch": 8.17, "learning_rate": 0.0006293292624749547, "loss": 1.7505, "step": 39425 }, { "epoch": 8.17, "learning_rate": 0.000629233851731705, "loss": 1.7464, "step": 39430 }, { "epoch": 8.17, "learning_rate": 0.0006291384409884553, "loss": 1.7465, "step": 39435 }, { "epoch": 8.17, "learning_rate": 0.0006290430302452056, "loss": 1.7473, "step": 39440 }, { "epoch": 8.17, "learning_rate": 0.0006289476195019558, "loss": 1.7449, "step": 39445 }, { "epoch": 8.17, "learning_rate": 0.0006288522087587062, "loss": 1.748, "step": 39450 }, { "epoch": 8.17, "learning_rate": 0.0006287567980154566, "loss": 1.7477, "step": 39455 }, { "epoch": 8.17, "learning_rate": 0.0006286613872722069, "loss": 1.7462, "step": 39460 }, { "epoch": 8.18, "learning_rate": 0.0006285659765289572, "loss": 1.745, "step": 39465 }, { "epoch": 8.18, "learning_rate": 0.0006284705657857075, "loss": 1.7486, "step": 39470 }, { "epoch": 8.18, "learning_rate": 0.0006283751550424577, "loss": 1.7458, "step": 39475 }, { "epoch": 8.18, "learning_rate": 0.0006282797442992081, "loss": 1.7474, "step": 39480 }, { "epoch": 8.18, "learning_rate": 0.0006281843335559584, "loss": 1.7389, "step": 39485 }, { "epoch": 8.18, "learning_rate": 0.0006280889228127087, "loss": 1.7466, "step": 39490 }, { "epoch": 8.18, "learning_rate": 0.000627993512069459, "loss": 1.744, "step": 39495 }, { "epoch": 8.18, "learning_rate": 0.0006278981013262094, "loss": 1.7442, "step": 39500 }, { "epoch": 8.18, "learning_rate": 0.0006278026905829596, "loss": 1.7451, "step": 39505 }, { "epoch": 8.19, "learning_rate": 0.00062770727983971, "loss": 1.7455, "step": 39510 }, { "epoch": 8.19, "learning_rate": 0.0006276118690964603, "loss": 1.7435, "step": 39515 }, { "epoch": 8.19, "learning_rate": 0.0006275164583532106, "loss": 1.7476, "step": 39520 }, { "epoch": 8.19, "learning_rate": 0.0006274210476099609, "loss": 1.7493, "step": 39525 }, { "epoch": 8.19, "learning_rate": 0.0006273256368667111, "loss": 1.749, "step": 39530 }, { "epoch": 8.19, "learning_rate": 0.0006272302261234615, "loss": 1.7423, "step": 39535 }, { "epoch": 8.19, "learning_rate": 0.0006271348153802118, "loss": 1.7476, "step": 39540 }, { "epoch": 8.19, "learning_rate": 0.0006270394046369622, "loss": 1.7436, "step": 39545 }, { "epoch": 8.19, "learning_rate": 0.0006269439938937125, "loss": 1.7462, "step": 39550 }, { "epoch": 8.19, "learning_rate": 0.0006268485831504628, "loss": 1.7433, "step": 39555 }, { "epoch": 8.2, "learning_rate": 0.000626753172407213, "loss": 1.748, "step": 39560 }, { "epoch": 8.2, "learning_rate": 0.0006266577616639634, "loss": 1.7513, "step": 39565 }, { "epoch": 8.2, "learning_rate": 0.0006265623509207137, "loss": 1.7453, "step": 39570 }, { "epoch": 8.2, "learning_rate": 0.000626466940177464, "loss": 1.7431, "step": 39575 }, { "epoch": 8.2, "learning_rate": 0.0006263715294342143, "loss": 1.7467, "step": 39580 }, { "epoch": 8.2, "learning_rate": 0.0006262761186909645, "loss": 1.748, "step": 39585 }, { "epoch": 8.2, "learning_rate": 0.0006261807079477149, "loss": 1.7426, "step": 39590 }, { "epoch": 8.2, "learning_rate": 0.0006260852972044653, "loss": 1.7422, "step": 39595 }, { "epoch": 8.2, "learning_rate": 0.0006259898864612156, "loss": 1.7461, "step": 39600 }, { "epoch": 8.2, "learning_rate": 0.0006258944757179659, "loss": 1.7432, "step": 39605 }, { "epoch": 8.21, "learning_rate": 0.0006257990649747162, "loss": 1.7464, "step": 39610 }, { "epoch": 8.21, "learning_rate": 0.0006257036542314664, "loss": 1.742, "step": 39615 }, { "epoch": 8.21, "learning_rate": 0.0006256082434882167, "loss": 1.7446, "step": 39620 }, { "epoch": 8.21, "learning_rate": 0.0006255128327449671, "loss": 1.7421, "step": 39625 }, { "epoch": 8.21, "learning_rate": 0.0006254174220017174, "loss": 1.7524, "step": 39630 }, { "epoch": 8.21, "learning_rate": 0.0006253220112584678, "loss": 1.7525, "step": 39635 }, { "epoch": 8.21, "learning_rate": 0.0006252266005152181, "loss": 1.7483, "step": 39640 }, { "epoch": 8.21, "learning_rate": 0.0006251311897719683, "loss": 1.7503, "step": 39645 }, { "epoch": 8.21, "learning_rate": 0.0006250357790287186, "loss": 1.7478, "step": 39650 }, { "epoch": 8.22, "learning_rate": 0.000624940368285469, "loss": 1.746, "step": 39655 }, { "epoch": 8.22, "learning_rate": 0.0006248449575422193, "loss": 1.7476, "step": 39660 }, { "epoch": 8.22, "learning_rate": 0.0006247495467989696, "loss": 1.7447, "step": 39665 }, { "epoch": 8.22, "learning_rate": 0.0006246541360557198, "loss": 1.748, "step": 39670 }, { "epoch": 8.22, "learning_rate": 0.0006245587253124701, "loss": 1.7482, "step": 39675 }, { "epoch": 8.22, "learning_rate": 0.0006244633145692204, "loss": 1.7478, "step": 39680 }, { "epoch": 8.22, "learning_rate": 0.0006243679038259709, "loss": 1.7429, "step": 39685 }, { "epoch": 8.22, "learning_rate": 0.0006242724930827212, "loss": 1.7418, "step": 39690 }, { "epoch": 8.22, "learning_rate": 0.0006241770823394715, "loss": 1.7488, "step": 39695 }, { "epoch": 8.22, "learning_rate": 0.0006240816715962217, "loss": 1.7506, "step": 39700 }, { "epoch": 8.23, "learning_rate": 0.000623986260852972, "loss": 1.7448, "step": 39705 }, { "epoch": 8.23, "learning_rate": 0.0006238908501097223, "loss": 1.7499, "step": 39710 }, { "epoch": 8.23, "learning_rate": 0.0006237954393664727, "loss": 1.7435, "step": 39715 }, { "epoch": 8.23, "learning_rate": 0.000623700028623223, "loss": 1.7454, "step": 39720 }, { "epoch": 8.23, "learning_rate": 0.0006236046178799732, "loss": 1.7436, "step": 39725 }, { "epoch": 8.23, "learning_rate": 0.0006235092071367236, "loss": 1.7492, "step": 39730 }, { "epoch": 8.23, "learning_rate": 0.0006234137963934739, "loss": 1.7447, "step": 39735 }, { "epoch": 8.23, "learning_rate": 0.0006233183856502243, "loss": 1.7488, "step": 39740 }, { "epoch": 8.23, "learning_rate": 0.0006232229749069746, "loss": 1.7484, "step": 39745 }, { "epoch": 8.23, "learning_rate": 0.0006231275641637249, "loss": 1.7457, "step": 39750 }, { "epoch": 8.24, "learning_rate": 0.0006230321534204751, "loss": 1.7455, "step": 39755 }, { "epoch": 8.24, "learning_rate": 0.0006229367426772254, "loss": 1.7491, "step": 39760 }, { "epoch": 8.24, "learning_rate": 0.0006228413319339757, "loss": 1.746, "step": 39765 }, { "epoch": 8.24, "learning_rate": 0.0006227459211907261, "loss": 1.7447, "step": 39770 }, { "epoch": 8.24, "learning_rate": 0.0006226505104474765, "loss": 1.7438, "step": 39775 }, { "epoch": 8.24, "learning_rate": 0.0006225550997042268, "loss": 1.7471, "step": 39780 }, { "epoch": 8.24, "learning_rate": 0.000622459688960977, "loss": 1.75, "step": 39785 }, { "epoch": 8.24, "learning_rate": 0.0006223642782177273, "loss": 1.7476, "step": 39790 }, { "epoch": 8.24, "learning_rate": 0.0006222688674744776, "loss": 1.7442, "step": 39795 }, { "epoch": 8.25, "learning_rate": 0.000622173456731228, "loss": 1.7483, "step": 39800 }, { "epoch": 8.25, "learning_rate": 0.0006220780459879783, "loss": 1.7427, "step": 39805 }, { "epoch": 8.25, "learning_rate": 0.0006219826352447285, "loss": 1.7461, "step": 39810 }, { "epoch": 8.25, "learning_rate": 0.0006218872245014788, "loss": 1.7448, "step": 39815 }, { "epoch": 8.25, "learning_rate": 0.0006217918137582292, "loss": 1.7455, "step": 39820 }, { "epoch": 8.25, "learning_rate": 0.0006216964030149795, "loss": 1.7489, "step": 39825 }, { "epoch": 8.25, "learning_rate": 0.0006216009922717299, "loss": 1.748, "step": 39830 }, { "epoch": 8.25, "learning_rate": 0.0006215055815284802, "loss": 1.7459, "step": 39835 }, { "epoch": 8.25, "learning_rate": 0.0006214101707852304, "loss": 1.7428, "step": 39840 }, { "epoch": 8.25, "learning_rate": 0.0006213147600419807, "loss": 1.7453, "step": 39845 }, { "epoch": 8.26, "learning_rate": 0.000621219349298731, "loss": 1.746, "step": 39850 }, { "epoch": 8.26, "learning_rate": 0.0006211239385554813, "loss": 1.7403, "step": 39855 }, { "epoch": 8.26, "learning_rate": 0.0006210285278122317, "loss": 1.7495, "step": 39860 }, { "epoch": 8.26, "learning_rate": 0.0006209331170689821, "loss": 1.7465, "step": 39865 }, { "epoch": 8.26, "learning_rate": 0.0006208377063257323, "loss": 1.744, "step": 39870 }, { "epoch": 8.26, "learning_rate": 0.0006207422955824826, "loss": 1.7462, "step": 39875 }, { "epoch": 8.26, "learning_rate": 0.0006206468848392329, "loss": 1.7459, "step": 39880 }, { "epoch": 8.26, "learning_rate": 0.0006205514740959832, "loss": 1.7439, "step": 39885 }, { "epoch": 8.26, "learning_rate": 0.0006204560633527336, "loss": 1.7484, "step": 39890 }, { "epoch": 8.26, "learning_rate": 0.0006203606526094838, "loss": 1.7453, "step": 39895 }, { "epoch": 8.27, "learning_rate": 0.0006202652418662341, "loss": 1.747, "step": 39900 }, { "epoch": 8.27, "learning_rate": 0.0006201698311229844, "loss": 1.7412, "step": 39905 }, { "epoch": 8.27, "learning_rate": 0.0006200744203797347, "loss": 1.7481, "step": 39910 }, { "epoch": 8.27, "learning_rate": 0.0006199790096364851, "loss": 1.7425, "step": 39915 }, { "epoch": 8.27, "learning_rate": 0.0006198835988932355, "loss": 1.7475, "step": 39920 }, { "epoch": 8.27, "learning_rate": 0.0006197881881499857, "loss": 1.7438, "step": 39925 }, { "epoch": 8.27, "learning_rate": 0.000619692777406736, "loss": 1.7481, "step": 39930 }, { "epoch": 8.27, "learning_rate": 0.0006195973666634863, "loss": 1.7458, "step": 39935 }, { "epoch": 8.27, "learning_rate": 0.0006195019559202366, "loss": 1.747, "step": 39940 }, { "epoch": 8.28, "learning_rate": 0.0006194065451769869, "loss": 1.7436, "step": 39945 }, { "epoch": 8.28, "learning_rate": 0.0006193111344337372, "loss": 1.7521, "step": 39950 }, { "epoch": 8.28, "learning_rate": 0.0006192157236904875, "loss": 1.7479, "step": 39955 }, { "epoch": 8.28, "learning_rate": 0.0006191203129472379, "loss": 1.7412, "step": 39960 }, { "epoch": 8.28, "learning_rate": 0.0006190249022039882, "loss": 1.7453, "step": 39965 }, { "epoch": 8.28, "learning_rate": 0.0006189294914607385, "loss": 1.7464, "step": 39970 }, { "epoch": 8.28, "learning_rate": 0.0006188340807174889, "loss": 1.7482, "step": 39975 }, { "epoch": 8.28, "learning_rate": 0.0006187386699742391, "loss": 1.7418, "step": 39980 }, { "epoch": 8.28, "learning_rate": 0.0006186432592309894, "loss": 1.746, "step": 39985 }, { "epoch": 8.28, "learning_rate": 0.0006185478484877397, "loss": 1.7431, "step": 39990 }, { "epoch": 8.29, "learning_rate": 0.00061845243774449, "loss": 1.7443, "step": 39995 }, { "epoch": 8.29, "learning_rate": 0.0006183570270012403, "loss": 1.7444, "step": 40000 }, { "epoch": 8.29, "learning_rate": 0.0006182616162579908, "loss": 1.743, "step": 40005 }, { "epoch": 8.29, "learning_rate": 0.000618166205514741, "loss": 1.7452, "step": 40010 }, { "epoch": 8.29, "learning_rate": 0.0006180707947714913, "loss": 1.7444, "step": 40015 }, { "epoch": 8.29, "learning_rate": 0.0006179753840282416, "loss": 1.7448, "step": 40020 }, { "epoch": 8.29, "learning_rate": 0.0006178799732849919, "loss": 1.7458, "step": 40025 }, { "epoch": 8.29, "learning_rate": 0.0006177845625417422, "loss": 1.7419, "step": 40030 }, { "epoch": 8.29, "learning_rate": 0.0006176891517984925, "loss": 1.7446, "step": 40035 }, { "epoch": 8.3, "learning_rate": 0.0006175937410552428, "loss": 1.7453, "step": 40040 }, { "epoch": 8.3, "learning_rate": 0.0006174983303119931, "loss": 1.7454, "step": 40045 }, { "epoch": 8.3, "learning_rate": 0.0006174029195687435, "loss": 1.7461, "step": 40050 }, { "epoch": 8.3, "learning_rate": 0.0006173075088254938, "loss": 1.7466, "step": 40055 }, { "epoch": 8.3, "learning_rate": 0.000617212098082244, "loss": 1.7501, "step": 40060 }, { "epoch": 8.3, "learning_rate": 0.0006171166873389944, "loss": 1.7491, "step": 40065 }, { "epoch": 8.3, "learning_rate": 0.0006170212765957447, "loss": 1.7468, "step": 40070 }, { "epoch": 8.3, "learning_rate": 0.000616925865852495, "loss": 1.7411, "step": 40075 }, { "epoch": 8.3, "learning_rate": 0.0006168304551092453, "loss": 1.7441, "step": 40080 }, { "epoch": 8.3, "learning_rate": 0.0006167350443659956, "loss": 1.7435, "step": 40085 }, { "epoch": 8.31, "learning_rate": 0.0006166396336227458, "loss": 1.7515, "step": 40090 }, { "epoch": 8.31, "learning_rate": 0.0006165442228794963, "loss": 1.7454, "step": 40095 }, { "epoch": 8.31, "learning_rate": 0.0006164488121362466, "loss": 1.7505, "step": 40100 }, { "epoch": 8.31, "learning_rate": 0.0006163534013929969, "loss": 1.7475, "step": 40105 }, { "epoch": 8.31, "learning_rate": 0.0006162579906497472, "loss": 1.7449, "step": 40110 }, { "epoch": 8.31, "learning_rate": 0.0006161625799064975, "loss": 1.7473, "step": 40115 }, { "epoch": 8.31, "learning_rate": 0.0006160671691632477, "loss": 1.7464, "step": 40120 }, { "epoch": 8.31, "learning_rate": 0.0006159717584199981, "loss": 1.7475, "step": 40125 }, { "epoch": 8.31, "learning_rate": 0.0006158763476767484, "loss": 1.7449, "step": 40130 }, { "epoch": 8.31, "learning_rate": 0.0006157809369334987, "loss": 1.7454, "step": 40135 }, { "epoch": 8.32, "learning_rate": 0.0006156855261902491, "loss": 1.7497, "step": 40140 }, { "epoch": 8.32, "learning_rate": 0.0006155901154469994, "loss": 1.7468, "step": 40145 }, { "epoch": 8.32, "learning_rate": 0.0006154947047037497, "loss": 1.7464, "step": 40150 }, { "epoch": 8.32, "learning_rate": 0.0006153992939605, "loss": 1.7439, "step": 40155 }, { "epoch": 8.32, "learning_rate": 0.0006153038832172503, "loss": 1.7466, "step": 40160 }, { "epoch": 8.32, "learning_rate": 0.0006152084724740006, "loss": 1.745, "step": 40165 }, { "epoch": 8.32, "learning_rate": 0.0006151130617307509, "loss": 1.7427, "step": 40170 }, { "epoch": 8.32, "learning_rate": 0.0006150176509875011, "loss": 1.7444, "step": 40175 }, { "epoch": 8.32, "learning_rate": 0.0006149222402442515, "loss": 1.7435, "step": 40180 }, { "epoch": 8.33, "learning_rate": 0.0006148268295010018, "loss": 1.7449, "step": 40185 }, { "epoch": 8.33, "learning_rate": 0.0006147314187577522, "loss": 1.7437, "step": 40190 }, { "epoch": 8.33, "learning_rate": 0.0006146360080145025, "loss": 1.7442, "step": 40195 }, { "epoch": 8.33, "learning_rate": 0.0006145405972712528, "loss": 1.7417, "step": 40200 }, { "epoch": 8.33, "learning_rate": 0.000614445186528003, "loss": 1.7502, "step": 40205 }, { "epoch": 8.33, "learning_rate": 0.0006143497757847534, "loss": 1.7462, "step": 40210 }, { "epoch": 8.33, "learning_rate": 0.0006142543650415037, "loss": 1.7451, "step": 40215 }, { "epoch": 8.33, "learning_rate": 0.000614158954298254, "loss": 1.7435, "step": 40220 }, { "epoch": 8.33, "learning_rate": 0.0006140635435550043, "loss": 1.751, "step": 40225 }, { "epoch": 8.33, "learning_rate": 0.0006139681328117545, "loss": 1.7495, "step": 40230 }, { "epoch": 8.34, "learning_rate": 0.0006138727220685049, "loss": 1.739, "step": 40235 }, { "epoch": 8.34, "learning_rate": 0.0006137773113252553, "loss": 1.7446, "step": 40240 }, { "epoch": 8.34, "learning_rate": 0.0006136819005820056, "loss": 1.7446, "step": 40245 }, { "epoch": 8.34, "learning_rate": 0.0006135864898387559, "loss": 1.7492, "step": 40250 }, { "epoch": 8.34, "learning_rate": 0.0006134910790955062, "loss": 1.746, "step": 40255 }, { "epoch": 8.34, "learning_rate": 0.0006133956683522564, "loss": 1.7403, "step": 40260 }, { "epoch": 8.34, "learning_rate": 0.0006133002576090067, "loss": 1.7491, "step": 40265 }, { "epoch": 8.34, "learning_rate": 0.0006132048468657571, "loss": 1.7552, "step": 40270 }, { "epoch": 8.34, "learning_rate": 0.0006131094361225074, "loss": 1.741, "step": 40275 }, { "epoch": 8.34, "learning_rate": 0.0006130140253792578, "loss": 1.7461, "step": 40280 }, { "epoch": 8.35, "learning_rate": 0.000612918614636008, "loss": 1.7449, "step": 40285 }, { "epoch": 8.35, "learning_rate": 0.0006128232038927583, "loss": 1.7431, "step": 40290 }, { "epoch": 8.35, "learning_rate": 0.0006127277931495086, "loss": 1.7391, "step": 40295 }, { "epoch": 8.35, "learning_rate": 0.000612632382406259, "loss": 1.7458, "step": 40300 }, { "epoch": 8.35, "learning_rate": 0.0006125369716630093, "loss": 1.7492, "step": 40305 }, { "epoch": 8.35, "learning_rate": 0.0006124415609197596, "loss": 1.7427, "step": 40310 }, { "epoch": 8.35, "learning_rate": 0.0006123461501765098, "loss": 1.7421, "step": 40315 }, { "epoch": 8.35, "learning_rate": 0.0006122507394332601, "loss": 1.7451, "step": 40320 }, { "epoch": 8.35, "learning_rate": 0.0006121553286900105, "loss": 1.7487, "step": 40325 }, { "epoch": 8.36, "learning_rate": 0.0006120599179467609, "loss": 1.7428, "step": 40330 }, { "epoch": 8.36, "learning_rate": 0.0006119645072035112, "loss": 1.745, "step": 40335 }, { "epoch": 8.36, "learning_rate": 0.0006118690964602615, "loss": 1.7453, "step": 40340 }, { "epoch": 8.36, "learning_rate": 0.0006117736857170117, "loss": 1.7435, "step": 40345 }, { "epoch": 8.36, "learning_rate": 0.000611678274973762, "loss": 1.7449, "step": 40350 }, { "epoch": 8.36, "learning_rate": 0.0006115828642305123, "loss": 1.7425, "step": 40355 }, { "epoch": 8.36, "learning_rate": 0.0006114874534872627, "loss": 1.7442, "step": 40360 }, { "epoch": 8.36, "learning_rate": 0.000611392042744013, "loss": 1.7459, "step": 40365 }, { "epoch": 8.36, "learning_rate": 0.0006112966320007634, "loss": 1.7495, "step": 40370 }, { "epoch": 8.36, "learning_rate": 0.0006112012212575136, "loss": 1.7486, "step": 40375 }, { "epoch": 8.37, "learning_rate": 0.0006111058105142639, "loss": 1.7424, "step": 40380 }, { "epoch": 8.37, "learning_rate": 0.0006110103997710143, "loss": 1.7455, "step": 40385 }, { "epoch": 8.37, "learning_rate": 0.0006109149890277646, "loss": 1.7438, "step": 40390 }, { "epoch": 8.37, "learning_rate": 0.0006108195782845149, "loss": 1.7443, "step": 40395 }, { "epoch": 8.37, "learning_rate": 0.0006107241675412651, "loss": 1.7456, "step": 40400 }, { "epoch": 8.37, "learning_rate": 0.0006106287567980154, "loss": 1.7457, "step": 40405 }, { "epoch": 8.37, "learning_rate": 0.0006105333460547657, "loss": 1.7465, "step": 40410 }, { "epoch": 8.37, "learning_rate": 0.0006104379353115161, "loss": 1.7463, "step": 40415 }, { "epoch": 8.37, "learning_rate": 0.0006103425245682665, "loss": 1.7433, "step": 40420 }, { "epoch": 8.37, "learning_rate": 0.0006102471138250168, "loss": 1.744, "step": 40425 }, { "epoch": 8.38, "learning_rate": 0.000610151703081767, "loss": 1.7496, "step": 40430 }, { "epoch": 8.38, "learning_rate": 0.0006100562923385173, "loss": 1.7471, "step": 40435 }, { "epoch": 8.38, "learning_rate": 0.0006099608815952676, "loss": 1.7471, "step": 40440 }, { "epoch": 8.38, "learning_rate": 0.000609865470852018, "loss": 1.7458, "step": 40445 }, { "epoch": 8.38, "learning_rate": 0.0006097700601087683, "loss": 1.7493, "step": 40450 }, { "epoch": 8.38, "learning_rate": 0.0006096746493655185, "loss": 1.7469, "step": 40455 }, { "epoch": 8.38, "learning_rate": 0.0006095792386222688, "loss": 1.7385, "step": 40460 }, { "epoch": 8.38, "learning_rate": 0.0006094838278790192, "loss": 1.7464, "step": 40465 }, { "epoch": 8.38, "learning_rate": 0.0006093884171357695, "loss": 1.7406, "step": 40470 }, { "epoch": 8.39, "learning_rate": 0.0006092930063925199, "loss": 1.7492, "step": 40475 }, { "epoch": 8.39, "learning_rate": 0.0006091975956492702, "loss": 1.7453, "step": 40480 }, { "epoch": 8.39, "learning_rate": 0.0006091021849060204, "loss": 1.7422, "step": 40485 }, { "epoch": 8.39, "learning_rate": 0.0006090067741627707, "loss": 1.7437, "step": 40490 }, { "epoch": 8.39, "learning_rate": 0.000608911363419521, "loss": 1.7483, "step": 40495 }, { "epoch": 8.39, "learning_rate": 0.0006088159526762713, "loss": 1.7452, "step": 40500 }, { "epoch": 8.39, "learning_rate": 0.0006087205419330217, "loss": 1.7458, "step": 40505 }, { "epoch": 8.39, "learning_rate": 0.000608625131189772, "loss": 1.7451, "step": 40510 }, { "epoch": 8.39, "learning_rate": 0.0006085297204465223, "loss": 1.7428, "step": 40515 }, { "epoch": 8.39, "learning_rate": 0.0006084343097032726, "loss": 1.7454, "step": 40520 }, { "epoch": 8.4, "learning_rate": 0.0006083388989600229, "loss": 1.7442, "step": 40525 }, { "epoch": 8.4, "learning_rate": 0.0006082434882167732, "loss": 1.7464, "step": 40530 }, { "epoch": 8.4, "learning_rate": 0.0006081480774735236, "loss": 1.7434, "step": 40535 }, { "epoch": 8.4, "learning_rate": 0.0006080526667302738, "loss": 1.7463, "step": 40540 }, { "epoch": 8.4, "learning_rate": 0.0006079572559870241, "loss": 1.7471, "step": 40545 }, { "epoch": 8.4, "learning_rate": 0.0006078618452437744, "loss": 1.7488, "step": 40550 }, { "epoch": 8.4, "learning_rate": 0.0006077664345005248, "loss": 1.7425, "step": 40555 }, { "epoch": 8.4, "learning_rate": 0.0006076710237572751, "loss": 1.7496, "step": 40560 }, { "epoch": 8.4, "learning_rate": 0.0006075756130140255, "loss": 1.745, "step": 40565 }, { "epoch": 8.4, "learning_rate": 0.0006074802022707757, "loss": 1.7428, "step": 40570 }, { "epoch": 8.41, "learning_rate": 0.000607384791527526, "loss": 1.7483, "step": 40575 }, { "epoch": 8.41, "learning_rate": 0.0006072893807842763, "loss": 1.7468, "step": 40580 }, { "epoch": 8.41, "learning_rate": 0.0006071939700410266, "loss": 1.7441, "step": 40585 }, { "epoch": 8.41, "learning_rate": 0.000607098559297777, "loss": 1.7414, "step": 40590 }, { "epoch": 8.41, "learning_rate": 0.0006070031485545272, "loss": 1.7485, "step": 40595 }, { "epoch": 8.41, "learning_rate": 0.0006069077378112776, "loss": 1.7474, "step": 40600 }, { "epoch": 8.41, "learning_rate": 0.0006068123270680279, "loss": 1.7438, "step": 40605 }, { "epoch": 8.41, "learning_rate": 0.0006067169163247782, "loss": 1.7473, "step": 40610 }, { "epoch": 8.41, "learning_rate": 0.0006066215055815285, "loss": 1.7443, "step": 40615 }, { "epoch": 8.42, "learning_rate": 0.0006065260948382789, "loss": 1.7471, "step": 40620 }, { "epoch": 8.42, "learning_rate": 0.0006064306840950291, "loss": 1.7502, "step": 40625 }, { "epoch": 8.42, "learning_rate": 0.0006063352733517794, "loss": 1.7438, "step": 40630 }, { "epoch": 8.42, "learning_rate": 0.0006062398626085297, "loss": 1.7471, "step": 40635 }, { "epoch": 8.42, "learning_rate": 0.00060614445186528, "loss": 1.7462, "step": 40640 }, { "epoch": 8.42, "learning_rate": 0.0006060490411220303, "loss": 1.7457, "step": 40645 }, { "epoch": 8.42, "learning_rate": 0.0006059536303787808, "loss": 1.7482, "step": 40650 }, { "epoch": 8.42, "learning_rate": 0.000605858219635531, "loss": 1.7432, "step": 40655 }, { "epoch": 8.42, "learning_rate": 0.0006057628088922813, "loss": 1.7501, "step": 40660 }, { "epoch": 8.42, "learning_rate": 0.0006056673981490316, "loss": 1.7405, "step": 40665 }, { "epoch": 8.43, "learning_rate": 0.0006055719874057819, "loss": 1.7472, "step": 40670 }, { "epoch": 8.43, "learning_rate": 0.0006054765766625322, "loss": 1.7512, "step": 40675 }, { "epoch": 8.43, "learning_rate": 0.0006053811659192825, "loss": 1.748, "step": 40680 }, { "epoch": 8.43, "learning_rate": 0.0006052857551760328, "loss": 1.747, "step": 40685 }, { "epoch": 8.43, "learning_rate": 0.0006051903444327831, "loss": 1.745, "step": 40690 }, { "epoch": 8.43, "learning_rate": 0.0006050949336895335, "loss": 1.749, "step": 40695 }, { "epoch": 8.43, "learning_rate": 0.0006049995229462838, "loss": 1.7438, "step": 40700 }, { "epoch": 8.43, "learning_rate": 0.000604904112203034, "loss": 1.7514, "step": 40705 }, { "epoch": 8.43, "learning_rate": 0.0006048087014597844, "loss": 1.7409, "step": 40710 }, { "epoch": 8.43, "learning_rate": 0.0006047132907165347, "loss": 1.7495, "step": 40715 }, { "epoch": 8.44, "learning_rate": 0.000604617879973285, "loss": 1.7506, "step": 40720 }, { "epoch": 8.44, "learning_rate": 0.0006045224692300353, "loss": 1.745, "step": 40725 }, { "epoch": 8.44, "learning_rate": 0.0006044270584867856, "loss": 1.7492, "step": 40730 }, { "epoch": 8.44, "learning_rate": 0.0006043316477435358, "loss": 1.7453, "step": 40735 }, { "epoch": 8.44, "learning_rate": 0.0006042362370002863, "loss": 1.7441, "step": 40740 }, { "epoch": 8.44, "learning_rate": 0.0006041408262570366, "loss": 1.7413, "step": 40745 }, { "epoch": 8.44, "learning_rate": 0.0006040454155137869, "loss": 1.7414, "step": 40750 }, { "epoch": 8.44, "learning_rate": 0.0006039500047705372, "loss": 1.7454, "step": 40755 }, { "epoch": 8.44, "learning_rate": 0.0006038545940272875, "loss": 1.7468, "step": 40760 }, { "epoch": 8.45, "learning_rate": 0.0006037591832840377, "loss": 1.7469, "step": 40765 }, { "epoch": 8.45, "learning_rate": 0.0006036637725407881, "loss": 1.7411, "step": 40770 }, { "epoch": 8.45, "learning_rate": 0.0006035683617975384, "loss": 1.7402, "step": 40775 }, { "epoch": 8.45, "learning_rate": 0.0006034729510542887, "loss": 1.7436, "step": 40780 }, { "epoch": 8.45, "learning_rate": 0.0006033775403110391, "loss": 1.742, "step": 40785 }, { "epoch": 8.45, "learning_rate": 0.0006032821295677893, "loss": 1.7437, "step": 40790 }, { "epoch": 8.45, "learning_rate": 0.0006031867188245397, "loss": 1.7464, "step": 40795 }, { "epoch": 8.45, "learning_rate": 0.00060309130808129, "loss": 1.7437, "step": 40800 }, { "epoch": 8.45, "learning_rate": 0.0006029958973380403, "loss": 1.743, "step": 40805 }, { "epoch": 8.45, "learning_rate": 0.0006029004865947906, "loss": 1.7414, "step": 40810 }, { "epoch": 8.46, "learning_rate": 0.0006028050758515409, "loss": 1.7453, "step": 40815 }, { "epoch": 8.46, "learning_rate": 0.0006027096651082911, "loss": 1.7445, "step": 40820 }, { "epoch": 8.46, "learning_rate": 0.0006026142543650415, "loss": 1.7447, "step": 40825 }, { "epoch": 8.46, "learning_rate": 0.0006025188436217919, "loss": 1.7379, "step": 40830 }, { "epoch": 8.46, "learning_rate": 0.0006024234328785422, "loss": 1.7467, "step": 40835 }, { "epoch": 8.46, "learning_rate": 0.0006023280221352925, "loss": 1.7433, "step": 40840 }, { "epoch": 8.46, "learning_rate": 0.0006022326113920427, "loss": 1.745, "step": 40845 }, { "epoch": 8.46, "learning_rate": 0.000602137200648793, "loss": 1.7497, "step": 40850 }, { "epoch": 8.46, "learning_rate": 0.0006020417899055434, "loss": 1.7425, "step": 40855 }, { "epoch": 8.46, "learning_rate": 0.0006019463791622937, "loss": 1.7452, "step": 40860 }, { "epoch": 8.47, "learning_rate": 0.000601850968419044, "loss": 1.7438, "step": 40865 }, { "epoch": 8.47, "learning_rate": 0.0006017555576757943, "loss": 1.7477, "step": 40870 }, { "epoch": 8.47, "learning_rate": 0.0006016601469325446, "loss": 1.7434, "step": 40875 }, { "epoch": 8.47, "learning_rate": 0.0006015647361892949, "loss": 1.7385, "step": 40880 }, { "epoch": 8.47, "learning_rate": 0.0006014693254460453, "loss": 1.7431, "step": 40885 }, { "epoch": 8.47, "learning_rate": 0.0006013739147027956, "loss": 1.7473, "step": 40890 }, { "epoch": 8.47, "learning_rate": 0.0006012785039595459, "loss": 1.7428, "step": 40895 }, { "epoch": 8.47, "learning_rate": 0.0006011830932162962, "loss": 1.743, "step": 40900 }, { "epoch": 8.47, "learning_rate": 0.0006010876824730464, "loss": 1.742, "step": 40905 }, { "epoch": 8.48, "learning_rate": 0.0006009922717297967, "loss": 1.7488, "step": 40910 }, { "epoch": 8.48, "learning_rate": 0.0006008968609865471, "loss": 1.7483, "step": 40915 }, { "epoch": 8.48, "learning_rate": 0.0006008014502432974, "loss": 1.74, "step": 40920 }, { "epoch": 8.48, "learning_rate": 0.0006007060395000478, "loss": 1.7445, "step": 40925 }, { "epoch": 8.48, "learning_rate": 0.000600610628756798, "loss": 1.7366, "step": 40930 }, { "epoch": 8.48, "learning_rate": 0.0006005152180135483, "loss": 1.7454, "step": 40935 }, { "epoch": 8.48, "learning_rate": 0.0006004198072702986, "loss": 1.7483, "step": 40940 }, { "epoch": 8.48, "learning_rate": 0.000600324396527049, "loss": 1.7417, "step": 40945 }, { "epoch": 8.48, "learning_rate": 0.0006002289857837993, "loss": 1.7414, "step": 40950 }, { "epoch": 8.48, "learning_rate": 0.0006001335750405496, "loss": 1.7397, "step": 40955 }, { "epoch": 8.49, "learning_rate": 0.0006000381642972998, "loss": 1.7503, "step": 40960 }, { "epoch": 8.49, "learning_rate": 0.0005999427535540501, "loss": 1.7464, "step": 40965 }, { "epoch": 8.49, "learning_rate": 0.0005998473428108005, "loss": 1.7478, "step": 40970 }, { "epoch": 8.49, "learning_rate": 0.0005997519320675509, "loss": 1.7445, "step": 40975 }, { "epoch": 8.49, "learning_rate": 0.0005996565213243012, "loss": 1.7428, "step": 40980 }, { "epoch": 8.49, "learning_rate": 0.0005995611105810515, "loss": 1.7435, "step": 40985 }, { "epoch": 8.49, "learning_rate": 0.0005994656998378017, "loss": 1.7429, "step": 40990 }, { "epoch": 8.49, "learning_rate": 0.000599370289094552, "loss": 1.744, "step": 40995 }, { "epoch": 8.49, "learning_rate": 0.0005992748783513023, "loss": 1.7507, "step": 41000 }, { "epoch": 8.49, "learning_rate": 0.0005991794676080527, "loss": 1.7436, "step": 41005 }, { "epoch": 8.5, "learning_rate": 0.000599084056864803, "loss": 1.7441, "step": 41010 }, { "epoch": 8.5, "learning_rate": 0.0005989886461215533, "loss": 1.7455, "step": 41015 }, { "epoch": 8.5, "learning_rate": 0.0005988932353783036, "loss": 1.7449, "step": 41020 }, { "epoch": 8.5, "learning_rate": 0.0005987978246350539, "loss": 1.7457, "step": 41025 }, { "epoch": 8.5, "learning_rate": 0.0005987024138918043, "loss": 1.7419, "step": 41030 }, { "epoch": 8.5, "learning_rate": 0.0005986070031485546, "loss": 1.7428, "step": 41035 }, { "epoch": 8.5, "learning_rate": 0.0005985115924053049, "loss": 1.7471, "step": 41040 }, { "epoch": 8.5, "learning_rate": 0.0005984161816620551, "loss": 1.7421, "step": 41045 }, { "epoch": 8.5, "learning_rate": 0.0005983207709188054, "loss": 1.7479, "step": 41050 }, { "epoch": 8.51, "learning_rate": 0.0005982253601755557, "loss": 1.7462, "step": 41055 }, { "epoch": 8.51, "learning_rate": 0.0005981299494323062, "loss": 1.7471, "step": 41060 }, { "epoch": 8.51, "learning_rate": 0.0005980345386890565, "loss": 1.7451, "step": 41065 }, { "epoch": 8.51, "learning_rate": 0.0005979391279458067, "loss": 1.7444, "step": 41070 }, { "epoch": 8.51, "learning_rate": 0.000597843717202557, "loss": 1.7438, "step": 41075 }, { "epoch": 8.51, "learning_rate": 0.0005977483064593073, "loss": 1.7481, "step": 41080 }, { "epoch": 8.51, "learning_rate": 0.0005976528957160576, "loss": 1.7437, "step": 41085 }, { "epoch": 8.51, "learning_rate": 0.000597557484972808, "loss": 1.7489, "step": 41090 }, { "epoch": 8.51, "learning_rate": 0.0005974620742295583, "loss": 1.7433, "step": 41095 }, { "epoch": 8.51, "learning_rate": 0.0005973666634863085, "loss": 1.7461, "step": 41100 }, { "epoch": 8.52, "learning_rate": 0.0005972712527430589, "loss": 1.7452, "step": 41105 }, { "epoch": 8.52, "learning_rate": 0.0005971758419998092, "loss": 1.7418, "step": 41110 }, { "epoch": 8.52, "learning_rate": 0.0005970804312565595, "loss": 1.743, "step": 41115 }, { "epoch": 8.52, "learning_rate": 0.0005969850205133099, "loss": 1.7411, "step": 41120 }, { "epoch": 8.52, "learning_rate": 0.0005968896097700602, "loss": 1.7458, "step": 41125 }, { "epoch": 8.52, "learning_rate": 0.0005967941990268104, "loss": 1.7367, "step": 41130 }, { "epoch": 8.52, "learning_rate": 0.0005966987882835607, "loss": 1.7461, "step": 41135 }, { "epoch": 8.52, "learning_rate": 0.000596603377540311, "loss": 1.7445, "step": 41140 }, { "epoch": 8.52, "learning_rate": 0.0005965079667970613, "loss": 1.7483, "step": 41145 }, { "epoch": 8.52, "learning_rate": 0.0005964125560538117, "loss": 1.7428, "step": 41150 }, { "epoch": 8.53, "learning_rate": 0.000596317145310562, "loss": 1.7437, "step": 41155 }, { "epoch": 8.53, "learning_rate": 0.0005962217345673123, "loss": 1.7464, "step": 41160 }, { "epoch": 8.53, "learning_rate": 0.0005961263238240626, "loss": 1.7433, "step": 41165 }, { "epoch": 8.53, "learning_rate": 0.0005960309130808129, "loss": 1.743, "step": 41170 }, { "epoch": 8.53, "learning_rate": 0.0005959355023375632, "loss": 1.7441, "step": 41175 }, { "epoch": 8.53, "learning_rate": 0.0005958400915943136, "loss": 1.7477, "step": 41180 }, { "epoch": 8.53, "learning_rate": 0.0005957446808510638, "loss": 1.7453, "step": 41185 }, { "epoch": 8.53, "learning_rate": 0.0005956492701078141, "loss": 1.7488, "step": 41190 }, { "epoch": 8.53, "learning_rate": 0.0005955538593645644, "loss": 1.7481, "step": 41195 }, { "epoch": 8.54, "learning_rate": 0.0005954584486213148, "loss": 1.7457, "step": 41200 }, { "epoch": 8.54, "learning_rate": 0.0005953630378780651, "loss": 1.7472, "step": 41205 }, { "epoch": 8.54, "learning_rate": 0.0005952676271348155, "loss": 1.7472, "step": 41210 }, { "epoch": 8.54, "learning_rate": 0.0005951722163915657, "loss": 1.7425, "step": 41215 }, { "epoch": 8.54, "learning_rate": 0.000595076805648316, "loss": 1.7456, "step": 41220 }, { "epoch": 8.54, "learning_rate": 0.0005949813949050663, "loss": 1.7423, "step": 41225 }, { "epoch": 8.54, "learning_rate": 0.0005948859841618166, "loss": 1.7429, "step": 41230 }, { "epoch": 8.54, "learning_rate": 0.000594790573418567, "loss": 1.7491, "step": 41235 }, { "epoch": 8.54, "learning_rate": 0.0005946951626753172, "loss": 1.7477, "step": 41240 }, { "epoch": 8.54, "learning_rate": 0.0005945997519320676, "loss": 1.7488, "step": 41245 }, { "epoch": 8.55, "learning_rate": 0.0005945043411888179, "loss": 1.7439, "step": 41250 }, { "epoch": 8.55, "learning_rate": 0.0005944089304455682, "loss": 1.7426, "step": 41255 }, { "epoch": 8.55, "learning_rate": 0.0005943135197023185, "loss": 1.742, "step": 41260 }, { "epoch": 8.55, "learning_rate": 0.0005942181089590689, "loss": 1.7436, "step": 41265 }, { "epoch": 8.55, "learning_rate": 0.0005941226982158191, "loss": 1.7459, "step": 41270 }, { "epoch": 8.55, "learning_rate": 0.0005940272874725694, "loss": 1.7457, "step": 41275 }, { "epoch": 8.55, "learning_rate": 0.0005939318767293197, "loss": 1.7464, "step": 41280 }, { "epoch": 8.55, "learning_rate": 0.00059383646598607, "loss": 1.7439, "step": 41285 }, { "epoch": 8.55, "learning_rate": 0.0005937410552428204, "loss": 1.7432, "step": 41290 }, { "epoch": 8.56, "learning_rate": 0.0005936456444995707, "loss": 1.7491, "step": 41295 }, { "epoch": 8.56, "learning_rate": 0.000593550233756321, "loss": 1.7452, "step": 41300 }, { "epoch": 8.56, "learning_rate": 0.0005934548230130713, "loss": 1.7433, "step": 41305 }, { "epoch": 8.56, "learning_rate": 0.0005933594122698216, "loss": 1.7422, "step": 41310 }, { "epoch": 8.56, "learning_rate": 0.0005932640015265719, "loss": 1.7459, "step": 41315 }, { "epoch": 8.56, "learning_rate": 0.0005931685907833221, "loss": 1.747, "step": 41320 }, { "epoch": 8.56, "learning_rate": 0.0005930731800400725, "loss": 1.7416, "step": 41325 }, { "epoch": 8.56, "learning_rate": 0.0005929777692968228, "loss": 1.745, "step": 41330 }, { "epoch": 8.56, "learning_rate": 0.0005928823585535732, "loss": 1.7429, "step": 41335 }, { "epoch": 8.56, "learning_rate": 0.0005927869478103235, "loss": 1.7403, "step": 41340 }, { "epoch": 8.57, "learning_rate": 0.0005926915370670738, "loss": 1.7486, "step": 41345 }, { "epoch": 8.57, "learning_rate": 0.000592596126323824, "loss": 1.7438, "step": 41350 }, { "epoch": 8.57, "learning_rate": 0.0005925007155805744, "loss": 1.7427, "step": 41355 }, { "epoch": 8.57, "learning_rate": 0.0005924053048373247, "loss": 1.7468, "step": 41360 }, { "epoch": 8.57, "learning_rate": 0.000592309894094075, "loss": 1.7491, "step": 41365 }, { "epoch": 8.57, "learning_rate": 0.0005922144833508253, "loss": 1.748, "step": 41370 }, { "epoch": 8.57, "learning_rate": 0.0005921190726075756, "loss": 1.7442, "step": 41375 }, { "epoch": 8.57, "learning_rate": 0.0005920236618643259, "loss": 1.7486, "step": 41380 }, { "epoch": 8.57, "learning_rate": 0.0005919282511210763, "loss": 1.7503, "step": 41385 }, { "epoch": 8.57, "learning_rate": 0.0005918328403778266, "loss": 1.7472, "step": 41390 }, { "epoch": 8.58, "learning_rate": 0.0005917374296345769, "loss": 1.743, "step": 41395 }, { "epoch": 8.58, "learning_rate": 0.0005916420188913272, "loss": 1.747, "step": 41400 }, { "epoch": 8.58, "learning_rate": 0.0005915466081480774, "loss": 1.753, "step": 41405 }, { "epoch": 8.58, "learning_rate": 0.0005914511974048277, "loss": 1.7488, "step": 41410 }, { "epoch": 8.58, "learning_rate": 0.0005913557866615781, "loss": 1.7427, "step": 41415 }, { "epoch": 8.58, "learning_rate": 0.0005912603759183284, "loss": 1.7421, "step": 41420 }, { "epoch": 8.58, "learning_rate": 0.0005911649651750787, "loss": 1.7438, "step": 41425 }, { "epoch": 8.58, "learning_rate": 0.0005910695544318291, "loss": 1.746, "step": 41430 }, { "epoch": 8.58, "learning_rate": 0.0005909741436885793, "loss": 1.7462, "step": 41435 }, { "epoch": 8.59, "learning_rate": 0.0005908787329453297, "loss": 1.7425, "step": 41440 }, { "epoch": 8.59, "learning_rate": 0.00059078332220208, "loss": 1.7486, "step": 41445 }, { "epoch": 8.59, "learning_rate": 0.0005906879114588303, "loss": 1.7428, "step": 41450 }, { "epoch": 8.59, "learning_rate": 0.0005905925007155806, "loss": 1.7499, "step": 41455 }, { "epoch": 8.59, "learning_rate": 0.0005904970899723308, "loss": 1.7437, "step": 41460 }, { "epoch": 8.59, "learning_rate": 0.0005904016792290811, "loss": 1.7498, "step": 41465 }, { "epoch": 8.59, "learning_rate": 0.0005903062684858315, "loss": 1.7429, "step": 41470 }, { "epoch": 8.59, "learning_rate": 0.0005902108577425819, "loss": 1.7435, "step": 41475 }, { "epoch": 8.59, "learning_rate": 0.0005901154469993322, "loss": 1.7454, "step": 41480 }, { "epoch": 8.59, "learning_rate": 0.0005900200362560825, "loss": 1.7452, "step": 41485 }, { "epoch": 8.6, "learning_rate": 0.0005899246255128327, "loss": 1.7471, "step": 41490 }, { "epoch": 8.6, "learning_rate": 0.000589829214769583, "loss": 1.7448, "step": 41495 }, { "epoch": 8.6, "learning_rate": 0.0005897338040263334, "loss": 1.7461, "step": 41500 }, { "epoch": 8.6, "learning_rate": 0.0005896383932830837, "loss": 1.7401, "step": 41505 }, { "epoch": 8.6, "learning_rate": 0.000589542982539834, "loss": 1.7456, "step": 41510 }, { "epoch": 8.6, "learning_rate": 0.0005894475717965843, "loss": 1.7439, "step": 41515 }, { "epoch": 8.6, "learning_rate": 0.0005893521610533346, "loss": 1.7437, "step": 41520 }, { "epoch": 8.6, "learning_rate": 0.0005892567503100849, "loss": 1.7507, "step": 41525 }, { "epoch": 8.6, "learning_rate": 0.0005891613395668353, "loss": 1.7431, "step": 41530 }, { "epoch": 8.6, "learning_rate": 0.0005890659288235856, "loss": 1.7465, "step": 41535 }, { "epoch": 8.61, "learning_rate": 0.0005889705180803359, "loss": 1.7435, "step": 41540 }, { "epoch": 8.61, "learning_rate": 0.0005888751073370861, "loss": 1.7402, "step": 41545 }, { "epoch": 8.61, "learning_rate": 0.0005887796965938364, "loss": 1.7475, "step": 41550 }, { "epoch": 8.61, "learning_rate": 0.0005886842858505867, "loss": 1.7442, "step": 41555 }, { "epoch": 8.61, "learning_rate": 0.0005885888751073371, "loss": 1.7448, "step": 41560 }, { "epoch": 8.61, "learning_rate": 0.0005884934643640875, "loss": 1.7392, "step": 41565 }, { "epoch": 8.61, "learning_rate": 0.0005883980536208378, "loss": 1.7403, "step": 41570 }, { "epoch": 8.61, "learning_rate": 0.000588302642877588, "loss": 1.7443, "step": 41575 }, { "epoch": 8.61, "learning_rate": 0.0005882072321343383, "loss": 1.7429, "step": 41580 }, { "epoch": 8.62, "learning_rate": 0.0005881118213910886, "loss": 1.7425, "step": 41585 }, { "epoch": 8.62, "learning_rate": 0.000588016410647839, "loss": 1.7515, "step": 41590 }, { "epoch": 8.62, "learning_rate": 0.0005879209999045893, "loss": 1.7469, "step": 41595 }, { "epoch": 8.62, "learning_rate": 0.0005878255891613396, "loss": 1.7431, "step": 41600 }, { "epoch": 8.62, "learning_rate": 0.0005877301784180898, "loss": 1.7412, "step": 41605 }, { "epoch": 8.62, "learning_rate": 0.0005876347676748402, "loss": 1.7453, "step": 41610 }, { "epoch": 8.62, "learning_rate": 0.0005875393569315905, "loss": 1.7451, "step": 41615 }, { "epoch": 8.62, "learning_rate": 0.0005874439461883409, "loss": 1.7427, "step": 41620 }, { "epoch": 8.62, "learning_rate": 0.0005873485354450912, "loss": 1.7528, "step": 41625 }, { "epoch": 8.62, "learning_rate": 0.0005872531247018414, "loss": 1.7457, "step": 41630 }, { "epoch": 8.63, "learning_rate": 0.0005871577139585917, "loss": 1.7527, "step": 41635 }, { "epoch": 8.63, "learning_rate": 0.000587062303215342, "loss": 1.7434, "step": 41640 }, { "epoch": 8.63, "learning_rate": 0.0005869668924720923, "loss": 1.7433, "step": 41645 }, { "epoch": 8.63, "learning_rate": 0.0005868714817288427, "loss": 1.7446, "step": 41650 }, { "epoch": 8.63, "learning_rate": 0.000586776070985593, "loss": 1.742, "step": 41655 }, { "epoch": 8.63, "learning_rate": 0.0005866806602423433, "loss": 1.743, "step": 41660 }, { "epoch": 8.63, "learning_rate": 0.0005865852494990936, "loss": 1.7524, "step": 41665 }, { "epoch": 8.63, "learning_rate": 0.0005864898387558439, "loss": 1.7444, "step": 41670 }, { "epoch": 8.63, "learning_rate": 0.0005863944280125943, "loss": 1.7461, "step": 41675 }, { "epoch": 8.63, "learning_rate": 0.0005862990172693446, "loss": 1.7448, "step": 41680 }, { "epoch": 8.64, "learning_rate": 0.0005862036065260948, "loss": 1.7442, "step": 41685 }, { "epoch": 8.64, "learning_rate": 0.0005861081957828451, "loss": 1.7449, "step": 41690 }, { "epoch": 8.64, "learning_rate": 0.0005860127850395954, "loss": 1.7453, "step": 41695 }, { "epoch": 8.64, "learning_rate": 0.0005859173742963457, "loss": 1.7443, "step": 41700 }, { "epoch": 8.64, "learning_rate": 0.0005858219635530962, "loss": 1.7426, "step": 41705 }, { "epoch": 8.64, "learning_rate": 0.0005857265528098465, "loss": 1.7479, "step": 41710 }, { "epoch": 8.64, "learning_rate": 0.0005856311420665967, "loss": 1.7422, "step": 41715 }, { "epoch": 8.64, "learning_rate": 0.000585535731323347, "loss": 1.7438, "step": 41720 }, { "epoch": 8.64, "learning_rate": 0.0005854403205800973, "loss": 1.7438, "step": 41725 }, { "epoch": 8.65, "learning_rate": 0.0005853449098368476, "loss": 1.7441, "step": 41730 }, { "epoch": 8.65, "learning_rate": 0.000585249499093598, "loss": 1.7438, "step": 41735 }, { "epoch": 8.65, "learning_rate": 0.0005851540883503483, "loss": 1.7506, "step": 41740 }, { "epoch": 8.65, "learning_rate": 0.0005850586776070985, "loss": 1.7411, "step": 41745 }, { "epoch": 8.65, "learning_rate": 0.0005849632668638489, "loss": 1.7451, "step": 41750 }, { "epoch": 8.65, "learning_rate": 0.0005848678561205992, "loss": 1.7438, "step": 41755 }, { "epoch": 8.65, "learning_rate": 0.0005847724453773495, "loss": 1.7446, "step": 41760 }, { "epoch": 8.65, "learning_rate": 0.0005846770346340999, "loss": 1.7438, "step": 41765 }, { "epoch": 8.65, "learning_rate": 0.0005845816238908501, "loss": 1.746, "step": 41770 }, { "epoch": 8.65, "learning_rate": 0.0005844862131476004, "loss": 1.7459, "step": 41775 }, { "epoch": 8.66, "learning_rate": 0.0005843908024043507, "loss": 1.7431, "step": 41780 }, { "epoch": 8.66, "learning_rate": 0.000584295391661101, "loss": 1.7432, "step": 41785 }, { "epoch": 8.66, "learning_rate": 0.0005841999809178513, "loss": 1.743, "step": 41790 }, { "epoch": 8.66, "learning_rate": 0.0005841045701746018, "loss": 1.7411, "step": 41795 }, { "epoch": 8.66, "learning_rate": 0.000584009159431352, "loss": 1.7419, "step": 41800 }, { "epoch": 8.66, "learning_rate": 0.0005839137486881023, "loss": 1.7466, "step": 41805 }, { "epoch": 8.66, "learning_rate": 0.0005838183379448526, "loss": 1.7435, "step": 41810 }, { "epoch": 8.66, "learning_rate": 0.0005837229272016029, "loss": 1.7415, "step": 41815 }, { "epoch": 8.66, "learning_rate": 0.0005836275164583532, "loss": 1.7442, "step": 41820 }, { "epoch": 8.66, "learning_rate": 0.0005835321057151036, "loss": 1.7444, "step": 41825 }, { "epoch": 8.67, "learning_rate": 0.0005834366949718538, "loss": 1.7447, "step": 41830 }, { "epoch": 8.67, "learning_rate": 0.0005833412842286041, "loss": 1.7416, "step": 41835 }, { "epoch": 8.67, "learning_rate": 0.0005832458734853545, "loss": 1.748, "step": 41840 }, { "epoch": 8.67, "learning_rate": 0.0005831504627421048, "loss": 1.7425, "step": 41845 }, { "epoch": 8.67, "learning_rate": 0.0005830550519988552, "loss": 1.7415, "step": 41850 }, { "epoch": 8.67, "learning_rate": 0.0005829596412556054, "loss": 1.742, "step": 41855 }, { "epoch": 8.67, "learning_rate": 0.0005828642305123557, "loss": 1.7399, "step": 41860 }, { "epoch": 8.67, "learning_rate": 0.000582768819769106, "loss": 1.7448, "step": 41865 }, { "epoch": 8.67, "learning_rate": 0.0005826734090258563, "loss": 1.7407, "step": 41870 }, { "epoch": 8.68, "learning_rate": 0.0005825779982826066, "loss": 1.7505, "step": 41875 }, { "epoch": 8.68, "learning_rate": 0.000582482587539357, "loss": 1.7509, "step": 41880 }, { "epoch": 8.68, "learning_rate": 0.0005823871767961072, "loss": 1.7418, "step": 41885 }, { "epoch": 8.68, "learning_rate": 0.0005822917660528576, "loss": 1.7518, "step": 41890 }, { "epoch": 8.68, "learning_rate": 0.0005821963553096079, "loss": 1.7442, "step": 41895 }, { "epoch": 8.68, "learning_rate": 0.0005821009445663582, "loss": 1.7452, "step": 41900 }, { "epoch": 8.68, "learning_rate": 0.0005820055338231085, "loss": 1.7462, "step": 41905 }, { "epoch": 8.68, "learning_rate": 0.0005819101230798588, "loss": 1.7454, "step": 41910 }, { "epoch": 8.68, "learning_rate": 0.0005818147123366091, "loss": 1.7429, "step": 41915 }, { "epoch": 8.68, "learning_rate": 0.0005817193015933594, "loss": 1.7457, "step": 41920 }, { "epoch": 8.69, "learning_rate": 0.0005816238908501097, "loss": 1.7493, "step": 41925 }, { "epoch": 8.69, "learning_rate": 0.00058152848010686, "loss": 1.7448, "step": 41930 }, { "epoch": 8.69, "learning_rate": 0.0005814330693636104, "loss": 1.74, "step": 41935 }, { "epoch": 8.69, "learning_rate": 0.0005813376586203607, "loss": 1.7439, "step": 41940 }, { "epoch": 8.69, "learning_rate": 0.000581242247877111, "loss": 1.7434, "step": 41945 }, { "epoch": 8.69, "learning_rate": 0.0005811468371338613, "loss": 1.7439, "step": 41950 }, { "epoch": 8.69, "learning_rate": 0.0005810514263906116, "loss": 1.7398, "step": 41955 }, { "epoch": 8.69, "learning_rate": 0.0005809560156473619, "loss": 1.7456, "step": 41960 }, { "epoch": 8.69, "learning_rate": 0.0005808606049041121, "loss": 1.7436, "step": 41965 }, { "epoch": 8.69, "learning_rate": 0.0005807651941608625, "loss": 1.7417, "step": 41970 }, { "epoch": 8.7, "learning_rate": 0.0005806697834176128, "loss": 1.748, "step": 41975 }, { "epoch": 8.7, "learning_rate": 0.0005805743726743632, "loss": 1.7456, "step": 41980 }, { "epoch": 8.7, "learning_rate": 0.0005804789619311135, "loss": 1.7427, "step": 41985 }, { "epoch": 8.7, "learning_rate": 0.0005803835511878638, "loss": 1.742, "step": 41990 }, { "epoch": 8.7, "learning_rate": 0.000580288140444614, "loss": 1.7429, "step": 41995 }, { "epoch": 8.7, "learning_rate": 0.0005801927297013644, "loss": 1.7399, "step": 42000 }, { "epoch": 8.7, "eval_accuracy": 0.5415424836601307, "eval_loss": 1.9308457374572754, "eval_runtime": 0.6702, "eval_samples_per_second": 223.823, "eval_steps_per_second": 1.492, "step": 42000 }, { "epoch": 8.7, "learning_rate": 0.0005800973189581147, "loss": 1.7441, "step": 42005 }, { "epoch": 8.7, "learning_rate": 0.000580001908214865, "loss": 1.7444, "step": 42010 }, { "epoch": 8.7, "learning_rate": 0.0005799064974716153, "loss": 1.7394, "step": 42015 }, { "epoch": 8.71, "learning_rate": 0.0005798110867283655, "loss": 1.7395, "step": 42020 }, { "epoch": 8.71, "learning_rate": 0.0005797156759851159, "loss": 1.7484, "step": 42025 }, { "epoch": 8.71, "learning_rate": 0.0005796202652418663, "loss": 1.7447, "step": 42030 }, { "epoch": 8.71, "learning_rate": 0.0005795248544986166, "loss": 1.7442, "step": 42035 }, { "epoch": 8.71, "learning_rate": 0.0005794294437553669, "loss": 1.7473, "step": 42040 }, { "epoch": 8.71, "learning_rate": 0.0005793340330121172, "loss": 1.7456, "step": 42045 }, { "epoch": 8.71, "learning_rate": 0.0005792386222688674, "loss": 1.7404, "step": 42050 }, { "epoch": 8.71, "learning_rate": 0.0005791432115256177, "loss": 1.7459, "step": 42055 }, { "epoch": 8.71, "learning_rate": 0.0005790478007823681, "loss": 1.7435, "step": 42060 }, { "epoch": 8.71, "learning_rate": 0.0005789523900391184, "loss": 1.7417, "step": 42065 }, { "epoch": 8.72, "learning_rate": 0.0005788569792958688, "loss": 1.7467, "step": 42070 }, { "epoch": 8.72, "learning_rate": 0.0005787615685526191, "loss": 1.7474, "step": 42075 }, { "epoch": 8.72, "learning_rate": 0.0005786661578093693, "loss": 1.7475, "step": 42080 }, { "epoch": 8.72, "learning_rate": 0.0005785707470661197, "loss": 1.7453, "step": 42085 }, { "epoch": 8.72, "learning_rate": 0.00057847533632287, "loss": 1.7413, "step": 42090 }, { "epoch": 8.72, "learning_rate": 0.0005783799255796203, "loss": 1.7482, "step": 42095 }, { "epoch": 8.72, "learning_rate": 0.0005782845148363706, "loss": 1.7506, "step": 42100 }, { "epoch": 8.72, "learning_rate": 0.0005781891040931208, "loss": 1.7462, "step": 42105 }, { "epoch": 8.72, "learning_rate": 0.0005780936933498711, "loss": 1.7432, "step": 42110 }, { "epoch": 8.72, "learning_rate": 0.0005779982826066216, "loss": 1.7418, "step": 42115 }, { "epoch": 8.73, "learning_rate": 0.0005779028718633719, "loss": 1.7412, "step": 42120 }, { "epoch": 8.73, "learning_rate": 0.0005778074611201222, "loss": 1.7363, "step": 42125 }, { "epoch": 8.73, "learning_rate": 0.0005777120503768725, "loss": 1.745, "step": 42130 }, { "epoch": 8.73, "learning_rate": 0.0005776166396336227, "loss": 1.7421, "step": 42135 }, { "epoch": 8.73, "learning_rate": 0.000577521228890373, "loss": 1.7427, "step": 42140 }, { "epoch": 8.73, "learning_rate": 0.0005774258181471234, "loss": 1.7485, "step": 42145 }, { "epoch": 8.73, "learning_rate": 0.0005773304074038737, "loss": 1.7438, "step": 42150 }, { "epoch": 8.73, "learning_rate": 0.000577234996660624, "loss": 1.7395, "step": 42155 }, { "epoch": 8.73, "learning_rate": 0.0005771395859173742, "loss": 1.7493, "step": 42160 }, { "epoch": 8.74, "learning_rate": 0.0005770441751741246, "loss": 1.7455, "step": 42165 }, { "epoch": 8.74, "learning_rate": 0.0005769487644308749, "loss": 1.7408, "step": 42170 }, { "epoch": 8.74, "learning_rate": 0.0005768533536876253, "loss": 1.7394, "step": 42175 }, { "epoch": 8.74, "learning_rate": 0.0005767579429443756, "loss": 1.7391, "step": 42180 }, { "epoch": 8.74, "learning_rate": 0.0005766625322011259, "loss": 1.7463, "step": 42185 }, { "epoch": 8.74, "learning_rate": 0.0005765671214578761, "loss": 1.7529, "step": 42190 }, { "epoch": 8.74, "learning_rate": 0.0005764717107146264, "loss": 1.7453, "step": 42195 }, { "epoch": 8.74, "learning_rate": 0.0005763762999713767, "loss": 1.7391, "step": 42200 }, { "epoch": 8.74, "learning_rate": 0.0005762808892281271, "loss": 1.7442, "step": 42205 }, { "epoch": 8.74, "learning_rate": 0.0005761854784848775, "loss": 1.7465, "step": 42210 }, { "epoch": 8.75, "learning_rate": 0.0005760900677416278, "loss": 1.7447, "step": 42215 }, { "epoch": 8.75, "learning_rate": 0.000575994656998378, "loss": 1.7435, "step": 42220 }, { "epoch": 8.75, "learning_rate": 0.0005758992462551283, "loss": 1.7441, "step": 42225 }, { "epoch": 8.75, "learning_rate": 0.0005758038355118786, "loss": 1.7398, "step": 42230 }, { "epoch": 8.75, "learning_rate": 0.000575708424768629, "loss": 1.7463, "step": 42235 }, { "epoch": 8.75, "learning_rate": 0.0005756130140253793, "loss": 1.7447, "step": 42240 }, { "epoch": 8.75, "learning_rate": 0.0005755176032821295, "loss": 1.744, "step": 42245 }, { "epoch": 8.75, "learning_rate": 0.0005754221925388798, "loss": 1.7439, "step": 42250 }, { "epoch": 8.75, "learning_rate": 0.0005753267817956302, "loss": 1.7426, "step": 42255 }, { "epoch": 8.75, "learning_rate": 0.0005752313710523805, "loss": 1.7412, "step": 42260 }, { "epoch": 8.76, "learning_rate": 0.0005751359603091309, "loss": 1.7438, "step": 42265 }, { "epoch": 8.76, "learning_rate": 0.0005750405495658812, "loss": 1.743, "step": 42270 }, { "epoch": 8.76, "learning_rate": 0.0005749451388226314, "loss": 1.744, "step": 42275 }, { "epoch": 8.76, "learning_rate": 0.0005748497280793817, "loss": 1.7449, "step": 42280 }, { "epoch": 8.76, "learning_rate": 0.000574754317336132, "loss": 1.7428, "step": 42285 }, { "epoch": 8.76, "learning_rate": 0.0005746589065928824, "loss": 1.7438, "step": 42290 }, { "epoch": 8.76, "learning_rate": 0.0005745634958496327, "loss": 1.7488, "step": 42295 }, { "epoch": 8.76, "learning_rate": 0.0005744680851063831, "loss": 1.7472, "step": 42300 }, { "epoch": 8.76, "learning_rate": 0.0005743726743631333, "loss": 1.7413, "step": 42305 }, { "epoch": 8.77, "learning_rate": 0.0005742772636198836, "loss": 1.7445, "step": 42310 }, { "epoch": 8.77, "learning_rate": 0.0005741818528766339, "loss": 1.7427, "step": 42315 }, { "epoch": 8.77, "learning_rate": 0.0005740864421333843, "loss": 1.7424, "step": 42320 }, { "epoch": 8.77, "learning_rate": 0.0005739910313901346, "loss": 1.7433, "step": 42325 }, { "epoch": 8.77, "learning_rate": 0.0005738956206468848, "loss": 1.7447, "step": 42330 }, { "epoch": 8.77, "learning_rate": 0.0005738002099036351, "loss": 1.7394, "step": 42335 }, { "epoch": 8.77, "learning_rate": 0.0005737047991603854, "loss": 1.7431, "step": 42340 }, { "epoch": 8.77, "learning_rate": 0.0005736093884171358, "loss": 1.7417, "step": 42345 }, { "epoch": 8.77, "learning_rate": 0.0005735139776738862, "loss": 1.7398, "step": 42350 }, { "epoch": 8.77, "learning_rate": 0.0005734185669306365, "loss": 1.7448, "step": 42355 }, { "epoch": 8.78, "learning_rate": 0.0005733231561873867, "loss": 1.7418, "step": 42360 }, { "epoch": 8.78, "learning_rate": 0.000573227745444137, "loss": 1.7439, "step": 42365 }, { "epoch": 8.78, "learning_rate": 0.0005731323347008873, "loss": 1.7419, "step": 42370 }, { "epoch": 8.78, "learning_rate": 0.0005730369239576376, "loss": 1.752, "step": 42375 }, { "epoch": 8.78, "learning_rate": 0.000572941513214388, "loss": 1.7416, "step": 42380 }, { "epoch": 8.78, "learning_rate": 0.0005728461024711382, "loss": 1.7472, "step": 42385 }, { "epoch": 8.78, "learning_rate": 0.0005727506917278885, "loss": 1.7424, "step": 42390 }, { "epoch": 8.78, "learning_rate": 0.0005726552809846389, "loss": 1.745, "step": 42395 }, { "epoch": 8.78, "learning_rate": 0.0005725598702413892, "loss": 1.7416, "step": 42400 }, { "epoch": 8.78, "learning_rate": 0.0005724644594981395, "loss": 1.7469, "step": 42405 }, { "epoch": 8.79, "learning_rate": 0.0005723690487548899, "loss": 1.7433, "step": 42410 }, { "epoch": 8.79, "learning_rate": 0.0005722736380116401, "loss": 1.7466, "step": 42415 }, { "epoch": 8.79, "learning_rate": 0.0005721782272683904, "loss": 1.7448, "step": 42420 }, { "epoch": 8.79, "learning_rate": 0.0005720828165251407, "loss": 1.7471, "step": 42425 }, { "epoch": 8.79, "learning_rate": 0.000571987405781891, "loss": 1.7469, "step": 42430 }, { "epoch": 8.79, "learning_rate": 0.0005718919950386413, "loss": 1.7429, "step": 42435 }, { "epoch": 8.79, "learning_rate": 0.0005717965842953918, "loss": 1.7466, "step": 42440 }, { "epoch": 8.79, "learning_rate": 0.000571701173552142, "loss": 1.7426, "step": 42445 }, { "epoch": 8.79, "learning_rate": 0.0005716057628088923, "loss": 1.7404, "step": 42450 }, { "epoch": 8.8, "learning_rate": 0.0005715103520656426, "loss": 1.7431, "step": 42455 }, { "epoch": 8.8, "learning_rate": 0.0005714149413223929, "loss": 1.7473, "step": 42460 }, { "epoch": 8.8, "learning_rate": 0.0005713195305791432, "loss": 1.743, "step": 42465 }, { "epoch": 8.8, "learning_rate": 0.0005712241198358935, "loss": 1.7465, "step": 42470 }, { "epoch": 8.8, "learning_rate": 0.0005711287090926438, "loss": 1.7463, "step": 42475 }, { "epoch": 8.8, "learning_rate": 0.0005710332983493941, "loss": 1.7375, "step": 42480 }, { "epoch": 8.8, "learning_rate": 0.0005709378876061445, "loss": 1.743, "step": 42485 }, { "epoch": 8.8, "learning_rate": 0.0005708424768628948, "loss": 1.7415, "step": 42490 }, { "epoch": 8.8, "learning_rate": 0.0005707470661196452, "loss": 1.7442, "step": 42495 }, { "epoch": 8.8, "learning_rate": 0.0005706516553763954, "loss": 1.7425, "step": 42500 }, { "epoch": 8.81, "learning_rate": 0.0005705562446331457, "loss": 1.7397, "step": 42505 }, { "epoch": 8.81, "learning_rate": 0.000570460833889896, "loss": 1.739, "step": 42510 }, { "epoch": 8.81, "learning_rate": 0.0005703654231466463, "loss": 1.7436, "step": 42515 }, { "epoch": 8.81, "learning_rate": 0.0005702700124033966, "loss": 1.7451, "step": 42520 }, { "epoch": 8.81, "learning_rate": 0.000570174601660147, "loss": 1.7463, "step": 42525 }, { "epoch": 8.81, "learning_rate": 0.0005700791909168973, "loss": 1.7361, "step": 42530 }, { "epoch": 8.81, "learning_rate": 0.0005699837801736476, "loss": 1.7467, "step": 42535 }, { "epoch": 8.81, "learning_rate": 0.0005698883694303979, "loss": 1.7415, "step": 42540 }, { "epoch": 8.81, "learning_rate": 0.0005697929586871482, "loss": 1.7423, "step": 42545 }, { "epoch": 8.81, "learning_rate": 0.0005696975479438985, "loss": 1.7435, "step": 42550 }, { "epoch": 8.82, "learning_rate": 0.0005696021372006488, "loss": 1.7469, "step": 42555 }, { "epoch": 8.82, "learning_rate": 0.0005695067264573991, "loss": 1.7489, "step": 42560 }, { "epoch": 8.82, "learning_rate": 0.0005694113157141494, "loss": 1.7464, "step": 42565 }, { "epoch": 8.82, "learning_rate": 0.0005693159049708997, "loss": 1.7403, "step": 42570 }, { "epoch": 8.82, "learning_rate": 0.0005692204942276501, "loss": 1.74, "step": 42575 }, { "epoch": 8.82, "learning_rate": 0.0005691250834844004, "loss": 1.746, "step": 42580 }, { "epoch": 8.82, "learning_rate": 0.0005690296727411507, "loss": 1.7436, "step": 42585 }, { "epoch": 8.82, "learning_rate": 0.000568934261997901, "loss": 1.745, "step": 42590 }, { "epoch": 8.82, "learning_rate": 0.0005688388512546513, "loss": 1.7451, "step": 42595 }, { "epoch": 8.83, "learning_rate": 0.0005687434405114016, "loss": 1.7455, "step": 42600 }, { "epoch": 8.83, "learning_rate": 0.0005686480297681519, "loss": 1.7473, "step": 42605 }, { "epoch": 8.83, "learning_rate": 0.0005685526190249021, "loss": 1.7443, "step": 42610 }, { "epoch": 8.83, "learning_rate": 0.0005684572082816525, "loss": 1.7426, "step": 42615 }, { "epoch": 8.83, "learning_rate": 0.0005683617975384028, "loss": 1.7422, "step": 42620 }, { "epoch": 8.83, "learning_rate": 0.0005682663867951532, "loss": 1.7394, "step": 42625 }, { "epoch": 8.83, "learning_rate": 0.0005681709760519035, "loss": 1.7451, "step": 42630 }, { "epoch": 8.83, "learning_rate": 0.0005680755653086538, "loss": 1.7442, "step": 42635 }, { "epoch": 8.83, "learning_rate": 0.000567980154565404, "loss": 1.7448, "step": 42640 }, { "epoch": 8.83, "learning_rate": 0.0005678847438221544, "loss": 1.7452, "step": 42645 }, { "epoch": 8.84, "learning_rate": 0.0005677893330789047, "loss": 1.7428, "step": 42650 }, { "epoch": 8.84, "learning_rate": 0.000567693922335655, "loss": 1.7402, "step": 42655 }, { "epoch": 8.84, "learning_rate": 0.0005675985115924053, "loss": 1.7423, "step": 42660 }, { "epoch": 8.84, "learning_rate": 0.0005675031008491555, "loss": 1.7392, "step": 42665 }, { "epoch": 8.84, "learning_rate": 0.0005674076901059059, "loss": 1.7506, "step": 42670 }, { "epoch": 8.84, "learning_rate": 0.0005673122793626563, "loss": 1.748, "step": 42675 }, { "epoch": 8.84, "learning_rate": 0.0005672168686194066, "loss": 1.7397, "step": 42680 }, { "epoch": 8.84, "learning_rate": 0.0005671214578761569, "loss": 1.7421, "step": 42685 }, { "epoch": 8.84, "learning_rate": 0.0005670260471329072, "loss": 1.7496, "step": 42690 }, { "epoch": 8.85, "learning_rate": 0.0005669306363896574, "loss": 1.7435, "step": 42695 }, { "epoch": 8.85, "learning_rate": 0.0005668352256464077, "loss": 1.7454, "step": 42700 }, { "epoch": 8.85, "learning_rate": 0.0005667398149031581, "loss": 1.7394, "step": 42705 }, { "epoch": 8.85, "learning_rate": 0.0005666444041599084, "loss": 1.7465, "step": 42710 }, { "epoch": 8.85, "learning_rate": 0.0005665489934166588, "loss": 1.7461, "step": 42715 }, { "epoch": 8.85, "learning_rate": 0.000566453582673409, "loss": 1.7428, "step": 42720 }, { "epoch": 8.85, "learning_rate": 0.0005663581719301593, "loss": 1.7453, "step": 42725 }, { "epoch": 8.85, "learning_rate": 0.0005662627611869097, "loss": 1.7415, "step": 42730 }, { "epoch": 8.85, "learning_rate": 0.00056616735044366, "loss": 1.7412, "step": 42735 }, { "epoch": 8.85, "learning_rate": 0.0005660719397004103, "loss": 1.7473, "step": 42740 }, { "epoch": 8.86, "learning_rate": 0.0005659765289571606, "loss": 1.7449, "step": 42745 }, { "epoch": 8.86, "learning_rate": 0.0005658811182139108, "loss": 1.7415, "step": 42750 }, { "epoch": 8.86, "learning_rate": 0.0005657857074706611, "loss": 1.7414, "step": 42755 }, { "epoch": 8.86, "learning_rate": 0.0005656902967274116, "loss": 1.7427, "step": 42760 }, { "epoch": 8.86, "learning_rate": 0.0005655948859841619, "loss": 1.7465, "step": 42765 }, { "epoch": 8.86, "learning_rate": 0.0005654994752409122, "loss": 1.7447, "step": 42770 }, { "epoch": 8.86, "learning_rate": 0.0005654040644976625, "loss": 1.7466, "step": 42775 }, { "epoch": 8.86, "learning_rate": 0.0005653086537544127, "loss": 1.7421, "step": 42780 }, { "epoch": 8.86, "learning_rate": 0.000565213243011163, "loss": 1.7421, "step": 42785 }, { "epoch": 8.86, "learning_rate": 0.0005651178322679134, "loss": 1.7417, "step": 42790 }, { "epoch": 8.87, "learning_rate": 0.0005650224215246637, "loss": 1.7376, "step": 42795 }, { "epoch": 8.87, "learning_rate": 0.000564927010781414, "loss": 1.741, "step": 42800 }, { "epoch": 8.87, "learning_rate": 0.0005648316000381644, "loss": 1.7456, "step": 42805 }, { "epoch": 8.87, "learning_rate": 0.0005647361892949146, "loss": 1.7406, "step": 42810 }, { "epoch": 8.87, "learning_rate": 0.0005646407785516649, "loss": 1.7403, "step": 42815 }, { "epoch": 8.87, "learning_rate": 0.0005645453678084153, "loss": 1.7447, "step": 42820 }, { "epoch": 8.87, "learning_rate": 0.0005644499570651656, "loss": 1.7454, "step": 42825 }, { "epoch": 8.87, "learning_rate": 0.0005643545463219159, "loss": 1.7379, "step": 42830 }, { "epoch": 8.87, "learning_rate": 0.0005642591355786661, "loss": 1.7393, "step": 42835 }, { "epoch": 8.88, "learning_rate": 0.0005641637248354164, "loss": 1.7416, "step": 42840 }, { "epoch": 8.88, "learning_rate": 0.0005640683140921667, "loss": 1.7416, "step": 42845 }, { "epoch": 8.88, "learning_rate": 0.0005639729033489172, "loss": 1.7413, "step": 42850 }, { "epoch": 8.88, "learning_rate": 0.0005638774926056675, "loss": 1.7422, "step": 42855 }, { "epoch": 8.88, "learning_rate": 0.0005637820818624178, "loss": 1.74, "step": 42860 }, { "epoch": 8.88, "learning_rate": 0.000563686671119168, "loss": 1.7387, "step": 42865 }, { "epoch": 8.88, "learning_rate": 0.0005635912603759183, "loss": 1.7437, "step": 42870 }, { "epoch": 8.88, "learning_rate": 0.0005634958496326686, "loss": 1.7427, "step": 42875 }, { "epoch": 8.88, "learning_rate": 0.000563400438889419, "loss": 1.7422, "step": 42880 }, { "epoch": 8.88, "learning_rate": 0.0005633050281461693, "loss": 1.7416, "step": 42885 }, { "epoch": 8.89, "learning_rate": 0.0005632096174029195, "loss": 1.7447, "step": 42890 }, { "epoch": 8.89, "learning_rate": 0.0005631142066596698, "loss": 1.7425, "step": 42895 }, { "epoch": 8.89, "learning_rate": 0.0005630187959164202, "loss": 1.7425, "step": 42900 }, { "epoch": 8.89, "learning_rate": 0.0005629233851731706, "loss": 1.7397, "step": 42905 }, { "epoch": 8.89, "learning_rate": 0.0005628279744299209, "loss": 1.7438, "step": 42910 }, { "epoch": 8.89, "learning_rate": 0.0005627325636866712, "loss": 1.7456, "step": 42915 }, { "epoch": 8.89, "learning_rate": 0.0005626371529434214, "loss": 1.7447, "step": 42920 }, { "epoch": 8.89, "learning_rate": 0.0005625417422001717, "loss": 1.7395, "step": 42925 }, { "epoch": 8.89, "learning_rate": 0.000562446331456922, "loss": 1.7459, "step": 42930 }, { "epoch": 8.89, "learning_rate": 0.0005623509207136724, "loss": 1.7429, "step": 42935 }, { "epoch": 8.9, "learning_rate": 0.0005622555099704227, "loss": 1.7438, "step": 42940 }, { "epoch": 8.9, "learning_rate": 0.000562160099227173, "loss": 1.7439, "step": 42945 }, { "epoch": 8.9, "learning_rate": 0.0005620646884839233, "loss": 1.7406, "step": 42950 }, { "epoch": 8.9, "learning_rate": 0.0005619692777406736, "loss": 1.7468, "step": 42955 }, { "epoch": 8.9, "learning_rate": 0.0005618738669974239, "loss": 1.742, "step": 42960 }, { "epoch": 8.9, "learning_rate": 0.0005617784562541743, "loss": 1.745, "step": 42965 }, { "epoch": 8.9, "learning_rate": 0.0005616830455109246, "loss": 1.7452, "step": 42970 }, { "epoch": 8.9, "learning_rate": 0.0005615876347676748, "loss": 1.7372, "step": 42975 }, { "epoch": 8.9, "learning_rate": 0.0005614922240244251, "loss": 1.7405, "step": 42980 }, { "epoch": 8.91, "learning_rate": 0.0005613968132811754, "loss": 1.7382, "step": 42985 }, { "epoch": 8.91, "learning_rate": 0.0005613014025379258, "loss": 1.7435, "step": 42990 }, { "epoch": 8.91, "learning_rate": 0.0005612059917946762, "loss": 1.7414, "step": 42995 }, { "epoch": 8.91, "learning_rate": 0.0005611105810514265, "loss": 1.7427, "step": 43000 }, { "epoch": 8.91, "learning_rate": 0.0005610151703081767, "loss": 1.7428, "step": 43005 }, { "epoch": 8.91, "learning_rate": 0.000560919759564927, "loss": 1.7437, "step": 43010 }, { "epoch": 8.91, "learning_rate": 0.0005608243488216773, "loss": 1.7447, "step": 43015 }, { "epoch": 8.91, "learning_rate": 0.0005607289380784276, "loss": 1.7418, "step": 43020 }, { "epoch": 8.91, "learning_rate": 0.000560633527335178, "loss": 1.7391, "step": 43025 }, { "epoch": 8.91, "learning_rate": 0.0005605381165919282, "loss": 1.744, "step": 43030 }, { "epoch": 8.92, "learning_rate": 0.0005604427058486786, "loss": 1.7403, "step": 43035 }, { "epoch": 8.92, "learning_rate": 0.0005603472951054289, "loss": 1.7455, "step": 43040 }, { "epoch": 8.92, "learning_rate": 0.0005602518843621792, "loss": 1.743, "step": 43045 }, { "epoch": 8.92, "learning_rate": 0.0005601564736189295, "loss": 1.7454, "step": 43050 }, { "epoch": 8.92, "learning_rate": 0.0005600610628756799, "loss": 1.747, "step": 43055 }, { "epoch": 8.92, "learning_rate": 0.0005599656521324301, "loss": 1.7466, "step": 43060 }, { "epoch": 8.92, "learning_rate": 0.0005598702413891804, "loss": 1.7414, "step": 43065 }, { "epoch": 8.92, "learning_rate": 0.0005597748306459307, "loss": 1.7372, "step": 43070 }, { "epoch": 8.92, "learning_rate": 0.000559679419902681, "loss": 1.7418, "step": 43075 }, { "epoch": 8.92, "learning_rate": 0.0005595840091594314, "loss": 1.7435, "step": 43080 }, { "epoch": 8.93, "learning_rate": 0.0005594885984161818, "loss": 1.7433, "step": 43085 }, { "epoch": 8.93, "learning_rate": 0.000559393187672932, "loss": 1.7469, "step": 43090 }, { "epoch": 8.93, "learning_rate": 0.0005592977769296823, "loss": 1.7473, "step": 43095 }, { "epoch": 8.93, "learning_rate": 0.0005592023661864326, "loss": 1.7464, "step": 43100 }, { "epoch": 8.93, "learning_rate": 0.0005591069554431829, "loss": 1.7468, "step": 43105 }, { "epoch": 8.93, "learning_rate": 0.0005590115446999332, "loss": 1.7431, "step": 43110 }, { "epoch": 8.93, "learning_rate": 0.0005589161339566835, "loss": 1.7428, "step": 43115 }, { "epoch": 8.93, "learning_rate": 0.0005588207232134338, "loss": 1.7389, "step": 43120 }, { "epoch": 8.93, "learning_rate": 0.0005587253124701841, "loss": 1.7426, "step": 43125 }, { "epoch": 8.94, "learning_rate": 0.0005586299017269345, "loss": 1.74, "step": 43130 }, { "epoch": 8.94, "learning_rate": 0.0005585344909836848, "loss": 1.7379, "step": 43135 }, { "epoch": 8.94, "learning_rate": 0.0005584390802404352, "loss": 1.7454, "step": 43140 }, { "epoch": 8.94, "learning_rate": 0.0005583436694971854, "loss": 1.7434, "step": 43145 }, { "epoch": 8.94, "learning_rate": 0.0005582482587539357, "loss": 1.7395, "step": 43150 }, { "epoch": 8.94, "learning_rate": 0.000558152848010686, "loss": 1.742, "step": 43155 }, { "epoch": 8.94, "learning_rate": 0.0005580574372674363, "loss": 1.7439, "step": 43160 }, { "epoch": 8.94, "learning_rate": 0.0005579620265241866, "loss": 1.7428, "step": 43165 }, { "epoch": 8.94, "learning_rate": 0.0005578666157809369, "loss": 1.7393, "step": 43170 }, { "epoch": 8.94, "learning_rate": 0.0005577712050376873, "loss": 1.7434, "step": 43175 }, { "epoch": 8.95, "learning_rate": 0.0005576757942944376, "loss": 1.742, "step": 43180 }, { "epoch": 8.95, "learning_rate": 0.0005575803835511879, "loss": 1.7404, "step": 43185 }, { "epoch": 8.95, "learning_rate": 0.0005574849728079382, "loss": 1.7406, "step": 43190 }, { "epoch": 8.95, "learning_rate": 0.0005573895620646885, "loss": 1.7396, "step": 43195 }, { "epoch": 8.95, "learning_rate": 0.0005572941513214388, "loss": 1.7419, "step": 43200 }, { "epoch": 8.95, "learning_rate": 0.0005571987405781891, "loss": 1.7439, "step": 43205 }, { "epoch": 8.95, "learning_rate": 0.0005571033298349394, "loss": 1.7443, "step": 43210 }, { "epoch": 8.95, "learning_rate": 0.0005570079190916897, "loss": 1.7445, "step": 43215 }, { "epoch": 8.95, "learning_rate": 0.0005569125083484401, "loss": 1.7407, "step": 43220 }, { "epoch": 8.95, "learning_rate": 0.0005568170976051903, "loss": 1.7497, "step": 43225 }, { "epoch": 8.96, "learning_rate": 0.0005567216868619407, "loss": 1.743, "step": 43230 }, { "epoch": 8.96, "learning_rate": 0.000556626276118691, "loss": 1.7454, "step": 43235 }, { "epoch": 8.96, "learning_rate": 0.0005565308653754413, "loss": 1.747, "step": 43240 }, { "epoch": 8.96, "learning_rate": 0.0005564354546321916, "loss": 1.7481, "step": 43245 }, { "epoch": 8.96, "learning_rate": 0.0005563400438889419, "loss": 1.7426, "step": 43250 }, { "epoch": 8.96, "learning_rate": 0.0005562446331456921, "loss": 1.7396, "step": 43255 }, { "epoch": 8.96, "learning_rate": 0.0005561492224024425, "loss": 1.7436, "step": 43260 }, { "epoch": 8.96, "learning_rate": 0.0005560538116591929, "loss": 1.7415, "step": 43265 }, { "epoch": 8.96, "learning_rate": 0.0005559584009159432, "loss": 1.7408, "step": 43270 }, { "epoch": 8.97, "learning_rate": 0.0005558629901726935, "loss": 1.7376, "step": 43275 }, { "epoch": 8.97, "learning_rate": 0.0005557675794294437, "loss": 1.7409, "step": 43280 }, { "epoch": 8.97, "learning_rate": 0.000555672168686194, "loss": 1.7405, "step": 43285 }, { "epoch": 8.97, "learning_rate": 0.0005555767579429444, "loss": 1.7414, "step": 43290 }, { "epoch": 8.97, "learning_rate": 0.0005554813471996947, "loss": 1.7399, "step": 43295 }, { "epoch": 8.97, "learning_rate": 0.000555385936456445, "loss": 1.7383, "step": 43300 }, { "epoch": 8.97, "learning_rate": 0.0005552905257131953, "loss": 1.7446, "step": 43305 }, { "epoch": 8.97, "learning_rate": 0.0005551951149699456, "loss": 1.7428, "step": 43310 }, { "epoch": 8.97, "learning_rate": 0.0005550997042266959, "loss": 1.7374, "step": 43315 }, { "epoch": 8.97, "learning_rate": 0.0005550042934834463, "loss": 1.7434, "step": 43320 }, { "epoch": 8.98, "learning_rate": 0.0005549088827401966, "loss": 1.7419, "step": 43325 }, { "epoch": 8.98, "learning_rate": 0.0005548134719969469, "loss": 1.7438, "step": 43330 }, { "epoch": 8.98, "learning_rate": 0.0005547180612536972, "loss": 1.7418, "step": 43335 }, { "epoch": 8.98, "learning_rate": 0.0005546226505104474, "loss": 1.7455, "step": 43340 }, { "epoch": 8.98, "learning_rate": 0.0005545272397671977, "loss": 1.742, "step": 43345 }, { "epoch": 8.98, "learning_rate": 0.0005544318290239481, "loss": 1.7399, "step": 43350 }, { "epoch": 8.98, "learning_rate": 0.0005543364182806985, "loss": 1.7437, "step": 43355 }, { "epoch": 8.98, "learning_rate": 0.0005542410075374488, "loss": 1.7412, "step": 43360 }, { "epoch": 8.98, "learning_rate": 0.000554145596794199, "loss": 1.7431, "step": 43365 }, { "epoch": 8.98, "learning_rate": 0.0005540501860509493, "loss": 1.7443, "step": 43370 }, { "epoch": 8.99, "learning_rate": 0.0005539547753076997, "loss": 1.7376, "step": 43375 }, { "epoch": 8.99, "learning_rate": 0.00055385936456445, "loss": 1.7377, "step": 43380 }, { "epoch": 8.99, "learning_rate": 0.0005537639538212003, "loss": 1.7447, "step": 43385 }, { "epoch": 8.99, "learning_rate": 0.0005536685430779506, "loss": 1.7424, "step": 43390 }, { "epoch": 8.99, "learning_rate": 0.0005535731323347008, "loss": 1.747, "step": 43395 }, { "epoch": 8.99, "learning_rate": 0.0005534777215914511, "loss": 1.745, "step": 43400 }, { "epoch": 8.99, "learning_rate": 0.0005533823108482016, "loss": 1.744, "step": 43405 }, { "epoch": 8.99, "learning_rate": 0.0005532869001049519, "loss": 1.7396, "step": 43410 }, { "epoch": 8.99, "learning_rate": 0.0005531914893617022, "loss": 1.7469, "step": 43415 }, { "epoch": 9.0, "learning_rate": 0.0005530960786184525, "loss": 1.7396, "step": 43420 }, { "epoch": 9.0, "learning_rate": 0.0005530006678752027, "loss": 1.7403, "step": 43425 }, { "epoch": 9.0, "learning_rate": 0.000552905257131953, "loss": 1.7431, "step": 43430 }, { "epoch": 9.0, "learning_rate": 0.0005528098463887034, "loss": 1.7459, "step": 43435 }, { "epoch": 9.0, "learning_rate": 0.0005527144356454537, "loss": 1.7398, "step": 43440 }, { "epoch": 9.0, "learning_rate": 0.000552619024902204, "loss": 1.7401, "step": 43445 }, { "epoch": 9.0, "learning_rate": 0.0005525236141589543, "loss": 1.7339, "step": 43450 }, { "epoch": 9.0, "learning_rate": 0.0005524282034157046, "loss": 1.7328, "step": 43455 }, { "epoch": 9.0, "learning_rate": 0.0005523327926724549, "loss": 1.732, "step": 43460 }, { "epoch": 9.0, "learning_rate": 0.0005522373819292053, "loss": 1.7354, "step": 43465 }, { "epoch": 9.01, "learning_rate": 0.0005521419711859556, "loss": 1.7332, "step": 43470 }, { "epoch": 9.01, "learning_rate": 0.0005520465604427059, "loss": 1.73, "step": 43475 }, { "epoch": 9.01, "learning_rate": 0.0005519511496994561, "loss": 1.7339, "step": 43480 }, { "epoch": 9.01, "learning_rate": 0.0005518557389562064, "loss": 1.7307, "step": 43485 }, { "epoch": 9.01, "learning_rate": 0.0005517603282129567, "loss": 1.7316, "step": 43490 }, { "epoch": 9.01, "learning_rate": 0.0005516649174697072, "loss": 1.7393, "step": 43495 }, { "epoch": 9.01, "learning_rate": 0.0005515695067264575, "loss": 1.7364, "step": 43500 }, { "epoch": 9.01, "learning_rate": 0.0005514740959832077, "loss": 1.7324, "step": 43505 }, { "epoch": 9.01, "learning_rate": 0.000551378685239958, "loss": 1.7368, "step": 43510 }, { "epoch": 9.01, "learning_rate": 0.0005512832744967083, "loss": 1.7361, "step": 43515 }, { "epoch": 9.02, "learning_rate": 0.0005511878637534586, "loss": 1.7324, "step": 43520 }, { "epoch": 9.02, "learning_rate": 0.000551092453010209, "loss": 1.7306, "step": 43525 }, { "epoch": 9.02, "learning_rate": 0.0005509970422669593, "loss": 1.7325, "step": 43530 }, { "epoch": 9.02, "learning_rate": 0.0005509016315237095, "loss": 1.7338, "step": 43535 }, { "epoch": 9.02, "learning_rate": 0.0005508062207804599, "loss": 1.7326, "step": 43540 }, { "epoch": 9.02, "learning_rate": 0.0005507108100372102, "loss": 1.7328, "step": 43545 }, { "epoch": 9.02, "learning_rate": 0.0005506153992939606, "loss": 1.7314, "step": 43550 }, { "epoch": 9.02, "learning_rate": 0.0005505199885507109, "loss": 1.7273, "step": 43555 }, { "epoch": 9.02, "learning_rate": 0.0005504245778074612, "loss": 1.7333, "step": 43560 }, { "epoch": 9.03, "learning_rate": 0.0005503291670642114, "loss": 1.7327, "step": 43565 }, { "epoch": 9.03, "learning_rate": 0.0005502337563209617, "loss": 1.7304, "step": 43570 }, { "epoch": 9.03, "learning_rate": 0.000550138345577712, "loss": 1.7339, "step": 43575 }, { "epoch": 9.03, "learning_rate": 0.0005500429348344624, "loss": 1.7333, "step": 43580 }, { "epoch": 9.03, "learning_rate": 0.0005499475240912128, "loss": 1.7305, "step": 43585 }, { "epoch": 9.03, "learning_rate": 0.000549852113347963, "loss": 1.735, "step": 43590 }, { "epoch": 9.03, "learning_rate": 0.0005497567026047133, "loss": 1.7277, "step": 43595 }, { "epoch": 9.03, "learning_rate": 0.0005496612918614636, "loss": 1.732, "step": 43600 }, { "epoch": 9.03, "learning_rate": 0.0005495658811182139, "loss": 1.7355, "step": 43605 }, { "epoch": 9.03, "learning_rate": 0.0005494704703749643, "loss": 1.7305, "step": 43610 }, { "epoch": 9.04, "learning_rate": 0.0005493750596317146, "loss": 1.7318, "step": 43615 }, { "epoch": 9.04, "learning_rate": 0.0005492796488884648, "loss": 1.7347, "step": 43620 }, { "epoch": 9.04, "learning_rate": 0.0005491842381452151, "loss": 1.7309, "step": 43625 }, { "epoch": 9.04, "learning_rate": 0.0005490888274019654, "loss": 1.7315, "step": 43630 }, { "epoch": 9.04, "learning_rate": 0.0005489934166587158, "loss": 1.7322, "step": 43635 }, { "epoch": 9.04, "learning_rate": 0.0005488980059154662, "loss": 1.7333, "step": 43640 }, { "epoch": 9.04, "learning_rate": 0.0005488025951722165, "loss": 1.7335, "step": 43645 }, { "epoch": 9.04, "learning_rate": 0.0005487071844289667, "loss": 1.7375, "step": 43650 }, { "epoch": 9.04, "learning_rate": 0.000548611773685717, "loss": 1.7292, "step": 43655 }, { "epoch": 9.04, "learning_rate": 0.0005485163629424673, "loss": 1.7335, "step": 43660 }, { "epoch": 9.05, "learning_rate": 0.0005484209521992176, "loss": 1.7347, "step": 43665 }, { "epoch": 9.05, "learning_rate": 0.000548325541455968, "loss": 1.7322, "step": 43670 }, { "epoch": 9.05, "learning_rate": 0.0005482301307127182, "loss": 1.7345, "step": 43675 }, { "epoch": 9.05, "learning_rate": 0.0005481347199694686, "loss": 1.7321, "step": 43680 }, { "epoch": 9.05, "learning_rate": 0.0005480393092262189, "loss": 1.7352, "step": 43685 }, { "epoch": 9.05, "learning_rate": 0.0005479438984829692, "loss": 1.7353, "step": 43690 }, { "epoch": 9.05, "learning_rate": 0.0005478484877397195, "loss": 1.7316, "step": 43695 }, { "epoch": 9.05, "learning_rate": 0.0005477530769964699, "loss": 1.7361, "step": 43700 }, { "epoch": 9.05, "learning_rate": 0.0005476576662532201, "loss": 1.7345, "step": 43705 }, { "epoch": 9.06, "learning_rate": 0.0005475622555099704, "loss": 1.7371, "step": 43710 }, { "epoch": 9.06, "learning_rate": 0.0005474668447667207, "loss": 1.7304, "step": 43715 }, { "epoch": 9.06, "learning_rate": 0.000547371434023471, "loss": 1.7312, "step": 43720 }, { "epoch": 9.06, "learning_rate": 0.0005472760232802214, "loss": 1.7311, "step": 43725 }, { "epoch": 9.06, "learning_rate": 0.0005471806125369717, "loss": 1.7367, "step": 43730 }, { "epoch": 9.06, "learning_rate": 0.000547085201793722, "loss": 1.7359, "step": 43735 }, { "epoch": 9.06, "learning_rate": 0.0005469897910504723, "loss": 1.7317, "step": 43740 }, { "epoch": 9.06, "learning_rate": 0.0005468943803072226, "loss": 1.7336, "step": 43745 }, { "epoch": 9.06, "learning_rate": 0.0005467989695639729, "loss": 1.7318, "step": 43750 }, { "epoch": 9.06, "learning_rate": 0.0005467035588207231, "loss": 1.7372, "step": 43755 }, { "epoch": 9.07, "learning_rate": 0.0005466081480774735, "loss": 1.732, "step": 43760 }, { "epoch": 9.07, "learning_rate": 0.0005465127373342238, "loss": 1.7327, "step": 43765 }, { "epoch": 9.07, "learning_rate": 0.0005464173265909742, "loss": 1.7365, "step": 43770 }, { "epoch": 9.07, "learning_rate": 0.0005463219158477245, "loss": 1.7352, "step": 43775 }, { "epoch": 9.07, "learning_rate": 0.0005462265051044748, "loss": 1.7399, "step": 43780 }, { "epoch": 9.07, "learning_rate": 0.0005461310943612252, "loss": 1.7372, "step": 43785 }, { "epoch": 9.07, "learning_rate": 0.0005460356836179754, "loss": 1.7326, "step": 43790 }, { "epoch": 9.07, "learning_rate": 0.0005459402728747257, "loss": 1.733, "step": 43795 }, { "epoch": 9.07, "learning_rate": 0.000545844862131476, "loss": 1.7293, "step": 43800 }, { "epoch": 9.07, "learning_rate": 0.0005457494513882263, "loss": 1.7307, "step": 43805 }, { "epoch": 9.08, "learning_rate": 0.0005456540406449766, "loss": 1.7361, "step": 43810 }, { "epoch": 9.08, "learning_rate": 0.000545558629901727, "loss": 1.7395, "step": 43815 }, { "epoch": 9.08, "learning_rate": 0.0005454632191584773, "loss": 1.7313, "step": 43820 }, { "epoch": 9.08, "learning_rate": 0.0005453678084152276, "loss": 1.733, "step": 43825 }, { "epoch": 9.08, "learning_rate": 0.0005452723976719779, "loss": 1.7368, "step": 43830 }, { "epoch": 9.08, "learning_rate": 0.0005451769869287282, "loss": 1.7334, "step": 43835 }, { "epoch": 9.08, "learning_rate": 0.0005450815761854784, "loss": 1.7345, "step": 43840 }, { "epoch": 9.08, "learning_rate": 0.0005449861654422288, "loss": 1.7348, "step": 43845 }, { "epoch": 9.08, "learning_rate": 0.0005448907546989791, "loss": 1.7289, "step": 43850 }, { "epoch": 9.09, "learning_rate": 0.0005447953439557294, "loss": 1.734, "step": 43855 }, { "epoch": 9.09, "learning_rate": 0.0005446999332124797, "loss": 1.7374, "step": 43860 }, { "epoch": 9.09, "learning_rate": 0.0005446045224692301, "loss": 1.7357, "step": 43865 }, { "epoch": 9.09, "learning_rate": 0.0005445091117259803, "loss": 1.735, "step": 43870 }, { "epoch": 9.09, "learning_rate": 0.0005444137009827307, "loss": 1.7361, "step": 43875 }, { "epoch": 9.09, "learning_rate": 0.000544318290239481, "loss": 1.7412, "step": 43880 }, { "epoch": 9.09, "learning_rate": 0.0005442228794962313, "loss": 1.7393, "step": 43885 }, { "epoch": 9.09, "learning_rate": 0.0005441274687529816, "loss": 1.7419, "step": 43890 }, { "epoch": 9.09, "learning_rate": 0.0005440320580097318, "loss": 1.7394, "step": 43895 }, { "epoch": 9.09, "learning_rate": 0.0005439366472664821, "loss": 1.734, "step": 43900 }, { "epoch": 9.1, "learning_rate": 0.0005438412365232325, "loss": 1.7399, "step": 43905 }, { "epoch": 9.1, "learning_rate": 0.0005437458257799829, "loss": 1.7369, "step": 43910 }, { "epoch": 9.1, "learning_rate": 0.0005436504150367332, "loss": 1.7385, "step": 43915 }, { "epoch": 9.1, "learning_rate": 0.0005435550042934835, "loss": 1.7331, "step": 43920 }, { "epoch": 9.1, "learning_rate": 0.0005434595935502337, "loss": 1.7388, "step": 43925 }, { "epoch": 9.1, "learning_rate": 0.000543364182806984, "loss": 1.7321, "step": 43930 }, { "epoch": 9.1, "learning_rate": 0.0005432687720637344, "loss": 1.7386, "step": 43935 }, { "epoch": 9.1, "learning_rate": 0.0005431733613204847, "loss": 1.7337, "step": 43940 }, { "epoch": 9.1, "learning_rate": 0.000543077950577235, "loss": 1.7313, "step": 43945 }, { "epoch": 9.11, "learning_rate": 0.0005429825398339853, "loss": 1.7326, "step": 43950 }, { "epoch": 9.11, "learning_rate": 0.0005428871290907356, "loss": 1.7394, "step": 43955 }, { "epoch": 9.11, "learning_rate": 0.0005427917183474859, "loss": 1.7317, "step": 43960 }, { "epoch": 9.11, "learning_rate": 0.0005426963076042363, "loss": 1.7421, "step": 43965 }, { "epoch": 9.11, "learning_rate": 0.0005426008968609866, "loss": 1.7366, "step": 43970 }, { "epoch": 9.11, "learning_rate": 0.0005425054861177369, "loss": 1.7365, "step": 43975 }, { "epoch": 9.11, "learning_rate": 0.0005424100753744871, "loss": 1.7352, "step": 43980 }, { "epoch": 9.11, "learning_rate": 0.0005423146646312374, "loss": 1.7334, "step": 43985 }, { "epoch": 9.11, "learning_rate": 0.0005422192538879878, "loss": 1.7339, "step": 43990 }, { "epoch": 9.11, "learning_rate": 0.0005421238431447381, "loss": 1.737, "step": 43995 }, { "epoch": 9.12, "learning_rate": 0.0005420284324014885, "loss": 1.7326, "step": 44000 }, { "epoch": 9.12, "learning_rate": 0.0005419330216582388, "loss": 1.7379, "step": 44005 }, { "epoch": 9.12, "learning_rate": 0.000541837610914989, "loss": 1.7385, "step": 44010 }, { "epoch": 9.12, "learning_rate": 0.0005417422001717393, "loss": 1.7343, "step": 44015 }, { "epoch": 9.12, "learning_rate": 0.0005416467894284897, "loss": 1.7326, "step": 44020 }, { "epoch": 9.12, "learning_rate": 0.00054155137868524, "loss": 1.7307, "step": 44025 }, { "epoch": 9.12, "learning_rate": 0.0005414559679419903, "loss": 1.7384, "step": 44030 }, { "epoch": 9.12, "learning_rate": 0.0005413605571987406, "loss": 1.7348, "step": 44035 }, { "epoch": 9.12, "learning_rate": 0.0005412651464554908, "loss": 1.7315, "step": 44040 }, { "epoch": 9.12, "learning_rate": 0.0005411697357122412, "loss": 1.7319, "step": 44045 }, { "epoch": 9.13, "learning_rate": 0.0005410743249689916, "loss": 1.7314, "step": 44050 }, { "epoch": 9.13, "learning_rate": 0.0005409789142257419, "loss": 1.737, "step": 44055 }, { "epoch": 9.13, "learning_rate": 0.0005408835034824922, "loss": 1.7322, "step": 44060 }, { "epoch": 9.13, "learning_rate": 0.0005407880927392424, "loss": 1.7382, "step": 44065 }, { "epoch": 9.13, "learning_rate": 0.0005406926819959927, "loss": 1.7353, "step": 44070 }, { "epoch": 9.13, "learning_rate": 0.000540597271252743, "loss": 1.7363, "step": 44075 }, { "epoch": 9.13, "learning_rate": 0.0005405018605094934, "loss": 1.7389, "step": 44080 }, { "epoch": 9.13, "learning_rate": 0.0005404064497662437, "loss": 1.7344, "step": 44085 }, { "epoch": 9.13, "learning_rate": 0.0005403110390229941, "loss": 1.7337, "step": 44090 }, { "epoch": 9.14, "learning_rate": 0.0005402156282797443, "loss": 1.7389, "step": 44095 }, { "epoch": 9.14, "learning_rate": 0.0005401202175364946, "loss": 1.7367, "step": 44100 }, { "epoch": 9.14, "learning_rate": 0.0005400248067932449, "loss": 1.7325, "step": 44105 }, { "epoch": 9.14, "learning_rate": 0.0005399293960499953, "loss": 1.7402, "step": 44110 }, { "epoch": 9.14, "learning_rate": 0.0005398339853067456, "loss": 1.7408, "step": 44115 }, { "epoch": 9.14, "learning_rate": 0.0005397385745634958, "loss": 1.7279, "step": 44120 }, { "epoch": 9.14, "learning_rate": 0.0005396431638202461, "loss": 1.739, "step": 44125 }, { "epoch": 9.14, "learning_rate": 0.0005395477530769964, "loss": 1.7332, "step": 44130 }, { "epoch": 9.14, "learning_rate": 0.0005394523423337467, "loss": 1.738, "step": 44135 }, { "epoch": 9.14, "learning_rate": 0.0005393569315904972, "loss": 1.7363, "step": 44140 }, { "epoch": 9.15, "learning_rate": 0.0005392615208472475, "loss": 1.7403, "step": 44145 }, { "epoch": 9.15, "learning_rate": 0.0005391661101039977, "loss": 1.7323, "step": 44150 }, { "epoch": 9.15, "learning_rate": 0.000539070699360748, "loss": 1.7315, "step": 44155 }, { "epoch": 9.15, "learning_rate": 0.0005389752886174983, "loss": 1.7371, "step": 44160 }, { "epoch": 9.15, "learning_rate": 0.0005388798778742486, "loss": 1.7294, "step": 44165 }, { "epoch": 9.15, "learning_rate": 0.000538784467130999, "loss": 1.7361, "step": 44170 }, { "epoch": 9.15, "learning_rate": 0.0005386890563877493, "loss": 1.7334, "step": 44175 }, { "epoch": 9.15, "learning_rate": 0.0005385936456444995, "loss": 1.737, "step": 44180 }, { "epoch": 9.15, "learning_rate": 0.0005384982349012499, "loss": 1.739, "step": 44185 }, { "epoch": 9.15, "learning_rate": 0.0005384028241580002, "loss": 1.7327, "step": 44190 }, { "epoch": 9.16, "learning_rate": 0.0005383074134147506, "loss": 1.7314, "step": 44195 }, { "epoch": 9.16, "learning_rate": 0.0005382120026715009, "loss": 1.7347, "step": 44200 }, { "epoch": 9.16, "learning_rate": 0.0005381165919282511, "loss": 1.7366, "step": 44205 }, { "epoch": 9.16, "learning_rate": 0.0005380211811850014, "loss": 1.741, "step": 44210 }, { "epoch": 9.16, "learning_rate": 0.0005379257704417517, "loss": 1.7347, "step": 44215 }, { "epoch": 9.16, "learning_rate": 0.000537830359698502, "loss": 1.7323, "step": 44220 }, { "epoch": 9.16, "learning_rate": 0.0005377349489552524, "loss": 1.735, "step": 44225 }, { "epoch": 9.16, "learning_rate": 0.0005376395382120028, "loss": 1.7391, "step": 44230 }, { "epoch": 9.16, "learning_rate": 0.000537544127468753, "loss": 1.7359, "step": 44235 }, { "epoch": 9.17, "learning_rate": 0.0005374487167255033, "loss": 1.738, "step": 44240 }, { "epoch": 9.17, "learning_rate": 0.0005373533059822536, "loss": 1.7358, "step": 44245 }, { "epoch": 9.17, "learning_rate": 0.0005372578952390039, "loss": 1.735, "step": 44250 }, { "epoch": 9.17, "learning_rate": 0.0005371624844957543, "loss": 1.7385, "step": 44255 }, { "epoch": 9.17, "learning_rate": 0.0005370670737525046, "loss": 1.7387, "step": 44260 }, { "epoch": 9.17, "learning_rate": 0.0005369716630092548, "loss": 1.7331, "step": 44265 }, { "epoch": 9.17, "learning_rate": 0.0005368762522660051, "loss": 1.7348, "step": 44270 }, { "epoch": 9.17, "learning_rate": 0.0005367808415227555, "loss": 1.739, "step": 44275 }, { "epoch": 9.17, "learning_rate": 0.0005366854307795058, "loss": 1.7335, "step": 44280 }, { "epoch": 9.17, "learning_rate": 0.0005365900200362562, "loss": 1.7358, "step": 44285 }, { "epoch": 9.18, "learning_rate": 0.0005364946092930064, "loss": 1.7355, "step": 44290 }, { "epoch": 9.18, "learning_rate": 0.0005363991985497567, "loss": 1.7346, "step": 44295 }, { "epoch": 9.18, "learning_rate": 0.000536303787806507, "loss": 1.7351, "step": 44300 }, { "epoch": 9.18, "learning_rate": 0.0005362083770632573, "loss": 1.7377, "step": 44305 }, { "epoch": 9.18, "learning_rate": 0.0005361129663200076, "loss": 1.7321, "step": 44310 }, { "epoch": 9.18, "learning_rate": 0.000536017555576758, "loss": 1.7352, "step": 44315 }, { "epoch": 9.18, "learning_rate": 0.0005359221448335083, "loss": 1.7333, "step": 44320 }, { "epoch": 9.18, "learning_rate": 0.0005358267340902586, "loss": 1.7391, "step": 44325 }, { "epoch": 9.18, "learning_rate": 0.0005357313233470089, "loss": 1.7376, "step": 44330 }, { "epoch": 9.18, "learning_rate": 0.0005356359126037592, "loss": 1.7339, "step": 44335 }, { "epoch": 9.19, "learning_rate": 0.0005355405018605095, "loss": 1.7322, "step": 44340 }, { "epoch": 9.19, "learning_rate": 0.0005354450911172598, "loss": 1.7384, "step": 44345 }, { "epoch": 9.19, "learning_rate": 0.0005353496803740101, "loss": 1.7328, "step": 44350 }, { "epoch": 9.19, "learning_rate": 0.0005352542696307604, "loss": 1.7336, "step": 44355 }, { "epoch": 9.19, "learning_rate": 0.0005351588588875107, "loss": 1.7338, "step": 44360 }, { "epoch": 9.19, "learning_rate": 0.000535063448144261, "loss": 1.7367, "step": 44365 }, { "epoch": 9.19, "learning_rate": 0.0005349680374010114, "loss": 1.7354, "step": 44370 }, { "epoch": 9.19, "learning_rate": 0.0005348726266577617, "loss": 1.7333, "step": 44375 }, { "epoch": 9.19, "learning_rate": 0.000534777215914512, "loss": 1.7353, "step": 44380 }, { "epoch": 9.2, "learning_rate": 0.0005346818051712623, "loss": 1.7409, "step": 44385 }, { "epoch": 9.2, "learning_rate": 0.0005345863944280126, "loss": 1.7292, "step": 44390 }, { "epoch": 9.2, "learning_rate": 0.0005344909836847629, "loss": 1.7354, "step": 44395 }, { "epoch": 9.2, "learning_rate": 0.0005343955729415131, "loss": 1.7354, "step": 44400 }, { "epoch": 9.2, "learning_rate": 0.0005343001621982635, "loss": 1.7406, "step": 44405 }, { "epoch": 9.2, "learning_rate": 0.0005342047514550138, "loss": 1.7355, "step": 44410 }, { "epoch": 9.2, "learning_rate": 0.0005341093407117642, "loss": 1.7334, "step": 44415 }, { "epoch": 9.2, "learning_rate": 0.0005340139299685145, "loss": 1.7359, "step": 44420 }, { "epoch": 9.2, "learning_rate": 0.0005339185192252648, "loss": 1.7342, "step": 44425 }, { "epoch": 9.2, "learning_rate": 0.0005338231084820151, "loss": 1.7327, "step": 44430 }, { "epoch": 9.21, "learning_rate": 0.0005337276977387654, "loss": 1.742, "step": 44435 }, { "epoch": 9.21, "learning_rate": 0.0005336322869955157, "loss": 1.7349, "step": 44440 }, { "epoch": 9.21, "learning_rate": 0.000533536876252266, "loss": 1.7378, "step": 44445 }, { "epoch": 9.21, "learning_rate": 0.0005334414655090163, "loss": 1.7376, "step": 44450 }, { "epoch": 9.21, "learning_rate": 0.0005333460547657665, "loss": 1.7368, "step": 44455 }, { "epoch": 9.21, "learning_rate": 0.000533250644022517, "loss": 1.733, "step": 44460 }, { "epoch": 9.21, "learning_rate": 0.0005331552332792673, "loss": 1.7367, "step": 44465 }, { "epoch": 9.21, "learning_rate": 0.0005330598225360176, "loss": 1.7334, "step": 44470 }, { "epoch": 9.21, "learning_rate": 0.0005329644117927679, "loss": 1.7404, "step": 44475 }, { "epoch": 9.21, "learning_rate": 0.0005328690010495182, "loss": 1.7333, "step": 44480 }, { "epoch": 9.22, "learning_rate": 0.0005327735903062684, "loss": 1.735, "step": 44485 }, { "epoch": 9.22, "learning_rate": 0.0005326781795630188, "loss": 1.7372, "step": 44490 }, { "epoch": 9.22, "learning_rate": 0.0005325827688197691, "loss": 1.7368, "step": 44495 }, { "epoch": 9.22, "learning_rate": 0.0005324873580765194, "loss": 1.7319, "step": 44500 }, { "epoch": 9.22, "learning_rate": 0.0005323919473332698, "loss": 1.7356, "step": 44505 }, { "epoch": 9.22, "learning_rate": 0.0005322965365900201, "loss": 1.7341, "step": 44510 }, { "epoch": 9.22, "learning_rate": 0.0005322011258467703, "loss": 1.7386, "step": 44515 }, { "epoch": 9.22, "learning_rate": 0.0005321057151035207, "loss": 1.7361, "step": 44520 }, { "epoch": 9.22, "learning_rate": 0.000532010304360271, "loss": 1.7378, "step": 44525 }, { "epoch": 9.23, "learning_rate": 0.0005319148936170213, "loss": 1.7401, "step": 44530 }, { "epoch": 9.23, "learning_rate": 0.0005318194828737716, "loss": 1.7354, "step": 44535 }, { "epoch": 9.23, "learning_rate": 0.0005317240721305218, "loss": 1.7371, "step": 44540 }, { "epoch": 9.23, "learning_rate": 0.0005316286613872721, "loss": 1.7407, "step": 44545 }, { "epoch": 9.23, "learning_rate": 0.0005315332506440226, "loss": 1.7329, "step": 44550 }, { "epoch": 9.23, "learning_rate": 0.0005314378399007729, "loss": 1.7363, "step": 44555 }, { "epoch": 9.23, "learning_rate": 0.0005313424291575232, "loss": 1.7426, "step": 44560 }, { "epoch": 9.23, "learning_rate": 0.0005312470184142735, "loss": 1.7254, "step": 44565 }, { "epoch": 9.23, "learning_rate": 0.0005311516076710237, "loss": 1.7334, "step": 44570 }, { "epoch": 9.23, "learning_rate": 0.000531056196927774, "loss": 1.737, "step": 44575 }, { "epoch": 9.24, "learning_rate": 0.0005309607861845244, "loss": 1.7351, "step": 44580 }, { "epoch": 9.24, "learning_rate": 0.0005308653754412747, "loss": 1.7354, "step": 44585 }, { "epoch": 9.24, "learning_rate": 0.000530769964698025, "loss": 1.7427, "step": 44590 }, { "epoch": 9.24, "learning_rate": 0.0005306745539547754, "loss": 1.7373, "step": 44595 }, { "epoch": 9.24, "learning_rate": 0.0005305791432115256, "loss": 1.7311, "step": 44600 }, { "epoch": 9.24, "learning_rate": 0.000530483732468276, "loss": 1.7315, "step": 44605 }, { "epoch": 9.24, "learning_rate": 0.0005303883217250263, "loss": 1.7358, "step": 44610 }, { "epoch": 9.24, "learning_rate": 0.0005302929109817766, "loss": 1.7338, "step": 44615 }, { "epoch": 9.24, "learning_rate": 0.0005301975002385269, "loss": 1.7381, "step": 44620 }, { "epoch": 9.24, "learning_rate": 0.0005301020894952771, "loss": 1.7309, "step": 44625 }, { "epoch": 9.25, "learning_rate": 0.0005300066787520274, "loss": 1.7357, "step": 44630 }, { "epoch": 9.25, "learning_rate": 0.0005299112680087778, "loss": 1.7351, "step": 44635 }, { "epoch": 9.25, "learning_rate": 0.0005298158572655281, "loss": 1.735, "step": 44640 }, { "epoch": 9.25, "learning_rate": 0.0005297204465222785, "loss": 1.7337, "step": 44645 }, { "epoch": 9.25, "learning_rate": 0.0005296250357790288, "loss": 1.7379, "step": 44650 }, { "epoch": 9.25, "learning_rate": 0.000529529625035779, "loss": 1.7366, "step": 44655 }, { "epoch": 9.25, "learning_rate": 0.0005294342142925293, "loss": 1.7343, "step": 44660 }, { "epoch": 9.25, "learning_rate": 0.0005293388035492797, "loss": 1.7385, "step": 44665 }, { "epoch": 9.25, "learning_rate": 0.00052924339280603, "loss": 1.7369, "step": 44670 }, { "epoch": 9.26, "learning_rate": 0.0005291479820627803, "loss": 1.7376, "step": 44675 }, { "epoch": 9.26, "learning_rate": 0.0005290525713195305, "loss": 1.7393, "step": 44680 }, { "epoch": 9.26, "learning_rate": 0.0005289571605762808, "loss": 1.7386, "step": 44685 }, { "epoch": 9.26, "learning_rate": 0.0005288617498330312, "loss": 1.7323, "step": 44690 }, { "epoch": 9.26, "learning_rate": 0.0005287663390897816, "loss": 1.739, "step": 44695 }, { "epoch": 9.26, "learning_rate": 0.0005286709283465319, "loss": 1.74, "step": 44700 }, { "epoch": 9.26, "learning_rate": 0.0005285755176032822, "loss": 1.7398, "step": 44705 }, { "epoch": 9.26, "learning_rate": 0.0005284801068600324, "loss": 1.7352, "step": 44710 }, { "epoch": 9.26, "learning_rate": 0.0005283846961167827, "loss": 1.7395, "step": 44715 }, { "epoch": 9.26, "learning_rate": 0.000528289285373533, "loss": 1.7351, "step": 44720 }, { "epoch": 9.27, "learning_rate": 0.0005281938746302834, "loss": 1.7343, "step": 44725 }, { "epoch": 9.27, "learning_rate": 0.0005280984638870337, "loss": 1.7375, "step": 44730 }, { "epoch": 9.27, "learning_rate": 0.0005280030531437841, "loss": 1.7332, "step": 44735 }, { "epoch": 9.27, "learning_rate": 0.0005279076424005343, "loss": 1.7356, "step": 44740 }, { "epoch": 9.27, "learning_rate": 0.0005278122316572846, "loss": 1.7353, "step": 44745 }, { "epoch": 9.27, "learning_rate": 0.0005277168209140349, "loss": 1.7368, "step": 44750 }, { "epoch": 9.27, "learning_rate": 0.0005276214101707853, "loss": 1.7361, "step": 44755 }, { "epoch": 9.27, "learning_rate": 0.0005275259994275356, "loss": 1.7393, "step": 44760 }, { "epoch": 9.27, "learning_rate": 0.0005274305886842858, "loss": 1.7345, "step": 44765 }, { "epoch": 9.27, "learning_rate": 0.0005273351779410361, "loss": 1.7398, "step": 44770 }, { "epoch": 9.28, "learning_rate": 0.0005272397671977864, "loss": 1.7317, "step": 44775 }, { "epoch": 9.28, "learning_rate": 0.0005271443564545368, "loss": 1.735, "step": 44780 }, { "epoch": 9.28, "learning_rate": 0.0005270489457112872, "loss": 1.7404, "step": 44785 }, { "epoch": 9.28, "learning_rate": 0.0005269535349680375, "loss": 1.7314, "step": 44790 }, { "epoch": 9.28, "learning_rate": 0.0005268581242247877, "loss": 1.7454, "step": 44795 }, { "epoch": 9.28, "learning_rate": 0.000526762713481538, "loss": 1.7391, "step": 44800 }, { "epoch": 9.28, "learning_rate": 0.0005266673027382883, "loss": 1.7364, "step": 44805 }, { "epoch": 9.28, "learning_rate": 0.0005265718919950386, "loss": 1.7343, "step": 44810 }, { "epoch": 9.28, "learning_rate": 0.000526476481251789, "loss": 1.7385, "step": 44815 }, { "epoch": 9.29, "learning_rate": 0.0005263810705085392, "loss": 1.7365, "step": 44820 }, { "epoch": 9.29, "learning_rate": 0.0005262856597652896, "loss": 1.7402, "step": 44825 }, { "epoch": 9.29, "learning_rate": 0.0005261902490220399, "loss": 1.733, "step": 44830 }, { "epoch": 9.29, "learning_rate": 0.0005260948382787902, "loss": 1.7343, "step": 44835 }, { "epoch": 9.29, "learning_rate": 0.0005259994275355406, "loss": 1.7344, "step": 44840 }, { "epoch": 9.29, "learning_rate": 0.0005259040167922909, "loss": 1.7342, "step": 44845 }, { "epoch": 9.29, "learning_rate": 0.0005258086060490411, "loss": 1.7394, "step": 44850 }, { "epoch": 9.29, "learning_rate": 0.0005257131953057914, "loss": 1.7376, "step": 44855 }, { "epoch": 9.29, "learning_rate": 0.0005256177845625417, "loss": 1.735, "step": 44860 }, { "epoch": 9.29, "learning_rate": 0.000525522373819292, "loss": 1.7348, "step": 44865 }, { "epoch": 9.3, "learning_rate": 0.0005254269630760424, "loss": 1.7342, "step": 44870 }, { "epoch": 9.3, "learning_rate": 0.0005253315523327928, "loss": 1.7389, "step": 44875 }, { "epoch": 9.3, "learning_rate": 0.000525236141589543, "loss": 1.7403, "step": 44880 }, { "epoch": 9.3, "learning_rate": 0.0005251407308462933, "loss": 1.7373, "step": 44885 }, { "epoch": 9.3, "learning_rate": 0.0005250453201030436, "loss": 1.7386, "step": 44890 }, { "epoch": 9.3, "learning_rate": 0.0005249499093597939, "loss": 1.7318, "step": 44895 }, { "epoch": 9.3, "learning_rate": 0.0005248544986165443, "loss": 1.7308, "step": 44900 }, { "epoch": 9.3, "learning_rate": 0.0005247590878732945, "loss": 1.7359, "step": 44905 }, { "epoch": 9.3, "learning_rate": 0.0005246636771300448, "loss": 1.7305, "step": 44910 }, { "epoch": 9.3, "learning_rate": 0.0005245682663867951, "loss": 1.733, "step": 44915 }, { "epoch": 9.31, "learning_rate": 0.0005244728556435455, "loss": 1.7396, "step": 44920 }, { "epoch": 9.31, "learning_rate": 0.0005243774449002958, "loss": 1.7361, "step": 44925 }, { "epoch": 9.31, "learning_rate": 0.0005242820341570462, "loss": 1.7368, "step": 44930 }, { "epoch": 9.31, "learning_rate": 0.0005241866234137964, "loss": 1.7299, "step": 44935 }, { "epoch": 9.31, "learning_rate": 0.0005240912126705467, "loss": 1.735, "step": 44940 }, { "epoch": 9.31, "learning_rate": 0.000523995801927297, "loss": 1.7358, "step": 44945 }, { "epoch": 9.31, "learning_rate": 0.0005239003911840473, "loss": 1.7363, "step": 44950 }, { "epoch": 9.31, "learning_rate": 0.0005238049804407976, "loss": 1.7364, "step": 44955 }, { "epoch": 9.31, "learning_rate": 0.000523709569697548, "loss": 1.7325, "step": 44960 }, { "epoch": 9.32, "learning_rate": 0.0005236141589542983, "loss": 1.7307, "step": 44965 }, { "epoch": 9.32, "learning_rate": 0.0005235187482110486, "loss": 1.737, "step": 44970 }, { "epoch": 9.32, "learning_rate": 0.0005234233374677989, "loss": 1.7331, "step": 44975 }, { "epoch": 9.32, "learning_rate": 0.0005233279267245492, "loss": 1.7319, "step": 44980 }, { "epoch": 9.32, "learning_rate": 0.0005232325159812995, "loss": 1.7322, "step": 44985 }, { "epoch": 9.32, "learning_rate": 0.0005231371052380498, "loss": 1.7313, "step": 44990 }, { "epoch": 9.32, "learning_rate": 0.0005230416944948001, "loss": 1.7373, "step": 44995 }, { "epoch": 9.32, "learning_rate": 0.0005229462837515504, "loss": 1.7303, "step": 45000 }, { "epoch": 9.32, "eval_accuracy": 0.5418562091503268, "eval_loss": 1.9261682033538818, "eval_runtime": 0.7992, "eval_samples_per_second": 187.686, "eval_steps_per_second": 1.251, "step": 45000 }, { "epoch": 9.32, "learning_rate": 0.0005228508730083007, "loss": 1.7256, "step": 45005 }, { "epoch": 9.32, "learning_rate": 0.0005227554622650511, "loss": 1.7357, "step": 45010 }, { "epoch": 9.33, "learning_rate": 0.0005226600515218014, "loss": 1.7318, "step": 45015 }, { "epoch": 9.33, "learning_rate": 0.0005225646407785517, "loss": 1.7386, "step": 45020 }, { "epoch": 9.33, "learning_rate": 0.000522469230035302, "loss": 1.7325, "step": 45025 }, { "epoch": 9.33, "learning_rate": 0.0005223738192920523, "loss": 1.7333, "step": 45030 }, { "epoch": 9.33, "learning_rate": 0.0005222784085488026, "loss": 1.7365, "step": 45035 }, { "epoch": 9.33, "learning_rate": 0.0005221829978055529, "loss": 1.7308, "step": 45040 }, { "epoch": 9.33, "learning_rate": 0.0005220875870623032, "loss": 1.734, "step": 45045 }, { "epoch": 9.33, "learning_rate": 0.0005219921763190535, "loss": 1.7307, "step": 45050 }, { "epoch": 9.33, "learning_rate": 0.0005218967655758039, "loss": 1.7276, "step": 45055 }, { "epoch": 9.33, "learning_rate": 0.0005218013548325542, "loss": 1.7327, "step": 45060 }, { "epoch": 9.34, "learning_rate": 0.0005217059440893045, "loss": 1.7318, "step": 45065 }, { "epoch": 9.34, "learning_rate": 0.0005216105333460548, "loss": 1.7315, "step": 45070 }, { "epoch": 9.34, "learning_rate": 0.0005215151226028051, "loss": 1.7392, "step": 45075 }, { "epoch": 9.34, "learning_rate": 0.0005214197118595554, "loss": 1.7364, "step": 45080 }, { "epoch": 9.34, "learning_rate": 0.0005213243011163057, "loss": 1.7394, "step": 45085 }, { "epoch": 9.34, "learning_rate": 0.000521228890373056, "loss": 1.7347, "step": 45090 }, { "epoch": 9.34, "learning_rate": 0.0005211334796298063, "loss": 1.7333, "step": 45095 }, { "epoch": 9.34, "learning_rate": 0.0005210380688865565, "loss": 1.7346, "step": 45100 }, { "epoch": 9.34, "learning_rate": 0.000520942658143307, "loss": 1.7347, "step": 45105 }, { "epoch": 9.35, "learning_rate": 0.0005208472474000573, "loss": 1.7345, "step": 45110 }, { "epoch": 9.35, "learning_rate": 0.0005207518366568076, "loss": 1.7332, "step": 45115 }, { "epoch": 9.35, "learning_rate": 0.0005206564259135579, "loss": 1.7332, "step": 45120 }, { "epoch": 9.35, "learning_rate": 0.0005205610151703082, "loss": 1.7396, "step": 45125 }, { "epoch": 9.35, "learning_rate": 0.0005204656044270584, "loss": 1.7369, "step": 45130 }, { "epoch": 9.35, "learning_rate": 0.0005203701936838088, "loss": 1.7326, "step": 45135 }, { "epoch": 9.35, "learning_rate": 0.0005202747829405591, "loss": 1.7351, "step": 45140 }, { "epoch": 9.35, "learning_rate": 0.0005201793721973094, "loss": 1.7327, "step": 45145 }, { "epoch": 9.35, "learning_rate": 0.0005200839614540598, "loss": 1.739, "step": 45150 }, { "epoch": 9.35, "learning_rate": 0.00051998855071081, "loss": 1.728, "step": 45155 }, { "epoch": 9.36, "learning_rate": 0.0005198931399675603, "loss": 1.7348, "step": 45160 }, { "epoch": 9.36, "learning_rate": 0.0005197977292243107, "loss": 1.7314, "step": 45165 }, { "epoch": 9.36, "learning_rate": 0.000519702318481061, "loss": 1.7383, "step": 45170 }, { "epoch": 9.36, "learning_rate": 0.0005196069077378113, "loss": 1.7322, "step": 45175 }, { "epoch": 9.36, "learning_rate": 0.0005195114969945616, "loss": 1.7301, "step": 45180 }, { "epoch": 9.36, "learning_rate": 0.0005194160862513118, "loss": 1.7366, "step": 45185 }, { "epoch": 9.36, "learning_rate": 0.0005193206755080621, "loss": 1.7353, "step": 45190 }, { "epoch": 9.36, "learning_rate": 0.0005192252647648126, "loss": 1.7295, "step": 45195 }, { "epoch": 9.36, "learning_rate": 0.0005191298540215629, "loss": 1.7398, "step": 45200 }, { "epoch": 9.37, "learning_rate": 0.0005190344432783132, "loss": 1.7376, "step": 45205 }, { "epoch": 9.37, "learning_rate": 0.0005189390325350635, "loss": 1.7359, "step": 45210 }, { "epoch": 9.37, "learning_rate": 0.0005188436217918137, "loss": 1.7357, "step": 45215 }, { "epoch": 9.37, "learning_rate": 0.000518748211048564, "loss": 1.7366, "step": 45220 }, { "epoch": 9.37, "learning_rate": 0.0005186528003053144, "loss": 1.7329, "step": 45225 }, { "epoch": 9.37, "learning_rate": 0.0005185573895620647, "loss": 1.7335, "step": 45230 }, { "epoch": 9.37, "learning_rate": 0.000518461978818815, "loss": 1.7324, "step": 45235 }, { "epoch": 9.37, "learning_rate": 0.0005183665680755654, "loss": 1.7398, "step": 45240 }, { "epoch": 9.37, "learning_rate": 0.0005182711573323156, "loss": 1.7353, "step": 45245 }, { "epoch": 9.37, "learning_rate": 0.000518175746589066, "loss": 1.7376, "step": 45250 }, { "epoch": 9.38, "learning_rate": 0.0005180803358458163, "loss": 1.7307, "step": 45255 }, { "epoch": 9.38, "learning_rate": 0.0005179849251025666, "loss": 1.7396, "step": 45260 }, { "epoch": 9.38, "learning_rate": 0.0005178895143593169, "loss": 1.736, "step": 45265 }, { "epoch": 9.38, "learning_rate": 0.0005177941036160671, "loss": 1.7365, "step": 45270 }, { "epoch": 9.38, "learning_rate": 0.0005176986928728174, "loss": 1.7369, "step": 45275 }, { "epoch": 9.38, "learning_rate": 0.0005176032821295678, "loss": 1.7353, "step": 45280 }, { "epoch": 9.38, "learning_rate": 0.0005175078713863182, "loss": 1.7335, "step": 45285 }, { "epoch": 9.38, "learning_rate": 0.0005174124606430685, "loss": 1.7369, "step": 45290 }, { "epoch": 9.38, "learning_rate": 0.0005173170498998188, "loss": 1.7386, "step": 45295 }, { "epoch": 9.38, "learning_rate": 0.000517221639156569, "loss": 1.7321, "step": 45300 }, { "epoch": 9.39, "learning_rate": 0.0005171262284133193, "loss": 1.7397, "step": 45305 }, { "epoch": 9.39, "learning_rate": 0.0005170308176700697, "loss": 1.7326, "step": 45310 }, { "epoch": 9.39, "learning_rate": 0.00051693540692682, "loss": 1.7326, "step": 45315 }, { "epoch": 9.39, "learning_rate": 0.0005168399961835703, "loss": 1.7365, "step": 45320 }, { "epoch": 9.39, "learning_rate": 0.0005167445854403205, "loss": 1.7396, "step": 45325 }, { "epoch": 9.39, "learning_rate": 0.0005166491746970709, "loss": 1.7365, "step": 45330 }, { "epoch": 9.39, "learning_rate": 0.0005165537639538212, "loss": 1.7331, "step": 45335 }, { "epoch": 9.39, "learning_rate": 0.0005164583532105716, "loss": 1.7358, "step": 45340 }, { "epoch": 9.39, "learning_rate": 0.0005163629424673219, "loss": 1.7401, "step": 45345 }, { "epoch": 9.4, "learning_rate": 0.0005162675317240722, "loss": 1.7336, "step": 45350 }, { "epoch": 9.4, "learning_rate": 0.0005161721209808224, "loss": 1.7324, "step": 45355 }, { "epoch": 9.4, "learning_rate": 0.0005160767102375727, "loss": 1.7347, "step": 45360 }, { "epoch": 9.4, "learning_rate": 0.000515981299494323, "loss": 1.733, "step": 45365 }, { "epoch": 9.4, "learning_rate": 0.0005158858887510734, "loss": 1.7359, "step": 45370 }, { "epoch": 9.4, "learning_rate": 0.0005157904780078237, "loss": 1.7351, "step": 45375 }, { "epoch": 9.4, "learning_rate": 0.000515695067264574, "loss": 1.7384, "step": 45380 }, { "epoch": 9.4, "learning_rate": 0.0005155996565213243, "loss": 1.7411, "step": 45385 }, { "epoch": 9.4, "learning_rate": 0.0005155042457780746, "loss": 1.7328, "step": 45390 }, { "epoch": 9.4, "learning_rate": 0.0005154088350348249, "loss": 1.7347, "step": 45395 }, { "epoch": 9.41, "learning_rate": 0.0005153134242915753, "loss": 1.7325, "step": 45400 }, { "epoch": 9.41, "learning_rate": 0.0005152180135483256, "loss": 1.7348, "step": 45405 }, { "epoch": 9.41, "learning_rate": 0.0005151226028050758, "loss": 1.7331, "step": 45410 }, { "epoch": 9.41, "learning_rate": 0.0005150271920618261, "loss": 1.7311, "step": 45415 }, { "epoch": 9.41, "learning_rate": 0.0005149317813185764, "loss": 1.7364, "step": 45420 }, { "epoch": 9.41, "learning_rate": 0.0005148363705753268, "loss": 1.7359, "step": 45425 }, { "epoch": 9.41, "learning_rate": 0.0005147409598320772, "loss": 1.7337, "step": 45430 }, { "epoch": 9.41, "learning_rate": 0.0005146455490888275, "loss": 1.733, "step": 45435 }, { "epoch": 9.41, "learning_rate": 0.0005145501383455777, "loss": 1.7377, "step": 45440 }, { "epoch": 9.41, "learning_rate": 0.000514454727602328, "loss": 1.7286, "step": 45445 }, { "epoch": 9.42, "learning_rate": 0.0005143593168590783, "loss": 1.7358, "step": 45450 }, { "epoch": 9.42, "learning_rate": 0.0005142639061158286, "loss": 1.7335, "step": 45455 }, { "epoch": 9.42, "learning_rate": 0.000514168495372579, "loss": 1.7371, "step": 45460 }, { "epoch": 9.42, "learning_rate": 0.0005140730846293292, "loss": 1.7406, "step": 45465 }, { "epoch": 9.42, "learning_rate": 0.0005139776738860796, "loss": 1.7364, "step": 45470 }, { "epoch": 9.42, "learning_rate": 0.0005138822631428299, "loss": 1.7351, "step": 45475 }, { "epoch": 9.42, "learning_rate": 0.0005137868523995802, "loss": 1.7321, "step": 45480 }, { "epoch": 9.42, "learning_rate": 0.0005136914416563306, "loss": 1.7366, "step": 45485 }, { "epoch": 9.42, "learning_rate": 0.0005135960309130809, "loss": 1.7343, "step": 45490 }, { "epoch": 9.43, "learning_rate": 0.0005135006201698311, "loss": 1.735, "step": 45495 }, { "epoch": 9.43, "learning_rate": 0.0005134052094265814, "loss": 1.7367, "step": 45500 }, { "epoch": 9.43, "learning_rate": 0.0005133097986833317, "loss": 1.7407, "step": 45505 }, { "epoch": 9.43, "learning_rate": 0.000513214387940082, "loss": 1.7406, "step": 45510 }, { "epoch": 9.43, "learning_rate": 0.0005131189771968325, "loss": 1.7376, "step": 45515 }, { "epoch": 9.43, "learning_rate": 0.0005130235664535828, "loss": 1.7371, "step": 45520 }, { "epoch": 9.43, "learning_rate": 0.000512928155710333, "loss": 1.7388, "step": 45525 }, { "epoch": 9.43, "learning_rate": 0.0005128327449670833, "loss": 1.7279, "step": 45530 }, { "epoch": 9.43, "learning_rate": 0.0005127373342238336, "loss": 1.7338, "step": 45535 }, { "epoch": 9.43, "learning_rate": 0.0005126419234805839, "loss": 1.7336, "step": 45540 }, { "epoch": 9.44, "learning_rate": 0.0005125465127373343, "loss": 1.7427, "step": 45545 }, { "epoch": 9.44, "learning_rate": 0.0005124511019940845, "loss": 1.738, "step": 45550 }, { "epoch": 9.44, "learning_rate": 0.0005123556912508348, "loss": 1.7412, "step": 45555 }, { "epoch": 9.44, "learning_rate": 0.0005122602805075852, "loss": 1.7326, "step": 45560 }, { "epoch": 9.44, "learning_rate": 0.0005121648697643355, "loss": 1.7364, "step": 45565 }, { "epoch": 9.44, "learning_rate": 0.0005120694590210858, "loss": 1.7371, "step": 45570 }, { "epoch": 9.44, "learning_rate": 0.0005119740482778362, "loss": 1.7336, "step": 45575 }, { "epoch": 9.44, "learning_rate": 0.0005118786375345864, "loss": 1.738, "step": 45580 }, { "epoch": 9.44, "learning_rate": 0.0005117832267913367, "loss": 1.7383, "step": 45585 }, { "epoch": 9.44, "learning_rate": 0.000511687816048087, "loss": 1.741, "step": 45590 }, { "epoch": 9.45, "learning_rate": 0.0005115924053048373, "loss": 1.7324, "step": 45595 }, { "epoch": 9.45, "learning_rate": 0.0005114969945615876, "loss": 1.7368, "step": 45600 }, { "epoch": 9.45, "learning_rate": 0.0005114015838183379, "loss": 1.7405, "step": 45605 }, { "epoch": 9.45, "learning_rate": 0.0005113061730750883, "loss": 1.7365, "step": 45610 }, { "epoch": 9.45, "learning_rate": 0.0005112107623318386, "loss": 1.7356, "step": 45615 }, { "epoch": 9.45, "learning_rate": 0.0005111153515885889, "loss": 1.7381, "step": 45620 }, { "epoch": 9.45, "learning_rate": 0.0005110199408453392, "loss": 1.7369, "step": 45625 }, { "epoch": 9.45, "learning_rate": 0.0005109245301020895, "loss": 1.734, "step": 45630 }, { "epoch": 9.45, "learning_rate": 0.0005108291193588398, "loss": 1.734, "step": 45635 }, { "epoch": 9.46, "learning_rate": 0.0005107337086155901, "loss": 1.7356, "step": 45640 }, { "epoch": 9.46, "learning_rate": 0.0005106382978723404, "loss": 1.735, "step": 45645 }, { "epoch": 9.46, "learning_rate": 0.0005105428871290907, "loss": 1.7357, "step": 45650 }, { "epoch": 9.46, "learning_rate": 0.0005104474763858411, "loss": 1.7305, "step": 45655 }, { "epoch": 9.46, "learning_rate": 0.0005103520656425913, "loss": 1.7354, "step": 45660 }, { "epoch": 9.46, "learning_rate": 0.0005102566548993417, "loss": 1.7337, "step": 45665 }, { "epoch": 9.46, "learning_rate": 0.000510161244156092, "loss": 1.7383, "step": 45670 }, { "epoch": 9.46, "learning_rate": 0.0005100658334128423, "loss": 1.7352, "step": 45675 }, { "epoch": 9.46, "learning_rate": 0.0005099704226695926, "loss": 1.7328, "step": 45680 }, { "epoch": 9.46, "learning_rate": 0.0005098750119263429, "loss": 1.7368, "step": 45685 }, { "epoch": 9.47, "learning_rate": 0.0005097796011830932, "loss": 1.7386, "step": 45690 }, { "epoch": 9.47, "learning_rate": 0.0005096841904398435, "loss": 1.7296, "step": 45695 }, { "epoch": 9.47, "learning_rate": 0.0005095887796965939, "loss": 1.735, "step": 45700 }, { "epoch": 9.47, "learning_rate": 0.0005094933689533442, "loss": 1.7409, "step": 45705 }, { "epoch": 9.47, "learning_rate": 0.0005093979582100945, "loss": 1.7331, "step": 45710 }, { "epoch": 9.47, "learning_rate": 0.0005093025474668447, "loss": 1.7363, "step": 45715 }, { "epoch": 9.47, "learning_rate": 0.0005092071367235951, "loss": 1.7317, "step": 45720 }, { "epoch": 9.47, "learning_rate": 0.0005091117259803454, "loss": 1.7368, "step": 45725 }, { "epoch": 9.47, "learning_rate": 0.0005090163152370957, "loss": 1.7371, "step": 45730 }, { "epoch": 9.47, "learning_rate": 0.000508920904493846, "loss": 1.7343, "step": 45735 }, { "epoch": 9.48, "learning_rate": 0.0005088254937505963, "loss": 1.732, "step": 45740 }, { "epoch": 9.48, "learning_rate": 0.0005087300830073466, "loss": 1.7349, "step": 45745 }, { "epoch": 9.48, "learning_rate": 0.000508634672264097, "loss": 1.7402, "step": 45750 }, { "epoch": 9.48, "learning_rate": 0.0005085392615208473, "loss": 1.7367, "step": 45755 }, { "epoch": 9.48, "learning_rate": 0.0005084438507775976, "loss": 1.7347, "step": 45760 }, { "epoch": 9.48, "learning_rate": 0.0005083484400343479, "loss": 1.7401, "step": 45765 }, { "epoch": 9.48, "learning_rate": 0.0005082530292910982, "loss": 1.7347, "step": 45770 }, { "epoch": 9.48, "learning_rate": 0.0005081576185478484, "loss": 1.7324, "step": 45775 }, { "epoch": 9.48, "learning_rate": 0.0005080622078045988, "loss": 1.7334, "step": 45780 }, { "epoch": 9.49, "learning_rate": 0.0005079667970613491, "loss": 1.7339, "step": 45785 }, { "epoch": 9.49, "learning_rate": 0.0005078713863180995, "loss": 1.7331, "step": 45790 }, { "epoch": 9.49, "learning_rate": 0.0005077759755748498, "loss": 1.7336, "step": 45795 }, { "epoch": 9.49, "learning_rate": 0.0005076805648316, "loss": 1.7368, "step": 45800 }, { "epoch": 9.49, "learning_rate": 0.0005075851540883503, "loss": 1.736, "step": 45805 }, { "epoch": 9.49, "learning_rate": 0.0005074897433451007, "loss": 1.7365, "step": 45810 }, { "epoch": 9.49, "learning_rate": 0.000507394332601851, "loss": 1.732, "step": 45815 }, { "epoch": 9.49, "learning_rate": 0.0005072989218586013, "loss": 1.7319, "step": 45820 }, { "epoch": 9.49, "learning_rate": 0.0005072035111153516, "loss": 1.7368, "step": 45825 }, { "epoch": 9.49, "learning_rate": 0.0005071081003721018, "loss": 1.7347, "step": 45830 }, { "epoch": 9.5, "learning_rate": 0.0005070126896288521, "loss": 1.7378, "step": 45835 }, { "epoch": 9.5, "learning_rate": 0.0005069172788856026, "loss": 1.7402, "step": 45840 }, { "epoch": 9.5, "learning_rate": 0.0005068218681423529, "loss": 1.7323, "step": 45845 }, { "epoch": 9.5, "learning_rate": 0.0005067264573991032, "loss": 1.7361, "step": 45850 }, { "epoch": 9.5, "learning_rate": 0.0005066310466558535, "loss": 1.7331, "step": 45855 }, { "epoch": 9.5, "learning_rate": 0.0005065356359126037, "loss": 1.7326, "step": 45860 }, { "epoch": 9.5, "learning_rate": 0.000506440225169354, "loss": 1.7376, "step": 45865 }, { "epoch": 9.5, "learning_rate": 0.0005063448144261044, "loss": 1.7373, "step": 45870 }, { "epoch": 9.5, "learning_rate": 0.0005062494036828547, "loss": 1.7328, "step": 45875 }, { "epoch": 9.5, "learning_rate": 0.000506153992939605, "loss": 1.7337, "step": 45880 }, { "epoch": 9.51, "learning_rate": 0.0005060585821963553, "loss": 1.7387, "step": 45885 }, { "epoch": 9.51, "learning_rate": 0.0005059631714531056, "loss": 1.7364, "step": 45890 }, { "epoch": 9.51, "learning_rate": 0.000505867760709856, "loss": 1.7334, "step": 45895 }, { "epoch": 9.51, "learning_rate": 0.0005057723499666063, "loss": 1.7337, "step": 45900 }, { "epoch": 9.51, "learning_rate": 0.0005056769392233566, "loss": 1.7335, "step": 45905 }, { "epoch": 9.51, "learning_rate": 0.0005055815284801069, "loss": 1.7404, "step": 45910 }, { "epoch": 9.51, "learning_rate": 0.0005054861177368571, "loss": 1.7266, "step": 45915 }, { "epoch": 9.51, "learning_rate": 0.0005053907069936074, "loss": 1.7312, "step": 45920 }, { "epoch": 9.51, "learning_rate": 0.0005052952962503578, "loss": 1.738, "step": 45925 }, { "epoch": 9.52, "learning_rate": 0.0005051998855071082, "loss": 1.7347, "step": 45930 }, { "epoch": 9.52, "learning_rate": 0.0005051044747638585, "loss": 1.7368, "step": 45935 }, { "epoch": 9.52, "learning_rate": 0.0005050090640206087, "loss": 1.7368, "step": 45940 }, { "epoch": 9.52, "learning_rate": 0.000504913653277359, "loss": 1.7363, "step": 45945 }, { "epoch": 9.52, "learning_rate": 0.0005048182425341093, "loss": 1.7422, "step": 45950 }, { "epoch": 9.52, "learning_rate": 0.0005047228317908597, "loss": 1.7306, "step": 45955 }, { "epoch": 9.52, "learning_rate": 0.00050462742104761, "loss": 1.7346, "step": 45960 }, { "epoch": 9.52, "learning_rate": 0.0005045320103043603, "loss": 1.7381, "step": 45965 }, { "epoch": 9.52, "learning_rate": 0.0005044365995611105, "loss": 1.7341, "step": 45970 }, { "epoch": 9.52, "learning_rate": 0.0005043411888178609, "loss": 1.7399, "step": 45975 }, { "epoch": 9.53, "learning_rate": 0.0005042457780746112, "loss": 1.7333, "step": 45980 }, { "epoch": 9.53, "learning_rate": 0.0005041503673313616, "loss": 1.7338, "step": 45985 }, { "epoch": 9.53, "learning_rate": 0.0005040549565881119, "loss": 1.7311, "step": 45990 }, { "epoch": 9.53, "learning_rate": 0.0005039595458448622, "loss": 1.7349, "step": 45995 }, { "epoch": 9.53, "learning_rate": 0.0005038641351016124, "loss": 1.7356, "step": 46000 }, { "epoch": 9.53, "learning_rate": 0.0005037687243583627, "loss": 1.736, "step": 46005 }, { "epoch": 9.53, "learning_rate": 0.000503673313615113, "loss": 1.74, "step": 46010 }, { "epoch": 9.53, "learning_rate": 0.0005035779028718634, "loss": 1.7336, "step": 46015 }, { "epoch": 9.53, "learning_rate": 0.0005034824921286138, "loss": 1.7332, "step": 46020 }, { "epoch": 9.53, "learning_rate": 0.000503387081385364, "loss": 1.7307, "step": 46025 }, { "epoch": 9.54, "learning_rate": 0.0005032916706421143, "loss": 1.736, "step": 46030 }, { "epoch": 9.54, "learning_rate": 0.0005031962598988646, "loss": 1.7334, "step": 46035 }, { "epoch": 9.54, "learning_rate": 0.0005031008491556149, "loss": 1.7366, "step": 46040 }, { "epoch": 9.54, "learning_rate": 0.0005030054384123653, "loss": 1.73, "step": 46045 }, { "epoch": 9.54, "learning_rate": 0.0005029100276691156, "loss": 1.739, "step": 46050 }, { "epoch": 9.54, "learning_rate": 0.0005028146169258658, "loss": 1.7323, "step": 46055 }, { "epoch": 9.54, "learning_rate": 0.0005027192061826161, "loss": 1.7346, "step": 46060 }, { "epoch": 9.54, "learning_rate": 0.0005026237954393665, "loss": 1.7323, "step": 46065 }, { "epoch": 9.54, "learning_rate": 0.0005025283846961168, "loss": 1.7356, "step": 46070 }, { "epoch": 9.55, "learning_rate": 0.0005024329739528672, "loss": 1.7346, "step": 46075 }, { "epoch": 9.55, "learning_rate": 0.0005023375632096175, "loss": 1.7328, "step": 46080 }, { "epoch": 9.55, "learning_rate": 0.0005022421524663677, "loss": 1.7291, "step": 46085 }, { "epoch": 9.55, "learning_rate": 0.000502146741723118, "loss": 1.732, "step": 46090 }, { "epoch": 9.55, "learning_rate": 0.0005020513309798683, "loss": 1.7364, "step": 46095 }, { "epoch": 9.55, "learning_rate": 0.0005019559202366186, "loss": 1.7348, "step": 46100 }, { "epoch": 9.55, "learning_rate": 0.000501860509493369, "loss": 1.7361, "step": 46105 }, { "epoch": 9.55, "learning_rate": 0.0005017650987501192, "loss": 1.7343, "step": 46110 }, { "epoch": 9.55, "learning_rate": 0.0005016696880068696, "loss": 1.7396, "step": 46115 }, { "epoch": 9.55, "learning_rate": 0.0005015742772636199, "loss": 1.7341, "step": 46120 }, { "epoch": 9.56, "learning_rate": 0.0005014788665203702, "loss": 1.7292, "step": 46125 }, { "epoch": 9.56, "learning_rate": 0.0005013834557771206, "loss": 1.7408, "step": 46130 }, { "epoch": 9.56, "learning_rate": 0.0005012880450338709, "loss": 1.738, "step": 46135 }, { "epoch": 9.56, "learning_rate": 0.0005011926342906211, "loss": 1.7372, "step": 46140 }, { "epoch": 9.56, "learning_rate": 0.0005010972235473714, "loss": 1.7362, "step": 46145 }, { "epoch": 9.56, "learning_rate": 0.0005010018128041217, "loss": 1.7348, "step": 46150 }, { "epoch": 9.56, "learning_rate": 0.000500906402060872, "loss": 1.7375, "step": 46155 }, { "epoch": 9.56, "learning_rate": 0.0005008109913176225, "loss": 1.7333, "step": 46160 }, { "epoch": 9.56, "learning_rate": 0.0005007155805743727, "loss": 1.7345, "step": 46165 }, { "epoch": 9.56, "learning_rate": 0.000500620169831123, "loss": 1.7284, "step": 46170 }, { "epoch": 9.57, "learning_rate": 0.0005005247590878733, "loss": 1.7352, "step": 46175 }, { "epoch": 9.57, "learning_rate": 0.0005004293483446236, "loss": 1.7311, "step": 46180 }, { "epoch": 9.57, "learning_rate": 0.0005003339376013739, "loss": 1.7377, "step": 46185 }, { "epoch": 9.57, "learning_rate": 0.0005002385268581243, "loss": 1.7351, "step": 46190 }, { "epoch": 9.57, "learning_rate": 0.0005001431161148745, "loss": 1.7355, "step": 46195 }, { "epoch": 9.57, "learning_rate": 0.0005000477053716248, "loss": 1.7353, "step": 46200 }, { "epoch": 9.57, "learning_rate": 0.0004999522946283752, "loss": 1.7337, "step": 46205 }, { "epoch": 9.57, "learning_rate": 0.0004998568838851255, "loss": 1.7348, "step": 46210 }, { "epoch": 9.57, "learning_rate": 0.0004997614731418758, "loss": 1.7362, "step": 46215 }, { "epoch": 9.58, "learning_rate": 0.0004996660623986262, "loss": 1.7366, "step": 46220 }, { "epoch": 9.58, "learning_rate": 0.0004995706516553764, "loss": 1.7359, "step": 46225 }, { "epoch": 9.58, "learning_rate": 0.0004994752409121267, "loss": 1.7356, "step": 46230 }, { "epoch": 9.58, "learning_rate": 0.000499379830168877, "loss": 1.7304, "step": 46235 }, { "epoch": 9.58, "learning_rate": 0.0004992844194256274, "loss": 1.7306, "step": 46240 }, { "epoch": 9.58, "learning_rate": 0.0004991890086823777, "loss": 1.739, "step": 46245 }, { "epoch": 9.58, "learning_rate": 0.0004990935979391279, "loss": 1.7373, "step": 46250 }, { "epoch": 9.58, "learning_rate": 0.0004989981871958782, "loss": 1.7352, "step": 46255 }, { "epoch": 9.58, "learning_rate": 0.0004989027764526286, "loss": 1.7361, "step": 46260 }, { "epoch": 9.58, "learning_rate": 0.0004988073657093789, "loss": 1.7336, "step": 46265 }, { "epoch": 9.59, "learning_rate": 0.0004987119549661292, "loss": 1.7367, "step": 46270 }, { "epoch": 9.59, "learning_rate": 0.0004986165442228794, "loss": 1.736, "step": 46275 }, { "epoch": 9.59, "learning_rate": 0.0004985211334796298, "loss": 1.7381, "step": 46280 }, { "epoch": 9.59, "learning_rate": 0.0004984257227363801, "loss": 1.7366, "step": 46285 }, { "epoch": 9.59, "learning_rate": 0.0004983303119931304, "loss": 1.7355, "step": 46290 }, { "epoch": 9.59, "learning_rate": 0.0004982349012498808, "loss": 1.7341, "step": 46295 }, { "epoch": 9.59, "learning_rate": 0.0004981394905066311, "loss": 1.7299, "step": 46300 }, { "epoch": 9.59, "learning_rate": 0.0004980440797633813, "loss": 1.7338, "step": 46305 }, { "epoch": 9.59, "learning_rate": 0.0004979486690201317, "loss": 1.7331, "step": 46310 }, { "epoch": 9.59, "learning_rate": 0.000497853258276882, "loss": 1.7315, "step": 46315 }, { "epoch": 9.6, "learning_rate": 0.0004977578475336323, "loss": 1.733, "step": 46320 }, { "epoch": 9.6, "learning_rate": 0.0004976624367903826, "loss": 1.7336, "step": 46325 }, { "epoch": 9.6, "learning_rate": 0.000497567026047133, "loss": 1.7321, "step": 46330 }, { "epoch": 9.6, "learning_rate": 0.0004974716153038832, "loss": 1.7342, "step": 46335 }, { "epoch": 9.6, "learning_rate": 0.0004973762045606335, "loss": 1.7357, "step": 46340 }, { "epoch": 9.6, "learning_rate": 0.0004972807938173838, "loss": 1.7312, "step": 46345 }, { "epoch": 9.6, "learning_rate": 0.0004971853830741342, "loss": 1.7294, "step": 46350 }, { "epoch": 9.6, "learning_rate": 0.0004970899723308845, "loss": 1.7339, "step": 46355 }, { "epoch": 9.6, "learning_rate": 0.0004969945615876347, "loss": 1.7353, "step": 46360 }, { "epoch": 9.61, "learning_rate": 0.0004968991508443851, "loss": 1.7334, "step": 46365 }, { "epoch": 9.61, "learning_rate": 0.0004968037401011354, "loss": 1.7397, "step": 46370 }, { "epoch": 9.61, "learning_rate": 0.0004967083293578857, "loss": 1.7299, "step": 46375 }, { "epoch": 9.61, "learning_rate": 0.0004966129186146361, "loss": 1.7294, "step": 46380 }, { "epoch": 9.61, "learning_rate": 0.0004965175078713864, "loss": 1.7364, "step": 46385 }, { "epoch": 9.61, "learning_rate": 0.0004964220971281366, "loss": 1.7361, "step": 46390 }, { "epoch": 9.61, "learning_rate": 0.0004963266863848869, "loss": 1.7324, "step": 46395 }, { "epoch": 9.61, "learning_rate": 0.0004962312756416373, "loss": 1.7369, "step": 46400 }, { "epoch": 9.61, "learning_rate": 0.0004961358648983876, "loss": 1.7352, "step": 46405 }, { "epoch": 9.61, "learning_rate": 0.0004960404541551379, "loss": 1.7395, "step": 46410 }, { "epoch": 9.62, "learning_rate": 0.0004959450434118881, "loss": 1.7359, "step": 46415 }, { "epoch": 9.62, "learning_rate": 0.0004958496326686384, "loss": 1.7331, "step": 46420 }, { "epoch": 9.62, "learning_rate": 0.0004957542219253888, "loss": 1.7362, "step": 46425 }, { "epoch": 9.62, "learning_rate": 0.0004956588111821391, "loss": 1.7332, "step": 46430 }, { "epoch": 9.62, "learning_rate": 0.0004955634004388894, "loss": 1.7328, "step": 46435 }, { "epoch": 9.62, "learning_rate": 0.0004954679896956398, "loss": 1.739, "step": 46440 }, { "epoch": 9.62, "learning_rate": 0.00049537257895239, "loss": 1.7332, "step": 46445 }, { "epoch": 9.62, "learning_rate": 0.0004952771682091403, "loss": 1.737, "step": 46450 }, { "epoch": 9.62, "learning_rate": 0.0004951817574658907, "loss": 1.7366, "step": 46455 }, { "epoch": 9.63, "learning_rate": 0.000495086346722641, "loss": 1.7365, "step": 46460 }, { "epoch": 9.63, "learning_rate": 0.0004949909359793913, "loss": 1.7311, "step": 46465 }, { "epoch": 9.63, "learning_rate": 0.0004948955252361417, "loss": 1.7326, "step": 46470 }, { "epoch": 9.63, "learning_rate": 0.0004948001144928919, "loss": 1.7324, "step": 46475 }, { "epoch": 9.63, "learning_rate": 0.0004947047037496422, "loss": 1.7378, "step": 46480 }, { "epoch": 9.63, "learning_rate": 0.0004946092930063925, "loss": 1.7313, "step": 46485 }, { "epoch": 9.63, "learning_rate": 0.0004945138822631429, "loss": 1.7317, "step": 46490 }, { "epoch": 9.63, "learning_rate": 0.0004944184715198932, "loss": 1.7372, "step": 46495 }, { "epoch": 9.63, "learning_rate": 0.0004943230607766434, "loss": 1.7389, "step": 46500 }, { "epoch": 9.63, "learning_rate": 0.0004942276500333937, "loss": 1.7338, "step": 46505 }, { "epoch": 9.64, "learning_rate": 0.000494132239290144, "loss": 1.7343, "step": 46510 }, { "epoch": 9.64, "learning_rate": 0.0004940368285468944, "loss": 1.7302, "step": 46515 }, { "epoch": 9.64, "learning_rate": 0.0004939414178036447, "loss": 1.7377, "step": 46520 }, { "epoch": 9.64, "learning_rate": 0.0004938460070603951, "loss": 1.7386, "step": 46525 }, { "epoch": 9.64, "learning_rate": 0.0004937505963171453, "loss": 1.7343, "step": 46530 }, { "epoch": 9.64, "learning_rate": 0.0004936551855738956, "loss": 1.7377, "step": 46535 }, { "epoch": 9.64, "learning_rate": 0.000493559774830646, "loss": 1.7348, "step": 46540 }, { "epoch": 9.64, "learning_rate": 0.0004934643640873963, "loss": 1.7412, "step": 46545 }, { "epoch": 9.64, "learning_rate": 0.0004933689533441466, "loss": 1.7383, "step": 46550 }, { "epoch": 9.64, "learning_rate": 0.0004932735426008968, "loss": 1.7346, "step": 46555 }, { "epoch": 9.65, "learning_rate": 0.0004931781318576472, "loss": 1.7366, "step": 46560 }, { "epoch": 9.65, "learning_rate": 0.0004930827211143975, "loss": 1.7292, "step": 46565 }, { "epoch": 9.65, "learning_rate": 0.0004929873103711478, "loss": 1.7332, "step": 46570 }, { "epoch": 9.65, "learning_rate": 0.0004928918996278981, "loss": 1.7412, "step": 46575 }, { "epoch": 9.65, "learning_rate": 0.0004927964888846484, "loss": 1.7404, "step": 46580 }, { "epoch": 9.65, "learning_rate": 0.0004927010781413987, "loss": 1.7283, "step": 46585 }, { "epoch": 9.65, "learning_rate": 0.000492605667398149, "loss": 1.7355, "step": 46590 }, { "epoch": 9.65, "learning_rate": 0.0004925102566548993, "loss": 1.7357, "step": 46595 }, { "epoch": 9.65, "learning_rate": 0.0004924148459116497, "loss": 1.7305, "step": 46600 }, { "epoch": 9.66, "learning_rate": 0.0004923194351684, "loss": 1.7333, "step": 46605 }, { "epoch": 9.66, "learning_rate": 0.0004922240244251503, "loss": 1.7367, "step": 46610 }, { "epoch": 9.66, "learning_rate": 0.0004921286136819006, "loss": 1.7331, "step": 46615 }, { "epoch": 9.66, "learning_rate": 0.0004920332029386509, "loss": 1.7336, "step": 46620 }, { "epoch": 9.66, "learning_rate": 0.0004919377921954012, "loss": 1.736, "step": 46625 }, { "epoch": 9.66, "learning_rate": 0.0004918423814521516, "loss": 1.7362, "step": 46630 }, { "epoch": 9.66, "learning_rate": 0.0004917469707089019, "loss": 1.7364, "step": 46635 }, { "epoch": 9.66, "learning_rate": 0.0004916515599656521, "loss": 1.7309, "step": 46640 }, { "epoch": 9.66, "learning_rate": 0.0004915561492224024, "loss": 1.7285, "step": 46645 }, { "epoch": 9.66, "learning_rate": 0.0004914607384791527, "loss": 1.7345, "step": 46650 }, { "epoch": 9.67, "learning_rate": 0.0004913653277359031, "loss": 1.7334, "step": 46655 }, { "epoch": 9.67, "learning_rate": 0.0004912699169926534, "loss": 1.7298, "step": 46660 }, { "epoch": 9.67, "learning_rate": 0.0004911745062494037, "loss": 1.739, "step": 46665 }, { "epoch": 9.67, "learning_rate": 0.0004910790955061539, "loss": 1.7348, "step": 46670 }, { "epoch": 9.67, "learning_rate": 0.0004909836847629043, "loss": 1.7383, "step": 46675 }, { "epoch": 9.67, "learning_rate": 0.0004908882740196546, "loss": 1.7399, "step": 46680 }, { "epoch": 9.67, "learning_rate": 0.0004907928632764049, "loss": 1.7386, "step": 46685 }, { "epoch": 9.67, "learning_rate": 0.0004906974525331553, "loss": 1.7387, "step": 46690 }, { "epoch": 9.67, "learning_rate": 0.0004906020417899056, "loss": 1.7292, "step": 46695 }, { "epoch": 9.67, "learning_rate": 0.0004905066310466558, "loss": 1.7337, "step": 46700 }, { "epoch": 9.68, "learning_rate": 0.0004904112203034062, "loss": 1.7327, "step": 46705 }, { "epoch": 9.68, "learning_rate": 0.0004903158095601565, "loss": 1.7354, "step": 46710 }, { "epoch": 9.68, "learning_rate": 0.0004902203988169068, "loss": 1.7392, "step": 46715 }, { "epoch": 9.68, "learning_rate": 0.0004901249880736572, "loss": 1.7337, "step": 46720 }, { "epoch": 9.68, "learning_rate": 0.0004900295773304074, "loss": 1.7331, "step": 46725 }, { "epoch": 9.68, "learning_rate": 0.0004899341665871577, "loss": 1.7352, "step": 46730 }, { "epoch": 9.68, "learning_rate": 0.000489838755843908, "loss": 1.7304, "step": 46735 }, { "epoch": 9.68, "learning_rate": 0.0004897433451006583, "loss": 1.7355, "step": 46740 }, { "epoch": 9.68, "learning_rate": 0.0004896479343574087, "loss": 1.7339, "step": 46745 }, { "epoch": 9.69, "learning_rate": 0.000489552523614159, "loss": 1.7357, "step": 46750 }, { "epoch": 9.69, "learning_rate": 0.0004894571128709092, "loss": 1.7316, "step": 46755 }, { "epoch": 9.69, "learning_rate": 0.0004893617021276596, "loss": 1.738, "step": 46760 }, { "epoch": 9.69, "learning_rate": 0.0004892662913844099, "loss": 1.7358, "step": 46765 }, { "epoch": 9.69, "learning_rate": 0.0004891708806411602, "loss": 1.7295, "step": 46770 }, { "epoch": 9.69, "learning_rate": 0.0004890754698979106, "loss": 1.7357, "step": 46775 }, { "epoch": 9.69, "learning_rate": 0.0004889800591546608, "loss": 1.7348, "step": 46780 }, { "epoch": 9.69, "learning_rate": 0.0004888846484114111, "loss": 1.7335, "step": 46785 }, { "epoch": 9.69, "learning_rate": 0.0004887892376681615, "loss": 1.738, "step": 46790 }, { "epoch": 9.69, "learning_rate": 0.0004886938269249118, "loss": 1.7327, "step": 46795 }, { "epoch": 9.7, "learning_rate": 0.0004885984161816621, "loss": 1.7337, "step": 46800 }, { "epoch": 9.7, "learning_rate": 0.0004885030054384124, "loss": 1.7366, "step": 46805 }, { "epoch": 9.7, "learning_rate": 0.0004884075946951626, "loss": 1.7335, "step": 46810 }, { "epoch": 9.7, "learning_rate": 0.000488312183951913, "loss": 1.7376, "step": 46815 }, { "epoch": 9.7, "learning_rate": 0.0004882167732086633, "loss": 1.7349, "step": 46820 }, { "epoch": 9.7, "learning_rate": 0.0004881213624654136, "loss": 1.7343, "step": 46825 }, { "epoch": 9.7, "learning_rate": 0.0004880259517221639, "loss": 1.7386, "step": 46830 }, { "epoch": 9.7, "learning_rate": 0.00048793054097891425, "loss": 1.7352, "step": 46835 }, { "epoch": 9.7, "learning_rate": 0.0004878351302356646, "loss": 1.7381, "step": 46840 }, { "epoch": 9.7, "learning_rate": 0.00048773971949241487, "loss": 1.7417, "step": 46845 }, { "epoch": 9.71, "learning_rate": 0.00048764430874916515, "loss": 1.7364, "step": 46850 }, { "epoch": 9.71, "learning_rate": 0.0004875488980059155, "loss": 1.7341, "step": 46855 }, { "epoch": 9.71, "learning_rate": 0.0004874534872626658, "loss": 1.7429, "step": 46860 }, { "epoch": 9.71, "learning_rate": 0.0004873580765194161, "loss": 1.7308, "step": 46865 }, { "epoch": 9.71, "learning_rate": 0.00048726266577616643, "loss": 1.7342, "step": 46870 }, { "epoch": 9.71, "learning_rate": 0.0004871672550329167, "loss": 1.7327, "step": 46875 }, { "epoch": 9.71, "learning_rate": 0.00048707184428966704, "loss": 1.7309, "step": 46880 }, { "epoch": 9.71, "learning_rate": 0.0004869764335464174, "loss": 1.7314, "step": 46885 }, { "epoch": 9.71, "learning_rate": 0.00048688102280316765, "loss": 1.7372, "step": 46890 }, { "epoch": 9.72, "learning_rate": 0.00048678561205991793, "loss": 1.7382, "step": 46895 }, { "epoch": 9.72, "learning_rate": 0.00048669020131666827, "loss": 1.7389, "step": 46900 }, { "epoch": 9.72, "learning_rate": 0.0004865947905734186, "loss": 1.7341, "step": 46905 }, { "epoch": 9.72, "learning_rate": 0.0004864993798301689, "loss": 1.7382, "step": 46910 }, { "epoch": 9.72, "learning_rate": 0.0004864039690869192, "loss": 1.7328, "step": 46915 }, { "epoch": 9.72, "learning_rate": 0.0004863085583436695, "loss": 1.7341, "step": 46920 }, { "epoch": 9.72, "learning_rate": 0.0004862131476004198, "loss": 1.7315, "step": 46925 }, { "epoch": 9.72, "learning_rate": 0.00048611773685717016, "loss": 1.7319, "step": 46930 }, { "epoch": 9.72, "learning_rate": 0.00048602232611392044, "loss": 1.7408, "step": 46935 }, { "epoch": 9.72, "learning_rate": 0.0004859269153706707, "loss": 1.7327, "step": 46940 }, { "epoch": 9.73, "learning_rate": 0.00048583150462742106, "loss": 1.7343, "step": 46945 }, { "epoch": 9.73, "learning_rate": 0.0004857360938841714, "loss": 1.734, "step": 46950 }, { "epoch": 9.73, "learning_rate": 0.00048564068314092167, "loss": 1.7326, "step": 46955 }, { "epoch": 9.73, "learning_rate": 0.000485545272397672, "loss": 1.731, "step": 46960 }, { "epoch": 9.73, "learning_rate": 0.0004854498616544223, "loss": 1.7298, "step": 46965 }, { "epoch": 9.73, "learning_rate": 0.00048535445091117257, "loss": 1.7378, "step": 46970 }, { "epoch": 9.73, "learning_rate": 0.00048525904016792295, "loss": 1.7346, "step": 46975 }, { "epoch": 9.73, "learning_rate": 0.00048516362942467323, "loss": 1.7357, "step": 46980 }, { "epoch": 9.73, "learning_rate": 0.0004850682186814235, "loss": 1.7297, "step": 46985 }, { "epoch": 9.73, "learning_rate": 0.00048497280793817385, "loss": 1.7348, "step": 46990 }, { "epoch": 9.74, "learning_rate": 0.0004848773971949242, "loss": 1.7344, "step": 46995 }, { "epoch": 9.74, "learning_rate": 0.00048478198645167446, "loss": 1.7314, "step": 47000 }, { "epoch": 9.74, "learning_rate": 0.0004846865757084248, "loss": 1.7395, "step": 47005 }, { "epoch": 9.74, "learning_rate": 0.0004845911649651751, "loss": 1.733, "step": 47010 }, { "epoch": 9.74, "learning_rate": 0.00048449575422192535, "loss": 1.7381, "step": 47015 }, { "epoch": 9.74, "learning_rate": 0.00048440034347867574, "loss": 1.7351, "step": 47020 }, { "epoch": 9.74, "learning_rate": 0.000484304932735426, "loss": 1.7349, "step": 47025 }, { "epoch": 9.74, "learning_rate": 0.0004842095219921763, "loss": 1.7308, "step": 47030 }, { "epoch": 9.74, "learning_rate": 0.00048411411124892664, "loss": 1.7345, "step": 47035 }, { "epoch": 9.75, "learning_rate": 0.0004840187005056769, "loss": 1.7299, "step": 47040 }, { "epoch": 9.75, "learning_rate": 0.00048392328976242725, "loss": 1.7337, "step": 47045 }, { "epoch": 9.75, "learning_rate": 0.0004838278790191776, "loss": 1.735, "step": 47050 }, { "epoch": 9.75, "learning_rate": 0.00048373246827592786, "loss": 1.7362, "step": 47055 }, { "epoch": 9.75, "learning_rate": 0.0004836370575326782, "loss": 1.7356, "step": 47060 }, { "epoch": 9.75, "learning_rate": 0.00048354164678942853, "loss": 1.737, "step": 47065 }, { "epoch": 9.75, "learning_rate": 0.0004834462360461788, "loss": 1.7374, "step": 47070 }, { "epoch": 9.75, "learning_rate": 0.00048335082530292915, "loss": 1.7347, "step": 47075 }, { "epoch": 9.75, "learning_rate": 0.0004832554145596794, "loss": 1.7337, "step": 47080 }, { "epoch": 9.75, "learning_rate": 0.0004831600038164297, "loss": 1.7357, "step": 47085 }, { "epoch": 9.76, "learning_rate": 0.0004830645930731801, "loss": 1.728, "step": 47090 }, { "epoch": 9.76, "learning_rate": 0.00048296918232993037, "loss": 1.7337, "step": 47095 }, { "epoch": 9.76, "learning_rate": 0.00048287377158668065, "loss": 1.7391, "step": 47100 }, { "epoch": 9.76, "learning_rate": 0.000482778360843431, "loss": 1.7338, "step": 47105 }, { "epoch": 9.76, "learning_rate": 0.0004826829501001813, "loss": 1.7309, "step": 47110 }, { "epoch": 9.76, "learning_rate": 0.0004825875393569316, "loss": 1.7334, "step": 47115 }, { "epoch": 9.76, "learning_rate": 0.00048249212861368193, "loss": 1.734, "step": 47120 }, { "epoch": 9.76, "learning_rate": 0.0004823967178704322, "loss": 1.7341, "step": 47125 }, { "epoch": 9.76, "learning_rate": 0.0004823013071271825, "loss": 1.7333, "step": 47130 }, { "epoch": 9.76, "learning_rate": 0.0004822058963839329, "loss": 1.7342, "step": 47135 }, { "epoch": 9.77, "learning_rate": 0.00048211048564068316, "loss": 1.7354, "step": 47140 }, { "epoch": 9.77, "learning_rate": 0.00048201507489743344, "loss": 1.7354, "step": 47145 }, { "epoch": 9.77, "learning_rate": 0.0004819196641541838, "loss": 1.738, "step": 47150 }, { "epoch": 9.77, "learning_rate": 0.00048182425341093406, "loss": 1.7393, "step": 47155 }, { "epoch": 9.77, "learning_rate": 0.0004817288426676844, "loss": 1.7355, "step": 47160 }, { "epoch": 9.77, "learning_rate": 0.0004816334319244347, "loss": 1.7377, "step": 47165 }, { "epoch": 9.77, "learning_rate": 0.000481538021181185, "loss": 1.7295, "step": 47170 }, { "epoch": 9.77, "learning_rate": 0.0004814426104379353, "loss": 1.731, "step": 47175 }, { "epoch": 9.77, "learning_rate": 0.00048134719969468567, "loss": 1.7318, "step": 47180 }, { "epoch": 9.78, "learning_rate": 0.00048125178895143595, "loss": 1.7374, "step": 47185 }, { "epoch": 9.78, "learning_rate": 0.00048115637820818623, "loss": 1.7352, "step": 47190 }, { "epoch": 9.78, "learning_rate": 0.00048106096746493656, "loss": 1.7382, "step": 47195 }, { "epoch": 9.78, "learning_rate": 0.00048096555672168684, "loss": 1.7353, "step": 47200 }, { "epoch": 9.78, "learning_rate": 0.0004808701459784372, "loss": 1.7331, "step": 47205 }, { "epoch": 9.78, "learning_rate": 0.0004807747352351875, "loss": 1.7308, "step": 47210 }, { "epoch": 9.78, "learning_rate": 0.0004806793244919378, "loss": 1.7346, "step": 47215 }, { "epoch": 9.78, "learning_rate": 0.00048058391374868807, "loss": 1.7365, "step": 47220 }, { "epoch": 9.78, "learning_rate": 0.00048048850300543846, "loss": 1.7341, "step": 47225 }, { "epoch": 9.78, "learning_rate": 0.00048039309226218874, "loss": 1.7377, "step": 47230 }, { "epoch": 9.79, "learning_rate": 0.000480297681518939, "loss": 1.7324, "step": 47235 }, { "epoch": 9.79, "learning_rate": 0.00048020227077568935, "loss": 1.7319, "step": 47240 }, { "epoch": 9.79, "learning_rate": 0.00048010686003243963, "loss": 1.7364, "step": 47245 }, { "epoch": 9.79, "learning_rate": 0.00048001144928918997, "loss": 1.7326, "step": 47250 }, { "epoch": 9.79, "learning_rate": 0.0004799160385459403, "loss": 1.733, "step": 47255 }, { "epoch": 9.79, "learning_rate": 0.0004798206278026906, "loss": 1.7333, "step": 47260 }, { "epoch": 9.79, "learning_rate": 0.00047972521705944086, "loss": 1.7343, "step": 47265 }, { "epoch": 9.79, "learning_rate": 0.0004796298063161912, "loss": 1.7328, "step": 47270 }, { "epoch": 9.79, "learning_rate": 0.00047953439557294153, "loss": 1.7364, "step": 47275 }, { "epoch": 9.79, "learning_rate": 0.00047943898482969186, "loss": 1.7274, "step": 47280 }, { "epoch": 9.8, "learning_rate": 0.00047934357408644214, "loss": 1.7377, "step": 47285 }, { "epoch": 9.8, "learning_rate": 0.0004792481633431924, "loss": 1.7387, "step": 47290 }, { "epoch": 9.8, "learning_rate": 0.0004791527525999428, "loss": 1.7373, "step": 47295 }, { "epoch": 9.8, "learning_rate": 0.0004790573418566931, "loss": 1.7346, "step": 47300 }, { "epoch": 9.8, "learning_rate": 0.00047896193111344337, "loss": 1.7312, "step": 47305 }, { "epoch": 9.8, "learning_rate": 0.0004788665203701937, "loss": 1.7386, "step": 47310 }, { "epoch": 9.8, "learning_rate": 0.000478771109626944, "loss": 1.7339, "step": 47315 }, { "epoch": 9.8, "learning_rate": 0.0004786756988836943, "loss": 1.736, "step": 47320 }, { "epoch": 9.8, "learning_rate": 0.00047858028814044465, "loss": 1.7371, "step": 47325 }, { "epoch": 9.81, "learning_rate": 0.00047848487739719493, "loss": 1.731, "step": 47330 }, { "epoch": 9.81, "learning_rate": 0.0004783894666539452, "loss": 1.7317, "step": 47335 }, { "epoch": 9.81, "learning_rate": 0.0004782940559106956, "loss": 1.7335, "step": 47340 }, { "epoch": 9.81, "learning_rate": 0.0004781986451674459, "loss": 1.7365, "step": 47345 }, { "epoch": 9.81, "learning_rate": 0.00047810323442419616, "loss": 1.7312, "step": 47350 }, { "epoch": 9.81, "learning_rate": 0.0004780078236809465, "loss": 1.7317, "step": 47355 }, { "epoch": 9.81, "learning_rate": 0.0004779124129376968, "loss": 1.7287, "step": 47360 }, { "epoch": 9.81, "learning_rate": 0.0004778170021944471, "loss": 1.7344, "step": 47365 }, { "epoch": 9.81, "learning_rate": 0.00047772159145119744, "loss": 1.7319, "step": 47370 }, { "epoch": 9.81, "learning_rate": 0.0004776261807079477, "loss": 1.7323, "step": 47375 }, { "epoch": 9.82, "learning_rate": 0.000477530769964698, "loss": 1.7311, "step": 47380 }, { "epoch": 9.82, "learning_rate": 0.00047743535922144834, "loss": 1.7349, "step": 47385 }, { "epoch": 9.82, "learning_rate": 0.00047733994847819867, "loss": 1.7327, "step": 47390 }, { "epoch": 9.82, "learning_rate": 0.00047724453773494895, "loss": 1.7336, "step": 47395 }, { "epoch": 9.82, "learning_rate": 0.0004771491269916993, "loss": 1.7297, "step": 47400 }, { "epoch": 9.82, "learning_rate": 0.00047705371624844956, "loss": 1.7341, "step": 47405 }, { "epoch": 9.82, "learning_rate": 0.0004769583055051999, "loss": 1.736, "step": 47410 }, { "epoch": 9.82, "learning_rate": 0.00047686289476195023, "loss": 1.7351, "step": 47415 }, { "epoch": 9.82, "learning_rate": 0.0004767674840187005, "loss": 1.7362, "step": 47420 }, { "epoch": 9.82, "learning_rate": 0.0004766720732754508, "loss": 1.7353, "step": 47425 }, { "epoch": 9.83, "learning_rate": 0.0004765766625322011, "loss": 1.7353, "step": 47430 }, { "epoch": 9.83, "learning_rate": 0.00047648125178895146, "loss": 1.7331, "step": 47435 }, { "epoch": 9.83, "learning_rate": 0.00047638584104570174, "loss": 1.7345, "step": 47440 }, { "epoch": 9.83, "learning_rate": 0.00047629043030245207, "loss": 1.7334, "step": 47445 }, { "epoch": 9.83, "learning_rate": 0.00047619501955920235, "loss": 1.7321, "step": 47450 }, { "epoch": 9.83, "learning_rate": 0.0004760996088159527, "loss": 1.7293, "step": 47455 }, { "epoch": 9.83, "learning_rate": 0.000476004198072703, "loss": 1.7341, "step": 47460 }, { "epoch": 9.83, "learning_rate": 0.0004759087873294533, "loss": 1.7296, "step": 47465 }, { "epoch": 9.83, "learning_rate": 0.0004758133765862036, "loss": 1.7364, "step": 47470 }, { "epoch": 9.84, "learning_rate": 0.0004757179658429539, "loss": 1.7382, "step": 47475 }, { "epoch": 9.84, "learning_rate": 0.00047562255509970425, "loss": 1.731, "step": 47480 }, { "epoch": 9.84, "learning_rate": 0.0004755271443564546, "loss": 1.7357, "step": 47485 }, { "epoch": 9.84, "learning_rate": 0.00047543173361320486, "loss": 1.7378, "step": 47490 }, { "epoch": 9.84, "learning_rate": 0.00047533632286995514, "loss": 1.7316, "step": 47495 }, { "epoch": 9.84, "learning_rate": 0.00047524091212670553, "loss": 1.7312, "step": 47500 }, { "epoch": 9.84, "learning_rate": 0.0004751455013834558, "loss": 1.7291, "step": 47505 }, { "epoch": 9.84, "learning_rate": 0.0004750500906402061, "loss": 1.7344, "step": 47510 }, { "epoch": 9.84, "learning_rate": 0.0004749546798969564, "loss": 1.7388, "step": 47515 }, { "epoch": 9.84, "learning_rate": 0.0004748592691537067, "loss": 1.7288, "step": 47520 }, { "epoch": 9.85, "learning_rate": 0.00047476385841045704, "loss": 1.7329, "step": 47525 }, { "epoch": 9.85, "learning_rate": 0.00047466844766720737, "loss": 1.7341, "step": 47530 }, { "epoch": 9.85, "learning_rate": 0.00047457303692395765, "loss": 1.736, "step": 47535 }, { "epoch": 9.85, "learning_rate": 0.00047447762618070793, "loss": 1.7275, "step": 47540 }, { "epoch": 9.85, "learning_rate": 0.00047438221543745826, "loss": 1.7361, "step": 47545 }, { "epoch": 9.85, "learning_rate": 0.0004742868046942086, "loss": 1.7354, "step": 47550 }, { "epoch": 9.85, "learning_rate": 0.0004741913939509589, "loss": 1.7367, "step": 47555 }, { "epoch": 9.85, "learning_rate": 0.0004740959832077092, "loss": 1.7346, "step": 47560 }, { "epoch": 9.85, "learning_rate": 0.0004740005724644595, "loss": 1.7375, "step": 47565 }, { "epoch": 9.85, "learning_rate": 0.0004739051617212098, "loss": 1.7351, "step": 47570 }, { "epoch": 9.86, "learning_rate": 0.00047380975097796016, "loss": 1.7332, "step": 47575 }, { "epoch": 9.86, "learning_rate": 0.00047371434023471044, "loss": 1.7331, "step": 47580 }, { "epoch": 9.86, "learning_rate": 0.0004736189294914607, "loss": 1.7362, "step": 47585 }, { "epoch": 9.86, "learning_rate": 0.00047352351874821105, "loss": 1.7369, "step": 47590 }, { "epoch": 9.86, "learning_rate": 0.0004734281080049614, "loss": 1.7353, "step": 47595 }, { "epoch": 9.86, "learning_rate": 0.00047333269726171167, "loss": 1.7321, "step": 47600 }, { "epoch": 9.86, "learning_rate": 0.000473237286518462, "loss": 1.7338, "step": 47605 }, { "epoch": 9.86, "learning_rate": 0.0004731418757752123, "loss": 1.7327, "step": 47610 }, { "epoch": 9.86, "learning_rate": 0.0004730464650319626, "loss": 1.7297, "step": 47615 }, { "epoch": 9.87, "learning_rate": 0.00047295105428871295, "loss": 1.7355, "step": 47620 }, { "epoch": 9.87, "learning_rate": 0.00047285564354546323, "loss": 1.727, "step": 47625 }, { "epoch": 9.87, "learning_rate": 0.0004727602328022135, "loss": 1.7365, "step": 47630 }, { "epoch": 9.87, "learning_rate": 0.00047266482205896384, "loss": 1.7339, "step": 47635 }, { "epoch": 9.87, "learning_rate": 0.0004725694113157142, "loss": 1.7358, "step": 47640 }, { "epoch": 9.87, "learning_rate": 0.00047247400057246446, "loss": 1.7314, "step": 47645 }, { "epoch": 9.87, "learning_rate": 0.0004723785898292148, "loss": 1.7406, "step": 47650 }, { "epoch": 9.87, "learning_rate": 0.00047228317908596507, "loss": 1.7354, "step": 47655 }, { "epoch": 9.87, "learning_rate": 0.00047218776834271535, "loss": 1.7317, "step": 47660 }, { "epoch": 9.87, "learning_rate": 0.00047209235759946574, "loss": 1.728, "step": 47665 }, { "epoch": 9.88, "learning_rate": 0.000471996946856216, "loss": 1.732, "step": 47670 }, { "epoch": 9.88, "learning_rate": 0.0004719015361129663, "loss": 1.7391, "step": 47675 }, { "epoch": 9.88, "learning_rate": 0.00047180612536971663, "loss": 1.7376, "step": 47680 }, { "epoch": 9.88, "learning_rate": 0.00047171071462646697, "loss": 1.7338, "step": 47685 }, { "epoch": 9.88, "learning_rate": 0.0004716153038832173, "loss": 1.7369, "step": 47690 }, { "epoch": 9.88, "learning_rate": 0.0004715198931399676, "loss": 1.7366, "step": 47695 }, { "epoch": 9.88, "learning_rate": 0.00047142448239671786, "loss": 1.7341, "step": 47700 }, { "epoch": 9.88, "learning_rate": 0.0004713290716534682, "loss": 1.7385, "step": 47705 }, { "epoch": 9.88, "learning_rate": 0.0004712336609102185, "loss": 1.7313, "step": 47710 }, { "epoch": 9.89, "learning_rate": 0.0004711382501669688, "loss": 1.7357, "step": 47715 }, { "epoch": 9.89, "learning_rate": 0.00047104283942371914, "loss": 1.7354, "step": 47720 }, { "epoch": 9.89, "learning_rate": 0.0004709474286804694, "loss": 1.7347, "step": 47725 }, { "epoch": 9.89, "learning_rate": 0.00047085201793721975, "loss": 1.7331, "step": 47730 }, { "epoch": 9.89, "learning_rate": 0.0004707566071939701, "loss": 1.7378, "step": 47735 }, { "epoch": 9.89, "learning_rate": 0.00047066119645072037, "loss": 1.7349, "step": 47740 }, { "epoch": 9.89, "learning_rate": 0.00047056578570747065, "loss": 1.7401, "step": 47745 }, { "epoch": 9.89, "learning_rate": 0.000470470374964221, "loss": 1.736, "step": 47750 }, { "epoch": 9.89, "learning_rate": 0.0004703749642209713, "loss": 1.7336, "step": 47755 }, { "epoch": 9.89, "learning_rate": 0.0004702795534777216, "loss": 1.7274, "step": 47760 }, { "epoch": 9.9, "learning_rate": 0.00047018414273447193, "loss": 1.7348, "step": 47765 }, { "epoch": 9.9, "learning_rate": 0.0004700887319912222, "loss": 1.7346, "step": 47770 }, { "epoch": 9.9, "learning_rate": 0.0004699933212479725, "loss": 1.7243, "step": 47775 }, { "epoch": 9.9, "learning_rate": 0.0004698979105047229, "loss": 1.732, "step": 47780 }, { "epoch": 9.9, "learning_rate": 0.00046980249976147316, "loss": 1.7337, "step": 47785 }, { "epoch": 9.9, "learning_rate": 0.00046970708901822344, "loss": 1.7344, "step": 47790 }, { "epoch": 9.9, "learning_rate": 0.00046961167827497377, "loss": 1.734, "step": 47795 }, { "epoch": 9.9, "learning_rate": 0.0004695162675317241, "loss": 1.7319, "step": 47800 }, { "epoch": 9.9, "learning_rate": 0.0004694208567884744, "loss": 1.7357, "step": 47805 }, { "epoch": 9.9, "learning_rate": 0.0004693254460452247, "loss": 1.7328, "step": 47810 }, { "epoch": 9.91, "learning_rate": 0.000469230035301975, "loss": 1.7349, "step": 47815 }, { "epoch": 9.91, "learning_rate": 0.0004691346245587253, "loss": 1.7406, "step": 47820 }, { "epoch": 9.91, "learning_rate": 0.00046903921381547567, "loss": 1.7336, "step": 47825 }, { "epoch": 9.91, "learning_rate": 0.00046894380307222595, "loss": 1.7344, "step": 47830 }, { "epoch": 9.91, "learning_rate": 0.0004688483923289762, "loss": 1.7375, "step": 47835 }, { "epoch": 9.91, "learning_rate": 0.00046875298158572656, "loss": 1.7339, "step": 47840 }, { "epoch": 9.91, "learning_rate": 0.0004686575708424769, "loss": 1.7395, "step": 47845 }, { "epoch": 9.91, "learning_rate": 0.0004685621600992272, "loss": 1.7367, "step": 47850 }, { "epoch": 9.91, "learning_rate": 0.0004684667493559775, "loss": 1.7339, "step": 47855 }, { "epoch": 9.92, "learning_rate": 0.0004683713386127278, "loss": 1.7334, "step": 47860 }, { "epoch": 9.92, "learning_rate": 0.00046827592786947807, "loss": 1.7289, "step": 47865 }, { "epoch": 9.92, "learning_rate": 0.00046818051712622846, "loss": 1.7326, "step": 47870 }, { "epoch": 9.92, "learning_rate": 0.00046808510638297874, "loss": 1.732, "step": 47875 }, { "epoch": 9.92, "learning_rate": 0.000467989695639729, "loss": 1.7325, "step": 47880 }, { "epoch": 9.92, "learning_rate": 0.00046789428489647935, "loss": 1.7326, "step": 47885 }, { "epoch": 9.92, "learning_rate": 0.00046779887415322963, "loss": 1.7326, "step": 47890 }, { "epoch": 9.92, "learning_rate": 0.00046770346340997996, "loss": 1.7322, "step": 47895 }, { "epoch": 9.92, "learning_rate": 0.0004676080526667303, "loss": 1.7296, "step": 47900 }, { "epoch": 9.92, "learning_rate": 0.0004675126419234806, "loss": 1.7324, "step": 47905 }, { "epoch": 9.93, "learning_rate": 0.0004674172311802309, "loss": 1.7299, "step": 47910 }, { "epoch": 9.93, "learning_rate": 0.00046732182043698124, "loss": 1.7333, "step": 47915 }, { "epoch": 9.93, "learning_rate": 0.0004672264096937315, "loss": 1.7346, "step": 47920 }, { "epoch": 9.93, "learning_rate": 0.00046713099895048186, "loss": 1.7331, "step": 47925 }, { "epoch": 9.93, "learning_rate": 0.00046703558820723214, "loss": 1.7336, "step": 47930 }, { "epoch": 9.93, "learning_rate": 0.0004669401774639824, "loss": 1.7347, "step": 47935 }, { "epoch": 9.93, "learning_rate": 0.0004668447667207328, "loss": 1.7353, "step": 47940 }, { "epoch": 9.93, "learning_rate": 0.0004667493559774831, "loss": 1.7389, "step": 47945 }, { "epoch": 9.93, "learning_rate": 0.00046665394523423337, "loss": 1.7335, "step": 47950 }, { "epoch": 9.93, "learning_rate": 0.0004665585344909837, "loss": 1.7369, "step": 47955 }, { "epoch": 9.94, "learning_rate": 0.00046646312374773403, "loss": 1.7328, "step": 47960 }, { "epoch": 9.94, "learning_rate": 0.0004663677130044843, "loss": 1.7356, "step": 47965 }, { "epoch": 9.94, "learning_rate": 0.00046627230226123465, "loss": 1.7384, "step": 47970 }, { "epoch": 9.94, "learning_rate": 0.00046617689151798493, "loss": 1.7381, "step": 47975 }, { "epoch": 9.94, "learning_rate": 0.0004660814807747352, "loss": 1.7315, "step": 47980 }, { "epoch": 9.94, "learning_rate": 0.0004659860700314856, "loss": 1.733, "step": 47985 }, { "epoch": 9.94, "learning_rate": 0.0004658906592882359, "loss": 1.732, "step": 47990 }, { "epoch": 9.94, "learning_rate": 0.00046579524854498616, "loss": 1.7305, "step": 47995 }, { "epoch": 9.94, "learning_rate": 0.0004656998378017365, "loss": 1.7353, "step": 48000 }, { "epoch": 9.94, "eval_accuracy": 0.5433986928104575, "eval_loss": 1.9257314205169678, "eval_runtime": 1.0105, "eval_samples_per_second": 148.435, "eval_steps_per_second": 0.99, "step": 48000 }, { "epoch": 9.95, "learning_rate": 0.00046560442705848677, "loss": 1.7316, "step": 48005 }, { "epoch": 9.95, "learning_rate": 0.0004655090163152371, "loss": 1.7337, "step": 48010 }, { "epoch": 9.95, "learning_rate": 0.00046541360557198744, "loss": 1.7318, "step": 48015 }, { "epoch": 9.95, "learning_rate": 0.0004653181948287377, "loss": 1.7351, "step": 48020 }, { "epoch": 9.95, "learning_rate": 0.000465222784085488, "loss": 1.7356, "step": 48025 }, { "epoch": 9.95, "learning_rate": 0.0004651273733422384, "loss": 1.7316, "step": 48030 }, { "epoch": 9.95, "learning_rate": 0.00046503196259898866, "loss": 1.74, "step": 48035 }, { "epoch": 9.95, "learning_rate": 0.00046493655185573894, "loss": 1.7315, "step": 48040 }, { "epoch": 9.95, "learning_rate": 0.0004648411411124893, "loss": 1.7411, "step": 48045 }, { "epoch": 9.95, "learning_rate": 0.00046474573036923956, "loss": 1.7307, "step": 48050 }, { "epoch": 9.96, "learning_rate": 0.0004646503196259899, "loss": 1.731, "step": 48055 }, { "epoch": 9.96, "learning_rate": 0.0004645549088827402, "loss": 1.7307, "step": 48060 }, { "epoch": 9.96, "learning_rate": 0.0004644594981394905, "loss": 1.733, "step": 48065 }, { "epoch": 9.96, "learning_rate": 0.0004643640873962408, "loss": 1.7343, "step": 48070 }, { "epoch": 9.96, "learning_rate": 0.0004642686766529912, "loss": 1.7339, "step": 48075 }, { "epoch": 9.96, "learning_rate": 0.00046417326590974145, "loss": 1.7287, "step": 48080 }, { "epoch": 9.96, "learning_rate": 0.00046407785516649173, "loss": 1.7336, "step": 48085 }, { "epoch": 9.96, "learning_rate": 0.00046398244442324207, "loss": 1.7324, "step": 48090 }, { "epoch": 9.96, "learning_rate": 0.00046388703367999235, "loss": 1.7376, "step": 48095 }, { "epoch": 9.96, "learning_rate": 0.0004637916229367427, "loss": 1.7357, "step": 48100 }, { "epoch": 9.97, "learning_rate": 0.000463696212193493, "loss": 1.734, "step": 48105 }, { "epoch": 9.97, "learning_rate": 0.0004636008014502433, "loss": 1.7345, "step": 48110 }, { "epoch": 9.97, "learning_rate": 0.0004635053907069936, "loss": 1.7319, "step": 48115 }, { "epoch": 9.97, "learning_rate": 0.0004634099799637439, "loss": 1.7308, "step": 48120 }, { "epoch": 9.97, "learning_rate": 0.00046331456922049424, "loss": 1.7348, "step": 48125 }, { "epoch": 9.97, "learning_rate": 0.0004632191584772446, "loss": 1.7344, "step": 48130 }, { "epoch": 9.97, "learning_rate": 0.00046312374773399486, "loss": 1.7374, "step": 48135 }, { "epoch": 9.97, "learning_rate": 0.00046302833699074514, "loss": 1.7325, "step": 48140 }, { "epoch": 9.97, "learning_rate": 0.0004629329262474955, "loss": 1.734, "step": 48145 }, { "epoch": 9.98, "learning_rate": 0.0004628375155042458, "loss": 1.7311, "step": 48150 }, { "epoch": 9.98, "learning_rate": 0.0004627421047609961, "loss": 1.7346, "step": 48155 }, { "epoch": 9.98, "learning_rate": 0.0004626466940177464, "loss": 1.7338, "step": 48160 }, { "epoch": 9.98, "learning_rate": 0.0004625512832744967, "loss": 1.7304, "step": 48165 }, { "epoch": 9.98, "learning_rate": 0.00046245587253124703, "loss": 1.7335, "step": 48170 }, { "epoch": 9.98, "learning_rate": 0.00046236046178799737, "loss": 1.7363, "step": 48175 }, { "epoch": 9.98, "learning_rate": 0.00046226505104474765, "loss": 1.7314, "step": 48180 }, { "epoch": 9.98, "learning_rate": 0.0004621696403014979, "loss": 1.7318, "step": 48185 }, { "epoch": 9.98, "learning_rate": 0.0004620742295582483, "loss": 1.7329, "step": 48190 }, { "epoch": 9.98, "learning_rate": 0.0004619788188149986, "loss": 1.7343, "step": 48195 }, { "epoch": 9.99, "learning_rate": 0.0004618834080717489, "loss": 1.7355, "step": 48200 }, { "epoch": 9.99, "learning_rate": 0.0004617879973284992, "loss": 1.7319, "step": 48205 }, { "epoch": 9.99, "learning_rate": 0.0004616925865852495, "loss": 1.7352, "step": 48210 }, { "epoch": 9.99, "learning_rate": 0.0004615971758419998, "loss": 1.7303, "step": 48215 }, { "epoch": 9.99, "learning_rate": 0.00046150176509875015, "loss": 1.7309, "step": 48220 }, { "epoch": 9.99, "learning_rate": 0.00046140635435550043, "loss": 1.7387, "step": 48225 }, { "epoch": 9.99, "learning_rate": 0.0004613109436122507, "loss": 1.7398, "step": 48230 }, { "epoch": 9.99, "learning_rate": 0.0004612155328690011, "loss": 1.7362, "step": 48235 }, { "epoch": 9.99, "learning_rate": 0.0004611201221257514, "loss": 1.7313, "step": 48240 }, { "epoch": 9.99, "learning_rate": 0.00046102471138250166, "loss": 1.7286, "step": 48245 }, { "epoch": 10.0, "learning_rate": 0.000460929300639252, "loss": 1.7319, "step": 48250 }, { "epoch": 10.0, "learning_rate": 0.0004608338898960023, "loss": 1.7343, "step": 48255 }, { "epoch": 10.0, "learning_rate": 0.0004607384791527526, "loss": 1.7315, "step": 48260 }, { "epoch": 10.0, "learning_rate": 0.00046064306840950294, "loss": 1.7375, "step": 48265 }, { "epoch": 10.0, "learning_rate": 0.0004605476576662532, "loss": 1.7301, "step": 48270 }, { "epoch": 10.0, "learning_rate": 0.0004604522469230035, "loss": 1.7285, "step": 48275 }, { "epoch": 10.0, "learning_rate": 0.00046035683617975384, "loss": 1.7275, "step": 48280 }, { "epoch": 10.0, "learning_rate": 0.00046026142543650417, "loss": 1.7217, "step": 48285 }, { "epoch": 10.0, "learning_rate": 0.00046016601469325445, "loss": 1.7264, "step": 48290 }, { "epoch": 10.01, "learning_rate": 0.0004600706039500048, "loss": 1.7198, "step": 48295 }, { "epoch": 10.01, "learning_rate": 0.00045997519320675506, "loss": 1.7243, "step": 48300 }, { "epoch": 10.01, "learning_rate": 0.0004598797824635054, "loss": 1.7216, "step": 48305 }, { "epoch": 10.01, "learning_rate": 0.00045978437172025573, "loss": 1.7233, "step": 48310 }, { "epoch": 10.01, "learning_rate": 0.000459688960977006, "loss": 1.7247, "step": 48315 }, { "epoch": 10.01, "learning_rate": 0.0004595935502337563, "loss": 1.722, "step": 48320 }, { "epoch": 10.01, "learning_rate": 0.0004594981394905066, "loss": 1.7242, "step": 48325 }, { "epoch": 10.01, "learning_rate": 0.00045940272874725696, "loss": 1.7235, "step": 48330 }, { "epoch": 10.01, "learning_rate": 0.0004593073180040073, "loss": 1.7235, "step": 48335 }, { "epoch": 10.01, "learning_rate": 0.0004592119072607576, "loss": 1.7253, "step": 48340 }, { "epoch": 10.02, "learning_rate": 0.00045911649651750785, "loss": 1.7227, "step": 48345 }, { "epoch": 10.02, "learning_rate": 0.00045902108577425824, "loss": 1.7267, "step": 48350 }, { "epoch": 10.02, "learning_rate": 0.0004589256750310085, "loss": 1.7266, "step": 48355 }, { "epoch": 10.02, "learning_rate": 0.0004588302642877588, "loss": 1.7253, "step": 48360 }, { "epoch": 10.02, "learning_rate": 0.00045873485354450914, "loss": 1.7298, "step": 48365 }, { "epoch": 10.02, "learning_rate": 0.0004586394428012594, "loss": 1.7261, "step": 48370 }, { "epoch": 10.02, "learning_rate": 0.00045854403205800975, "loss": 1.7226, "step": 48375 }, { "epoch": 10.02, "learning_rate": 0.0004584486213147601, "loss": 1.7213, "step": 48380 }, { "epoch": 10.02, "learning_rate": 0.00045835321057151036, "loss": 1.7262, "step": 48385 }, { "epoch": 10.02, "learning_rate": 0.00045825779982826064, "loss": 1.7259, "step": 48390 }, { "epoch": 10.03, "learning_rate": 0.000458162389085011, "loss": 1.7206, "step": 48395 }, { "epoch": 10.03, "learning_rate": 0.0004580669783417613, "loss": 1.7258, "step": 48400 }, { "epoch": 10.03, "learning_rate": 0.0004579715675985116, "loss": 1.7256, "step": 48405 }, { "epoch": 10.03, "learning_rate": 0.0004578761568552619, "loss": 1.7236, "step": 48410 }, { "epoch": 10.03, "learning_rate": 0.0004577807461120122, "loss": 1.7298, "step": 48415 }, { "epoch": 10.03, "learning_rate": 0.00045768533536876254, "loss": 1.723, "step": 48420 }, { "epoch": 10.03, "learning_rate": 0.00045758992462551287, "loss": 1.7233, "step": 48425 }, { "epoch": 10.03, "learning_rate": 0.00045749451388226315, "loss": 1.7257, "step": 48430 }, { "epoch": 10.03, "learning_rate": 0.00045739910313901343, "loss": 1.7254, "step": 48435 }, { "epoch": 10.04, "learning_rate": 0.00045730369239576377, "loss": 1.7236, "step": 48440 }, { "epoch": 10.04, "learning_rate": 0.0004572082816525141, "loss": 1.7272, "step": 48445 }, { "epoch": 10.04, "learning_rate": 0.0004571128709092644, "loss": 1.733, "step": 48450 }, { "epoch": 10.04, "learning_rate": 0.0004570174601660147, "loss": 1.7212, "step": 48455 }, { "epoch": 10.04, "learning_rate": 0.000456922049422765, "loss": 1.7333, "step": 48460 }, { "epoch": 10.04, "learning_rate": 0.00045682663867951533, "loss": 1.7328, "step": 48465 }, { "epoch": 10.04, "learning_rate": 0.00045673122793626566, "loss": 1.7247, "step": 48470 }, { "epoch": 10.04, "learning_rate": 0.00045663581719301594, "loss": 1.7242, "step": 48475 }, { "epoch": 10.04, "learning_rate": 0.0004565404064497662, "loss": 1.7254, "step": 48480 }, { "epoch": 10.04, "learning_rate": 0.00045644499570651656, "loss": 1.7171, "step": 48485 }, { "epoch": 10.05, "learning_rate": 0.0004563495849632669, "loss": 1.7272, "step": 48490 }, { "epoch": 10.05, "learning_rate": 0.00045625417422001717, "loss": 1.72, "step": 48495 }, { "epoch": 10.05, "learning_rate": 0.0004561587634767675, "loss": 1.7213, "step": 48500 }, { "epoch": 10.05, "learning_rate": 0.0004560633527335178, "loss": 1.7229, "step": 48505 }, { "epoch": 10.05, "learning_rate": 0.00045596794199026806, "loss": 1.7224, "step": 48510 }, { "epoch": 10.05, "learning_rate": 0.00045587253124701845, "loss": 1.7273, "step": 48515 }, { "epoch": 10.05, "learning_rate": 0.00045577712050376873, "loss": 1.7256, "step": 48520 }, { "epoch": 10.05, "learning_rate": 0.000455681709760519, "loss": 1.7241, "step": 48525 }, { "epoch": 10.05, "learning_rate": 0.00045558629901726934, "loss": 1.7265, "step": 48530 }, { "epoch": 10.05, "learning_rate": 0.0004554908882740197, "loss": 1.7224, "step": 48535 }, { "epoch": 10.06, "learning_rate": 0.00045539547753077, "loss": 1.7292, "step": 48540 }, { "epoch": 10.06, "learning_rate": 0.0004553000667875203, "loss": 1.7231, "step": 48545 }, { "epoch": 10.06, "learning_rate": 0.00045520465604427057, "loss": 1.7301, "step": 48550 }, { "epoch": 10.06, "learning_rate": 0.0004551092453010209, "loss": 1.7267, "step": 48555 }, { "epoch": 10.06, "learning_rate": 0.00045501383455777124, "loss": 1.7238, "step": 48560 }, { "epoch": 10.06, "learning_rate": 0.0004549184238145215, "loss": 1.7201, "step": 48565 }, { "epoch": 10.06, "learning_rate": 0.00045482301307127185, "loss": 1.7255, "step": 48570 }, { "epoch": 10.06, "learning_rate": 0.00045472760232802213, "loss": 1.7253, "step": 48575 }, { "epoch": 10.06, "learning_rate": 0.00045463219158477247, "loss": 1.7243, "step": 48580 }, { "epoch": 10.07, "learning_rate": 0.0004545367808415228, "loss": 1.7291, "step": 48585 }, { "epoch": 10.07, "learning_rate": 0.0004544413700982731, "loss": 1.7278, "step": 48590 }, { "epoch": 10.07, "learning_rate": 0.00045434595935502336, "loss": 1.7294, "step": 48595 }, { "epoch": 10.07, "learning_rate": 0.0004542505486117737, "loss": 1.731, "step": 48600 }, { "epoch": 10.07, "learning_rate": 0.00045415513786852403, "loss": 1.7291, "step": 48605 }, { "epoch": 10.07, "learning_rate": 0.0004540597271252743, "loss": 1.7227, "step": 48610 }, { "epoch": 10.07, "learning_rate": 0.00045396431638202464, "loss": 1.7233, "step": 48615 }, { "epoch": 10.07, "learning_rate": 0.0004538689056387749, "loss": 1.7249, "step": 48620 }, { "epoch": 10.07, "learning_rate": 0.0004537734948955252, "loss": 1.7231, "step": 48625 }, { "epoch": 10.07, "learning_rate": 0.0004536780841522756, "loss": 1.7258, "step": 48630 }, { "epoch": 10.08, "learning_rate": 0.00045358267340902587, "loss": 1.7191, "step": 48635 }, { "epoch": 10.08, "learning_rate": 0.00045348726266577615, "loss": 1.728, "step": 48640 }, { "epoch": 10.08, "learning_rate": 0.0004533918519225265, "loss": 1.7248, "step": 48645 }, { "epoch": 10.08, "learning_rate": 0.0004532964411792768, "loss": 1.7236, "step": 48650 }, { "epoch": 10.08, "learning_rate": 0.0004532010304360271, "loss": 1.7253, "step": 48655 }, { "epoch": 10.08, "learning_rate": 0.00045310561969277743, "loss": 1.7218, "step": 48660 }, { "epoch": 10.08, "learning_rate": 0.0004530102089495277, "loss": 1.7224, "step": 48665 }, { "epoch": 10.08, "learning_rate": 0.000452914798206278, "loss": 1.7242, "step": 48670 }, { "epoch": 10.08, "learning_rate": 0.0004528193874630284, "loss": 1.7252, "step": 48675 }, { "epoch": 10.08, "learning_rate": 0.00045272397671977866, "loss": 1.7272, "step": 48680 }, { "epoch": 10.09, "learning_rate": 0.00045262856597652894, "loss": 1.7281, "step": 48685 }, { "epoch": 10.09, "learning_rate": 0.0004525331552332793, "loss": 1.7208, "step": 48690 }, { "epoch": 10.09, "learning_rate": 0.0004524377444900296, "loss": 1.7285, "step": 48695 }, { "epoch": 10.09, "learning_rate": 0.0004523423337467799, "loss": 1.7229, "step": 48700 }, { "epoch": 10.09, "learning_rate": 0.0004522469230035302, "loss": 1.7303, "step": 48705 }, { "epoch": 10.09, "learning_rate": 0.0004521515122602805, "loss": 1.7242, "step": 48710 }, { "epoch": 10.09, "learning_rate": 0.0004520561015170308, "loss": 1.7244, "step": 48715 }, { "epoch": 10.09, "learning_rate": 0.00045196069077378117, "loss": 1.7223, "step": 48720 }, { "epoch": 10.09, "learning_rate": 0.00045186528003053145, "loss": 1.726, "step": 48725 }, { "epoch": 10.1, "learning_rate": 0.00045176986928728173, "loss": 1.7249, "step": 48730 }, { "epoch": 10.1, "learning_rate": 0.00045167445854403206, "loss": 1.7286, "step": 48735 }, { "epoch": 10.1, "learning_rate": 0.00045157904780078234, "loss": 1.7306, "step": 48740 }, { "epoch": 10.1, "learning_rate": 0.00045148363705753273, "loss": 1.724, "step": 48745 }, { "epoch": 10.1, "learning_rate": 0.000451388226314283, "loss": 1.7287, "step": 48750 }, { "epoch": 10.1, "learning_rate": 0.0004512928155710333, "loss": 1.7226, "step": 48755 }, { "epoch": 10.1, "learning_rate": 0.0004511974048277836, "loss": 1.7239, "step": 48760 }, { "epoch": 10.1, "learning_rate": 0.00045110199408453396, "loss": 1.725, "step": 48765 }, { "epoch": 10.1, "learning_rate": 0.00045100658334128424, "loss": 1.728, "step": 48770 }, { "epoch": 10.1, "learning_rate": 0.00045091117259803457, "loss": 1.7285, "step": 48775 }, { "epoch": 10.11, "learning_rate": 0.00045081576185478485, "loss": 1.7252, "step": 48780 }, { "epoch": 10.11, "learning_rate": 0.00045072035111153513, "loss": 1.7245, "step": 48785 }, { "epoch": 10.11, "learning_rate": 0.0004506249403682855, "loss": 1.7257, "step": 48790 }, { "epoch": 10.11, "learning_rate": 0.0004505295296250358, "loss": 1.7271, "step": 48795 }, { "epoch": 10.11, "learning_rate": 0.0004504341188817861, "loss": 1.7204, "step": 48800 }, { "epoch": 10.11, "learning_rate": 0.0004503387081385364, "loss": 1.7258, "step": 48805 }, { "epoch": 10.11, "learning_rate": 0.00045024329739528675, "loss": 1.7327, "step": 48810 }, { "epoch": 10.11, "learning_rate": 0.000450147886652037, "loss": 1.7211, "step": 48815 }, { "epoch": 10.11, "learning_rate": 0.00045005247590878736, "loss": 1.7259, "step": 48820 }, { "epoch": 10.11, "learning_rate": 0.00044995706516553764, "loss": 1.724, "step": 48825 }, { "epoch": 10.12, "learning_rate": 0.0004498616544222879, "loss": 1.7229, "step": 48830 }, { "epoch": 10.12, "learning_rate": 0.0004497662436790383, "loss": 1.7273, "step": 48835 }, { "epoch": 10.12, "learning_rate": 0.0004496708329357886, "loss": 1.7233, "step": 48840 }, { "epoch": 10.12, "learning_rate": 0.00044957542219253887, "loss": 1.729, "step": 48845 }, { "epoch": 10.12, "learning_rate": 0.0004494800114492892, "loss": 1.7248, "step": 48850 }, { "epoch": 10.12, "learning_rate": 0.00044938460070603954, "loss": 1.7228, "step": 48855 }, { "epoch": 10.12, "learning_rate": 0.0004492891899627898, "loss": 1.7189, "step": 48860 }, { "epoch": 10.12, "learning_rate": 0.00044919377921954015, "loss": 1.7284, "step": 48865 }, { "epoch": 10.12, "learning_rate": 0.00044909836847629043, "loss": 1.7254, "step": 48870 }, { "epoch": 10.13, "learning_rate": 0.0004490029577330407, "loss": 1.7181, "step": 48875 }, { "epoch": 10.13, "learning_rate": 0.0004489075469897911, "loss": 1.7223, "step": 48880 }, { "epoch": 10.13, "learning_rate": 0.0004488121362465414, "loss": 1.7243, "step": 48885 }, { "epoch": 10.13, "learning_rate": 0.00044871672550329166, "loss": 1.7301, "step": 48890 }, { "epoch": 10.13, "learning_rate": 0.000448621314760042, "loss": 1.7261, "step": 48895 }, { "epoch": 10.13, "learning_rate": 0.00044852590401679227, "loss": 1.7264, "step": 48900 }, { "epoch": 10.13, "learning_rate": 0.0004484304932735426, "loss": 1.724, "step": 48905 }, { "epoch": 10.13, "learning_rate": 0.00044833508253029294, "loss": 1.7237, "step": 48910 }, { "epoch": 10.13, "learning_rate": 0.0004482396717870432, "loss": 1.7267, "step": 48915 }, { "epoch": 10.13, "learning_rate": 0.0004481442610437935, "loss": 1.7249, "step": 48920 }, { "epoch": 10.14, "learning_rate": 0.0004480488503005439, "loss": 1.7253, "step": 48925 }, { "epoch": 10.14, "learning_rate": 0.00044795343955729417, "loss": 1.7283, "step": 48930 }, { "epoch": 10.14, "learning_rate": 0.00044785802881404445, "loss": 1.731, "step": 48935 }, { "epoch": 10.14, "learning_rate": 0.0004477626180707948, "loss": 1.7219, "step": 48940 }, { "epoch": 10.14, "learning_rate": 0.00044766720732754506, "loss": 1.7185, "step": 48945 }, { "epoch": 10.14, "learning_rate": 0.0004475717965842954, "loss": 1.7286, "step": 48950 }, { "epoch": 10.14, "learning_rate": 0.00044747638584104573, "loss": 1.7268, "step": 48955 }, { "epoch": 10.14, "learning_rate": 0.000447380975097796, "loss": 1.7287, "step": 48960 }, { "epoch": 10.14, "learning_rate": 0.0004472855643545463, "loss": 1.7235, "step": 48965 }, { "epoch": 10.15, "learning_rate": 0.0004471901536112967, "loss": 1.7227, "step": 48970 }, { "epoch": 10.15, "learning_rate": 0.00044709474286804696, "loss": 1.7272, "step": 48975 }, { "epoch": 10.15, "learning_rate": 0.0004469993321247973, "loss": 1.7288, "step": 48980 }, { "epoch": 10.15, "learning_rate": 0.00044690392138154757, "loss": 1.7248, "step": 48985 }, { "epoch": 10.15, "learning_rate": 0.00044680851063829785, "loss": 1.7245, "step": 48990 }, { "epoch": 10.15, "learning_rate": 0.00044671309989504824, "loss": 1.7215, "step": 48995 }, { "epoch": 10.15, "learning_rate": 0.0004466176891517985, "loss": 1.7282, "step": 49000 }, { "epoch": 10.15, "learning_rate": 0.0004465222784085488, "loss": 1.7257, "step": 49005 }, { "epoch": 10.15, "learning_rate": 0.00044642686766529913, "loss": 1.7271, "step": 49010 }, { "epoch": 10.15, "learning_rate": 0.0004463314569220494, "loss": 1.7259, "step": 49015 }, { "epoch": 10.16, "learning_rate": 0.00044623604617879974, "loss": 1.7197, "step": 49020 }, { "epoch": 10.16, "learning_rate": 0.0004461406354355501, "loss": 1.7278, "step": 49025 }, { "epoch": 10.16, "learning_rate": 0.00044604522469230036, "loss": 1.723, "step": 49030 }, { "epoch": 10.16, "learning_rate": 0.00044594981394905064, "loss": 1.7214, "step": 49035 }, { "epoch": 10.16, "learning_rate": 0.000445854403205801, "loss": 1.7267, "step": 49040 }, { "epoch": 10.16, "learning_rate": 0.0004457589924625513, "loss": 1.7303, "step": 49045 }, { "epoch": 10.16, "learning_rate": 0.0004456635817193016, "loss": 1.726, "step": 49050 }, { "epoch": 10.16, "learning_rate": 0.0004455681709760519, "loss": 1.7183, "step": 49055 }, { "epoch": 10.16, "learning_rate": 0.0004454727602328022, "loss": 1.7206, "step": 49060 }, { "epoch": 10.16, "learning_rate": 0.00044537734948955253, "loss": 1.7277, "step": 49065 }, { "epoch": 10.17, "learning_rate": 0.00044528193874630287, "loss": 1.7306, "step": 49070 }, { "epoch": 10.17, "learning_rate": 0.00044518652800305315, "loss": 1.7248, "step": 49075 }, { "epoch": 10.17, "learning_rate": 0.00044509111725980343, "loss": 1.725, "step": 49080 }, { "epoch": 10.17, "learning_rate": 0.0004449957065165538, "loss": 1.7253, "step": 49085 }, { "epoch": 10.17, "learning_rate": 0.0004449002957733041, "loss": 1.7204, "step": 49090 }, { "epoch": 10.17, "learning_rate": 0.0004448048850300544, "loss": 1.7245, "step": 49095 }, { "epoch": 10.17, "learning_rate": 0.0004447094742868047, "loss": 1.7283, "step": 49100 }, { "epoch": 10.17, "learning_rate": 0.000444614063543555, "loss": 1.7254, "step": 49105 }, { "epoch": 10.17, "learning_rate": 0.0004445186528003053, "loss": 1.7325, "step": 49110 }, { "epoch": 10.18, "learning_rate": 0.00044442324205705566, "loss": 1.7199, "step": 49115 }, { "epoch": 10.18, "learning_rate": 0.00044432783131380594, "loss": 1.7291, "step": 49120 }, { "epoch": 10.18, "learning_rate": 0.0004442324205705562, "loss": 1.7253, "step": 49125 }, { "epoch": 10.18, "learning_rate": 0.00044413700982730655, "loss": 1.7273, "step": 49130 }, { "epoch": 10.18, "learning_rate": 0.0004440415990840569, "loss": 1.7325, "step": 49135 }, { "epoch": 10.18, "learning_rate": 0.00044394618834080716, "loss": 1.7296, "step": 49140 }, { "epoch": 10.18, "learning_rate": 0.0004438507775975575, "loss": 1.7295, "step": 49145 }, { "epoch": 10.18, "learning_rate": 0.0004437553668543078, "loss": 1.7276, "step": 49150 }, { "epoch": 10.18, "learning_rate": 0.0004436599561110581, "loss": 1.73, "step": 49155 }, { "epoch": 10.18, "learning_rate": 0.00044356454536780845, "loss": 1.7213, "step": 49160 }, { "epoch": 10.19, "learning_rate": 0.0004434691346245587, "loss": 1.7214, "step": 49165 }, { "epoch": 10.19, "learning_rate": 0.000443373723881309, "loss": 1.725, "step": 49170 }, { "epoch": 10.19, "learning_rate": 0.00044327831313805934, "loss": 1.7259, "step": 49175 }, { "epoch": 10.19, "learning_rate": 0.0004431829023948097, "loss": 1.7231, "step": 49180 }, { "epoch": 10.19, "learning_rate": 0.00044308749165156, "loss": 1.7265, "step": 49185 }, { "epoch": 10.19, "learning_rate": 0.0004429920809083103, "loss": 1.7257, "step": 49190 }, { "epoch": 10.19, "learning_rate": 0.00044289667016506057, "loss": 1.7252, "step": 49195 }, { "epoch": 10.19, "learning_rate": 0.00044280125942181096, "loss": 1.7251, "step": 49200 }, { "epoch": 10.19, "learning_rate": 0.00044270584867856124, "loss": 1.7205, "step": 49205 }, { "epoch": 10.19, "learning_rate": 0.0004426104379353115, "loss": 1.7263, "step": 49210 }, { "epoch": 10.2, "learning_rate": 0.00044251502719206185, "loss": 1.7228, "step": 49215 }, { "epoch": 10.2, "learning_rate": 0.00044241961644881213, "loss": 1.7207, "step": 49220 }, { "epoch": 10.2, "learning_rate": 0.00044232420570556246, "loss": 1.7255, "step": 49225 }, { "epoch": 10.2, "learning_rate": 0.0004422287949623128, "loss": 1.7236, "step": 49230 }, { "epoch": 10.2, "learning_rate": 0.0004421333842190631, "loss": 1.7281, "step": 49235 }, { "epoch": 10.2, "learning_rate": 0.00044203797347581336, "loss": 1.7252, "step": 49240 }, { "epoch": 10.2, "learning_rate": 0.0004419425627325637, "loss": 1.7231, "step": 49245 }, { "epoch": 10.2, "learning_rate": 0.000441847151989314, "loss": 1.7218, "step": 49250 }, { "epoch": 10.2, "learning_rate": 0.0004417517412460643, "loss": 1.7313, "step": 49255 }, { "epoch": 10.21, "learning_rate": 0.00044165633050281464, "loss": 1.7251, "step": 49260 }, { "epoch": 10.21, "learning_rate": 0.0004415609197595649, "loss": 1.7272, "step": 49265 }, { "epoch": 10.21, "learning_rate": 0.00044146550901631525, "loss": 1.7227, "step": 49270 }, { "epoch": 10.21, "learning_rate": 0.0004413700982730656, "loss": 1.7234, "step": 49275 }, { "epoch": 10.21, "learning_rate": 0.00044127468752981587, "loss": 1.732, "step": 49280 }, { "epoch": 10.21, "learning_rate": 0.00044117927678656615, "loss": 1.7294, "step": 49285 }, { "epoch": 10.21, "learning_rate": 0.0004410838660433165, "loss": 1.7234, "step": 49290 }, { "epoch": 10.21, "learning_rate": 0.0004409884553000668, "loss": 1.7258, "step": 49295 }, { "epoch": 10.21, "learning_rate": 0.0004408930445568171, "loss": 1.7256, "step": 49300 }, { "epoch": 10.21, "learning_rate": 0.00044079763381356743, "loss": 1.7252, "step": 49305 }, { "epoch": 10.22, "learning_rate": 0.0004407022230703177, "loss": 1.7296, "step": 49310 }, { "epoch": 10.22, "learning_rate": 0.00044060681232706804, "loss": 1.7288, "step": 49315 }, { "epoch": 10.22, "learning_rate": 0.0004405114015838184, "loss": 1.728, "step": 49320 }, { "epoch": 10.22, "learning_rate": 0.00044041599084056865, "loss": 1.7293, "step": 49325 }, { "epoch": 10.22, "learning_rate": 0.00044032058009731893, "loss": 1.7295, "step": 49330 }, { "epoch": 10.22, "learning_rate": 0.00044022516935406927, "loss": 1.7243, "step": 49335 }, { "epoch": 10.22, "learning_rate": 0.0004401297586108196, "loss": 1.729, "step": 49340 }, { "epoch": 10.22, "learning_rate": 0.0004400343478675699, "loss": 1.7325, "step": 49345 }, { "epoch": 10.22, "learning_rate": 0.0004399389371243202, "loss": 1.7263, "step": 49350 }, { "epoch": 10.22, "learning_rate": 0.0004398435263810705, "loss": 1.7284, "step": 49355 }, { "epoch": 10.23, "learning_rate": 0.0004397481156378208, "loss": 1.7274, "step": 49360 }, { "epoch": 10.23, "learning_rate": 0.00043965270489457116, "loss": 1.7302, "step": 49365 }, { "epoch": 10.23, "learning_rate": 0.00043955729415132144, "loss": 1.7287, "step": 49370 }, { "epoch": 10.23, "learning_rate": 0.0004394618834080717, "loss": 1.7284, "step": 49375 }, { "epoch": 10.23, "learning_rate": 0.00043936647266482206, "loss": 1.7265, "step": 49380 }, { "epoch": 10.23, "learning_rate": 0.0004392710619215724, "loss": 1.7253, "step": 49385 }, { "epoch": 10.23, "learning_rate": 0.0004391756511783227, "loss": 1.7255, "step": 49390 }, { "epoch": 10.23, "learning_rate": 0.000439080240435073, "loss": 1.7281, "step": 49395 }, { "epoch": 10.23, "learning_rate": 0.0004389848296918233, "loss": 1.7293, "step": 49400 }, { "epoch": 10.24, "learning_rate": 0.0004388894189485736, "loss": 1.7308, "step": 49405 }, { "epoch": 10.24, "learning_rate": 0.00043879400820532395, "loss": 1.7243, "step": 49410 }, { "epoch": 10.24, "learning_rate": 0.00043869859746207423, "loss": 1.728, "step": 49415 }, { "epoch": 10.24, "learning_rate": 0.00043860318671882457, "loss": 1.7302, "step": 49420 }, { "epoch": 10.24, "learning_rate": 0.00043850777597557485, "loss": 1.7247, "step": 49425 }, { "epoch": 10.24, "learning_rate": 0.0004384123652323252, "loss": 1.7253, "step": 49430 }, { "epoch": 10.24, "learning_rate": 0.0004383169544890755, "loss": 1.7257, "step": 49435 }, { "epoch": 10.24, "learning_rate": 0.0004382215437458258, "loss": 1.7302, "step": 49440 }, { "epoch": 10.24, "learning_rate": 0.0004381261330025761, "loss": 1.7264, "step": 49445 }, { "epoch": 10.24, "learning_rate": 0.0004380307222593264, "loss": 1.7286, "step": 49450 }, { "epoch": 10.25, "learning_rate": 0.00043793531151607674, "loss": 1.7306, "step": 49455 }, { "epoch": 10.25, "learning_rate": 0.000437839900772827, "loss": 1.725, "step": 49460 }, { "epoch": 10.25, "learning_rate": 0.00043774449002957736, "loss": 1.7247, "step": 49465 }, { "epoch": 10.25, "learning_rate": 0.00043764907928632764, "loss": 1.7272, "step": 49470 }, { "epoch": 10.25, "learning_rate": 0.00043755366854307797, "loss": 1.722, "step": 49475 }, { "epoch": 10.25, "learning_rate": 0.0004374582577998283, "loss": 1.7255, "step": 49480 }, { "epoch": 10.25, "learning_rate": 0.0004373628470565786, "loss": 1.7242, "step": 49485 }, { "epoch": 10.25, "learning_rate": 0.00043726743631332886, "loss": 1.7213, "step": 49490 }, { "epoch": 10.25, "learning_rate": 0.0004371720255700792, "loss": 1.7246, "step": 49495 }, { "epoch": 10.25, "learning_rate": 0.00043707661482682953, "loss": 1.7313, "step": 49500 }, { "epoch": 10.26, "learning_rate": 0.0004369812040835798, "loss": 1.7288, "step": 49505 }, { "epoch": 10.26, "learning_rate": 0.00043688579334033015, "loss": 1.7256, "step": 49510 }, { "epoch": 10.26, "learning_rate": 0.0004367903825970804, "loss": 1.7277, "step": 49515 }, { "epoch": 10.26, "learning_rate": 0.0004366949718538307, "loss": 1.7255, "step": 49520 }, { "epoch": 10.26, "learning_rate": 0.0004365995611105811, "loss": 1.7288, "step": 49525 }, { "epoch": 10.26, "learning_rate": 0.00043650415036733137, "loss": 1.7279, "step": 49530 }, { "epoch": 10.26, "learning_rate": 0.00043640873962408165, "loss": 1.7291, "step": 49535 }, { "epoch": 10.26, "learning_rate": 0.000436313328880832, "loss": 1.7245, "step": 49540 }, { "epoch": 10.26, "learning_rate": 0.0004362179181375823, "loss": 1.7244, "step": 49545 }, { "epoch": 10.27, "learning_rate": 0.0004361225073943326, "loss": 1.7221, "step": 49550 }, { "epoch": 10.27, "learning_rate": 0.00043602709665108293, "loss": 1.7304, "step": 49555 }, { "epoch": 10.27, "learning_rate": 0.0004359316859078332, "loss": 1.7311, "step": 49560 }, { "epoch": 10.27, "learning_rate": 0.0004358362751645835, "loss": 1.7272, "step": 49565 }, { "epoch": 10.27, "learning_rate": 0.0004357408644213339, "loss": 1.724, "step": 49570 }, { "epoch": 10.27, "learning_rate": 0.00043564545367808416, "loss": 1.7316, "step": 49575 }, { "epoch": 10.27, "learning_rate": 0.00043555004293483444, "loss": 1.7249, "step": 49580 }, { "epoch": 10.27, "learning_rate": 0.0004354546321915848, "loss": 1.7232, "step": 49585 }, { "epoch": 10.27, "learning_rate": 0.0004353592214483351, "loss": 1.7235, "step": 49590 }, { "epoch": 10.27, "learning_rate": 0.00043526381070508544, "loss": 1.7264, "step": 49595 }, { "epoch": 10.28, "learning_rate": 0.0004351683999618357, "loss": 1.7258, "step": 49600 }, { "epoch": 10.28, "learning_rate": 0.000435072989218586, "loss": 1.7214, "step": 49605 }, { "epoch": 10.28, "learning_rate": 0.00043497757847533634, "loss": 1.7289, "step": 49610 }, { "epoch": 10.28, "learning_rate": 0.00043488216773208667, "loss": 1.7257, "step": 49615 }, { "epoch": 10.28, "learning_rate": 0.00043478675698883695, "loss": 1.7288, "step": 49620 }, { "epoch": 10.28, "learning_rate": 0.0004346913462455873, "loss": 1.7268, "step": 49625 }, { "epoch": 10.28, "learning_rate": 0.00043459593550233756, "loss": 1.7258, "step": 49630 }, { "epoch": 10.28, "learning_rate": 0.00043450052475908784, "loss": 1.7314, "step": 49635 }, { "epoch": 10.28, "learning_rate": 0.00043440511401583823, "loss": 1.7314, "step": 49640 }, { "epoch": 10.28, "learning_rate": 0.0004343097032725885, "loss": 1.7258, "step": 49645 }, { "epoch": 10.29, "learning_rate": 0.0004342142925293388, "loss": 1.7276, "step": 49650 }, { "epoch": 10.29, "learning_rate": 0.0004341188817860891, "loss": 1.7271, "step": 49655 }, { "epoch": 10.29, "learning_rate": 0.00043402347104283946, "loss": 1.7289, "step": 49660 }, { "epoch": 10.29, "learning_rate": 0.00043392806029958974, "loss": 1.7271, "step": 49665 }, { "epoch": 10.29, "learning_rate": 0.0004338326495563401, "loss": 1.7262, "step": 49670 }, { "epoch": 10.29, "learning_rate": 0.00043373723881309035, "loss": 1.7314, "step": 49675 }, { "epoch": 10.29, "learning_rate": 0.00043364182806984063, "loss": 1.7268, "step": 49680 }, { "epoch": 10.29, "learning_rate": 0.000433546417326591, "loss": 1.7308, "step": 49685 }, { "epoch": 10.29, "learning_rate": 0.0004334510065833413, "loss": 1.7195, "step": 49690 }, { "epoch": 10.3, "learning_rate": 0.0004333555958400916, "loss": 1.725, "step": 49695 }, { "epoch": 10.3, "learning_rate": 0.0004332601850968419, "loss": 1.7276, "step": 49700 }, { "epoch": 10.3, "learning_rate": 0.00043316477435359225, "loss": 1.7272, "step": 49705 }, { "epoch": 10.3, "learning_rate": 0.00043306936361034253, "loss": 1.7272, "step": 49710 }, { "epoch": 10.3, "learning_rate": 0.00043297395286709286, "loss": 1.7231, "step": 49715 }, { "epoch": 10.3, "learning_rate": 0.00043287854212384314, "loss": 1.7266, "step": 49720 }, { "epoch": 10.3, "learning_rate": 0.0004327831313805934, "loss": 1.7293, "step": 49725 }, { "epoch": 10.3, "learning_rate": 0.0004326877206373438, "loss": 1.7299, "step": 49730 }, { "epoch": 10.3, "learning_rate": 0.0004325923098940941, "loss": 1.7321, "step": 49735 }, { "epoch": 10.3, "learning_rate": 0.00043249689915084437, "loss": 1.7267, "step": 49740 }, { "epoch": 10.31, "learning_rate": 0.0004324014884075947, "loss": 1.7234, "step": 49745 }, { "epoch": 10.31, "learning_rate": 0.000432306077664345, "loss": 1.727, "step": 49750 }, { "epoch": 10.31, "learning_rate": 0.0004322106669210953, "loss": 1.7289, "step": 49755 }, { "epoch": 10.31, "learning_rate": 0.00043211525617784565, "loss": 1.7266, "step": 49760 }, { "epoch": 10.31, "learning_rate": 0.00043201984543459593, "loss": 1.7223, "step": 49765 }, { "epoch": 10.31, "learning_rate": 0.0004319244346913462, "loss": 1.7323, "step": 49770 }, { "epoch": 10.31, "learning_rate": 0.0004318290239480966, "loss": 1.7293, "step": 49775 }, { "epoch": 10.31, "learning_rate": 0.0004317336132048469, "loss": 1.7261, "step": 49780 }, { "epoch": 10.31, "learning_rate": 0.00043163820246159716, "loss": 1.7253, "step": 49785 }, { "epoch": 10.31, "learning_rate": 0.0004315427917183475, "loss": 1.7274, "step": 49790 }, { "epoch": 10.32, "learning_rate": 0.0004314473809750978, "loss": 1.7293, "step": 49795 }, { "epoch": 10.32, "learning_rate": 0.0004313519702318481, "loss": 1.7261, "step": 49800 }, { "epoch": 10.32, "learning_rate": 0.00043125655948859844, "loss": 1.7283, "step": 49805 }, { "epoch": 10.32, "learning_rate": 0.0004311611487453487, "loss": 1.7322, "step": 49810 }, { "epoch": 10.32, "learning_rate": 0.00043106573800209906, "loss": 1.7315, "step": 49815 }, { "epoch": 10.32, "learning_rate": 0.0004309703272588494, "loss": 1.7299, "step": 49820 }, { "epoch": 10.32, "learning_rate": 0.00043087491651559967, "loss": 1.7248, "step": 49825 }, { "epoch": 10.32, "learning_rate": 0.00043077950577235, "loss": 1.7275, "step": 49830 }, { "epoch": 10.32, "learning_rate": 0.0004306840950291003, "loss": 1.7246, "step": 49835 }, { "epoch": 10.33, "learning_rate": 0.00043058868428585056, "loss": 1.7289, "step": 49840 }, { "epoch": 10.33, "learning_rate": 0.00043049327354260095, "loss": 1.7273, "step": 49845 }, { "epoch": 10.33, "learning_rate": 0.00043039786279935123, "loss": 1.7216, "step": 49850 }, { "epoch": 10.33, "learning_rate": 0.0004303024520561015, "loss": 1.7293, "step": 49855 }, { "epoch": 10.33, "learning_rate": 0.00043020704131285184, "loss": 1.729, "step": 49860 }, { "epoch": 10.33, "learning_rate": 0.0004301116305696021, "loss": 1.7286, "step": 49865 }, { "epoch": 10.33, "learning_rate": 0.00043001621982635246, "loss": 1.7302, "step": 49870 }, { "epoch": 10.33, "learning_rate": 0.0004299208090831028, "loss": 1.724, "step": 49875 }, { "epoch": 10.33, "learning_rate": 0.00042982539833985307, "loss": 1.7282, "step": 49880 }, { "epoch": 10.33, "learning_rate": 0.00042972998759660335, "loss": 1.7253, "step": 49885 }, { "epoch": 10.34, "learning_rate": 0.00042963457685335374, "loss": 1.7296, "step": 49890 }, { "epoch": 10.34, "learning_rate": 0.000429539166110104, "loss": 1.7303, "step": 49895 }, { "epoch": 10.34, "learning_rate": 0.0004294437553668543, "loss": 1.7252, "step": 49900 }, { "epoch": 10.34, "learning_rate": 0.00042934834462360463, "loss": 1.7318, "step": 49905 }, { "epoch": 10.34, "learning_rate": 0.0004292529338803549, "loss": 1.7276, "step": 49910 }, { "epoch": 10.34, "learning_rate": 0.00042915752313710525, "loss": 1.7302, "step": 49915 }, { "epoch": 10.34, "learning_rate": 0.0004290621123938556, "loss": 1.7287, "step": 49920 }, { "epoch": 10.34, "learning_rate": 0.00042896670165060586, "loss": 1.7265, "step": 49925 }, { "epoch": 10.34, "learning_rate": 0.00042887129090735614, "loss": 1.7245, "step": 49930 }, { "epoch": 10.34, "learning_rate": 0.00042877588016410653, "loss": 1.7302, "step": 49935 }, { "epoch": 10.35, "learning_rate": 0.0004286804694208568, "loss": 1.7191, "step": 49940 }, { "epoch": 10.35, "learning_rate": 0.0004285850586776071, "loss": 1.7242, "step": 49945 }, { "epoch": 10.35, "learning_rate": 0.0004284896479343574, "loss": 1.7267, "step": 49950 }, { "epoch": 10.35, "learning_rate": 0.0004283942371911077, "loss": 1.73, "step": 49955 }, { "epoch": 10.35, "learning_rate": 0.00042829882644785804, "loss": 1.7235, "step": 49960 }, { "epoch": 10.35, "learning_rate": 0.00042820341570460837, "loss": 1.7232, "step": 49965 }, { "epoch": 10.35, "learning_rate": 0.00042810800496135865, "loss": 1.7279, "step": 49970 }, { "epoch": 10.35, "learning_rate": 0.00042801259421810893, "loss": 1.7307, "step": 49975 }, { "epoch": 10.35, "learning_rate": 0.00042791718347485926, "loss": 1.7266, "step": 49980 }, { "epoch": 10.36, "learning_rate": 0.0004278217727316096, "loss": 1.7285, "step": 49985 }, { "epoch": 10.36, "learning_rate": 0.0004277263619883599, "loss": 1.7298, "step": 49990 }, { "epoch": 10.36, "learning_rate": 0.0004276309512451102, "loss": 1.7242, "step": 49995 }, { "epoch": 10.36, "learning_rate": 0.0004275355405018605, "loss": 1.7265, "step": 50000 }, { "epoch": 10.36, "learning_rate": 0.0004274401297586108, "loss": 1.7272, "step": 50005 }, { "epoch": 10.36, "learning_rate": 0.00042734471901536116, "loss": 1.7315, "step": 50010 }, { "epoch": 10.36, "learning_rate": 0.00042724930827211144, "loss": 1.7225, "step": 50015 }, { "epoch": 10.36, "learning_rate": 0.0004271538975288617, "loss": 1.7313, "step": 50020 }, { "epoch": 10.36, "learning_rate": 0.00042705848678561205, "loss": 1.7269, "step": 50025 }, { "epoch": 10.36, "learning_rate": 0.0004269630760423624, "loss": 1.7267, "step": 50030 }, { "epoch": 10.37, "learning_rate": 0.0004268676652991127, "loss": 1.7274, "step": 50035 }, { "epoch": 10.37, "learning_rate": 0.000426772254555863, "loss": 1.724, "step": 50040 }, { "epoch": 10.37, "learning_rate": 0.0004266768438126133, "loss": 1.7313, "step": 50045 }, { "epoch": 10.37, "learning_rate": 0.00042658143306936367, "loss": 1.727, "step": 50050 }, { "epoch": 10.37, "learning_rate": 0.00042648602232611395, "loss": 1.7245, "step": 50055 }, { "epoch": 10.37, "learning_rate": 0.00042639061158286423, "loss": 1.7252, "step": 50060 }, { "epoch": 10.37, "learning_rate": 0.00042629520083961456, "loss": 1.7295, "step": 50065 }, { "epoch": 10.37, "learning_rate": 0.00042619979009636484, "loss": 1.7244, "step": 50070 }, { "epoch": 10.37, "learning_rate": 0.0004261043793531152, "loss": 1.7272, "step": 50075 }, { "epoch": 10.37, "learning_rate": 0.0004260089686098655, "loss": 1.7293, "step": 50080 }, { "epoch": 10.38, "learning_rate": 0.0004259135578666158, "loss": 1.7263, "step": 50085 }, { "epoch": 10.38, "learning_rate": 0.00042581814712336607, "loss": 1.7291, "step": 50090 }, { "epoch": 10.38, "learning_rate": 0.00042572273638011646, "loss": 1.7284, "step": 50095 }, { "epoch": 10.38, "learning_rate": 0.00042562732563686674, "loss": 1.7227, "step": 50100 }, { "epoch": 10.38, "learning_rate": 0.000425531914893617, "loss": 1.7264, "step": 50105 }, { "epoch": 10.38, "learning_rate": 0.00042543650415036735, "loss": 1.7262, "step": 50110 }, { "epoch": 10.38, "learning_rate": 0.00042534109340711763, "loss": 1.7347, "step": 50115 }, { "epoch": 10.38, "learning_rate": 0.00042524568266386797, "loss": 1.7215, "step": 50120 }, { "epoch": 10.38, "learning_rate": 0.0004251502719206183, "loss": 1.7262, "step": 50125 }, { "epoch": 10.39, "learning_rate": 0.0004250548611773686, "loss": 1.7341, "step": 50130 }, { "epoch": 10.39, "learning_rate": 0.00042495945043411886, "loss": 1.7267, "step": 50135 }, { "epoch": 10.39, "learning_rate": 0.0004248640396908692, "loss": 1.7289, "step": 50140 }, { "epoch": 10.39, "learning_rate": 0.0004247686289476195, "loss": 1.7252, "step": 50145 }, { "epoch": 10.39, "learning_rate": 0.0004246732182043698, "loss": 1.7229, "step": 50150 }, { "epoch": 10.39, "learning_rate": 0.00042457780746112014, "loss": 1.7298, "step": 50155 }, { "epoch": 10.39, "learning_rate": 0.0004244823967178704, "loss": 1.7216, "step": 50160 }, { "epoch": 10.39, "learning_rate": 0.00042438698597462075, "loss": 1.7261, "step": 50165 }, { "epoch": 10.39, "learning_rate": 0.0004242915752313711, "loss": 1.7283, "step": 50170 }, { "epoch": 10.39, "learning_rate": 0.00042419616448812137, "loss": 1.7252, "step": 50175 }, { "epoch": 10.4, "learning_rate": 0.00042410075374487165, "loss": 1.7258, "step": 50180 }, { "epoch": 10.4, "learning_rate": 0.000424005343001622, "loss": 1.7266, "step": 50185 }, { "epoch": 10.4, "learning_rate": 0.0004239099322583723, "loss": 1.7274, "step": 50190 }, { "epoch": 10.4, "learning_rate": 0.0004238145215151226, "loss": 1.729, "step": 50195 }, { "epoch": 10.4, "learning_rate": 0.00042371911077187293, "loss": 1.7294, "step": 50200 }, { "epoch": 10.4, "learning_rate": 0.0004236237000286232, "loss": 1.726, "step": 50205 }, { "epoch": 10.4, "learning_rate": 0.00042352828928537354, "loss": 1.7258, "step": 50210 }, { "epoch": 10.4, "learning_rate": 0.0004234328785421239, "loss": 1.7297, "step": 50215 }, { "epoch": 10.4, "learning_rate": 0.00042333746779887416, "loss": 1.731, "step": 50220 }, { "epoch": 10.41, "learning_rate": 0.00042324205705562444, "loss": 1.7221, "step": 50225 }, { "epoch": 10.41, "learning_rate": 0.00042314664631237477, "loss": 1.7271, "step": 50230 }, { "epoch": 10.41, "learning_rate": 0.0004230512355691251, "loss": 1.7319, "step": 50235 }, { "epoch": 10.41, "learning_rate": 0.00042295582482587544, "loss": 1.7304, "step": 50240 }, { "epoch": 10.41, "learning_rate": 0.0004228604140826257, "loss": 1.726, "step": 50245 }, { "epoch": 10.41, "learning_rate": 0.000422765003339376, "loss": 1.7291, "step": 50250 }, { "epoch": 10.41, "learning_rate": 0.00042266959259612633, "loss": 1.7267, "step": 50255 }, { "epoch": 10.41, "learning_rate": 0.00042257418185287667, "loss": 1.7285, "step": 50260 }, { "epoch": 10.41, "learning_rate": 0.00042247877110962695, "loss": 1.7283, "step": 50265 }, { "epoch": 10.41, "learning_rate": 0.0004223833603663773, "loss": 1.7243, "step": 50270 }, { "epoch": 10.42, "learning_rate": 0.00042228794962312756, "loss": 1.729, "step": 50275 }, { "epoch": 10.42, "learning_rate": 0.0004221925388798779, "loss": 1.7236, "step": 50280 }, { "epoch": 10.42, "learning_rate": 0.00042209712813662823, "loss": 1.7243, "step": 50285 }, { "epoch": 10.42, "learning_rate": 0.0004220017173933785, "loss": 1.7272, "step": 50290 }, { "epoch": 10.42, "learning_rate": 0.0004219063066501288, "loss": 1.7268, "step": 50295 }, { "epoch": 10.42, "learning_rate": 0.0004218108959068791, "loss": 1.7235, "step": 50300 }, { "epoch": 10.42, "learning_rate": 0.00042171548516362946, "loss": 1.725, "step": 50305 }, { "epoch": 10.42, "learning_rate": 0.00042162007442037974, "loss": 1.7205, "step": 50310 }, { "epoch": 10.42, "learning_rate": 0.00042152466367713007, "loss": 1.7258, "step": 50315 }, { "epoch": 10.42, "learning_rate": 0.00042142925293388035, "loss": 1.7294, "step": 50320 }, { "epoch": 10.43, "learning_rate": 0.0004213338421906307, "loss": 1.7253, "step": 50325 }, { "epoch": 10.43, "learning_rate": 0.000421238431447381, "loss": 1.7295, "step": 50330 }, { "epoch": 10.43, "learning_rate": 0.0004211430207041313, "loss": 1.7282, "step": 50335 }, { "epoch": 10.43, "learning_rate": 0.0004210476099608816, "loss": 1.7234, "step": 50340 }, { "epoch": 10.43, "learning_rate": 0.0004209521992176319, "loss": 1.7298, "step": 50345 }, { "epoch": 10.43, "learning_rate": 0.00042085678847438224, "loss": 1.7223, "step": 50350 }, { "epoch": 10.43, "learning_rate": 0.0004207613777311325, "loss": 1.7244, "step": 50355 }, { "epoch": 10.43, "learning_rate": 0.00042066596698788286, "loss": 1.7233, "step": 50360 }, { "epoch": 10.43, "learning_rate": 0.00042057055624463314, "loss": 1.7248, "step": 50365 }, { "epoch": 10.44, "learning_rate": 0.0004204751455013834, "loss": 1.7286, "step": 50370 }, { "epoch": 10.44, "learning_rate": 0.0004203797347581338, "loss": 1.7265, "step": 50375 }, { "epoch": 10.44, "learning_rate": 0.0004202843240148841, "loss": 1.7259, "step": 50380 }, { "epoch": 10.44, "learning_rate": 0.00042018891327163437, "loss": 1.729, "step": 50385 }, { "epoch": 10.44, "learning_rate": 0.0004200935025283847, "loss": 1.7234, "step": 50390 }, { "epoch": 10.44, "learning_rate": 0.00041999809178513503, "loss": 1.725, "step": 50395 }, { "epoch": 10.44, "learning_rate": 0.0004199026810418853, "loss": 1.7215, "step": 50400 }, { "epoch": 10.44, "learning_rate": 0.00041980727029863565, "loss": 1.7251, "step": 50405 }, { "epoch": 10.44, "learning_rate": 0.00041971185955538593, "loss": 1.725, "step": 50410 }, { "epoch": 10.44, "learning_rate": 0.0004196164488121362, "loss": 1.726, "step": 50415 }, { "epoch": 10.45, "learning_rate": 0.0004195210380688866, "loss": 1.7232, "step": 50420 }, { "epoch": 10.45, "learning_rate": 0.0004194256273256369, "loss": 1.7252, "step": 50425 }, { "epoch": 10.45, "learning_rate": 0.00041933021658238715, "loss": 1.7256, "step": 50430 }, { "epoch": 10.45, "learning_rate": 0.0004192348058391375, "loss": 1.728, "step": 50435 }, { "epoch": 10.45, "learning_rate": 0.0004191393950958878, "loss": 1.7338, "step": 50440 }, { "epoch": 10.45, "learning_rate": 0.00041904398435263816, "loss": 1.727, "step": 50445 }, { "epoch": 10.45, "learning_rate": 0.00041894857360938844, "loss": 1.7314, "step": 50450 }, { "epoch": 10.45, "learning_rate": 0.0004188531628661387, "loss": 1.7295, "step": 50455 }, { "epoch": 10.45, "learning_rate": 0.00041875775212288905, "loss": 1.7237, "step": 50460 }, { "epoch": 10.45, "learning_rate": 0.0004186623413796394, "loss": 1.7299, "step": 50465 }, { "epoch": 10.46, "learning_rate": 0.00041856693063638966, "loss": 1.7285, "step": 50470 }, { "epoch": 10.46, "learning_rate": 0.00041847151989314, "loss": 1.7285, "step": 50475 }, { "epoch": 10.46, "learning_rate": 0.0004183761091498903, "loss": 1.7263, "step": 50480 }, { "epoch": 10.46, "learning_rate": 0.00041828069840664056, "loss": 1.7258, "step": 50485 }, { "epoch": 10.46, "learning_rate": 0.00041818528766339095, "loss": 1.7251, "step": 50490 }, { "epoch": 10.46, "learning_rate": 0.0004180898769201412, "loss": 1.7266, "step": 50495 }, { "epoch": 10.46, "learning_rate": 0.0004179944661768915, "loss": 1.7285, "step": 50500 }, { "epoch": 10.46, "learning_rate": 0.00041789905543364184, "loss": 1.7237, "step": 50505 }, { "epoch": 10.46, "learning_rate": 0.0004178036446903922, "loss": 1.7303, "step": 50510 }, { "epoch": 10.47, "learning_rate": 0.00041770823394714245, "loss": 1.7274, "step": 50515 }, { "epoch": 10.47, "learning_rate": 0.0004176128232038928, "loss": 1.721, "step": 50520 }, { "epoch": 10.47, "learning_rate": 0.00041751741246064307, "loss": 1.7284, "step": 50525 }, { "epoch": 10.47, "learning_rate": 0.00041742200171739335, "loss": 1.7284, "step": 50530 }, { "epoch": 10.47, "learning_rate": 0.00041732659097414374, "loss": 1.7267, "step": 50535 }, { "epoch": 10.47, "learning_rate": 0.000417231180230894, "loss": 1.7244, "step": 50540 }, { "epoch": 10.47, "learning_rate": 0.0004171357694876443, "loss": 1.7246, "step": 50545 }, { "epoch": 10.47, "learning_rate": 0.00041704035874439463, "loss": 1.7225, "step": 50550 }, { "epoch": 10.47, "learning_rate": 0.00041694494800114496, "loss": 1.7233, "step": 50555 }, { "epoch": 10.47, "learning_rate": 0.00041684953725789524, "loss": 1.7244, "step": 50560 }, { "epoch": 10.48, "learning_rate": 0.0004167541265146456, "loss": 1.7248, "step": 50565 }, { "epoch": 10.48, "learning_rate": 0.00041665871577139586, "loss": 1.7289, "step": 50570 }, { "epoch": 10.48, "learning_rate": 0.00041656330502814614, "loss": 1.7273, "step": 50575 }, { "epoch": 10.48, "learning_rate": 0.0004164678942848965, "loss": 1.7239, "step": 50580 }, { "epoch": 10.48, "learning_rate": 0.0004163724835416468, "loss": 1.728, "step": 50585 }, { "epoch": 10.48, "learning_rate": 0.0004162770727983971, "loss": 1.7226, "step": 50590 }, { "epoch": 10.48, "learning_rate": 0.0004161816620551474, "loss": 1.7295, "step": 50595 }, { "epoch": 10.48, "learning_rate": 0.0004160862513118977, "loss": 1.7262, "step": 50600 }, { "epoch": 10.48, "learning_rate": 0.00041599084056864803, "loss": 1.7269, "step": 50605 }, { "epoch": 10.48, "learning_rate": 0.00041589542982539837, "loss": 1.7229, "step": 50610 }, { "epoch": 10.49, "learning_rate": 0.00041580001908214865, "loss": 1.7293, "step": 50615 }, { "epoch": 10.49, "learning_rate": 0.0004157046083388989, "loss": 1.7284, "step": 50620 }, { "epoch": 10.49, "learning_rate": 0.0004156091975956493, "loss": 1.7291, "step": 50625 }, { "epoch": 10.49, "learning_rate": 0.0004155137868523996, "loss": 1.724, "step": 50630 }, { "epoch": 10.49, "learning_rate": 0.0004154183761091499, "loss": 1.7292, "step": 50635 }, { "epoch": 10.49, "learning_rate": 0.0004153229653659002, "loss": 1.7278, "step": 50640 }, { "epoch": 10.49, "learning_rate": 0.0004152275546226505, "loss": 1.7274, "step": 50645 }, { "epoch": 10.49, "learning_rate": 0.0004151321438794008, "loss": 1.7233, "step": 50650 }, { "epoch": 10.49, "learning_rate": 0.00041503673313615115, "loss": 1.7288, "step": 50655 }, { "epoch": 10.5, "learning_rate": 0.00041494132239290143, "loss": 1.7241, "step": 50660 }, { "epoch": 10.5, "learning_rate": 0.00041484591164965177, "loss": 1.7189, "step": 50665 }, { "epoch": 10.5, "learning_rate": 0.0004147505009064021, "loss": 1.7311, "step": 50670 }, { "epoch": 10.5, "learning_rate": 0.0004146550901631524, "loss": 1.732, "step": 50675 }, { "epoch": 10.5, "learning_rate": 0.0004145596794199027, "loss": 1.7263, "step": 50680 }, { "epoch": 10.5, "learning_rate": 0.000414464268676653, "loss": 1.73, "step": 50685 }, { "epoch": 10.5, "learning_rate": 0.0004143688579334033, "loss": 1.7286, "step": 50690 }, { "epoch": 10.5, "learning_rate": 0.00041427344719015366, "loss": 1.7345, "step": 50695 }, { "epoch": 10.5, "learning_rate": 0.00041417803644690394, "loss": 1.7315, "step": 50700 }, { "epoch": 10.5, "learning_rate": 0.0004140826257036542, "loss": 1.7283, "step": 50705 }, { "epoch": 10.51, "learning_rate": 0.00041398721496040456, "loss": 1.7283, "step": 50710 }, { "epoch": 10.51, "learning_rate": 0.00041389180421715484, "loss": 1.7256, "step": 50715 }, { "epoch": 10.51, "learning_rate": 0.00041379639347390517, "loss": 1.7252, "step": 50720 }, { "epoch": 10.51, "learning_rate": 0.0004137009827306555, "loss": 1.7243, "step": 50725 }, { "epoch": 10.51, "learning_rate": 0.0004136055719874058, "loss": 1.7269, "step": 50730 }, { "epoch": 10.51, "learning_rate": 0.00041351016124415606, "loss": 1.7266, "step": 50735 }, { "epoch": 10.51, "learning_rate": 0.00041341475050090645, "loss": 1.7301, "step": 50740 }, { "epoch": 10.51, "learning_rate": 0.00041331933975765673, "loss": 1.7277, "step": 50745 }, { "epoch": 10.51, "learning_rate": 0.000413223929014407, "loss": 1.7244, "step": 50750 }, { "epoch": 10.51, "learning_rate": 0.00041312851827115735, "loss": 1.7275, "step": 50755 }, { "epoch": 10.52, "learning_rate": 0.0004130331075279076, "loss": 1.7244, "step": 50760 }, { "epoch": 10.52, "learning_rate": 0.00041293769678465796, "loss": 1.725, "step": 50765 }, { "epoch": 10.52, "learning_rate": 0.0004128422860414083, "loss": 1.7272, "step": 50770 }, { "epoch": 10.52, "learning_rate": 0.0004127468752981586, "loss": 1.7239, "step": 50775 }, { "epoch": 10.52, "learning_rate": 0.00041265146455490885, "loss": 1.7321, "step": 50780 }, { "epoch": 10.52, "learning_rate": 0.00041255605381165924, "loss": 1.7269, "step": 50785 }, { "epoch": 10.52, "learning_rate": 0.0004124606430684095, "loss": 1.7218, "step": 50790 }, { "epoch": 10.52, "learning_rate": 0.0004123652323251598, "loss": 1.7253, "step": 50795 }, { "epoch": 10.52, "learning_rate": 0.00041226982158191014, "loss": 1.7251, "step": 50800 }, { "epoch": 10.53, "learning_rate": 0.0004121744108386604, "loss": 1.7275, "step": 50805 }, { "epoch": 10.53, "learning_rate": 0.00041207900009541075, "loss": 1.728, "step": 50810 }, { "epoch": 10.53, "learning_rate": 0.0004119835893521611, "loss": 1.7247, "step": 50815 }, { "epoch": 10.53, "learning_rate": 0.00041188817860891136, "loss": 1.7237, "step": 50820 }, { "epoch": 10.53, "learning_rate": 0.00041179276786566164, "loss": 1.7309, "step": 50825 }, { "epoch": 10.53, "learning_rate": 0.00041169735712241203, "loss": 1.722, "step": 50830 }, { "epoch": 10.53, "learning_rate": 0.0004116019463791623, "loss": 1.723, "step": 50835 }, { "epoch": 10.53, "learning_rate": 0.0004115065356359126, "loss": 1.7227, "step": 50840 }, { "epoch": 10.53, "learning_rate": 0.0004114111248926629, "loss": 1.7277, "step": 50845 }, { "epoch": 10.53, "learning_rate": 0.0004113157141494132, "loss": 1.7228, "step": 50850 }, { "epoch": 10.54, "learning_rate": 0.00041122030340616354, "loss": 1.7269, "step": 50855 }, { "epoch": 10.54, "learning_rate": 0.00041112489266291387, "loss": 1.7259, "step": 50860 }, { "epoch": 10.54, "learning_rate": 0.00041102948191966415, "loss": 1.7262, "step": 50865 }, { "epoch": 10.54, "learning_rate": 0.00041093407117641443, "loss": 1.7253, "step": 50870 }, { "epoch": 10.54, "learning_rate": 0.00041083866043316477, "loss": 1.7227, "step": 50875 }, { "epoch": 10.54, "learning_rate": 0.0004107432496899151, "loss": 1.7259, "step": 50880 }, { "epoch": 10.54, "learning_rate": 0.00041064783894666543, "loss": 1.7283, "step": 50885 }, { "epoch": 10.54, "learning_rate": 0.0004105524282034157, "loss": 1.7243, "step": 50890 }, { "epoch": 10.54, "learning_rate": 0.000410457017460166, "loss": 1.7276, "step": 50895 }, { "epoch": 10.54, "learning_rate": 0.0004103616067169164, "loss": 1.7242, "step": 50900 }, { "epoch": 10.55, "learning_rate": 0.00041026619597366666, "loss": 1.7317, "step": 50905 }, { "epoch": 10.55, "learning_rate": 0.00041017078523041694, "loss": 1.7235, "step": 50910 }, { "epoch": 10.55, "learning_rate": 0.0004100753744871673, "loss": 1.7215, "step": 50915 }, { "epoch": 10.55, "learning_rate": 0.00040997996374391756, "loss": 1.7278, "step": 50920 }, { "epoch": 10.55, "learning_rate": 0.0004098845530006679, "loss": 1.7236, "step": 50925 }, { "epoch": 10.55, "learning_rate": 0.0004097891422574182, "loss": 1.7277, "step": 50930 }, { "epoch": 10.55, "learning_rate": 0.0004096937315141685, "loss": 1.7254, "step": 50935 }, { "epoch": 10.55, "learning_rate": 0.0004095983207709188, "loss": 1.7215, "step": 50940 }, { "epoch": 10.55, "learning_rate": 0.00040950291002766917, "loss": 1.7238, "step": 50945 }, { "epoch": 10.56, "learning_rate": 0.00040940749928441945, "loss": 1.722, "step": 50950 }, { "epoch": 10.56, "learning_rate": 0.00040931208854116973, "loss": 1.7268, "step": 50955 }, { "epoch": 10.56, "learning_rate": 0.00040921667779792006, "loss": 1.7281, "step": 50960 }, { "epoch": 10.56, "learning_rate": 0.00040912126705467034, "loss": 1.7268, "step": 50965 }, { "epoch": 10.56, "learning_rate": 0.0004090258563114207, "loss": 1.7294, "step": 50970 }, { "epoch": 10.56, "learning_rate": 0.000408930445568171, "loss": 1.7234, "step": 50975 }, { "epoch": 10.56, "learning_rate": 0.0004088350348249213, "loss": 1.7289, "step": 50980 }, { "epoch": 10.56, "learning_rate": 0.00040873962408167157, "loss": 1.7312, "step": 50985 }, { "epoch": 10.56, "learning_rate": 0.0004086442133384219, "loss": 1.7279, "step": 50990 }, { "epoch": 10.56, "learning_rate": 0.00040854880259517224, "loss": 1.7232, "step": 50995 }, { "epoch": 10.57, "learning_rate": 0.0004084533918519225, "loss": 1.7267, "step": 51000 }, { "epoch": 10.57, "eval_accuracy": 0.5452549019607843, "eval_loss": 1.9181323051452637, "eval_runtime": 0.4962, "eval_samples_per_second": 302.306, "eval_steps_per_second": 2.015, "step": 51000 }, { "epoch": 10.57, "learning_rate": 0.00040835798110867285, "loss": 1.728, "step": 51005 }, { "epoch": 10.57, "learning_rate": 0.00040826257036542313, "loss": 1.7261, "step": 51010 }, { "epoch": 10.57, "learning_rate": 0.00040816715962217347, "loss": 1.7247, "step": 51015 }, { "epoch": 10.57, "learning_rate": 0.0004080717488789238, "loss": 1.7305, "step": 51020 }, { "epoch": 10.57, "learning_rate": 0.0004079763381356741, "loss": 1.7273, "step": 51025 }, { "epoch": 10.57, "learning_rate": 0.00040788092739242436, "loss": 1.7252, "step": 51030 }, { "epoch": 10.57, "learning_rate": 0.0004077855166491747, "loss": 1.7279, "step": 51035 }, { "epoch": 10.57, "learning_rate": 0.00040769010590592503, "loss": 1.7241, "step": 51040 }, { "epoch": 10.57, "learning_rate": 0.0004075946951626753, "loss": 1.7242, "step": 51045 }, { "epoch": 10.58, "learning_rate": 0.00040749928441942564, "loss": 1.7289, "step": 51050 }, { "epoch": 10.58, "learning_rate": 0.0004074038736761759, "loss": 1.7216, "step": 51055 }, { "epoch": 10.58, "learning_rate": 0.00040730846293292626, "loss": 1.7263, "step": 51060 }, { "epoch": 10.58, "learning_rate": 0.0004072130521896766, "loss": 1.7271, "step": 51065 }, { "epoch": 10.58, "learning_rate": 0.00040711764144642687, "loss": 1.727, "step": 51070 }, { "epoch": 10.58, "learning_rate": 0.00040702223070317715, "loss": 1.727, "step": 51075 }, { "epoch": 10.58, "learning_rate": 0.0004069268199599275, "loss": 1.7253, "step": 51080 }, { "epoch": 10.58, "learning_rate": 0.0004068314092166778, "loss": 1.7242, "step": 51085 }, { "epoch": 10.58, "learning_rate": 0.00040673599847342815, "loss": 1.7261, "step": 51090 }, { "epoch": 10.59, "learning_rate": 0.00040664058773017843, "loss": 1.7262, "step": 51095 }, { "epoch": 10.59, "learning_rate": 0.0004065451769869287, "loss": 1.7226, "step": 51100 }, { "epoch": 10.59, "learning_rate": 0.00040644976624367905, "loss": 1.7276, "step": 51105 }, { "epoch": 10.59, "learning_rate": 0.0004063543555004294, "loss": 1.726, "step": 51110 }, { "epoch": 10.59, "learning_rate": 0.00040625894475717966, "loss": 1.727, "step": 51115 }, { "epoch": 10.59, "learning_rate": 0.00040616353401393, "loss": 1.7319, "step": 51120 }, { "epoch": 10.59, "learning_rate": 0.0004060681232706803, "loss": 1.731, "step": 51125 }, { "epoch": 10.59, "learning_rate": 0.0004059727125274306, "loss": 1.7247, "step": 51130 }, { "epoch": 10.59, "learning_rate": 0.00040587730178418094, "loss": 1.7293, "step": 51135 }, { "epoch": 10.59, "learning_rate": 0.0004057818910409312, "loss": 1.7292, "step": 51140 }, { "epoch": 10.6, "learning_rate": 0.0004056864802976815, "loss": 1.7303, "step": 51145 }, { "epoch": 10.6, "learning_rate": 0.00040559106955443183, "loss": 1.7261, "step": 51150 }, { "epoch": 10.6, "learning_rate": 0.00040549565881118217, "loss": 1.7264, "step": 51155 }, { "epoch": 10.6, "learning_rate": 0.00040540024806793245, "loss": 1.7288, "step": 51160 }, { "epoch": 10.6, "learning_rate": 0.0004053048373246828, "loss": 1.7263, "step": 51165 }, { "epoch": 10.6, "learning_rate": 0.00040520942658143306, "loss": 1.7296, "step": 51170 }, { "epoch": 10.6, "learning_rate": 0.0004051140158381834, "loss": 1.7254, "step": 51175 }, { "epoch": 10.6, "learning_rate": 0.00040501860509493373, "loss": 1.7199, "step": 51180 }, { "epoch": 10.6, "learning_rate": 0.000404923194351684, "loss": 1.7286, "step": 51185 }, { "epoch": 10.6, "learning_rate": 0.0004048277836084343, "loss": 1.7291, "step": 51190 }, { "epoch": 10.61, "learning_rate": 0.0004047323728651846, "loss": 1.7203, "step": 51195 }, { "epoch": 10.61, "learning_rate": 0.00040463696212193496, "loss": 1.7264, "step": 51200 }, { "epoch": 10.61, "learning_rate": 0.00040454155137868524, "loss": 1.7203, "step": 51205 }, { "epoch": 10.61, "learning_rate": 0.00040444614063543557, "loss": 1.725, "step": 51210 }, { "epoch": 10.61, "learning_rate": 0.00040435072989218585, "loss": 1.7328, "step": 51215 }, { "epoch": 10.61, "learning_rate": 0.00040425531914893613, "loss": 1.7313, "step": 51220 }, { "epoch": 10.61, "learning_rate": 0.0004041599084056865, "loss": 1.7273, "step": 51225 }, { "epoch": 10.61, "learning_rate": 0.0004040644976624368, "loss": 1.7285, "step": 51230 }, { "epoch": 10.61, "learning_rate": 0.0004039690869191871, "loss": 1.7255, "step": 51235 }, { "epoch": 10.62, "learning_rate": 0.0004038736761759374, "loss": 1.7269, "step": 51240 }, { "epoch": 10.62, "learning_rate": 0.00040377826543268775, "loss": 1.727, "step": 51245 }, { "epoch": 10.62, "learning_rate": 0.000403682854689438, "loss": 1.7277, "step": 51250 }, { "epoch": 10.62, "learning_rate": 0.00040358744394618836, "loss": 1.7269, "step": 51255 }, { "epoch": 10.62, "learning_rate": 0.00040349203320293864, "loss": 1.7265, "step": 51260 }, { "epoch": 10.62, "learning_rate": 0.0004033966224596889, "loss": 1.7253, "step": 51265 }, { "epoch": 10.62, "learning_rate": 0.0004033012117164393, "loss": 1.7272, "step": 51270 }, { "epoch": 10.62, "learning_rate": 0.0004032058009731896, "loss": 1.722, "step": 51275 }, { "epoch": 10.62, "learning_rate": 0.00040311039022993987, "loss": 1.7218, "step": 51280 }, { "epoch": 10.62, "learning_rate": 0.0004030149794866902, "loss": 1.7228, "step": 51285 }, { "epoch": 10.63, "learning_rate": 0.00040291956874344054, "loss": 1.7274, "step": 51290 }, { "epoch": 10.63, "learning_rate": 0.00040282415800019087, "loss": 1.7273, "step": 51295 }, { "epoch": 10.63, "learning_rate": 0.00040272874725694115, "loss": 1.7218, "step": 51300 }, { "epoch": 10.63, "learning_rate": 0.00040263333651369143, "loss": 1.7216, "step": 51305 }, { "epoch": 10.63, "learning_rate": 0.00040253792577044176, "loss": 1.7282, "step": 51310 }, { "epoch": 10.63, "learning_rate": 0.0004024425150271921, "loss": 1.7348, "step": 51315 }, { "epoch": 10.63, "learning_rate": 0.0004023471042839424, "loss": 1.7283, "step": 51320 }, { "epoch": 10.63, "learning_rate": 0.0004022516935406927, "loss": 1.7268, "step": 51325 }, { "epoch": 10.63, "learning_rate": 0.000402156282797443, "loss": 1.7336, "step": 51330 }, { "epoch": 10.63, "learning_rate": 0.00040206087205419327, "loss": 1.7211, "step": 51335 }, { "epoch": 10.64, "learning_rate": 0.00040196546131094366, "loss": 1.7274, "step": 51340 }, { "epoch": 10.64, "learning_rate": 0.00040187005056769394, "loss": 1.7263, "step": 51345 }, { "epoch": 10.64, "learning_rate": 0.0004017746398244442, "loss": 1.7231, "step": 51350 }, { "epoch": 10.64, "learning_rate": 0.00040167922908119455, "loss": 1.7252, "step": 51355 }, { "epoch": 10.64, "learning_rate": 0.0004015838183379449, "loss": 1.7255, "step": 51360 }, { "epoch": 10.64, "learning_rate": 0.00040148840759469517, "loss": 1.7239, "step": 51365 }, { "epoch": 10.64, "learning_rate": 0.0004013929968514455, "loss": 1.723, "step": 51370 }, { "epoch": 10.64, "learning_rate": 0.0004012975861081958, "loss": 1.7248, "step": 51375 }, { "epoch": 10.64, "learning_rate": 0.00040120217536494606, "loss": 1.7248, "step": 51380 }, { "epoch": 10.65, "learning_rate": 0.00040110676462169645, "loss": 1.7272, "step": 51385 }, { "epoch": 10.65, "learning_rate": 0.00040101135387844673, "loss": 1.7283, "step": 51390 }, { "epoch": 10.65, "learning_rate": 0.000400915943135197, "loss": 1.7195, "step": 51395 }, { "epoch": 10.65, "learning_rate": 0.00040082053239194734, "loss": 1.7289, "step": 51400 }, { "epoch": 10.65, "learning_rate": 0.0004007251216486977, "loss": 1.723, "step": 51405 }, { "epoch": 10.65, "learning_rate": 0.00040062971090544796, "loss": 1.731, "step": 51410 }, { "epoch": 10.65, "learning_rate": 0.0004005343001621983, "loss": 1.7313, "step": 51415 }, { "epoch": 10.65, "learning_rate": 0.00040043888941894857, "loss": 1.733, "step": 51420 }, { "epoch": 10.65, "learning_rate": 0.00040034347867569885, "loss": 1.7262, "step": 51425 }, { "epoch": 10.65, "learning_rate": 0.00040024806793244924, "loss": 1.7307, "step": 51430 }, { "epoch": 10.66, "learning_rate": 0.0004001526571891995, "loss": 1.7283, "step": 51435 }, { "epoch": 10.66, "learning_rate": 0.0004000572464459498, "loss": 1.7271, "step": 51440 }, { "epoch": 10.66, "learning_rate": 0.00039996183570270013, "loss": 1.7192, "step": 51445 }, { "epoch": 10.66, "learning_rate": 0.00039986642495945047, "loss": 1.7222, "step": 51450 }, { "epoch": 10.66, "learning_rate": 0.00039977101421620074, "loss": 1.7258, "step": 51455 }, { "epoch": 10.66, "learning_rate": 0.0003996756034729511, "loss": 1.7232, "step": 51460 }, { "epoch": 10.66, "learning_rate": 0.00039958019272970136, "loss": 1.727, "step": 51465 }, { "epoch": 10.66, "learning_rate": 0.00039948478198645164, "loss": 1.7206, "step": 51470 }, { "epoch": 10.66, "learning_rate": 0.000399389371243202, "loss": 1.7295, "step": 51475 }, { "epoch": 10.67, "learning_rate": 0.0003992939604999523, "loss": 1.7222, "step": 51480 }, { "epoch": 10.67, "learning_rate": 0.0003991985497567026, "loss": 1.7253, "step": 51485 }, { "epoch": 10.67, "learning_rate": 0.0003991031390134529, "loss": 1.7256, "step": 51490 }, { "epoch": 10.67, "learning_rate": 0.0003990077282702032, "loss": 1.7228, "step": 51495 }, { "epoch": 10.67, "learning_rate": 0.00039891231752695353, "loss": 1.7199, "step": 51500 }, { "epoch": 10.67, "learning_rate": 0.00039881690678370387, "loss": 1.7305, "step": 51505 }, { "epoch": 10.67, "learning_rate": 0.00039872149604045415, "loss": 1.7253, "step": 51510 }, { "epoch": 10.67, "learning_rate": 0.0003986260852972045, "loss": 1.7288, "step": 51515 }, { "epoch": 10.67, "learning_rate": 0.0003985306745539548, "loss": 1.7178, "step": 51520 }, { "epoch": 10.67, "learning_rate": 0.0003984352638107051, "loss": 1.7289, "step": 51525 }, { "epoch": 10.68, "learning_rate": 0.00039833985306745543, "loss": 1.7267, "step": 51530 }, { "epoch": 10.68, "learning_rate": 0.0003982444423242057, "loss": 1.7257, "step": 51535 }, { "epoch": 10.68, "learning_rate": 0.000398149031580956, "loss": 1.7276, "step": 51540 }, { "epoch": 10.68, "learning_rate": 0.0003980536208377064, "loss": 1.7297, "step": 51545 }, { "epoch": 10.68, "learning_rate": 0.00039795821009445666, "loss": 1.7227, "step": 51550 }, { "epoch": 10.68, "learning_rate": 0.00039786279935120694, "loss": 1.7223, "step": 51555 }, { "epoch": 10.68, "learning_rate": 0.00039776738860795727, "loss": 1.7271, "step": 51560 }, { "epoch": 10.68, "learning_rate": 0.0003976719778647076, "loss": 1.7254, "step": 51565 }, { "epoch": 10.68, "learning_rate": 0.0003975765671214579, "loss": 1.7293, "step": 51570 }, { "epoch": 10.68, "learning_rate": 0.0003974811563782082, "loss": 1.7246, "step": 51575 }, { "epoch": 10.69, "learning_rate": 0.0003973857456349585, "loss": 1.7246, "step": 51580 }, { "epoch": 10.69, "learning_rate": 0.0003972903348917088, "loss": 1.7224, "step": 51585 }, { "epoch": 10.69, "learning_rate": 0.00039719492414845917, "loss": 1.7263, "step": 51590 }, { "epoch": 10.69, "learning_rate": 0.00039709951340520945, "loss": 1.7284, "step": 51595 }, { "epoch": 10.69, "learning_rate": 0.0003970041026619597, "loss": 1.7253, "step": 51600 }, { "epoch": 10.69, "learning_rate": 0.00039690869191871006, "loss": 1.726, "step": 51605 }, { "epoch": 10.69, "learning_rate": 0.00039681328117546034, "loss": 1.724, "step": 51610 }, { "epoch": 10.69, "learning_rate": 0.0003967178704322107, "loss": 1.7278, "step": 51615 }, { "epoch": 10.69, "learning_rate": 0.000396622459688961, "loss": 1.7296, "step": 51620 }, { "epoch": 10.7, "learning_rate": 0.0003965270489457113, "loss": 1.724, "step": 51625 }, { "epoch": 10.7, "learning_rate": 0.00039643163820246157, "loss": 1.7249, "step": 51630 }, { "epoch": 10.7, "learning_rate": 0.00039633622745921196, "loss": 1.7287, "step": 51635 }, { "epoch": 10.7, "learning_rate": 0.00039624081671596224, "loss": 1.7283, "step": 51640 }, { "epoch": 10.7, "learning_rate": 0.0003961454059727125, "loss": 1.7295, "step": 51645 }, { "epoch": 10.7, "learning_rate": 0.00039604999522946285, "loss": 1.7182, "step": 51650 }, { "epoch": 10.7, "learning_rate": 0.00039595458448621313, "loss": 1.7248, "step": 51655 }, { "epoch": 10.7, "learning_rate": 0.00039585917374296346, "loss": 1.7206, "step": 51660 }, { "epoch": 10.7, "learning_rate": 0.0003957637629997138, "loss": 1.725, "step": 51665 }, { "epoch": 10.7, "learning_rate": 0.0003956683522564641, "loss": 1.726, "step": 51670 }, { "epoch": 10.71, "learning_rate": 0.00039557294151321436, "loss": 1.7235, "step": 51675 }, { "epoch": 10.71, "learning_rate": 0.00039547753076996474, "loss": 1.7227, "step": 51680 }, { "epoch": 10.71, "learning_rate": 0.000395382120026715, "loss": 1.7244, "step": 51685 }, { "epoch": 10.71, "learning_rate": 0.0003952867092834653, "loss": 1.725, "step": 51690 }, { "epoch": 10.71, "learning_rate": 0.00039519129854021564, "loss": 1.7335, "step": 51695 }, { "epoch": 10.71, "learning_rate": 0.0003950958877969659, "loss": 1.7285, "step": 51700 }, { "epoch": 10.71, "learning_rate": 0.00039500047705371625, "loss": 1.7258, "step": 51705 }, { "epoch": 10.71, "learning_rate": 0.0003949050663104666, "loss": 1.7249, "step": 51710 }, { "epoch": 10.71, "learning_rate": 0.00039480965556721687, "loss": 1.7292, "step": 51715 }, { "epoch": 10.71, "learning_rate": 0.00039471424482396715, "loss": 1.727, "step": 51720 }, { "epoch": 10.72, "learning_rate": 0.0003946188340807175, "loss": 1.7282, "step": 51725 }, { "epoch": 10.72, "learning_rate": 0.0003945234233374678, "loss": 1.7207, "step": 51730 }, { "epoch": 10.72, "learning_rate": 0.00039442801259421815, "loss": 1.7306, "step": 51735 }, { "epoch": 10.72, "learning_rate": 0.00039433260185096843, "loss": 1.7303, "step": 51740 }, { "epoch": 10.72, "learning_rate": 0.0003942371911077187, "loss": 1.7287, "step": 51745 }, { "epoch": 10.72, "learning_rate": 0.0003941417803644691, "loss": 1.7285, "step": 51750 }, { "epoch": 10.72, "learning_rate": 0.0003940463696212194, "loss": 1.7274, "step": 51755 }, { "epoch": 10.72, "learning_rate": 0.00039395095887796965, "loss": 1.7271, "step": 51760 }, { "epoch": 10.72, "learning_rate": 0.00039385554813472, "loss": 1.7241, "step": 51765 }, { "epoch": 10.73, "learning_rate": 0.00039376013739147027, "loss": 1.7216, "step": 51770 }, { "epoch": 10.73, "learning_rate": 0.0003936647266482206, "loss": 1.7246, "step": 51775 }, { "epoch": 10.73, "learning_rate": 0.00039356931590497094, "loss": 1.7231, "step": 51780 }, { "epoch": 10.73, "learning_rate": 0.0003934739051617212, "loss": 1.7325, "step": 51785 }, { "epoch": 10.73, "learning_rate": 0.0003933784944184715, "loss": 1.727, "step": 51790 }, { "epoch": 10.73, "learning_rate": 0.0003932830836752219, "loss": 1.7281, "step": 51795 }, { "epoch": 10.73, "learning_rate": 0.00039318767293197216, "loss": 1.7282, "step": 51800 }, { "epoch": 10.73, "learning_rate": 0.00039309226218872244, "loss": 1.729, "step": 51805 }, { "epoch": 10.73, "learning_rate": 0.0003929968514454728, "loss": 1.7243, "step": 51810 }, { "epoch": 10.73, "learning_rate": 0.00039290144070222306, "loss": 1.7259, "step": 51815 }, { "epoch": 10.74, "learning_rate": 0.0003928060299589734, "loss": 1.7284, "step": 51820 }, { "epoch": 10.74, "learning_rate": 0.0003927106192157237, "loss": 1.7325, "step": 51825 }, { "epoch": 10.74, "learning_rate": 0.000392615208472474, "loss": 1.727, "step": 51830 }, { "epoch": 10.74, "learning_rate": 0.0003925197977292243, "loss": 1.7271, "step": 51835 }, { "epoch": 10.74, "learning_rate": 0.0003924243869859746, "loss": 1.7269, "step": 51840 }, { "epoch": 10.74, "learning_rate": 0.00039232897624272495, "loss": 1.7266, "step": 51845 }, { "epoch": 10.74, "learning_rate": 0.00039223356549947523, "loss": 1.7271, "step": 51850 }, { "epoch": 10.74, "learning_rate": 0.00039213815475622557, "loss": 1.7291, "step": 51855 }, { "epoch": 10.74, "learning_rate": 0.00039204274401297585, "loss": 1.7255, "step": 51860 }, { "epoch": 10.74, "learning_rate": 0.0003919473332697262, "loss": 1.7277, "step": 51865 }, { "epoch": 10.75, "learning_rate": 0.0003918519225264765, "loss": 1.7272, "step": 51870 }, { "epoch": 10.75, "learning_rate": 0.0003917565117832268, "loss": 1.7239, "step": 51875 }, { "epoch": 10.75, "learning_rate": 0.0003916611010399771, "loss": 1.7238, "step": 51880 }, { "epoch": 10.75, "learning_rate": 0.0003915656902967274, "loss": 1.7295, "step": 51885 }, { "epoch": 10.75, "learning_rate": 0.00039147027955347774, "loss": 1.7282, "step": 51890 }, { "epoch": 10.75, "learning_rate": 0.000391374868810228, "loss": 1.732, "step": 51895 }, { "epoch": 10.75, "learning_rate": 0.00039127945806697836, "loss": 1.7221, "step": 51900 }, { "epoch": 10.75, "learning_rate": 0.00039118404732372864, "loss": 1.7224, "step": 51905 }, { "epoch": 10.75, "learning_rate": 0.00039108863658047897, "loss": 1.7247, "step": 51910 }, { "epoch": 10.76, "learning_rate": 0.0003909932258372293, "loss": 1.7276, "step": 51915 }, { "epoch": 10.76, "learning_rate": 0.0003908978150939796, "loss": 1.7294, "step": 51920 }, { "epoch": 10.76, "learning_rate": 0.00039080240435072986, "loss": 1.7263, "step": 51925 }, { "epoch": 10.76, "learning_rate": 0.0003907069936074802, "loss": 1.7303, "step": 51930 }, { "epoch": 10.76, "learning_rate": 0.00039061158286423053, "loss": 1.7298, "step": 51935 }, { "epoch": 10.76, "learning_rate": 0.00039051617212098087, "loss": 1.7278, "step": 51940 }, { "epoch": 10.76, "learning_rate": 0.00039042076137773115, "loss": 1.7231, "step": 51945 }, { "epoch": 10.76, "learning_rate": 0.0003903253506344814, "loss": 1.7227, "step": 51950 }, { "epoch": 10.76, "learning_rate": 0.00039022993989123176, "loss": 1.7258, "step": 51955 }, { "epoch": 10.76, "learning_rate": 0.0003901345291479821, "loss": 1.7199, "step": 51960 }, { "epoch": 10.77, "learning_rate": 0.00039003911840473237, "loss": 1.7286, "step": 51965 }, { "epoch": 10.77, "learning_rate": 0.0003899437076614827, "loss": 1.7264, "step": 51970 }, { "epoch": 10.77, "learning_rate": 0.000389848296918233, "loss": 1.7285, "step": 51975 }, { "epoch": 10.77, "learning_rate": 0.0003897528861749833, "loss": 1.7247, "step": 51980 }, { "epoch": 10.77, "learning_rate": 0.00038965747543173365, "loss": 1.7263, "step": 51985 }, { "epoch": 10.77, "learning_rate": 0.00038956206468848393, "loss": 1.7276, "step": 51990 }, { "epoch": 10.77, "learning_rate": 0.0003894666539452342, "loss": 1.7229, "step": 51995 }, { "epoch": 10.77, "learning_rate": 0.00038937124320198455, "loss": 1.729, "step": 52000 }, { "epoch": 10.77, "learning_rate": 0.0003892758324587349, "loss": 1.7266, "step": 52005 }, { "epoch": 10.77, "learning_rate": 0.00038918042171548516, "loss": 1.7267, "step": 52010 }, { "epoch": 10.78, "learning_rate": 0.0003890850109722355, "loss": 1.7299, "step": 52015 }, { "epoch": 10.78, "learning_rate": 0.0003889896002289858, "loss": 1.7321, "step": 52020 }, { "epoch": 10.78, "learning_rate": 0.0003888941894857361, "loss": 1.7282, "step": 52025 }, { "epoch": 10.78, "learning_rate": 0.00038879877874248644, "loss": 1.7268, "step": 52030 }, { "epoch": 10.78, "learning_rate": 0.0003887033679992367, "loss": 1.7261, "step": 52035 }, { "epoch": 10.78, "learning_rate": 0.000388607957255987, "loss": 1.7235, "step": 52040 }, { "epoch": 10.78, "learning_rate": 0.00038851254651273734, "loss": 1.7268, "step": 52045 }, { "epoch": 10.78, "learning_rate": 0.00038841713576948767, "loss": 1.7272, "step": 52050 }, { "epoch": 10.78, "learning_rate": 0.00038832172502623795, "loss": 1.7257, "step": 52055 }, { "epoch": 10.79, "learning_rate": 0.0003882263142829883, "loss": 1.7203, "step": 52060 }, { "epoch": 10.79, "learning_rate": 0.00038813090353973856, "loss": 1.7305, "step": 52065 }, { "epoch": 10.79, "learning_rate": 0.0003880354927964889, "loss": 1.7241, "step": 52070 }, { "epoch": 10.79, "learning_rate": 0.00038794008205323923, "loss": 1.7257, "step": 52075 }, { "epoch": 10.79, "learning_rate": 0.0003878446713099895, "loss": 1.7226, "step": 52080 }, { "epoch": 10.79, "learning_rate": 0.0003877492605667398, "loss": 1.7245, "step": 52085 }, { "epoch": 10.79, "learning_rate": 0.0003876538498234901, "loss": 1.7306, "step": 52090 }, { "epoch": 10.79, "learning_rate": 0.00038755843908024046, "loss": 1.7303, "step": 52095 }, { "epoch": 10.79, "learning_rate": 0.00038746302833699074, "loss": 1.7282, "step": 52100 }, { "epoch": 10.79, "learning_rate": 0.0003873676175937411, "loss": 1.7222, "step": 52105 }, { "epoch": 10.8, "learning_rate": 0.00038727220685049135, "loss": 1.7236, "step": 52110 }, { "epoch": 10.8, "learning_rate": 0.00038717679610724163, "loss": 1.7277, "step": 52115 }, { "epoch": 10.8, "learning_rate": 0.000387081385363992, "loss": 1.727, "step": 52120 }, { "epoch": 10.8, "learning_rate": 0.0003869859746207423, "loss": 1.7219, "step": 52125 }, { "epoch": 10.8, "learning_rate": 0.0003868905638774926, "loss": 1.7226, "step": 52130 }, { "epoch": 10.8, "learning_rate": 0.0003867951531342429, "loss": 1.7281, "step": 52135 }, { "epoch": 10.8, "learning_rate": 0.00038669974239099325, "loss": 1.7233, "step": 52140 }, { "epoch": 10.8, "learning_rate": 0.0003866043316477436, "loss": 1.7274, "step": 52145 }, { "epoch": 10.8, "learning_rate": 0.00038650892090449386, "loss": 1.7275, "step": 52150 }, { "epoch": 10.8, "learning_rate": 0.00038641351016124414, "loss": 1.7265, "step": 52155 }, { "epoch": 10.81, "learning_rate": 0.0003863180994179945, "loss": 1.7262, "step": 52160 }, { "epoch": 10.81, "learning_rate": 0.0003862226886747448, "loss": 1.7234, "step": 52165 }, { "epoch": 10.81, "learning_rate": 0.0003861272779314951, "loss": 1.726, "step": 52170 }, { "epoch": 10.81, "learning_rate": 0.0003860318671882454, "loss": 1.728, "step": 52175 }, { "epoch": 10.81, "learning_rate": 0.0003859364564449957, "loss": 1.7254, "step": 52180 }, { "epoch": 10.81, "learning_rate": 0.00038584104570174604, "loss": 1.7223, "step": 52185 }, { "epoch": 10.81, "learning_rate": 0.00038574563495849637, "loss": 1.726, "step": 52190 }, { "epoch": 10.81, "learning_rate": 0.00038565022421524665, "loss": 1.7204, "step": 52195 }, { "epoch": 10.81, "learning_rate": 0.00038555481347199693, "loss": 1.7202, "step": 52200 }, { "epoch": 10.82, "learning_rate": 0.00038545940272874727, "loss": 1.7301, "step": 52205 }, { "epoch": 10.82, "learning_rate": 0.0003853639919854976, "loss": 1.727, "step": 52210 }, { "epoch": 10.82, "learning_rate": 0.0003852685812422479, "loss": 1.725, "step": 52215 }, { "epoch": 10.82, "learning_rate": 0.0003851731704989982, "loss": 1.7282, "step": 52220 }, { "epoch": 10.82, "learning_rate": 0.0003850777597557485, "loss": 1.7225, "step": 52225 }, { "epoch": 10.82, "learning_rate": 0.0003849823490124988, "loss": 1.7249, "step": 52230 }, { "epoch": 10.82, "learning_rate": 0.00038488693826924916, "loss": 1.7295, "step": 52235 }, { "epoch": 10.82, "learning_rate": 0.00038479152752599944, "loss": 1.7263, "step": 52240 }, { "epoch": 10.82, "learning_rate": 0.0003846961167827497, "loss": 1.7232, "step": 52245 }, { "epoch": 10.82, "learning_rate": 0.00038460070603950006, "loss": 1.7301, "step": 52250 }, { "epoch": 10.83, "learning_rate": 0.0003845052952962504, "loss": 1.7278, "step": 52255 }, { "epoch": 10.83, "learning_rate": 0.00038440988455300067, "loss": 1.7275, "step": 52260 }, { "epoch": 10.83, "learning_rate": 0.000384314473809751, "loss": 1.7265, "step": 52265 }, { "epoch": 10.83, "learning_rate": 0.0003842190630665013, "loss": 1.7239, "step": 52270 }, { "epoch": 10.83, "learning_rate": 0.00038412365232325156, "loss": 1.7258, "step": 52275 }, { "epoch": 10.83, "learning_rate": 0.00038402824158000195, "loss": 1.7267, "step": 52280 }, { "epoch": 10.83, "learning_rate": 0.00038393283083675223, "loss": 1.7247, "step": 52285 }, { "epoch": 10.83, "learning_rate": 0.0003838374200935025, "loss": 1.7272, "step": 52290 }, { "epoch": 10.83, "learning_rate": 0.00038374200935025284, "loss": 1.7229, "step": 52295 }, { "epoch": 10.83, "learning_rate": 0.0003836465986070032, "loss": 1.7205, "step": 52300 }, { "epoch": 10.84, "learning_rate": 0.00038355118786375346, "loss": 1.7292, "step": 52305 }, { "epoch": 10.84, "learning_rate": 0.0003834557771205038, "loss": 1.7232, "step": 52310 }, { "epoch": 10.84, "learning_rate": 0.00038336036637725407, "loss": 1.7318, "step": 52315 }, { "epoch": 10.84, "learning_rate": 0.00038326495563400435, "loss": 1.73, "step": 52320 }, { "epoch": 10.84, "learning_rate": 0.00038316954489075474, "loss": 1.7301, "step": 52325 }, { "epoch": 10.84, "learning_rate": 0.000383074134147505, "loss": 1.7289, "step": 52330 }, { "epoch": 10.84, "learning_rate": 0.0003829787234042553, "loss": 1.7264, "step": 52335 }, { "epoch": 10.84, "learning_rate": 0.00038288331266100563, "loss": 1.7281, "step": 52340 }, { "epoch": 10.84, "learning_rate": 0.0003827879019177559, "loss": 1.7244, "step": 52345 }, { "epoch": 10.85, "learning_rate": 0.00038269249117450625, "loss": 1.7269, "step": 52350 }, { "epoch": 10.85, "learning_rate": 0.0003825970804312566, "loss": 1.7272, "step": 52355 }, { "epoch": 10.85, "learning_rate": 0.00038250166968800686, "loss": 1.7281, "step": 52360 }, { "epoch": 10.85, "learning_rate": 0.0003824062589447572, "loss": 1.7239, "step": 52365 }, { "epoch": 10.85, "learning_rate": 0.00038231084820150753, "loss": 1.7224, "step": 52370 }, { "epoch": 10.85, "learning_rate": 0.0003822154374582578, "loss": 1.7257, "step": 52375 }, { "epoch": 10.85, "learning_rate": 0.00038212002671500814, "loss": 1.7207, "step": 52380 }, { "epoch": 10.85, "learning_rate": 0.0003820246159717584, "loss": 1.7297, "step": 52385 }, { "epoch": 10.85, "learning_rate": 0.0003819292052285087, "loss": 1.7289, "step": 52390 }, { "epoch": 10.85, "learning_rate": 0.0003818337944852591, "loss": 1.723, "step": 52395 }, { "epoch": 10.86, "learning_rate": 0.00038173838374200937, "loss": 1.7293, "step": 52400 }, { "epoch": 10.86, "learning_rate": 0.00038164297299875965, "loss": 1.7257, "step": 52405 }, { "epoch": 10.86, "learning_rate": 0.00038154756225551, "loss": 1.7256, "step": 52410 }, { "epoch": 10.86, "learning_rate": 0.0003814521515122603, "loss": 1.725, "step": 52415 }, { "epoch": 10.86, "learning_rate": 0.0003813567407690106, "loss": 1.7244, "step": 52420 }, { "epoch": 10.86, "learning_rate": 0.00038126133002576093, "loss": 1.7246, "step": 52425 }, { "epoch": 10.86, "learning_rate": 0.0003811659192825112, "loss": 1.7231, "step": 52430 }, { "epoch": 10.86, "learning_rate": 0.0003810705085392615, "loss": 1.7226, "step": 52435 }, { "epoch": 10.86, "learning_rate": 0.0003809750977960119, "loss": 1.7291, "step": 52440 }, { "epoch": 10.86, "learning_rate": 0.00038087968705276216, "loss": 1.7242, "step": 52445 }, { "epoch": 10.87, "learning_rate": 0.00038078427630951244, "loss": 1.7227, "step": 52450 }, { "epoch": 10.87, "learning_rate": 0.0003806888655662628, "loss": 1.7213, "step": 52455 }, { "epoch": 10.87, "learning_rate": 0.00038059345482301305, "loss": 1.7245, "step": 52460 }, { "epoch": 10.87, "learning_rate": 0.0003804980440797634, "loss": 1.7227, "step": 52465 }, { "epoch": 10.87, "learning_rate": 0.0003804026333365137, "loss": 1.7267, "step": 52470 }, { "epoch": 10.87, "learning_rate": 0.000380307222593264, "loss": 1.7288, "step": 52475 }, { "epoch": 10.87, "learning_rate": 0.0003802118118500143, "loss": 1.7308, "step": 52480 }, { "epoch": 10.87, "learning_rate": 0.00038011640110676467, "loss": 1.7283, "step": 52485 }, { "epoch": 10.87, "learning_rate": 0.00038002099036351495, "loss": 1.7233, "step": 52490 }, { "epoch": 10.88, "learning_rate": 0.00037992557962026523, "loss": 1.7221, "step": 52495 }, { "epoch": 10.88, "learning_rate": 0.00037983016887701556, "loss": 1.7295, "step": 52500 }, { "epoch": 10.88, "learning_rate": 0.00037973475813376584, "loss": 1.7276, "step": 52505 }, { "epoch": 10.88, "learning_rate": 0.0003796393473905162, "loss": 1.7233, "step": 52510 }, { "epoch": 10.88, "learning_rate": 0.0003795439366472665, "loss": 1.7243, "step": 52515 }, { "epoch": 10.88, "learning_rate": 0.0003794485259040168, "loss": 1.7243, "step": 52520 }, { "epoch": 10.88, "learning_rate": 0.00037935311516076707, "loss": 1.728, "step": 52525 }, { "epoch": 10.88, "learning_rate": 0.00037925770441751746, "loss": 1.7201, "step": 52530 }, { "epoch": 10.88, "learning_rate": 0.00037916229367426774, "loss": 1.7269, "step": 52535 }, { "epoch": 10.88, "learning_rate": 0.000379066882931018, "loss": 1.7234, "step": 52540 }, { "epoch": 10.89, "learning_rate": 0.00037897147218776835, "loss": 1.7293, "step": 52545 }, { "epoch": 10.89, "learning_rate": 0.00037887606144451863, "loss": 1.7206, "step": 52550 }, { "epoch": 10.89, "learning_rate": 0.00037878065070126897, "loss": 1.7238, "step": 52555 }, { "epoch": 10.89, "learning_rate": 0.0003786852399580193, "loss": 1.7192, "step": 52560 }, { "epoch": 10.89, "learning_rate": 0.0003785898292147696, "loss": 1.7231, "step": 52565 }, { "epoch": 10.89, "learning_rate": 0.00037849441847151986, "loss": 1.7182, "step": 52570 }, { "epoch": 10.89, "learning_rate": 0.0003783990077282702, "loss": 1.7269, "step": 52575 }, { "epoch": 10.89, "learning_rate": 0.0003783035969850205, "loss": 1.7305, "step": 52580 }, { "epoch": 10.89, "learning_rate": 0.00037820818624177086, "loss": 1.7271, "step": 52585 }, { "epoch": 10.89, "learning_rate": 0.00037811277549852114, "loss": 1.7248, "step": 52590 }, { "epoch": 10.9, "learning_rate": 0.0003780173647552714, "loss": 1.7247, "step": 52595 }, { "epoch": 10.9, "learning_rate": 0.0003779219540120218, "loss": 1.7268, "step": 52600 }, { "epoch": 10.9, "learning_rate": 0.0003778265432687721, "loss": 1.7303, "step": 52605 }, { "epoch": 10.9, "learning_rate": 0.00037773113252552237, "loss": 1.7301, "step": 52610 }, { "epoch": 10.9, "learning_rate": 0.0003776357217822727, "loss": 1.7228, "step": 52615 }, { "epoch": 10.9, "learning_rate": 0.000377540311039023, "loss": 1.7241, "step": 52620 }, { "epoch": 10.9, "learning_rate": 0.0003774449002957733, "loss": 1.7278, "step": 52625 }, { "epoch": 10.9, "learning_rate": 0.00037734948955252365, "loss": 1.7269, "step": 52630 }, { "epoch": 10.9, "learning_rate": 0.00037725407880927393, "loss": 1.7298, "step": 52635 }, { "epoch": 10.91, "learning_rate": 0.0003771586680660242, "loss": 1.7246, "step": 52640 }, { "epoch": 10.91, "learning_rate": 0.0003770632573227746, "loss": 1.7264, "step": 52645 }, { "epoch": 10.91, "learning_rate": 0.0003769678465795249, "loss": 1.7229, "step": 52650 }, { "epoch": 10.91, "learning_rate": 0.00037687243583627516, "loss": 1.7265, "step": 52655 }, { "epoch": 10.91, "learning_rate": 0.0003767770250930255, "loss": 1.7268, "step": 52660 }, { "epoch": 10.91, "learning_rate": 0.00037668161434977577, "loss": 1.7245, "step": 52665 }, { "epoch": 10.91, "learning_rate": 0.0003765862036065261, "loss": 1.729, "step": 52670 }, { "epoch": 10.91, "learning_rate": 0.00037649079286327644, "loss": 1.7291, "step": 52675 }, { "epoch": 10.91, "learning_rate": 0.0003763953821200267, "loss": 1.7255, "step": 52680 }, { "epoch": 10.91, "learning_rate": 0.000376299971376777, "loss": 1.7263, "step": 52685 }, { "epoch": 10.92, "learning_rate": 0.0003762045606335274, "loss": 1.7264, "step": 52690 }, { "epoch": 10.92, "learning_rate": 0.00037610914989027767, "loss": 1.7268, "step": 52695 }, { "epoch": 10.92, "learning_rate": 0.00037601373914702795, "loss": 1.7245, "step": 52700 }, { "epoch": 10.92, "learning_rate": 0.0003759183284037783, "loss": 1.7219, "step": 52705 }, { "epoch": 10.92, "learning_rate": 0.00037582291766052856, "loss": 1.7247, "step": 52710 }, { "epoch": 10.92, "learning_rate": 0.0003757275069172789, "loss": 1.7275, "step": 52715 }, { "epoch": 10.92, "learning_rate": 0.00037563209617402923, "loss": 1.7247, "step": 52720 }, { "epoch": 10.92, "learning_rate": 0.0003755366854307795, "loss": 1.7245, "step": 52725 }, { "epoch": 10.92, "learning_rate": 0.0003754412746875298, "loss": 1.7242, "step": 52730 }, { "epoch": 10.93, "learning_rate": 0.0003753458639442801, "loss": 1.7226, "step": 52735 }, { "epoch": 10.93, "learning_rate": 0.00037525045320103046, "loss": 1.7262, "step": 52740 }, { "epoch": 10.93, "learning_rate": 0.00037515504245778074, "loss": 1.7225, "step": 52745 }, { "epoch": 10.93, "learning_rate": 0.00037505963171453107, "loss": 1.7246, "step": 52750 }, { "epoch": 10.93, "learning_rate": 0.00037496422097128135, "loss": 1.7256, "step": 52755 }, { "epoch": 10.93, "learning_rate": 0.0003748688102280317, "loss": 1.731, "step": 52760 }, { "epoch": 10.93, "learning_rate": 0.000374773399484782, "loss": 1.7297, "step": 52765 }, { "epoch": 10.93, "learning_rate": 0.0003746779887415323, "loss": 1.7309, "step": 52770 }, { "epoch": 10.93, "learning_rate": 0.0003745825779982826, "loss": 1.7255, "step": 52775 }, { "epoch": 10.93, "learning_rate": 0.0003744871672550329, "loss": 1.7226, "step": 52780 }, { "epoch": 10.94, "learning_rate": 0.00037439175651178324, "loss": 1.7261, "step": 52785 }, { "epoch": 10.94, "learning_rate": 0.0003742963457685336, "loss": 1.7232, "step": 52790 }, { "epoch": 10.94, "learning_rate": 0.00037420093502528386, "loss": 1.7243, "step": 52795 }, { "epoch": 10.94, "learning_rate": 0.00037410552428203414, "loss": 1.7288, "step": 52800 }, { "epoch": 10.94, "learning_rate": 0.0003740101135387845, "loss": 1.7236, "step": 52805 }, { "epoch": 10.94, "learning_rate": 0.0003739147027955348, "loss": 1.7263, "step": 52810 }, { "epoch": 10.94, "learning_rate": 0.0003738192920522851, "loss": 1.7248, "step": 52815 }, { "epoch": 10.94, "learning_rate": 0.0003737238813090354, "loss": 1.7285, "step": 52820 }, { "epoch": 10.94, "learning_rate": 0.0003736284705657857, "loss": 1.7309, "step": 52825 }, { "epoch": 10.94, "learning_rate": 0.00037353305982253603, "loss": 1.7256, "step": 52830 }, { "epoch": 10.95, "learning_rate": 0.00037343764907928637, "loss": 1.7243, "step": 52835 }, { "epoch": 10.95, "learning_rate": 0.00037334223833603665, "loss": 1.7228, "step": 52840 }, { "epoch": 10.95, "learning_rate": 0.00037324682759278693, "loss": 1.7211, "step": 52845 }, { "epoch": 10.95, "learning_rate": 0.00037315141684953726, "loss": 1.7237, "step": 52850 }, { "epoch": 10.95, "learning_rate": 0.0003730560061062876, "loss": 1.7271, "step": 52855 }, { "epoch": 10.95, "learning_rate": 0.0003729605953630379, "loss": 1.7203, "step": 52860 }, { "epoch": 10.95, "learning_rate": 0.0003728651846197882, "loss": 1.7202, "step": 52865 }, { "epoch": 10.95, "learning_rate": 0.0003727697738765385, "loss": 1.7239, "step": 52870 }, { "epoch": 10.95, "learning_rate": 0.0003726743631332888, "loss": 1.7234, "step": 52875 }, { "epoch": 10.96, "learning_rate": 0.00037257895239003916, "loss": 1.726, "step": 52880 }, { "epoch": 10.96, "learning_rate": 0.00037248354164678944, "loss": 1.7249, "step": 52885 }, { "epoch": 10.96, "learning_rate": 0.0003723881309035397, "loss": 1.7244, "step": 52890 }, { "epoch": 10.96, "learning_rate": 0.00037229272016029005, "loss": 1.7263, "step": 52895 }, { "epoch": 10.96, "learning_rate": 0.0003721973094170404, "loss": 1.7274, "step": 52900 }, { "epoch": 10.96, "learning_rate": 0.00037210189867379066, "loss": 1.7266, "step": 52905 }, { "epoch": 10.96, "learning_rate": 0.000372006487930541, "loss": 1.7238, "step": 52910 }, { "epoch": 10.96, "learning_rate": 0.0003719110771872913, "loss": 1.7245, "step": 52915 }, { "epoch": 10.96, "learning_rate": 0.0003718156664440416, "loss": 1.7253, "step": 52920 }, { "epoch": 10.96, "learning_rate": 0.00037172025570079195, "loss": 1.7297, "step": 52925 }, { "epoch": 10.97, "learning_rate": 0.0003716248449575422, "loss": 1.7267, "step": 52930 }, { "epoch": 10.97, "learning_rate": 0.0003715294342142925, "loss": 1.7213, "step": 52935 }, { "epoch": 10.97, "learning_rate": 0.00037143402347104284, "loss": 1.7302, "step": 52940 }, { "epoch": 10.97, "learning_rate": 0.0003713386127277932, "loss": 1.7245, "step": 52945 }, { "epoch": 10.97, "learning_rate": 0.00037124320198454345, "loss": 1.7322, "step": 52950 }, { "epoch": 10.97, "learning_rate": 0.0003711477912412938, "loss": 1.7255, "step": 52955 }, { "epoch": 10.97, "learning_rate": 0.00037105238049804407, "loss": 1.7275, "step": 52960 }, { "epoch": 10.97, "learning_rate": 0.00037095696975479435, "loss": 1.7179, "step": 52965 }, { "epoch": 10.97, "learning_rate": 0.00037086155901154474, "loss": 1.7237, "step": 52970 }, { "epoch": 10.97, "learning_rate": 0.000370766148268295, "loss": 1.7269, "step": 52975 }, { "epoch": 10.98, "learning_rate": 0.0003706707375250453, "loss": 1.727, "step": 52980 }, { "epoch": 10.98, "learning_rate": 0.00037057532678179563, "loss": 1.7249, "step": 52985 }, { "epoch": 10.98, "learning_rate": 0.00037047991603854596, "loss": 1.7233, "step": 52990 }, { "epoch": 10.98, "learning_rate": 0.0003703845052952963, "loss": 1.7225, "step": 52995 }, { "epoch": 10.98, "learning_rate": 0.0003702890945520466, "loss": 1.7251, "step": 53000 }, { "epoch": 10.98, "learning_rate": 0.00037019368380879686, "loss": 1.7316, "step": 53005 }, { "epoch": 10.98, "learning_rate": 0.0003700982730655472, "loss": 1.7259, "step": 53010 }, { "epoch": 10.98, "learning_rate": 0.0003700028623222975, "loss": 1.7262, "step": 53015 }, { "epoch": 10.98, "learning_rate": 0.0003699074515790478, "loss": 1.7248, "step": 53020 }, { "epoch": 10.99, "learning_rate": 0.00036981204083579814, "loss": 1.7235, "step": 53025 }, { "epoch": 10.99, "learning_rate": 0.0003697166300925484, "loss": 1.7208, "step": 53030 }, { "epoch": 10.99, "learning_rate": 0.00036962121934929875, "loss": 1.725, "step": 53035 }, { "epoch": 10.99, "learning_rate": 0.0003695258086060491, "loss": 1.7305, "step": 53040 }, { "epoch": 10.99, "learning_rate": 0.00036943039786279937, "loss": 1.7288, "step": 53045 }, { "epoch": 10.99, "learning_rate": 0.00036933498711954965, "loss": 1.7275, "step": 53050 }, { "epoch": 10.99, "learning_rate": 0.0003692395763763, "loss": 1.7266, "step": 53055 }, { "epoch": 10.99, "learning_rate": 0.0003691441656330503, "loss": 1.7227, "step": 53060 }, { "epoch": 10.99, "learning_rate": 0.0003690487548898006, "loss": 1.7263, "step": 53065 }, { "epoch": 10.99, "learning_rate": 0.00036895334414655093, "loss": 1.7263, "step": 53070 }, { "epoch": 11.0, "learning_rate": 0.0003688579334033012, "loss": 1.7246, "step": 53075 }, { "epoch": 11.0, "learning_rate": 0.0003687625226600515, "loss": 1.7278, "step": 53080 }, { "epoch": 11.0, "learning_rate": 0.0003686671119168019, "loss": 1.7228, "step": 53085 }, { "epoch": 11.0, "learning_rate": 0.00036857170117355215, "loss": 1.7216, "step": 53090 }, { "epoch": 11.0, "learning_rate": 0.00036847629043030243, "loss": 1.729, "step": 53095 }, { "epoch": 11.0, "learning_rate": 0.00036838087968705277, "loss": 1.7177, "step": 53100 }, { "epoch": 11.0, "learning_rate": 0.0003682854689438031, "loss": 1.7189, "step": 53105 }, { "epoch": 11.0, "learning_rate": 0.0003681900582005534, "loss": 1.7201, "step": 53110 }, { "epoch": 11.0, "learning_rate": 0.0003680946474573037, "loss": 1.7188, "step": 53115 }, { "epoch": 11.0, "learning_rate": 0.000367999236714054, "loss": 1.7185, "step": 53120 }, { "epoch": 11.01, "learning_rate": 0.0003679038259708043, "loss": 1.7145, "step": 53125 }, { "epoch": 11.01, "learning_rate": 0.00036780841522755466, "loss": 1.7142, "step": 53130 }, { "epoch": 11.01, "learning_rate": 0.00036771300448430494, "loss": 1.7206, "step": 53135 }, { "epoch": 11.01, "learning_rate": 0.0003676175937410552, "loss": 1.7171, "step": 53140 }, { "epoch": 11.01, "learning_rate": 0.00036752218299780556, "loss": 1.7218, "step": 53145 }, { "epoch": 11.01, "learning_rate": 0.0003674267722545559, "loss": 1.7133, "step": 53150 }, { "epoch": 11.01, "learning_rate": 0.00036733136151130617, "loss": 1.7159, "step": 53155 }, { "epoch": 11.01, "learning_rate": 0.0003672359507680565, "loss": 1.7164, "step": 53160 }, { "epoch": 11.01, "learning_rate": 0.0003671405400248068, "loss": 1.7162, "step": 53165 }, { "epoch": 11.02, "learning_rate": 0.00036704512928155706, "loss": 1.7122, "step": 53170 }, { "epoch": 11.02, "learning_rate": 0.00036694971853830745, "loss": 1.7178, "step": 53175 }, { "epoch": 11.02, "learning_rate": 0.00036685430779505773, "loss": 1.7173, "step": 53180 }, { "epoch": 11.02, "learning_rate": 0.000366758897051808, "loss": 1.7167, "step": 53185 }, { "epoch": 11.02, "learning_rate": 0.00036666348630855835, "loss": 1.7135, "step": 53190 }, { "epoch": 11.02, "learning_rate": 0.0003665680755653086, "loss": 1.7176, "step": 53195 }, { "epoch": 11.02, "learning_rate": 0.000366472664822059, "loss": 1.7195, "step": 53200 }, { "epoch": 11.02, "learning_rate": 0.0003663772540788093, "loss": 1.7212, "step": 53205 }, { "epoch": 11.02, "learning_rate": 0.0003662818433355596, "loss": 1.7182, "step": 53210 }, { "epoch": 11.02, "learning_rate": 0.0003661864325923099, "loss": 1.7185, "step": 53215 }, { "epoch": 11.03, "learning_rate": 0.00036609102184906024, "loss": 1.7172, "step": 53220 }, { "epoch": 11.03, "learning_rate": 0.0003659956111058105, "loss": 1.7159, "step": 53225 }, { "epoch": 11.03, "learning_rate": 0.00036590020036256086, "loss": 1.7152, "step": 53230 }, { "epoch": 11.03, "learning_rate": 0.00036580478961931114, "loss": 1.7172, "step": 53235 }, { "epoch": 11.03, "learning_rate": 0.0003657093788760614, "loss": 1.7189, "step": 53240 }, { "epoch": 11.03, "learning_rate": 0.0003656139681328118, "loss": 1.7153, "step": 53245 }, { "epoch": 11.03, "learning_rate": 0.0003655185573895621, "loss": 1.7172, "step": 53250 }, { "epoch": 11.03, "learning_rate": 0.00036542314664631236, "loss": 1.7179, "step": 53255 }, { "epoch": 11.03, "learning_rate": 0.0003653277359030627, "loss": 1.7215, "step": 53260 }, { "epoch": 11.03, "learning_rate": 0.00036523232515981303, "loss": 1.7144, "step": 53265 }, { "epoch": 11.04, "learning_rate": 0.0003651369144165633, "loss": 1.715, "step": 53270 }, { "epoch": 11.04, "learning_rate": 0.00036504150367331365, "loss": 1.714, "step": 53275 }, { "epoch": 11.04, "learning_rate": 0.0003649460929300639, "loss": 1.7138, "step": 53280 }, { "epoch": 11.04, "learning_rate": 0.0003648506821868142, "loss": 1.719, "step": 53285 }, { "epoch": 11.04, "learning_rate": 0.0003647552714435646, "loss": 1.7198, "step": 53290 }, { "epoch": 11.04, "learning_rate": 0.00036465986070031487, "loss": 1.7187, "step": 53295 }, { "epoch": 11.04, "learning_rate": 0.00036456444995706515, "loss": 1.7159, "step": 53300 }, { "epoch": 11.04, "learning_rate": 0.0003644690392138155, "loss": 1.7222, "step": 53305 }, { "epoch": 11.04, "learning_rate": 0.00036437362847056577, "loss": 1.7169, "step": 53310 }, { "epoch": 11.05, "learning_rate": 0.0003642782177273161, "loss": 1.7173, "step": 53315 }, { "epoch": 11.05, "learning_rate": 0.00036418280698406643, "loss": 1.7125, "step": 53320 }, { "epoch": 11.05, "learning_rate": 0.0003640873962408167, "loss": 1.7227, "step": 53325 }, { "epoch": 11.05, "learning_rate": 0.000363991985497567, "loss": 1.7173, "step": 53330 }, { "epoch": 11.05, "learning_rate": 0.0003638965747543174, "loss": 1.7154, "step": 53335 }, { "epoch": 11.05, "learning_rate": 0.00036380116401106766, "loss": 1.7136, "step": 53340 }, { "epoch": 11.05, "learning_rate": 0.00036370575326781794, "loss": 1.7169, "step": 53345 }, { "epoch": 11.05, "learning_rate": 0.0003636103425245683, "loss": 1.719, "step": 53350 }, { "epoch": 11.05, "learning_rate": 0.00036351493178131856, "loss": 1.7175, "step": 53355 }, { "epoch": 11.05, "learning_rate": 0.0003634195210380689, "loss": 1.714, "step": 53360 }, { "epoch": 11.06, "learning_rate": 0.0003633241102948192, "loss": 1.7176, "step": 53365 }, { "epoch": 11.06, "learning_rate": 0.0003632286995515695, "loss": 1.7136, "step": 53370 }, { "epoch": 11.06, "learning_rate": 0.0003631332888083198, "loss": 1.7198, "step": 53375 }, { "epoch": 11.06, "learning_rate": 0.00036303787806507017, "loss": 1.7184, "step": 53380 }, { "epoch": 11.06, "learning_rate": 0.00036294246732182045, "loss": 1.7127, "step": 53385 }, { "epoch": 11.06, "learning_rate": 0.00036284705657857073, "loss": 1.7196, "step": 53390 }, { "epoch": 11.06, "learning_rate": 0.00036275164583532106, "loss": 1.7132, "step": 53395 }, { "epoch": 11.06, "learning_rate": 0.00036265623509207134, "loss": 1.7187, "step": 53400 }, { "epoch": 11.06, "learning_rate": 0.0003625608243488217, "loss": 1.7209, "step": 53405 }, { "epoch": 11.06, "learning_rate": 0.000362465413605572, "loss": 1.7186, "step": 53410 }, { "epoch": 11.07, "learning_rate": 0.0003623700028623223, "loss": 1.7179, "step": 53415 }, { "epoch": 11.07, "learning_rate": 0.00036227459211907257, "loss": 1.7149, "step": 53420 }, { "epoch": 11.07, "learning_rate": 0.00036217918137582296, "loss": 1.7177, "step": 53425 }, { "epoch": 11.07, "learning_rate": 0.00036208377063257324, "loss": 1.7221, "step": 53430 }, { "epoch": 11.07, "learning_rate": 0.0003619883598893236, "loss": 1.7174, "step": 53435 }, { "epoch": 11.07, "learning_rate": 0.00036189294914607385, "loss": 1.7143, "step": 53440 }, { "epoch": 11.07, "learning_rate": 0.00036179753840282413, "loss": 1.7189, "step": 53445 }, { "epoch": 11.07, "learning_rate": 0.0003617021276595745, "loss": 1.7223, "step": 53450 }, { "epoch": 11.07, "learning_rate": 0.0003616067169163248, "loss": 1.7176, "step": 53455 }, { "epoch": 11.08, "learning_rate": 0.0003615113061730751, "loss": 1.7178, "step": 53460 }, { "epoch": 11.08, "learning_rate": 0.0003614158954298254, "loss": 1.7197, "step": 53465 }, { "epoch": 11.08, "learning_rate": 0.0003613204846865757, "loss": 1.7182, "step": 53470 }, { "epoch": 11.08, "learning_rate": 0.00036122507394332603, "loss": 1.7194, "step": 53475 }, { "epoch": 11.08, "learning_rate": 0.00036112966320007636, "loss": 1.7152, "step": 53480 }, { "epoch": 11.08, "learning_rate": 0.00036103425245682664, "loss": 1.7166, "step": 53485 }, { "epoch": 11.08, "learning_rate": 0.0003609388417135769, "loss": 1.7173, "step": 53490 }, { "epoch": 11.08, "learning_rate": 0.0003608434309703273, "loss": 1.719, "step": 53495 }, { "epoch": 11.08, "learning_rate": 0.0003607480202270776, "loss": 1.7143, "step": 53500 }, { "epoch": 11.08, "learning_rate": 0.00036065260948382787, "loss": 1.7178, "step": 53505 }, { "epoch": 11.09, "learning_rate": 0.0003605571987405782, "loss": 1.7211, "step": 53510 }, { "epoch": 11.09, "learning_rate": 0.0003604617879973285, "loss": 1.7176, "step": 53515 }, { "epoch": 11.09, "learning_rate": 0.0003603663772540788, "loss": 1.716, "step": 53520 }, { "epoch": 11.09, "learning_rate": 0.00036027096651082915, "loss": 1.7226, "step": 53525 }, { "epoch": 11.09, "learning_rate": 0.00036017555576757943, "loss": 1.714, "step": 53530 }, { "epoch": 11.09, "learning_rate": 0.0003600801450243297, "loss": 1.7139, "step": 53535 }, { "epoch": 11.09, "learning_rate": 0.0003599847342810801, "loss": 1.7191, "step": 53540 }, { "epoch": 11.09, "learning_rate": 0.0003598893235378304, "loss": 1.7225, "step": 53545 }, { "epoch": 11.09, "learning_rate": 0.00035979391279458066, "loss": 1.715, "step": 53550 }, { "epoch": 11.09, "learning_rate": 0.000359698502051331, "loss": 1.7151, "step": 53555 }, { "epoch": 11.1, "learning_rate": 0.0003596030913080813, "loss": 1.7221, "step": 53560 }, { "epoch": 11.1, "learning_rate": 0.0003595076805648316, "loss": 1.7123, "step": 53565 }, { "epoch": 11.1, "learning_rate": 0.00035941226982158194, "loss": 1.7205, "step": 53570 }, { "epoch": 11.1, "learning_rate": 0.0003593168590783322, "loss": 1.7204, "step": 53575 }, { "epoch": 11.1, "learning_rate": 0.0003592214483350825, "loss": 1.7167, "step": 53580 }, { "epoch": 11.1, "learning_rate": 0.00035912603759183283, "loss": 1.718, "step": 53585 }, { "epoch": 11.1, "learning_rate": 0.00035903062684858317, "loss": 1.7159, "step": 53590 }, { "epoch": 11.1, "learning_rate": 0.00035893521610533345, "loss": 1.7178, "step": 53595 }, { "epoch": 11.1, "learning_rate": 0.0003588398053620838, "loss": 1.7144, "step": 53600 }, { "epoch": 11.11, "learning_rate": 0.00035874439461883406, "loss": 1.7223, "step": 53605 }, { "epoch": 11.11, "learning_rate": 0.0003586489838755844, "loss": 1.718, "step": 53610 }, { "epoch": 11.11, "learning_rate": 0.00035855357313233473, "loss": 1.7172, "step": 53615 }, { "epoch": 11.11, "learning_rate": 0.000358458162389085, "loss": 1.7146, "step": 53620 }, { "epoch": 11.11, "learning_rate": 0.0003583627516458353, "loss": 1.7151, "step": 53625 }, { "epoch": 11.11, "learning_rate": 0.0003582673409025856, "loss": 1.7146, "step": 53630 }, { "epoch": 11.11, "learning_rate": 0.00035817193015933596, "loss": 1.7151, "step": 53635 }, { "epoch": 11.11, "learning_rate": 0.0003580765194160863, "loss": 1.7174, "step": 53640 }, { "epoch": 11.11, "learning_rate": 0.00035798110867283657, "loss": 1.7159, "step": 53645 }, { "epoch": 11.11, "learning_rate": 0.00035788569792958685, "loss": 1.7186, "step": 53650 }, { "epoch": 11.12, "learning_rate": 0.00035779028718633724, "loss": 1.7203, "step": 53655 }, { "epoch": 11.12, "learning_rate": 0.0003576948764430875, "loss": 1.7173, "step": 53660 }, { "epoch": 11.12, "learning_rate": 0.0003575994656998378, "loss": 1.7195, "step": 53665 }, { "epoch": 11.12, "learning_rate": 0.00035750405495658813, "loss": 1.7167, "step": 53670 }, { "epoch": 11.12, "learning_rate": 0.0003574086442133384, "loss": 1.7173, "step": 53675 }, { "epoch": 11.12, "learning_rate": 0.00035731323347008875, "loss": 1.7195, "step": 53680 }, { "epoch": 11.12, "learning_rate": 0.0003572178227268391, "loss": 1.7204, "step": 53685 }, { "epoch": 11.12, "learning_rate": 0.00035712241198358936, "loss": 1.7174, "step": 53690 }, { "epoch": 11.12, "learning_rate": 0.00035702700124033964, "loss": 1.719, "step": 53695 }, { "epoch": 11.12, "learning_rate": 0.00035693159049709, "loss": 1.7171, "step": 53700 }, { "epoch": 11.13, "learning_rate": 0.0003568361797538403, "loss": 1.7174, "step": 53705 }, { "epoch": 11.13, "learning_rate": 0.0003567407690105906, "loss": 1.7235, "step": 53710 }, { "epoch": 11.13, "learning_rate": 0.0003566453582673409, "loss": 1.7177, "step": 53715 }, { "epoch": 11.13, "learning_rate": 0.0003565499475240912, "loss": 1.7153, "step": 53720 }, { "epoch": 11.13, "learning_rate": 0.00035645453678084154, "loss": 1.7216, "step": 53725 }, { "epoch": 11.13, "learning_rate": 0.00035635912603759187, "loss": 1.7227, "step": 53730 }, { "epoch": 11.13, "learning_rate": 0.00035626371529434215, "loss": 1.7137, "step": 53735 }, { "epoch": 11.13, "learning_rate": 0.00035616830455109243, "loss": 1.7188, "step": 53740 }, { "epoch": 11.13, "learning_rate": 0.00035607289380784276, "loss": 1.719, "step": 53745 }, { "epoch": 11.14, "learning_rate": 0.0003559774830645931, "loss": 1.7178, "step": 53750 }, { "epoch": 11.14, "learning_rate": 0.0003558820723213434, "loss": 1.7203, "step": 53755 }, { "epoch": 11.14, "learning_rate": 0.0003557866615780937, "loss": 1.7159, "step": 53760 }, { "epoch": 11.14, "learning_rate": 0.000355691250834844, "loss": 1.7184, "step": 53765 }, { "epoch": 11.14, "learning_rate": 0.0003555958400915943, "loss": 1.7195, "step": 53770 }, { "epoch": 11.14, "learning_rate": 0.00035550042934834466, "loss": 1.7172, "step": 53775 }, { "epoch": 11.14, "learning_rate": 0.00035540501860509494, "loss": 1.7143, "step": 53780 }, { "epoch": 11.14, "learning_rate": 0.0003553096078618452, "loss": 1.7204, "step": 53785 }, { "epoch": 11.14, "learning_rate": 0.00035521419711859555, "loss": 1.7179, "step": 53790 }, { "epoch": 11.14, "learning_rate": 0.0003551187863753459, "loss": 1.7192, "step": 53795 }, { "epoch": 11.15, "learning_rate": 0.00035502337563209617, "loss": 1.7166, "step": 53800 }, { "epoch": 11.15, "learning_rate": 0.0003549279648888465, "loss": 1.7221, "step": 53805 }, { "epoch": 11.15, "learning_rate": 0.0003548325541455968, "loss": 1.7174, "step": 53810 }, { "epoch": 11.15, "learning_rate": 0.00035473714340234706, "loss": 1.716, "step": 53815 }, { "epoch": 11.15, "learning_rate": 0.00035464173265909745, "loss": 1.7243, "step": 53820 }, { "epoch": 11.15, "learning_rate": 0.00035454632191584773, "loss": 1.7197, "step": 53825 }, { "epoch": 11.15, "learning_rate": 0.000354450911172598, "loss": 1.7182, "step": 53830 }, { "epoch": 11.15, "learning_rate": 0.00035435550042934834, "loss": 1.7154, "step": 53835 }, { "epoch": 11.15, "learning_rate": 0.0003542600896860987, "loss": 1.7144, "step": 53840 }, { "epoch": 11.15, "learning_rate": 0.000354164678942849, "loss": 1.718, "step": 53845 }, { "epoch": 11.16, "learning_rate": 0.0003540692681995993, "loss": 1.721, "step": 53850 }, { "epoch": 11.16, "learning_rate": 0.00035397385745634957, "loss": 1.7161, "step": 53855 }, { "epoch": 11.16, "learning_rate": 0.0003538784467130999, "loss": 1.7201, "step": 53860 }, { "epoch": 11.16, "learning_rate": 0.00035378303596985024, "loss": 1.719, "step": 53865 }, { "epoch": 11.16, "learning_rate": 0.0003536876252266005, "loss": 1.7146, "step": 53870 }, { "epoch": 11.16, "learning_rate": 0.00035359221448335085, "loss": 1.7161, "step": 53875 }, { "epoch": 11.16, "learning_rate": 0.00035349680374010113, "loss": 1.7219, "step": 53880 }, { "epoch": 11.16, "learning_rate": 0.00035340139299685147, "loss": 1.7164, "step": 53885 }, { "epoch": 11.16, "learning_rate": 0.0003533059822536018, "loss": 1.7168, "step": 53890 }, { "epoch": 11.17, "learning_rate": 0.0003532105715103521, "loss": 1.7178, "step": 53895 }, { "epoch": 11.17, "learning_rate": 0.00035311516076710236, "loss": 1.72, "step": 53900 }, { "epoch": 11.17, "learning_rate": 0.0003530197500238527, "loss": 1.7268, "step": 53905 }, { "epoch": 11.17, "learning_rate": 0.000352924339280603, "loss": 1.7201, "step": 53910 }, { "epoch": 11.17, "learning_rate": 0.0003528289285373533, "loss": 1.7165, "step": 53915 }, { "epoch": 11.17, "learning_rate": 0.00035273351779410364, "loss": 1.7213, "step": 53920 }, { "epoch": 11.17, "learning_rate": 0.0003526381070508539, "loss": 1.7211, "step": 53925 }, { "epoch": 11.17, "learning_rate": 0.0003525426963076042, "loss": 1.7171, "step": 53930 }, { "epoch": 11.17, "learning_rate": 0.0003524472855643546, "loss": 1.7221, "step": 53935 }, { "epoch": 11.17, "learning_rate": 0.00035235187482110487, "loss": 1.7182, "step": 53940 }, { "epoch": 11.18, "learning_rate": 0.00035225646407785515, "loss": 1.7186, "step": 53945 }, { "epoch": 11.18, "learning_rate": 0.0003521610533346055, "loss": 1.7169, "step": 53950 }, { "epoch": 11.18, "learning_rate": 0.0003520656425913558, "loss": 1.7203, "step": 53955 }, { "epoch": 11.18, "learning_rate": 0.0003519702318481061, "loss": 1.7193, "step": 53960 }, { "epoch": 11.18, "learning_rate": 0.00035187482110485643, "loss": 1.718, "step": 53965 }, { "epoch": 11.18, "learning_rate": 0.0003517794103616067, "loss": 1.7191, "step": 53970 }, { "epoch": 11.18, "learning_rate": 0.000351683999618357, "loss": 1.7219, "step": 53975 }, { "epoch": 11.18, "learning_rate": 0.0003515885888751074, "loss": 1.7203, "step": 53980 }, { "epoch": 11.18, "learning_rate": 0.00035149317813185766, "loss": 1.7162, "step": 53985 }, { "epoch": 11.19, "learning_rate": 0.00035139776738860794, "loss": 1.719, "step": 53990 }, { "epoch": 11.19, "learning_rate": 0.00035130235664535827, "loss": 1.7173, "step": 53995 }, { "epoch": 11.19, "learning_rate": 0.0003512069459021086, "loss": 1.719, "step": 54000 }, { "epoch": 11.19, "eval_accuracy": 0.5442875816993464, "eval_loss": 1.920386791229248, "eval_runtime": 0.6721, "eval_samples_per_second": 223.179, "eval_steps_per_second": 1.488, "step": 54000 }, { "epoch": 11.19, "learning_rate": 0.0003511115351588589, "loss": 1.7213, "step": 54005 }, { "epoch": 11.19, "learning_rate": 0.0003510161244156092, "loss": 1.7165, "step": 54010 }, { "epoch": 11.19, "learning_rate": 0.0003509207136723595, "loss": 1.7149, "step": 54015 }, { "epoch": 11.19, "learning_rate": 0.0003508253029291098, "loss": 1.7184, "step": 54020 }, { "epoch": 11.19, "learning_rate": 0.00035072989218586017, "loss": 1.7128, "step": 54025 }, { "epoch": 11.19, "learning_rate": 0.00035063448144261045, "loss": 1.7185, "step": 54030 }, { "epoch": 11.19, "learning_rate": 0.0003505390706993607, "loss": 1.7206, "step": 54035 }, { "epoch": 11.2, "learning_rate": 0.00035044365995611106, "loss": 1.7189, "step": 54040 }, { "epoch": 11.2, "learning_rate": 0.0003503482492128614, "loss": 1.7167, "step": 54045 }, { "epoch": 11.2, "learning_rate": 0.00035025283846961173, "loss": 1.7159, "step": 54050 }, { "epoch": 11.2, "learning_rate": 0.000350157427726362, "loss": 1.7187, "step": 54055 }, { "epoch": 11.2, "learning_rate": 0.0003500620169831123, "loss": 1.7182, "step": 54060 }, { "epoch": 11.2, "learning_rate": 0.0003499666062398626, "loss": 1.7158, "step": 54065 }, { "epoch": 11.2, "learning_rate": 0.00034987119549661296, "loss": 1.7177, "step": 54070 }, { "epoch": 11.2, "learning_rate": 0.00034977578475336324, "loss": 1.7196, "step": 54075 }, { "epoch": 11.2, "learning_rate": 0.00034968037401011357, "loss": 1.7226, "step": 54080 }, { "epoch": 11.2, "learning_rate": 0.00034958496326686385, "loss": 1.7227, "step": 54085 }, { "epoch": 11.21, "learning_rate": 0.00034948955252361413, "loss": 1.7192, "step": 54090 }, { "epoch": 11.21, "learning_rate": 0.0003493941417803645, "loss": 1.7192, "step": 54095 }, { "epoch": 11.21, "learning_rate": 0.0003492987310371148, "loss": 1.7148, "step": 54100 }, { "epoch": 11.21, "learning_rate": 0.0003492033202938651, "loss": 1.7165, "step": 54105 }, { "epoch": 11.21, "learning_rate": 0.0003491079095506154, "loss": 1.7178, "step": 54110 }, { "epoch": 11.21, "learning_rate": 0.00034901249880736574, "loss": 1.7193, "step": 54115 }, { "epoch": 11.21, "learning_rate": 0.000348917088064116, "loss": 1.7143, "step": 54120 }, { "epoch": 11.21, "learning_rate": 0.00034882167732086636, "loss": 1.722, "step": 54125 }, { "epoch": 11.21, "learning_rate": 0.00034872626657761664, "loss": 1.7189, "step": 54130 }, { "epoch": 11.22, "learning_rate": 0.0003486308558343669, "loss": 1.7186, "step": 54135 }, { "epoch": 11.22, "learning_rate": 0.0003485354450911173, "loss": 1.7193, "step": 54140 }, { "epoch": 11.22, "learning_rate": 0.0003484400343478676, "loss": 1.7183, "step": 54145 }, { "epoch": 11.22, "learning_rate": 0.00034834462360461787, "loss": 1.7193, "step": 54150 }, { "epoch": 11.22, "learning_rate": 0.0003482492128613682, "loss": 1.719, "step": 54155 }, { "epoch": 11.22, "learning_rate": 0.00034815380211811853, "loss": 1.7178, "step": 54160 }, { "epoch": 11.22, "learning_rate": 0.0003480583913748688, "loss": 1.7165, "step": 54165 }, { "epoch": 11.22, "learning_rate": 0.00034796298063161915, "loss": 1.7167, "step": 54170 }, { "epoch": 11.22, "learning_rate": 0.00034786756988836943, "loss": 1.7163, "step": 54175 }, { "epoch": 11.22, "learning_rate": 0.0003477721591451197, "loss": 1.7203, "step": 54180 }, { "epoch": 11.23, "learning_rate": 0.0003476767484018701, "loss": 1.7232, "step": 54185 }, { "epoch": 11.23, "learning_rate": 0.0003475813376586204, "loss": 1.722, "step": 54190 }, { "epoch": 11.23, "learning_rate": 0.00034748592691537065, "loss": 1.723, "step": 54195 }, { "epoch": 11.23, "learning_rate": 0.000347390516172121, "loss": 1.7161, "step": 54200 }, { "epoch": 11.23, "learning_rate": 0.00034729510542887127, "loss": 1.717, "step": 54205 }, { "epoch": 11.23, "learning_rate": 0.0003471996946856216, "loss": 1.717, "step": 54210 }, { "epoch": 11.23, "learning_rate": 0.00034710428394237194, "loss": 1.718, "step": 54215 }, { "epoch": 11.23, "learning_rate": 0.0003470088731991222, "loss": 1.7221, "step": 54220 }, { "epoch": 11.23, "learning_rate": 0.0003469134624558725, "loss": 1.72, "step": 54225 }, { "epoch": 11.23, "learning_rate": 0.0003468180517126229, "loss": 1.7188, "step": 54230 }, { "epoch": 11.24, "learning_rate": 0.00034672264096937316, "loss": 1.7139, "step": 54235 }, { "epoch": 11.24, "learning_rate": 0.00034662723022612344, "loss": 1.7127, "step": 54240 }, { "epoch": 11.24, "learning_rate": 0.0003465318194828738, "loss": 1.7243, "step": 54245 }, { "epoch": 11.24, "learning_rate": 0.00034643640873962406, "loss": 1.72, "step": 54250 }, { "epoch": 11.24, "learning_rate": 0.0003463409979963744, "loss": 1.7204, "step": 54255 }, { "epoch": 11.24, "learning_rate": 0.0003462455872531247, "loss": 1.7149, "step": 54260 }, { "epoch": 11.24, "learning_rate": 0.000346150176509875, "loss": 1.7236, "step": 54265 }, { "epoch": 11.24, "learning_rate": 0.00034605476576662534, "loss": 1.722, "step": 54270 }, { "epoch": 11.24, "learning_rate": 0.0003459593550233757, "loss": 1.7196, "step": 54275 }, { "epoch": 11.25, "learning_rate": 0.00034586394428012595, "loss": 1.7197, "step": 54280 }, { "epoch": 11.25, "learning_rate": 0.0003457685335368763, "loss": 1.7179, "step": 54285 }, { "epoch": 11.25, "learning_rate": 0.00034567312279362657, "loss": 1.7207, "step": 54290 }, { "epoch": 11.25, "learning_rate": 0.00034557771205037685, "loss": 1.7216, "step": 54295 }, { "epoch": 11.25, "learning_rate": 0.00034548230130712723, "loss": 1.7188, "step": 54300 }, { "epoch": 11.25, "learning_rate": 0.0003453868905638775, "loss": 1.7163, "step": 54305 }, { "epoch": 11.25, "learning_rate": 0.0003452914798206278, "loss": 1.7169, "step": 54310 }, { "epoch": 11.25, "learning_rate": 0.00034519606907737813, "loss": 1.7169, "step": 54315 }, { "epoch": 11.25, "learning_rate": 0.0003451006583341284, "loss": 1.7198, "step": 54320 }, { "epoch": 11.25, "learning_rate": 0.00034500524759087874, "loss": 1.718, "step": 54325 }, { "epoch": 11.26, "learning_rate": 0.0003449098368476291, "loss": 1.7213, "step": 54330 }, { "epoch": 11.26, "learning_rate": 0.00034481442610437936, "loss": 1.717, "step": 54335 }, { "epoch": 11.26, "learning_rate": 0.00034471901536112964, "loss": 1.7216, "step": 54340 }, { "epoch": 11.26, "learning_rate": 0.00034462360461788, "loss": 1.718, "step": 54345 }, { "epoch": 11.26, "learning_rate": 0.0003445281938746303, "loss": 1.7166, "step": 54350 }, { "epoch": 11.26, "learning_rate": 0.0003444327831313806, "loss": 1.7169, "step": 54355 }, { "epoch": 11.26, "learning_rate": 0.0003443373723881309, "loss": 1.723, "step": 54360 }, { "epoch": 11.26, "learning_rate": 0.0003442419616448812, "loss": 1.7173, "step": 54365 }, { "epoch": 11.26, "learning_rate": 0.00034414655090163153, "loss": 1.7216, "step": 54370 }, { "epoch": 11.26, "learning_rate": 0.00034405114015838187, "loss": 1.7194, "step": 54375 }, { "epoch": 11.27, "learning_rate": 0.00034395572941513215, "loss": 1.7173, "step": 54380 }, { "epoch": 11.27, "learning_rate": 0.0003438603186718824, "loss": 1.718, "step": 54385 }, { "epoch": 11.27, "learning_rate": 0.0003437649079286328, "loss": 1.7182, "step": 54390 }, { "epoch": 11.27, "learning_rate": 0.0003436694971853831, "loss": 1.7141, "step": 54395 }, { "epoch": 11.27, "learning_rate": 0.00034357408644213337, "loss": 1.723, "step": 54400 }, { "epoch": 11.27, "learning_rate": 0.0003434786756988837, "loss": 1.717, "step": 54405 }, { "epoch": 11.27, "learning_rate": 0.000343383264955634, "loss": 1.7161, "step": 54410 }, { "epoch": 11.27, "learning_rate": 0.0003432878542123843, "loss": 1.7199, "step": 54415 }, { "epoch": 11.27, "learning_rate": 0.00034319244346913465, "loss": 1.7226, "step": 54420 }, { "epoch": 11.28, "learning_rate": 0.00034309703272588493, "loss": 1.7154, "step": 54425 }, { "epoch": 11.28, "learning_rate": 0.0003430016219826352, "loss": 1.7219, "step": 54430 }, { "epoch": 11.28, "learning_rate": 0.00034290621123938555, "loss": 1.7171, "step": 54435 }, { "epoch": 11.28, "learning_rate": 0.0003428108004961359, "loss": 1.7273, "step": 54440 }, { "epoch": 11.28, "learning_rate": 0.00034271538975288616, "loss": 1.7187, "step": 54445 }, { "epoch": 11.28, "learning_rate": 0.0003426199790096365, "loss": 1.7162, "step": 54450 }, { "epoch": 11.28, "learning_rate": 0.0003425245682663868, "loss": 1.7184, "step": 54455 }, { "epoch": 11.28, "learning_rate": 0.0003424291575231371, "loss": 1.7221, "step": 54460 }, { "epoch": 11.28, "learning_rate": 0.00034233374677988744, "loss": 1.7213, "step": 54465 }, { "epoch": 11.28, "learning_rate": 0.0003422383360366377, "loss": 1.7179, "step": 54470 }, { "epoch": 11.29, "learning_rate": 0.000342142925293388, "loss": 1.7174, "step": 54475 }, { "epoch": 11.29, "learning_rate": 0.00034204751455013834, "loss": 1.7175, "step": 54480 }, { "epoch": 11.29, "learning_rate": 0.00034195210380688867, "loss": 1.7158, "step": 54485 }, { "epoch": 11.29, "learning_rate": 0.000341856693063639, "loss": 1.7218, "step": 54490 }, { "epoch": 11.29, "learning_rate": 0.0003417612823203893, "loss": 1.7191, "step": 54495 }, { "epoch": 11.29, "learning_rate": 0.00034166587157713956, "loss": 1.7153, "step": 54500 }, { "epoch": 11.29, "learning_rate": 0.00034157046083388995, "loss": 1.7198, "step": 54505 }, { "epoch": 11.29, "learning_rate": 0.00034147505009064023, "loss": 1.7162, "step": 54510 }, { "epoch": 11.29, "learning_rate": 0.0003413796393473905, "loss": 1.7167, "step": 54515 }, { "epoch": 11.29, "learning_rate": 0.00034128422860414085, "loss": 1.7179, "step": 54520 }, { "epoch": 11.3, "learning_rate": 0.0003411888178608911, "loss": 1.7135, "step": 54525 }, { "epoch": 11.3, "learning_rate": 0.00034109340711764146, "loss": 1.7214, "step": 54530 }, { "epoch": 11.3, "learning_rate": 0.0003409979963743918, "loss": 1.7127, "step": 54535 }, { "epoch": 11.3, "learning_rate": 0.0003409025856311421, "loss": 1.7214, "step": 54540 }, { "epoch": 11.3, "learning_rate": 0.00034080717488789235, "loss": 1.7222, "step": 54545 }, { "epoch": 11.3, "learning_rate": 0.0003407117641446427, "loss": 1.7176, "step": 54550 }, { "epoch": 11.3, "learning_rate": 0.000340616353401393, "loss": 1.7159, "step": 54555 }, { "epoch": 11.3, "learning_rate": 0.0003405209426581433, "loss": 1.7197, "step": 54560 }, { "epoch": 11.3, "learning_rate": 0.00034042553191489364, "loss": 1.7219, "step": 54565 }, { "epoch": 11.31, "learning_rate": 0.0003403301211716439, "loss": 1.7197, "step": 54570 }, { "epoch": 11.31, "learning_rate": 0.00034023471042839425, "loss": 1.7206, "step": 54575 }, { "epoch": 11.31, "learning_rate": 0.0003401392996851446, "loss": 1.7197, "step": 54580 }, { "epoch": 11.31, "learning_rate": 0.00034004388894189486, "loss": 1.7119, "step": 54585 }, { "epoch": 11.31, "learning_rate": 0.00033994847819864514, "loss": 1.7217, "step": 54590 }, { "epoch": 11.31, "learning_rate": 0.0003398530674553955, "loss": 1.7237, "step": 54595 }, { "epoch": 11.31, "learning_rate": 0.0003397576567121458, "loss": 1.7139, "step": 54600 }, { "epoch": 11.31, "learning_rate": 0.0003396622459688961, "loss": 1.721, "step": 54605 }, { "epoch": 11.31, "learning_rate": 0.0003395668352256464, "loss": 1.7147, "step": 54610 }, { "epoch": 11.31, "learning_rate": 0.0003394714244823967, "loss": 1.7167, "step": 54615 }, { "epoch": 11.32, "learning_rate": 0.00033937601373914704, "loss": 1.7207, "step": 54620 }, { "epoch": 11.32, "learning_rate": 0.00033928060299589737, "loss": 1.7179, "step": 54625 }, { "epoch": 11.32, "learning_rate": 0.00033918519225264765, "loss": 1.718, "step": 54630 }, { "epoch": 11.32, "learning_rate": 0.00033908978150939793, "loss": 1.7226, "step": 54635 }, { "epoch": 11.32, "learning_rate": 0.00033899437076614827, "loss": 1.72, "step": 54640 }, { "epoch": 11.32, "learning_rate": 0.0003388989600228986, "loss": 1.7186, "step": 54645 }, { "epoch": 11.32, "learning_rate": 0.0003388035492796489, "loss": 1.7177, "step": 54650 }, { "epoch": 11.32, "learning_rate": 0.0003387081385363992, "loss": 1.7134, "step": 54655 }, { "epoch": 11.32, "learning_rate": 0.0003386127277931495, "loss": 1.7171, "step": 54660 }, { "epoch": 11.32, "learning_rate": 0.00033851731704989983, "loss": 1.7249, "step": 54665 }, { "epoch": 11.33, "learning_rate": 0.00033842190630665016, "loss": 1.717, "step": 54670 }, { "epoch": 11.33, "learning_rate": 0.00033832649556340044, "loss": 1.7215, "step": 54675 }, { "epoch": 11.33, "learning_rate": 0.0003382310848201507, "loss": 1.7187, "step": 54680 }, { "epoch": 11.33, "learning_rate": 0.00033813567407690106, "loss": 1.7215, "step": 54685 }, { "epoch": 11.33, "learning_rate": 0.0003380402633336514, "loss": 1.7184, "step": 54690 }, { "epoch": 11.33, "learning_rate": 0.0003379448525904017, "loss": 1.717, "step": 54695 }, { "epoch": 11.33, "learning_rate": 0.000337849441847152, "loss": 1.7165, "step": 54700 }, { "epoch": 11.33, "learning_rate": 0.0003377540311039023, "loss": 1.7168, "step": 54705 }, { "epoch": 11.33, "learning_rate": 0.0003376586203606526, "loss": 1.7205, "step": 54710 }, { "epoch": 11.34, "learning_rate": 0.00033756320961740295, "loss": 1.7183, "step": 54715 }, { "epoch": 11.34, "learning_rate": 0.00033746779887415323, "loss": 1.7211, "step": 54720 }, { "epoch": 11.34, "learning_rate": 0.00033737238813090356, "loss": 1.719, "step": 54725 }, { "epoch": 11.34, "learning_rate": 0.00033727697738765384, "loss": 1.7167, "step": 54730 }, { "epoch": 11.34, "learning_rate": 0.0003371815666444042, "loss": 1.723, "step": 54735 }, { "epoch": 11.34, "learning_rate": 0.0003370861559011545, "loss": 1.7152, "step": 54740 }, { "epoch": 11.34, "learning_rate": 0.0003369907451579048, "loss": 1.7181, "step": 54745 }, { "epoch": 11.34, "learning_rate": 0.00033689533441465507, "loss": 1.7181, "step": 54750 }, { "epoch": 11.34, "learning_rate": 0.0003367999236714054, "loss": 1.7203, "step": 54755 }, { "epoch": 11.34, "learning_rate": 0.00033670451292815574, "loss": 1.7227, "step": 54760 }, { "epoch": 11.35, "learning_rate": 0.000336609102184906, "loss": 1.7201, "step": 54765 }, { "epoch": 11.35, "learning_rate": 0.00033651369144165635, "loss": 1.7199, "step": 54770 }, { "epoch": 11.35, "learning_rate": 0.00033641828069840663, "loss": 1.7179, "step": 54775 }, { "epoch": 11.35, "learning_rate": 0.00033632286995515697, "loss": 1.7142, "step": 54780 }, { "epoch": 11.35, "learning_rate": 0.0003362274592119073, "loss": 1.7184, "step": 54785 }, { "epoch": 11.35, "learning_rate": 0.0003361320484686576, "loss": 1.7218, "step": 54790 }, { "epoch": 11.35, "learning_rate": 0.00033603663772540786, "loss": 1.716, "step": 54795 }, { "epoch": 11.35, "learning_rate": 0.0003359412269821582, "loss": 1.7184, "step": 54800 }, { "epoch": 11.35, "learning_rate": 0.00033584581623890853, "loss": 1.7146, "step": 54805 }, { "epoch": 11.35, "learning_rate": 0.0003357504054956588, "loss": 1.7205, "step": 54810 }, { "epoch": 11.36, "learning_rate": 0.00033565499475240914, "loss": 1.7169, "step": 54815 }, { "epoch": 11.36, "learning_rate": 0.0003355595840091594, "loss": 1.7172, "step": 54820 }, { "epoch": 11.36, "learning_rate": 0.0003354641732659097, "loss": 1.7177, "step": 54825 }, { "epoch": 11.36, "learning_rate": 0.0003353687625226601, "loss": 1.716, "step": 54830 }, { "epoch": 11.36, "learning_rate": 0.00033527335177941037, "loss": 1.7185, "step": 54835 }, { "epoch": 11.36, "learning_rate": 0.00033517794103616065, "loss": 1.7214, "step": 54840 }, { "epoch": 11.36, "learning_rate": 0.000335082530292911, "loss": 1.7173, "step": 54845 }, { "epoch": 11.36, "learning_rate": 0.0003349871195496613, "loss": 1.7214, "step": 54850 }, { "epoch": 11.36, "learning_rate": 0.0003348917088064116, "loss": 1.7173, "step": 54855 }, { "epoch": 11.37, "learning_rate": 0.00033479629806316193, "loss": 1.719, "step": 54860 }, { "epoch": 11.37, "learning_rate": 0.0003347008873199122, "loss": 1.7211, "step": 54865 }, { "epoch": 11.37, "learning_rate": 0.0003346054765766625, "loss": 1.7204, "step": 54870 }, { "epoch": 11.37, "learning_rate": 0.0003345100658334129, "loss": 1.7199, "step": 54875 }, { "epoch": 11.37, "learning_rate": 0.00033441465509016316, "loss": 1.717, "step": 54880 }, { "epoch": 11.37, "learning_rate": 0.00033431924434691344, "loss": 1.7162, "step": 54885 }, { "epoch": 11.37, "learning_rate": 0.0003342238336036638, "loss": 1.7175, "step": 54890 }, { "epoch": 11.37, "learning_rate": 0.0003341284228604141, "loss": 1.721, "step": 54895 }, { "epoch": 11.37, "learning_rate": 0.00033403301211716444, "loss": 1.7177, "step": 54900 }, { "epoch": 11.37, "learning_rate": 0.0003339376013739147, "loss": 1.7194, "step": 54905 }, { "epoch": 11.38, "learning_rate": 0.000333842190630665, "loss": 1.7216, "step": 54910 }, { "epoch": 11.38, "learning_rate": 0.00033374677988741533, "loss": 1.7126, "step": 54915 }, { "epoch": 11.38, "learning_rate": 0.00033365136914416567, "loss": 1.7133, "step": 54920 }, { "epoch": 11.38, "learning_rate": 0.00033355595840091595, "loss": 1.7218, "step": 54925 }, { "epoch": 11.38, "learning_rate": 0.0003334605476576663, "loss": 1.7165, "step": 54930 }, { "epoch": 11.38, "learning_rate": 0.00033336513691441656, "loss": 1.719, "step": 54935 }, { "epoch": 11.38, "learning_rate": 0.00033326972617116684, "loss": 1.7165, "step": 54940 }, { "epoch": 11.38, "learning_rate": 0.00033317431542791723, "loss": 1.7216, "step": 54945 }, { "epoch": 11.38, "learning_rate": 0.0003330789046846675, "loss": 1.7264, "step": 54950 }, { "epoch": 11.38, "learning_rate": 0.0003329834939414178, "loss": 1.7163, "step": 54955 }, { "epoch": 11.39, "learning_rate": 0.0003328880831981681, "loss": 1.7189, "step": 54960 }, { "epoch": 11.39, "learning_rate": 0.00033279267245491846, "loss": 1.723, "step": 54965 }, { "epoch": 11.39, "learning_rate": 0.00033269726171166874, "loss": 1.7184, "step": 54970 }, { "epoch": 11.39, "learning_rate": 0.00033260185096841907, "loss": 1.7209, "step": 54975 }, { "epoch": 11.39, "learning_rate": 0.00033250644022516935, "loss": 1.7211, "step": 54980 }, { "epoch": 11.39, "learning_rate": 0.00033241102948191963, "loss": 1.7162, "step": 54985 }, { "epoch": 11.39, "learning_rate": 0.00033231561873867, "loss": 1.7161, "step": 54990 }, { "epoch": 11.39, "learning_rate": 0.0003322202079954203, "loss": 1.7174, "step": 54995 }, { "epoch": 11.39, "learning_rate": 0.0003321247972521706, "loss": 1.7201, "step": 55000 }, { "epoch": 11.4, "learning_rate": 0.0003320293865089209, "loss": 1.7208, "step": 55005 }, { "epoch": 11.4, "learning_rate": 0.00033193397576567125, "loss": 1.7189, "step": 55010 }, { "epoch": 11.4, "learning_rate": 0.0003318385650224215, "loss": 1.7151, "step": 55015 }, { "epoch": 11.4, "learning_rate": 0.00033174315427917186, "loss": 1.7217, "step": 55020 }, { "epoch": 11.4, "learning_rate": 0.00033164774353592214, "loss": 1.7178, "step": 55025 }, { "epoch": 11.4, "learning_rate": 0.0003315523327926724, "loss": 1.7191, "step": 55030 }, { "epoch": 11.4, "learning_rate": 0.0003314569220494228, "loss": 1.7244, "step": 55035 }, { "epoch": 11.4, "learning_rate": 0.0003313615113061731, "loss": 1.7157, "step": 55040 }, { "epoch": 11.4, "learning_rate": 0.00033126610056292337, "loss": 1.7208, "step": 55045 }, { "epoch": 11.4, "learning_rate": 0.0003311706898196737, "loss": 1.719, "step": 55050 }, { "epoch": 11.41, "learning_rate": 0.000331075279076424, "loss": 1.7215, "step": 55055 }, { "epoch": 11.41, "learning_rate": 0.0003309798683331743, "loss": 1.719, "step": 55060 }, { "epoch": 11.41, "learning_rate": 0.00033088445758992465, "loss": 1.7186, "step": 55065 }, { "epoch": 11.41, "learning_rate": 0.00033078904684667493, "loss": 1.7238, "step": 55070 }, { "epoch": 11.41, "learning_rate": 0.0003306936361034252, "loss": 1.7212, "step": 55075 }, { "epoch": 11.41, "learning_rate": 0.0003305982253601756, "loss": 1.7194, "step": 55080 }, { "epoch": 11.41, "learning_rate": 0.0003305028146169259, "loss": 1.7211, "step": 55085 }, { "epoch": 11.41, "learning_rate": 0.00033040740387367616, "loss": 1.7234, "step": 55090 }, { "epoch": 11.41, "learning_rate": 0.0003303119931304265, "loss": 1.7183, "step": 55095 }, { "epoch": 11.41, "learning_rate": 0.00033021658238717677, "loss": 1.7203, "step": 55100 }, { "epoch": 11.42, "learning_rate": 0.0003301211716439271, "loss": 1.727, "step": 55105 }, { "epoch": 11.42, "learning_rate": 0.00033002576090067744, "loss": 1.715, "step": 55110 }, { "epoch": 11.42, "learning_rate": 0.0003299303501574277, "loss": 1.7192, "step": 55115 }, { "epoch": 11.42, "learning_rate": 0.00032983493941417805, "loss": 1.7201, "step": 55120 }, { "epoch": 11.42, "learning_rate": 0.0003297395286709284, "loss": 1.721, "step": 55125 }, { "epoch": 11.42, "learning_rate": 0.00032964411792767867, "loss": 1.717, "step": 55130 }, { "epoch": 11.42, "learning_rate": 0.000329548707184429, "loss": 1.7223, "step": 55135 }, { "epoch": 11.42, "learning_rate": 0.0003294532964411793, "loss": 1.7217, "step": 55140 }, { "epoch": 11.42, "learning_rate": 0.00032935788569792956, "loss": 1.7155, "step": 55145 }, { "epoch": 11.43, "learning_rate": 0.00032926247495467995, "loss": 1.7143, "step": 55150 }, { "epoch": 11.43, "learning_rate": 0.00032916706421143023, "loss": 1.7211, "step": 55155 }, { "epoch": 11.43, "learning_rate": 0.0003290716534681805, "loss": 1.7185, "step": 55160 }, { "epoch": 11.43, "learning_rate": 0.00032897624272493084, "loss": 1.723, "step": 55165 }, { "epoch": 11.43, "learning_rate": 0.0003288808319816811, "loss": 1.7153, "step": 55170 }, { "epoch": 11.43, "learning_rate": 0.00032878542123843146, "loss": 1.7181, "step": 55175 }, { "epoch": 11.43, "learning_rate": 0.0003286900104951818, "loss": 1.7224, "step": 55180 }, { "epoch": 11.43, "learning_rate": 0.00032859459975193207, "loss": 1.717, "step": 55185 }, { "epoch": 11.43, "learning_rate": 0.00032849918900868235, "loss": 1.7177, "step": 55190 }, { "epoch": 11.43, "learning_rate": 0.00032840377826543274, "loss": 1.7187, "step": 55195 }, { "epoch": 11.44, "learning_rate": 0.000328308367522183, "loss": 1.7164, "step": 55200 }, { "epoch": 11.44, "learning_rate": 0.0003282129567789333, "loss": 1.718, "step": 55205 }, { "epoch": 11.44, "learning_rate": 0.00032811754603568363, "loss": 1.7237, "step": 55210 }, { "epoch": 11.44, "learning_rate": 0.0003280221352924339, "loss": 1.717, "step": 55215 }, { "epoch": 11.44, "learning_rate": 0.00032792672454918424, "loss": 1.7242, "step": 55220 }, { "epoch": 11.44, "learning_rate": 0.0003278313138059346, "loss": 1.7212, "step": 55225 }, { "epoch": 11.44, "learning_rate": 0.00032773590306268486, "loss": 1.7208, "step": 55230 }, { "epoch": 11.44, "learning_rate": 0.00032764049231943514, "loss": 1.7255, "step": 55235 }, { "epoch": 11.44, "learning_rate": 0.0003275450815761855, "loss": 1.7245, "step": 55240 }, { "epoch": 11.44, "learning_rate": 0.0003274496708329358, "loss": 1.7215, "step": 55245 }, { "epoch": 11.45, "learning_rate": 0.0003273542600896861, "loss": 1.7189, "step": 55250 }, { "epoch": 11.45, "learning_rate": 0.0003272588493464364, "loss": 1.7206, "step": 55255 }, { "epoch": 11.45, "learning_rate": 0.0003271634386031867, "loss": 1.7184, "step": 55260 }, { "epoch": 11.45, "learning_rate": 0.00032706802785993703, "loss": 1.7208, "step": 55265 }, { "epoch": 11.45, "learning_rate": 0.00032697261711668737, "loss": 1.719, "step": 55270 }, { "epoch": 11.45, "learning_rate": 0.00032687720637343765, "loss": 1.7192, "step": 55275 }, { "epoch": 11.45, "learning_rate": 0.00032678179563018793, "loss": 1.723, "step": 55280 }, { "epoch": 11.45, "learning_rate": 0.0003266863848869383, "loss": 1.7215, "step": 55285 }, { "epoch": 11.45, "learning_rate": 0.0003265909741436886, "loss": 1.7184, "step": 55290 }, { "epoch": 11.46, "learning_rate": 0.0003264955634004389, "loss": 1.7181, "step": 55295 }, { "epoch": 11.46, "learning_rate": 0.0003264001526571892, "loss": 1.7179, "step": 55300 }, { "epoch": 11.46, "learning_rate": 0.0003263047419139395, "loss": 1.7196, "step": 55305 }, { "epoch": 11.46, "learning_rate": 0.0003262093311706898, "loss": 1.7169, "step": 55310 }, { "epoch": 11.46, "learning_rate": 0.00032611392042744016, "loss": 1.7179, "step": 55315 }, { "epoch": 11.46, "learning_rate": 0.00032601850968419044, "loss": 1.7258, "step": 55320 }, { "epoch": 11.46, "learning_rate": 0.0003259230989409407, "loss": 1.7192, "step": 55325 }, { "epoch": 11.46, "learning_rate": 0.00032582768819769105, "loss": 1.7169, "step": 55330 }, { "epoch": 11.46, "learning_rate": 0.0003257322774544414, "loss": 1.7201, "step": 55335 }, { "epoch": 11.46, "learning_rate": 0.0003256368667111917, "loss": 1.7163, "step": 55340 }, { "epoch": 11.47, "learning_rate": 0.000325541455967942, "loss": 1.7218, "step": 55345 }, { "epoch": 11.47, "learning_rate": 0.0003254460452246923, "loss": 1.7272, "step": 55350 }, { "epoch": 11.47, "learning_rate": 0.00032535063448144267, "loss": 1.7218, "step": 55355 }, { "epoch": 11.47, "learning_rate": 0.00032525522373819295, "loss": 1.7166, "step": 55360 }, { "epoch": 11.47, "learning_rate": 0.0003251598129949432, "loss": 1.7185, "step": 55365 }, { "epoch": 11.47, "learning_rate": 0.00032506440225169356, "loss": 1.7147, "step": 55370 }, { "epoch": 11.47, "learning_rate": 0.00032496899150844384, "loss": 1.7222, "step": 55375 }, { "epoch": 11.47, "learning_rate": 0.0003248735807651942, "loss": 1.7239, "step": 55380 }, { "epoch": 11.47, "learning_rate": 0.0003247781700219445, "loss": 1.7183, "step": 55385 }, { "epoch": 11.48, "learning_rate": 0.0003246827592786948, "loss": 1.7184, "step": 55390 }, { "epoch": 11.48, "learning_rate": 0.00032458734853544507, "loss": 1.7211, "step": 55395 }, { "epoch": 11.48, "learning_rate": 0.00032449193779219546, "loss": 1.723, "step": 55400 }, { "epoch": 11.48, "learning_rate": 0.00032439652704894574, "loss": 1.7199, "step": 55405 }, { "epoch": 11.48, "learning_rate": 0.000324301116305696, "loss": 1.7209, "step": 55410 }, { "epoch": 11.48, "learning_rate": 0.00032420570556244635, "loss": 1.7197, "step": 55415 }, { "epoch": 11.48, "learning_rate": 0.00032411029481919663, "loss": 1.7208, "step": 55420 }, { "epoch": 11.48, "learning_rate": 0.00032401488407594696, "loss": 1.721, "step": 55425 }, { "epoch": 11.48, "learning_rate": 0.0003239194733326973, "loss": 1.7173, "step": 55430 }, { "epoch": 11.48, "learning_rate": 0.0003238240625894476, "loss": 1.7201, "step": 55435 }, { "epoch": 11.49, "learning_rate": 0.00032372865184619786, "loss": 1.7221, "step": 55440 }, { "epoch": 11.49, "learning_rate": 0.0003236332411029482, "loss": 1.7225, "step": 55445 }, { "epoch": 11.49, "learning_rate": 0.0003235378303596985, "loss": 1.7192, "step": 55450 }, { "epoch": 11.49, "learning_rate": 0.0003234424196164488, "loss": 1.7144, "step": 55455 }, { "epoch": 11.49, "learning_rate": 0.00032334700887319914, "loss": 1.7168, "step": 55460 }, { "epoch": 11.49, "learning_rate": 0.0003232515981299494, "loss": 1.7173, "step": 55465 }, { "epoch": 11.49, "learning_rate": 0.00032315618738669975, "loss": 1.7162, "step": 55470 }, { "epoch": 11.49, "learning_rate": 0.0003230607766434501, "loss": 1.7192, "step": 55475 }, { "epoch": 11.49, "learning_rate": 0.00032296536590020037, "loss": 1.7178, "step": 55480 }, { "epoch": 11.49, "learning_rate": 0.00032286995515695065, "loss": 1.7174, "step": 55485 }, { "epoch": 11.5, "learning_rate": 0.000322774544413701, "loss": 1.7214, "step": 55490 }, { "epoch": 11.5, "learning_rate": 0.0003226791336704513, "loss": 1.7196, "step": 55495 }, { "epoch": 11.5, "learning_rate": 0.0003225837229272016, "loss": 1.7167, "step": 55500 }, { "epoch": 11.5, "learning_rate": 0.0003224883121839519, "loss": 1.7211, "step": 55505 }, { "epoch": 11.5, "learning_rate": 0.0003223929014407022, "loss": 1.7178, "step": 55510 }, { "epoch": 11.5, "learning_rate": 0.00032229749069745254, "loss": 1.7173, "step": 55515 }, { "epoch": 11.5, "learning_rate": 0.0003222020799542029, "loss": 1.7168, "step": 55520 }, { "epoch": 11.5, "learning_rate": 0.00032210666921095315, "loss": 1.7235, "step": 55525 }, { "epoch": 11.5, "learning_rate": 0.00032201125846770343, "loss": 1.7199, "step": 55530 }, { "epoch": 11.51, "learning_rate": 0.00032191584772445377, "loss": 1.7174, "step": 55535 }, { "epoch": 11.51, "learning_rate": 0.0003218204369812041, "loss": 1.7179, "step": 55540 }, { "epoch": 11.51, "learning_rate": 0.00032172502623795444, "loss": 1.7172, "step": 55545 }, { "epoch": 11.51, "learning_rate": 0.0003216296154947047, "loss": 1.7189, "step": 55550 }, { "epoch": 11.51, "learning_rate": 0.000321534204751455, "loss": 1.7174, "step": 55555 }, { "epoch": 11.51, "learning_rate": 0.00032143879400820533, "loss": 1.7185, "step": 55560 }, { "epoch": 11.51, "learning_rate": 0.00032134338326495566, "loss": 1.7217, "step": 55565 }, { "epoch": 11.51, "learning_rate": 0.00032124797252170594, "loss": 1.7197, "step": 55570 }, { "epoch": 11.51, "learning_rate": 0.0003211525617784563, "loss": 1.7211, "step": 55575 }, { "epoch": 11.51, "learning_rate": 0.00032105715103520656, "loss": 1.7182, "step": 55580 }, { "epoch": 11.52, "learning_rate": 0.0003209617402919569, "loss": 1.7181, "step": 55585 }, { "epoch": 11.52, "learning_rate": 0.0003208663295487072, "loss": 1.7175, "step": 55590 }, { "epoch": 11.52, "learning_rate": 0.0003207709188054575, "loss": 1.7206, "step": 55595 }, { "epoch": 11.52, "learning_rate": 0.0003206755080622078, "loss": 1.7146, "step": 55600 }, { "epoch": 11.52, "learning_rate": 0.0003205800973189581, "loss": 1.7205, "step": 55605 }, { "epoch": 11.52, "learning_rate": 0.00032048468657570845, "loss": 1.719, "step": 55610 }, { "epoch": 11.52, "learning_rate": 0.00032038927583245873, "loss": 1.7143, "step": 55615 }, { "epoch": 11.52, "learning_rate": 0.00032029386508920907, "loss": 1.7176, "step": 55620 }, { "epoch": 11.52, "learning_rate": 0.00032019845434595935, "loss": 1.7191, "step": 55625 }, { "epoch": 11.52, "learning_rate": 0.0003201030436027097, "loss": 1.7171, "step": 55630 }, { "epoch": 11.53, "learning_rate": 0.00032000763285946, "loss": 1.7229, "step": 55635 }, { "epoch": 11.53, "learning_rate": 0.0003199122221162103, "loss": 1.7175, "step": 55640 }, { "epoch": 11.53, "learning_rate": 0.0003198168113729606, "loss": 1.7199, "step": 55645 }, { "epoch": 11.53, "learning_rate": 0.0003197214006297109, "loss": 1.7194, "step": 55650 }, { "epoch": 11.53, "learning_rate": 0.00031962598988646124, "loss": 1.7202, "step": 55655 }, { "epoch": 11.53, "learning_rate": 0.0003195305791432115, "loss": 1.7223, "step": 55660 }, { "epoch": 11.53, "learning_rate": 0.00031943516839996186, "loss": 1.721, "step": 55665 }, { "epoch": 11.53, "learning_rate": 0.00031933975765671214, "loss": 1.7175, "step": 55670 }, { "epoch": 11.53, "learning_rate": 0.0003192443469134624, "loss": 1.722, "step": 55675 }, { "epoch": 11.54, "learning_rate": 0.0003191489361702128, "loss": 1.7191, "step": 55680 }, { "epoch": 11.54, "learning_rate": 0.0003190535254269631, "loss": 1.7194, "step": 55685 }, { "epoch": 11.54, "learning_rate": 0.00031895811468371336, "loss": 1.7162, "step": 55690 }, { "epoch": 11.54, "learning_rate": 0.0003188627039404637, "loss": 1.719, "step": 55695 }, { "epoch": 11.54, "learning_rate": 0.00031876729319721403, "loss": 1.7236, "step": 55700 }, { "epoch": 11.54, "learning_rate": 0.0003186718824539643, "loss": 1.7247, "step": 55705 }, { "epoch": 11.54, "learning_rate": 0.00031857647171071465, "loss": 1.7204, "step": 55710 }, { "epoch": 11.54, "learning_rate": 0.0003184810609674649, "loss": 1.7213, "step": 55715 }, { "epoch": 11.54, "learning_rate": 0.0003183856502242152, "loss": 1.7189, "step": 55720 }, { "epoch": 11.54, "learning_rate": 0.0003182902394809656, "loss": 1.7201, "step": 55725 }, { "epoch": 11.55, "learning_rate": 0.00031819482873771587, "loss": 1.714, "step": 55730 }, { "epoch": 11.55, "learning_rate": 0.00031809941799446615, "loss": 1.7169, "step": 55735 }, { "epoch": 11.55, "learning_rate": 0.0003180040072512165, "loss": 1.7174, "step": 55740 }, { "epoch": 11.55, "learning_rate": 0.0003179085965079668, "loss": 1.7172, "step": 55745 }, { "epoch": 11.55, "learning_rate": 0.00031781318576471715, "loss": 1.7116, "step": 55750 }, { "epoch": 11.55, "learning_rate": 0.00031771777502146743, "loss": 1.7189, "step": 55755 }, { "epoch": 11.55, "learning_rate": 0.0003176223642782177, "loss": 1.7166, "step": 55760 }, { "epoch": 11.55, "learning_rate": 0.00031752695353496805, "loss": 1.7181, "step": 55765 }, { "epoch": 11.55, "learning_rate": 0.0003174315427917184, "loss": 1.7158, "step": 55770 }, { "epoch": 11.55, "learning_rate": 0.00031733613204846866, "loss": 1.7161, "step": 55775 }, { "epoch": 11.56, "learning_rate": 0.000317240721305219, "loss": 1.7197, "step": 55780 }, { "epoch": 11.56, "learning_rate": 0.0003171453105619693, "loss": 1.7218, "step": 55785 }, { "epoch": 11.56, "learning_rate": 0.00031704989981871956, "loss": 1.7189, "step": 55790 }, { "epoch": 11.56, "learning_rate": 0.00031695448907546994, "loss": 1.7204, "step": 55795 }, { "epoch": 11.56, "learning_rate": 0.0003168590783322202, "loss": 1.7199, "step": 55800 }, { "epoch": 11.56, "learning_rate": 0.0003167636675889705, "loss": 1.7221, "step": 55805 }, { "epoch": 11.56, "learning_rate": 0.00031666825684572084, "loss": 1.706, "step": 55810 }, { "epoch": 11.56, "learning_rate": 0.00031657284610247117, "loss": 1.7202, "step": 55815 }, { "epoch": 11.56, "learning_rate": 0.00031647743535922145, "loss": 1.7166, "step": 55820 }, { "epoch": 11.57, "learning_rate": 0.0003163820246159718, "loss": 1.7223, "step": 55825 }, { "epoch": 11.57, "learning_rate": 0.00031628661387272206, "loss": 1.7171, "step": 55830 }, { "epoch": 11.57, "learning_rate": 0.00031619120312947234, "loss": 1.7187, "step": 55835 }, { "epoch": 11.57, "learning_rate": 0.00031609579238622273, "loss": 1.7169, "step": 55840 }, { "epoch": 11.57, "learning_rate": 0.000316000381642973, "loss": 1.712, "step": 55845 }, { "epoch": 11.57, "learning_rate": 0.0003159049708997233, "loss": 1.7226, "step": 55850 }, { "epoch": 11.57, "learning_rate": 0.0003158095601564736, "loss": 1.7147, "step": 55855 }, { "epoch": 11.57, "learning_rate": 0.00031571414941322396, "loss": 1.7177, "step": 55860 }, { "epoch": 11.57, "learning_rate": 0.00031561873866997424, "loss": 1.7169, "step": 55865 }, { "epoch": 11.57, "learning_rate": 0.0003155233279267246, "loss": 1.7156, "step": 55870 }, { "epoch": 11.58, "learning_rate": 0.00031542791718347485, "loss": 1.7175, "step": 55875 }, { "epoch": 11.58, "learning_rate": 0.00031533250644022513, "loss": 1.7173, "step": 55880 }, { "epoch": 11.58, "learning_rate": 0.0003152370956969755, "loss": 1.7153, "step": 55885 }, { "epoch": 11.58, "learning_rate": 0.0003151416849537258, "loss": 1.7161, "step": 55890 }, { "epoch": 11.58, "learning_rate": 0.0003150462742104761, "loss": 1.7174, "step": 55895 }, { "epoch": 11.58, "learning_rate": 0.0003149508634672264, "loss": 1.7147, "step": 55900 }, { "epoch": 11.58, "learning_rate": 0.0003148554527239767, "loss": 1.7162, "step": 55905 }, { "epoch": 11.58, "learning_rate": 0.00031476004198072703, "loss": 1.7204, "step": 55910 }, { "epoch": 11.58, "learning_rate": 0.00031466463123747736, "loss": 1.7162, "step": 55915 }, { "epoch": 11.58, "learning_rate": 0.00031456922049422764, "loss": 1.7175, "step": 55920 }, { "epoch": 11.59, "learning_rate": 0.0003144738097509779, "loss": 1.7181, "step": 55925 }, { "epoch": 11.59, "learning_rate": 0.0003143783990077283, "loss": 1.7188, "step": 55930 }, { "epoch": 11.59, "learning_rate": 0.0003142829882644786, "loss": 1.7205, "step": 55935 }, { "epoch": 11.59, "learning_rate": 0.00031418757752122887, "loss": 1.7195, "step": 55940 }, { "epoch": 11.59, "learning_rate": 0.0003140921667779792, "loss": 1.7208, "step": 55945 }, { "epoch": 11.59, "learning_rate": 0.0003139967560347295, "loss": 1.7205, "step": 55950 }, { "epoch": 11.59, "learning_rate": 0.0003139013452914798, "loss": 1.7219, "step": 55955 }, { "epoch": 11.59, "learning_rate": 0.00031380593454823015, "loss": 1.7182, "step": 55960 }, { "epoch": 11.59, "learning_rate": 0.00031371052380498043, "loss": 1.7213, "step": 55965 }, { "epoch": 11.6, "learning_rate": 0.00031361511306173077, "loss": 1.7239, "step": 55970 }, { "epoch": 11.6, "learning_rate": 0.0003135197023184811, "loss": 1.7186, "step": 55975 }, { "epoch": 11.6, "learning_rate": 0.0003134242915752314, "loss": 1.7198, "step": 55980 }, { "epoch": 11.6, "learning_rate": 0.0003133288808319817, "loss": 1.7198, "step": 55985 }, { "epoch": 11.6, "learning_rate": 0.000313233470088732, "loss": 1.7164, "step": 55990 }, { "epoch": 11.6, "learning_rate": 0.0003131380593454823, "loss": 1.7241, "step": 55995 }, { "epoch": 11.6, "learning_rate": 0.00031304264860223266, "loss": 1.7173, "step": 56000 }, { "epoch": 11.6, "learning_rate": 0.00031294723785898294, "loss": 1.7185, "step": 56005 }, { "epoch": 11.6, "learning_rate": 0.0003128518271157332, "loss": 1.7195, "step": 56010 }, { "epoch": 11.6, "learning_rate": 0.00031275641637248356, "loss": 1.7221, "step": 56015 }, { "epoch": 11.61, "learning_rate": 0.0003126610056292339, "loss": 1.7161, "step": 56020 }, { "epoch": 11.61, "learning_rate": 0.00031256559488598417, "loss": 1.7145, "step": 56025 }, { "epoch": 11.61, "learning_rate": 0.0003124701841427345, "loss": 1.7179, "step": 56030 }, { "epoch": 11.61, "learning_rate": 0.0003123747733994848, "loss": 1.7106, "step": 56035 }, { "epoch": 11.61, "learning_rate": 0.00031227936265623506, "loss": 1.7195, "step": 56040 }, { "epoch": 11.61, "learning_rate": 0.00031218395191298545, "loss": 1.718, "step": 56045 }, { "epoch": 11.61, "learning_rate": 0.00031208854116973573, "loss": 1.7174, "step": 56050 }, { "epoch": 11.61, "learning_rate": 0.000311993130426486, "loss": 1.7173, "step": 56055 }, { "epoch": 11.61, "learning_rate": 0.00031189771968323634, "loss": 1.7175, "step": 56060 }, { "epoch": 11.61, "learning_rate": 0.0003118023089399866, "loss": 1.718, "step": 56065 }, { "epoch": 11.62, "learning_rate": 0.00031170689819673696, "loss": 1.7221, "step": 56070 }, { "epoch": 11.62, "learning_rate": 0.0003116114874534873, "loss": 1.719, "step": 56075 }, { "epoch": 11.62, "learning_rate": 0.00031151607671023757, "loss": 1.7159, "step": 56080 }, { "epoch": 11.62, "learning_rate": 0.00031142066596698785, "loss": 1.7206, "step": 56085 }, { "epoch": 11.62, "learning_rate": 0.00031132525522373824, "loss": 1.7153, "step": 56090 }, { "epoch": 11.62, "learning_rate": 0.0003112298444804885, "loss": 1.7157, "step": 56095 }, { "epoch": 11.62, "learning_rate": 0.0003111344337372388, "loss": 1.7155, "step": 56100 }, { "epoch": 11.62, "learning_rate": 0.00031103902299398913, "loss": 1.7167, "step": 56105 }, { "epoch": 11.62, "learning_rate": 0.0003109436122507394, "loss": 1.7163, "step": 56110 }, { "epoch": 11.63, "learning_rate": 0.00031084820150748975, "loss": 1.7227, "step": 56115 }, { "epoch": 11.63, "learning_rate": 0.0003107527907642401, "loss": 1.7117, "step": 56120 }, { "epoch": 11.63, "learning_rate": 0.00031065738002099036, "loss": 1.7167, "step": 56125 }, { "epoch": 11.63, "learning_rate": 0.00031056196927774064, "loss": 1.7162, "step": 56130 }, { "epoch": 11.63, "learning_rate": 0.00031046655853449103, "loss": 1.7219, "step": 56135 }, { "epoch": 11.63, "learning_rate": 0.0003103711477912413, "loss": 1.714, "step": 56140 }, { "epoch": 11.63, "learning_rate": 0.0003102757370479916, "loss": 1.7158, "step": 56145 }, { "epoch": 11.63, "learning_rate": 0.0003101803263047419, "loss": 1.7215, "step": 56150 }, { "epoch": 11.63, "learning_rate": 0.0003100849155614922, "loss": 1.7195, "step": 56155 }, { "epoch": 11.63, "learning_rate": 0.00030998950481824254, "loss": 1.7213, "step": 56160 }, { "epoch": 11.64, "learning_rate": 0.00030989409407499287, "loss": 1.7193, "step": 56165 }, { "epoch": 11.64, "learning_rate": 0.00030979868333174315, "loss": 1.7187, "step": 56170 }, { "epoch": 11.64, "learning_rate": 0.00030970327258849343, "loss": 1.717, "step": 56175 }, { "epoch": 11.64, "learning_rate": 0.00030960786184524376, "loss": 1.7159, "step": 56180 }, { "epoch": 11.64, "learning_rate": 0.0003095124511019941, "loss": 1.7194, "step": 56185 }, { "epoch": 11.64, "learning_rate": 0.00030941704035874443, "loss": 1.7208, "step": 56190 }, { "epoch": 11.64, "learning_rate": 0.0003093216296154947, "loss": 1.7184, "step": 56195 }, { "epoch": 11.64, "learning_rate": 0.000309226218872245, "loss": 1.7189, "step": 56200 }, { "epoch": 11.64, "learning_rate": 0.0003091308081289954, "loss": 1.721, "step": 56205 }, { "epoch": 11.64, "learning_rate": 0.00030903539738574566, "loss": 1.7152, "step": 56210 }, { "epoch": 11.65, "learning_rate": 0.00030893998664249594, "loss": 1.7194, "step": 56215 }, { "epoch": 11.65, "learning_rate": 0.0003088445758992463, "loss": 1.7163, "step": 56220 }, { "epoch": 11.65, "learning_rate": 0.00030874916515599655, "loss": 1.717, "step": 56225 }, { "epoch": 11.65, "learning_rate": 0.0003086537544127469, "loss": 1.7272, "step": 56230 }, { "epoch": 11.65, "learning_rate": 0.0003085583436694972, "loss": 1.7183, "step": 56235 }, { "epoch": 11.65, "learning_rate": 0.0003084629329262475, "loss": 1.717, "step": 56240 }, { "epoch": 11.65, "learning_rate": 0.0003083675221829978, "loss": 1.7146, "step": 56245 }, { "epoch": 11.65, "learning_rate": 0.00030827211143974817, "loss": 1.7166, "step": 56250 }, { "epoch": 11.65, "learning_rate": 0.00030817670069649845, "loss": 1.7149, "step": 56255 }, { "epoch": 11.66, "learning_rate": 0.00030808128995324873, "loss": 1.7152, "step": 56260 }, { "epoch": 11.66, "learning_rate": 0.00030798587920999906, "loss": 1.7173, "step": 56265 }, { "epoch": 11.66, "learning_rate": 0.00030789046846674934, "loss": 1.7162, "step": 56270 }, { "epoch": 11.66, "learning_rate": 0.0003077950577234997, "loss": 1.715, "step": 56275 }, { "epoch": 11.66, "learning_rate": 0.00030769964698025, "loss": 1.7219, "step": 56280 }, { "epoch": 11.66, "learning_rate": 0.0003076042362370003, "loss": 1.7207, "step": 56285 }, { "epoch": 11.66, "learning_rate": 0.00030750882549375057, "loss": 1.7187, "step": 56290 }, { "epoch": 11.66, "learning_rate": 0.0003074134147505009, "loss": 1.7185, "step": 56295 }, { "epoch": 11.66, "learning_rate": 0.00030731800400725124, "loss": 1.7176, "step": 56300 }, { "epoch": 11.66, "learning_rate": 0.0003072225932640015, "loss": 1.724, "step": 56305 }, { "epoch": 11.67, "learning_rate": 0.00030712718252075185, "loss": 1.717, "step": 56310 }, { "epoch": 11.67, "learning_rate": 0.00030703177177750213, "loss": 1.7187, "step": 56315 }, { "epoch": 11.67, "learning_rate": 0.00030693636103425247, "loss": 1.7219, "step": 56320 }, { "epoch": 11.67, "learning_rate": 0.0003068409502910028, "loss": 1.7201, "step": 56325 }, { "epoch": 11.67, "learning_rate": 0.0003067455395477531, "loss": 1.7144, "step": 56330 }, { "epoch": 11.67, "learning_rate": 0.00030665012880450336, "loss": 1.7214, "step": 56335 }, { "epoch": 11.67, "learning_rate": 0.0003065547180612537, "loss": 1.7193, "step": 56340 }, { "epoch": 11.67, "learning_rate": 0.000306459307318004, "loss": 1.7143, "step": 56345 }, { "epoch": 11.67, "learning_rate": 0.0003063638965747543, "loss": 1.7192, "step": 56350 }, { "epoch": 11.67, "learning_rate": 0.00030626848583150464, "loss": 1.7124, "step": 56355 }, { "epoch": 11.68, "learning_rate": 0.0003061730750882549, "loss": 1.7162, "step": 56360 }, { "epoch": 11.68, "learning_rate": 0.00030607766434500525, "loss": 1.7166, "step": 56365 }, { "epoch": 11.68, "learning_rate": 0.0003059822536017556, "loss": 1.7171, "step": 56370 }, { "epoch": 11.68, "learning_rate": 0.00030588684285850587, "loss": 1.7213, "step": 56375 }, { "epoch": 11.68, "learning_rate": 0.00030579143211525615, "loss": 1.7194, "step": 56380 }, { "epoch": 11.68, "learning_rate": 0.0003056960213720065, "loss": 1.721, "step": 56385 }, { "epoch": 11.68, "learning_rate": 0.0003056006106287568, "loss": 1.7205, "step": 56390 }, { "epoch": 11.68, "learning_rate": 0.00030550519988550715, "loss": 1.7197, "step": 56395 }, { "epoch": 11.68, "learning_rate": 0.00030540978914225743, "loss": 1.7225, "step": 56400 }, { "epoch": 11.69, "learning_rate": 0.0003053143783990077, "loss": 1.7213, "step": 56405 }, { "epoch": 11.69, "learning_rate": 0.00030521896765575804, "loss": 1.7187, "step": 56410 }, { "epoch": 11.69, "learning_rate": 0.0003051235569125084, "loss": 1.7184, "step": 56415 }, { "epoch": 11.69, "learning_rate": 0.00030502814616925866, "loss": 1.7205, "step": 56420 }, { "epoch": 11.69, "learning_rate": 0.000304932735426009, "loss": 1.7203, "step": 56425 }, { "epoch": 11.69, "learning_rate": 0.00030483732468275927, "loss": 1.7118, "step": 56430 }, { "epoch": 11.69, "learning_rate": 0.0003047419139395096, "loss": 1.7141, "step": 56435 }, { "epoch": 11.69, "learning_rate": 0.00030464650319625994, "loss": 1.7167, "step": 56440 }, { "epoch": 11.69, "learning_rate": 0.0003045510924530102, "loss": 1.7169, "step": 56445 }, { "epoch": 11.69, "learning_rate": 0.0003044556817097605, "loss": 1.7214, "step": 56450 }, { "epoch": 11.7, "learning_rate": 0.00030436027096651083, "loss": 1.7271, "step": 56455 }, { "epoch": 11.7, "learning_rate": 0.00030426486022326117, "loss": 1.7172, "step": 56460 }, { "epoch": 11.7, "learning_rate": 0.00030416944948001145, "loss": 1.7193, "step": 56465 }, { "epoch": 11.7, "learning_rate": 0.0003040740387367618, "loss": 1.7187, "step": 56470 }, { "epoch": 11.7, "learning_rate": 0.00030397862799351206, "loss": 1.7232, "step": 56475 }, { "epoch": 11.7, "learning_rate": 0.0003038832172502624, "loss": 1.7187, "step": 56480 }, { "epoch": 11.7, "learning_rate": 0.00030378780650701273, "loss": 1.714, "step": 56485 }, { "epoch": 11.7, "learning_rate": 0.000303692395763763, "loss": 1.7176, "step": 56490 }, { "epoch": 11.7, "learning_rate": 0.0003035969850205133, "loss": 1.7127, "step": 56495 }, { "epoch": 11.7, "learning_rate": 0.0003035015742772636, "loss": 1.718, "step": 56500 }, { "epoch": 11.71, "learning_rate": 0.00030340616353401396, "loss": 1.7112, "step": 56505 }, { "epoch": 11.71, "learning_rate": 0.00030331075279076424, "loss": 1.7178, "step": 56510 }, { "epoch": 11.71, "learning_rate": 0.00030321534204751457, "loss": 1.7199, "step": 56515 }, { "epoch": 11.71, "learning_rate": 0.00030311993130426485, "loss": 1.7146, "step": 56520 }, { "epoch": 11.71, "learning_rate": 0.00030302452056101513, "loss": 1.715, "step": 56525 }, { "epoch": 11.71, "learning_rate": 0.0003029291098177655, "loss": 1.7197, "step": 56530 }, { "epoch": 11.71, "learning_rate": 0.0003028336990745158, "loss": 1.7115, "step": 56535 }, { "epoch": 11.71, "learning_rate": 0.0003027382883312661, "loss": 1.7179, "step": 56540 }, { "epoch": 11.71, "learning_rate": 0.0003026428775880164, "loss": 1.7255, "step": 56545 }, { "epoch": 11.72, "learning_rate": 0.00030254746684476674, "loss": 1.7191, "step": 56550 }, { "epoch": 11.72, "learning_rate": 0.000302452056101517, "loss": 1.7201, "step": 56555 }, { "epoch": 11.72, "learning_rate": 0.00030235664535826736, "loss": 1.7173, "step": 56560 }, { "epoch": 11.72, "learning_rate": 0.00030226123461501764, "loss": 1.719, "step": 56565 }, { "epoch": 11.72, "learning_rate": 0.0003021658238717679, "loss": 1.7201, "step": 56570 }, { "epoch": 11.72, "learning_rate": 0.0003020704131285183, "loss": 1.7181, "step": 56575 }, { "epoch": 11.72, "learning_rate": 0.0003019750023852686, "loss": 1.7171, "step": 56580 }, { "epoch": 11.72, "learning_rate": 0.00030187959164201887, "loss": 1.7208, "step": 56585 }, { "epoch": 11.72, "learning_rate": 0.0003017841808987692, "loss": 1.7196, "step": 56590 }, { "epoch": 11.72, "learning_rate": 0.00030168877015551953, "loss": 1.7147, "step": 56595 }, { "epoch": 11.73, "learning_rate": 0.00030159335941226987, "loss": 1.7239, "step": 56600 }, { "epoch": 11.73, "learning_rate": 0.00030149794866902015, "loss": 1.714, "step": 56605 }, { "epoch": 11.73, "learning_rate": 0.00030140253792577043, "loss": 1.7139, "step": 56610 }, { "epoch": 11.73, "learning_rate": 0.00030130712718252076, "loss": 1.7183, "step": 56615 }, { "epoch": 11.73, "learning_rate": 0.0003012117164392711, "loss": 1.7218, "step": 56620 }, { "epoch": 11.73, "learning_rate": 0.0003011163056960214, "loss": 1.7181, "step": 56625 }, { "epoch": 11.73, "learning_rate": 0.0003010208949527717, "loss": 1.7193, "step": 56630 }, { "epoch": 11.73, "learning_rate": 0.000300925484209522, "loss": 1.7165, "step": 56635 }, { "epoch": 11.73, "learning_rate": 0.0003008300734662723, "loss": 1.7208, "step": 56640 }, { "epoch": 11.74, "learning_rate": 0.00030073466272302266, "loss": 1.7184, "step": 56645 }, { "epoch": 11.74, "learning_rate": 0.00030063925197977294, "loss": 1.7126, "step": 56650 }, { "epoch": 11.74, "learning_rate": 0.0003005438412365232, "loss": 1.7216, "step": 56655 }, { "epoch": 11.74, "learning_rate": 0.00030044843049327355, "loss": 1.7187, "step": 56660 }, { "epoch": 11.74, "learning_rate": 0.0003003530197500239, "loss": 1.7222, "step": 56665 }, { "epoch": 11.74, "learning_rate": 0.00030025760900677416, "loss": 1.7174, "step": 56670 }, { "epoch": 11.74, "learning_rate": 0.0003001621982635245, "loss": 1.7167, "step": 56675 }, { "epoch": 11.74, "learning_rate": 0.0003000667875202748, "loss": 1.7131, "step": 56680 }, { "epoch": 11.74, "learning_rate": 0.00029997137677702506, "loss": 1.7185, "step": 56685 }, { "epoch": 11.74, "learning_rate": 0.00029987596603377545, "loss": 1.7185, "step": 56690 }, { "epoch": 11.75, "learning_rate": 0.0002997805552905257, "loss": 1.7179, "step": 56695 }, { "epoch": 11.75, "learning_rate": 0.000299685144547276, "loss": 1.7217, "step": 56700 }, { "epoch": 11.75, "learning_rate": 0.00029958973380402634, "loss": 1.7188, "step": 56705 }, { "epoch": 11.75, "learning_rate": 0.0002994943230607767, "loss": 1.7152, "step": 56710 }, { "epoch": 11.75, "learning_rate": 0.00029939891231752695, "loss": 1.7179, "step": 56715 }, { "epoch": 11.75, "learning_rate": 0.0002993035015742773, "loss": 1.7178, "step": 56720 }, { "epoch": 11.75, "learning_rate": 0.00029920809083102757, "loss": 1.7152, "step": 56725 }, { "epoch": 11.75, "learning_rate": 0.00029911268008777785, "loss": 1.719, "step": 56730 }, { "epoch": 11.75, "learning_rate": 0.00029901726934452823, "loss": 1.7212, "step": 56735 }, { "epoch": 11.75, "learning_rate": 0.0002989218586012785, "loss": 1.7146, "step": 56740 }, { "epoch": 11.76, "learning_rate": 0.0002988264478580288, "loss": 1.7187, "step": 56745 }, { "epoch": 11.76, "learning_rate": 0.00029873103711477913, "loss": 1.7156, "step": 56750 }, { "epoch": 11.76, "learning_rate": 0.00029863562637152946, "loss": 1.7226, "step": 56755 }, { "epoch": 11.76, "learning_rate": 0.00029854021562827974, "loss": 1.7177, "step": 56760 }, { "epoch": 11.76, "learning_rate": 0.0002984448048850301, "loss": 1.7199, "step": 56765 }, { "epoch": 11.76, "learning_rate": 0.00029834939414178036, "loss": 1.717, "step": 56770 }, { "epoch": 11.76, "learning_rate": 0.00029825398339853064, "loss": 1.7133, "step": 56775 }, { "epoch": 11.76, "learning_rate": 0.000298158572655281, "loss": 1.7171, "step": 56780 }, { "epoch": 11.76, "learning_rate": 0.0002980631619120313, "loss": 1.7194, "step": 56785 }, { "epoch": 11.77, "learning_rate": 0.0002979677511687816, "loss": 1.7175, "step": 56790 }, { "epoch": 11.77, "learning_rate": 0.0002978723404255319, "loss": 1.7161, "step": 56795 }, { "epoch": 11.77, "learning_rate": 0.0002977769296822822, "loss": 1.719, "step": 56800 }, { "epoch": 11.77, "learning_rate": 0.00029768151893903253, "loss": 1.7163, "step": 56805 }, { "epoch": 11.77, "learning_rate": 0.00029758610819578287, "loss": 1.7193, "step": 56810 }, { "epoch": 11.77, "learning_rate": 0.00029749069745253315, "loss": 1.7184, "step": 56815 }, { "epoch": 11.77, "learning_rate": 0.0002973952867092835, "loss": 1.7153, "step": 56820 }, { "epoch": 11.77, "learning_rate": 0.0002972998759660338, "loss": 1.719, "step": 56825 }, { "epoch": 11.77, "learning_rate": 0.0002972044652227841, "loss": 1.7212, "step": 56830 }, { "epoch": 11.77, "learning_rate": 0.0002971090544795344, "loss": 1.7215, "step": 56835 }, { "epoch": 11.78, "learning_rate": 0.0002970136437362847, "loss": 1.7182, "step": 56840 }, { "epoch": 11.78, "learning_rate": 0.000296918232993035, "loss": 1.7216, "step": 56845 }, { "epoch": 11.78, "learning_rate": 0.0002968228222497854, "loss": 1.7131, "step": 56850 }, { "epoch": 11.78, "learning_rate": 0.00029672741150653565, "loss": 1.7175, "step": 56855 }, { "epoch": 11.78, "learning_rate": 0.00029663200076328593, "loss": 1.7149, "step": 56860 }, { "epoch": 11.78, "learning_rate": 0.00029653659002003627, "loss": 1.7227, "step": 56865 }, { "epoch": 11.78, "learning_rate": 0.0002964411792767866, "loss": 1.7188, "step": 56870 }, { "epoch": 11.78, "learning_rate": 0.0002963457685335369, "loss": 1.7169, "step": 56875 }, { "epoch": 11.78, "learning_rate": 0.0002962503577902872, "loss": 1.7141, "step": 56880 }, { "epoch": 11.78, "learning_rate": 0.0002961549470470375, "loss": 1.7147, "step": 56885 }, { "epoch": 11.79, "learning_rate": 0.0002960595363037878, "loss": 1.7221, "step": 56890 }, { "epoch": 11.79, "learning_rate": 0.00029596412556053816, "loss": 1.7202, "step": 56895 }, { "epoch": 11.79, "learning_rate": 0.00029586871481728844, "loss": 1.7124, "step": 56900 }, { "epoch": 11.79, "learning_rate": 0.0002957733040740387, "loss": 1.7188, "step": 56905 }, { "epoch": 11.79, "learning_rate": 0.00029567789333078906, "loss": 1.7243, "step": 56910 }, { "epoch": 11.79, "learning_rate": 0.00029558248258753934, "loss": 1.7176, "step": 56915 }, { "epoch": 11.79, "learning_rate": 0.00029548707184428967, "loss": 1.7196, "step": 56920 }, { "epoch": 11.79, "learning_rate": 0.00029539166110104, "loss": 1.7152, "step": 56925 }, { "epoch": 11.79, "learning_rate": 0.0002952962503577903, "loss": 1.7163, "step": 56930 }, { "epoch": 11.8, "learning_rate": 0.00029520083961454056, "loss": 1.7142, "step": 56935 }, { "epoch": 11.8, "learning_rate": 0.00029510542887129095, "loss": 1.7158, "step": 56940 }, { "epoch": 11.8, "learning_rate": 0.00029501001812804123, "loss": 1.7176, "step": 56945 }, { "epoch": 11.8, "learning_rate": 0.0002949146073847915, "loss": 1.7193, "step": 56950 }, { "epoch": 11.8, "learning_rate": 0.00029481919664154185, "loss": 1.7166, "step": 56955 }, { "epoch": 11.8, "learning_rate": 0.0002947237858982921, "loss": 1.7196, "step": 56960 }, { "epoch": 11.8, "learning_rate": 0.00029462837515504246, "loss": 1.7145, "step": 56965 }, { "epoch": 11.8, "learning_rate": 0.0002945329644117928, "loss": 1.7257, "step": 56970 }, { "epoch": 11.8, "learning_rate": 0.0002944375536685431, "loss": 1.7222, "step": 56975 }, { "epoch": 11.8, "learning_rate": 0.00029434214292529335, "loss": 1.716, "step": 56980 }, { "epoch": 11.81, "learning_rate": 0.00029424673218204374, "loss": 1.7185, "step": 56985 }, { "epoch": 11.81, "learning_rate": 0.000294151321438794, "loss": 1.7148, "step": 56990 }, { "epoch": 11.81, "learning_rate": 0.0002940559106955443, "loss": 1.718, "step": 56995 }, { "epoch": 11.81, "learning_rate": 0.00029396049995229464, "loss": 1.716, "step": 57000 }, { "epoch": 11.81, "eval_accuracy": 0.5473464052287582, "eval_loss": 1.9073282480239868, "eval_runtime": 0.6495, "eval_samples_per_second": 230.949, "eval_steps_per_second": 1.54, "step": 57000 }, { "epoch": 11.81, "learning_rate": 0.0002938650892090449, "loss": 1.7183, "step": 57005 }, { "epoch": 11.81, "learning_rate": 0.00029376967846579525, "loss": 1.72, "step": 57010 }, { "epoch": 11.81, "learning_rate": 0.0002936742677225456, "loss": 1.7198, "step": 57015 }, { "epoch": 11.81, "learning_rate": 0.00029357885697929586, "loss": 1.7172, "step": 57020 }, { "epoch": 11.81, "learning_rate": 0.00029348344623604614, "loss": 1.7175, "step": 57025 }, { "epoch": 11.81, "learning_rate": 0.0002933880354927965, "loss": 1.7124, "step": 57030 }, { "epoch": 11.82, "learning_rate": 0.0002932926247495468, "loss": 1.7203, "step": 57035 }, { "epoch": 11.82, "learning_rate": 0.00029319721400629714, "loss": 1.7118, "step": 57040 }, { "epoch": 11.82, "learning_rate": 0.0002931018032630474, "loss": 1.7192, "step": 57045 }, { "epoch": 11.82, "learning_rate": 0.0002930063925197977, "loss": 1.7173, "step": 57050 }, { "epoch": 11.82, "learning_rate": 0.0002929109817765481, "loss": 1.7191, "step": 57055 }, { "epoch": 11.82, "learning_rate": 0.00029281557103329837, "loss": 1.715, "step": 57060 }, { "epoch": 11.82, "learning_rate": 0.00029272016029004865, "loss": 1.7153, "step": 57065 }, { "epoch": 11.82, "learning_rate": 0.000292624749546799, "loss": 1.7159, "step": 57070 }, { "epoch": 11.82, "learning_rate": 0.00029252933880354927, "loss": 1.7183, "step": 57075 }, { "epoch": 11.83, "learning_rate": 0.0002924339280602996, "loss": 1.7206, "step": 57080 }, { "epoch": 11.83, "learning_rate": 0.00029233851731704993, "loss": 1.7146, "step": 57085 }, { "epoch": 11.83, "learning_rate": 0.0002922431065738002, "loss": 1.7173, "step": 57090 }, { "epoch": 11.83, "learning_rate": 0.0002921476958305505, "loss": 1.7198, "step": 57095 }, { "epoch": 11.83, "learning_rate": 0.0002920522850873009, "loss": 1.7204, "step": 57100 }, { "epoch": 11.83, "learning_rate": 0.00029195687434405116, "loss": 1.7139, "step": 57105 }, { "epoch": 11.83, "learning_rate": 0.00029186146360080144, "loss": 1.7185, "step": 57110 }, { "epoch": 11.83, "learning_rate": 0.0002917660528575518, "loss": 1.725, "step": 57115 }, { "epoch": 11.83, "learning_rate": 0.00029167064211430206, "loss": 1.7196, "step": 57120 }, { "epoch": 11.83, "learning_rate": 0.0002915752313710524, "loss": 1.7164, "step": 57125 }, { "epoch": 11.84, "learning_rate": 0.0002914798206278027, "loss": 1.7165, "step": 57130 }, { "epoch": 11.84, "learning_rate": 0.000291384409884553, "loss": 1.7163, "step": 57135 }, { "epoch": 11.84, "learning_rate": 0.0002912889991413033, "loss": 1.719, "step": 57140 }, { "epoch": 11.84, "learning_rate": 0.0002911935883980536, "loss": 1.722, "step": 57145 }, { "epoch": 11.84, "learning_rate": 0.00029109817765480395, "loss": 1.7184, "step": 57150 }, { "epoch": 11.84, "learning_rate": 0.00029100276691155423, "loss": 1.7233, "step": 57155 }, { "epoch": 11.84, "learning_rate": 0.00029090735616830456, "loss": 1.7152, "step": 57160 }, { "epoch": 11.84, "learning_rate": 0.00029081194542505484, "loss": 1.7183, "step": 57165 }, { "epoch": 11.84, "learning_rate": 0.0002907165346818052, "loss": 1.7187, "step": 57170 }, { "epoch": 11.84, "learning_rate": 0.0002906211239385555, "loss": 1.7165, "step": 57175 }, { "epoch": 11.85, "learning_rate": 0.0002905257131953058, "loss": 1.716, "step": 57180 }, { "epoch": 11.85, "learning_rate": 0.00029043030245205607, "loss": 1.7172, "step": 57185 }, { "epoch": 11.85, "learning_rate": 0.0002903348917088064, "loss": 1.7185, "step": 57190 }, { "epoch": 11.85, "learning_rate": 0.00029023948096555674, "loss": 1.7171, "step": 57195 }, { "epoch": 11.85, "learning_rate": 0.000290144070222307, "loss": 1.7154, "step": 57200 }, { "epoch": 11.85, "learning_rate": 0.00029004865947905735, "loss": 1.7121, "step": 57205 }, { "epoch": 11.85, "learning_rate": 0.00028995324873580763, "loss": 1.7143, "step": 57210 }, { "epoch": 11.85, "learning_rate": 0.00028985783799255797, "loss": 1.7188, "step": 57215 }, { "epoch": 11.85, "learning_rate": 0.0002897624272493083, "loss": 1.7161, "step": 57220 }, { "epoch": 11.86, "learning_rate": 0.0002896670165060586, "loss": 1.7162, "step": 57225 }, { "epoch": 11.86, "learning_rate": 0.00028957160576280886, "loss": 1.7207, "step": 57230 }, { "epoch": 11.86, "learning_rate": 0.0002894761950195592, "loss": 1.721, "step": 57235 }, { "epoch": 11.86, "learning_rate": 0.00028938078427630953, "loss": 1.7216, "step": 57240 }, { "epoch": 11.86, "learning_rate": 0.00028928537353305986, "loss": 1.7146, "step": 57245 }, { "epoch": 11.86, "learning_rate": 0.00028918996278981014, "loss": 1.7204, "step": 57250 }, { "epoch": 11.86, "learning_rate": 0.0002890945520465604, "loss": 1.7155, "step": 57255 }, { "epoch": 11.86, "learning_rate": 0.0002889991413033108, "loss": 1.7202, "step": 57260 }, { "epoch": 11.86, "learning_rate": 0.0002889037305600611, "loss": 1.7207, "step": 57265 }, { "epoch": 11.86, "learning_rate": 0.00028880831981681137, "loss": 1.7188, "step": 57270 }, { "epoch": 11.87, "learning_rate": 0.0002887129090735617, "loss": 1.7172, "step": 57275 }, { "epoch": 11.87, "learning_rate": 0.000288617498330312, "loss": 1.7185, "step": 57280 }, { "epoch": 11.87, "learning_rate": 0.0002885220875870623, "loss": 1.7147, "step": 57285 }, { "epoch": 11.87, "learning_rate": 0.00028842667684381265, "loss": 1.7167, "step": 57290 }, { "epoch": 11.87, "learning_rate": 0.00028833126610056293, "loss": 1.72, "step": 57295 }, { "epoch": 11.87, "learning_rate": 0.0002882358553573132, "loss": 1.7224, "step": 57300 }, { "epoch": 11.87, "learning_rate": 0.00028814044461406355, "loss": 1.7178, "step": 57305 }, { "epoch": 11.87, "learning_rate": 0.0002880450338708139, "loss": 1.7146, "step": 57310 }, { "epoch": 11.87, "learning_rate": 0.00028794962312756416, "loss": 1.7134, "step": 57315 }, { "epoch": 11.87, "learning_rate": 0.0002878542123843145, "loss": 1.7152, "step": 57320 }, { "epoch": 11.88, "learning_rate": 0.0002877588016410648, "loss": 1.7151, "step": 57325 }, { "epoch": 11.88, "learning_rate": 0.0002876633908978151, "loss": 1.7178, "step": 57330 }, { "epoch": 11.88, "learning_rate": 0.00028756798015456544, "loss": 1.7154, "step": 57335 }, { "epoch": 11.88, "learning_rate": 0.0002874725694113157, "loss": 1.7196, "step": 57340 }, { "epoch": 11.88, "learning_rate": 0.000287377158668066, "loss": 1.7176, "step": 57345 }, { "epoch": 11.88, "learning_rate": 0.00028728174792481633, "loss": 1.7194, "step": 57350 }, { "epoch": 11.88, "learning_rate": 0.00028718633718156667, "loss": 1.72, "step": 57355 }, { "epoch": 11.88, "learning_rate": 0.00028709092643831695, "loss": 1.7159, "step": 57360 }, { "epoch": 11.88, "learning_rate": 0.0002869955156950673, "loss": 1.7157, "step": 57365 }, { "epoch": 11.89, "learning_rate": 0.00028690010495181756, "loss": 1.7135, "step": 57370 }, { "epoch": 11.89, "learning_rate": 0.0002868046942085679, "loss": 1.7154, "step": 57375 }, { "epoch": 11.89, "learning_rate": 0.00028670928346531823, "loss": 1.7176, "step": 57380 }, { "epoch": 11.89, "learning_rate": 0.0002866138727220685, "loss": 1.7219, "step": 57385 }, { "epoch": 11.89, "learning_rate": 0.0002865184619788188, "loss": 1.7186, "step": 57390 }, { "epoch": 11.89, "learning_rate": 0.0002864230512355691, "loss": 1.7175, "step": 57395 }, { "epoch": 11.89, "learning_rate": 0.00028632764049231946, "loss": 1.7158, "step": 57400 }, { "epoch": 11.89, "learning_rate": 0.00028623222974906974, "loss": 1.7156, "step": 57405 }, { "epoch": 11.89, "learning_rate": 0.00028613681900582007, "loss": 1.7169, "step": 57410 }, { "epoch": 11.89, "learning_rate": 0.00028604140826257035, "loss": 1.7187, "step": 57415 }, { "epoch": 11.9, "learning_rate": 0.00028594599751932063, "loss": 1.7211, "step": 57420 }, { "epoch": 11.9, "learning_rate": 0.000285850586776071, "loss": 1.7167, "step": 57425 }, { "epoch": 11.9, "learning_rate": 0.0002857551760328213, "loss": 1.7181, "step": 57430 }, { "epoch": 11.9, "learning_rate": 0.0002856597652895716, "loss": 1.7186, "step": 57435 }, { "epoch": 11.9, "learning_rate": 0.0002855643545463219, "loss": 1.7162, "step": 57440 }, { "epoch": 11.9, "learning_rate": 0.00028546894380307225, "loss": 1.7202, "step": 57445 }, { "epoch": 11.9, "learning_rate": 0.0002853735330598226, "loss": 1.7219, "step": 57450 }, { "epoch": 11.9, "learning_rate": 0.00028527812231657286, "loss": 1.7141, "step": 57455 }, { "epoch": 11.9, "learning_rate": 0.00028518271157332314, "loss": 1.7175, "step": 57460 }, { "epoch": 11.9, "learning_rate": 0.0002850873008300735, "loss": 1.7142, "step": 57465 }, { "epoch": 11.91, "learning_rate": 0.0002849918900868238, "loss": 1.7154, "step": 57470 }, { "epoch": 11.91, "learning_rate": 0.0002848964793435741, "loss": 1.7153, "step": 57475 }, { "epoch": 11.91, "learning_rate": 0.0002848010686003244, "loss": 1.7146, "step": 57480 }, { "epoch": 11.91, "learning_rate": 0.0002847056578570747, "loss": 1.7201, "step": 57485 }, { "epoch": 11.91, "learning_rate": 0.00028461024711382504, "loss": 1.7233, "step": 57490 }, { "epoch": 11.91, "learning_rate": 0.00028451483637057537, "loss": 1.7191, "step": 57495 }, { "epoch": 11.91, "learning_rate": 0.00028441942562732565, "loss": 1.7166, "step": 57500 }, { "epoch": 11.91, "learning_rate": 0.00028432401488407593, "loss": 1.718, "step": 57505 }, { "epoch": 11.91, "learning_rate": 0.00028422860414082626, "loss": 1.7218, "step": 57510 }, { "epoch": 11.92, "learning_rate": 0.0002841331933975766, "loss": 1.7184, "step": 57515 }, { "epoch": 11.92, "learning_rate": 0.0002840377826543269, "loss": 1.7217, "step": 57520 }, { "epoch": 11.92, "learning_rate": 0.0002839423719110772, "loss": 1.7196, "step": 57525 }, { "epoch": 11.92, "learning_rate": 0.0002838469611678275, "loss": 1.7137, "step": 57530 }, { "epoch": 11.92, "learning_rate": 0.00028375155042457777, "loss": 1.7172, "step": 57535 }, { "epoch": 11.92, "learning_rate": 0.00028365613968132816, "loss": 1.7211, "step": 57540 }, { "epoch": 11.92, "learning_rate": 0.00028356072893807844, "loss": 1.7159, "step": 57545 }, { "epoch": 11.92, "learning_rate": 0.0002834653181948287, "loss": 1.7214, "step": 57550 }, { "epoch": 11.92, "learning_rate": 0.00028336990745157905, "loss": 1.7208, "step": 57555 }, { "epoch": 11.92, "learning_rate": 0.0002832744967083294, "loss": 1.7206, "step": 57560 }, { "epoch": 11.93, "learning_rate": 0.00028317908596507967, "loss": 1.7124, "step": 57565 }, { "epoch": 11.93, "learning_rate": 0.00028308367522183, "loss": 1.7166, "step": 57570 }, { "epoch": 11.93, "learning_rate": 0.0002829882644785803, "loss": 1.715, "step": 57575 }, { "epoch": 11.93, "learning_rate": 0.00028289285373533056, "loss": 1.719, "step": 57580 }, { "epoch": 11.93, "learning_rate": 0.00028279744299208095, "loss": 1.7169, "step": 57585 }, { "epoch": 11.93, "learning_rate": 0.00028270203224883123, "loss": 1.7236, "step": 57590 }, { "epoch": 11.93, "learning_rate": 0.0002826066215055815, "loss": 1.7217, "step": 57595 }, { "epoch": 11.93, "learning_rate": 0.00028251121076233184, "loss": 1.7182, "step": 57600 }, { "epoch": 11.93, "learning_rate": 0.0002824158000190822, "loss": 1.7147, "step": 57605 }, { "epoch": 11.93, "learning_rate": 0.00028232038927583246, "loss": 1.7153, "step": 57610 }, { "epoch": 11.94, "learning_rate": 0.0002822249785325828, "loss": 1.7184, "step": 57615 }, { "epoch": 11.94, "learning_rate": 0.00028212956778933307, "loss": 1.7225, "step": 57620 }, { "epoch": 11.94, "learning_rate": 0.00028203415704608335, "loss": 1.7163, "step": 57625 }, { "epoch": 11.94, "learning_rate": 0.00028193874630283374, "loss": 1.7177, "step": 57630 }, { "epoch": 11.94, "learning_rate": 0.000281843335559584, "loss": 1.7194, "step": 57635 }, { "epoch": 11.94, "learning_rate": 0.0002817479248163343, "loss": 1.7235, "step": 57640 }, { "epoch": 11.94, "learning_rate": 0.00028165251407308463, "loss": 1.7221, "step": 57645 }, { "epoch": 11.94, "learning_rate": 0.0002815571033298349, "loss": 1.7149, "step": 57650 }, { "epoch": 11.94, "learning_rate": 0.0002814616925865853, "loss": 1.7154, "step": 57655 }, { "epoch": 11.95, "learning_rate": 0.0002813662818433356, "loss": 1.7195, "step": 57660 }, { "epoch": 11.95, "learning_rate": 0.00028127087110008586, "loss": 1.722, "step": 57665 }, { "epoch": 11.95, "learning_rate": 0.0002811754603568362, "loss": 1.7228, "step": 57670 }, { "epoch": 11.95, "learning_rate": 0.0002810800496135865, "loss": 1.7179, "step": 57675 }, { "epoch": 11.95, "learning_rate": 0.0002809846388703368, "loss": 1.7173, "step": 57680 }, { "epoch": 11.95, "learning_rate": 0.00028088922812708714, "loss": 1.7158, "step": 57685 }, { "epoch": 11.95, "learning_rate": 0.0002807938173838374, "loss": 1.716, "step": 57690 }, { "epoch": 11.95, "learning_rate": 0.0002806984066405877, "loss": 1.723, "step": 57695 }, { "epoch": 11.95, "learning_rate": 0.0002806029958973381, "loss": 1.7188, "step": 57700 }, { "epoch": 11.95, "learning_rate": 0.00028050758515408837, "loss": 1.7153, "step": 57705 }, { "epoch": 11.96, "learning_rate": 0.00028041217441083865, "loss": 1.7186, "step": 57710 }, { "epoch": 11.96, "learning_rate": 0.000280316763667589, "loss": 1.7203, "step": 57715 }, { "epoch": 11.96, "learning_rate": 0.0002802213529243393, "loss": 1.7173, "step": 57720 }, { "epoch": 11.96, "learning_rate": 0.0002801259421810896, "loss": 1.7249, "step": 57725 }, { "epoch": 11.96, "learning_rate": 0.00028003053143783993, "loss": 1.7179, "step": 57730 }, { "epoch": 11.96, "learning_rate": 0.0002799351206945902, "loss": 1.7175, "step": 57735 }, { "epoch": 11.96, "learning_rate": 0.0002798397099513405, "loss": 1.7174, "step": 57740 }, { "epoch": 11.96, "learning_rate": 0.0002797442992080909, "loss": 1.7239, "step": 57745 }, { "epoch": 11.96, "learning_rate": 0.00027964888846484116, "loss": 1.7213, "step": 57750 }, { "epoch": 11.96, "learning_rate": 0.00027955347772159144, "loss": 1.7165, "step": 57755 }, { "epoch": 11.97, "learning_rate": 0.00027945806697834177, "loss": 1.7145, "step": 57760 }, { "epoch": 11.97, "learning_rate": 0.00027936265623509205, "loss": 1.7179, "step": 57765 }, { "epoch": 11.97, "learning_rate": 0.0002792672454918424, "loss": 1.7177, "step": 57770 }, { "epoch": 11.97, "learning_rate": 0.0002791718347485927, "loss": 1.715, "step": 57775 }, { "epoch": 11.97, "learning_rate": 0.000279076424005343, "loss": 1.7189, "step": 57780 }, { "epoch": 11.97, "learning_rate": 0.0002789810132620933, "loss": 1.7221, "step": 57785 }, { "epoch": 11.97, "learning_rate": 0.00027888560251884367, "loss": 1.716, "step": 57790 }, { "epoch": 11.97, "learning_rate": 0.00027879019177559395, "loss": 1.7175, "step": 57795 }, { "epoch": 11.97, "learning_rate": 0.0002786947810323442, "loss": 1.717, "step": 57800 }, { "epoch": 11.98, "learning_rate": 0.00027859937028909456, "loss": 1.7147, "step": 57805 }, { "epoch": 11.98, "learning_rate": 0.00027850395954584484, "loss": 1.7164, "step": 57810 }, { "epoch": 11.98, "learning_rate": 0.0002784085488025952, "loss": 1.7184, "step": 57815 }, { "epoch": 11.98, "learning_rate": 0.0002783131380593455, "loss": 1.7191, "step": 57820 }, { "epoch": 11.98, "learning_rate": 0.0002782177273160958, "loss": 1.7204, "step": 57825 }, { "epoch": 11.98, "learning_rate": 0.00027812231657284607, "loss": 1.7177, "step": 57830 }, { "epoch": 11.98, "learning_rate": 0.00027802690582959646, "loss": 1.7152, "step": 57835 }, { "epoch": 11.98, "learning_rate": 0.00027793149508634674, "loss": 1.717, "step": 57840 }, { "epoch": 11.98, "learning_rate": 0.000277836084343097, "loss": 1.7148, "step": 57845 }, { "epoch": 11.98, "learning_rate": 0.00027774067359984735, "loss": 1.7181, "step": 57850 }, { "epoch": 11.99, "learning_rate": 0.00027764526285659763, "loss": 1.7187, "step": 57855 }, { "epoch": 11.99, "learning_rate": 0.00027754985211334796, "loss": 1.713, "step": 57860 }, { "epoch": 11.99, "learning_rate": 0.0002774544413700983, "loss": 1.7139, "step": 57865 }, { "epoch": 11.99, "learning_rate": 0.0002773590306268486, "loss": 1.7177, "step": 57870 }, { "epoch": 11.99, "learning_rate": 0.00027726361988359886, "loss": 1.7217, "step": 57875 }, { "epoch": 11.99, "learning_rate": 0.00027716820914034924, "loss": 1.7116, "step": 57880 }, { "epoch": 11.99, "learning_rate": 0.0002770727983970995, "loss": 1.7176, "step": 57885 }, { "epoch": 11.99, "learning_rate": 0.00027697738765384986, "loss": 1.7148, "step": 57890 }, { "epoch": 11.99, "learning_rate": 0.00027688197691060014, "loss": 1.7169, "step": 57895 }, { "epoch": 12.0, "learning_rate": 0.0002767865661673504, "loss": 1.7193, "step": 57900 }, { "epoch": 12.0, "learning_rate": 0.0002766911554241008, "loss": 1.7141, "step": 57905 }, { "epoch": 12.0, "learning_rate": 0.0002765957446808511, "loss": 1.7134, "step": 57910 }, { "epoch": 12.0, "learning_rate": 0.00027650033393760137, "loss": 1.7145, "step": 57915 }, { "epoch": 12.0, "learning_rate": 0.0002764049231943517, "loss": 1.7191, "step": 57920 }, { "epoch": 12.0, "learning_rate": 0.000276309512451102, "loss": 1.7113, "step": 57925 }, { "epoch": 12.0, "learning_rate": 0.0002762141017078523, "loss": 1.7151, "step": 57930 }, { "epoch": 12.0, "learning_rate": 0.00027611869096460265, "loss": 1.7126, "step": 57935 }, { "epoch": 12.0, "learning_rate": 0.0002760232802213529, "loss": 1.7027, "step": 57940 }, { "epoch": 12.0, "learning_rate": 0.0002759278694781032, "loss": 1.7091, "step": 57945 }, { "epoch": 12.01, "learning_rate": 0.0002758324587348536, "loss": 1.7135, "step": 57950 }, { "epoch": 12.01, "learning_rate": 0.0002757370479916039, "loss": 1.7097, "step": 57955 }, { "epoch": 12.01, "learning_rate": 0.00027564163724835415, "loss": 1.7094, "step": 57960 }, { "epoch": 12.01, "learning_rate": 0.0002755462265051045, "loss": 1.7061, "step": 57965 }, { "epoch": 12.01, "learning_rate": 0.00027545081576185477, "loss": 1.7096, "step": 57970 }, { "epoch": 12.01, "learning_rate": 0.0002753554050186051, "loss": 1.715, "step": 57975 }, { "epoch": 12.01, "learning_rate": 0.00027525999427535544, "loss": 1.7111, "step": 57980 }, { "epoch": 12.01, "learning_rate": 0.0002751645835321057, "loss": 1.7055, "step": 57985 }, { "epoch": 12.01, "learning_rate": 0.000275069172788856, "loss": 1.7119, "step": 57990 }, { "epoch": 12.01, "learning_rate": 0.0002749737620456064, "loss": 1.7088, "step": 57995 }, { "epoch": 12.02, "learning_rate": 0.00027487835130235666, "loss": 1.7043, "step": 58000 }, { "epoch": 12.02, "learning_rate": 0.00027478294055910694, "loss": 1.7096, "step": 58005 }, { "epoch": 12.02, "learning_rate": 0.0002746875298158573, "loss": 1.7083, "step": 58010 }, { "epoch": 12.02, "learning_rate": 0.00027459211907260756, "loss": 1.7134, "step": 58015 }, { "epoch": 12.02, "learning_rate": 0.0002744967083293579, "loss": 1.7072, "step": 58020 }, { "epoch": 12.02, "learning_rate": 0.0002744012975861082, "loss": 1.7131, "step": 58025 }, { "epoch": 12.02, "learning_rate": 0.0002743058868428585, "loss": 1.7088, "step": 58030 }, { "epoch": 12.02, "learning_rate": 0.0002742104760996088, "loss": 1.7048, "step": 58035 }, { "epoch": 12.02, "learning_rate": 0.0002741150653563591, "loss": 1.7082, "step": 58040 }, { "epoch": 12.03, "learning_rate": 0.00027401965461310945, "loss": 1.7094, "step": 58045 }, { "epoch": 12.03, "learning_rate": 0.00027392424386985973, "loss": 1.7115, "step": 58050 }, { "epoch": 12.03, "learning_rate": 0.00027382883312661007, "loss": 1.7087, "step": 58055 }, { "epoch": 12.03, "learning_rate": 0.00027373342238336035, "loss": 1.7147, "step": 58060 }, { "epoch": 12.03, "learning_rate": 0.0002736380116401107, "loss": 1.7055, "step": 58065 }, { "epoch": 12.03, "learning_rate": 0.000273542600896861, "loss": 1.7095, "step": 58070 }, { "epoch": 12.03, "learning_rate": 0.0002734471901536113, "loss": 1.7083, "step": 58075 }, { "epoch": 12.03, "learning_rate": 0.0002733517794103616, "loss": 1.7064, "step": 58080 }, { "epoch": 12.03, "learning_rate": 0.0002732563686671119, "loss": 1.7044, "step": 58085 }, { "epoch": 12.03, "learning_rate": 0.00027316095792386224, "loss": 1.7124, "step": 58090 }, { "epoch": 12.04, "learning_rate": 0.0002730655471806126, "loss": 1.7145, "step": 58095 }, { "epoch": 12.04, "learning_rate": 0.00027297013643736286, "loss": 1.7066, "step": 58100 }, { "epoch": 12.04, "learning_rate": 0.00027287472569411314, "loss": 1.7127, "step": 58105 }, { "epoch": 12.04, "learning_rate": 0.0002727793149508635, "loss": 1.7081, "step": 58110 }, { "epoch": 12.04, "learning_rate": 0.0002726839042076138, "loss": 1.712, "step": 58115 }, { "epoch": 12.04, "learning_rate": 0.0002725884934643641, "loss": 1.7077, "step": 58120 }, { "epoch": 12.04, "learning_rate": 0.0002724930827211144, "loss": 1.7191, "step": 58125 }, { "epoch": 12.04, "learning_rate": 0.0002723976719778647, "loss": 1.7089, "step": 58130 }, { "epoch": 12.04, "learning_rate": 0.00027230226123461503, "loss": 1.7109, "step": 58135 }, { "epoch": 12.04, "learning_rate": 0.00027220685049136537, "loss": 1.712, "step": 58140 }, { "epoch": 12.05, "learning_rate": 0.00027211143974811565, "loss": 1.7047, "step": 58145 }, { "epoch": 12.05, "learning_rate": 0.0002720160290048659, "loss": 1.7151, "step": 58150 }, { "epoch": 12.05, "learning_rate": 0.00027192061826161626, "loss": 1.7111, "step": 58155 }, { "epoch": 12.05, "learning_rate": 0.0002718252075183666, "loss": 1.7086, "step": 58160 }, { "epoch": 12.05, "learning_rate": 0.00027172979677511687, "loss": 1.7158, "step": 58165 }, { "epoch": 12.05, "learning_rate": 0.0002716343860318672, "loss": 1.7125, "step": 58170 }, { "epoch": 12.05, "learning_rate": 0.0002715389752886175, "loss": 1.703, "step": 58175 }, { "epoch": 12.05, "learning_rate": 0.0002714435645453678, "loss": 1.7079, "step": 58180 }, { "epoch": 12.05, "learning_rate": 0.00027134815380211815, "loss": 1.7104, "step": 58185 }, { "epoch": 12.06, "learning_rate": 0.00027125274305886843, "loss": 1.7146, "step": 58190 }, { "epoch": 12.06, "learning_rate": 0.0002711573323156187, "loss": 1.707, "step": 58195 }, { "epoch": 12.06, "learning_rate": 0.00027106192157236905, "loss": 1.7097, "step": 58200 }, { "epoch": 12.06, "learning_rate": 0.0002709665108291194, "loss": 1.7109, "step": 58205 }, { "epoch": 12.06, "learning_rate": 0.00027087110008586966, "loss": 1.7087, "step": 58210 }, { "epoch": 12.06, "learning_rate": 0.00027077568934262, "loss": 1.71, "step": 58215 }, { "epoch": 12.06, "learning_rate": 0.0002706802785993703, "loss": 1.7088, "step": 58220 }, { "epoch": 12.06, "learning_rate": 0.0002705848678561206, "loss": 1.7119, "step": 58225 }, { "epoch": 12.06, "learning_rate": 0.00027048945711287094, "loss": 1.7119, "step": 58230 }, { "epoch": 12.06, "learning_rate": 0.0002703940463696212, "loss": 1.7112, "step": 58235 }, { "epoch": 12.07, "learning_rate": 0.0002702986356263715, "loss": 1.7068, "step": 58240 }, { "epoch": 12.07, "learning_rate": 0.00027020322488312184, "loss": 1.7057, "step": 58245 }, { "epoch": 12.07, "learning_rate": 0.00027010781413987217, "loss": 1.7041, "step": 58250 }, { "epoch": 12.07, "learning_rate": 0.00027001240339662245, "loss": 1.713, "step": 58255 }, { "epoch": 12.07, "learning_rate": 0.0002699169926533728, "loss": 1.7131, "step": 58260 }, { "epoch": 12.07, "learning_rate": 0.00026982158191012306, "loss": 1.7108, "step": 58265 }, { "epoch": 12.07, "learning_rate": 0.00026972617116687334, "loss": 1.7096, "step": 58270 }, { "epoch": 12.07, "learning_rate": 0.00026963076042362373, "loss": 1.713, "step": 58275 }, { "epoch": 12.07, "learning_rate": 0.000269535349680374, "loss": 1.7099, "step": 58280 }, { "epoch": 12.07, "learning_rate": 0.0002694399389371243, "loss": 1.7143, "step": 58285 }, { "epoch": 12.08, "learning_rate": 0.0002693445281938746, "loss": 1.7082, "step": 58290 }, { "epoch": 12.08, "learning_rate": 0.00026924911745062496, "loss": 1.711, "step": 58295 }, { "epoch": 12.08, "learning_rate": 0.0002691537067073753, "loss": 1.709, "step": 58300 }, { "epoch": 12.08, "learning_rate": 0.0002690582959641256, "loss": 1.7089, "step": 58305 }, { "epoch": 12.08, "learning_rate": 0.00026896288522087585, "loss": 1.7134, "step": 58310 }, { "epoch": 12.08, "learning_rate": 0.0002688674744776262, "loss": 1.7065, "step": 58315 }, { "epoch": 12.08, "learning_rate": 0.0002687720637343765, "loss": 1.717, "step": 58320 }, { "epoch": 12.08, "learning_rate": 0.0002686766529911268, "loss": 1.7098, "step": 58325 }, { "epoch": 12.08, "learning_rate": 0.00026858124224787714, "loss": 1.7075, "step": 58330 }, { "epoch": 12.09, "learning_rate": 0.0002684858315046274, "loss": 1.7089, "step": 58335 }, { "epoch": 12.09, "learning_rate": 0.00026839042076137775, "loss": 1.7133, "step": 58340 }, { "epoch": 12.09, "learning_rate": 0.0002682950100181281, "loss": 1.7118, "step": 58345 }, { "epoch": 12.09, "learning_rate": 0.00026819959927487836, "loss": 1.7098, "step": 58350 }, { "epoch": 12.09, "learning_rate": 0.00026810418853162864, "loss": 1.7067, "step": 58355 }, { "epoch": 12.09, "learning_rate": 0.000268008777788379, "loss": 1.7118, "step": 58360 }, { "epoch": 12.09, "learning_rate": 0.0002679133670451293, "loss": 1.7104, "step": 58365 }, { "epoch": 12.09, "learning_rate": 0.0002678179563018796, "loss": 1.7119, "step": 58370 }, { "epoch": 12.09, "learning_rate": 0.0002677225455586299, "loss": 1.7118, "step": 58375 }, { "epoch": 12.09, "learning_rate": 0.0002676271348153802, "loss": 1.7128, "step": 58380 }, { "epoch": 12.1, "learning_rate": 0.0002675317240721305, "loss": 1.7143, "step": 58385 }, { "epoch": 12.1, "learning_rate": 0.00026743631332888087, "loss": 1.7116, "step": 58390 }, { "epoch": 12.1, "learning_rate": 0.00026734090258563115, "loss": 1.7123, "step": 58395 }, { "epoch": 12.1, "learning_rate": 0.00026724549184238143, "loss": 1.7111, "step": 58400 }, { "epoch": 12.1, "learning_rate": 0.00026715008109913177, "loss": 1.7095, "step": 58405 }, { "epoch": 12.1, "learning_rate": 0.0002670546703558821, "loss": 1.7068, "step": 58410 }, { "epoch": 12.1, "learning_rate": 0.0002669592596126324, "loss": 1.7164, "step": 58415 }, { "epoch": 12.1, "learning_rate": 0.0002668638488693827, "loss": 1.7125, "step": 58420 }, { "epoch": 12.1, "learning_rate": 0.000266768438126133, "loss": 1.7007, "step": 58425 }, { "epoch": 12.1, "learning_rate": 0.0002666730273828833, "loss": 1.7133, "step": 58430 }, { "epoch": 12.11, "learning_rate": 0.00026657761663963366, "loss": 1.7113, "step": 58435 }, { "epoch": 12.11, "learning_rate": 0.00026648220589638394, "loss": 1.7089, "step": 58440 }, { "epoch": 12.11, "learning_rate": 0.0002663867951531342, "loss": 1.7131, "step": 58445 }, { "epoch": 12.11, "learning_rate": 0.00026629138440988456, "loss": 1.7137, "step": 58450 }, { "epoch": 12.11, "learning_rate": 0.0002661959736666349, "loss": 1.7066, "step": 58455 }, { "epoch": 12.11, "learning_rate": 0.00026610056292338517, "loss": 1.7052, "step": 58460 }, { "epoch": 12.11, "learning_rate": 0.0002660051521801355, "loss": 1.7123, "step": 58465 }, { "epoch": 12.11, "learning_rate": 0.0002659097414368858, "loss": 1.7117, "step": 58470 }, { "epoch": 12.11, "learning_rate": 0.00026581433069363606, "loss": 1.7085, "step": 58475 }, { "epoch": 12.12, "learning_rate": 0.00026571891995038645, "loss": 1.706, "step": 58480 }, { "epoch": 12.12, "learning_rate": 0.00026562350920713673, "loss": 1.707, "step": 58485 }, { "epoch": 12.12, "learning_rate": 0.000265528098463887, "loss": 1.7147, "step": 58490 }, { "epoch": 12.12, "learning_rate": 0.00026543268772063734, "loss": 1.7102, "step": 58495 }, { "epoch": 12.12, "learning_rate": 0.0002653372769773877, "loss": 1.7099, "step": 58500 }, { "epoch": 12.12, "learning_rate": 0.000265241866234138, "loss": 1.7079, "step": 58505 }, { "epoch": 12.12, "learning_rate": 0.0002651464554908883, "loss": 1.7072, "step": 58510 }, { "epoch": 12.12, "learning_rate": 0.00026505104474763857, "loss": 1.707, "step": 58515 }, { "epoch": 12.12, "learning_rate": 0.0002649556340043889, "loss": 1.7118, "step": 58520 }, { "epoch": 12.12, "learning_rate": 0.00026486022326113924, "loss": 1.7054, "step": 58525 }, { "epoch": 12.13, "learning_rate": 0.0002647648125178895, "loss": 1.7042, "step": 58530 }, { "epoch": 12.13, "learning_rate": 0.00026466940177463985, "loss": 1.7104, "step": 58535 }, { "epoch": 12.13, "learning_rate": 0.00026457399103139013, "loss": 1.7151, "step": 58540 }, { "epoch": 12.13, "learning_rate": 0.0002644785802881404, "loss": 1.7104, "step": 58545 }, { "epoch": 12.13, "learning_rate": 0.0002643831695448908, "loss": 1.7101, "step": 58550 }, { "epoch": 12.13, "learning_rate": 0.0002642877588016411, "loss": 1.7071, "step": 58555 }, { "epoch": 12.13, "learning_rate": 0.00026419234805839136, "loss": 1.7132, "step": 58560 }, { "epoch": 12.13, "learning_rate": 0.0002640969373151417, "loss": 1.7126, "step": 58565 }, { "epoch": 12.13, "learning_rate": 0.00026400152657189203, "loss": 1.7152, "step": 58570 }, { "epoch": 12.13, "learning_rate": 0.0002639061158286423, "loss": 1.7139, "step": 58575 }, { "epoch": 12.14, "learning_rate": 0.00026381070508539264, "loss": 1.709, "step": 58580 }, { "epoch": 12.14, "learning_rate": 0.0002637152943421429, "loss": 1.7114, "step": 58585 }, { "epoch": 12.14, "learning_rate": 0.0002636198835988932, "loss": 1.7143, "step": 58590 }, { "epoch": 12.14, "learning_rate": 0.0002635244728556436, "loss": 1.7125, "step": 58595 }, { "epoch": 12.14, "learning_rate": 0.00026342906211239387, "loss": 1.7124, "step": 58600 }, { "epoch": 12.14, "learning_rate": 0.00026333365136914415, "loss": 1.7097, "step": 58605 }, { "epoch": 12.14, "learning_rate": 0.0002632382406258945, "loss": 1.7136, "step": 58610 }, { "epoch": 12.14, "learning_rate": 0.0002631428298826448, "loss": 1.7121, "step": 58615 }, { "epoch": 12.14, "learning_rate": 0.0002630474191393951, "loss": 1.7117, "step": 58620 }, { "epoch": 12.15, "learning_rate": 0.00026295200839614543, "loss": 1.7116, "step": 58625 }, { "epoch": 12.15, "learning_rate": 0.0002628565976528957, "loss": 1.7093, "step": 58630 }, { "epoch": 12.15, "learning_rate": 0.000262761186909646, "loss": 1.7103, "step": 58635 }, { "epoch": 12.15, "learning_rate": 0.0002626657761663964, "loss": 1.714, "step": 58640 }, { "epoch": 12.15, "learning_rate": 0.00026257036542314666, "loss": 1.705, "step": 58645 }, { "epoch": 12.15, "learning_rate": 0.00026247495467989694, "loss": 1.7089, "step": 58650 }, { "epoch": 12.15, "learning_rate": 0.0002623795439366473, "loss": 1.7091, "step": 58655 }, { "epoch": 12.15, "learning_rate": 0.00026228413319339755, "loss": 1.7118, "step": 58660 }, { "epoch": 12.15, "learning_rate": 0.0002621887224501479, "loss": 1.7109, "step": 58665 }, { "epoch": 12.15, "learning_rate": 0.0002620933117068982, "loss": 1.7138, "step": 58670 }, { "epoch": 12.16, "learning_rate": 0.0002619979009636485, "loss": 1.7096, "step": 58675 }, { "epoch": 12.16, "learning_rate": 0.0002619024902203988, "loss": 1.7123, "step": 58680 }, { "epoch": 12.16, "learning_rate": 0.00026180707947714917, "loss": 1.7079, "step": 58685 }, { "epoch": 12.16, "learning_rate": 0.00026171166873389945, "loss": 1.7156, "step": 58690 }, { "epoch": 12.16, "learning_rate": 0.00026161625799064973, "loss": 1.7137, "step": 58695 }, { "epoch": 12.16, "learning_rate": 0.00026152084724740006, "loss": 1.7109, "step": 58700 }, { "epoch": 12.16, "learning_rate": 0.00026142543650415034, "loss": 1.7112, "step": 58705 }, { "epoch": 12.16, "learning_rate": 0.0002613300257609007, "loss": 1.7102, "step": 58710 }, { "epoch": 12.16, "learning_rate": 0.000261234615017651, "loss": 1.7081, "step": 58715 }, { "epoch": 12.16, "learning_rate": 0.0002611392042744013, "loss": 1.7162, "step": 58720 }, { "epoch": 12.17, "learning_rate": 0.0002610437935311516, "loss": 1.7117, "step": 58725 }, { "epoch": 12.17, "learning_rate": 0.00026094838278790196, "loss": 1.709, "step": 58730 }, { "epoch": 12.17, "learning_rate": 0.00026085297204465224, "loss": 1.7079, "step": 58735 }, { "epoch": 12.17, "learning_rate": 0.00026075756130140257, "loss": 1.7157, "step": 58740 }, { "epoch": 12.17, "learning_rate": 0.00026066215055815285, "loss": 1.7113, "step": 58745 }, { "epoch": 12.17, "learning_rate": 0.00026056673981490313, "loss": 1.7116, "step": 58750 }, { "epoch": 12.17, "learning_rate": 0.0002604713290716535, "loss": 1.708, "step": 58755 }, { "epoch": 12.17, "learning_rate": 0.0002603759183284038, "loss": 1.7124, "step": 58760 }, { "epoch": 12.17, "learning_rate": 0.0002602805075851541, "loss": 1.7047, "step": 58765 }, { "epoch": 12.18, "learning_rate": 0.0002601850968419044, "loss": 1.7119, "step": 58770 }, { "epoch": 12.18, "learning_rate": 0.0002600896860986547, "loss": 1.7131, "step": 58775 }, { "epoch": 12.18, "learning_rate": 0.000259994275355405, "loss": 1.7087, "step": 58780 }, { "epoch": 12.18, "learning_rate": 0.00025989886461215536, "loss": 1.7097, "step": 58785 }, { "epoch": 12.18, "learning_rate": 0.00025980345386890564, "loss": 1.7153, "step": 58790 }, { "epoch": 12.18, "learning_rate": 0.0002597080431256559, "loss": 1.7112, "step": 58795 }, { "epoch": 12.18, "learning_rate": 0.0002596126323824063, "loss": 1.7125, "step": 58800 }, { "epoch": 12.18, "learning_rate": 0.0002595172216391566, "loss": 1.7111, "step": 58805 }, { "epoch": 12.18, "learning_rate": 0.00025942181089590687, "loss": 1.7079, "step": 58810 }, { "epoch": 12.18, "learning_rate": 0.0002593264001526572, "loss": 1.7069, "step": 58815 }, { "epoch": 12.19, "learning_rate": 0.0002592309894094075, "loss": 1.7147, "step": 58820 }, { "epoch": 12.19, "learning_rate": 0.0002591355786661578, "loss": 1.7122, "step": 58825 }, { "epoch": 12.19, "learning_rate": 0.00025904016792290815, "loss": 1.7122, "step": 58830 }, { "epoch": 12.19, "learning_rate": 0.00025894475717965843, "loss": 1.7162, "step": 58835 }, { "epoch": 12.19, "learning_rate": 0.0002588493464364087, "loss": 1.7059, "step": 58840 }, { "epoch": 12.19, "learning_rate": 0.0002587539356931591, "loss": 1.7101, "step": 58845 }, { "epoch": 12.19, "learning_rate": 0.0002586585249499094, "loss": 1.7116, "step": 58850 }, { "epoch": 12.19, "learning_rate": 0.00025856311420665966, "loss": 1.7112, "step": 58855 }, { "epoch": 12.19, "learning_rate": 0.00025846770346341, "loss": 1.712, "step": 58860 }, { "epoch": 12.19, "learning_rate": 0.00025837229272016027, "loss": 1.7101, "step": 58865 }, { "epoch": 12.2, "learning_rate": 0.0002582768819769106, "loss": 1.7124, "step": 58870 }, { "epoch": 12.2, "learning_rate": 0.00025818147123366094, "loss": 1.7096, "step": 58875 }, { "epoch": 12.2, "learning_rate": 0.0002580860604904112, "loss": 1.709, "step": 58880 }, { "epoch": 12.2, "learning_rate": 0.0002579906497471615, "loss": 1.7138, "step": 58885 }, { "epoch": 12.2, "learning_rate": 0.00025789523900391183, "loss": 1.708, "step": 58890 }, { "epoch": 12.2, "learning_rate": 0.00025779982826066217, "loss": 1.7129, "step": 58895 }, { "epoch": 12.2, "learning_rate": 0.00025770441751741245, "loss": 1.7078, "step": 58900 }, { "epoch": 12.2, "learning_rate": 0.0002576090067741628, "loss": 1.7119, "step": 58905 }, { "epoch": 12.2, "learning_rate": 0.00025751359603091306, "loss": 1.7093, "step": 58910 }, { "epoch": 12.21, "learning_rate": 0.0002574181852876634, "loss": 1.7138, "step": 58915 }, { "epoch": 12.21, "learning_rate": 0.00025732277454441373, "loss": 1.7121, "step": 58920 }, { "epoch": 12.21, "learning_rate": 0.000257227363801164, "loss": 1.7129, "step": 58925 }, { "epoch": 12.21, "learning_rate": 0.0002571319530579143, "loss": 1.7131, "step": 58930 }, { "epoch": 12.21, "learning_rate": 0.0002570365423146646, "loss": 1.7074, "step": 58935 }, { "epoch": 12.21, "learning_rate": 0.00025694113157141496, "loss": 1.7084, "step": 58940 }, { "epoch": 12.21, "learning_rate": 0.0002568457208281653, "loss": 1.7083, "step": 58945 }, { "epoch": 12.21, "learning_rate": 0.00025675031008491557, "loss": 1.7094, "step": 58950 }, { "epoch": 12.21, "learning_rate": 0.00025665489934166585, "loss": 1.7159, "step": 58955 }, { "epoch": 12.21, "learning_rate": 0.00025655948859841624, "loss": 1.7089, "step": 58960 }, { "epoch": 12.22, "learning_rate": 0.0002564640778551665, "loss": 1.708, "step": 58965 }, { "epoch": 12.22, "learning_rate": 0.0002563686671119168, "loss": 1.7098, "step": 58970 }, { "epoch": 12.22, "learning_rate": 0.00025627325636866713, "loss": 1.7087, "step": 58975 }, { "epoch": 12.22, "learning_rate": 0.0002561778456254174, "loss": 1.7146, "step": 58980 }, { "epoch": 12.22, "learning_rate": 0.00025608243488216774, "loss": 1.7104, "step": 58985 }, { "epoch": 12.22, "learning_rate": 0.0002559870241389181, "loss": 1.7113, "step": 58990 }, { "epoch": 12.22, "learning_rate": 0.00025589161339566836, "loss": 1.7133, "step": 58995 }, { "epoch": 12.22, "learning_rate": 0.00025579620265241864, "loss": 1.7126, "step": 59000 }, { "epoch": 12.22, "learning_rate": 0.00025570079190916897, "loss": 1.7049, "step": 59005 }, { "epoch": 12.22, "learning_rate": 0.0002556053811659193, "loss": 1.7114, "step": 59010 }, { "epoch": 12.23, "learning_rate": 0.0002555099704226696, "loss": 1.7169, "step": 59015 }, { "epoch": 12.23, "learning_rate": 0.0002554145596794199, "loss": 1.7076, "step": 59020 }, { "epoch": 12.23, "learning_rate": 0.0002553191489361702, "loss": 1.7131, "step": 59025 }, { "epoch": 12.23, "learning_rate": 0.00025522373819292053, "loss": 1.7136, "step": 59030 }, { "epoch": 12.23, "learning_rate": 0.00025512832744967087, "loss": 1.7167, "step": 59035 }, { "epoch": 12.23, "learning_rate": 0.00025503291670642115, "loss": 1.7111, "step": 59040 }, { "epoch": 12.23, "learning_rate": 0.00025493750596317143, "loss": 1.7125, "step": 59045 }, { "epoch": 12.23, "learning_rate": 0.00025484209521992176, "loss": 1.7149, "step": 59050 }, { "epoch": 12.23, "learning_rate": 0.0002547466844766721, "loss": 1.7143, "step": 59055 }, { "epoch": 12.24, "learning_rate": 0.0002546512737334224, "loss": 1.7117, "step": 59060 }, { "epoch": 12.24, "learning_rate": 0.0002545558629901727, "loss": 1.7151, "step": 59065 }, { "epoch": 12.24, "learning_rate": 0.000254460452246923, "loss": 1.7171, "step": 59070 }, { "epoch": 12.24, "learning_rate": 0.0002543650415036733, "loss": 1.7115, "step": 59075 }, { "epoch": 12.24, "learning_rate": 0.00025426963076042366, "loss": 1.7188, "step": 59080 }, { "epoch": 12.24, "learning_rate": 0.00025417422001717394, "loss": 1.7132, "step": 59085 }, { "epoch": 12.24, "learning_rate": 0.0002540788092739242, "loss": 1.7077, "step": 59090 }, { "epoch": 12.24, "learning_rate": 0.00025398339853067455, "loss": 1.7107, "step": 59095 }, { "epoch": 12.24, "learning_rate": 0.0002538879877874249, "loss": 1.7122, "step": 59100 }, { "epoch": 12.24, "learning_rate": 0.00025379257704417516, "loss": 1.7119, "step": 59105 }, { "epoch": 12.25, "learning_rate": 0.0002536971663009255, "loss": 1.7112, "step": 59110 }, { "epoch": 12.25, "learning_rate": 0.0002536017555576758, "loss": 1.7102, "step": 59115 }, { "epoch": 12.25, "learning_rate": 0.00025350634481442606, "loss": 1.7076, "step": 59120 }, { "epoch": 12.25, "learning_rate": 0.00025341093407117645, "loss": 1.7145, "step": 59125 }, { "epoch": 12.25, "learning_rate": 0.0002533155233279267, "loss": 1.7135, "step": 59130 }, { "epoch": 12.25, "learning_rate": 0.000253220112584677, "loss": 1.7112, "step": 59135 }, { "epoch": 12.25, "learning_rate": 0.00025312470184142734, "loss": 1.7107, "step": 59140 }, { "epoch": 12.25, "learning_rate": 0.0002530292910981777, "loss": 1.7137, "step": 59145 }, { "epoch": 12.25, "learning_rate": 0.000252933880354928, "loss": 1.7176, "step": 59150 }, { "epoch": 12.26, "learning_rate": 0.0002528384696116783, "loss": 1.7126, "step": 59155 }, { "epoch": 12.26, "learning_rate": 0.00025274305886842857, "loss": 1.7055, "step": 59160 }, { "epoch": 12.26, "learning_rate": 0.0002526476481251789, "loss": 1.7106, "step": 59165 }, { "epoch": 12.26, "learning_rate": 0.00025255223738192923, "loss": 1.7127, "step": 59170 }, { "epoch": 12.26, "learning_rate": 0.0002524568266386795, "loss": 1.7112, "step": 59175 }, { "epoch": 12.26, "learning_rate": 0.00025236141589542985, "loss": 1.7089, "step": 59180 }, { "epoch": 12.26, "learning_rate": 0.00025226600515218013, "loss": 1.7107, "step": 59185 }, { "epoch": 12.26, "learning_rate": 0.00025217059440893046, "loss": 1.7113, "step": 59190 }, { "epoch": 12.26, "learning_rate": 0.0002520751836656808, "loss": 1.7122, "step": 59195 }, { "epoch": 12.26, "learning_rate": 0.0002519797729224311, "loss": 1.7103, "step": 59200 }, { "epoch": 12.27, "learning_rate": 0.00025188436217918136, "loss": 1.7138, "step": 59205 }, { "epoch": 12.27, "learning_rate": 0.0002517889514359317, "loss": 1.7099, "step": 59210 }, { "epoch": 12.27, "learning_rate": 0.000251693540692682, "loss": 1.7108, "step": 59215 }, { "epoch": 12.27, "learning_rate": 0.0002515981299494323, "loss": 1.7119, "step": 59220 }, { "epoch": 12.27, "learning_rate": 0.00025150271920618264, "loss": 1.7056, "step": 59225 }, { "epoch": 12.27, "learning_rate": 0.0002514073084629329, "loss": 1.7055, "step": 59230 }, { "epoch": 12.27, "learning_rate": 0.00025131189771968325, "loss": 1.7093, "step": 59235 }, { "epoch": 12.27, "learning_rate": 0.0002512164869764336, "loss": 1.712, "step": 59240 }, { "epoch": 12.27, "learning_rate": 0.00025112107623318387, "loss": 1.7135, "step": 59245 }, { "epoch": 12.27, "learning_rate": 0.00025102566548993415, "loss": 1.7122, "step": 59250 }, { "epoch": 12.28, "learning_rate": 0.0002509302547466845, "loss": 1.7135, "step": 59255 }, { "epoch": 12.28, "learning_rate": 0.0002508348440034348, "loss": 1.7108, "step": 59260 }, { "epoch": 12.28, "learning_rate": 0.0002507394332601851, "loss": 1.7148, "step": 59265 }, { "epoch": 12.28, "learning_rate": 0.0002506440225169354, "loss": 1.7128, "step": 59270 }, { "epoch": 12.28, "learning_rate": 0.0002505486117736857, "loss": 1.7126, "step": 59275 }, { "epoch": 12.28, "learning_rate": 0.000250453201030436, "loss": 1.7116, "step": 59280 }, { "epoch": 12.28, "learning_rate": 0.0002503577902871864, "loss": 1.7102, "step": 59285 }, { "epoch": 12.28, "learning_rate": 0.00025026237954393665, "loss": 1.7104, "step": 59290 }, { "epoch": 12.28, "learning_rate": 0.00025016696880068693, "loss": 1.7108, "step": 59295 }, { "epoch": 12.29, "learning_rate": 0.00025007155805743727, "loss": 1.713, "step": 59300 }, { "epoch": 12.29, "learning_rate": 0.0002499761473141876, "loss": 1.714, "step": 59305 }, { "epoch": 12.29, "learning_rate": 0.0002498807365709379, "loss": 1.706, "step": 59310 }, { "epoch": 12.29, "learning_rate": 0.0002497853258276882, "loss": 1.7079, "step": 59315 }, { "epoch": 12.29, "learning_rate": 0.0002496899150844385, "loss": 1.7157, "step": 59320 }, { "epoch": 12.29, "learning_rate": 0.00024959450434118883, "loss": 1.7141, "step": 59325 }, { "epoch": 12.29, "learning_rate": 0.0002494990935979391, "loss": 1.7121, "step": 59330 }, { "epoch": 12.29, "learning_rate": 0.00024940368285468944, "loss": 1.7102, "step": 59335 }, { "epoch": 12.29, "learning_rate": 0.0002493082721114397, "loss": 1.711, "step": 59340 }, { "epoch": 12.29, "learning_rate": 0.00024921286136819006, "loss": 1.712, "step": 59345 }, { "epoch": 12.3, "learning_rate": 0.0002491174506249404, "loss": 1.7134, "step": 59350 }, { "epoch": 12.3, "learning_rate": 0.00024902203988169067, "loss": 1.7095, "step": 59355 }, { "epoch": 12.3, "learning_rate": 0.000248926629138441, "loss": 1.7096, "step": 59360 }, { "epoch": 12.3, "learning_rate": 0.0002488312183951913, "loss": 1.7142, "step": 59365 }, { "epoch": 12.3, "learning_rate": 0.0002487358076519416, "loss": 1.7134, "step": 59370 }, { "epoch": 12.3, "learning_rate": 0.0002486403969086919, "loss": 1.7076, "step": 59375 }, { "epoch": 12.3, "learning_rate": 0.00024854498616544223, "loss": 1.711, "step": 59380 }, { "epoch": 12.3, "learning_rate": 0.00024844957542219257, "loss": 1.711, "step": 59385 }, { "epoch": 12.3, "learning_rate": 0.00024835416467894285, "loss": 1.7113, "step": 59390 }, { "epoch": 12.3, "learning_rate": 0.0002482587539356932, "loss": 1.7133, "step": 59395 }, { "epoch": 12.31, "learning_rate": 0.00024816334319244346, "loss": 1.709, "step": 59400 }, { "epoch": 12.31, "learning_rate": 0.0002480679324491938, "loss": 1.7113, "step": 59405 }, { "epoch": 12.31, "learning_rate": 0.0002479725217059441, "loss": 1.7154, "step": 59410 }, { "epoch": 12.31, "learning_rate": 0.0002478771109626944, "loss": 1.7137, "step": 59415 }, { "epoch": 12.31, "learning_rate": 0.0002477817002194447, "loss": 1.7146, "step": 59420 }, { "epoch": 12.31, "learning_rate": 0.000247686289476195, "loss": 1.7201, "step": 59425 }, { "epoch": 12.31, "learning_rate": 0.00024759087873294536, "loss": 1.71, "step": 59430 }, { "epoch": 12.31, "learning_rate": 0.00024749546798969564, "loss": 1.7131, "step": 59435 }, { "epoch": 12.31, "learning_rate": 0.00024740005724644597, "loss": 1.7132, "step": 59440 }, { "epoch": 12.32, "learning_rate": 0.00024730464650319625, "loss": 1.7123, "step": 59445 }, { "epoch": 12.32, "learning_rate": 0.0002472092357599466, "loss": 1.7102, "step": 59450 }, { "epoch": 12.32, "learning_rate": 0.00024711382501669686, "loss": 1.711, "step": 59455 }, { "epoch": 12.32, "learning_rate": 0.0002470184142734472, "loss": 1.709, "step": 59460 }, { "epoch": 12.32, "learning_rate": 0.00024692300353019753, "loss": 1.7102, "step": 59465 }, { "epoch": 12.32, "learning_rate": 0.0002468275927869478, "loss": 1.711, "step": 59470 }, { "epoch": 12.32, "learning_rate": 0.00024673218204369814, "loss": 1.7116, "step": 59475 }, { "epoch": 12.32, "learning_rate": 0.0002466367713004484, "loss": 1.7155, "step": 59480 }, { "epoch": 12.32, "learning_rate": 0.00024654136055719876, "loss": 1.7104, "step": 59485 }, { "epoch": 12.32, "learning_rate": 0.00024644594981394904, "loss": 1.7134, "step": 59490 }, { "epoch": 12.33, "learning_rate": 0.00024635053907069937, "loss": 1.7132, "step": 59495 }, { "epoch": 12.33, "learning_rate": 0.00024625512832744965, "loss": 1.7111, "step": 59500 }, { "epoch": 12.33, "learning_rate": 0.0002461597175842, "loss": 1.7179, "step": 59505 }, { "epoch": 12.33, "learning_rate": 0.0002460643068409503, "loss": 1.7073, "step": 59510 }, { "epoch": 12.33, "learning_rate": 0.0002459688960977006, "loss": 1.7126, "step": 59515 }, { "epoch": 12.33, "learning_rate": 0.00024587348535445093, "loss": 1.7099, "step": 59520 }, { "epoch": 12.33, "learning_rate": 0.0002457780746112012, "loss": 1.7094, "step": 59525 }, { "epoch": 12.33, "learning_rate": 0.00024568266386795155, "loss": 1.7125, "step": 59530 }, { "epoch": 12.33, "learning_rate": 0.00024558725312470183, "loss": 1.7101, "step": 59535 }, { "epoch": 12.33, "learning_rate": 0.00024549184238145216, "loss": 1.7119, "step": 59540 }, { "epoch": 12.34, "learning_rate": 0.00024539643163820244, "loss": 1.7173, "step": 59545 }, { "epoch": 12.34, "learning_rate": 0.0002453010208949528, "loss": 1.7084, "step": 59550 }, { "epoch": 12.34, "learning_rate": 0.0002452056101517031, "loss": 1.7114, "step": 59555 }, { "epoch": 12.34, "learning_rate": 0.0002451101994084534, "loss": 1.712, "step": 59560 }, { "epoch": 12.34, "learning_rate": 0.0002450147886652037, "loss": 1.7153, "step": 59565 }, { "epoch": 12.34, "learning_rate": 0.000244919377921954, "loss": 1.7174, "step": 59570 }, { "epoch": 12.34, "learning_rate": 0.00024482396717870434, "loss": 1.7108, "step": 59575 }, { "epoch": 12.34, "learning_rate": 0.0002447285564354546, "loss": 1.7136, "step": 59580 }, { "epoch": 12.34, "learning_rate": 0.00024463314569220495, "loss": 1.7105, "step": 59585 }, { "epoch": 12.35, "learning_rate": 0.0002445377349489553, "loss": 1.713, "step": 59590 }, { "epoch": 12.35, "learning_rate": 0.00024444232420570556, "loss": 1.7149, "step": 59595 }, { "epoch": 12.35, "learning_rate": 0.0002443469134624559, "loss": 1.7137, "step": 59600 }, { "epoch": 12.35, "learning_rate": 0.0002442515027192062, "loss": 1.7081, "step": 59605 }, { "epoch": 12.35, "learning_rate": 0.0002441560919759565, "loss": 1.7144, "step": 59610 }, { "epoch": 12.35, "learning_rate": 0.0002440606812327068, "loss": 1.713, "step": 59615 }, { "epoch": 12.35, "learning_rate": 0.00024396527048945713, "loss": 1.7111, "step": 59620 }, { "epoch": 12.35, "learning_rate": 0.00024386985974620743, "loss": 1.7082, "step": 59625 }, { "epoch": 12.35, "learning_rate": 0.00024377444900295774, "loss": 1.713, "step": 59630 }, { "epoch": 12.35, "learning_rate": 0.00024367903825970805, "loss": 1.7139, "step": 59635 }, { "epoch": 12.36, "learning_rate": 0.00024358362751645835, "loss": 1.7194, "step": 59640 }, { "epoch": 12.36, "learning_rate": 0.0002434882167732087, "loss": 1.7163, "step": 59645 }, { "epoch": 12.36, "learning_rate": 0.00024339280602995897, "loss": 1.7126, "step": 59650 }, { "epoch": 12.36, "learning_rate": 0.0002432973952867093, "loss": 1.7102, "step": 59655 }, { "epoch": 12.36, "learning_rate": 0.0002432019845434596, "loss": 1.7185, "step": 59660 }, { "epoch": 12.36, "learning_rate": 0.0002431065738002099, "loss": 1.7096, "step": 59665 }, { "epoch": 12.36, "learning_rate": 0.00024301116305696022, "loss": 1.7155, "step": 59670 }, { "epoch": 12.36, "learning_rate": 0.00024291575231371053, "loss": 1.7125, "step": 59675 }, { "epoch": 12.36, "learning_rate": 0.00024282034157046084, "loss": 1.7146, "step": 59680 }, { "epoch": 12.36, "learning_rate": 0.00024272493082721114, "loss": 1.7095, "step": 59685 }, { "epoch": 12.37, "learning_rate": 0.00024262952008396148, "loss": 1.7076, "step": 59690 }, { "epoch": 12.37, "learning_rate": 0.00024253410934071176, "loss": 1.711, "step": 59695 }, { "epoch": 12.37, "learning_rate": 0.0002424386985974621, "loss": 1.7181, "step": 59700 }, { "epoch": 12.37, "learning_rate": 0.0002423432878542124, "loss": 1.7187, "step": 59705 }, { "epoch": 12.37, "learning_rate": 0.00024224787711096268, "loss": 1.7101, "step": 59710 }, { "epoch": 12.37, "learning_rate": 0.000242152466367713, "loss": 1.711, "step": 59715 }, { "epoch": 12.37, "learning_rate": 0.00024205705562446332, "loss": 1.7107, "step": 59720 }, { "epoch": 12.37, "learning_rate": 0.00024196164488121362, "loss": 1.7118, "step": 59725 }, { "epoch": 12.37, "learning_rate": 0.00024186623413796393, "loss": 1.7086, "step": 59730 }, { "epoch": 12.38, "learning_rate": 0.00024177082339471427, "loss": 1.7137, "step": 59735 }, { "epoch": 12.38, "learning_rate": 0.00024167541265146457, "loss": 1.716, "step": 59740 }, { "epoch": 12.38, "learning_rate": 0.00024158000190821485, "loss": 1.7158, "step": 59745 }, { "epoch": 12.38, "learning_rate": 0.00024148459116496519, "loss": 1.7097, "step": 59750 }, { "epoch": 12.38, "learning_rate": 0.0002413891804217155, "loss": 1.7132, "step": 59755 }, { "epoch": 12.38, "learning_rate": 0.0002412937696784658, "loss": 1.7068, "step": 59760 }, { "epoch": 12.38, "learning_rate": 0.0002411983589352161, "loss": 1.7114, "step": 59765 }, { "epoch": 12.38, "learning_rate": 0.00024110294819196644, "loss": 1.7086, "step": 59770 }, { "epoch": 12.38, "learning_rate": 0.00024100753744871672, "loss": 1.7112, "step": 59775 }, { "epoch": 12.38, "learning_rate": 0.00024091212670546703, "loss": 1.7132, "step": 59780 }, { "epoch": 12.39, "learning_rate": 0.00024081671596221736, "loss": 1.7111, "step": 59785 }, { "epoch": 12.39, "learning_rate": 0.00024072130521896764, "loss": 1.7113, "step": 59790 }, { "epoch": 12.39, "learning_rate": 0.00024062589447571798, "loss": 1.7137, "step": 59795 }, { "epoch": 12.39, "learning_rate": 0.00024053048373246828, "loss": 1.7119, "step": 59800 }, { "epoch": 12.39, "learning_rate": 0.0002404350729892186, "loss": 1.7135, "step": 59805 }, { "epoch": 12.39, "learning_rate": 0.0002403396622459689, "loss": 1.7088, "step": 59810 }, { "epoch": 12.39, "learning_rate": 0.00024024425150271923, "loss": 1.7124, "step": 59815 }, { "epoch": 12.39, "learning_rate": 0.0002401488407594695, "loss": 1.7132, "step": 59820 }, { "epoch": 12.39, "learning_rate": 0.00024005343001621982, "loss": 1.7132, "step": 59825 }, { "epoch": 12.39, "learning_rate": 0.00023995801927297015, "loss": 1.7119, "step": 59830 }, { "epoch": 12.4, "learning_rate": 0.00023986260852972043, "loss": 1.7126, "step": 59835 }, { "epoch": 12.4, "learning_rate": 0.00023976719778647076, "loss": 1.7123, "step": 59840 }, { "epoch": 12.4, "learning_rate": 0.00023967178704322107, "loss": 1.7142, "step": 59845 }, { "epoch": 12.4, "learning_rate": 0.0002395763762999714, "loss": 1.7114, "step": 59850 }, { "epoch": 12.4, "learning_rate": 0.00023948096555672169, "loss": 1.7117, "step": 59855 }, { "epoch": 12.4, "learning_rate": 0.000239385554813472, "loss": 1.7112, "step": 59860 }, { "epoch": 12.4, "learning_rate": 0.00023929014407022233, "loss": 1.7075, "step": 59865 }, { "epoch": 12.4, "learning_rate": 0.0002391947333269726, "loss": 1.7124, "step": 59870 }, { "epoch": 12.4, "learning_rate": 0.00023909932258372294, "loss": 1.7082, "step": 59875 }, { "epoch": 12.41, "learning_rate": 0.00023900391184047325, "loss": 1.7109, "step": 59880 }, { "epoch": 12.41, "learning_rate": 0.00023890850109722355, "loss": 1.7103, "step": 59885 }, { "epoch": 12.41, "learning_rate": 0.00023881309035397386, "loss": 1.7181, "step": 59890 }, { "epoch": 12.41, "learning_rate": 0.00023871767961072417, "loss": 1.7095, "step": 59895 }, { "epoch": 12.41, "learning_rate": 0.00023862226886747447, "loss": 1.7132, "step": 59900 }, { "epoch": 12.41, "learning_rate": 0.00023852685812422478, "loss": 1.7093, "step": 59905 }, { "epoch": 12.41, "learning_rate": 0.00023843144738097512, "loss": 1.7098, "step": 59910 }, { "epoch": 12.41, "learning_rate": 0.0002383360366377254, "loss": 1.7078, "step": 59915 }, { "epoch": 12.41, "learning_rate": 0.00023824062589447573, "loss": 1.7127, "step": 59920 }, { "epoch": 12.41, "learning_rate": 0.00023814521515122604, "loss": 1.7083, "step": 59925 }, { "epoch": 12.42, "learning_rate": 0.00023804980440797634, "loss": 1.7117, "step": 59930 }, { "epoch": 12.42, "learning_rate": 0.00023795439366472665, "loss": 1.716, "step": 59935 }, { "epoch": 12.42, "learning_rate": 0.00023785898292147696, "loss": 1.7198, "step": 59940 }, { "epoch": 12.42, "learning_rate": 0.0002377635721782273, "loss": 1.7103, "step": 59945 }, { "epoch": 12.42, "learning_rate": 0.00023766816143497757, "loss": 1.7168, "step": 59950 }, { "epoch": 12.42, "learning_rate": 0.0002375727506917279, "loss": 1.7136, "step": 59955 }, { "epoch": 12.42, "learning_rate": 0.0002374773399484782, "loss": 1.7141, "step": 59960 }, { "epoch": 12.42, "learning_rate": 0.00023738192920522852, "loss": 1.707, "step": 59965 }, { "epoch": 12.42, "learning_rate": 0.00023728651846197883, "loss": 1.7175, "step": 59970 }, { "epoch": 12.42, "learning_rate": 0.00023719110771872913, "loss": 1.7069, "step": 59975 }, { "epoch": 12.43, "learning_rate": 0.00023709569697547944, "loss": 1.7113, "step": 59980 }, { "epoch": 12.43, "learning_rate": 0.00023700028623222975, "loss": 1.7066, "step": 59985 }, { "epoch": 12.43, "learning_rate": 0.00023690487548898008, "loss": 1.711, "step": 59990 }, { "epoch": 12.43, "learning_rate": 0.00023680946474573036, "loss": 1.7065, "step": 59995 }, { "epoch": 12.43, "learning_rate": 0.0002367140540024807, "loss": 1.7072, "step": 60000 }, { "epoch": 12.43, "eval_accuracy": 0.5464836601307189, "eval_loss": 1.9051240682601929, "eval_runtime": 0.5071, "eval_samples_per_second": 295.819, "eval_steps_per_second": 1.972, "step": 60000 }, { "epoch": 12.43, "learning_rate": 0.000236618643259231, "loss": 1.7116, "step": 60005 }, { "epoch": 12.43, "learning_rate": 0.0002365232325159813, "loss": 1.7145, "step": 60010 }, { "epoch": 12.43, "learning_rate": 0.00023642782177273161, "loss": 1.7133, "step": 60015 }, { "epoch": 12.43, "learning_rate": 0.00023633241102948192, "loss": 1.7146, "step": 60020 }, { "epoch": 12.44, "learning_rate": 0.00023623700028623223, "loss": 1.7142, "step": 60025 }, { "epoch": 12.44, "learning_rate": 0.00023614158954298253, "loss": 1.713, "step": 60030 }, { "epoch": 12.44, "learning_rate": 0.00023604617879973287, "loss": 1.7066, "step": 60035 }, { "epoch": 12.44, "learning_rate": 0.00023595076805648315, "loss": 1.7139, "step": 60040 }, { "epoch": 12.44, "learning_rate": 0.00023585535731323348, "loss": 1.7081, "step": 60045 }, { "epoch": 12.44, "learning_rate": 0.0002357599465699838, "loss": 1.7106, "step": 60050 }, { "epoch": 12.44, "learning_rate": 0.0002356645358267341, "loss": 1.7086, "step": 60055 }, { "epoch": 12.44, "learning_rate": 0.0002355691250834844, "loss": 1.7133, "step": 60060 }, { "epoch": 12.44, "learning_rate": 0.0002354737143402347, "loss": 1.7106, "step": 60065 }, { "epoch": 12.44, "learning_rate": 0.00023537830359698504, "loss": 1.7096, "step": 60070 }, { "epoch": 12.45, "learning_rate": 0.00023528289285373532, "loss": 1.711, "step": 60075 }, { "epoch": 12.45, "learning_rate": 0.00023518748211048566, "loss": 1.7133, "step": 60080 }, { "epoch": 12.45, "learning_rate": 0.00023509207136723596, "loss": 1.7146, "step": 60085 }, { "epoch": 12.45, "learning_rate": 0.00023499666062398624, "loss": 1.7109, "step": 60090 }, { "epoch": 12.45, "learning_rate": 0.00023490124988073658, "loss": 1.7099, "step": 60095 }, { "epoch": 12.45, "learning_rate": 0.00023480583913748689, "loss": 1.7095, "step": 60100 }, { "epoch": 12.45, "learning_rate": 0.0002347104283942372, "loss": 1.7116, "step": 60105 }, { "epoch": 12.45, "learning_rate": 0.0002346150176509875, "loss": 1.7098, "step": 60110 }, { "epoch": 12.45, "learning_rate": 0.00023451960690773783, "loss": 1.7078, "step": 60115 }, { "epoch": 12.45, "learning_rate": 0.0002344241961644881, "loss": 1.7144, "step": 60120 }, { "epoch": 12.46, "learning_rate": 0.00023432878542123845, "loss": 1.7079, "step": 60125 }, { "epoch": 12.46, "learning_rate": 0.00023423337467798875, "loss": 1.7065, "step": 60130 }, { "epoch": 12.46, "learning_rate": 0.00023413796393473903, "loss": 1.7193, "step": 60135 }, { "epoch": 12.46, "learning_rate": 0.00023404255319148937, "loss": 1.7151, "step": 60140 }, { "epoch": 12.46, "learning_rate": 0.00023394714244823967, "loss": 1.7111, "step": 60145 }, { "epoch": 12.46, "learning_rate": 0.00023385173170498998, "loss": 1.7138, "step": 60150 }, { "epoch": 12.46, "learning_rate": 0.0002337563209617403, "loss": 1.7105, "step": 60155 }, { "epoch": 12.46, "learning_rate": 0.00023366091021849062, "loss": 1.7112, "step": 60160 }, { "epoch": 12.46, "learning_rate": 0.00023356549947524093, "loss": 1.7106, "step": 60165 }, { "epoch": 12.47, "learning_rate": 0.0002334700887319912, "loss": 1.7146, "step": 60170 }, { "epoch": 12.47, "learning_rate": 0.00023337467798874154, "loss": 1.7105, "step": 60175 }, { "epoch": 12.47, "learning_rate": 0.00023327926724549185, "loss": 1.7162, "step": 60180 }, { "epoch": 12.47, "learning_rate": 0.00023318385650224216, "loss": 1.7169, "step": 60185 }, { "epoch": 12.47, "learning_rate": 0.00023308844575899246, "loss": 1.7101, "step": 60190 }, { "epoch": 12.47, "learning_rate": 0.0002329930350157428, "loss": 1.7146, "step": 60195 }, { "epoch": 12.47, "learning_rate": 0.00023289762427249308, "loss": 1.7103, "step": 60200 }, { "epoch": 12.47, "learning_rate": 0.00023280221352924338, "loss": 1.7105, "step": 60205 }, { "epoch": 12.47, "learning_rate": 0.00023270680278599372, "loss": 1.7125, "step": 60210 }, { "epoch": 12.47, "learning_rate": 0.000232611392042744, "loss": 1.7122, "step": 60215 }, { "epoch": 12.48, "learning_rate": 0.00023251598129949433, "loss": 1.7129, "step": 60220 }, { "epoch": 12.48, "learning_rate": 0.00023242057055624464, "loss": 1.7107, "step": 60225 }, { "epoch": 12.48, "learning_rate": 0.00023232515981299495, "loss": 1.7082, "step": 60230 }, { "epoch": 12.48, "learning_rate": 0.00023222974906974525, "loss": 1.7101, "step": 60235 }, { "epoch": 12.48, "learning_rate": 0.0002321343383264956, "loss": 1.7127, "step": 60240 }, { "epoch": 12.48, "learning_rate": 0.00023203892758324587, "loss": 1.7139, "step": 60245 }, { "epoch": 12.48, "learning_rate": 0.00023194351683999617, "loss": 1.7128, "step": 60250 }, { "epoch": 12.48, "learning_rate": 0.0002318481060967465, "loss": 1.7124, "step": 60255 }, { "epoch": 12.48, "learning_rate": 0.0002317526953534968, "loss": 1.7138, "step": 60260 }, { "epoch": 12.48, "learning_rate": 0.00023165728461024712, "loss": 1.713, "step": 60265 }, { "epoch": 12.49, "learning_rate": 0.00023156187386699743, "loss": 1.7175, "step": 60270 }, { "epoch": 12.49, "learning_rate": 0.00023146646312374776, "loss": 1.7093, "step": 60275 }, { "epoch": 12.49, "learning_rate": 0.00023137105238049804, "loss": 1.716, "step": 60280 }, { "epoch": 12.49, "learning_rate": 0.00023127564163724835, "loss": 1.7095, "step": 60285 }, { "epoch": 12.49, "learning_rate": 0.00023118023089399868, "loss": 1.713, "step": 60290 }, { "epoch": 12.49, "learning_rate": 0.00023108482015074896, "loss": 1.7087, "step": 60295 }, { "epoch": 12.49, "learning_rate": 0.0002309894094074993, "loss": 1.7116, "step": 60300 }, { "epoch": 12.49, "learning_rate": 0.0002308939986642496, "loss": 1.7175, "step": 60305 }, { "epoch": 12.49, "learning_rate": 0.0002307985879209999, "loss": 1.7122, "step": 60310 }, { "epoch": 12.5, "learning_rate": 0.00023070317717775022, "loss": 1.7096, "step": 60315 }, { "epoch": 12.5, "learning_rate": 0.00023060776643450055, "loss": 1.7139, "step": 60320 }, { "epoch": 12.5, "learning_rate": 0.00023051235569125083, "loss": 1.7085, "step": 60325 }, { "epoch": 12.5, "learning_rate": 0.00023041694494800114, "loss": 1.7135, "step": 60330 }, { "epoch": 12.5, "learning_rate": 0.00023032153420475147, "loss": 1.715, "step": 60335 }, { "epoch": 12.5, "learning_rate": 0.00023022612346150175, "loss": 1.7081, "step": 60340 }, { "epoch": 12.5, "learning_rate": 0.00023013071271825209, "loss": 1.7163, "step": 60345 }, { "epoch": 12.5, "learning_rate": 0.0002300353019750024, "loss": 1.7092, "step": 60350 }, { "epoch": 12.5, "learning_rate": 0.0002299398912317527, "loss": 1.7124, "step": 60355 }, { "epoch": 12.5, "learning_rate": 0.000229844480488503, "loss": 1.7085, "step": 60360 }, { "epoch": 12.51, "learning_rate": 0.0002297490697452533, "loss": 1.7122, "step": 60365 }, { "epoch": 12.51, "learning_rate": 0.00022965365900200365, "loss": 1.716, "step": 60370 }, { "epoch": 12.51, "learning_rate": 0.00022955824825875393, "loss": 1.7103, "step": 60375 }, { "epoch": 12.51, "learning_rate": 0.00022946283751550426, "loss": 1.7158, "step": 60380 }, { "epoch": 12.51, "learning_rate": 0.00022936742677225457, "loss": 1.7126, "step": 60385 }, { "epoch": 12.51, "learning_rate": 0.00022927201602900487, "loss": 1.7157, "step": 60390 }, { "epoch": 12.51, "learning_rate": 0.00022917660528575518, "loss": 1.7091, "step": 60395 }, { "epoch": 12.51, "learning_rate": 0.0002290811945425055, "loss": 1.7122, "step": 60400 }, { "epoch": 12.51, "learning_rate": 0.0002289857837992558, "loss": 1.7171, "step": 60405 }, { "epoch": 12.52, "learning_rate": 0.0002288903730560061, "loss": 1.7143, "step": 60410 }, { "epoch": 12.52, "learning_rate": 0.00022879496231275644, "loss": 1.7152, "step": 60415 }, { "epoch": 12.52, "learning_rate": 0.00022869955156950672, "loss": 1.7085, "step": 60420 }, { "epoch": 12.52, "learning_rate": 0.00022860414082625705, "loss": 1.7157, "step": 60425 }, { "epoch": 12.52, "learning_rate": 0.00022850873008300736, "loss": 1.7088, "step": 60430 }, { "epoch": 12.52, "learning_rate": 0.00022841331933975766, "loss": 1.7109, "step": 60435 }, { "epoch": 12.52, "learning_rate": 0.00022831790859650797, "loss": 1.7143, "step": 60440 }, { "epoch": 12.52, "learning_rate": 0.00022822249785325828, "loss": 1.7146, "step": 60445 }, { "epoch": 12.52, "learning_rate": 0.00022812708711000858, "loss": 1.7089, "step": 60450 }, { "epoch": 12.52, "learning_rate": 0.0002280316763667589, "loss": 1.7125, "step": 60455 }, { "epoch": 12.53, "learning_rate": 0.00022793626562350923, "loss": 1.7113, "step": 60460 }, { "epoch": 12.53, "learning_rate": 0.0002278408548802595, "loss": 1.7171, "step": 60465 }, { "epoch": 12.53, "learning_rate": 0.00022774544413700984, "loss": 1.7148, "step": 60470 }, { "epoch": 12.53, "learning_rate": 0.00022765003339376015, "loss": 1.7079, "step": 60475 }, { "epoch": 12.53, "learning_rate": 0.00022755462265051045, "loss": 1.707, "step": 60480 }, { "epoch": 12.53, "learning_rate": 0.00022745921190726076, "loss": 1.7062, "step": 60485 }, { "epoch": 12.53, "learning_rate": 0.00022736380116401107, "loss": 1.7088, "step": 60490 }, { "epoch": 12.53, "learning_rate": 0.0002272683904207614, "loss": 1.7085, "step": 60495 }, { "epoch": 12.53, "learning_rate": 0.00022717297967751168, "loss": 1.7166, "step": 60500 }, { "epoch": 12.53, "learning_rate": 0.00022707756893426201, "loss": 1.711, "step": 60505 }, { "epoch": 12.54, "learning_rate": 0.00022698215819101232, "loss": 1.7128, "step": 60510 }, { "epoch": 12.54, "learning_rate": 0.0002268867474477626, "loss": 1.709, "step": 60515 }, { "epoch": 12.54, "learning_rate": 0.00022679133670451294, "loss": 1.7106, "step": 60520 }, { "epoch": 12.54, "learning_rate": 0.00022669592596126324, "loss": 1.7109, "step": 60525 }, { "epoch": 12.54, "learning_rate": 0.00022660051521801355, "loss": 1.7135, "step": 60530 }, { "epoch": 12.54, "learning_rate": 0.00022650510447476386, "loss": 1.7079, "step": 60535 }, { "epoch": 12.54, "learning_rate": 0.0002264096937315142, "loss": 1.7082, "step": 60540 }, { "epoch": 12.54, "learning_rate": 0.00022631428298826447, "loss": 1.711, "step": 60545 }, { "epoch": 12.54, "learning_rate": 0.0002262188722450148, "loss": 1.7131, "step": 60550 }, { "epoch": 12.55, "learning_rate": 0.0002261234615017651, "loss": 1.711, "step": 60555 }, { "epoch": 12.55, "learning_rate": 0.0002260280507585154, "loss": 1.7074, "step": 60560 }, { "epoch": 12.55, "learning_rate": 0.00022593264001526572, "loss": 1.7071, "step": 60565 }, { "epoch": 12.55, "learning_rate": 0.00022583722927201603, "loss": 1.707, "step": 60570 }, { "epoch": 12.55, "learning_rate": 0.00022574181852876637, "loss": 1.7165, "step": 60575 }, { "epoch": 12.55, "learning_rate": 0.00022564640778551665, "loss": 1.7048, "step": 60580 }, { "epoch": 12.55, "learning_rate": 0.00022555099704226698, "loss": 1.7051, "step": 60585 }, { "epoch": 12.55, "learning_rate": 0.00022545558629901729, "loss": 1.7118, "step": 60590 }, { "epoch": 12.55, "learning_rate": 0.00022536017555576757, "loss": 1.709, "step": 60595 }, { "epoch": 12.55, "learning_rate": 0.0002252647648125179, "loss": 1.7124, "step": 60600 }, { "epoch": 12.56, "learning_rate": 0.0002251693540692682, "loss": 1.7097, "step": 60605 }, { "epoch": 12.56, "learning_rate": 0.0002250739433260185, "loss": 1.7103, "step": 60610 }, { "epoch": 12.56, "learning_rate": 0.00022497853258276882, "loss": 1.7074, "step": 60615 }, { "epoch": 12.56, "learning_rate": 0.00022488312183951915, "loss": 1.7139, "step": 60620 }, { "epoch": 12.56, "learning_rate": 0.00022478771109626943, "loss": 1.7101, "step": 60625 }, { "epoch": 12.56, "learning_rate": 0.00022469230035301977, "loss": 1.7137, "step": 60630 }, { "epoch": 12.56, "learning_rate": 0.00022459688960977008, "loss": 1.7081, "step": 60635 }, { "epoch": 12.56, "learning_rate": 0.00022450147886652035, "loss": 1.7134, "step": 60640 }, { "epoch": 12.56, "learning_rate": 0.0002244060681232707, "loss": 1.7122, "step": 60645 }, { "epoch": 12.56, "learning_rate": 0.000224310657380021, "loss": 1.7118, "step": 60650 }, { "epoch": 12.57, "learning_rate": 0.0002242152466367713, "loss": 1.7102, "step": 60655 }, { "epoch": 12.57, "learning_rate": 0.0002241198358935216, "loss": 1.7089, "step": 60660 }, { "epoch": 12.57, "learning_rate": 0.00022402442515027194, "loss": 1.7061, "step": 60665 }, { "epoch": 12.57, "learning_rate": 0.00022392901440702222, "loss": 1.7124, "step": 60670 }, { "epoch": 12.57, "learning_rate": 0.00022383360366377253, "loss": 1.7058, "step": 60675 }, { "epoch": 12.57, "learning_rate": 0.00022373819292052286, "loss": 1.7072, "step": 60680 }, { "epoch": 12.57, "learning_rate": 0.00022364278217727314, "loss": 1.71, "step": 60685 }, { "epoch": 12.57, "learning_rate": 0.00022354737143402348, "loss": 1.7102, "step": 60690 }, { "epoch": 12.57, "learning_rate": 0.00022345196069077378, "loss": 1.7137, "step": 60695 }, { "epoch": 12.58, "learning_rate": 0.00022335654994752412, "loss": 1.7086, "step": 60700 }, { "epoch": 12.58, "learning_rate": 0.0002232611392042744, "loss": 1.7133, "step": 60705 }, { "epoch": 12.58, "learning_rate": 0.0002231657284610247, "loss": 1.7145, "step": 60710 }, { "epoch": 12.58, "learning_rate": 0.00022307031771777504, "loss": 1.7138, "step": 60715 }, { "epoch": 12.58, "learning_rate": 0.00022297490697452532, "loss": 1.7105, "step": 60720 }, { "epoch": 12.58, "learning_rate": 0.00022287949623127565, "loss": 1.7121, "step": 60725 }, { "epoch": 12.58, "learning_rate": 0.00022278408548802596, "loss": 1.7163, "step": 60730 }, { "epoch": 12.58, "learning_rate": 0.00022268867474477627, "loss": 1.7126, "step": 60735 }, { "epoch": 12.58, "learning_rate": 0.00022259326400152657, "loss": 1.712, "step": 60740 }, { "epoch": 12.58, "learning_rate": 0.0002224978532582769, "loss": 1.7117, "step": 60745 }, { "epoch": 12.59, "learning_rate": 0.0002224024425150272, "loss": 1.7127, "step": 60750 }, { "epoch": 12.59, "learning_rate": 0.0002223070317717775, "loss": 1.7089, "step": 60755 }, { "epoch": 12.59, "learning_rate": 0.00022221162102852783, "loss": 1.7127, "step": 60760 }, { "epoch": 12.59, "learning_rate": 0.0002221162102852781, "loss": 1.7081, "step": 60765 }, { "epoch": 12.59, "learning_rate": 0.00022202079954202844, "loss": 1.7114, "step": 60770 }, { "epoch": 12.59, "learning_rate": 0.00022192538879877875, "loss": 1.7121, "step": 60775 }, { "epoch": 12.59, "learning_rate": 0.00022182997805552906, "loss": 1.7133, "step": 60780 }, { "epoch": 12.59, "learning_rate": 0.00022173456731227936, "loss": 1.7137, "step": 60785 }, { "epoch": 12.59, "learning_rate": 0.00022163915656902967, "loss": 1.7097, "step": 60790 }, { "epoch": 12.59, "learning_rate": 0.00022154374582578, "loss": 1.7126, "step": 60795 }, { "epoch": 12.6, "learning_rate": 0.00022144833508253028, "loss": 1.7071, "step": 60800 }, { "epoch": 12.6, "learning_rate": 0.00022135292433928062, "loss": 1.7111, "step": 60805 }, { "epoch": 12.6, "learning_rate": 0.00022125751359603092, "loss": 1.7114, "step": 60810 }, { "epoch": 12.6, "learning_rate": 0.00022116210285278123, "loss": 1.7143, "step": 60815 }, { "epoch": 12.6, "learning_rate": 0.00022106669210953154, "loss": 1.7122, "step": 60820 }, { "epoch": 12.6, "learning_rate": 0.00022097128136628185, "loss": 1.7106, "step": 60825 }, { "epoch": 12.6, "learning_rate": 0.00022087587062303215, "loss": 1.7094, "step": 60830 }, { "epoch": 12.6, "learning_rate": 0.00022078045987978246, "loss": 1.7077, "step": 60835 }, { "epoch": 12.6, "learning_rate": 0.0002206850491365328, "loss": 1.7071, "step": 60840 }, { "epoch": 12.61, "learning_rate": 0.00022058963839328307, "loss": 1.7171, "step": 60845 }, { "epoch": 12.61, "learning_rate": 0.0002204942276500334, "loss": 1.7084, "step": 60850 }, { "epoch": 12.61, "learning_rate": 0.00022039881690678371, "loss": 1.7055, "step": 60855 }, { "epoch": 12.61, "learning_rate": 0.00022030340616353402, "loss": 1.7198, "step": 60860 }, { "epoch": 12.61, "learning_rate": 0.00022020799542028433, "loss": 1.7102, "step": 60865 }, { "epoch": 12.61, "learning_rate": 0.00022011258467703463, "loss": 1.7127, "step": 60870 }, { "epoch": 12.61, "learning_rate": 0.00022001717393378494, "loss": 1.7123, "step": 60875 }, { "epoch": 12.61, "learning_rate": 0.00021992176319053525, "loss": 1.7141, "step": 60880 }, { "epoch": 12.61, "learning_rate": 0.00021982635244728558, "loss": 1.7134, "step": 60885 }, { "epoch": 12.61, "learning_rate": 0.00021973094170403586, "loss": 1.7133, "step": 60890 }, { "epoch": 12.62, "learning_rate": 0.0002196355309607862, "loss": 1.7087, "step": 60895 }, { "epoch": 12.62, "learning_rate": 0.0002195401202175365, "loss": 1.7087, "step": 60900 }, { "epoch": 12.62, "learning_rate": 0.0002194447094742868, "loss": 1.7089, "step": 60905 }, { "epoch": 12.62, "learning_rate": 0.00021934929873103712, "loss": 1.7135, "step": 60910 }, { "epoch": 12.62, "learning_rate": 0.00021925388798778742, "loss": 1.7143, "step": 60915 }, { "epoch": 12.62, "learning_rate": 0.00021915847724453776, "loss": 1.7106, "step": 60920 }, { "epoch": 12.62, "learning_rate": 0.00021906306650128804, "loss": 1.7132, "step": 60925 }, { "epoch": 12.62, "learning_rate": 0.00021896765575803837, "loss": 1.7105, "step": 60930 }, { "epoch": 12.62, "learning_rate": 0.00021887224501478868, "loss": 1.7145, "step": 60935 }, { "epoch": 12.62, "learning_rate": 0.00021877683427153898, "loss": 1.7095, "step": 60940 }, { "epoch": 12.63, "learning_rate": 0.0002186814235282893, "loss": 1.7085, "step": 60945 }, { "epoch": 12.63, "learning_rate": 0.0002185860127850396, "loss": 1.7142, "step": 60950 }, { "epoch": 12.63, "learning_rate": 0.0002184906020417899, "loss": 1.7132, "step": 60955 }, { "epoch": 12.63, "learning_rate": 0.0002183951912985402, "loss": 1.7125, "step": 60960 }, { "epoch": 12.63, "learning_rate": 0.00021829978055529055, "loss": 1.705, "step": 60965 }, { "epoch": 12.63, "learning_rate": 0.00021820436981204083, "loss": 1.7115, "step": 60970 }, { "epoch": 12.63, "learning_rate": 0.00021810895906879116, "loss": 1.7103, "step": 60975 }, { "epoch": 12.63, "learning_rate": 0.00021801354832554147, "loss": 1.7085, "step": 60980 }, { "epoch": 12.63, "learning_rate": 0.00021791813758229175, "loss": 1.7116, "step": 60985 }, { "epoch": 12.64, "learning_rate": 0.00021782272683904208, "loss": 1.7102, "step": 60990 }, { "epoch": 12.64, "learning_rate": 0.0002177273160957924, "loss": 1.7118, "step": 60995 }, { "epoch": 12.64, "learning_rate": 0.00021763190535254272, "loss": 1.7119, "step": 61000 }, { "epoch": 12.64, "learning_rate": 0.000217536494609293, "loss": 1.7087, "step": 61005 }, { "epoch": 12.64, "learning_rate": 0.00021744108386604334, "loss": 1.7151, "step": 61010 }, { "epoch": 12.64, "learning_rate": 0.00021734567312279364, "loss": 1.7114, "step": 61015 }, { "epoch": 12.64, "learning_rate": 0.00021725026237954392, "loss": 1.7071, "step": 61020 }, { "epoch": 12.64, "learning_rate": 0.00021715485163629426, "loss": 1.7149, "step": 61025 }, { "epoch": 12.64, "learning_rate": 0.00021705944089304456, "loss": 1.7109, "step": 61030 }, { "epoch": 12.64, "learning_rate": 0.00021696403014979487, "loss": 1.719, "step": 61035 }, { "epoch": 12.65, "learning_rate": 0.00021686861940654518, "loss": 1.7126, "step": 61040 }, { "epoch": 12.65, "learning_rate": 0.0002167732086632955, "loss": 1.7113, "step": 61045 }, { "epoch": 12.65, "learning_rate": 0.0002166777979200458, "loss": 1.7083, "step": 61050 }, { "epoch": 12.65, "learning_rate": 0.00021658238717679612, "loss": 1.711, "step": 61055 }, { "epoch": 12.65, "learning_rate": 0.00021648697643354643, "loss": 1.7174, "step": 61060 }, { "epoch": 12.65, "learning_rate": 0.0002163915656902967, "loss": 1.7178, "step": 61065 }, { "epoch": 12.65, "learning_rate": 0.00021629615494704705, "loss": 1.7151, "step": 61070 }, { "epoch": 12.65, "learning_rate": 0.00021620074420379735, "loss": 1.7041, "step": 61075 }, { "epoch": 12.65, "learning_rate": 0.00021610533346054766, "loss": 1.7112, "step": 61080 }, { "epoch": 12.65, "learning_rate": 0.00021600992271729797, "loss": 1.709, "step": 61085 }, { "epoch": 12.66, "learning_rate": 0.0002159145119740483, "loss": 1.712, "step": 61090 }, { "epoch": 12.66, "learning_rate": 0.00021581910123079858, "loss": 1.7103, "step": 61095 }, { "epoch": 12.66, "learning_rate": 0.0002157236904875489, "loss": 1.709, "step": 61100 }, { "epoch": 12.66, "learning_rate": 0.00021562827974429922, "loss": 1.7133, "step": 61105 }, { "epoch": 12.66, "learning_rate": 0.00021553286900104953, "loss": 1.7152, "step": 61110 }, { "epoch": 12.66, "learning_rate": 0.00021543745825779983, "loss": 1.7146, "step": 61115 }, { "epoch": 12.66, "learning_rate": 0.00021534204751455014, "loss": 1.71, "step": 61120 }, { "epoch": 12.66, "learning_rate": 0.00021524663677130048, "loss": 1.7092, "step": 61125 }, { "epoch": 12.66, "learning_rate": 0.00021515122602805076, "loss": 1.7119, "step": 61130 }, { "epoch": 12.67, "learning_rate": 0.00021505581528480106, "loss": 1.7072, "step": 61135 }, { "epoch": 12.67, "learning_rate": 0.0002149604045415514, "loss": 1.71, "step": 61140 }, { "epoch": 12.67, "learning_rate": 0.00021486499379830168, "loss": 1.7096, "step": 61145 }, { "epoch": 12.67, "learning_rate": 0.000214769583055052, "loss": 1.7142, "step": 61150 }, { "epoch": 12.67, "learning_rate": 0.00021467417231180232, "loss": 1.7149, "step": 61155 }, { "epoch": 12.67, "learning_rate": 0.00021457876156855262, "loss": 1.7134, "step": 61160 }, { "epoch": 12.67, "learning_rate": 0.00021448335082530293, "loss": 1.7139, "step": 61165 }, { "epoch": 12.67, "learning_rate": 0.00021438794008205326, "loss": 1.7124, "step": 61170 }, { "epoch": 12.67, "learning_rate": 0.00021429252933880354, "loss": 1.7103, "step": 61175 }, { "epoch": 12.67, "learning_rate": 0.00021419711859555385, "loss": 1.7099, "step": 61180 }, { "epoch": 12.68, "learning_rate": 0.00021410170785230419, "loss": 1.7073, "step": 61185 }, { "epoch": 12.68, "learning_rate": 0.00021400629710905446, "loss": 1.7138, "step": 61190 }, { "epoch": 12.68, "learning_rate": 0.0002139108863658048, "loss": 1.7102, "step": 61195 }, { "epoch": 12.68, "learning_rate": 0.0002138154756225551, "loss": 1.7108, "step": 61200 }, { "epoch": 12.68, "learning_rate": 0.0002137200648793054, "loss": 1.7091, "step": 61205 }, { "epoch": 12.68, "learning_rate": 0.00021362465413605572, "loss": 1.7062, "step": 61210 }, { "epoch": 12.68, "learning_rate": 0.00021352924339280603, "loss": 1.7136, "step": 61215 }, { "epoch": 12.68, "learning_rate": 0.00021343383264955636, "loss": 1.7127, "step": 61220 }, { "epoch": 12.68, "learning_rate": 0.00021333842190630664, "loss": 1.7065, "step": 61225 }, { "epoch": 12.68, "learning_rate": 0.00021324301116305697, "loss": 1.7088, "step": 61230 }, { "epoch": 12.69, "learning_rate": 0.00021314760041980728, "loss": 1.7123, "step": 61235 }, { "epoch": 12.69, "learning_rate": 0.0002130521896765576, "loss": 1.7091, "step": 61240 }, { "epoch": 12.69, "learning_rate": 0.0002129567789333079, "loss": 1.7065, "step": 61245 }, { "epoch": 12.69, "learning_rate": 0.00021286136819005823, "loss": 1.7099, "step": 61250 }, { "epoch": 12.69, "learning_rate": 0.0002127659574468085, "loss": 1.7149, "step": 61255 }, { "epoch": 12.69, "learning_rate": 0.00021267054670355882, "loss": 1.7074, "step": 61260 }, { "epoch": 12.69, "learning_rate": 0.00021257513596030915, "loss": 1.7091, "step": 61265 }, { "epoch": 12.69, "learning_rate": 0.00021247972521705943, "loss": 1.715, "step": 61270 }, { "epoch": 12.69, "learning_rate": 0.00021238431447380976, "loss": 1.7041, "step": 61275 }, { "epoch": 12.7, "learning_rate": 0.00021228890373056007, "loss": 1.7083, "step": 61280 }, { "epoch": 12.7, "learning_rate": 0.00021219349298731038, "loss": 1.7109, "step": 61285 }, { "epoch": 12.7, "learning_rate": 0.00021209808224406068, "loss": 1.7126, "step": 61290 }, { "epoch": 12.7, "learning_rate": 0.000212002671500811, "loss": 1.7105, "step": 61295 }, { "epoch": 12.7, "learning_rate": 0.0002119072607575613, "loss": 1.7123, "step": 61300 }, { "epoch": 12.7, "learning_rate": 0.0002118118500143116, "loss": 1.7077, "step": 61305 }, { "epoch": 12.7, "learning_rate": 0.00021171643927106194, "loss": 1.7133, "step": 61310 }, { "epoch": 12.7, "learning_rate": 0.00021162102852781222, "loss": 1.71, "step": 61315 }, { "epoch": 12.7, "learning_rate": 0.00021152561778456255, "loss": 1.7105, "step": 61320 }, { "epoch": 12.7, "learning_rate": 0.00021143020704131286, "loss": 1.7097, "step": 61325 }, { "epoch": 12.71, "learning_rate": 0.00021133479629806317, "loss": 1.7116, "step": 61330 }, { "epoch": 12.71, "learning_rate": 0.00021123938555481347, "loss": 1.7078, "step": 61335 }, { "epoch": 12.71, "learning_rate": 0.00021114397481156378, "loss": 1.7104, "step": 61340 }, { "epoch": 12.71, "learning_rate": 0.00021104856406831411, "loss": 1.7115, "step": 61345 }, { "epoch": 12.71, "learning_rate": 0.0002109531533250644, "loss": 1.7086, "step": 61350 }, { "epoch": 12.71, "learning_rate": 0.00021085774258181473, "loss": 1.7125, "step": 61355 }, { "epoch": 12.71, "learning_rate": 0.00021076233183856503, "loss": 1.7064, "step": 61360 }, { "epoch": 12.71, "learning_rate": 0.00021066692109531534, "loss": 1.7077, "step": 61365 }, { "epoch": 12.71, "learning_rate": 0.00021057151035206565, "loss": 1.7036, "step": 61370 }, { "epoch": 12.71, "learning_rate": 0.00021047609960881596, "loss": 1.7128, "step": 61375 }, { "epoch": 12.72, "learning_rate": 0.00021038068886556626, "loss": 1.716, "step": 61380 }, { "epoch": 12.72, "learning_rate": 0.00021028527812231657, "loss": 1.7122, "step": 61385 }, { "epoch": 12.72, "learning_rate": 0.0002101898673790669, "loss": 1.7141, "step": 61390 }, { "epoch": 12.72, "learning_rate": 0.00021009445663581718, "loss": 1.7136, "step": 61395 }, { "epoch": 12.72, "learning_rate": 0.00020999904589256752, "loss": 1.7183, "step": 61400 }, { "epoch": 12.72, "learning_rate": 0.00020990363514931782, "loss": 1.7112, "step": 61405 }, { "epoch": 12.72, "learning_rate": 0.0002098082244060681, "loss": 1.7147, "step": 61410 }, { "epoch": 12.72, "learning_rate": 0.00020971281366281844, "loss": 1.7124, "step": 61415 }, { "epoch": 12.72, "learning_rate": 0.00020961740291956874, "loss": 1.7106, "step": 61420 }, { "epoch": 12.73, "learning_rate": 0.00020952199217631908, "loss": 1.708, "step": 61425 }, { "epoch": 12.73, "learning_rate": 0.00020942658143306936, "loss": 1.7114, "step": 61430 }, { "epoch": 12.73, "learning_rate": 0.0002093311706898197, "loss": 1.7097, "step": 61435 }, { "epoch": 12.73, "learning_rate": 0.00020923575994657, "loss": 1.71, "step": 61440 }, { "epoch": 12.73, "learning_rate": 0.00020914034920332028, "loss": 1.7099, "step": 61445 }, { "epoch": 12.73, "learning_rate": 0.0002090449384600706, "loss": 1.7111, "step": 61450 }, { "epoch": 12.73, "learning_rate": 0.00020894952771682092, "loss": 1.7136, "step": 61455 }, { "epoch": 12.73, "learning_rate": 0.00020885411697357123, "loss": 1.7103, "step": 61460 }, { "epoch": 12.73, "learning_rate": 0.00020875870623032153, "loss": 1.7138, "step": 61465 }, { "epoch": 12.73, "learning_rate": 0.00020866329548707187, "loss": 1.7111, "step": 61470 }, { "epoch": 12.74, "learning_rate": 0.00020856788474382215, "loss": 1.7084, "step": 61475 }, { "epoch": 12.74, "learning_rate": 0.00020847247400057248, "loss": 1.7097, "step": 61480 }, { "epoch": 12.74, "learning_rate": 0.0002083770632573228, "loss": 1.7123, "step": 61485 }, { "epoch": 12.74, "learning_rate": 0.00020828165251407307, "loss": 1.7111, "step": 61490 }, { "epoch": 12.74, "learning_rate": 0.0002081862417708234, "loss": 1.7089, "step": 61495 }, { "epoch": 12.74, "learning_rate": 0.0002080908310275737, "loss": 1.7149, "step": 61500 }, { "epoch": 12.74, "learning_rate": 0.00020799542028432402, "loss": 1.7129, "step": 61505 }, { "epoch": 12.74, "learning_rate": 0.00020790000954107432, "loss": 1.7138, "step": 61510 }, { "epoch": 12.74, "learning_rate": 0.00020780459879782466, "loss": 1.7101, "step": 61515 }, { "epoch": 12.74, "learning_rate": 0.00020770918805457494, "loss": 1.7158, "step": 61520 }, { "epoch": 12.75, "learning_rate": 0.00020761377731132524, "loss": 1.7091, "step": 61525 }, { "epoch": 12.75, "learning_rate": 0.00020751836656807558, "loss": 1.7104, "step": 61530 }, { "epoch": 12.75, "learning_rate": 0.00020742295582482588, "loss": 1.7131, "step": 61535 }, { "epoch": 12.75, "learning_rate": 0.0002073275450815762, "loss": 1.7098, "step": 61540 }, { "epoch": 12.75, "learning_rate": 0.0002072321343383265, "loss": 1.7179, "step": 61545 }, { "epoch": 12.75, "learning_rate": 0.00020713672359507683, "loss": 1.7119, "step": 61550 }, { "epoch": 12.75, "learning_rate": 0.0002070413128518271, "loss": 1.7115, "step": 61555 }, { "epoch": 12.75, "learning_rate": 0.00020694590210857742, "loss": 1.7057, "step": 61560 }, { "epoch": 12.75, "learning_rate": 0.00020685049136532775, "loss": 1.7126, "step": 61565 }, { "epoch": 12.76, "learning_rate": 0.00020675508062207803, "loss": 1.7086, "step": 61570 }, { "epoch": 12.76, "learning_rate": 0.00020665966987882837, "loss": 1.711, "step": 61575 }, { "epoch": 12.76, "learning_rate": 0.00020656425913557867, "loss": 1.7118, "step": 61580 }, { "epoch": 12.76, "learning_rate": 0.00020646884839232898, "loss": 1.7126, "step": 61585 }, { "epoch": 12.76, "learning_rate": 0.0002063734376490793, "loss": 1.7099, "step": 61590 }, { "epoch": 12.76, "learning_rate": 0.00020627802690582962, "loss": 1.7091, "step": 61595 }, { "epoch": 12.76, "learning_rate": 0.0002061826161625799, "loss": 1.7139, "step": 61600 }, { "epoch": 12.76, "learning_rate": 0.0002060872054193302, "loss": 1.7106, "step": 61605 }, { "epoch": 12.76, "learning_rate": 0.00020599179467608054, "loss": 1.7147, "step": 61610 }, { "epoch": 12.76, "learning_rate": 0.00020589638393283082, "loss": 1.7068, "step": 61615 }, { "epoch": 12.77, "learning_rate": 0.00020580097318958116, "loss": 1.7157, "step": 61620 }, { "epoch": 12.77, "learning_rate": 0.00020570556244633146, "loss": 1.7083, "step": 61625 }, { "epoch": 12.77, "learning_rate": 0.00020561015170308177, "loss": 1.7056, "step": 61630 }, { "epoch": 12.77, "learning_rate": 0.00020551474095983208, "loss": 1.716, "step": 61635 }, { "epoch": 12.77, "learning_rate": 0.00020541933021658238, "loss": 1.7106, "step": 61640 }, { "epoch": 12.77, "learning_rate": 0.00020532391947333272, "loss": 1.7061, "step": 61645 }, { "epoch": 12.77, "learning_rate": 0.000205228508730083, "loss": 1.715, "step": 61650 }, { "epoch": 12.77, "learning_rate": 0.00020513309798683333, "loss": 1.7073, "step": 61655 }, { "epoch": 12.77, "learning_rate": 0.00020503768724358364, "loss": 1.7124, "step": 61660 }, { "epoch": 12.78, "learning_rate": 0.00020494227650033394, "loss": 1.7123, "step": 61665 }, { "epoch": 12.78, "learning_rate": 0.00020484686575708425, "loss": 1.7091, "step": 61670 }, { "epoch": 12.78, "learning_rate": 0.00020475145501383459, "loss": 1.7138, "step": 61675 }, { "epoch": 12.78, "learning_rate": 0.00020465604427058487, "loss": 1.7053, "step": 61680 }, { "epoch": 12.78, "learning_rate": 0.00020456063352733517, "loss": 1.7119, "step": 61685 }, { "epoch": 12.78, "learning_rate": 0.0002044652227840855, "loss": 1.7123, "step": 61690 }, { "epoch": 12.78, "learning_rate": 0.00020436981204083579, "loss": 1.713, "step": 61695 }, { "epoch": 12.78, "learning_rate": 0.00020427440129758612, "loss": 1.7166, "step": 61700 }, { "epoch": 12.78, "learning_rate": 0.00020417899055433643, "loss": 1.7112, "step": 61705 }, { "epoch": 12.78, "learning_rate": 0.00020408357981108673, "loss": 1.7071, "step": 61710 }, { "epoch": 12.79, "learning_rate": 0.00020398816906783704, "loss": 1.7088, "step": 61715 }, { "epoch": 12.79, "learning_rate": 0.00020389275832458735, "loss": 1.7097, "step": 61720 }, { "epoch": 12.79, "learning_rate": 0.00020379734758133765, "loss": 1.7095, "step": 61725 }, { "epoch": 12.79, "learning_rate": 0.00020370193683808796, "loss": 1.7103, "step": 61730 }, { "epoch": 12.79, "learning_rate": 0.0002036065260948383, "loss": 1.7103, "step": 61735 }, { "epoch": 12.79, "learning_rate": 0.00020351111535158858, "loss": 1.7106, "step": 61740 }, { "epoch": 12.79, "learning_rate": 0.0002034157046083389, "loss": 1.7118, "step": 61745 }, { "epoch": 12.79, "learning_rate": 0.00020332029386508922, "loss": 1.7105, "step": 61750 }, { "epoch": 12.79, "learning_rate": 0.00020322488312183952, "loss": 1.7139, "step": 61755 }, { "epoch": 12.79, "learning_rate": 0.00020312947237858983, "loss": 1.7106, "step": 61760 }, { "epoch": 12.8, "learning_rate": 0.00020303406163534014, "loss": 1.7134, "step": 61765 }, { "epoch": 12.8, "learning_rate": 0.00020293865089209047, "loss": 1.7109, "step": 61770 }, { "epoch": 12.8, "learning_rate": 0.00020284324014884075, "loss": 1.7111, "step": 61775 }, { "epoch": 12.8, "learning_rate": 0.00020274782940559108, "loss": 1.7085, "step": 61780 }, { "epoch": 12.8, "learning_rate": 0.0002026524186623414, "loss": 1.7126, "step": 61785 }, { "epoch": 12.8, "learning_rate": 0.0002025570079190917, "loss": 1.7118, "step": 61790 }, { "epoch": 12.8, "learning_rate": 0.000202461597175842, "loss": 1.7138, "step": 61795 }, { "epoch": 12.8, "learning_rate": 0.0002023661864325923, "loss": 1.7091, "step": 61800 }, { "epoch": 12.8, "learning_rate": 0.00020227077568934262, "loss": 1.7123, "step": 61805 }, { "epoch": 12.81, "learning_rate": 0.00020217536494609293, "loss": 1.7089, "step": 61810 }, { "epoch": 12.81, "learning_rate": 0.00020207995420284326, "loss": 1.7098, "step": 61815 }, { "epoch": 12.81, "learning_rate": 0.00020198454345959354, "loss": 1.7045, "step": 61820 }, { "epoch": 12.81, "learning_rate": 0.00020188913271634387, "loss": 1.7136, "step": 61825 }, { "epoch": 12.81, "learning_rate": 0.00020179372197309418, "loss": 1.7069, "step": 61830 }, { "epoch": 12.81, "learning_rate": 0.00020169831122984446, "loss": 1.711, "step": 61835 }, { "epoch": 12.81, "learning_rate": 0.0002016029004865948, "loss": 1.7134, "step": 61840 }, { "epoch": 12.81, "learning_rate": 0.0002015074897433451, "loss": 1.7126, "step": 61845 }, { "epoch": 12.81, "learning_rate": 0.00020141207900009544, "loss": 1.7095, "step": 61850 }, { "epoch": 12.81, "learning_rate": 0.00020131666825684571, "loss": 1.7138, "step": 61855 }, { "epoch": 12.82, "learning_rate": 0.00020122125751359605, "loss": 1.7068, "step": 61860 }, { "epoch": 12.82, "learning_rate": 0.00020112584677034636, "loss": 1.7177, "step": 61865 }, { "epoch": 12.82, "learning_rate": 0.00020103043602709664, "loss": 1.7134, "step": 61870 }, { "epoch": 12.82, "learning_rate": 0.00020093502528384697, "loss": 1.7042, "step": 61875 }, { "epoch": 12.82, "learning_rate": 0.00020083961454059728, "loss": 1.707, "step": 61880 }, { "epoch": 12.82, "learning_rate": 0.00020074420379734758, "loss": 1.7133, "step": 61885 }, { "epoch": 12.82, "learning_rate": 0.0002006487930540979, "loss": 1.7017, "step": 61890 }, { "epoch": 12.82, "learning_rate": 0.00020055338231084822, "loss": 1.7078, "step": 61895 }, { "epoch": 12.82, "learning_rate": 0.0002004579715675985, "loss": 1.716, "step": 61900 }, { "epoch": 12.82, "learning_rate": 0.00020036256082434884, "loss": 1.7123, "step": 61905 }, { "epoch": 12.83, "learning_rate": 0.00020026715008109914, "loss": 1.7117, "step": 61910 }, { "epoch": 12.83, "learning_rate": 0.00020017173933784942, "loss": 1.7063, "step": 61915 }, { "epoch": 12.83, "learning_rate": 0.00020007632859459976, "loss": 1.7148, "step": 61920 }, { "epoch": 12.83, "learning_rate": 0.00019998091785135007, "loss": 1.7123, "step": 61925 }, { "epoch": 12.83, "learning_rate": 0.00019988550710810037, "loss": 1.7098, "step": 61930 }, { "epoch": 12.83, "learning_rate": 0.00019979009636485068, "loss": 1.7125, "step": 61935 }, { "epoch": 12.83, "learning_rate": 0.000199694685621601, "loss": 1.7104, "step": 61940 }, { "epoch": 12.83, "learning_rate": 0.0001995992748783513, "loss": 1.7082, "step": 61945 }, { "epoch": 12.83, "learning_rate": 0.0001995038641351016, "loss": 1.7119, "step": 61950 }, { "epoch": 12.84, "learning_rate": 0.00019940845339185193, "loss": 1.7097, "step": 61955 }, { "epoch": 12.84, "learning_rate": 0.00019931304264860224, "loss": 1.7111, "step": 61960 }, { "epoch": 12.84, "learning_rate": 0.00019921763190535255, "loss": 1.7102, "step": 61965 }, { "epoch": 12.84, "learning_rate": 0.00019912222116210285, "loss": 1.7086, "step": 61970 }, { "epoch": 12.84, "learning_rate": 0.0001990268104188532, "loss": 1.7086, "step": 61975 }, { "epoch": 12.84, "learning_rate": 0.00019893139967560347, "loss": 1.704, "step": 61980 }, { "epoch": 12.84, "learning_rate": 0.0001988359889323538, "loss": 1.7125, "step": 61985 }, { "epoch": 12.84, "learning_rate": 0.0001987405781891041, "loss": 1.7129, "step": 61990 }, { "epoch": 12.84, "learning_rate": 0.0001986451674458544, "loss": 1.7151, "step": 61995 }, { "epoch": 12.84, "learning_rate": 0.00019854975670260472, "loss": 1.7118, "step": 62000 }, { "epoch": 12.85, "learning_rate": 0.00019845434595935503, "loss": 1.709, "step": 62005 }, { "epoch": 12.85, "learning_rate": 0.00019835893521610534, "loss": 1.7109, "step": 62010 }, { "epoch": 12.85, "learning_rate": 0.00019826352447285564, "loss": 1.712, "step": 62015 }, { "epoch": 12.85, "learning_rate": 0.00019816811372960598, "loss": 1.7103, "step": 62020 }, { "epoch": 12.85, "learning_rate": 0.00019807270298635626, "loss": 1.7149, "step": 62025 }, { "epoch": 12.85, "learning_rate": 0.00019797729224310656, "loss": 1.7124, "step": 62030 }, { "epoch": 12.85, "learning_rate": 0.0001978818814998569, "loss": 1.7131, "step": 62035 }, { "epoch": 12.85, "learning_rate": 0.00019778647075660718, "loss": 1.7112, "step": 62040 }, { "epoch": 12.85, "learning_rate": 0.0001976910600133575, "loss": 1.7064, "step": 62045 }, { "epoch": 12.85, "learning_rate": 0.00019759564927010782, "loss": 1.7152, "step": 62050 }, { "epoch": 12.86, "learning_rate": 0.00019750023852685813, "loss": 1.7099, "step": 62055 }, { "epoch": 12.86, "learning_rate": 0.00019740482778360843, "loss": 1.7074, "step": 62060 }, { "epoch": 12.86, "learning_rate": 0.00019730941704035874, "loss": 1.7121, "step": 62065 }, { "epoch": 12.86, "learning_rate": 0.00019721400629710907, "loss": 1.7117, "step": 62070 }, { "epoch": 12.86, "learning_rate": 0.00019711859555385935, "loss": 1.7096, "step": 62075 }, { "epoch": 12.86, "learning_rate": 0.0001970231848106097, "loss": 1.7119, "step": 62080 }, { "epoch": 12.86, "learning_rate": 0.00019692777406736, "loss": 1.7089, "step": 62085 }, { "epoch": 12.86, "learning_rate": 0.0001968323633241103, "loss": 1.704, "step": 62090 }, { "epoch": 12.86, "learning_rate": 0.0001967369525808606, "loss": 1.714, "step": 62095 }, { "epoch": 12.87, "learning_rate": 0.00019664154183761094, "loss": 1.7201, "step": 62100 }, { "epoch": 12.87, "learning_rate": 0.00019654613109436122, "loss": 1.7106, "step": 62105 }, { "epoch": 12.87, "learning_rate": 0.00019645072035111153, "loss": 1.7102, "step": 62110 }, { "epoch": 12.87, "learning_rate": 0.00019635530960786186, "loss": 1.711, "step": 62115 }, { "epoch": 12.87, "learning_rate": 0.00019625989886461214, "loss": 1.7097, "step": 62120 }, { "epoch": 12.87, "learning_rate": 0.00019616448812136248, "loss": 1.7137, "step": 62125 }, { "epoch": 12.87, "learning_rate": 0.00019606907737811278, "loss": 1.7091, "step": 62130 }, { "epoch": 12.87, "learning_rate": 0.0001959736666348631, "loss": 1.7096, "step": 62135 }, { "epoch": 12.87, "learning_rate": 0.0001958782558916134, "loss": 1.7133, "step": 62140 }, { "epoch": 12.87, "learning_rate": 0.0001957828451483637, "loss": 1.7112, "step": 62145 }, { "epoch": 12.88, "learning_rate": 0.000195687434405114, "loss": 1.7093, "step": 62150 }, { "epoch": 12.88, "learning_rate": 0.00019559202366186432, "loss": 1.7144, "step": 62155 }, { "epoch": 12.88, "learning_rate": 0.00019549661291861465, "loss": 1.7092, "step": 62160 }, { "epoch": 12.88, "learning_rate": 0.00019540120217536493, "loss": 1.7146, "step": 62165 }, { "epoch": 12.88, "learning_rate": 0.00019530579143211527, "loss": 1.7088, "step": 62170 }, { "epoch": 12.88, "learning_rate": 0.00019521038068886557, "loss": 1.7136, "step": 62175 }, { "epoch": 12.88, "learning_rate": 0.00019511496994561588, "loss": 1.7122, "step": 62180 }, { "epoch": 12.88, "learning_rate": 0.00019501955920236619, "loss": 1.7137, "step": 62185 }, { "epoch": 12.88, "learning_rate": 0.0001949241484591165, "loss": 1.7112, "step": 62190 }, { "epoch": 12.88, "learning_rate": 0.00019482873771586683, "loss": 1.7107, "step": 62195 }, { "epoch": 12.89, "learning_rate": 0.0001947333269726171, "loss": 1.7126, "step": 62200 }, { "epoch": 12.89, "learning_rate": 0.00019463791622936744, "loss": 1.7092, "step": 62205 }, { "epoch": 12.89, "learning_rate": 0.00019454250548611775, "loss": 1.7122, "step": 62210 }, { "epoch": 12.89, "learning_rate": 0.00019444709474286805, "loss": 1.7079, "step": 62215 }, { "epoch": 12.89, "learning_rate": 0.00019435168399961836, "loss": 1.7126, "step": 62220 }, { "epoch": 12.89, "learning_rate": 0.00019425627325636867, "loss": 1.7063, "step": 62225 }, { "epoch": 12.89, "learning_rate": 0.00019416086251311898, "loss": 1.71, "step": 62230 }, { "epoch": 12.89, "learning_rate": 0.00019406545176986928, "loss": 1.7141, "step": 62235 }, { "epoch": 12.89, "learning_rate": 0.00019397004102661962, "loss": 1.7102, "step": 62240 }, { "epoch": 12.9, "learning_rate": 0.0001938746302833699, "loss": 1.7104, "step": 62245 }, { "epoch": 12.9, "learning_rate": 0.00019377921954012023, "loss": 1.7077, "step": 62250 }, { "epoch": 12.9, "learning_rate": 0.00019368380879687054, "loss": 1.7109, "step": 62255 }, { "epoch": 12.9, "learning_rate": 0.00019358839805362082, "loss": 1.7112, "step": 62260 }, { "epoch": 12.9, "learning_rate": 0.00019349298731037115, "loss": 1.7105, "step": 62265 }, { "epoch": 12.9, "learning_rate": 0.00019339757656712146, "loss": 1.7107, "step": 62270 }, { "epoch": 12.9, "learning_rate": 0.0001933021658238718, "loss": 1.7135, "step": 62275 }, { "epoch": 12.9, "learning_rate": 0.00019320675508062207, "loss": 1.71, "step": 62280 }, { "epoch": 12.9, "learning_rate": 0.0001931113443373724, "loss": 1.7086, "step": 62285 }, { "epoch": 12.9, "learning_rate": 0.0001930159335941227, "loss": 1.7112, "step": 62290 }, { "epoch": 12.91, "learning_rate": 0.00019292052285087302, "loss": 1.7101, "step": 62295 }, { "epoch": 12.91, "learning_rate": 0.00019282511210762333, "loss": 1.7093, "step": 62300 }, { "epoch": 12.91, "learning_rate": 0.00019272970136437363, "loss": 1.7071, "step": 62305 }, { "epoch": 12.91, "learning_rate": 0.00019263429062112394, "loss": 1.703, "step": 62310 }, { "epoch": 12.91, "learning_rate": 0.00019253887987787425, "loss": 1.7142, "step": 62315 }, { "epoch": 12.91, "learning_rate": 0.00019244346913462458, "loss": 1.7097, "step": 62320 }, { "epoch": 12.91, "learning_rate": 0.00019234805839137486, "loss": 1.7107, "step": 62325 }, { "epoch": 12.91, "learning_rate": 0.0001922526476481252, "loss": 1.7175, "step": 62330 }, { "epoch": 12.91, "learning_rate": 0.0001921572369048755, "loss": 1.7046, "step": 62335 }, { "epoch": 12.91, "learning_rate": 0.00019206182616162578, "loss": 1.7149, "step": 62340 }, { "epoch": 12.92, "learning_rate": 0.00019196641541837612, "loss": 1.7081, "step": 62345 }, { "epoch": 12.92, "learning_rate": 0.00019187100467512642, "loss": 1.7099, "step": 62350 }, { "epoch": 12.92, "learning_rate": 0.00019177559393187673, "loss": 1.716, "step": 62355 }, { "epoch": 12.92, "learning_rate": 0.00019168018318862704, "loss": 1.713, "step": 62360 }, { "epoch": 12.92, "learning_rate": 0.00019158477244537737, "loss": 1.7076, "step": 62365 }, { "epoch": 12.92, "learning_rate": 0.00019148936170212765, "loss": 1.7033, "step": 62370 }, { "epoch": 12.92, "learning_rate": 0.00019139395095887796, "loss": 1.7065, "step": 62375 }, { "epoch": 12.92, "learning_rate": 0.0001912985402156283, "loss": 1.7131, "step": 62380 }, { "epoch": 12.92, "learning_rate": 0.0001912031294723786, "loss": 1.7135, "step": 62385 }, { "epoch": 12.93, "learning_rate": 0.0001911077187291289, "loss": 1.7083, "step": 62390 }, { "epoch": 12.93, "learning_rate": 0.0001910123079858792, "loss": 1.7103, "step": 62395 }, { "epoch": 12.93, "learning_rate": 0.00019091689724262955, "loss": 1.7068, "step": 62400 }, { "epoch": 12.93, "learning_rate": 0.00019082148649937983, "loss": 1.7036, "step": 62405 }, { "epoch": 12.93, "learning_rate": 0.00019072607575613016, "loss": 1.7164, "step": 62410 }, { "epoch": 12.93, "learning_rate": 0.00019063066501288047, "loss": 1.7121, "step": 62415 }, { "epoch": 12.93, "learning_rate": 0.00019053525426963075, "loss": 1.7115, "step": 62420 }, { "epoch": 12.93, "learning_rate": 0.00019043984352638108, "loss": 1.709, "step": 62425 }, { "epoch": 12.93, "learning_rate": 0.0001903444327831314, "loss": 1.7104, "step": 62430 }, { "epoch": 12.93, "learning_rate": 0.0001902490220398817, "loss": 1.71, "step": 62435 }, { "epoch": 12.94, "learning_rate": 0.000190153611296632, "loss": 1.7126, "step": 62440 }, { "epoch": 12.94, "learning_rate": 0.00019005820055338233, "loss": 1.7054, "step": 62445 }, { "epoch": 12.94, "learning_rate": 0.00018996278981013261, "loss": 1.7092, "step": 62450 }, { "epoch": 12.94, "learning_rate": 0.00018986737906688292, "loss": 1.7083, "step": 62455 }, { "epoch": 12.94, "learning_rate": 0.00018977196832363326, "loss": 1.714, "step": 62460 }, { "epoch": 12.94, "learning_rate": 0.00018967655758038353, "loss": 1.705, "step": 62465 }, { "epoch": 12.94, "learning_rate": 0.00018958114683713387, "loss": 1.71, "step": 62470 }, { "epoch": 12.94, "learning_rate": 0.00018948573609388418, "loss": 1.7127, "step": 62475 }, { "epoch": 12.94, "learning_rate": 0.00018939032535063448, "loss": 1.7089, "step": 62480 }, { "epoch": 12.94, "learning_rate": 0.0001892949146073848, "loss": 1.7161, "step": 62485 }, { "epoch": 12.95, "learning_rate": 0.0001891995038641351, "loss": 1.71, "step": 62490 }, { "epoch": 12.95, "learning_rate": 0.00018910409312088543, "loss": 1.706, "step": 62495 }, { "epoch": 12.95, "learning_rate": 0.0001890086823776357, "loss": 1.709, "step": 62500 }, { "epoch": 12.95, "learning_rate": 0.00018891327163438604, "loss": 1.7106, "step": 62505 }, { "epoch": 12.95, "learning_rate": 0.00018881786089113635, "loss": 1.7073, "step": 62510 }, { "epoch": 12.95, "learning_rate": 0.00018872245014788666, "loss": 1.7093, "step": 62515 }, { "epoch": 12.95, "learning_rate": 0.00018862703940463696, "loss": 1.7096, "step": 62520 }, { "epoch": 12.95, "learning_rate": 0.0001885316286613873, "loss": 1.71, "step": 62525 }, { "epoch": 12.95, "learning_rate": 0.00018843621791813758, "loss": 1.7093, "step": 62530 }, { "epoch": 12.96, "learning_rate": 0.00018834080717488789, "loss": 1.7095, "step": 62535 }, { "epoch": 12.96, "learning_rate": 0.00018824539643163822, "loss": 1.711, "step": 62540 }, { "epoch": 12.96, "learning_rate": 0.0001881499856883885, "loss": 1.7092, "step": 62545 }, { "epoch": 12.96, "learning_rate": 0.00018805457494513883, "loss": 1.7097, "step": 62550 }, { "epoch": 12.96, "learning_rate": 0.00018795916420188914, "loss": 1.7087, "step": 62555 }, { "epoch": 12.96, "learning_rate": 0.00018786375345863945, "loss": 1.7143, "step": 62560 }, { "epoch": 12.96, "learning_rate": 0.00018776834271538975, "loss": 1.7048, "step": 62565 }, { "epoch": 12.96, "learning_rate": 0.00018767293197214006, "loss": 1.7116, "step": 62570 }, { "epoch": 12.96, "learning_rate": 0.00018757752122889037, "loss": 1.7117, "step": 62575 }, { "epoch": 12.96, "learning_rate": 0.00018748211048564067, "loss": 1.7099, "step": 62580 }, { "epoch": 12.97, "learning_rate": 0.000187386699742391, "loss": 1.7074, "step": 62585 }, { "epoch": 12.97, "learning_rate": 0.0001872912889991413, "loss": 1.7086, "step": 62590 }, { "epoch": 12.97, "learning_rate": 0.00018719587825589162, "loss": 1.7077, "step": 62595 }, { "epoch": 12.97, "learning_rate": 0.00018710046751264193, "loss": 1.7114, "step": 62600 }, { "epoch": 12.97, "learning_rate": 0.00018700505676939226, "loss": 1.7124, "step": 62605 }, { "epoch": 12.97, "learning_rate": 0.00018690964602614254, "loss": 1.706, "step": 62610 }, { "epoch": 12.97, "learning_rate": 0.00018681423528289285, "loss": 1.7112, "step": 62615 }, { "epoch": 12.97, "learning_rate": 0.00018671882453964318, "loss": 1.7088, "step": 62620 }, { "epoch": 12.97, "learning_rate": 0.00018662341379639346, "loss": 1.7071, "step": 62625 }, { "epoch": 12.97, "learning_rate": 0.0001865280030531438, "loss": 1.7052, "step": 62630 }, { "epoch": 12.98, "learning_rate": 0.0001864325923098941, "loss": 1.7126, "step": 62635 }, { "epoch": 12.98, "learning_rate": 0.0001863371815666444, "loss": 1.7104, "step": 62640 }, { "epoch": 12.98, "learning_rate": 0.00018624177082339472, "loss": 1.7096, "step": 62645 }, { "epoch": 12.98, "learning_rate": 0.00018614636008014503, "loss": 1.7071, "step": 62650 }, { "epoch": 12.98, "learning_rate": 0.00018605094933689533, "loss": 1.7094, "step": 62655 }, { "epoch": 12.98, "learning_rate": 0.00018595553859364564, "loss": 1.7051, "step": 62660 }, { "epoch": 12.98, "learning_rate": 0.00018586012785039597, "loss": 1.708, "step": 62665 }, { "epoch": 12.98, "learning_rate": 0.00018576471710714625, "loss": 1.7085, "step": 62670 }, { "epoch": 12.98, "learning_rate": 0.0001856693063638966, "loss": 1.7095, "step": 62675 }, { "epoch": 12.99, "learning_rate": 0.0001855738956206469, "loss": 1.7108, "step": 62680 }, { "epoch": 12.99, "learning_rate": 0.00018547848487739717, "loss": 1.7063, "step": 62685 }, { "epoch": 12.99, "learning_rate": 0.0001853830741341475, "loss": 1.7075, "step": 62690 }, { "epoch": 12.99, "learning_rate": 0.00018528766339089781, "loss": 1.7143, "step": 62695 }, { "epoch": 12.99, "learning_rate": 0.00018519225264764815, "loss": 1.7108, "step": 62700 }, { "epoch": 12.99, "learning_rate": 0.00018509684190439843, "loss": 1.7116, "step": 62705 }, { "epoch": 12.99, "learning_rate": 0.00018500143116114876, "loss": 1.7103, "step": 62710 }, { "epoch": 12.99, "learning_rate": 0.00018490602041789907, "loss": 1.7116, "step": 62715 }, { "epoch": 12.99, "learning_rate": 0.00018481060967464938, "loss": 1.7144, "step": 62720 }, { "epoch": 12.99, "learning_rate": 0.00018471519893139968, "loss": 1.7095, "step": 62725 }, { "epoch": 13.0, "learning_rate": 0.00018461978818815, "loss": 1.7097, "step": 62730 }, { "epoch": 13.0, "learning_rate": 0.0001845243774449003, "loss": 1.707, "step": 62735 }, { "epoch": 13.0, "learning_rate": 0.0001844289667016506, "loss": 1.7025, "step": 62740 }, { "epoch": 13.0, "learning_rate": 0.00018433355595840094, "loss": 1.7082, "step": 62745 }, { "epoch": 13.0, "learning_rate": 0.00018423814521515122, "loss": 1.7108, "step": 62750 }, { "epoch": 13.0, "learning_rate": 0.00018414273447190155, "loss": 1.6981, "step": 62755 }, { "epoch": 13.0, "learning_rate": 0.00018404732372865186, "loss": 1.7041, "step": 62760 }, { "epoch": 13.0, "learning_rate": 0.00018395191298540214, "loss": 1.709, "step": 62765 }, { "epoch": 13.0, "learning_rate": 0.00018385650224215247, "loss": 1.7008, "step": 62770 }, { "epoch": 13.0, "learning_rate": 0.00018376109149890278, "loss": 1.7086, "step": 62775 }, { "epoch": 13.01, "learning_rate": 0.00018366568075565309, "loss": 1.7018, "step": 62780 }, { "epoch": 13.01, "learning_rate": 0.0001835702700124034, "loss": 1.7016, "step": 62785 }, { "epoch": 13.01, "learning_rate": 0.00018347485926915373, "loss": 1.7075, "step": 62790 }, { "epoch": 13.01, "learning_rate": 0.000183379448525904, "loss": 1.7006, "step": 62795 }, { "epoch": 13.01, "learning_rate": 0.0001832840377826543, "loss": 1.7013, "step": 62800 }, { "epoch": 13.01, "learning_rate": 0.00018318862703940465, "loss": 1.7087, "step": 62805 }, { "epoch": 13.01, "learning_rate": 0.00018309321629615495, "loss": 1.7023, "step": 62810 }, { "epoch": 13.01, "learning_rate": 0.00018299780555290526, "loss": 1.7076, "step": 62815 }, { "epoch": 13.01, "learning_rate": 0.00018290239480965557, "loss": 1.7047, "step": 62820 }, { "epoch": 13.02, "learning_rate": 0.0001828069840664059, "loss": 1.7054, "step": 62825 }, { "epoch": 13.02, "learning_rate": 0.00018271157332315618, "loss": 1.7011, "step": 62830 }, { "epoch": 13.02, "learning_rate": 0.00018261616257990652, "loss": 1.6989, "step": 62835 }, { "epoch": 13.02, "learning_rate": 0.00018252075183665682, "loss": 1.703, "step": 62840 }, { "epoch": 13.02, "learning_rate": 0.0001824253410934071, "loss": 1.7012, "step": 62845 }, { "epoch": 13.02, "learning_rate": 0.00018232993035015744, "loss": 1.7008, "step": 62850 }, { "epoch": 13.02, "learning_rate": 0.00018223451960690774, "loss": 1.7066, "step": 62855 }, { "epoch": 13.02, "learning_rate": 0.00018213910886365805, "loss": 1.7027, "step": 62860 }, { "epoch": 13.02, "learning_rate": 0.00018204369812040836, "loss": 1.7037, "step": 62865 }, { "epoch": 13.02, "learning_rate": 0.0001819482873771587, "loss": 1.7062, "step": 62870 }, { "epoch": 13.03, "learning_rate": 0.00018185287663390897, "loss": 1.7016, "step": 62875 }, { "epoch": 13.03, "learning_rate": 0.00018175746589065928, "loss": 1.7065, "step": 62880 }, { "epoch": 13.03, "learning_rate": 0.0001816620551474096, "loss": 1.708, "step": 62885 }, { "epoch": 13.03, "learning_rate": 0.0001815666444041599, "loss": 1.7056, "step": 62890 }, { "epoch": 13.03, "learning_rate": 0.00018147123366091023, "loss": 1.7061, "step": 62895 }, { "epoch": 13.03, "learning_rate": 0.00018137582291766053, "loss": 1.7009, "step": 62900 }, { "epoch": 13.03, "learning_rate": 0.00018128041217441084, "loss": 1.7024, "step": 62905 }, { "epoch": 13.03, "learning_rate": 0.00018118500143116115, "loss": 1.7051, "step": 62910 }, { "epoch": 13.03, "learning_rate": 0.00018108959068791148, "loss": 1.7061, "step": 62915 }, { "epoch": 13.04, "learning_rate": 0.0001809941799446618, "loss": 1.7017, "step": 62920 }, { "epoch": 13.04, "learning_rate": 0.00018089876920141207, "loss": 1.696, "step": 62925 }, { "epoch": 13.04, "learning_rate": 0.0001808033584581624, "loss": 1.7024, "step": 62930 }, { "epoch": 13.04, "learning_rate": 0.0001807079477149127, "loss": 1.7023, "step": 62935 }, { "epoch": 13.04, "learning_rate": 0.00018061253697166301, "loss": 1.7042, "step": 62940 }, { "epoch": 13.04, "learning_rate": 0.00018051712622841332, "loss": 1.7055, "step": 62945 }, { "epoch": 13.04, "learning_rate": 0.00018042171548516366, "loss": 1.7026, "step": 62950 }, { "epoch": 13.04, "learning_rate": 0.00018032630474191394, "loss": 1.7096, "step": 62955 }, { "epoch": 13.04, "learning_rate": 0.00018023089399866424, "loss": 1.7007, "step": 62960 }, { "epoch": 13.04, "learning_rate": 0.00018013548325541458, "loss": 1.7035, "step": 62965 }, { "epoch": 13.05, "learning_rate": 0.00018004007251216486, "loss": 1.7022, "step": 62970 }, { "epoch": 13.05, "learning_rate": 0.0001799446617689152, "loss": 1.7018, "step": 62975 }, { "epoch": 13.05, "learning_rate": 0.0001798492510256655, "loss": 1.7049, "step": 62980 }, { "epoch": 13.05, "learning_rate": 0.0001797538402824158, "loss": 1.7015, "step": 62985 }, { "epoch": 13.05, "learning_rate": 0.0001796584295391661, "loss": 1.7053, "step": 62990 }, { "epoch": 13.05, "learning_rate": 0.00017956301879591642, "loss": 1.7082, "step": 62995 }, { "epoch": 13.05, "learning_rate": 0.00017946760805266672, "loss": 1.7093, "step": 63000 }, { "epoch": 13.05, "eval_accuracy": 0.5490196078431373, "eval_loss": 1.900115966796875, "eval_runtime": 0.6484, "eval_samples_per_second": 231.327, "eval_steps_per_second": 1.542, "step": 63000 }, { "epoch": 13.05, "learning_rate": 0.00017937219730941703, "loss": 1.7055, "step": 63005 }, { "epoch": 13.05, "learning_rate": 0.00017927678656616737, "loss": 1.7035, "step": 63010 }, { "epoch": 13.05, "learning_rate": 0.00017918137582291764, "loss": 1.7042, "step": 63015 }, { "epoch": 13.06, "learning_rate": 0.00017908596507966798, "loss": 1.7048, "step": 63020 }, { "epoch": 13.06, "learning_rate": 0.00017899055433641829, "loss": 1.7027, "step": 63025 }, { "epoch": 13.06, "learning_rate": 0.00017889514359316862, "loss": 1.7033, "step": 63030 }, { "epoch": 13.06, "learning_rate": 0.0001787997328499189, "loss": 1.702, "step": 63035 }, { "epoch": 13.06, "learning_rate": 0.0001787043221066692, "loss": 1.7046, "step": 63040 }, { "epoch": 13.06, "learning_rate": 0.00017860891136341954, "loss": 1.6997, "step": 63045 }, { "epoch": 13.06, "learning_rate": 0.00017851350062016982, "loss": 1.7055, "step": 63050 }, { "epoch": 13.06, "learning_rate": 0.00017841808987692015, "loss": 1.7, "step": 63055 }, { "epoch": 13.06, "learning_rate": 0.00017832267913367046, "loss": 1.7031, "step": 63060 }, { "epoch": 13.07, "learning_rate": 0.00017822726839042077, "loss": 1.7031, "step": 63065 }, { "epoch": 13.07, "learning_rate": 0.00017813185764717107, "loss": 1.7077, "step": 63070 }, { "epoch": 13.07, "learning_rate": 0.00017803644690392138, "loss": 1.7047, "step": 63075 }, { "epoch": 13.07, "learning_rate": 0.0001779410361606717, "loss": 1.7051, "step": 63080 }, { "epoch": 13.07, "learning_rate": 0.000177845625417422, "loss": 1.7055, "step": 63085 }, { "epoch": 13.07, "learning_rate": 0.00017775021467417233, "loss": 1.7015, "step": 63090 }, { "epoch": 13.07, "learning_rate": 0.0001776548039309226, "loss": 1.7072, "step": 63095 }, { "epoch": 13.07, "learning_rate": 0.00017755939318767294, "loss": 1.7007, "step": 63100 }, { "epoch": 13.07, "learning_rate": 0.00017746398244442325, "loss": 1.7049, "step": 63105 }, { "epoch": 13.07, "learning_rate": 0.00017736857170117353, "loss": 1.7023, "step": 63110 }, { "epoch": 13.08, "learning_rate": 0.00017727316095792386, "loss": 1.7024, "step": 63115 }, { "epoch": 13.08, "learning_rate": 0.00017717775021467417, "loss": 1.7043, "step": 63120 }, { "epoch": 13.08, "learning_rate": 0.0001770823394714245, "loss": 1.7063, "step": 63125 }, { "epoch": 13.08, "learning_rate": 0.00017698692872817478, "loss": 1.7012, "step": 63130 }, { "epoch": 13.08, "learning_rate": 0.00017689151798492512, "loss": 1.707, "step": 63135 }, { "epoch": 13.08, "learning_rate": 0.00017679610724167543, "loss": 1.7019, "step": 63140 }, { "epoch": 13.08, "learning_rate": 0.00017670069649842573, "loss": 1.7082, "step": 63145 }, { "epoch": 13.08, "learning_rate": 0.00017660528575517604, "loss": 1.7029, "step": 63150 }, { "epoch": 13.08, "learning_rate": 0.00017650987501192635, "loss": 1.7024, "step": 63155 }, { "epoch": 13.08, "learning_rate": 0.00017641446426867665, "loss": 1.7022, "step": 63160 }, { "epoch": 13.09, "learning_rate": 0.00017631905352542696, "loss": 1.7063, "step": 63165 }, { "epoch": 13.09, "learning_rate": 0.0001762236427821773, "loss": 1.6991, "step": 63170 }, { "epoch": 13.09, "learning_rate": 0.00017612823203892757, "loss": 1.7003, "step": 63175 }, { "epoch": 13.09, "learning_rate": 0.0001760328212956779, "loss": 1.7036, "step": 63180 }, { "epoch": 13.09, "learning_rate": 0.00017593741055242821, "loss": 1.7019, "step": 63185 }, { "epoch": 13.09, "learning_rate": 0.0001758419998091785, "loss": 1.6989, "step": 63190 }, { "epoch": 13.09, "learning_rate": 0.00017574658906592883, "loss": 1.7056, "step": 63195 }, { "epoch": 13.09, "learning_rate": 0.00017565117832267914, "loss": 1.7081, "step": 63200 }, { "epoch": 13.09, "learning_rate": 0.00017555576757942944, "loss": 1.7035, "step": 63205 }, { "epoch": 13.1, "learning_rate": 0.00017546035683617975, "loss": 1.7019, "step": 63210 }, { "epoch": 13.1, "learning_rate": 0.00017536494609293008, "loss": 1.7028, "step": 63215 }, { "epoch": 13.1, "learning_rate": 0.00017526953534968036, "loss": 1.7058, "step": 63220 }, { "epoch": 13.1, "learning_rate": 0.0001751741246064307, "loss": 1.7043, "step": 63225 }, { "epoch": 13.1, "learning_rate": 0.000175078713863181, "loss": 1.7075, "step": 63230 }, { "epoch": 13.1, "learning_rate": 0.0001749833031199313, "loss": 1.7034, "step": 63235 }, { "epoch": 13.1, "learning_rate": 0.00017488789237668162, "loss": 1.7065, "step": 63240 }, { "epoch": 13.1, "learning_rate": 0.00017479248163343192, "loss": 1.7058, "step": 63245 }, { "epoch": 13.1, "learning_rate": 0.00017469707089018226, "loss": 1.7057, "step": 63250 }, { "epoch": 13.1, "learning_rate": 0.00017460166014693254, "loss": 1.7008, "step": 63255 }, { "epoch": 13.11, "learning_rate": 0.00017450624940368287, "loss": 1.7004, "step": 63260 }, { "epoch": 13.11, "learning_rate": 0.00017441083866043318, "loss": 1.7055, "step": 63265 }, { "epoch": 13.11, "learning_rate": 0.00017431542791718346, "loss": 1.7024, "step": 63270 }, { "epoch": 13.11, "learning_rate": 0.0001742200171739338, "loss": 1.7049, "step": 63275 }, { "epoch": 13.11, "learning_rate": 0.0001741246064306841, "loss": 1.7029, "step": 63280 }, { "epoch": 13.11, "learning_rate": 0.0001740291956874344, "loss": 1.7063, "step": 63285 }, { "epoch": 13.11, "learning_rate": 0.00017393378494418471, "loss": 1.7066, "step": 63290 }, { "epoch": 13.11, "learning_rate": 0.00017383837420093505, "loss": 1.703, "step": 63295 }, { "epoch": 13.11, "learning_rate": 0.00017374296345768533, "loss": 1.7068, "step": 63300 }, { "epoch": 13.11, "learning_rate": 0.00017364755271443563, "loss": 1.7014, "step": 63305 }, { "epoch": 13.12, "learning_rate": 0.00017355214197118597, "loss": 1.7035, "step": 63310 }, { "epoch": 13.12, "learning_rate": 0.00017345673122793625, "loss": 1.7026, "step": 63315 }, { "epoch": 13.12, "learning_rate": 0.00017336132048468658, "loss": 1.7036, "step": 63320 }, { "epoch": 13.12, "learning_rate": 0.0001732659097414369, "loss": 1.708, "step": 63325 }, { "epoch": 13.12, "learning_rate": 0.0001731704989981872, "loss": 1.7053, "step": 63330 }, { "epoch": 13.12, "learning_rate": 0.0001730750882549375, "loss": 1.7031, "step": 63335 }, { "epoch": 13.12, "learning_rate": 0.00017297967751168784, "loss": 1.7041, "step": 63340 }, { "epoch": 13.12, "learning_rate": 0.00017288426676843814, "loss": 1.7057, "step": 63345 }, { "epoch": 13.12, "learning_rate": 0.00017278885602518842, "loss": 1.7032, "step": 63350 }, { "epoch": 13.13, "learning_rate": 0.00017269344528193876, "loss": 1.7087, "step": 63355 }, { "epoch": 13.13, "learning_rate": 0.00017259803453868906, "loss": 1.7114, "step": 63360 }, { "epoch": 13.13, "learning_rate": 0.00017250262379543937, "loss": 1.7073, "step": 63365 }, { "epoch": 13.13, "learning_rate": 0.00017240721305218968, "loss": 1.7023, "step": 63370 }, { "epoch": 13.13, "learning_rate": 0.00017231180230894, "loss": 1.7031, "step": 63375 }, { "epoch": 13.13, "learning_rate": 0.0001722163915656903, "loss": 1.6969, "step": 63380 }, { "epoch": 13.13, "learning_rate": 0.0001721209808224406, "loss": 1.7015, "step": 63385 }, { "epoch": 13.13, "learning_rate": 0.00017202557007919093, "loss": 1.7051, "step": 63390 }, { "epoch": 13.13, "learning_rate": 0.0001719301593359412, "loss": 1.7101, "step": 63395 }, { "epoch": 13.13, "learning_rate": 0.00017183474859269155, "loss": 1.7054, "step": 63400 }, { "epoch": 13.14, "learning_rate": 0.00017173933784944185, "loss": 1.7068, "step": 63405 }, { "epoch": 13.14, "learning_rate": 0.00017164392710619216, "loss": 1.7031, "step": 63410 }, { "epoch": 13.14, "learning_rate": 0.00017154851636294247, "loss": 1.7041, "step": 63415 }, { "epoch": 13.14, "learning_rate": 0.00017145310561969277, "loss": 1.7063, "step": 63420 }, { "epoch": 13.14, "learning_rate": 0.00017135769487644308, "loss": 1.7049, "step": 63425 }, { "epoch": 13.14, "learning_rate": 0.0001712622841331934, "loss": 1.7024, "step": 63430 }, { "epoch": 13.14, "learning_rate": 0.00017116687338994372, "loss": 1.7036, "step": 63435 }, { "epoch": 13.14, "learning_rate": 0.000171071462646694, "loss": 1.6988, "step": 63440 }, { "epoch": 13.14, "learning_rate": 0.00017097605190344434, "loss": 1.7041, "step": 63445 }, { "epoch": 13.14, "learning_rate": 0.00017088064116019464, "loss": 1.7085, "step": 63450 }, { "epoch": 13.15, "learning_rate": 0.00017078523041694498, "loss": 1.7042, "step": 63455 }, { "epoch": 13.15, "learning_rate": 0.00017068981967369526, "loss": 1.7048, "step": 63460 }, { "epoch": 13.15, "learning_rate": 0.00017059440893044556, "loss": 1.7001, "step": 63465 }, { "epoch": 13.15, "learning_rate": 0.0001704989981871959, "loss": 1.7062, "step": 63470 }, { "epoch": 13.15, "learning_rate": 0.00017040358744394618, "loss": 1.6995, "step": 63475 }, { "epoch": 13.15, "learning_rate": 0.0001703081767006965, "loss": 1.709, "step": 63480 }, { "epoch": 13.15, "learning_rate": 0.00017021276595744682, "loss": 1.7089, "step": 63485 }, { "epoch": 13.15, "learning_rate": 0.00017011735521419712, "loss": 1.7054, "step": 63490 }, { "epoch": 13.15, "learning_rate": 0.00017002194447094743, "loss": 1.7066, "step": 63495 }, { "epoch": 13.16, "learning_rate": 0.00016992653372769774, "loss": 1.7053, "step": 63500 }, { "epoch": 13.16, "learning_rate": 0.00016983112298444805, "loss": 1.7029, "step": 63505 }, { "epoch": 13.16, "learning_rate": 0.00016973571224119835, "loss": 1.7082, "step": 63510 }, { "epoch": 13.16, "learning_rate": 0.00016964030149794869, "loss": 1.7084, "step": 63515 }, { "epoch": 13.16, "learning_rate": 0.00016954489075469897, "loss": 1.6996, "step": 63520 }, { "epoch": 13.16, "learning_rate": 0.0001694494800114493, "loss": 1.7028, "step": 63525 }, { "epoch": 13.16, "learning_rate": 0.0001693540692681996, "loss": 1.7063, "step": 63530 }, { "epoch": 13.16, "learning_rate": 0.00016925865852494991, "loss": 1.7085, "step": 63535 }, { "epoch": 13.16, "learning_rate": 0.00016916324778170022, "loss": 1.7056, "step": 63540 }, { "epoch": 13.16, "learning_rate": 0.00016906783703845053, "loss": 1.7087, "step": 63545 }, { "epoch": 13.17, "learning_rate": 0.00016897242629520086, "loss": 1.7046, "step": 63550 }, { "epoch": 13.17, "learning_rate": 0.00016887701555195114, "loss": 1.7079, "step": 63555 }, { "epoch": 13.17, "learning_rate": 0.00016878160480870148, "loss": 1.7042, "step": 63560 }, { "epoch": 13.17, "learning_rate": 0.00016868619406545178, "loss": 1.704, "step": 63565 }, { "epoch": 13.17, "learning_rate": 0.0001685907833222021, "loss": 1.7026, "step": 63570 }, { "epoch": 13.17, "learning_rate": 0.0001684953725789524, "loss": 1.7048, "step": 63575 }, { "epoch": 13.17, "learning_rate": 0.0001683999618357027, "loss": 1.7032, "step": 63580 }, { "epoch": 13.17, "learning_rate": 0.000168304551092453, "loss": 1.7012, "step": 63585 }, { "epoch": 13.17, "learning_rate": 0.00016820914034920332, "loss": 1.7063, "step": 63590 }, { "epoch": 13.17, "learning_rate": 0.00016811372960595365, "loss": 1.7022, "step": 63595 }, { "epoch": 13.18, "learning_rate": 0.00016801831886270393, "loss": 1.7048, "step": 63600 }, { "epoch": 13.18, "learning_rate": 0.00016792290811945426, "loss": 1.6995, "step": 63605 }, { "epoch": 13.18, "learning_rate": 0.00016782749737620457, "loss": 1.7055, "step": 63610 }, { "epoch": 13.18, "learning_rate": 0.00016773208663295485, "loss": 1.7016, "step": 63615 }, { "epoch": 13.18, "learning_rate": 0.00016763667588970519, "loss": 1.7077, "step": 63620 }, { "epoch": 13.18, "learning_rate": 0.0001675412651464555, "loss": 1.7036, "step": 63625 }, { "epoch": 13.18, "learning_rate": 0.0001674458544032058, "loss": 1.7062, "step": 63630 }, { "epoch": 13.18, "learning_rate": 0.0001673504436599561, "loss": 1.7071, "step": 63635 }, { "epoch": 13.18, "learning_rate": 0.00016725503291670644, "loss": 1.7006, "step": 63640 }, { "epoch": 13.19, "learning_rate": 0.00016715962217345672, "loss": 1.7041, "step": 63645 }, { "epoch": 13.19, "learning_rate": 0.00016706421143020705, "loss": 1.7017, "step": 63650 }, { "epoch": 13.19, "learning_rate": 0.00016696880068695736, "loss": 1.7004, "step": 63655 }, { "epoch": 13.19, "learning_rate": 0.00016687338994370767, "loss": 1.7042, "step": 63660 }, { "epoch": 13.19, "learning_rate": 0.00016677797920045797, "loss": 1.7052, "step": 63665 }, { "epoch": 13.19, "learning_rate": 0.00016668256845720828, "loss": 1.7064, "step": 63670 }, { "epoch": 13.19, "learning_rate": 0.00016658715771395862, "loss": 1.7102, "step": 63675 }, { "epoch": 13.19, "learning_rate": 0.0001664917469707089, "loss": 1.7053, "step": 63680 }, { "epoch": 13.19, "learning_rate": 0.00016639633622745923, "loss": 1.7064, "step": 63685 }, { "epoch": 13.19, "learning_rate": 0.00016630092548420954, "loss": 1.703, "step": 63690 }, { "epoch": 13.2, "learning_rate": 0.00016620551474095982, "loss": 1.709, "step": 63695 }, { "epoch": 13.2, "learning_rate": 0.00016611010399771015, "loss": 1.7014, "step": 63700 }, { "epoch": 13.2, "learning_rate": 0.00016601469325446046, "loss": 1.7067, "step": 63705 }, { "epoch": 13.2, "learning_rate": 0.00016591928251121076, "loss": 1.7099, "step": 63710 }, { "epoch": 13.2, "learning_rate": 0.00016582387176796107, "loss": 1.7026, "step": 63715 }, { "epoch": 13.2, "learning_rate": 0.0001657284610247114, "loss": 1.707, "step": 63720 }, { "epoch": 13.2, "learning_rate": 0.00016563305028146168, "loss": 1.7046, "step": 63725 }, { "epoch": 13.2, "learning_rate": 0.000165537639538212, "loss": 1.7102, "step": 63730 }, { "epoch": 13.2, "learning_rate": 0.00016544222879496232, "loss": 1.7038, "step": 63735 }, { "epoch": 13.2, "learning_rate": 0.0001653468180517126, "loss": 1.7078, "step": 63740 }, { "epoch": 13.21, "learning_rate": 0.00016525140730846294, "loss": 1.6985, "step": 63745 }, { "epoch": 13.21, "learning_rate": 0.00016515599656521325, "loss": 1.7028, "step": 63750 }, { "epoch": 13.21, "learning_rate": 0.00016506058582196355, "loss": 1.7, "step": 63755 }, { "epoch": 13.21, "learning_rate": 0.00016496517507871386, "loss": 1.7063, "step": 63760 }, { "epoch": 13.21, "learning_rate": 0.0001648697643354642, "loss": 1.7089, "step": 63765 }, { "epoch": 13.21, "learning_rate": 0.0001647743535922145, "loss": 1.7072, "step": 63770 }, { "epoch": 13.21, "learning_rate": 0.00016467894284896478, "loss": 1.7044, "step": 63775 }, { "epoch": 13.21, "learning_rate": 0.00016458353210571511, "loss": 1.7058, "step": 63780 }, { "epoch": 13.21, "learning_rate": 0.00016448812136246542, "loss": 1.7098, "step": 63785 }, { "epoch": 13.22, "learning_rate": 0.00016439271061921573, "loss": 1.7007, "step": 63790 }, { "epoch": 13.22, "learning_rate": 0.00016429729987596603, "loss": 1.7029, "step": 63795 }, { "epoch": 13.22, "learning_rate": 0.00016420188913271637, "loss": 1.7051, "step": 63800 }, { "epoch": 13.22, "learning_rate": 0.00016410647838946665, "loss": 1.705, "step": 63805 }, { "epoch": 13.22, "learning_rate": 0.00016401106764621696, "loss": 1.7083, "step": 63810 }, { "epoch": 13.22, "learning_rate": 0.0001639156569029673, "loss": 1.7056, "step": 63815 }, { "epoch": 13.22, "learning_rate": 0.00016382024615971757, "loss": 1.7053, "step": 63820 }, { "epoch": 13.22, "learning_rate": 0.0001637248354164679, "loss": 1.7064, "step": 63825 }, { "epoch": 13.22, "learning_rate": 0.0001636294246732182, "loss": 1.7059, "step": 63830 }, { "epoch": 13.22, "learning_rate": 0.00016353401392996852, "loss": 1.705, "step": 63835 }, { "epoch": 13.23, "learning_rate": 0.00016343860318671882, "loss": 1.7049, "step": 63840 }, { "epoch": 13.23, "learning_rate": 0.00016334319244346916, "loss": 1.707, "step": 63845 }, { "epoch": 13.23, "learning_rate": 0.00016324778170021944, "loss": 1.7014, "step": 63850 }, { "epoch": 13.23, "learning_rate": 0.00016315237095696974, "loss": 1.7064, "step": 63855 }, { "epoch": 13.23, "learning_rate": 0.00016305696021372008, "loss": 1.7037, "step": 63860 }, { "epoch": 13.23, "learning_rate": 0.00016296154947047036, "loss": 1.7077, "step": 63865 }, { "epoch": 13.23, "learning_rate": 0.0001628661387272207, "loss": 1.7046, "step": 63870 }, { "epoch": 13.23, "learning_rate": 0.000162770727983971, "loss": 1.7054, "step": 63875 }, { "epoch": 13.23, "learning_rate": 0.00016267531724072133, "loss": 1.7069, "step": 63880 }, { "epoch": 13.23, "learning_rate": 0.0001625799064974716, "loss": 1.7062, "step": 63885 }, { "epoch": 13.24, "learning_rate": 0.00016248449575422192, "loss": 1.7062, "step": 63890 }, { "epoch": 13.24, "learning_rate": 0.00016238908501097225, "loss": 1.7081, "step": 63895 }, { "epoch": 13.24, "learning_rate": 0.00016229367426772253, "loss": 1.7055, "step": 63900 }, { "epoch": 13.24, "learning_rate": 0.00016219826352447287, "loss": 1.7043, "step": 63905 }, { "epoch": 13.24, "learning_rate": 0.00016210285278122317, "loss": 1.7091, "step": 63910 }, { "epoch": 13.24, "learning_rate": 0.00016200744203797348, "loss": 1.7031, "step": 63915 }, { "epoch": 13.24, "learning_rate": 0.0001619120312947238, "loss": 1.7069, "step": 63920 }, { "epoch": 13.24, "learning_rate": 0.0001618166205514741, "loss": 1.7061, "step": 63925 }, { "epoch": 13.24, "learning_rate": 0.0001617212098082244, "loss": 1.7046, "step": 63930 }, { "epoch": 13.25, "learning_rate": 0.0001616257990649747, "loss": 1.7038, "step": 63935 }, { "epoch": 13.25, "learning_rate": 0.00016153038832172504, "loss": 1.7025, "step": 63940 }, { "epoch": 13.25, "learning_rate": 0.00016143497757847532, "loss": 1.7079, "step": 63945 }, { "epoch": 13.25, "learning_rate": 0.00016133956683522566, "loss": 1.7061, "step": 63950 }, { "epoch": 13.25, "learning_rate": 0.00016124415609197596, "loss": 1.7053, "step": 63955 }, { "epoch": 13.25, "learning_rate": 0.00016114874534872627, "loss": 1.7059, "step": 63960 }, { "epoch": 13.25, "learning_rate": 0.00016105333460547658, "loss": 1.704, "step": 63965 }, { "epoch": 13.25, "learning_rate": 0.00016095792386222688, "loss": 1.7018, "step": 63970 }, { "epoch": 13.25, "learning_rate": 0.00016086251311897722, "loss": 1.7054, "step": 63975 }, { "epoch": 13.25, "learning_rate": 0.0001607671023757275, "loss": 1.7033, "step": 63980 }, { "epoch": 13.26, "learning_rate": 0.00016067169163247783, "loss": 1.7055, "step": 63985 }, { "epoch": 13.26, "learning_rate": 0.00016057628088922814, "loss": 1.7093, "step": 63990 }, { "epoch": 13.26, "learning_rate": 0.00016048087014597845, "loss": 1.7017, "step": 63995 }, { "epoch": 13.26, "learning_rate": 0.00016038545940272875, "loss": 1.7084, "step": 64000 }, { "epoch": 13.26, "learning_rate": 0.00016029004865947906, "loss": 1.7019, "step": 64005 }, { "epoch": 13.26, "learning_rate": 0.00016019463791622937, "loss": 1.6958, "step": 64010 }, { "epoch": 13.26, "learning_rate": 0.00016009922717297967, "loss": 1.7066, "step": 64015 }, { "epoch": 13.26, "learning_rate": 0.00016000381642973, "loss": 1.7047, "step": 64020 }, { "epoch": 13.26, "learning_rate": 0.0001599084056864803, "loss": 1.7006, "step": 64025 }, { "epoch": 13.26, "learning_rate": 0.00015981299494323062, "loss": 1.7041, "step": 64030 }, { "epoch": 13.27, "learning_rate": 0.00015971758419998093, "loss": 1.7074, "step": 64035 }, { "epoch": 13.27, "learning_rate": 0.0001596221734567312, "loss": 1.7065, "step": 64040 }, { "epoch": 13.27, "learning_rate": 0.00015952676271348154, "loss": 1.7104, "step": 64045 }, { "epoch": 13.27, "learning_rate": 0.00015943135197023185, "loss": 1.705, "step": 64050 }, { "epoch": 13.27, "learning_rate": 0.00015933594122698216, "loss": 1.7045, "step": 64055 }, { "epoch": 13.27, "learning_rate": 0.00015924053048373246, "loss": 1.7108, "step": 64060 }, { "epoch": 13.27, "learning_rate": 0.0001591451197404828, "loss": 1.7011, "step": 64065 }, { "epoch": 13.27, "learning_rate": 0.00015904970899723308, "loss": 1.7049, "step": 64070 }, { "epoch": 13.27, "learning_rate": 0.0001589542982539834, "loss": 1.7038, "step": 64075 }, { "epoch": 13.28, "learning_rate": 0.00015885888751073372, "loss": 1.7049, "step": 64080 }, { "epoch": 13.28, "learning_rate": 0.00015876347676748402, "loss": 1.7025, "step": 64085 }, { "epoch": 13.28, "learning_rate": 0.00015866806602423433, "loss": 1.7029, "step": 64090 }, { "epoch": 13.28, "learning_rate": 0.00015857265528098464, "loss": 1.7044, "step": 64095 }, { "epoch": 13.28, "learning_rate": 0.00015847724453773497, "loss": 1.7013, "step": 64100 }, { "epoch": 13.28, "learning_rate": 0.00015838183379448525, "loss": 1.7091, "step": 64105 }, { "epoch": 13.28, "learning_rate": 0.00015828642305123559, "loss": 1.7048, "step": 64110 }, { "epoch": 13.28, "learning_rate": 0.0001581910123079859, "loss": 1.7054, "step": 64115 }, { "epoch": 13.28, "learning_rate": 0.00015809560156473617, "loss": 1.7052, "step": 64120 }, { "epoch": 13.28, "learning_rate": 0.0001580001908214865, "loss": 1.7085, "step": 64125 }, { "epoch": 13.29, "learning_rate": 0.0001579047800782368, "loss": 1.7047, "step": 64130 }, { "epoch": 13.29, "learning_rate": 0.00015780936933498712, "loss": 1.7065, "step": 64135 }, { "epoch": 13.29, "learning_rate": 0.00015771395859173743, "loss": 1.7042, "step": 64140 }, { "epoch": 13.29, "learning_rate": 0.00015761854784848776, "loss": 1.7023, "step": 64145 }, { "epoch": 13.29, "learning_rate": 0.00015752313710523804, "loss": 1.709, "step": 64150 }, { "epoch": 13.29, "learning_rate": 0.00015742772636198835, "loss": 1.7053, "step": 64155 }, { "epoch": 13.29, "learning_rate": 0.00015733231561873868, "loss": 1.7058, "step": 64160 }, { "epoch": 13.29, "learning_rate": 0.00015723690487548896, "loss": 1.7074, "step": 64165 }, { "epoch": 13.29, "learning_rate": 0.0001571414941322393, "loss": 1.7061, "step": 64170 }, { "epoch": 13.3, "learning_rate": 0.0001570460833889896, "loss": 1.701, "step": 64175 }, { "epoch": 13.3, "learning_rate": 0.0001569506726457399, "loss": 1.708, "step": 64180 }, { "epoch": 13.3, "learning_rate": 0.00015685526190249022, "loss": 1.7058, "step": 64185 }, { "epoch": 13.3, "learning_rate": 0.00015675985115924055, "loss": 1.7018, "step": 64190 }, { "epoch": 13.3, "learning_rate": 0.00015666444041599086, "loss": 1.6993, "step": 64195 }, { "epoch": 13.3, "learning_rate": 0.00015656902967274114, "loss": 1.7044, "step": 64200 }, { "epoch": 13.3, "learning_rate": 0.00015647361892949147, "loss": 1.7036, "step": 64205 }, { "epoch": 13.3, "learning_rate": 0.00015637820818624178, "loss": 1.7001, "step": 64210 }, { "epoch": 13.3, "learning_rate": 0.00015628279744299208, "loss": 1.7076, "step": 64215 }, { "epoch": 13.3, "learning_rate": 0.0001561873866997424, "loss": 1.706, "step": 64220 }, { "epoch": 13.31, "learning_rate": 0.00015609197595649273, "loss": 1.7055, "step": 64225 }, { "epoch": 13.31, "learning_rate": 0.000155996565213243, "loss": 1.7071, "step": 64230 }, { "epoch": 13.31, "learning_rate": 0.0001559011544699933, "loss": 1.7031, "step": 64235 }, { "epoch": 13.31, "learning_rate": 0.00015580574372674365, "loss": 1.7101, "step": 64240 }, { "epoch": 13.31, "learning_rate": 0.00015571033298349393, "loss": 1.708, "step": 64245 }, { "epoch": 13.31, "learning_rate": 0.00015561492224024426, "loss": 1.7033, "step": 64250 }, { "epoch": 13.31, "learning_rate": 0.00015551951149699457, "loss": 1.6994, "step": 64255 }, { "epoch": 13.31, "learning_rate": 0.00015542410075374487, "loss": 1.7009, "step": 64260 }, { "epoch": 13.31, "learning_rate": 0.00015532869001049518, "loss": 1.7021, "step": 64265 }, { "epoch": 13.31, "learning_rate": 0.00015523327926724551, "loss": 1.707, "step": 64270 }, { "epoch": 13.32, "learning_rate": 0.0001551378685239958, "loss": 1.7057, "step": 64275 }, { "epoch": 13.32, "learning_rate": 0.0001550424577807461, "loss": 1.705, "step": 64280 }, { "epoch": 13.32, "learning_rate": 0.00015494704703749644, "loss": 1.7065, "step": 64285 }, { "epoch": 13.32, "learning_rate": 0.00015485163629424671, "loss": 1.7065, "step": 64290 }, { "epoch": 13.32, "learning_rate": 0.00015475622555099705, "loss": 1.7069, "step": 64295 }, { "epoch": 13.32, "learning_rate": 0.00015466081480774736, "loss": 1.7046, "step": 64300 }, { "epoch": 13.32, "learning_rate": 0.0001545654040644977, "loss": 1.707, "step": 64305 }, { "epoch": 13.32, "learning_rate": 0.00015446999332124797, "loss": 1.705, "step": 64310 }, { "epoch": 13.32, "learning_rate": 0.00015437458257799828, "loss": 1.7012, "step": 64315 }, { "epoch": 13.33, "learning_rate": 0.0001542791718347486, "loss": 1.7045, "step": 64320 }, { "epoch": 13.33, "learning_rate": 0.0001541837610914989, "loss": 1.7056, "step": 64325 }, { "epoch": 13.33, "learning_rate": 0.00015408835034824922, "loss": 1.7049, "step": 64330 }, { "epoch": 13.33, "learning_rate": 0.00015399293960499953, "loss": 1.7061, "step": 64335 }, { "epoch": 13.33, "learning_rate": 0.00015389752886174984, "loss": 1.7019, "step": 64340 }, { "epoch": 13.33, "learning_rate": 0.00015380211811850014, "loss": 1.7044, "step": 64345 }, { "epoch": 13.33, "learning_rate": 0.00015370670737525045, "loss": 1.7062, "step": 64350 }, { "epoch": 13.33, "learning_rate": 0.00015361129663200076, "loss": 1.7041, "step": 64355 }, { "epoch": 13.33, "learning_rate": 0.00015351588588875107, "loss": 1.7008, "step": 64360 }, { "epoch": 13.33, "learning_rate": 0.0001534204751455014, "loss": 1.7032, "step": 64365 }, { "epoch": 13.34, "learning_rate": 0.00015332506440225168, "loss": 1.7068, "step": 64370 }, { "epoch": 13.34, "learning_rate": 0.000153229653659002, "loss": 1.7086, "step": 64375 }, { "epoch": 13.34, "learning_rate": 0.00015313424291575232, "loss": 1.7081, "step": 64380 }, { "epoch": 13.34, "learning_rate": 0.00015303883217250263, "loss": 1.7015, "step": 64385 }, { "epoch": 13.34, "learning_rate": 0.00015294342142925293, "loss": 1.7035, "step": 64390 }, { "epoch": 13.34, "learning_rate": 0.00015284801068600324, "loss": 1.7029, "step": 64395 }, { "epoch": 13.34, "learning_rate": 0.00015275259994275357, "loss": 1.7011, "step": 64400 }, { "epoch": 13.34, "learning_rate": 0.00015265718919950385, "loss": 1.6996, "step": 64405 }, { "epoch": 13.34, "learning_rate": 0.0001525617784562542, "loss": 1.7082, "step": 64410 }, { "epoch": 13.34, "learning_rate": 0.0001524663677130045, "loss": 1.7061, "step": 64415 }, { "epoch": 13.35, "learning_rate": 0.0001523709569697548, "loss": 1.7037, "step": 64420 }, { "epoch": 13.35, "learning_rate": 0.0001522755462265051, "loss": 1.7012, "step": 64425 }, { "epoch": 13.35, "learning_rate": 0.00015218013548325542, "loss": 1.7073, "step": 64430 }, { "epoch": 13.35, "learning_rate": 0.00015208472474000572, "loss": 1.7031, "step": 64435 }, { "epoch": 13.35, "learning_rate": 0.00015198931399675603, "loss": 1.7076, "step": 64440 }, { "epoch": 13.35, "learning_rate": 0.00015189390325350636, "loss": 1.7038, "step": 64445 }, { "epoch": 13.35, "learning_rate": 0.00015179849251025664, "loss": 1.7075, "step": 64450 }, { "epoch": 13.35, "learning_rate": 0.00015170308176700698, "loss": 1.7026, "step": 64455 }, { "epoch": 13.35, "learning_rate": 0.00015160767102375728, "loss": 1.7063, "step": 64460 }, { "epoch": 13.36, "learning_rate": 0.00015151226028050756, "loss": 1.7056, "step": 64465 }, { "epoch": 13.36, "learning_rate": 0.0001514168495372579, "loss": 1.7016, "step": 64470 }, { "epoch": 13.36, "learning_rate": 0.0001513214387940082, "loss": 1.7039, "step": 64475 }, { "epoch": 13.36, "learning_rate": 0.0001512260280507585, "loss": 1.7024, "step": 64480 }, { "epoch": 13.36, "learning_rate": 0.00015113061730750882, "loss": 1.7065, "step": 64485 }, { "epoch": 13.36, "learning_rate": 0.00015103520656425915, "loss": 1.7061, "step": 64490 }, { "epoch": 13.36, "learning_rate": 0.00015093979582100943, "loss": 1.703, "step": 64495 }, { "epoch": 13.36, "learning_rate": 0.00015084438507775977, "loss": 1.7044, "step": 64500 }, { "epoch": 13.36, "learning_rate": 0.00015074897433451007, "loss": 1.7086, "step": 64505 }, { "epoch": 13.36, "learning_rate": 0.00015065356359126038, "loss": 1.7059, "step": 64510 }, { "epoch": 13.37, "learning_rate": 0.0001505581528480107, "loss": 1.704, "step": 64515 }, { "epoch": 13.37, "learning_rate": 0.000150462742104761, "loss": 1.7003, "step": 64520 }, { "epoch": 13.37, "learning_rate": 0.00015036733136151133, "loss": 1.7091, "step": 64525 }, { "epoch": 13.37, "learning_rate": 0.0001502719206182616, "loss": 1.7028, "step": 64530 }, { "epoch": 13.37, "learning_rate": 0.00015017650987501194, "loss": 1.7067, "step": 64535 }, { "epoch": 13.37, "learning_rate": 0.00015008109913176225, "loss": 1.7117, "step": 64540 }, { "epoch": 13.37, "learning_rate": 0.00014998568838851253, "loss": 1.7004, "step": 64545 }, { "epoch": 13.37, "learning_rate": 0.00014989027764526286, "loss": 1.7063, "step": 64550 }, { "epoch": 13.37, "learning_rate": 0.00014979486690201317, "loss": 1.705, "step": 64555 }, { "epoch": 13.37, "learning_rate": 0.00014969945615876348, "loss": 1.7097, "step": 64560 }, { "epoch": 13.38, "learning_rate": 0.00014960404541551378, "loss": 1.7039, "step": 64565 }, { "epoch": 13.38, "learning_rate": 0.00014950863467226412, "loss": 1.7046, "step": 64570 }, { "epoch": 13.38, "learning_rate": 0.0001494132239290144, "loss": 1.7038, "step": 64575 }, { "epoch": 13.38, "learning_rate": 0.00014931781318576473, "loss": 1.7036, "step": 64580 }, { "epoch": 13.38, "learning_rate": 0.00014922240244251504, "loss": 1.7026, "step": 64585 }, { "epoch": 13.38, "learning_rate": 0.00014912699169926532, "loss": 1.7088, "step": 64590 }, { "epoch": 13.38, "learning_rate": 0.00014903158095601565, "loss": 1.7055, "step": 64595 }, { "epoch": 13.38, "learning_rate": 0.00014893617021276596, "loss": 1.7062, "step": 64600 }, { "epoch": 13.38, "learning_rate": 0.00014884075946951627, "loss": 1.7036, "step": 64605 }, { "epoch": 13.39, "learning_rate": 0.00014874534872626657, "loss": 1.704, "step": 64610 }, { "epoch": 13.39, "learning_rate": 0.0001486499379830169, "loss": 1.7026, "step": 64615 }, { "epoch": 13.39, "learning_rate": 0.0001485545272397672, "loss": 1.7043, "step": 64620 }, { "epoch": 13.39, "learning_rate": 0.0001484591164965175, "loss": 1.7059, "step": 64625 }, { "epoch": 13.39, "learning_rate": 0.00014836370575326783, "loss": 1.7073, "step": 64630 }, { "epoch": 13.39, "learning_rate": 0.00014826829501001813, "loss": 1.7016, "step": 64635 }, { "epoch": 13.39, "learning_rate": 0.00014817288426676844, "loss": 1.7085, "step": 64640 }, { "epoch": 13.39, "learning_rate": 0.00014807747352351875, "loss": 1.7007, "step": 64645 }, { "epoch": 13.39, "learning_rate": 0.00014798206278026908, "loss": 1.7059, "step": 64650 }, { "epoch": 13.39, "learning_rate": 0.00014788665203701936, "loss": 1.7049, "step": 64655 }, { "epoch": 13.4, "learning_rate": 0.00014779124129376967, "loss": 1.7074, "step": 64660 }, { "epoch": 13.4, "learning_rate": 0.00014769583055052, "loss": 1.7071, "step": 64665 }, { "epoch": 13.4, "learning_rate": 0.00014760041980727028, "loss": 1.7057, "step": 64670 }, { "epoch": 13.4, "learning_rate": 0.00014750500906402062, "loss": 1.7052, "step": 64675 }, { "epoch": 13.4, "learning_rate": 0.00014740959832077092, "loss": 1.7024, "step": 64680 }, { "epoch": 13.4, "learning_rate": 0.00014731418757752123, "loss": 1.7057, "step": 64685 }, { "epoch": 13.4, "learning_rate": 0.00014721877683427154, "loss": 1.7044, "step": 64690 }, { "epoch": 13.4, "learning_rate": 0.00014712336609102187, "loss": 1.7106, "step": 64695 }, { "epoch": 13.4, "learning_rate": 0.00014702795534777215, "loss": 1.7067, "step": 64700 }, { "epoch": 13.4, "learning_rate": 0.00014693254460452246, "loss": 1.702, "step": 64705 }, { "epoch": 13.41, "learning_rate": 0.0001468371338612728, "loss": 1.6987, "step": 64710 }, { "epoch": 13.41, "learning_rate": 0.00014674172311802307, "loss": 1.7071, "step": 64715 }, { "epoch": 13.41, "learning_rate": 0.0001466463123747734, "loss": 1.7061, "step": 64720 }, { "epoch": 13.41, "learning_rate": 0.0001465509016315237, "loss": 1.6981, "step": 64725 }, { "epoch": 13.41, "learning_rate": 0.00014645549088827405, "loss": 1.706, "step": 64730 }, { "epoch": 13.41, "learning_rate": 0.00014636008014502433, "loss": 1.7064, "step": 64735 }, { "epoch": 13.41, "learning_rate": 0.00014626466940177463, "loss": 1.7049, "step": 64740 }, { "epoch": 13.41, "learning_rate": 0.00014616925865852497, "loss": 1.7064, "step": 64745 }, { "epoch": 13.41, "learning_rate": 0.00014607384791527525, "loss": 1.7025, "step": 64750 }, { "epoch": 13.42, "learning_rate": 0.00014597843717202558, "loss": 1.7022, "step": 64755 }, { "epoch": 13.42, "learning_rate": 0.0001458830264287759, "loss": 1.708, "step": 64760 }, { "epoch": 13.42, "learning_rate": 0.0001457876156855262, "loss": 1.7078, "step": 64765 }, { "epoch": 13.42, "learning_rate": 0.0001456922049422765, "loss": 1.7033, "step": 64770 }, { "epoch": 13.42, "learning_rate": 0.0001455967941990268, "loss": 1.7043, "step": 64775 }, { "epoch": 13.42, "learning_rate": 0.00014550138345577712, "loss": 1.7106, "step": 64780 }, { "epoch": 13.42, "learning_rate": 0.00014540597271252742, "loss": 1.7078, "step": 64785 }, { "epoch": 13.42, "learning_rate": 0.00014531056196927776, "loss": 1.7056, "step": 64790 }, { "epoch": 13.42, "learning_rate": 0.00014521515122602804, "loss": 1.7071, "step": 64795 }, { "epoch": 13.42, "learning_rate": 0.00014511974048277837, "loss": 1.7065, "step": 64800 }, { "epoch": 13.43, "learning_rate": 0.00014502432973952868, "loss": 1.7072, "step": 64805 }, { "epoch": 13.43, "learning_rate": 0.00014492891899627898, "loss": 1.7036, "step": 64810 }, { "epoch": 13.43, "learning_rate": 0.0001448335082530293, "loss": 1.701, "step": 64815 }, { "epoch": 13.43, "learning_rate": 0.0001447380975097796, "loss": 1.697, "step": 64820 }, { "epoch": 13.43, "learning_rate": 0.00014464268676652993, "loss": 1.7036, "step": 64825 }, { "epoch": 13.43, "learning_rate": 0.0001445472760232802, "loss": 1.7011, "step": 64830 }, { "epoch": 13.43, "learning_rate": 0.00014445186528003055, "loss": 1.7045, "step": 64835 }, { "epoch": 13.43, "learning_rate": 0.00014435645453678085, "loss": 1.7033, "step": 64840 }, { "epoch": 13.43, "learning_rate": 0.00014426104379353116, "loss": 1.6964, "step": 64845 }, { "epoch": 13.43, "learning_rate": 0.00014416563305028147, "loss": 1.7101, "step": 64850 }, { "epoch": 13.44, "learning_rate": 0.00014407022230703177, "loss": 1.7046, "step": 64855 }, { "epoch": 13.44, "learning_rate": 0.00014397481156378208, "loss": 1.7055, "step": 64860 }, { "epoch": 13.44, "learning_rate": 0.0001438794008205324, "loss": 1.704, "step": 64865 }, { "epoch": 13.44, "learning_rate": 0.00014378399007728272, "loss": 1.7039, "step": 64870 }, { "epoch": 13.44, "learning_rate": 0.000143688579334033, "loss": 1.71, "step": 64875 }, { "epoch": 13.44, "learning_rate": 0.00014359316859078333, "loss": 1.7028, "step": 64880 }, { "epoch": 13.44, "learning_rate": 0.00014349775784753364, "loss": 1.7079, "step": 64885 }, { "epoch": 13.44, "learning_rate": 0.00014340234710428395, "loss": 1.7069, "step": 64890 }, { "epoch": 13.44, "learning_rate": 0.00014330693636103426, "loss": 1.7037, "step": 64895 }, { "epoch": 13.45, "learning_rate": 0.00014321152561778456, "loss": 1.7039, "step": 64900 }, { "epoch": 13.45, "learning_rate": 0.00014311611487453487, "loss": 1.7018, "step": 64905 }, { "epoch": 13.45, "learning_rate": 0.00014302070413128518, "loss": 1.6984, "step": 64910 }, { "epoch": 13.45, "learning_rate": 0.0001429252933880355, "loss": 1.7019, "step": 64915 }, { "epoch": 13.45, "learning_rate": 0.0001428298826447858, "loss": 1.7107, "step": 64920 }, { "epoch": 13.45, "learning_rate": 0.00014273447190153612, "loss": 1.7021, "step": 64925 }, { "epoch": 13.45, "learning_rate": 0.00014263906115828643, "loss": 1.7076, "step": 64930 }, { "epoch": 13.45, "learning_rate": 0.00014254365041503674, "loss": 1.7029, "step": 64935 }, { "epoch": 13.45, "learning_rate": 0.00014244823967178704, "loss": 1.7049, "step": 64940 }, { "epoch": 13.45, "learning_rate": 0.00014235282892853735, "loss": 1.7078, "step": 64945 }, { "epoch": 13.46, "learning_rate": 0.00014225741818528768, "loss": 1.7055, "step": 64950 }, { "epoch": 13.46, "learning_rate": 0.00014216200744203796, "loss": 1.7074, "step": 64955 }, { "epoch": 13.46, "learning_rate": 0.0001420665966987883, "loss": 1.7056, "step": 64960 }, { "epoch": 13.46, "learning_rate": 0.0001419711859555386, "loss": 1.7022, "step": 64965 }, { "epoch": 13.46, "learning_rate": 0.00014187577521228889, "loss": 1.6995, "step": 64970 }, { "epoch": 13.46, "learning_rate": 0.00014178036446903922, "loss": 1.7013, "step": 64975 }, { "epoch": 13.46, "learning_rate": 0.00014168495372578953, "loss": 1.7007, "step": 64980 }, { "epoch": 13.46, "learning_rate": 0.00014158954298253983, "loss": 1.703, "step": 64985 }, { "epoch": 13.46, "learning_rate": 0.00014149413223929014, "loss": 1.705, "step": 64990 }, { "epoch": 13.46, "learning_rate": 0.00014139872149604047, "loss": 1.7083, "step": 64995 }, { "epoch": 13.47, "learning_rate": 0.00014130331075279075, "loss": 1.7008, "step": 65000 }, { "epoch": 13.47, "learning_rate": 0.0001412079000095411, "loss": 1.7063, "step": 65005 }, { "epoch": 13.47, "learning_rate": 0.0001411124892662914, "loss": 1.7032, "step": 65010 }, { "epoch": 13.47, "learning_rate": 0.00014101707852304167, "loss": 1.7054, "step": 65015 }, { "epoch": 13.47, "learning_rate": 0.000140921667779792, "loss": 1.7024, "step": 65020 }, { "epoch": 13.47, "learning_rate": 0.00014082625703654232, "loss": 1.7015, "step": 65025 }, { "epoch": 13.47, "learning_rate": 0.00014073084629329265, "loss": 1.7036, "step": 65030 }, { "epoch": 13.47, "learning_rate": 0.00014063543555004293, "loss": 1.706, "step": 65035 }, { "epoch": 13.47, "learning_rate": 0.00014054002480679326, "loss": 1.7068, "step": 65040 }, { "epoch": 13.48, "learning_rate": 0.00014044461406354357, "loss": 1.705, "step": 65045 }, { "epoch": 13.48, "learning_rate": 0.00014034920332029385, "loss": 1.706, "step": 65050 }, { "epoch": 13.48, "learning_rate": 0.00014025379257704418, "loss": 1.7101, "step": 65055 }, { "epoch": 13.48, "learning_rate": 0.0001401583818337945, "loss": 1.7051, "step": 65060 }, { "epoch": 13.48, "learning_rate": 0.0001400629710905448, "loss": 1.701, "step": 65065 }, { "epoch": 13.48, "learning_rate": 0.0001399675603472951, "loss": 1.7035, "step": 65070 }, { "epoch": 13.48, "learning_rate": 0.00013987214960404544, "loss": 1.702, "step": 65075 }, { "epoch": 13.48, "learning_rate": 0.00013977673886079572, "loss": 1.71, "step": 65080 }, { "epoch": 13.48, "learning_rate": 0.00013968132811754603, "loss": 1.7005, "step": 65085 }, { "epoch": 13.48, "learning_rate": 0.00013958591737429636, "loss": 1.706, "step": 65090 }, { "epoch": 13.49, "learning_rate": 0.00013949050663104664, "loss": 1.7019, "step": 65095 }, { "epoch": 13.49, "learning_rate": 0.00013939509588779697, "loss": 1.7006, "step": 65100 }, { "epoch": 13.49, "learning_rate": 0.00013929968514454728, "loss": 1.7081, "step": 65105 }, { "epoch": 13.49, "learning_rate": 0.0001392042744012976, "loss": 1.7044, "step": 65110 }, { "epoch": 13.49, "learning_rate": 0.0001391088636580479, "loss": 1.7019, "step": 65115 }, { "epoch": 13.49, "learning_rate": 0.00013901345291479823, "loss": 1.7019, "step": 65120 }, { "epoch": 13.49, "learning_rate": 0.0001389180421715485, "loss": 1.7053, "step": 65125 }, { "epoch": 13.49, "learning_rate": 0.00013882263142829881, "loss": 1.7086, "step": 65130 }, { "epoch": 13.49, "learning_rate": 0.00013872722068504915, "loss": 1.7007, "step": 65135 }, { "epoch": 13.49, "learning_rate": 0.00013863180994179943, "loss": 1.7032, "step": 65140 }, { "epoch": 13.5, "learning_rate": 0.00013853639919854976, "loss": 1.7023, "step": 65145 }, { "epoch": 13.5, "learning_rate": 0.00013844098845530007, "loss": 1.7071, "step": 65150 }, { "epoch": 13.5, "learning_rate": 0.0001383455777120504, "loss": 1.7025, "step": 65155 }, { "epoch": 13.5, "learning_rate": 0.00013825016696880068, "loss": 1.7085, "step": 65160 }, { "epoch": 13.5, "learning_rate": 0.000138154756225551, "loss": 1.7021, "step": 65165 }, { "epoch": 13.5, "learning_rate": 0.00013805934548230132, "loss": 1.6978, "step": 65170 }, { "epoch": 13.5, "learning_rate": 0.0001379639347390516, "loss": 1.705, "step": 65175 }, { "epoch": 13.5, "learning_rate": 0.00013786852399580194, "loss": 1.701, "step": 65180 }, { "epoch": 13.5, "learning_rate": 0.00013777311325255224, "loss": 1.704, "step": 65185 }, { "epoch": 13.51, "learning_rate": 0.00013767770250930255, "loss": 1.7041, "step": 65190 }, { "epoch": 13.51, "learning_rate": 0.00013758229176605286, "loss": 1.6997, "step": 65195 }, { "epoch": 13.51, "learning_rate": 0.0001374868810228032, "loss": 1.7042, "step": 65200 }, { "epoch": 13.51, "learning_rate": 0.00013739147027955347, "loss": 1.7057, "step": 65205 }, { "epoch": 13.51, "learning_rate": 0.00013729605953630378, "loss": 1.7045, "step": 65210 }, { "epoch": 13.51, "learning_rate": 0.0001372006487930541, "loss": 1.7033, "step": 65215 }, { "epoch": 13.51, "learning_rate": 0.0001371052380498044, "loss": 1.7086, "step": 65220 }, { "epoch": 13.51, "learning_rate": 0.00013700982730655473, "loss": 1.6991, "step": 65225 }, { "epoch": 13.51, "learning_rate": 0.00013691441656330503, "loss": 1.6996, "step": 65230 }, { "epoch": 13.51, "learning_rate": 0.00013681900582005534, "loss": 1.7061, "step": 65235 }, { "epoch": 13.52, "learning_rate": 0.00013672359507680565, "loss": 1.7025, "step": 65240 }, { "epoch": 13.52, "learning_rate": 0.00013662818433355595, "loss": 1.7104, "step": 65245 }, { "epoch": 13.52, "learning_rate": 0.0001365327735903063, "loss": 1.7041, "step": 65250 }, { "epoch": 13.52, "learning_rate": 0.00013643736284705657, "loss": 1.7009, "step": 65255 }, { "epoch": 13.52, "learning_rate": 0.0001363419521038069, "loss": 1.7052, "step": 65260 }, { "epoch": 13.52, "learning_rate": 0.0001362465413605572, "loss": 1.7071, "step": 65265 }, { "epoch": 13.52, "learning_rate": 0.00013615113061730752, "loss": 1.7032, "step": 65270 }, { "epoch": 13.52, "learning_rate": 0.00013605571987405782, "loss": 1.7017, "step": 65275 }, { "epoch": 13.52, "learning_rate": 0.00013596030913080813, "loss": 1.7097, "step": 65280 }, { "epoch": 13.52, "learning_rate": 0.00013586489838755844, "loss": 1.707, "step": 65285 }, { "epoch": 13.53, "learning_rate": 0.00013576948764430874, "loss": 1.7025, "step": 65290 }, { "epoch": 13.53, "learning_rate": 0.00013567407690105908, "loss": 1.7013, "step": 65295 }, { "epoch": 13.53, "learning_rate": 0.00013557866615780936, "loss": 1.7013, "step": 65300 }, { "epoch": 13.53, "learning_rate": 0.0001354832554145597, "loss": 1.7044, "step": 65305 }, { "epoch": 13.53, "learning_rate": 0.00013538784467131, "loss": 1.7055, "step": 65310 }, { "epoch": 13.53, "learning_rate": 0.0001352924339280603, "loss": 1.7019, "step": 65315 }, { "epoch": 13.53, "learning_rate": 0.0001351970231848106, "loss": 1.7019, "step": 65320 }, { "epoch": 13.53, "learning_rate": 0.00013510161244156092, "loss": 1.6999, "step": 65325 }, { "epoch": 13.53, "learning_rate": 0.00013500620169831123, "loss": 1.7079, "step": 65330 }, { "epoch": 13.54, "learning_rate": 0.00013491079095506153, "loss": 1.701, "step": 65335 }, { "epoch": 13.54, "learning_rate": 0.00013481538021181187, "loss": 1.7034, "step": 65340 }, { "epoch": 13.54, "learning_rate": 0.00013471996946856215, "loss": 1.7012, "step": 65345 }, { "epoch": 13.54, "learning_rate": 0.00013462455872531248, "loss": 1.7058, "step": 65350 }, { "epoch": 13.54, "learning_rate": 0.0001345291479820628, "loss": 1.7048, "step": 65355 }, { "epoch": 13.54, "learning_rate": 0.0001344337372388131, "loss": 1.7079, "step": 65360 }, { "epoch": 13.54, "learning_rate": 0.0001343383264955634, "loss": 1.7011, "step": 65365 }, { "epoch": 13.54, "learning_rate": 0.0001342429157523137, "loss": 1.7031, "step": 65370 }, { "epoch": 13.54, "learning_rate": 0.00013414750500906404, "loss": 1.7, "step": 65375 }, { "epoch": 13.54, "learning_rate": 0.00013405209426581432, "loss": 1.7122, "step": 65380 }, { "epoch": 13.55, "learning_rate": 0.00013395668352256466, "loss": 1.7041, "step": 65385 }, { "epoch": 13.55, "learning_rate": 0.00013386127277931496, "loss": 1.7033, "step": 65390 }, { "epoch": 13.55, "learning_rate": 0.00013376586203606524, "loss": 1.7036, "step": 65395 }, { "epoch": 13.55, "learning_rate": 0.00013367045129281558, "loss": 1.7043, "step": 65400 }, { "epoch": 13.55, "learning_rate": 0.00013357504054956588, "loss": 1.702, "step": 65405 }, { "epoch": 13.55, "learning_rate": 0.0001334796298063162, "loss": 1.7045, "step": 65410 }, { "epoch": 13.55, "learning_rate": 0.0001333842190630665, "loss": 1.7074, "step": 65415 }, { "epoch": 13.55, "learning_rate": 0.00013328880831981683, "loss": 1.7045, "step": 65420 }, { "epoch": 13.55, "learning_rate": 0.0001331933975765671, "loss": 1.7061, "step": 65425 }, { "epoch": 13.56, "learning_rate": 0.00013309798683331744, "loss": 1.7034, "step": 65430 }, { "epoch": 13.56, "learning_rate": 0.00013300257609006775, "loss": 1.7017, "step": 65435 }, { "epoch": 13.56, "learning_rate": 0.00013290716534681803, "loss": 1.7031, "step": 65440 }, { "epoch": 13.56, "learning_rate": 0.00013281175460356837, "loss": 1.706, "step": 65445 }, { "epoch": 13.56, "learning_rate": 0.00013271634386031867, "loss": 1.7018, "step": 65450 }, { "epoch": 13.56, "learning_rate": 0.000132620933117069, "loss": 1.707, "step": 65455 }, { "epoch": 13.56, "learning_rate": 0.00013252552237381929, "loss": 1.7052, "step": 65460 }, { "epoch": 13.56, "learning_rate": 0.00013243011163056962, "loss": 1.7066, "step": 65465 }, { "epoch": 13.56, "learning_rate": 0.00013233470088731993, "loss": 1.6963, "step": 65470 }, { "epoch": 13.56, "learning_rate": 0.0001322392901440702, "loss": 1.7054, "step": 65475 }, { "epoch": 13.57, "learning_rate": 0.00013214387940082054, "loss": 1.7018, "step": 65480 }, { "epoch": 13.57, "learning_rate": 0.00013204846865757085, "loss": 1.701, "step": 65485 }, { "epoch": 13.57, "learning_rate": 0.00013195305791432115, "loss": 1.7044, "step": 65490 }, { "epoch": 13.57, "learning_rate": 0.00013185764717107146, "loss": 1.7115, "step": 65495 }, { "epoch": 13.57, "learning_rate": 0.0001317622364278218, "loss": 1.7065, "step": 65500 }, { "epoch": 13.57, "learning_rate": 0.00013166682568457207, "loss": 1.7095, "step": 65505 }, { "epoch": 13.57, "learning_rate": 0.0001315714149413224, "loss": 1.6999, "step": 65510 }, { "epoch": 13.57, "learning_rate": 0.00013147600419807272, "loss": 1.7044, "step": 65515 }, { "epoch": 13.57, "learning_rate": 0.000131380593454823, "loss": 1.6999, "step": 65520 }, { "epoch": 13.57, "learning_rate": 0.00013128518271157333, "loss": 1.7012, "step": 65525 }, { "epoch": 13.58, "learning_rate": 0.00013118977196832364, "loss": 1.7085, "step": 65530 }, { "epoch": 13.58, "learning_rate": 0.00013109436122507394, "loss": 1.706, "step": 65535 }, { "epoch": 13.58, "learning_rate": 0.00013099895048182425, "loss": 1.7046, "step": 65540 }, { "epoch": 13.58, "learning_rate": 0.00013090353973857458, "loss": 1.7058, "step": 65545 }, { "epoch": 13.58, "learning_rate": 0.00013080812899532486, "loss": 1.7041, "step": 65550 }, { "epoch": 13.58, "learning_rate": 0.00013071271825207517, "loss": 1.7019, "step": 65555 }, { "epoch": 13.58, "learning_rate": 0.0001306173075088255, "loss": 1.7013, "step": 65560 }, { "epoch": 13.58, "learning_rate": 0.0001305218967655758, "loss": 1.7017, "step": 65565 }, { "epoch": 13.58, "learning_rate": 0.00013042648602232612, "loss": 1.7059, "step": 65570 }, { "epoch": 13.59, "learning_rate": 0.00013033107527907643, "loss": 1.7079, "step": 65575 }, { "epoch": 13.59, "learning_rate": 0.00013023566453582676, "loss": 1.7023, "step": 65580 }, { "epoch": 13.59, "learning_rate": 0.00013014025379257704, "loss": 1.7064, "step": 65585 }, { "epoch": 13.59, "learning_rate": 0.00013004484304932735, "loss": 1.7101, "step": 65590 }, { "epoch": 13.59, "learning_rate": 0.00012994943230607768, "loss": 1.7064, "step": 65595 }, { "epoch": 13.59, "learning_rate": 0.00012985402156282796, "loss": 1.7017, "step": 65600 }, { "epoch": 13.59, "learning_rate": 0.0001297586108195783, "loss": 1.7019, "step": 65605 }, { "epoch": 13.59, "learning_rate": 0.0001296632000763286, "loss": 1.706, "step": 65610 }, { "epoch": 13.59, "learning_rate": 0.0001295677893330789, "loss": 1.7034, "step": 65615 }, { "epoch": 13.59, "learning_rate": 0.00012947237858982921, "loss": 1.7092, "step": 65620 }, { "epoch": 13.6, "learning_rate": 0.00012937696784657955, "loss": 1.7071, "step": 65625 }, { "epoch": 13.6, "learning_rate": 0.00012928155710332983, "loss": 1.7013, "step": 65630 }, { "epoch": 13.6, "learning_rate": 0.00012918614636008014, "loss": 1.7057, "step": 65635 }, { "epoch": 13.6, "learning_rate": 0.00012909073561683047, "loss": 1.7063, "step": 65640 }, { "epoch": 13.6, "learning_rate": 0.00012899532487358075, "loss": 1.703, "step": 65645 }, { "epoch": 13.6, "learning_rate": 0.00012889991413033108, "loss": 1.7041, "step": 65650 }, { "epoch": 13.6, "learning_rate": 0.0001288045033870814, "loss": 1.7013, "step": 65655 }, { "epoch": 13.6, "learning_rate": 0.0001287090926438317, "loss": 1.702, "step": 65660 }, { "epoch": 13.6, "learning_rate": 0.000128613681900582, "loss": 1.7025, "step": 65665 }, { "epoch": 13.6, "learning_rate": 0.0001285182711573323, "loss": 1.7, "step": 65670 }, { "epoch": 13.61, "learning_rate": 0.00012842286041408264, "loss": 1.7056, "step": 65675 }, { "epoch": 13.61, "learning_rate": 0.00012832744967083292, "loss": 1.7049, "step": 65680 }, { "epoch": 13.61, "learning_rate": 0.00012823203892758326, "loss": 1.7052, "step": 65685 }, { "epoch": 13.61, "learning_rate": 0.00012813662818433357, "loss": 1.7088, "step": 65690 }, { "epoch": 13.61, "learning_rate": 0.00012804121744108387, "loss": 1.7031, "step": 65695 }, { "epoch": 13.61, "learning_rate": 0.00012794580669783418, "loss": 1.7025, "step": 65700 }, { "epoch": 13.61, "learning_rate": 0.00012785039595458449, "loss": 1.7061, "step": 65705 }, { "epoch": 13.61, "learning_rate": 0.0001277549852113348, "loss": 1.7058, "step": 65710 }, { "epoch": 13.61, "learning_rate": 0.0001276595744680851, "loss": 1.7071, "step": 65715 }, { "epoch": 13.62, "learning_rate": 0.00012756416372483543, "loss": 1.7048, "step": 65720 }, { "epoch": 13.62, "learning_rate": 0.00012746875298158571, "loss": 1.7082, "step": 65725 }, { "epoch": 13.62, "learning_rate": 0.00012737334223833605, "loss": 1.7111, "step": 65730 }, { "epoch": 13.62, "learning_rate": 0.00012727793149508635, "loss": 1.7086, "step": 65735 }, { "epoch": 13.62, "learning_rate": 0.00012718252075183666, "loss": 1.7017, "step": 65740 }, { "epoch": 13.62, "learning_rate": 0.00012708711000858697, "loss": 1.7037, "step": 65745 }, { "epoch": 13.62, "learning_rate": 0.00012699169926533728, "loss": 1.7058, "step": 65750 }, { "epoch": 13.62, "learning_rate": 0.00012689628852208758, "loss": 1.7071, "step": 65755 }, { "epoch": 13.62, "learning_rate": 0.0001268008777788379, "loss": 1.7025, "step": 65760 }, { "epoch": 13.62, "learning_rate": 0.00012670546703558822, "loss": 1.7046, "step": 65765 }, { "epoch": 13.63, "learning_rate": 0.0001266100562923385, "loss": 1.7024, "step": 65770 }, { "epoch": 13.63, "learning_rate": 0.00012651464554908884, "loss": 1.7055, "step": 65775 }, { "epoch": 13.63, "learning_rate": 0.00012641923480583914, "loss": 1.7038, "step": 65780 }, { "epoch": 13.63, "learning_rate": 0.00012632382406258945, "loss": 1.7047, "step": 65785 }, { "epoch": 13.63, "learning_rate": 0.00012622841331933976, "loss": 1.7075, "step": 65790 }, { "epoch": 13.63, "learning_rate": 0.00012613300257609006, "loss": 1.699, "step": 65795 }, { "epoch": 13.63, "learning_rate": 0.0001260375918328404, "loss": 1.7061, "step": 65800 }, { "epoch": 13.63, "learning_rate": 0.00012594218108959068, "loss": 1.7044, "step": 65805 }, { "epoch": 13.63, "learning_rate": 0.000125846770346341, "loss": 1.708, "step": 65810 }, { "epoch": 13.63, "learning_rate": 0.00012575135960309132, "loss": 1.7037, "step": 65815 }, { "epoch": 13.64, "learning_rate": 0.00012565594885984163, "loss": 1.703, "step": 65820 }, { "epoch": 13.64, "learning_rate": 0.00012556053811659193, "loss": 1.7069, "step": 65825 }, { "epoch": 13.64, "learning_rate": 0.00012546512737334224, "loss": 1.701, "step": 65830 }, { "epoch": 13.64, "learning_rate": 0.00012536971663009255, "loss": 1.7088, "step": 65835 }, { "epoch": 13.64, "learning_rate": 0.00012527430588684285, "loss": 1.7011, "step": 65840 }, { "epoch": 13.64, "learning_rate": 0.0001251788951435932, "loss": 1.7022, "step": 65845 }, { "epoch": 13.64, "learning_rate": 0.00012508348440034347, "loss": 1.7102, "step": 65850 }, { "epoch": 13.64, "learning_rate": 0.0001249880736570938, "loss": 1.7043, "step": 65855 }, { "epoch": 13.64, "learning_rate": 0.0001248926629138441, "loss": 1.7052, "step": 65860 }, { "epoch": 13.65, "learning_rate": 0.00012479725217059441, "loss": 1.6993, "step": 65865 }, { "epoch": 13.65, "learning_rate": 0.00012470184142734472, "loss": 1.7019, "step": 65870 }, { "epoch": 13.65, "learning_rate": 0.00012460643068409503, "loss": 1.7099, "step": 65875 }, { "epoch": 13.65, "learning_rate": 0.00012451101994084534, "loss": 1.7067, "step": 65880 }, { "epoch": 13.65, "learning_rate": 0.00012441560919759564, "loss": 1.7089, "step": 65885 }, { "epoch": 13.65, "learning_rate": 0.00012432019845434595, "loss": 1.705, "step": 65890 }, { "epoch": 13.65, "learning_rate": 0.00012422478771109628, "loss": 1.7035, "step": 65895 }, { "epoch": 13.65, "learning_rate": 0.0001241293769678466, "loss": 1.7058, "step": 65900 }, { "epoch": 13.65, "learning_rate": 0.0001240339662245969, "loss": 1.7089, "step": 65905 }, { "epoch": 13.65, "learning_rate": 0.0001239385554813472, "loss": 1.7049, "step": 65910 }, { "epoch": 13.66, "learning_rate": 0.0001238431447380975, "loss": 1.7007, "step": 65915 }, { "epoch": 13.66, "learning_rate": 0.00012374773399484782, "loss": 1.7024, "step": 65920 }, { "epoch": 13.66, "learning_rate": 0.00012365232325159812, "loss": 1.7004, "step": 65925 }, { "epoch": 13.66, "learning_rate": 0.00012355691250834843, "loss": 1.702, "step": 65930 }, { "epoch": 13.66, "learning_rate": 0.00012346150176509877, "loss": 1.703, "step": 65935 }, { "epoch": 13.66, "learning_rate": 0.00012336609102184907, "loss": 1.7009, "step": 65940 }, { "epoch": 13.66, "learning_rate": 0.00012327068027859938, "loss": 1.7074, "step": 65945 }, { "epoch": 13.66, "learning_rate": 0.00012317526953534969, "loss": 1.7023, "step": 65950 }, { "epoch": 13.66, "learning_rate": 0.0001230798587921, "loss": 1.706, "step": 65955 }, { "epoch": 13.66, "learning_rate": 0.0001229844480488503, "loss": 1.7115, "step": 65960 }, { "epoch": 13.67, "learning_rate": 0.0001228890373056006, "loss": 1.7079, "step": 65965 }, { "epoch": 13.67, "learning_rate": 0.00012279362656235091, "loss": 1.7056, "step": 65970 }, { "epoch": 13.67, "learning_rate": 0.00012269821581910122, "loss": 1.7038, "step": 65975 }, { "epoch": 13.67, "learning_rate": 0.00012260280507585155, "loss": 1.6989, "step": 65980 }, { "epoch": 13.67, "learning_rate": 0.00012250739433260186, "loss": 1.7036, "step": 65985 }, { "epoch": 13.67, "learning_rate": 0.00012241198358935217, "loss": 1.7033, "step": 65990 }, { "epoch": 13.67, "learning_rate": 0.00012231657284610248, "loss": 1.7072, "step": 65995 }, { "epoch": 13.67, "learning_rate": 0.00012222116210285278, "loss": 1.708, "step": 66000 }, { "epoch": 13.67, "eval_accuracy": 0.5482875816993464, "eval_loss": 1.8998075723648071, "eval_runtime": 0.4965, "eval_samples_per_second": 302.138, "eval_steps_per_second": 2.014, "step": 66000 }, { "epoch": 13.67, "learning_rate": 0.0001221257513596031, "loss": 1.7088, "step": 66005 }, { "epoch": 13.68, "learning_rate": 0.0001220303406163534, "loss": 1.702, "step": 66010 }, { "epoch": 13.68, "learning_rate": 0.00012193492987310372, "loss": 1.7101, "step": 66015 }, { "epoch": 13.68, "learning_rate": 0.00012183951912985402, "loss": 1.7028, "step": 66020 }, { "epoch": 13.68, "learning_rate": 0.00012174410838660434, "loss": 1.7011, "step": 66025 }, { "epoch": 13.68, "learning_rate": 0.00012164869764335465, "loss": 1.7094, "step": 66030 }, { "epoch": 13.68, "learning_rate": 0.00012155328690010494, "loss": 1.7025, "step": 66035 }, { "epoch": 13.68, "learning_rate": 0.00012145787615685526, "loss": 1.7041, "step": 66040 }, { "epoch": 13.68, "learning_rate": 0.00012136246541360557, "loss": 1.6991, "step": 66045 }, { "epoch": 13.68, "learning_rate": 0.00012126705467035588, "loss": 1.7, "step": 66050 }, { "epoch": 13.68, "learning_rate": 0.0001211716439271062, "loss": 1.7085, "step": 66055 }, { "epoch": 13.69, "learning_rate": 0.0001210762331838565, "loss": 1.6993, "step": 66060 }, { "epoch": 13.69, "learning_rate": 0.00012098082244060681, "loss": 1.7002, "step": 66065 }, { "epoch": 13.69, "learning_rate": 0.00012088541169735713, "loss": 1.7012, "step": 66070 }, { "epoch": 13.69, "learning_rate": 0.00012079000095410743, "loss": 1.7051, "step": 66075 }, { "epoch": 13.69, "learning_rate": 0.00012069459021085775, "loss": 1.705, "step": 66080 }, { "epoch": 13.69, "learning_rate": 0.00012059917946760805, "loss": 1.7052, "step": 66085 }, { "epoch": 13.69, "learning_rate": 0.00012050376872435836, "loss": 1.705, "step": 66090 }, { "epoch": 13.69, "learning_rate": 0.00012040835798110868, "loss": 1.6993, "step": 66095 }, { "epoch": 13.69, "learning_rate": 0.00012031294723785899, "loss": 1.7088, "step": 66100 }, { "epoch": 13.69, "learning_rate": 0.0001202175364946093, "loss": 1.7035, "step": 66105 }, { "epoch": 13.7, "learning_rate": 0.00012012212575135962, "loss": 1.7075, "step": 66110 }, { "epoch": 13.7, "learning_rate": 0.00012002671500810991, "loss": 1.7023, "step": 66115 }, { "epoch": 13.7, "learning_rate": 0.00011993130426486022, "loss": 1.7091, "step": 66120 }, { "epoch": 13.7, "learning_rate": 0.00011983589352161054, "loss": 1.705, "step": 66125 }, { "epoch": 13.7, "learning_rate": 0.00011974048277836084, "loss": 1.7072, "step": 66130 }, { "epoch": 13.7, "learning_rate": 0.00011964507203511116, "loss": 1.7075, "step": 66135 }, { "epoch": 13.7, "learning_rate": 0.00011954966129186147, "loss": 1.7066, "step": 66140 }, { "epoch": 13.7, "learning_rate": 0.00011945425054861178, "loss": 1.7057, "step": 66145 }, { "epoch": 13.7, "learning_rate": 0.00011935883980536208, "loss": 1.7016, "step": 66150 }, { "epoch": 13.71, "learning_rate": 0.00011926342906211239, "loss": 1.6999, "step": 66155 }, { "epoch": 13.71, "learning_rate": 0.0001191680183188627, "loss": 1.7008, "step": 66160 }, { "epoch": 13.71, "learning_rate": 0.00011907260757561302, "loss": 1.7075, "step": 66165 }, { "epoch": 13.71, "learning_rate": 0.00011897719683236332, "loss": 1.7083, "step": 66170 }, { "epoch": 13.71, "learning_rate": 0.00011888178608911365, "loss": 1.7051, "step": 66175 }, { "epoch": 13.71, "learning_rate": 0.00011878637534586395, "loss": 1.7047, "step": 66180 }, { "epoch": 13.71, "learning_rate": 0.00011869096460261426, "loss": 1.7002, "step": 66185 }, { "epoch": 13.71, "learning_rate": 0.00011859555385936457, "loss": 1.703, "step": 66190 }, { "epoch": 13.71, "learning_rate": 0.00011850014311611487, "loss": 1.7029, "step": 66195 }, { "epoch": 13.71, "learning_rate": 0.00011840473237286518, "loss": 1.7022, "step": 66200 }, { "epoch": 13.72, "learning_rate": 0.0001183093216296155, "loss": 1.7058, "step": 66205 }, { "epoch": 13.72, "learning_rate": 0.00011821391088636581, "loss": 1.7073, "step": 66210 }, { "epoch": 13.72, "learning_rate": 0.00011811850014311611, "loss": 1.7031, "step": 66215 }, { "epoch": 13.72, "learning_rate": 0.00011802308939986643, "loss": 1.7033, "step": 66220 }, { "epoch": 13.72, "learning_rate": 0.00011792767865661674, "loss": 1.7083, "step": 66225 }, { "epoch": 13.72, "learning_rate": 0.00011783226791336705, "loss": 1.7005, "step": 66230 }, { "epoch": 13.72, "learning_rate": 0.00011773685717011736, "loss": 1.7024, "step": 66235 }, { "epoch": 13.72, "learning_rate": 0.00011764144642686766, "loss": 1.7047, "step": 66240 }, { "epoch": 13.72, "learning_rate": 0.00011754603568361798, "loss": 1.7106, "step": 66245 }, { "epoch": 13.72, "learning_rate": 0.00011745062494036829, "loss": 1.7021, "step": 66250 }, { "epoch": 13.73, "learning_rate": 0.0001173552141971186, "loss": 1.7083, "step": 66255 }, { "epoch": 13.73, "learning_rate": 0.00011725980345386892, "loss": 1.7059, "step": 66260 }, { "epoch": 13.73, "learning_rate": 0.00011716439271061922, "loss": 1.702, "step": 66265 }, { "epoch": 13.73, "learning_rate": 0.00011706898196736952, "loss": 1.7065, "step": 66270 }, { "epoch": 13.73, "learning_rate": 0.00011697357122411984, "loss": 1.7022, "step": 66275 }, { "epoch": 13.73, "learning_rate": 0.00011687816048087014, "loss": 1.7074, "step": 66280 }, { "epoch": 13.73, "learning_rate": 0.00011678274973762046, "loss": 1.7071, "step": 66285 }, { "epoch": 13.73, "learning_rate": 0.00011668733899437077, "loss": 1.7003, "step": 66290 }, { "epoch": 13.73, "learning_rate": 0.00011659192825112108, "loss": 1.7053, "step": 66295 }, { "epoch": 13.74, "learning_rate": 0.0001164965175078714, "loss": 1.7068, "step": 66300 }, { "epoch": 13.74, "learning_rate": 0.00011640110676462169, "loss": 1.705, "step": 66305 }, { "epoch": 13.74, "learning_rate": 0.000116305696021372, "loss": 1.7046, "step": 66310 }, { "epoch": 13.74, "learning_rate": 0.00011621028527812232, "loss": 1.7076, "step": 66315 }, { "epoch": 13.74, "learning_rate": 0.00011611487453487263, "loss": 1.6998, "step": 66320 }, { "epoch": 13.74, "learning_rate": 0.00011601946379162293, "loss": 1.706, "step": 66325 }, { "epoch": 13.74, "learning_rate": 0.00011592405304837325, "loss": 1.7034, "step": 66330 }, { "epoch": 13.74, "learning_rate": 0.00011582864230512356, "loss": 1.7021, "step": 66335 }, { "epoch": 13.74, "learning_rate": 0.00011573323156187388, "loss": 1.7004, "step": 66340 }, { "epoch": 13.74, "learning_rate": 0.00011563782081862417, "loss": 1.7059, "step": 66345 }, { "epoch": 13.75, "learning_rate": 0.00011554241007537448, "loss": 1.7028, "step": 66350 }, { "epoch": 13.75, "learning_rate": 0.0001154469993321248, "loss": 1.6997, "step": 66355 }, { "epoch": 13.75, "learning_rate": 0.00011535158858887511, "loss": 1.7017, "step": 66360 }, { "epoch": 13.75, "learning_rate": 0.00011525617784562542, "loss": 1.7041, "step": 66365 }, { "epoch": 13.75, "learning_rate": 0.00011516076710237574, "loss": 1.699, "step": 66370 }, { "epoch": 13.75, "learning_rate": 0.00011506535635912604, "loss": 1.7087, "step": 66375 }, { "epoch": 13.75, "learning_rate": 0.00011496994561587635, "loss": 1.7001, "step": 66380 }, { "epoch": 13.75, "learning_rate": 0.00011487453487262666, "loss": 1.7027, "step": 66385 }, { "epoch": 13.75, "learning_rate": 0.00011477912412937696, "loss": 1.7044, "step": 66390 }, { "epoch": 13.75, "learning_rate": 0.00011468371338612728, "loss": 1.7036, "step": 66395 }, { "epoch": 13.76, "learning_rate": 0.00011458830264287759, "loss": 1.7066, "step": 66400 }, { "epoch": 13.76, "learning_rate": 0.0001144928918996279, "loss": 1.6976, "step": 66405 }, { "epoch": 13.76, "learning_rate": 0.00011439748115637822, "loss": 1.7008, "step": 66410 }, { "epoch": 13.76, "learning_rate": 0.00011430207041312853, "loss": 1.7095, "step": 66415 }, { "epoch": 13.76, "learning_rate": 0.00011420665966987883, "loss": 1.71, "step": 66420 }, { "epoch": 13.76, "learning_rate": 0.00011411124892662914, "loss": 1.705, "step": 66425 }, { "epoch": 13.76, "learning_rate": 0.00011401583818337945, "loss": 1.6999, "step": 66430 }, { "epoch": 13.76, "learning_rate": 0.00011392042744012975, "loss": 1.7069, "step": 66435 }, { "epoch": 13.76, "learning_rate": 0.00011382501669688007, "loss": 1.7034, "step": 66440 }, { "epoch": 13.77, "learning_rate": 0.00011372960595363038, "loss": 1.7023, "step": 66445 }, { "epoch": 13.77, "learning_rate": 0.0001136341952103807, "loss": 1.7014, "step": 66450 }, { "epoch": 13.77, "learning_rate": 0.00011353878446713101, "loss": 1.7095, "step": 66455 }, { "epoch": 13.77, "learning_rate": 0.0001134433737238813, "loss": 1.7047, "step": 66460 }, { "epoch": 13.77, "learning_rate": 0.00011334796298063162, "loss": 1.7004, "step": 66465 }, { "epoch": 13.77, "learning_rate": 0.00011325255223738193, "loss": 1.705, "step": 66470 }, { "epoch": 13.77, "learning_rate": 0.00011315714149413223, "loss": 1.7056, "step": 66475 }, { "epoch": 13.77, "learning_rate": 0.00011306173075088256, "loss": 1.7048, "step": 66480 }, { "epoch": 13.77, "learning_rate": 0.00011296632000763286, "loss": 1.7064, "step": 66485 }, { "epoch": 13.77, "learning_rate": 0.00011287090926438318, "loss": 1.7011, "step": 66490 }, { "epoch": 13.78, "learning_rate": 0.00011277549852113349, "loss": 1.7018, "step": 66495 }, { "epoch": 13.78, "learning_rate": 0.00011268008777788378, "loss": 1.7007, "step": 66500 }, { "epoch": 13.78, "learning_rate": 0.0001125846770346341, "loss": 1.7041, "step": 66505 }, { "epoch": 13.78, "learning_rate": 0.00011248926629138441, "loss": 1.6976, "step": 66510 }, { "epoch": 13.78, "learning_rate": 0.00011239385554813472, "loss": 1.7023, "step": 66515 }, { "epoch": 13.78, "learning_rate": 0.00011229844480488504, "loss": 1.7057, "step": 66520 }, { "epoch": 13.78, "learning_rate": 0.00011220303406163534, "loss": 1.7018, "step": 66525 }, { "epoch": 13.78, "learning_rate": 0.00011210762331838565, "loss": 1.706, "step": 66530 }, { "epoch": 13.78, "learning_rate": 0.00011201221257513597, "loss": 1.7011, "step": 66535 }, { "epoch": 13.78, "learning_rate": 0.00011191680183188627, "loss": 1.7063, "step": 66540 }, { "epoch": 13.79, "learning_rate": 0.00011182139108863657, "loss": 1.7071, "step": 66545 }, { "epoch": 13.79, "learning_rate": 0.00011172598034538689, "loss": 1.7066, "step": 66550 }, { "epoch": 13.79, "learning_rate": 0.0001116305696021372, "loss": 1.7037, "step": 66555 }, { "epoch": 13.79, "learning_rate": 0.00011153515885888752, "loss": 1.704, "step": 66560 }, { "epoch": 13.79, "learning_rate": 0.00011143974811563783, "loss": 1.7017, "step": 66565 }, { "epoch": 13.79, "learning_rate": 0.00011134433737238813, "loss": 1.703, "step": 66570 }, { "epoch": 13.79, "learning_rate": 0.00011124892662913845, "loss": 1.6992, "step": 66575 }, { "epoch": 13.79, "learning_rate": 0.00011115351588588875, "loss": 1.7079, "step": 66580 }, { "epoch": 13.79, "learning_rate": 0.00011105810514263905, "loss": 1.7009, "step": 66585 }, { "epoch": 13.8, "learning_rate": 0.00011096269439938937, "loss": 1.7029, "step": 66590 }, { "epoch": 13.8, "learning_rate": 0.00011086728365613968, "loss": 1.7002, "step": 66595 }, { "epoch": 13.8, "learning_rate": 0.00011077187291289, "loss": 1.699, "step": 66600 }, { "epoch": 13.8, "learning_rate": 0.00011067646216964031, "loss": 1.7057, "step": 66605 }, { "epoch": 13.8, "learning_rate": 0.00011058105142639062, "loss": 1.6943, "step": 66610 }, { "epoch": 13.8, "learning_rate": 0.00011048564068314092, "loss": 1.7006, "step": 66615 }, { "epoch": 13.8, "learning_rate": 0.00011039022993989123, "loss": 1.7088, "step": 66620 }, { "epoch": 13.8, "learning_rate": 0.00011029481919664154, "loss": 1.7057, "step": 66625 }, { "epoch": 13.8, "learning_rate": 0.00011019940845339186, "loss": 1.7057, "step": 66630 }, { "epoch": 13.8, "learning_rate": 0.00011010399771014216, "loss": 1.7051, "step": 66635 }, { "epoch": 13.81, "learning_rate": 0.00011000858696689247, "loss": 1.7063, "step": 66640 }, { "epoch": 13.81, "learning_rate": 0.00010991317622364279, "loss": 1.7, "step": 66645 }, { "epoch": 13.81, "learning_rate": 0.0001098177654803931, "loss": 1.7002, "step": 66650 }, { "epoch": 13.81, "learning_rate": 0.0001097223547371434, "loss": 1.7042, "step": 66655 }, { "epoch": 13.81, "learning_rate": 0.00010962694399389371, "loss": 1.7064, "step": 66660 }, { "epoch": 13.81, "learning_rate": 0.00010953153325064402, "loss": 1.703, "step": 66665 }, { "epoch": 13.81, "learning_rate": 0.00010943612250739434, "loss": 1.7032, "step": 66670 }, { "epoch": 13.81, "learning_rate": 0.00010934071176414465, "loss": 1.7063, "step": 66675 }, { "epoch": 13.81, "learning_rate": 0.00010924530102089495, "loss": 1.7039, "step": 66680 }, { "epoch": 13.81, "learning_rate": 0.00010914989027764527, "loss": 1.7017, "step": 66685 }, { "epoch": 13.82, "learning_rate": 0.00010905447953439558, "loss": 1.7046, "step": 66690 }, { "epoch": 13.82, "learning_rate": 0.00010895906879114587, "loss": 1.7027, "step": 66695 }, { "epoch": 13.82, "learning_rate": 0.0001088636580478962, "loss": 1.7054, "step": 66700 }, { "epoch": 13.82, "learning_rate": 0.0001087682473046465, "loss": 1.7062, "step": 66705 }, { "epoch": 13.82, "learning_rate": 0.00010867283656139682, "loss": 1.7085, "step": 66710 }, { "epoch": 13.82, "learning_rate": 0.00010857742581814713, "loss": 1.7016, "step": 66715 }, { "epoch": 13.82, "learning_rate": 0.00010848201507489744, "loss": 1.7006, "step": 66720 }, { "epoch": 13.82, "learning_rate": 0.00010838660433164776, "loss": 1.703, "step": 66725 }, { "epoch": 13.82, "learning_rate": 0.00010829119358839806, "loss": 1.7118, "step": 66730 }, { "epoch": 13.83, "learning_rate": 0.00010819578284514836, "loss": 1.7034, "step": 66735 }, { "epoch": 13.83, "learning_rate": 0.00010810037210189868, "loss": 1.7019, "step": 66740 }, { "epoch": 13.83, "learning_rate": 0.00010800496135864898, "loss": 1.7057, "step": 66745 }, { "epoch": 13.83, "learning_rate": 0.00010790955061539929, "loss": 1.7058, "step": 66750 }, { "epoch": 13.83, "learning_rate": 0.00010781413987214961, "loss": 1.7004, "step": 66755 }, { "epoch": 13.83, "learning_rate": 0.00010771872912889992, "loss": 1.7041, "step": 66760 }, { "epoch": 13.83, "learning_rate": 0.00010762331838565024, "loss": 1.7023, "step": 66765 }, { "epoch": 13.83, "learning_rate": 0.00010752790764240053, "loss": 1.7068, "step": 66770 }, { "epoch": 13.83, "learning_rate": 0.00010743249689915084, "loss": 1.7014, "step": 66775 }, { "epoch": 13.83, "learning_rate": 0.00010733708615590116, "loss": 1.7, "step": 66780 }, { "epoch": 13.84, "learning_rate": 0.00010724167541265147, "loss": 1.7074, "step": 66785 }, { "epoch": 13.84, "learning_rate": 0.00010714626466940177, "loss": 1.7007, "step": 66790 }, { "epoch": 13.84, "learning_rate": 0.00010705085392615209, "loss": 1.7106, "step": 66795 }, { "epoch": 13.84, "learning_rate": 0.0001069554431829024, "loss": 1.7039, "step": 66800 }, { "epoch": 13.84, "learning_rate": 0.0001068600324396527, "loss": 1.7023, "step": 66805 }, { "epoch": 13.84, "learning_rate": 0.00010676462169640301, "loss": 1.708, "step": 66810 }, { "epoch": 13.84, "learning_rate": 0.00010666921095315332, "loss": 1.7025, "step": 66815 }, { "epoch": 13.84, "learning_rate": 0.00010657380020990364, "loss": 1.7026, "step": 66820 }, { "epoch": 13.84, "learning_rate": 0.00010647838946665395, "loss": 1.7039, "step": 66825 }, { "epoch": 13.85, "learning_rate": 0.00010638297872340425, "loss": 1.6998, "step": 66830 }, { "epoch": 13.85, "learning_rate": 0.00010628756798015457, "loss": 1.7015, "step": 66835 }, { "epoch": 13.85, "learning_rate": 0.00010619215723690488, "loss": 1.7035, "step": 66840 }, { "epoch": 13.85, "learning_rate": 0.00010609674649365519, "loss": 1.7063, "step": 66845 }, { "epoch": 13.85, "learning_rate": 0.0001060013357504055, "loss": 1.6986, "step": 66850 }, { "epoch": 13.85, "learning_rate": 0.0001059059250071558, "loss": 1.7036, "step": 66855 }, { "epoch": 13.85, "learning_rate": 0.00010581051426390611, "loss": 1.7042, "step": 66860 }, { "epoch": 13.85, "learning_rate": 0.00010571510352065643, "loss": 1.7007, "step": 66865 }, { "epoch": 13.85, "learning_rate": 0.00010561969277740674, "loss": 1.7039, "step": 66870 }, { "epoch": 13.85, "learning_rate": 0.00010552428203415706, "loss": 1.7043, "step": 66875 }, { "epoch": 13.86, "learning_rate": 0.00010542887129090736, "loss": 1.7037, "step": 66880 }, { "epoch": 13.86, "learning_rate": 0.00010533346054765767, "loss": 1.7088, "step": 66885 }, { "epoch": 13.86, "learning_rate": 0.00010523804980440798, "loss": 1.7081, "step": 66890 }, { "epoch": 13.86, "learning_rate": 0.00010514263906115828, "loss": 1.7012, "step": 66895 }, { "epoch": 13.86, "learning_rate": 0.00010504722831790859, "loss": 1.7042, "step": 66900 }, { "epoch": 13.86, "learning_rate": 0.00010495181757465891, "loss": 1.7047, "step": 66905 }, { "epoch": 13.86, "learning_rate": 0.00010485640683140922, "loss": 1.7062, "step": 66910 }, { "epoch": 13.86, "learning_rate": 0.00010476099608815954, "loss": 1.7045, "step": 66915 }, { "epoch": 13.86, "learning_rate": 0.00010466558534490985, "loss": 1.7023, "step": 66920 }, { "epoch": 13.86, "learning_rate": 0.00010457017460166014, "loss": 1.702, "step": 66925 }, { "epoch": 13.87, "learning_rate": 0.00010447476385841046, "loss": 1.7011, "step": 66930 }, { "epoch": 13.87, "learning_rate": 0.00010437935311516077, "loss": 1.7099, "step": 66935 }, { "epoch": 13.87, "learning_rate": 0.00010428394237191107, "loss": 1.7077, "step": 66940 }, { "epoch": 13.87, "learning_rate": 0.0001041885316286614, "loss": 1.7021, "step": 66945 }, { "epoch": 13.87, "learning_rate": 0.0001040931208854117, "loss": 1.703, "step": 66950 }, { "epoch": 13.87, "learning_rate": 0.00010399771014216201, "loss": 1.6991, "step": 66955 }, { "epoch": 13.87, "learning_rate": 0.00010390229939891233, "loss": 1.7024, "step": 66960 }, { "epoch": 13.87, "learning_rate": 0.00010380688865566262, "loss": 1.7072, "step": 66965 }, { "epoch": 13.87, "learning_rate": 0.00010371147791241294, "loss": 1.7078, "step": 66970 }, { "epoch": 13.88, "learning_rate": 0.00010361606716916325, "loss": 1.7015, "step": 66975 }, { "epoch": 13.88, "learning_rate": 0.00010352065642591356, "loss": 1.703, "step": 66980 }, { "epoch": 13.88, "learning_rate": 0.00010342524568266388, "loss": 1.7008, "step": 66985 }, { "epoch": 13.88, "learning_rate": 0.00010332983493941418, "loss": 1.7104, "step": 66990 }, { "epoch": 13.88, "learning_rate": 0.00010323442419616449, "loss": 1.7044, "step": 66995 }, { "epoch": 13.88, "learning_rate": 0.00010313901345291481, "loss": 1.7026, "step": 67000 }, { "epoch": 13.88, "learning_rate": 0.0001030436027096651, "loss": 1.7035, "step": 67005 }, { "epoch": 13.88, "learning_rate": 0.00010294819196641541, "loss": 1.7091, "step": 67010 }, { "epoch": 13.88, "learning_rate": 0.00010285278122316573, "loss": 1.7051, "step": 67015 }, { "epoch": 13.88, "learning_rate": 0.00010275737047991604, "loss": 1.7073, "step": 67020 }, { "epoch": 13.89, "learning_rate": 0.00010266195973666636, "loss": 1.6981, "step": 67025 }, { "epoch": 13.89, "learning_rate": 0.00010256654899341667, "loss": 1.7061, "step": 67030 }, { "epoch": 13.89, "learning_rate": 0.00010247113825016697, "loss": 1.7037, "step": 67035 }, { "epoch": 13.89, "learning_rate": 0.00010237572750691729, "loss": 1.702, "step": 67040 }, { "epoch": 13.89, "learning_rate": 0.00010228031676366759, "loss": 1.6996, "step": 67045 }, { "epoch": 13.89, "learning_rate": 0.00010218490602041789, "loss": 1.7088, "step": 67050 }, { "epoch": 13.89, "learning_rate": 0.00010208949527716821, "loss": 1.7074, "step": 67055 }, { "epoch": 13.89, "learning_rate": 0.00010199408453391852, "loss": 1.7072, "step": 67060 }, { "epoch": 13.89, "learning_rate": 0.00010189867379066883, "loss": 1.7048, "step": 67065 }, { "epoch": 13.89, "learning_rate": 0.00010180326304741915, "loss": 1.7049, "step": 67070 }, { "epoch": 13.9, "learning_rate": 0.00010170785230416945, "loss": 1.706, "step": 67075 }, { "epoch": 13.9, "learning_rate": 0.00010161244156091976, "loss": 1.7014, "step": 67080 }, { "epoch": 13.9, "learning_rate": 0.00010151703081767007, "loss": 1.7, "step": 67085 }, { "epoch": 13.9, "learning_rate": 0.00010142162007442038, "loss": 1.7013, "step": 67090 }, { "epoch": 13.9, "learning_rate": 0.0001013262093311707, "loss": 1.698, "step": 67095 }, { "epoch": 13.9, "learning_rate": 0.000101230798587921, "loss": 1.7031, "step": 67100 }, { "epoch": 13.9, "learning_rate": 0.00010113538784467131, "loss": 1.7054, "step": 67105 }, { "epoch": 13.9, "learning_rate": 0.00010103997710142163, "loss": 1.7047, "step": 67110 }, { "epoch": 13.9, "learning_rate": 0.00010094456635817194, "loss": 1.7076, "step": 67115 }, { "epoch": 13.91, "learning_rate": 0.00010084915561492223, "loss": 1.7026, "step": 67120 }, { "epoch": 13.91, "learning_rate": 0.00010075374487167255, "loss": 1.7065, "step": 67125 }, { "epoch": 13.91, "learning_rate": 0.00010065833412842286, "loss": 1.7072, "step": 67130 }, { "epoch": 13.91, "learning_rate": 0.00010056292338517318, "loss": 1.7017, "step": 67135 }, { "epoch": 13.91, "learning_rate": 0.00010046751264192348, "loss": 1.7047, "step": 67140 }, { "epoch": 13.91, "learning_rate": 0.00010037210189867379, "loss": 1.7056, "step": 67145 }, { "epoch": 13.91, "learning_rate": 0.00010027669115542411, "loss": 1.7009, "step": 67150 }, { "epoch": 13.91, "learning_rate": 0.00010018128041217442, "loss": 1.7042, "step": 67155 }, { "epoch": 13.91, "learning_rate": 0.00010008586966892471, "loss": 1.7031, "step": 67160 }, { "epoch": 13.91, "learning_rate": 9.999045892567503e-05, "loss": 1.7048, "step": 67165 }, { "epoch": 13.92, "learning_rate": 9.989504818242534e-05, "loss": 1.7021, "step": 67170 }, { "epoch": 13.92, "learning_rate": 9.979963743917565e-05, "loss": 1.7028, "step": 67175 }, { "epoch": 13.92, "learning_rate": 9.970422669592597e-05, "loss": 1.7057, "step": 67180 }, { "epoch": 13.92, "learning_rate": 9.960881595267627e-05, "loss": 1.7028, "step": 67185 }, { "epoch": 13.92, "learning_rate": 9.95134052094266e-05, "loss": 1.7043, "step": 67190 }, { "epoch": 13.92, "learning_rate": 9.94179944661769e-05, "loss": 1.701, "step": 67195 }, { "epoch": 13.92, "learning_rate": 9.93225837229272e-05, "loss": 1.7037, "step": 67200 }, { "epoch": 13.92, "learning_rate": 9.922717297967751e-05, "loss": 1.7064, "step": 67205 }, { "epoch": 13.92, "learning_rate": 9.913176223642782e-05, "loss": 1.7067, "step": 67210 }, { "epoch": 13.92, "learning_rate": 9.903635149317813e-05, "loss": 1.7079, "step": 67215 }, { "epoch": 13.93, "learning_rate": 9.894094074992845e-05, "loss": 1.697, "step": 67220 }, { "epoch": 13.93, "learning_rate": 9.884553000667876e-05, "loss": 1.7093, "step": 67225 }, { "epoch": 13.93, "learning_rate": 9.875011926342906e-05, "loss": 1.7052, "step": 67230 }, { "epoch": 13.93, "learning_rate": 9.865470852017937e-05, "loss": 1.7035, "step": 67235 }, { "epoch": 13.93, "learning_rate": 9.855929777692968e-05, "loss": 1.7022, "step": 67240 }, { "epoch": 13.93, "learning_rate": 9.846388703368e-05, "loss": 1.7075, "step": 67245 }, { "epoch": 13.93, "learning_rate": 9.83684762904303e-05, "loss": 1.7056, "step": 67250 }, { "epoch": 13.93, "learning_rate": 9.827306554718061e-05, "loss": 1.7044, "step": 67255 }, { "epoch": 13.93, "learning_rate": 9.817765480393093e-05, "loss": 1.705, "step": 67260 }, { "epoch": 13.94, "learning_rate": 9.808224406068124e-05, "loss": 1.6983, "step": 67265 }, { "epoch": 13.94, "learning_rate": 9.798683331743155e-05, "loss": 1.6991, "step": 67270 }, { "epoch": 13.94, "learning_rate": 9.789142257418185e-05, "loss": 1.7003, "step": 67275 }, { "epoch": 13.94, "learning_rate": 9.779601183093216e-05, "loss": 1.7099, "step": 67280 }, { "epoch": 13.94, "learning_rate": 9.770060108768247e-05, "loss": 1.7077, "step": 67285 }, { "epoch": 13.94, "learning_rate": 9.760519034443279e-05, "loss": 1.7037, "step": 67290 }, { "epoch": 13.94, "learning_rate": 9.750977960118309e-05, "loss": 1.7035, "step": 67295 }, { "epoch": 13.94, "learning_rate": 9.741436885793341e-05, "loss": 1.7034, "step": 67300 }, { "epoch": 13.94, "learning_rate": 9.731895811468372e-05, "loss": 1.7046, "step": 67305 }, { "epoch": 13.94, "learning_rate": 9.722354737143403e-05, "loss": 1.7021, "step": 67310 }, { "epoch": 13.95, "learning_rate": 9.712813662818433e-05, "loss": 1.7042, "step": 67315 }, { "epoch": 13.95, "learning_rate": 9.703272588493464e-05, "loss": 1.7043, "step": 67320 }, { "epoch": 13.95, "learning_rate": 9.693731514168495e-05, "loss": 1.7021, "step": 67325 }, { "epoch": 13.95, "learning_rate": 9.684190439843527e-05, "loss": 1.7047, "step": 67330 }, { "epoch": 13.95, "learning_rate": 9.674649365518558e-05, "loss": 1.7059, "step": 67335 }, { "epoch": 13.95, "learning_rate": 9.66510829119359e-05, "loss": 1.7006, "step": 67340 }, { "epoch": 13.95, "learning_rate": 9.65556721686862e-05, "loss": 1.704, "step": 67345 }, { "epoch": 13.95, "learning_rate": 9.646026142543651e-05, "loss": 1.7036, "step": 67350 }, { "epoch": 13.95, "learning_rate": 9.636485068218682e-05, "loss": 1.6993, "step": 67355 }, { "epoch": 13.95, "learning_rate": 9.626943993893712e-05, "loss": 1.7077, "step": 67360 }, { "epoch": 13.96, "learning_rate": 9.617402919568743e-05, "loss": 1.7045, "step": 67365 }, { "epoch": 13.96, "learning_rate": 9.607861845243775e-05, "loss": 1.7002, "step": 67370 }, { "epoch": 13.96, "learning_rate": 9.598320770918806e-05, "loss": 1.7019, "step": 67375 }, { "epoch": 13.96, "learning_rate": 9.588779696593836e-05, "loss": 1.7031, "step": 67380 }, { "epoch": 13.96, "learning_rate": 9.579238622268868e-05, "loss": 1.7043, "step": 67385 }, { "epoch": 13.96, "learning_rate": 9.569697547943898e-05, "loss": 1.7047, "step": 67390 }, { "epoch": 13.96, "learning_rate": 9.56015647361893e-05, "loss": 1.7027, "step": 67395 }, { "epoch": 13.96, "learning_rate": 9.55061539929396e-05, "loss": 1.7058, "step": 67400 }, { "epoch": 13.96, "learning_rate": 9.541074324968991e-05, "loss": 1.7035, "step": 67405 }, { "epoch": 13.97, "learning_rate": 9.531533250644023e-05, "loss": 1.708, "step": 67410 }, { "epoch": 13.97, "learning_rate": 9.521992176319054e-05, "loss": 1.7013, "step": 67415 }, { "epoch": 13.97, "learning_rate": 9.512451101994085e-05, "loss": 1.7, "step": 67420 }, { "epoch": 13.97, "learning_rate": 9.502910027669117e-05, "loss": 1.7036, "step": 67425 }, { "epoch": 13.97, "learning_rate": 9.493368953344146e-05, "loss": 1.6989, "step": 67430 }, { "epoch": 13.97, "learning_rate": 9.483827879019177e-05, "loss": 1.7057, "step": 67435 }, { "epoch": 13.97, "learning_rate": 9.474286804694209e-05, "loss": 1.7011, "step": 67440 }, { "epoch": 13.97, "learning_rate": 9.46474573036924e-05, "loss": 1.7006, "step": 67445 }, { "epoch": 13.97, "learning_rate": 9.455204656044272e-05, "loss": 1.6994, "step": 67450 }, { "epoch": 13.97, "learning_rate": 9.445663581719302e-05, "loss": 1.7036, "step": 67455 }, { "epoch": 13.98, "learning_rate": 9.436122507394333e-05, "loss": 1.7036, "step": 67460 }, { "epoch": 13.98, "learning_rate": 9.426581433069365e-05, "loss": 1.7033, "step": 67465 }, { "epoch": 13.98, "learning_rate": 9.417040358744394e-05, "loss": 1.7063, "step": 67470 }, { "epoch": 13.98, "learning_rate": 9.407499284419425e-05, "loss": 1.7058, "step": 67475 }, { "epoch": 13.98, "learning_rate": 9.397958210094457e-05, "loss": 1.7002, "step": 67480 }, { "epoch": 13.98, "learning_rate": 9.388417135769488e-05, "loss": 1.7068, "step": 67485 }, { "epoch": 13.98, "learning_rate": 9.378876061444518e-05, "loss": 1.6985, "step": 67490 }, { "epoch": 13.98, "learning_rate": 9.36933498711955e-05, "loss": 1.7033, "step": 67495 }, { "epoch": 13.98, "learning_rate": 9.359793912794581e-05, "loss": 1.706, "step": 67500 }, { "epoch": 13.98, "learning_rate": 9.350252838469613e-05, "loss": 1.7069, "step": 67505 }, { "epoch": 13.99, "learning_rate": 9.340711764144642e-05, "loss": 1.7034, "step": 67510 }, { "epoch": 13.99, "learning_rate": 9.331170689819673e-05, "loss": 1.7039, "step": 67515 }, { "epoch": 13.99, "learning_rate": 9.321629615494705e-05, "loss": 1.702, "step": 67520 }, { "epoch": 13.99, "learning_rate": 9.312088541169736e-05, "loss": 1.7037, "step": 67525 }, { "epoch": 13.99, "learning_rate": 9.302547466844767e-05, "loss": 1.7033, "step": 67530 }, { "epoch": 13.99, "learning_rate": 9.293006392519799e-05, "loss": 1.7035, "step": 67535 }, { "epoch": 13.99, "learning_rate": 9.28346531819483e-05, "loss": 1.7026, "step": 67540 }, { "epoch": 13.99, "learning_rate": 9.273924243869859e-05, "loss": 1.7004, "step": 67545 }, { "epoch": 13.99, "learning_rate": 9.264383169544891e-05, "loss": 1.7051, "step": 67550 }, { "epoch": 14.0, "learning_rate": 9.254842095219921e-05, "loss": 1.7032, "step": 67555 }, { "epoch": 14.0, "learning_rate": 9.245301020894953e-05, "loss": 1.7017, "step": 67560 }, { "epoch": 14.0, "learning_rate": 9.235759946569984e-05, "loss": 1.7026, "step": 67565 }, { "epoch": 14.0, "learning_rate": 9.226218872245015e-05, "loss": 1.7007, "step": 67570 }, { "epoch": 14.0, "learning_rate": 9.216677797920047e-05, "loss": 1.7028, "step": 67575 }, { "epoch": 14.0, "learning_rate": 9.207136723595078e-05, "loss": 1.6974, "step": 67580 }, { "epoch": 14.0, "learning_rate": 9.197595649270107e-05, "loss": 1.695, "step": 67585 }, { "epoch": 14.0, "learning_rate": 9.188054574945139e-05, "loss": 1.6982, "step": 67590 }, { "epoch": 14.0, "learning_rate": 9.17851350062017e-05, "loss": 1.6999, "step": 67595 }, { "epoch": 14.0, "learning_rate": 9.1689724262952e-05, "loss": 1.6998, "step": 67600 }, { "epoch": 14.01, "learning_rate": 9.159431351970232e-05, "loss": 1.6923, "step": 67605 }, { "epoch": 14.01, "learning_rate": 9.149890277645263e-05, "loss": 1.7005, "step": 67610 }, { "epoch": 14.01, "learning_rate": 9.140349203320295e-05, "loss": 1.696, "step": 67615 }, { "epoch": 14.01, "learning_rate": 9.130808128995326e-05, "loss": 1.6966, "step": 67620 }, { "epoch": 14.01, "learning_rate": 9.121267054670355e-05, "loss": 1.7005, "step": 67625 }, { "epoch": 14.01, "learning_rate": 9.111725980345387e-05, "loss": 1.6955, "step": 67630 }, { "epoch": 14.01, "learning_rate": 9.102184906020418e-05, "loss": 1.698, "step": 67635 }, { "epoch": 14.01, "learning_rate": 9.092643831695449e-05, "loss": 1.6968, "step": 67640 }, { "epoch": 14.01, "learning_rate": 9.08310275737048e-05, "loss": 1.6975, "step": 67645 }, { "epoch": 14.01, "learning_rate": 9.073561683045511e-05, "loss": 1.6979, "step": 67650 }, { "epoch": 14.02, "learning_rate": 9.064020608720542e-05, "loss": 1.6965, "step": 67655 }, { "epoch": 14.02, "learning_rate": 9.054479534395574e-05, "loss": 1.7017, "step": 67660 }, { "epoch": 14.02, "learning_rate": 9.044938460070603e-05, "loss": 1.701, "step": 67665 }, { "epoch": 14.02, "learning_rate": 9.035397385745635e-05, "loss": 1.6997, "step": 67670 }, { "epoch": 14.02, "learning_rate": 9.025856311420666e-05, "loss": 1.6986, "step": 67675 }, { "epoch": 14.02, "learning_rate": 9.016315237095697e-05, "loss": 1.6966, "step": 67680 }, { "epoch": 14.02, "learning_rate": 9.006774162770729e-05, "loss": 1.6968, "step": 67685 }, { "epoch": 14.02, "learning_rate": 8.99723308844576e-05, "loss": 1.6959, "step": 67690 }, { "epoch": 14.02, "learning_rate": 8.98769201412079e-05, "loss": 1.7002, "step": 67695 }, { "epoch": 14.03, "learning_rate": 8.978150939795821e-05, "loss": 1.6992, "step": 67700 }, { "epoch": 14.03, "learning_rate": 8.968609865470852e-05, "loss": 1.6917, "step": 67705 }, { "epoch": 14.03, "learning_rate": 8.959068791145882e-05, "loss": 1.6989, "step": 67710 }, { "epoch": 14.03, "learning_rate": 8.949527716820914e-05, "loss": 1.7028, "step": 67715 }, { "epoch": 14.03, "learning_rate": 8.939986642495945e-05, "loss": 1.7018, "step": 67720 }, { "epoch": 14.03, "learning_rate": 8.930445568170977e-05, "loss": 1.7042, "step": 67725 }, { "epoch": 14.03, "learning_rate": 8.920904493846008e-05, "loss": 1.6994, "step": 67730 }, { "epoch": 14.03, "learning_rate": 8.911363419521038e-05, "loss": 1.6984, "step": 67735 }, { "epoch": 14.03, "learning_rate": 8.901822345196069e-05, "loss": 1.6994, "step": 67740 }, { "epoch": 14.03, "learning_rate": 8.8922812708711e-05, "loss": 1.7022, "step": 67745 }, { "epoch": 14.04, "learning_rate": 8.88274019654613e-05, "loss": 1.703, "step": 67750 }, { "epoch": 14.04, "learning_rate": 8.873199122221163e-05, "loss": 1.6961, "step": 67755 }, { "epoch": 14.04, "learning_rate": 8.863658047896193e-05, "loss": 1.6992, "step": 67760 }, { "epoch": 14.04, "learning_rate": 8.854116973571225e-05, "loss": 1.7, "step": 67765 }, { "epoch": 14.04, "learning_rate": 8.844575899246256e-05, "loss": 1.7012, "step": 67770 }, { "epoch": 14.04, "learning_rate": 8.835034824921287e-05, "loss": 1.6974, "step": 67775 }, { "epoch": 14.04, "learning_rate": 8.825493750596317e-05, "loss": 1.6958, "step": 67780 }, { "epoch": 14.04, "learning_rate": 8.815952676271348e-05, "loss": 1.703, "step": 67785 }, { "epoch": 14.04, "learning_rate": 8.806411601946379e-05, "loss": 1.6984, "step": 67790 }, { "epoch": 14.04, "learning_rate": 8.796870527621411e-05, "loss": 1.6992, "step": 67795 }, { "epoch": 14.05, "learning_rate": 8.787329453296441e-05, "loss": 1.6993, "step": 67800 }, { "epoch": 14.05, "learning_rate": 8.777788378971472e-05, "loss": 1.6973, "step": 67805 }, { "epoch": 14.05, "learning_rate": 8.768247304646504e-05, "loss": 1.6993, "step": 67810 }, { "epoch": 14.05, "learning_rate": 8.758706230321535e-05, "loss": 1.6984, "step": 67815 }, { "epoch": 14.05, "learning_rate": 8.749165155996566e-05, "loss": 1.6973, "step": 67820 }, { "epoch": 14.05, "learning_rate": 8.739624081671596e-05, "loss": 1.6976, "step": 67825 }, { "epoch": 14.05, "learning_rate": 8.730083007346627e-05, "loss": 1.6991, "step": 67830 }, { "epoch": 14.05, "learning_rate": 8.720541933021659e-05, "loss": 1.6992, "step": 67835 }, { "epoch": 14.05, "learning_rate": 8.71100085869669e-05, "loss": 1.7014, "step": 67840 }, { "epoch": 14.06, "learning_rate": 8.70145978437172e-05, "loss": 1.7002, "step": 67845 }, { "epoch": 14.06, "learning_rate": 8.691918710046752e-05, "loss": 1.6961, "step": 67850 }, { "epoch": 14.06, "learning_rate": 8.682377635721782e-05, "loss": 1.695, "step": 67855 }, { "epoch": 14.06, "learning_rate": 8.672836561396812e-05, "loss": 1.7014, "step": 67860 }, { "epoch": 14.06, "learning_rate": 8.663295487071844e-05, "loss": 1.6977, "step": 67865 }, { "epoch": 14.06, "learning_rate": 8.653754412746875e-05, "loss": 1.7, "step": 67870 }, { "epoch": 14.06, "learning_rate": 8.644213338421907e-05, "loss": 1.6953, "step": 67875 }, { "epoch": 14.06, "learning_rate": 8.634672264096938e-05, "loss": 1.6994, "step": 67880 }, { "epoch": 14.06, "learning_rate": 8.625131189771969e-05, "loss": 1.7014, "step": 67885 }, { "epoch": 14.06, "learning_rate": 8.615590115447e-05, "loss": 1.6992, "step": 67890 }, { "epoch": 14.07, "learning_rate": 8.60604904112203e-05, "loss": 1.6991, "step": 67895 }, { "epoch": 14.07, "learning_rate": 8.59650796679706e-05, "loss": 1.6968, "step": 67900 }, { "epoch": 14.07, "learning_rate": 8.586966892472093e-05, "loss": 1.696, "step": 67905 }, { "epoch": 14.07, "learning_rate": 8.577425818147123e-05, "loss": 1.6982, "step": 67910 }, { "epoch": 14.07, "learning_rate": 8.567884743822154e-05, "loss": 1.6969, "step": 67915 }, { "epoch": 14.07, "learning_rate": 8.558343669497186e-05, "loss": 1.6999, "step": 67920 }, { "epoch": 14.07, "learning_rate": 8.548802595172217e-05, "loss": 1.6975, "step": 67925 }, { "epoch": 14.07, "learning_rate": 8.539261520847249e-05, "loss": 1.6939, "step": 67930 }, { "epoch": 14.07, "learning_rate": 8.529720446522278e-05, "loss": 1.6965, "step": 67935 }, { "epoch": 14.07, "learning_rate": 8.520179372197309e-05, "loss": 1.6981, "step": 67940 }, { "epoch": 14.08, "learning_rate": 8.510638297872341e-05, "loss": 1.6926, "step": 67945 }, { "epoch": 14.08, "learning_rate": 8.501097223547372e-05, "loss": 1.7044, "step": 67950 }, { "epoch": 14.08, "learning_rate": 8.491556149222402e-05, "loss": 1.7005, "step": 67955 }, { "epoch": 14.08, "learning_rate": 8.482015074897434e-05, "loss": 1.6989, "step": 67960 }, { "epoch": 14.08, "learning_rate": 8.472474000572465e-05, "loss": 1.698, "step": 67965 }, { "epoch": 14.08, "learning_rate": 8.462932926247496e-05, "loss": 1.698, "step": 67970 }, { "epoch": 14.08, "learning_rate": 8.453391851922526e-05, "loss": 1.7018, "step": 67975 }, { "epoch": 14.08, "learning_rate": 8.443850777597557e-05, "loss": 1.6986, "step": 67980 }, { "epoch": 14.08, "learning_rate": 8.434309703272589e-05, "loss": 1.6993, "step": 67985 }, { "epoch": 14.09, "learning_rate": 8.42476862894762e-05, "loss": 1.6958, "step": 67990 }, { "epoch": 14.09, "learning_rate": 8.41522755462265e-05, "loss": 1.7018, "step": 67995 }, { "epoch": 14.09, "learning_rate": 8.405686480297683e-05, "loss": 1.7016, "step": 68000 }, { "epoch": 14.09, "learning_rate": 8.396145405972713e-05, "loss": 1.6953, "step": 68005 }, { "epoch": 14.09, "learning_rate": 8.386604331647743e-05, "loss": 1.6999, "step": 68010 }, { "epoch": 14.09, "learning_rate": 8.377063257322775e-05, "loss": 1.6996, "step": 68015 }, { "epoch": 14.09, "learning_rate": 8.367522182997805e-05, "loss": 1.6987, "step": 68020 }, { "epoch": 14.09, "learning_rate": 8.357981108672836e-05, "loss": 1.6996, "step": 68025 }, { "epoch": 14.09, "learning_rate": 8.348440034347868e-05, "loss": 1.6951, "step": 68030 }, { "epoch": 14.09, "learning_rate": 8.338898960022899e-05, "loss": 1.692, "step": 68035 }, { "epoch": 14.1, "learning_rate": 8.329357885697931e-05, "loss": 1.7017, "step": 68040 }, { "epoch": 14.1, "learning_rate": 8.319816811372961e-05, "loss": 1.6956, "step": 68045 }, { "epoch": 14.1, "learning_rate": 8.310275737047991e-05, "loss": 1.7018, "step": 68050 }, { "epoch": 14.1, "learning_rate": 8.300734662723023e-05, "loss": 1.699, "step": 68055 }, { "epoch": 14.1, "learning_rate": 8.291193588398054e-05, "loss": 1.6995, "step": 68060 }, { "epoch": 14.1, "learning_rate": 8.281652514073084e-05, "loss": 1.6998, "step": 68065 }, { "epoch": 14.1, "learning_rate": 8.272111439748116e-05, "loss": 1.6999, "step": 68070 }, { "epoch": 14.1, "learning_rate": 8.262570365423147e-05, "loss": 1.7004, "step": 68075 }, { "epoch": 14.1, "learning_rate": 8.253029291098178e-05, "loss": 1.7054, "step": 68080 }, { "epoch": 14.11, "learning_rate": 8.24348821677321e-05, "loss": 1.6987, "step": 68085 }, { "epoch": 14.11, "learning_rate": 8.233947142448239e-05, "loss": 1.7042, "step": 68090 }, { "epoch": 14.11, "learning_rate": 8.224406068123271e-05, "loss": 1.696, "step": 68095 }, { "epoch": 14.11, "learning_rate": 8.214864993798302e-05, "loss": 1.6997, "step": 68100 }, { "epoch": 14.11, "learning_rate": 8.205323919473332e-05, "loss": 1.7002, "step": 68105 }, { "epoch": 14.11, "learning_rate": 8.195782845148364e-05, "loss": 1.6956, "step": 68110 }, { "epoch": 14.11, "learning_rate": 8.186241770823395e-05, "loss": 1.699, "step": 68115 }, { "epoch": 14.11, "learning_rate": 8.176700696498426e-05, "loss": 1.6936, "step": 68120 }, { "epoch": 14.11, "learning_rate": 8.167159622173458e-05, "loss": 1.6952, "step": 68125 }, { "epoch": 14.11, "learning_rate": 8.157618547848487e-05, "loss": 1.6949, "step": 68130 }, { "epoch": 14.12, "learning_rate": 8.148077473523518e-05, "loss": 1.6998, "step": 68135 }, { "epoch": 14.12, "learning_rate": 8.13853639919855e-05, "loss": 1.698, "step": 68140 }, { "epoch": 14.12, "learning_rate": 8.12899532487358e-05, "loss": 1.6969, "step": 68145 }, { "epoch": 14.12, "learning_rate": 8.119454250548613e-05, "loss": 1.6987, "step": 68150 }, { "epoch": 14.12, "learning_rate": 8.109913176223643e-05, "loss": 1.6958, "step": 68155 }, { "epoch": 14.12, "learning_rate": 8.100372101898674e-05, "loss": 1.6994, "step": 68160 }, { "epoch": 14.12, "learning_rate": 8.090831027573705e-05, "loss": 1.6991, "step": 68165 }, { "epoch": 14.12, "learning_rate": 8.081289953248735e-05, "loss": 1.6989, "step": 68170 }, { "epoch": 14.12, "learning_rate": 8.071748878923766e-05, "loss": 1.6973, "step": 68175 }, { "epoch": 14.12, "learning_rate": 8.062207804598798e-05, "loss": 1.6972, "step": 68180 }, { "epoch": 14.13, "learning_rate": 8.052666730273829e-05, "loss": 1.6995, "step": 68185 }, { "epoch": 14.13, "learning_rate": 8.043125655948861e-05, "loss": 1.7008, "step": 68190 }, { "epoch": 14.13, "learning_rate": 8.033584581623892e-05, "loss": 1.7013, "step": 68195 }, { "epoch": 14.13, "learning_rate": 8.024043507298922e-05, "loss": 1.7056, "step": 68200 }, { "epoch": 14.13, "learning_rate": 8.014502432973953e-05, "loss": 1.6994, "step": 68205 }, { "epoch": 14.13, "learning_rate": 8.004961358648984e-05, "loss": 1.7017, "step": 68210 }, { "epoch": 14.13, "learning_rate": 7.995420284324014e-05, "loss": 1.7001, "step": 68215 }, { "epoch": 14.13, "learning_rate": 7.985879209999046e-05, "loss": 1.6993, "step": 68220 }, { "epoch": 14.13, "learning_rate": 7.976338135674077e-05, "loss": 1.7033, "step": 68225 }, { "epoch": 14.14, "learning_rate": 7.966797061349108e-05, "loss": 1.7018, "step": 68230 }, { "epoch": 14.14, "learning_rate": 7.95725598702414e-05, "loss": 1.6958, "step": 68235 }, { "epoch": 14.14, "learning_rate": 7.94771491269917e-05, "loss": 1.6986, "step": 68240 }, { "epoch": 14.14, "learning_rate": 7.938173838374201e-05, "loss": 1.6987, "step": 68245 }, { "epoch": 14.14, "learning_rate": 7.928632764049232e-05, "loss": 1.6943, "step": 68250 }, { "epoch": 14.14, "learning_rate": 7.919091689724263e-05, "loss": 1.698, "step": 68255 }, { "epoch": 14.14, "learning_rate": 7.909550615399295e-05, "loss": 1.6932, "step": 68260 }, { "epoch": 14.14, "learning_rate": 7.900009541074325e-05, "loss": 1.6939, "step": 68265 }, { "epoch": 14.14, "learning_rate": 7.890468466749356e-05, "loss": 1.6989, "step": 68270 }, { "epoch": 14.14, "learning_rate": 7.880927392424388e-05, "loss": 1.703, "step": 68275 }, { "epoch": 14.15, "learning_rate": 7.871386318099417e-05, "loss": 1.7012, "step": 68280 }, { "epoch": 14.15, "learning_rate": 7.861845243774448e-05, "loss": 1.6987, "step": 68285 }, { "epoch": 14.15, "learning_rate": 7.85230416944948e-05, "loss": 1.6959, "step": 68290 }, { "epoch": 14.15, "learning_rate": 7.842763095124511e-05, "loss": 1.7016, "step": 68295 }, { "epoch": 14.15, "learning_rate": 7.833222020799543e-05, "loss": 1.6956, "step": 68300 }, { "epoch": 14.15, "learning_rate": 7.823680946474574e-05, "loss": 1.7004, "step": 68305 }, { "epoch": 14.15, "learning_rate": 7.814139872149604e-05, "loss": 1.6965, "step": 68310 }, { "epoch": 14.15, "learning_rate": 7.804598797824636e-05, "loss": 1.7002, "step": 68315 }, { "epoch": 14.15, "learning_rate": 7.795057723499666e-05, "loss": 1.7023, "step": 68320 }, { "epoch": 14.15, "learning_rate": 7.785516649174696e-05, "loss": 1.7, "step": 68325 }, { "epoch": 14.16, "learning_rate": 7.775975574849728e-05, "loss": 1.6981, "step": 68330 }, { "epoch": 14.16, "learning_rate": 7.766434500524759e-05, "loss": 1.6931, "step": 68335 }, { "epoch": 14.16, "learning_rate": 7.75689342619979e-05, "loss": 1.6984, "step": 68340 }, { "epoch": 14.16, "learning_rate": 7.747352351874822e-05, "loss": 1.6968, "step": 68345 }, { "epoch": 14.16, "learning_rate": 7.737811277549852e-05, "loss": 1.696, "step": 68350 }, { "epoch": 14.16, "learning_rate": 7.728270203224884e-05, "loss": 1.6939, "step": 68355 }, { "epoch": 14.16, "learning_rate": 7.718729128899914e-05, "loss": 1.704, "step": 68360 }, { "epoch": 14.16, "learning_rate": 7.709188054574945e-05, "loss": 1.6957, "step": 68365 }, { "epoch": 14.16, "learning_rate": 7.699646980249977e-05, "loss": 1.6989, "step": 68370 }, { "epoch": 14.17, "learning_rate": 7.690105905925007e-05, "loss": 1.695, "step": 68375 }, { "epoch": 14.17, "learning_rate": 7.680564831600038e-05, "loss": 1.6971, "step": 68380 }, { "epoch": 14.17, "learning_rate": 7.67102375727507e-05, "loss": 1.7023, "step": 68385 }, { "epoch": 14.17, "learning_rate": 7.6614826829501e-05, "loss": 1.6945, "step": 68390 }, { "epoch": 14.17, "learning_rate": 7.651941608625131e-05, "loss": 1.6968, "step": 68395 }, { "epoch": 14.17, "learning_rate": 7.642400534300162e-05, "loss": 1.6965, "step": 68400 }, { "epoch": 14.17, "learning_rate": 7.632859459975193e-05, "loss": 1.6961, "step": 68405 }, { "epoch": 14.17, "learning_rate": 7.623318385650225e-05, "loss": 1.6977, "step": 68410 }, { "epoch": 14.17, "learning_rate": 7.613777311325255e-05, "loss": 1.6977, "step": 68415 }, { "epoch": 14.17, "learning_rate": 7.604236237000286e-05, "loss": 1.699, "step": 68420 }, { "epoch": 14.18, "learning_rate": 7.594695162675318e-05, "loss": 1.6975, "step": 68425 }, { "epoch": 14.18, "learning_rate": 7.585154088350349e-05, "loss": 1.7007, "step": 68430 }, { "epoch": 14.18, "learning_rate": 7.575613014025378e-05, "loss": 1.6979, "step": 68435 }, { "epoch": 14.18, "learning_rate": 7.56607193970041e-05, "loss": 1.7017, "step": 68440 }, { "epoch": 14.18, "learning_rate": 7.556530865375441e-05, "loss": 1.6968, "step": 68445 }, { "epoch": 14.18, "learning_rate": 7.546989791050472e-05, "loss": 1.7001, "step": 68450 }, { "epoch": 14.18, "learning_rate": 7.537448716725504e-05, "loss": 1.6972, "step": 68455 }, { "epoch": 14.18, "learning_rate": 7.527907642400534e-05, "loss": 1.7005, "step": 68460 }, { "epoch": 14.18, "learning_rate": 7.518366568075566e-05, "loss": 1.7026, "step": 68465 }, { "epoch": 14.18, "learning_rate": 7.508825493750597e-05, "loss": 1.6957, "step": 68470 }, { "epoch": 14.19, "learning_rate": 7.499284419425626e-05, "loss": 1.7008, "step": 68475 }, { "epoch": 14.19, "learning_rate": 7.489743345100658e-05, "loss": 1.6987, "step": 68480 }, { "epoch": 14.19, "learning_rate": 7.480202270775689e-05, "loss": 1.6996, "step": 68485 }, { "epoch": 14.19, "learning_rate": 7.47066119645072e-05, "loss": 1.6953, "step": 68490 }, { "epoch": 14.19, "learning_rate": 7.461120122125752e-05, "loss": 1.694, "step": 68495 }, { "epoch": 14.19, "learning_rate": 7.451579047800783e-05, "loss": 1.6938, "step": 68500 }, { "epoch": 14.19, "learning_rate": 7.442037973475813e-05, "loss": 1.7004, "step": 68505 }, { "epoch": 14.19, "learning_rate": 7.432496899150845e-05, "loss": 1.7015, "step": 68510 }, { "epoch": 14.19, "learning_rate": 7.422955824825875e-05, "loss": 1.7031, "step": 68515 }, { "epoch": 14.2, "learning_rate": 7.413414750500907e-05, "loss": 1.697, "step": 68520 }, { "epoch": 14.2, "learning_rate": 7.403873676175937e-05, "loss": 1.6985, "step": 68525 }, { "epoch": 14.2, "learning_rate": 7.394332601850968e-05, "loss": 1.6963, "step": 68530 }, { "epoch": 14.2, "learning_rate": 7.384791527526e-05, "loss": 1.6987, "step": 68535 }, { "epoch": 14.2, "learning_rate": 7.375250453201031e-05, "loss": 1.7027, "step": 68540 }, { "epoch": 14.2, "learning_rate": 7.365709378876062e-05, "loss": 1.6983, "step": 68545 }, { "epoch": 14.2, "learning_rate": 7.356168304551094e-05, "loss": 1.6984, "step": 68550 }, { "epoch": 14.2, "learning_rate": 7.346627230226123e-05, "loss": 1.6974, "step": 68555 }, { "epoch": 14.2, "learning_rate": 7.337086155901154e-05, "loss": 1.6986, "step": 68560 }, { "epoch": 14.2, "learning_rate": 7.327545081576186e-05, "loss": 1.7032, "step": 68565 }, { "epoch": 14.21, "learning_rate": 7.318004007251216e-05, "loss": 1.6965, "step": 68570 }, { "epoch": 14.21, "learning_rate": 7.308462932926248e-05, "loss": 1.6966, "step": 68575 }, { "epoch": 14.21, "learning_rate": 7.298921858601279e-05, "loss": 1.696, "step": 68580 }, { "epoch": 14.21, "learning_rate": 7.28938078427631e-05, "loss": 1.6997, "step": 68585 }, { "epoch": 14.21, "learning_rate": 7.27983970995134e-05, "loss": 1.6955, "step": 68590 }, { "epoch": 14.21, "learning_rate": 7.270298635626371e-05, "loss": 1.6966, "step": 68595 }, { "epoch": 14.21, "learning_rate": 7.260757561301402e-05, "loss": 1.6987, "step": 68600 }, { "epoch": 14.21, "learning_rate": 7.251216486976434e-05, "loss": 1.701, "step": 68605 }, { "epoch": 14.21, "learning_rate": 7.241675412651465e-05, "loss": 1.6998, "step": 68610 }, { "epoch": 14.21, "learning_rate": 7.232134338326497e-05, "loss": 1.7, "step": 68615 }, { "epoch": 14.22, "learning_rate": 7.222593264001527e-05, "loss": 1.697, "step": 68620 }, { "epoch": 14.22, "learning_rate": 7.213052189676558e-05, "loss": 1.6984, "step": 68625 }, { "epoch": 14.22, "learning_rate": 7.203511115351589e-05, "loss": 1.6986, "step": 68630 }, { "epoch": 14.22, "learning_rate": 7.19397004102662e-05, "loss": 1.6955, "step": 68635 }, { "epoch": 14.22, "learning_rate": 7.18442896670165e-05, "loss": 1.699, "step": 68640 }, { "epoch": 14.22, "learning_rate": 7.174887892376682e-05, "loss": 1.6996, "step": 68645 }, { "epoch": 14.22, "learning_rate": 7.165346818051713e-05, "loss": 1.6948, "step": 68650 }, { "epoch": 14.22, "learning_rate": 7.155805743726743e-05, "loss": 1.6985, "step": 68655 }, { "epoch": 14.22, "learning_rate": 7.146264669401775e-05, "loss": 1.7015, "step": 68660 }, { "epoch": 14.23, "learning_rate": 7.136723595076806e-05, "loss": 1.6977, "step": 68665 }, { "epoch": 14.23, "learning_rate": 7.127182520751837e-05, "loss": 1.7006, "step": 68670 }, { "epoch": 14.23, "learning_rate": 7.117641446426868e-05, "loss": 1.7009, "step": 68675 }, { "epoch": 14.23, "learning_rate": 7.108100372101898e-05, "loss": 1.6939, "step": 68680 }, { "epoch": 14.23, "learning_rate": 7.09855929777693e-05, "loss": 1.7023, "step": 68685 }, { "epoch": 14.23, "learning_rate": 7.089018223451961e-05, "loss": 1.6982, "step": 68690 }, { "epoch": 14.23, "learning_rate": 7.079477149126992e-05, "loss": 1.7011, "step": 68695 }, { "epoch": 14.23, "learning_rate": 7.069936074802024e-05, "loss": 1.7, "step": 68700 }, { "epoch": 14.23, "learning_rate": 7.060395000477054e-05, "loss": 1.7009, "step": 68705 }, { "epoch": 14.23, "learning_rate": 7.050853926152084e-05, "loss": 1.6937, "step": 68710 }, { "epoch": 14.24, "learning_rate": 7.041312851827116e-05, "loss": 1.6991, "step": 68715 }, { "epoch": 14.24, "learning_rate": 7.031771777502146e-05, "loss": 1.7016, "step": 68720 }, { "epoch": 14.24, "learning_rate": 7.022230703177179e-05, "loss": 1.6975, "step": 68725 }, { "epoch": 14.24, "learning_rate": 7.012689628852209e-05, "loss": 1.697, "step": 68730 }, { "epoch": 14.24, "learning_rate": 7.00314855452724e-05, "loss": 1.7042, "step": 68735 }, { "epoch": 14.24, "learning_rate": 6.993607480202272e-05, "loss": 1.7029, "step": 68740 }, { "epoch": 14.24, "learning_rate": 6.984066405877301e-05, "loss": 1.6999, "step": 68745 }, { "epoch": 14.24, "learning_rate": 6.974525331552332e-05, "loss": 1.7017, "step": 68750 }, { "epoch": 14.24, "learning_rate": 6.964984257227364e-05, "loss": 1.6996, "step": 68755 }, { "epoch": 14.24, "learning_rate": 6.955443182902395e-05, "loss": 1.7016, "step": 68760 }, { "epoch": 14.25, "learning_rate": 6.945902108577425e-05, "loss": 1.6973, "step": 68765 }, { "epoch": 14.25, "learning_rate": 6.936361034252457e-05, "loss": 1.7005, "step": 68770 }, { "epoch": 14.25, "learning_rate": 6.926819959927488e-05, "loss": 1.696, "step": 68775 }, { "epoch": 14.25, "learning_rate": 6.91727888560252e-05, "loss": 1.6989, "step": 68780 }, { "epoch": 14.25, "learning_rate": 6.90773781127755e-05, "loss": 1.6995, "step": 68785 }, { "epoch": 14.25, "learning_rate": 6.89819673695258e-05, "loss": 1.6947, "step": 68790 }, { "epoch": 14.25, "learning_rate": 6.888655662627612e-05, "loss": 1.6975, "step": 68795 }, { "epoch": 14.25, "learning_rate": 6.879114588302643e-05, "loss": 1.6968, "step": 68800 }, { "epoch": 14.25, "learning_rate": 6.869573513977674e-05, "loss": 1.7026, "step": 68805 }, { "epoch": 14.26, "learning_rate": 6.860032439652706e-05, "loss": 1.7013, "step": 68810 }, { "epoch": 14.26, "learning_rate": 6.850491365327736e-05, "loss": 1.6969, "step": 68815 }, { "epoch": 14.26, "learning_rate": 6.840950291002767e-05, "loss": 1.6993, "step": 68820 }, { "epoch": 14.26, "learning_rate": 6.831409216677798e-05, "loss": 1.6979, "step": 68825 }, { "epoch": 14.26, "learning_rate": 6.821868142352828e-05, "loss": 1.6987, "step": 68830 }, { "epoch": 14.26, "learning_rate": 6.81232706802786e-05, "loss": 1.7033, "step": 68835 }, { "epoch": 14.26, "learning_rate": 6.802785993702891e-05, "loss": 1.6984, "step": 68840 }, { "epoch": 14.26, "learning_rate": 6.793244919377922e-05, "loss": 1.6998, "step": 68845 }, { "epoch": 14.26, "learning_rate": 6.783703845052954e-05, "loss": 1.6997, "step": 68850 }, { "epoch": 14.26, "learning_rate": 6.774162770727985e-05, "loss": 1.705, "step": 68855 }, { "epoch": 14.27, "learning_rate": 6.764621696403015e-05, "loss": 1.7042, "step": 68860 }, { "epoch": 14.27, "learning_rate": 6.755080622078046e-05, "loss": 1.6991, "step": 68865 }, { "epoch": 14.27, "learning_rate": 6.745539547753077e-05, "loss": 1.6953, "step": 68870 }, { "epoch": 14.27, "learning_rate": 6.735998473428107e-05, "loss": 1.6984, "step": 68875 }, { "epoch": 14.27, "learning_rate": 6.72645739910314e-05, "loss": 1.6968, "step": 68880 }, { "epoch": 14.27, "learning_rate": 6.71691632477817e-05, "loss": 1.6988, "step": 68885 }, { "epoch": 14.27, "learning_rate": 6.707375250453202e-05, "loss": 1.7019, "step": 68890 }, { "epoch": 14.27, "learning_rate": 6.697834176128233e-05, "loss": 1.7056, "step": 68895 }, { "epoch": 14.27, "learning_rate": 6.688293101803262e-05, "loss": 1.6993, "step": 68900 }, { "epoch": 14.27, "learning_rate": 6.678752027478294e-05, "loss": 1.6979, "step": 68905 }, { "epoch": 14.28, "learning_rate": 6.669210953153325e-05, "loss": 1.6932, "step": 68910 }, { "epoch": 14.28, "learning_rate": 6.659669878828356e-05, "loss": 1.6998, "step": 68915 }, { "epoch": 14.28, "learning_rate": 6.650128804503388e-05, "loss": 1.6978, "step": 68920 }, { "epoch": 14.28, "learning_rate": 6.640587730178418e-05, "loss": 1.6989, "step": 68925 }, { "epoch": 14.28, "learning_rate": 6.63104665585345e-05, "loss": 1.697, "step": 68930 }, { "epoch": 14.28, "learning_rate": 6.621505581528481e-05, "loss": 1.7006, "step": 68935 }, { "epoch": 14.28, "learning_rate": 6.61196450720351e-05, "loss": 1.7018, "step": 68940 }, { "epoch": 14.28, "learning_rate": 6.602423432878542e-05, "loss": 1.6968, "step": 68945 }, { "epoch": 14.28, "learning_rate": 6.592882358553573e-05, "loss": 1.7004, "step": 68950 }, { "epoch": 14.29, "learning_rate": 6.583341284228604e-05, "loss": 1.7013, "step": 68955 }, { "epoch": 14.29, "learning_rate": 6.573800209903636e-05, "loss": 1.6929, "step": 68960 }, { "epoch": 14.29, "learning_rate": 6.564259135578666e-05, "loss": 1.6981, "step": 68965 }, { "epoch": 14.29, "learning_rate": 6.554718061253697e-05, "loss": 1.698, "step": 68970 }, { "epoch": 14.29, "learning_rate": 6.545176986928729e-05, "loss": 1.7013, "step": 68975 }, { "epoch": 14.29, "learning_rate": 6.535635912603759e-05, "loss": 1.698, "step": 68980 }, { "epoch": 14.29, "learning_rate": 6.52609483827879e-05, "loss": 1.6961, "step": 68985 }, { "epoch": 14.29, "learning_rate": 6.516553763953821e-05, "loss": 1.7005, "step": 68990 }, { "epoch": 14.29, "learning_rate": 6.507012689628852e-05, "loss": 1.6999, "step": 68995 }, { "epoch": 14.29, "learning_rate": 6.497471615303884e-05, "loss": 1.6972, "step": 69000 }, { "epoch": 14.29, "eval_accuracy": 0.5488627450980392, "eval_loss": 1.8967515230178833, "eval_runtime": 0.6502, "eval_samples_per_second": 230.704, "eval_steps_per_second": 1.538, "step": 69000 }, { "epoch": 14.3, "learning_rate": 6.487930540978915e-05, "loss": 1.6973, "step": 69005 }, { "epoch": 14.3, "learning_rate": 6.478389466653945e-05, "loss": 1.7032, "step": 69010 }, { "epoch": 14.3, "learning_rate": 6.468848392328977e-05, "loss": 1.6975, "step": 69015 }, { "epoch": 14.3, "learning_rate": 6.459307318004007e-05, "loss": 1.6987, "step": 69020 }, { "epoch": 14.3, "learning_rate": 6.449766243679037e-05, "loss": 1.6977, "step": 69025 }, { "epoch": 14.3, "learning_rate": 6.44022516935407e-05, "loss": 1.6916, "step": 69030 }, { "epoch": 14.3, "learning_rate": 6.4306840950291e-05, "loss": 1.6983, "step": 69035 }, { "epoch": 14.3, "learning_rate": 6.421143020704132e-05, "loss": 1.6961, "step": 69040 }, { "epoch": 14.3, "learning_rate": 6.411601946379163e-05, "loss": 1.6969, "step": 69045 }, { "epoch": 14.3, "learning_rate": 6.402060872054194e-05, "loss": 1.6983, "step": 69050 }, { "epoch": 14.31, "learning_rate": 6.392519797729224e-05, "loss": 1.7049, "step": 69055 }, { "epoch": 14.31, "learning_rate": 6.382978723404255e-05, "loss": 1.6966, "step": 69060 }, { "epoch": 14.31, "learning_rate": 6.373437649079286e-05, "loss": 1.6923, "step": 69065 }, { "epoch": 14.31, "learning_rate": 6.363896574754318e-05, "loss": 1.6988, "step": 69070 }, { "epoch": 14.31, "learning_rate": 6.354355500429348e-05, "loss": 1.7012, "step": 69075 }, { "epoch": 14.31, "learning_rate": 6.344814426104379e-05, "loss": 1.6972, "step": 69080 }, { "epoch": 14.31, "learning_rate": 6.335273351779411e-05, "loss": 1.7021, "step": 69085 }, { "epoch": 14.31, "learning_rate": 6.325732277454442e-05, "loss": 1.7012, "step": 69090 }, { "epoch": 14.31, "learning_rate": 6.316191203129473e-05, "loss": 1.6968, "step": 69095 }, { "epoch": 14.32, "learning_rate": 6.306650128804503e-05, "loss": 1.7004, "step": 69100 }, { "epoch": 14.32, "learning_rate": 6.297109054479534e-05, "loss": 1.6974, "step": 69105 }, { "epoch": 14.32, "learning_rate": 6.287567980154566e-05, "loss": 1.701, "step": 69110 }, { "epoch": 14.32, "learning_rate": 6.278026905829597e-05, "loss": 1.6962, "step": 69115 }, { "epoch": 14.32, "learning_rate": 6.268485831504627e-05, "loss": 1.6978, "step": 69120 }, { "epoch": 14.32, "learning_rate": 6.25894475717966e-05, "loss": 1.6981, "step": 69125 }, { "epoch": 14.32, "learning_rate": 6.24940368285469e-05, "loss": 1.6979, "step": 69130 }, { "epoch": 14.32, "learning_rate": 6.239862608529721e-05, "loss": 1.6992, "step": 69135 }, { "epoch": 14.32, "learning_rate": 6.230321534204751e-05, "loss": 1.697, "step": 69140 }, { "epoch": 14.32, "learning_rate": 6.220780459879782e-05, "loss": 1.6949, "step": 69145 }, { "epoch": 14.33, "learning_rate": 6.211239385554814e-05, "loss": 1.7003, "step": 69150 }, { "epoch": 14.33, "learning_rate": 6.201698311229845e-05, "loss": 1.7018, "step": 69155 }, { "epoch": 14.33, "learning_rate": 6.192157236904876e-05, "loss": 1.7014, "step": 69160 }, { "epoch": 14.33, "learning_rate": 6.182616162579906e-05, "loss": 1.6988, "step": 69165 }, { "epoch": 14.33, "learning_rate": 6.173075088254938e-05, "loss": 1.697, "step": 69170 }, { "epoch": 14.33, "learning_rate": 6.163534013929969e-05, "loss": 1.6954, "step": 69175 }, { "epoch": 14.33, "learning_rate": 6.153992939605e-05, "loss": 1.6969, "step": 69180 }, { "epoch": 14.33, "learning_rate": 6.14445186528003e-05, "loss": 1.7024, "step": 69185 }, { "epoch": 14.33, "learning_rate": 6.134910790955061e-05, "loss": 1.6936, "step": 69190 }, { "epoch": 14.33, "learning_rate": 6.125369716630093e-05, "loss": 1.7039, "step": 69195 }, { "epoch": 14.34, "learning_rate": 6.115828642305124e-05, "loss": 1.6994, "step": 69200 }, { "epoch": 14.34, "learning_rate": 6.106287567980154e-05, "loss": 1.6975, "step": 69205 }, { "epoch": 14.34, "learning_rate": 6.096746493655186e-05, "loss": 1.6983, "step": 69210 }, { "epoch": 14.34, "learning_rate": 6.087205419330217e-05, "loss": 1.6997, "step": 69215 }, { "epoch": 14.34, "learning_rate": 6.077664345005247e-05, "loss": 1.6919, "step": 69220 }, { "epoch": 14.34, "learning_rate": 6.0681232706802786e-05, "loss": 1.7041, "step": 69225 }, { "epoch": 14.34, "learning_rate": 6.05858219635531e-05, "loss": 1.6998, "step": 69230 }, { "epoch": 14.34, "learning_rate": 6.0490411220303406e-05, "loss": 1.6959, "step": 69235 }, { "epoch": 14.34, "learning_rate": 6.039500047705371e-05, "loss": 1.6969, "step": 69240 }, { "epoch": 14.35, "learning_rate": 6.029958973380403e-05, "loss": 1.6997, "step": 69245 }, { "epoch": 14.35, "learning_rate": 6.020417899055434e-05, "loss": 1.6976, "step": 69250 }, { "epoch": 14.35, "learning_rate": 6.010876824730465e-05, "loss": 1.6999, "step": 69255 }, { "epoch": 14.35, "learning_rate": 6.0013357504054954e-05, "loss": 1.7, "step": 69260 }, { "epoch": 14.35, "learning_rate": 5.991794676080527e-05, "loss": 1.7016, "step": 69265 }, { "epoch": 14.35, "learning_rate": 5.982253601755558e-05, "loss": 1.6993, "step": 69270 }, { "epoch": 14.35, "learning_rate": 5.972712527430589e-05, "loss": 1.6984, "step": 69275 }, { "epoch": 14.35, "learning_rate": 5.9631714531056195e-05, "loss": 1.6951, "step": 69280 }, { "epoch": 14.35, "learning_rate": 5.953630378780651e-05, "loss": 1.6981, "step": 69285 }, { "epoch": 14.35, "learning_rate": 5.944089304455682e-05, "loss": 1.7026, "step": 69290 }, { "epoch": 14.36, "learning_rate": 5.934548230130713e-05, "loss": 1.6944, "step": 69295 }, { "epoch": 14.36, "learning_rate": 5.9250071558057436e-05, "loss": 1.6952, "step": 69300 }, { "epoch": 14.36, "learning_rate": 5.915466081480775e-05, "loss": 1.6995, "step": 69305 }, { "epoch": 14.36, "learning_rate": 5.905925007155806e-05, "loss": 1.6975, "step": 69310 }, { "epoch": 14.36, "learning_rate": 5.896383932830837e-05, "loss": 1.6953, "step": 69315 }, { "epoch": 14.36, "learning_rate": 5.886842858505868e-05, "loss": 1.6974, "step": 69320 }, { "epoch": 14.36, "learning_rate": 5.877301784180899e-05, "loss": 1.6995, "step": 69325 }, { "epoch": 14.36, "learning_rate": 5.86776070985593e-05, "loss": 1.6975, "step": 69330 }, { "epoch": 14.36, "learning_rate": 5.858219635530961e-05, "loss": 1.7005, "step": 69335 }, { "epoch": 14.37, "learning_rate": 5.848678561205992e-05, "loss": 1.704, "step": 69340 }, { "epoch": 14.37, "learning_rate": 5.839137486881023e-05, "loss": 1.6977, "step": 69345 }, { "epoch": 14.37, "learning_rate": 5.829596412556054e-05, "loss": 1.6976, "step": 69350 }, { "epoch": 14.37, "learning_rate": 5.8200553382310846e-05, "loss": 1.6923, "step": 69355 }, { "epoch": 14.37, "learning_rate": 5.810514263906116e-05, "loss": 1.702, "step": 69360 }, { "epoch": 14.37, "learning_rate": 5.800973189581147e-05, "loss": 1.6966, "step": 69365 }, { "epoch": 14.37, "learning_rate": 5.791432115256178e-05, "loss": 1.701, "step": 69370 }, { "epoch": 14.37, "learning_rate": 5.781891040931209e-05, "loss": 1.7012, "step": 69375 }, { "epoch": 14.37, "learning_rate": 5.77234996660624e-05, "loss": 1.6979, "step": 69380 }, { "epoch": 14.37, "learning_rate": 5.762808892281271e-05, "loss": 1.6974, "step": 69385 }, { "epoch": 14.38, "learning_rate": 5.753267817956302e-05, "loss": 1.6946, "step": 69390 }, { "epoch": 14.38, "learning_rate": 5.743726743631333e-05, "loss": 1.7033, "step": 69395 }, { "epoch": 14.38, "learning_rate": 5.734185669306364e-05, "loss": 1.6959, "step": 69400 }, { "epoch": 14.38, "learning_rate": 5.724644594981395e-05, "loss": 1.697, "step": 69405 }, { "epoch": 14.38, "learning_rate": 5.715103520656426e-05, "loss": 1.6984, "step": 69410 }, { "epoch": 14.38, "learning_rate": 5.705562446331457e-05, "loss": 1.6954, "step": 69415 }, { "epoch": 14.38, "learning_rate": 5.6960213720064876e-05, "loss": 1.704, "step": 69420 }, { "epoch": 14.38, "learning_rate": 5.686480297681519e-05, "loss": 1.698, "step": 69425 }, { "epoch": 14.38, "learning_rate": 5.6769392233565504e-05, "loss": 1.6965, "step": 69430 }, { "epoch": 14.38, "learning_rate": 5.667398149031581e-05, "loss": 1.6998, "step": 69435 }, { "epoch": 14.39, "learning_rate": 5.657857074706612e-05, "loss": 1.6952, "step": 69440 }, { "epoch": 14.39, "learning_rate": 5.648316000381643e-05, "loss": 1.6996, "step": 69445 }, { "epoch": 14.39, "learning_rate": 5.6387749260566745e-05, "loss": 1.7011, "step": 69450 }, { "epoch": 14.39, "learning_rate": 5.629233851731705e-05, "loss": 1.7014, "step": 69455 }, { "epoch": 14.39, "learning_rate": 5.619692777406736e-05, "loss": 1.6979, "step": 69460 }, { "epoch": 14.39, "learning_rate": 5.610151703081767e-05, "loss": 1.7022, "step": 69465 }, { "epoch": 14.39, "learning_rate": 5.6006106287567986e-05, "loss": 1.6979, "step": 69470 }, { "epoch": 14.39, "learning_rate": 5.5910695544318286e-05, "loss": 1.6977, "step": 69475 }, { "epoch": 14.39, "learning_rate": 5.58152848010686e-05, "loss": 1.7007, "step": 69480 }, { "epoch": 14.4, "learning_rate": 5.571987405781891e-05, "loss": 1.6971, "step": 69485 }, { "epoch": 14.4, "learning_rate": 5.562446331456923e-05, "loss": 1.6997, "step": 69490 }, { "epoch": 14.4, "learning_rate": 5.552905257131953e-05, "loss": 1.6952, "step": 69495 }, { "epoch": 14.4, "learning_rate": 5.543364182806984e-05, "loss": 1.6979, "step": 69500 }, { "epoch": 14.4, "learning_rate": 5.5338231084820154e-05, "loss": 1.6979, "step": 69505 }, { "epoch": 14.4, "learning_rate": 5.524282034157046e-05, "loss": 1.6968, "step": 69510 }, { "epoch": 14.4, "learning_rate": 5.514740959832077e-05, "loss": 1.6987, "step": 69515 }, { "epoch": 14.4, "learning_rate": 5.505199885507108e-05, "loss": 1.6997, "step": 69520 }, { "epoch": 14.4, "learning_rate": 5.4956588111821396e-05, "loss": 1.6958, "step": 69525 }, { "epoch": 14.4, "learning_rate": 5.48611773685717e-05, "loss": 1.7006, "step": 69530 }, { "epoch": 14.41, "learning_rate": 5.476576662532201e-05, "loss": 1.6993, "step": 69535 }, { "epoch": 14.41, "learning_rate": 5.467035588207232e-05, "loss": 1.6987, "step": 69540 }, { "epoch": 14.41, "learning_rate": 5.457494513882264e-05, "loss": 1.6946, "step": 69545 }, { "epoch": 14.41, "learning_rate": 5.447953439557294e-05, "loss": 1.7016, "step": 69550 }, { "epoch": 14.41, "learning_rate": 5.438412365232325e-05, "loss": 1.7034, "step": 69555 }, { "epoch": 14.41, "learning_rate": 5.4288712909073564e-05, "loss": 1.6936, "step": 69560 }, { "epoch": 14.41, "learning_rate": 5.419330216582388e-05, "loss": 1.702, "step": 69565 }, { "epoch": 14.41, "learning_rate": 5.409789142257418e-05, "loss": 1.7022, "step": 69570 }, { "epoch": 14.41, "learning_rate": 5.400248067932449e-05, "loss": 1.7023, "step": 69575 }, { "epoch": 14.41, "learning_rate": 5.3907069936074805e-05, "loss": 1.7028, "step": 69580 }, { "epoch": 14.42, "learning_rate": 5.381165919282512e-05, "loss": 1.6975, "step": 69585 }, { "epoch": 14.42, "learning_rate": 5.371624844957542e-05, "loss": 1.6978, "step": 69590 }, { "epoch": 14.42, "learning_rate": 5.362083770632573e-05, "loss": 1.7085, "step": 69595 }, { "epoch": 14.42, "learning_rate": 5.3525426963076046e-05, "loss": 1.6958, "step": 69600 }, { "epoch": 14.42, "learning_rate": 5.343001621982635e-05, "loss": 1.7, "step": 69605 }, { "epoch": 14.42, "learning_rate": 5.333460547657666e-05, "loss": 1.6987, "step": 69610 }, { "epoch": 14.42, "learning_rate": 5.3239194733326974e-05, "loss": 1.6988, "step": 69615 }, { "epoch": 14.42, "learning_rate": 5.314378399007729e-05, "loss": 1.6942, "step": 69620 }, { "epoch": 14.42, "learning_rate": 5.3048373246827594e-05, "loss": 1.6967, "step": 69625 }, { "epoch": 14.43, "learning_rate": 5.29529625035779e-05, "loss": 1.6997, "step": 69630 }, { "epoch": 14.43, "learning_rate": 5.2857551760328215e-05, "loss": 1.6969, "step": 69635 }, { "epoch": 14.43, "learning_rate": 5.276214101707853e-05, "loss": 1.6995, "step": 69640 }, { "epoch": 14.43, "learning_rate": 5.2666730273828835e-05, "loss": 1.7003, "step": 69645 }, { "epoch": 14.43, "learning_rate": 5.257131953057914e-05, "loss": 1.7017, "step": 69650 }, { "epoch": 14.43, "learning_rate": 5.2475908787329456e-05, "loss": 1.6939, "step": 69655 }, { "epoch": 14.43, "learning_rate": 5.238049804407977e-05, "loss": 1.7021, "step": 69660 }, { "epoch": 14.43, "learning_rate": 5.228508730083007e-05, "loss": 1.703, "step": 69665 }, { "epoch": 14.43, "learning_rate": 5.2189676557580383e-05, "loss": 1.6951, "step": 69670 }, { "epoch": 14.43, "learning_rate": 5.20942658143307e-05, "loss": 1.6993, "step": 69675 }, { "epoch": 14.44, "learning_rate": 5.1998855071081004e-05, "loss": 1.6985, "step": 69680 }, { "epoch": 14.44, "learning_rate": 5.190344432783131e-05, "loss": 1.697, "step": 69685 }, { "epoch": 14.44, "learning_rate": 5.1808033584581625e-05, "loss": 1.6963, "step": 69690 }, { "epoch": 14.44, "learning_rate": 5.171262284133194e-05, "loss": 1.7005, "step": 69695 }, { "epoch": 14.44, "learning_rate": 5.1617212098082245e-05, "loss": 1.7005, "step": 69700 }, { "epoch": 14.44, "learning_rate": 5.152180135483255e-05, "loss": 1.6994, "step": 69705 }, { "epoch": 14.44, "learning_rate": 5.1426390611582866e-05, "loss": 1.7011, "step": 69710 }, { "epoch": 14.44, "learning_rate": 5.133097986833318e-05, "loss": 1.6967, "step": 69715 }, { "epoch": 14.44, "learning_rate": 5.1235569125083486e-05, "loss": 1.6988, "step": 69720 }, { "epoch": 14.44, "learning_rate": 5.114015838183379e-05, "loss": 1.7025, "step": 69725 }, { "epoch": 14.45, "learning_rate": 5.104474763858411e-05, "loss": 1.6972, "step": 69730 }, { "epoch": 14.45, "learning_rate": 5.0949336895334414e-05, "loss": 1.6999, "step": 69735 }, { "epoch": 14.45, "learning_rate": 5.085392615208473e-05, "loss": 1.6985, "step": 69740 }, { "epoch": 14.45, "learning_rate": 5.0758515408835034e-05, "loss": 1.696, "step": 69745 }, { "epoch": 14.45, "learning_rate": 5.066310466558535e-05, "loss": 1.6962, "step": 69750 }, { "epoch": 14.45, "learning_rate": 5.0567693922335655e-05, "loss": 1.6969, "step": 69755 }, { "epoch": 14.45, "learning_rate": 5.047228317908597e-05, "loss": 1.6981, "step": 69760 }, { "epoch": 14.45, "learning_rate": 5.0376872435836275e-05, "loss": 1.6943, "step": 69765 }, { "epoch": 14.45, "learning_rate": 5.028146169258659e-05, "loss": 1.6949, "step": 69770 }, { "epoch": 14.46, "learning_rate": 5.0186050949336896e-05, "loss": 1.6971, "step": 69775 }, { "epoch": 14.46, "learning_rate": 5.009064020608721e-05, "loss": 1.7004, "step": 69780 }, { "epoch": 14.46, "learning_rate": 4.9995229462837516e-05, "loss": 1.6971, "step": 69785 }, { "epoch": 14.46, "learning_rate": 4.989981871958782e-05, "loss": 1.7001, "step": 69790 }, { "epoch": 14.46, "learning_rate": 4.980440797633814e-05, "loss": 1.6937, "step": 69795 }, { "epoch": 14.46, "learning_rate": 4.970899723308845e-05, "loss": 1.6978, "step": 69800 }, { "epoch": 14.46, "learning_rate": 4.961358648983876e-05, "loss": 1.7011, "step": 69805 }, { "epoch": 14.46, "learning_rate": 4.9518175746589064e-05, "loss": 1.6958, "step": 69810 }, { "epoch": 14.46, "learning_rate": 4.942276500333938e-05, "loss": 1.7004, "step": 69815 }, { "epoch": 14.46, "learning_rate": 4.9327354260089685e-05, "loss": 1.6935, "step": 69820 }, { "epoch": 14.47, "learning_rate": 4.923194351684e-05, "loss": 1.6939, "step": 69825 }, { "epoch": 14.47, "learning_rate": 4.9136532773590305e-05, "loss": 1.6964, "step": 69830 }, { "epoch": 14.47, "learning_rate": 4.904112203034062e-05, "loss": 1.7007, "step": 69835 }, { "epoch": 14.47, "learning_rate": 4.8945711287090926e-05, "loss": 1.7071, "step": 69840 }, { "epoch": 14.47, "learning_rate": 4.885030054384123e-05, "loss": 1.6965, "step": 69845 }, { "epoch": 14.47, "learning_rate": 4.8754889800591547e-05, "loss": 1.6993, "step": 69850 }, { "epoch": 14.47, "learning_rate": 4.865947905734186e-05, "loss": 1.701, "step": 69855 }, { "epoch": 14.47, "learning_rate": 4.856406831409217e-05, "loss": 1.6964, "step": 69860 }, { "epoch": 14.47, "learning_rate": 4.8468657570842474e-05, "loss": 1.7, "step": 69865 }, { "epoch": 14.47, "learning_rate": 4.837324682759279e-05, "loss": 1.6941, "step": 69870 }, { "epoch": 14.48, "learning_rate": 4.82778360843431e-05, "loss": 1.7002, "step": 69875 }, { "epoch": 14.48, "learning_rate": 4.818242534109341e-05, "loss": 1.698, "step": 69880 }, { "epoch": 14.48, "learning_rate": 4.8087014597843715e-05, "loss": 1.6982, "step": 69885 }, { "epoch": 14.48, "learning_rate": 4.799160385459403e-05, "loss": 1.7023, "step": 69890 }, { "epoch": 14.48, "learning_rate": 4.789619311134434e-05, "loss": 1.6978, "step": 69895 }, { "epoch": 14.48, "learning_rate": 4.780078236809465e-05, "loss": 1.7001, "step": 69900 }, { "epoch": 14.48, "learning_rate": 4.7705371624844956e-05, "loss": 1.6953, "step": 69905 }, { "epoch": 14.48, "learning_rate": 4.760996088159527e-05, "loss": 1.6961, "step": 69910 }, { "epoch": 14.48, "learning_rate": 4.7514550138345584e-05, "loss": 1.6977, "step": 69915 }, { "epoch": 14.49, "learning_rate": 4.7419139395095884e-05, "loss": 1.6932, "step": 69920 }, { "epoch": 14.49, "learning_rate": 4.73237286518462e-05, "loss": 1.7031, "step": 69925 }, { "epoch": 14.49, "learning_rate": 4.722831790859651e-05, "loss": 1.6935, "step": 69930 }, { "epoch": 14.49, "learning_rate": 4.7132907165346825e-05, "loss": 1.6987, "step": 69935 }, { "epoch": 14.49, "learning_rate": 4.7037496422097125e-05, "loss": 1.699, "step": 69940 }, { "epoch": 14.49, "learning_rate": 4.694208567884744e-05, "loss": 1.7016, "step": 69945 }, { "epoch": 14.49, "learning_rate": 4.684667493559775e-05, "loss": 1.701, "step": 69950 }, { "epoch": 14.49, "learning_rate": 4.6751264192348066e-05, "loss": 1.7012, "step": 69955 }, { "epoch": 14.49, "learning_rate": 4.6655853449098366e-05, "loss": 1.6949, "step": 69960 }, { "epoch": 14.49, "learning_rate": 4.656044270584868e-05, "loss": 1.6991, "step": 69965 }, { "epoch": 14.5, "learning_rate": 4.646503196259899e-05, "loss": 1.7027, "step": 69970 }, { "epoch": 14.5, "learning_rate": 4.636962121934929e-05, "loss": 1.7024, "step": 69975 }, { "epoch": 14.5, "learning_rate": 4.627421047609961e-05, "loss": 1.6928, "step": 69980 }, { "epoch": 14.5, "learning_rate": 4.617879973284992e-05, "loss": 1.6966, "step": 69985 }, { "epoch": 14.5, "learning_rate": 4.6083388989600234e-05, "loss": 1.6987, "step": 69990 }, { "epoch": 14.5, "learning_rate": 4.5987978246350534e-05, "loss": 1.6995, "step": 69995 }, { "epoch": 14.5, "learning_rate": 4.589256750310085e-05, "loss": 1.7035, "step": 70000 }, { "epoch": 14.5, "learning_rate": 4.579715675985116e-05, "loss": 1.6973, "step": 70005 }, { "epoch": 14.5, "learning_rate": 4.5701746016601475e-05, "loss": 1.7016, "step": 70010 }, { "epoch": 14.5, "learning_rate": 4.5606335273351776e-05, "loss": 1.6938, "step": 70015 }, { "epoch": 14.51, "learning_rate": 4.551092453010209e-05, "loss": 1.6927, "step": 70020 }, { "epoch": 14.51, "learning_rate": 4.54155137868524e-05, "loss": 1.6968, "step": 70025 }, { "epoch": 14.51, "learning_rate": 4.532010304360271e-05, "loss": 1.7024, "step": 70030 }, { "epoch": 14.51, "learning_rate": 4.522469230035302e-05, "loss": 1.6962, "step": 70035 }, { "epoch": 14.51, "learning_rate": 4.512928155710333e-05, "loss": 1.6963, "step": 70040 }, { "epoch": 14.51, "learning_rate": 4.5033870813853644e-05, "loss": 1.6993, "step": 70045 }, { "epoch": 14.51, "learning_rate": 4.493846007060395e-05, "loss": 1.696, "step": 70050 }, { "epoch": 14.51, "learning_rate": 4.484304932735426e-05, "loss": 1.6963, "step": 70055 }, { "epoch": 14.51, "learning_rate": 4.474763858410457e-05, "loss": 1.7005, "step": 70060 }, { "epoch": 14.52, "learning_rate": 4.4652227840854885e-05, "loss": 1.6965, "step": 70065 }, { "epoch": 14.52, "learning_rate": 4.455681709760519e-05, "loss": 1.6933, "step": 70070 }, { "epoch": 14.52, "learning_rate": 4.44614063543555e-05, "loss": 1.6985, "step": 70075 }, { "epoch": 14.52, "learning_rate": 4.436599561110581e-05, "loss": 1.6993, "step": 70080 }, { "epoch": 14.52, "learning_rate": 4.4270584867856126e-05, "loss": 1.6947, "step": 70085 }, { "epoch": 14.52, "learning_rate": 4.417517412460643e-05, "loss": 1.698, "step": 70090 }, { "epoch": 14.52, "learning_rate": 4.407976338135674e-05, "loss": 1.6983, "step": 70095 }, { "epoch": 14.52, "learning_rate": 4.3984352638107054e-05, "loss": 1.6975, "step": 70100 }, { "epoch": 14.52, "learning_rate": 4.388894189485736e-05, "loss": 1.695, "step": 70105 }, { "epoch": 14.52, "learning_rate": 4.3793531151607674e-05, "loss": 1.6965, "step": 70110 }, { "epoch": 14.53, "learning_rate": 4.369812040835798e-05, "loss": 1.7011, "step": 70115 }, { "epoch": 14.53, "learning_rate": 4.3602709665108295e-05, "loss": 1.6986, "step": 70120 }, { "epoch": 14.53, "learning_rate": 4.35072989218586e-05, "loss": 1.6998, "step": 70125 }, { "epoch": 14.53, "learning_rate": 4.341188817860891e-05, "loss": 1.7, "step": 70130 }, { "epoch": 14.53, "learning_rate": 4.331647743535922e-05, "loss": 1.6966, "step": 70135 }, { "epoch": 14.53, "learning_rate": 4.3221066692109536e-05, "loss": 1.6953, "step": 70140 }, { "epoch": 14.53, "learning_rate": 4.312565594885984e-05, "loss": 1.6943, "step": 70145 }, { "epoch": 14.53, "learning_rate": 4.303024520561015e-05, "loss": 1.6982, "step": 70150 }, { "epoch": 14.53, "learning_rate": 4.293483446236046e-05, "loss": 1.6984, "step": 70155 }, { "epoch": 14.53, "learning_rate": 4.283942371911077e-05, "loss": 1.6934, "step": 70160 }, { "epoch": 14.54, "learning_rate": 4.2744012975861084e-05, "loss": 1.6965, "step": 70165 }, { "epoch": 14.54, "learning_rate": 4.264860223261139e-05, "loss": 1.6931, "step": 70170 }, { "epoch": 14.54, "learning_rate": 4.2553191489361704e-05, "loss": 1.6979, "step": 70175 }, { "epoch": 14.54, "learning_rate": 4.245778074611201e-05, "loss": 1.6982, "step": 70180 }, { "epoch": 14.54, "learning_rate": 4.2362370002862325e-05, "loss": 1.7028, "step": 70185 }, { "epoch": 14.54, "learning_rate": 4.226695925961263e-05, "loss": 1.6995, "step": 70190 }, { "epoch": 14.54, "learning_rate": 4.2171548516362946e-05, "loss": 1.7037, "step": 70195 }, { "epoch": 14.54, "learning_rate": 4.207613777311325e-05, "loss": 1.6949, "step": 70200 }, { "epoch": 14.54, "learning_rate": 4.1980727029863566e-05, "loss": 1.6952, "step": 70205 }, { "epoch": 14.55, "learning_rate": 4.188531628661387e-05, "loss": 1.7008, "step": 70210 }, { "epoch": 14.55, "learning_rate": 4.178990554336418e-05, "loss": 1.6986, "step": 70215 }, { "epoch": 14.55, "learning_rate": 4.1694494800114494e-05, "loss": 1.6968, "step": 70220 }, { "epoch": 14.55, "learning_rate": 4.159908405686481e-05, "loss": 1.6964, "step": 70225 }, { "epoch": 14.55, "learning_rate": 4.1503673313615114e-05, "loss": 1.698, "step": 70230 }, { "epoch": 14.55, "learning_rate": 4.140826257036542e-05, "loss": 1.6966, "step": 70235 }, { "epoch": 14.55, "learning_rate": 4.1312851827115735e-05, "loss": 1.6943, "step": 70240 }, { "epoch": 14.55, "learning_rate": 4.121744108386605e-05, "loss": 1.6998, "step": 70245 }, { "epoch": 14.55, "learning_rate": 4.1122030340616355e-05, "loss": 1.6913, "step": 70250 }, { "epoch": 14.55, "learning_rate": 4.102661959736666e-05, "loss": 1.6984, "step": 70255 }, { "epoch": 14.56, "learning_rate": 4.0931208854116976e-05, "loss": 1.7041, "step": 70260 }, { "epoch": 14.56, "learning_rate": 4.083579811086729e-05, "loss": 1.6998, "step": 70265 }, { "epoch": 14.56, "learning_rate": 4.074038736761759e-05, "loss": 1.6958, "step": 70270 }, { "epoch": 14.56, "learning_rate": 4.06449766243679e-05, "loss": 1.6921, "step": 70275 }, { "epoch": 14.56, "learning_rate": 4.054956588111822e-05, "loss": 1.6973, "step": 70280 }, { "epoch": 14.56, "learning_rate": 4.0454155137868524e-05, "loss": 1.7036, "step": 70285 }, { "epoch": 14.56, "learning_rate": 4.035874439461883e-05, "loss": 1.6969, "step": 70290 }, { "epoch": 14.56, "learning_rate": 4.0263333651369144e-05, "loss": 1.7017, "step": 70295 }, { "epoch": 14.56, "learning_rate": 4.016792290811946e-05, "loss": 1.6998, "step": 70300 }, { "epoch": 14.56, "learning_rate": 4.0072512164869765e-05, "loss": 1.6954, "step": 70305 }, { "epoch": 14.57, "learning_rate": 3.997710142162007e-05, "loss": 1.6934, "step": 70310 }, { "epoch": 14.57, "learning_rate": 3.9881690678370385e-05, "loss": 1.697, "step": 70315 }, { "epoch": 14.57, "learning_rate": 3.97862799351207e-05, "loss": 1.6985, "step": 70320 }, { "epoch": 14.57, "learning_rate": 3.9690869191871006e-05, "loss": 1.6969, "step": 70325 }, { "epoch": 14.57, "learning_rate": 3.959545844862131e-05, "loss": 1.7003, "step": 70330 }, { "epoch": 14.57, "learning_rate": 3.9500047705371627e-05, "loss": 1.696, "step": 70335 }, { "epoch": 14.57, "learning_rate": 3.940463696212194e-05, "loss": 1.6985, "step": 70340 }, { "epoch": 14.57, "learning_rate": 3.930922621887224e-05, "loss": 1.6937, "step": 70345 }, { "epoch": 14.57, "learning_rate": 3.9213815475622554e-05, "loss": 1.6924, "step": 70350 }, { "epoch": 14.58, "learning_rate": 3.911840473237287e-05, "loss": 1.6995, "step": 70355 }, { "epoch": 14.58, "learning_rate": 3.902299398912318e-05, "loss": 1.695, "step": 70360 }, { "epoch": 14.58, "learning_rate": 3.892758324587348e-05, "loss": 1.702, "step": 70365 }, { "epoch": 14.58, "learning_rate": 3.8832172502623795e-05, "loss": 1.7001, "step": 70370 }, { "epoch": 14.58, "learning_rate": 3.873676175937411e-05, "loss": 1.6945, "step": 70375 }, { "epoch": 14.58, "learning_rate": 3.864135101612442e-05, "loss": 1.6972, "step": 70380 }, { "epoch": 14.58, "learning_rate": 3.854594027287472e-05, "loss": 1.7035, "step": 70385 }, { "epoch": 14.58, "learning_rate": 3.8450529529625036e-05, "loss": 1.7001, "step": 70390 }, { "epoch": 14.58, "learning_rate": 3.835511878637535e-05, "loss": 1.7006, "step": 70395 }, { "epoch": 14.58, "learning_rate": 3.825970804312566e-05, "loss": 1.6947, "step": 70400 }, { "epoch": 14.59, "learning_rate": 3.8164297299875964e-05, "loss": 1.6958, "step": 70405 }, { "epoch": 14.59, "learning_rate": 3.806888655662628e-05, "loss": 1.7013, "step": 70410 }, { "epoch": 14.59, "learning_rate": 3.797347581337659e-05, "loss": 1.6982, "step": 70415 }, { "epoch": 14.59, "learning_rate": 3.787806507012689e-05, "loss": 1.6991, "step": 70420 }, { "epoch": 14.59, "learning_rate": 3.7782654326877205e-05, "loss": 1.6993, "step": 70425 }, { "epoch": 14.59, "learning_rate": 3.768724358362752e-05, "loss": 1.6997, "step": 70430 }, { "epoch": 14.59, "learning_rate": 3.759183284037783e-05, "loss": 1.6987, "step": 70435 }, { "epoch": 14.59, "learning_rate": 3.749642209712813e-05, "loss": 1.6996, "step": 70440 }, { "epoch": 14.59, "learning_rate": 3.7401011353878446e-05, "loss": 1.7002, "step": 70445 }, { "epoch": 14.59, "learning_rate": 3.730560061062876e-05, "loss": 1.6968, "step": 70450 }, { "epoch": 14.6, "learning_rate": 3.7210189867379066e-05, "loss": 1.7006, "step": 70455 }, { "epoch": 14.6, "learning_rate": 3.711477912412937e-05, "loss": 1.6979, "step": 70460 }, { "epoch": 14.6, "learning_rate": 3.701936838087969e-05, "loss": 1.6989, "step": 70465 }, { "epoch": 14.6, "learning_rate": 3.692395763763e-05, "loss": 1.7006, "step": 70470 }, { "epoch": 14.6, "learning_rate": 3.682854689438031e-05, "loss": 1.7031, "step": 70475 }, { "epoch": 14.6, "learning_rate": 3.6733136151130614e-05, "loss": 1.6946, "step": 70480 }, { "epoch": 14.6, "learning_rate": 3.663772540788093e-05, "loss": 1.7022, "step": 70485 }, { "epoch": 14.6, "learning_rate": 3.654231466463124e-05, "loss": 1.7, "step": 70490 }, { "epoch": 14.6, "learning_rate": 3.644690392138155e-05, "loss": 1.6931, "step": 70495 }, { "epoch": 14.61, "learning_rate": 3.6351493178131856e-05, "loss": 1.6977, "step": 70500 }, { "epoch": 14.61, "learning_rate": 3.625608243488217e-05, "loss": 1.6983, "step": 70505 }, { "epoch": 14.61, "learning_rate": 3.616067169163248e-05, "loss": 1.7031, "step": 70510 }, { "epoch": 14.61, "learning_rate": 3.606526094838279e-05, "loss": 1.6967, "step": 70515 }, { "epoch": 14.61, "learning_rate": 3.59698502051331e-05, "loss": 1.7003, "step": 70520 }, { "epoch": 14.61, "learning_rate": 3.587443946188341e-05, "loss": 1.6978, "step": 70525 }, { "epoch": 14.61, "learning_rate": 3.577902871863372e-05, "loss": 1.7034, "step": 70530 }, { "epoch": 14.61, "learning_rate": 3.568361797538403e-05, "loss": 1.7005, "step": 70535 }, { "epoch": 14.61, "learning_rate": 3.558820723213434e-05, "loss": 1.6943, "step": 70540 }, { "epoch": 14.61, "learning_rate": 3.549279648888465e-05, "loss": 1.703, "step": 70545 }, { "epoch": 14.62, "learning_rate": 3.539738574563496e-05, "loss": 1.7013, "step": 70550 }, { "epoch": 14.62, "learning_rate": 3.530197500238527e-05, "loss": 1.694, "step": 70555 }, { "epoch": 14.62, "learning_rate": 3.520656425913558e-05, "loss": 1.6963, "step": 70560 }, { "epoch": 14.62, "learning_rate": 3.511115351588589e-05, "loss": 1.7006, "step": 70565 }, { "epoch": 14.62, "learning_rate": 3.50157427726362e-05, "loss": 1.6983, "step": 70570 }, { "epoch": 14.62, "learning_rate": 3.4920332029386506e-05, "loss": 1.697, "step": 70575 }, { "epoch": 14.62, "learning_rate": 3.482492128613682e-05, "loss": 1.6976, "step": 70580 }, { "epoch": 14.62, "learning_rate": 3.472951054288713e-05, "loss": 1.6973, "step": 70585 }, { "epoch": 14.62, "learning_rate": 3.463409979963744e-05, "loss": 1.7, "step": 70590 }, { "epoch": 14.63, "learning_rate": 3.453868905638775e-05, "loss": 1.6989, "step": 70595 }, { "epoch": 14.63, "learning_rate": 3.444327831313806e-05, "loss": 1.6941, "step": 70600 }, { "epoch": 14.63, "learning_rate": 3.434786756988837e-05, "loss": 1.6986, "step": 70605 }, { "epoch": 14.63, "learning_rate": 3.425245682663868e-05, "loss": 1.6993, "step": 70610 }, { "epoch": 14.63, "learning_rate": 3.415704608338899e-05, "loss": 1.7003, "step": 70615 }, { "epoch": 14.63, "learning_rate": 3.40616353401393e-05, "loss": 1.703, "step": 70620 }, { "epoch": 14.63, "learning_rate": 3.396622459688961e-05, "loss": 1.6972, "step": 70625 }, { "epoch": 14.63, "learning_rate": 3.387081385363992e-05, "loss": 1.698, "step": 70630 }, { "epoch": 14.63, "learning_rate": 3.377540311039023e-05, "loss": 1.6934, "step": 70635 }, { "epoch": 14.63, "learning_rate": 3.3679992367140537e-05, "loss": 1.7047, "step": 70640 }, { "epoch": 14.64, "learning_rate": 3.358458162389085e-05, "loss": 1.6965, "step": 70645 }, { "epoch": 14.64, "learning_rate": 3.3489170880641164e-05, "loss": 1.7018, "step": 70650 }, { "epoch": 14.64, "learning_rate": 3.339376013739147e-05, "loss": 1.6906, "step": 70655 }, { "epoch": 14.64, "learning_rate": 3.329834939414178e-05, "loss": 1.6974, "step": 70660 }, { "epoch": 14.64, "learning_rate": 3.320293865089209e-05, "loss": 1.6952, "step": 70665 }, { "epoch": 14.64, "learning_rate": 3.3107527907642405e-05, "loss": 1.6988, "step": 70670 }, { "epoch": 14.64, "learning_rate": 3.301211716439271e-05, "loss": 1.6974, "step": 70675 }, { "epoch": 14.64, "learning_rate": 3.291670642114302e-05, "loss": 1.6982, "step": 70680 }, { "epoch": 14.64, "learning_rate": 3.282129567789333e-05, "loss": 1.6986, "step": 70685 }, { "epoch": 14.64, "learning_rate": 3.2725884934643646e-05, "loss": 1.693, "step": 70690 }, { "epoch": 14.65, "learning_rate": 3.263047419139395e-05, "loss": 1.6997, "step": 70695 }, { "epoch": 14.65, "learning_rate": 3.253506344814426e-05, "loss": 1.6973, "step": 70700 }, { "epoch": 14.65, "learning_rate": 3.2439652704894574e-05, "loss": 1.703, "step": 70705 }, { "epoch": 14.65, "learning_rate": 3.234424196164489e-05, "loss": 1.6973, "step": 70710 }, { "epoch": 14.65, "learning_rate": 3.224883121839519e-05, "loss": 1.701, "step": 70715 }, { "epoch": 14.65, "learning_rate": 3.21534204751455e-05, "loss": 1.6931, "step": 70720 }, { "epoch": 14.65, "learning_rate": 3.2058009731895815e-05, "loss": 1.699, "step": 70725 }, { "epoch": 14.65, "learning_rate": 3.196259898864612e-05, "loss": 1.6977, "step": 70730 }, { "epoch": 14.65, "learning_rate": 3.186718824539643e-05, "loss": 1.7001, "step": 70735 }, { "epoch": 14.66, "learning_rate": 3.177177750214674e-05, "loss": 1.7005, "step": 70740 }, { "epoch": 14.66, "learning_rate": 3.1676366758897056e-05, "loss": 1.6939, "step": 70745 }, { "epoch": 14.66, "learning_rate": 3.158095601564736e-05, "loss": 1.6923, "step": 70750 }, { "epoch": 14.66, "learning_rate": 3.148554527239767e-05, "loss": 1.6947, "step": 70755 }, { "epoch": 14.66, "learning_rate": 3.139013452914798e-05, "loss": 1.6955, "step": 70760 }, { "epoch": 14.66, "learning_rate": 3.12947237858983e-05, "loss": 1.6982, "step": 70765 }, { "epoch": 14.66, "learning_rate": 3.1199313042648604e-05, "loss": 1.6985, "step": 70770 }, { "epoch": 14.66, "learning_rate": 3.110390229939891e-05, "loss": 1.698, "step": 70775 }, { "epoch": 14.66, "learning_rate": 3.1008491556149224e-05, "loss": 1.6966, "step": 70780 }, { "epoch": 14.66, "learning_rate": 3.091308081289953e-05, "loss": 1.6988, "step": 70785 }, { "epoch": 14.67, "learning_rate": 3.0817670069649845e-05, "loss": 1.6983, "step": 70790 }, { "epoch": 14.67, "learning_rate": 3.072225932640015e-05, "loss": 1.6994, "step": 70795 }, { "epoch": 14.67, "learning_rate": 3.0626848583150465e-05, "loss": 1.6959, "step": 70800 }, { "epoch": 14.67, "learning_rate": 3.053143783990077e-05, "loss": 1.7025, "step": 70805 }, { "epoch": 14.67, "learning_rate": 3.0436027096651086e-05, "loss": 1.6975, "step": 70810 }, { "epoch": 14.67, "learning_rate": 3.0340616353401393e-05, "loss": 1.6977, "step": 70815 }, { "epoch": 14.67, "learning_rate": 3.0245205610151703e-05, "loss": 1.7018, "step": 70820 }, { "epoch": 14.67, "learning_rate": 3.0149794866902013e-05, "loss": 1.698, "step": 70825 }, { "epoch": 14.67, "learning_rate": 3.0054384123652324e-05, "loss": 1.7004, "step": 70830 }, { "epoch": 14.67, "learning_rate": 2.9958973380402634e-05, "loss": 1.6977, "step": 70835 }, { "epoch": 14.68, "learning_rate": 2.9863562637152944e-05, "loss": 1.6988, "step": 70840 }, { "epoch": 14.68, "learning_rate": 2.9768151893903254e-05, "loss": 1.6961, "step": 70845 }, { "epoch": 14.68, "learning_rate": 2.9672741150653565e-05, "loss": 1.7005, "step": 70850 }, { "epoch": 14.68, "learning_rate": 2.9577330407403875e-05, "loss": 1.6962, "step": 70855 }, { "epoch": 14.68, "learning_rate": 2.9481919664154185e-05, "loss": 1.6961, "step": 70860 }, { "epoch": 14.68, "learning_rate": 2.9386508920904496e-05, "loss": 1.6962, "step": 70865 }, { "epoch": 14.68, "learning_rate": 2.9291098177654806e-05, "loss": 1.6975, "step": 70870 }, { "epoch": 14.68, "learning_rate": 2.9195687434405116e-05, "loss": 1.6953, "step": 70875 }, { "epoch": 14.68, "learning_rate": 2.9100276691155423e-05, "loss": 1.6931, "step": 70880 }, { "epoch": 14.69, "learning_rate": 2.9004865947905733e-05, "loss": 1.696, "step": 70885 }, { "epoch": 14.69, "learning_rate": 2.8909455204656044e-05, "loss": 1.6983, "step": 70890 }, { "epoch": 14.69, "learning_rate": 2.8814044461406354e-05, "loss": 1.701, "step": 70895 }, { "epoch": 14.69, "learning_rate": 2.8718633718156664e-05, "loss": 1.6958, "step": 70900 }, { "epoch": 14.69, "learning_rate": 2.8623222974906974e-05, "loss": 1.6982, "step": 70905 }, { "epoch": 14.69, "learning_rate": 2.8527812231657285e-05, "loss": 1.7013, "step": 70910 }, { "epoch": 14.69, "learning_rate": 2.8432401488407595e-05, "loss": 1.6955, "step": 70915 }, { "epoch": 14.69, "learning_rate": 2.8336990745157905e-05, "loss": 1.693, "step": 70920 }, { "epoch": 14.69, "learning_rate": 2.8241580001908216e-05, "loss": 1.7019, "step": 70925 }, { "epoch": 14.69, "learning_rate": 2.8146169258658526e-05, "loss": 1.6955, "step": 70930 }, { "epoch": 14.7, "learning_rate": 2.8050758515408836e-05, "loss": 1.6998, "step": 70935 }, { "epoch": 14.7, "learning_rate": 2.7955347772159143e-05, "loss": 1.6928, "step": 70940 }, { "epoch": 14.7, "learning_rate": 2.7859937028909457e-05, "loss": 1.6963, "step": 70945 }, { "epoch": 14.7, "learning_rate": 2.7764526285659764e-05, "loss": 1.6966, "step": 70950 }, { "epoch": 14.7, "learning_rate": 2.7669115542410077e-05, "loss": 1.695, "step": 70955 }, { "epoch": 14.7, "learning_rate": 2.7573704799160384e-05, "loss": 1.6947, "step": 70960 }, { "epoch": 14.7, "learning_rate": 2.7478294055910698e-05, "loss": 1.7021, "step": 70965 }, { "epoch": 14.7, "learning_rate": 2.7382883312661005e-05, "loss": 1.6975, "step": 70970 }, { "epoch": 14.7, "learning_rate": 2.728747256941132e-05, "loss": 1.7002, "step": 70975 }, { "epoch": 14.7, "learning_rate": 2.7192061826161625e-05, "loss": 1.6991, "step": 70980 }, { "epoch": 14.71, "learning_rate": 2.709665108291194e-05, "loss": 1.6985, "step": 70985 }, { "epoch": 14.71, "learning_rate": 2.7001240339662246e-05, "loss": 1.6974, "step": 70990 }, { "epoch": 14.71, "learning_rate": 2.690582959641256e-05, "loss": 1.6916, "step": 70995 }, { "epoch": 14.71, "learning_rate": 2.6810418853162866e-05, "loss": 1.6948, "step": 71000 }, { "epoch": 14.71, "learning_rate": 2.6715008109913177e-05, "loss": 1.7016, "step": 71005 }, { "epoch": 14.71, "learning_rate": 2.6619597366663487e-05, "loss": 1.7004, "step": 71010 }, { "epoch": 14.71, "learning_rate": 2.6524186623413797e-05, "loss": 1.7006, "step": 71015 }, { "epoch": 14.71, "learning_rate": 2.6428775880164107e-05, "loss": 1.7004, "step": 71020 }, { "epoch": 14.71, "learning_rate": 2.6333365136914418e-05, "loss": 1.6989, "step": 71025 }, { "epoch": 14.72, "learning_rate": 2.6237954393664728e-05, "loss": 1.6925, "step": 71030 }, { "epoch": 14.72, "learning_rate": 2.6142543650415035e-05, "loss": 1.6961, "step": 71035 }, { "epoch": 14.72, "learning_rate": 2.604713290716535e-05, "loss": 1.6966, "step": 71040 }, { "epoch": 14.72, "learning_rate": 2.5951722163915655e-05, "loss": 1.6949, "step": 71045 }, { "epoch": 14.72, "learning_rate": 2.585631142066597e-05, "loss": 1.7021, "step": 71050 }, { "epoch": 14.72, "learning_rate": 2.5760900677416276e-05, "loss": 1.6994, "step": 71055 }, { "epoch": 14.72, "learning_rate": 2.566548993416659e-05, "loss": 1.6959, "step": 71060 }, { "epoch": 14.72, "learning_rate": 2.5570079190916897e-05, "loss": 1.6963, "step": 71065 }, { "epoch": 14.72, "learning_rate": 2.5474668447667207e-05, "loss": 1.6948, "step": 71070 }, { "epoch": 14.72, "learning_rate": 2.5379257704417517e-05, "loss": 1.6991, "step": 71075 }, { "epoch": 14.73, "learning_rate": 2.5283846961167827e-05, "loss": 1.6987, "step": 71080 }, { "epoch": 14.73, "learning_rate": 2.5188436217918138e-05, "loss": 1.6991, "step": 71085 }, { "epoch": 14.73, "learning_rate": 2.5093025474668448e-05, "loss": 1.699, "step": 71090 }, { "epoch": 14.73, "learning_rate": 2.4997614731418758e-05, "loss": 1.6988, "step": 71095 }, { "epoch": 14.73, "learning_rate": 2.490220398816907e-05, "loss": 1.6994, "step": 71100 }, { "epoch": 14.73, "learning_rate": 2.480679324491938e-05, "loss": 1.7006, "step": 71105 }, { "epoch": 14.73, "learning_rate": 2.471138250166969e-05, "loss": 1.6954, "step": 71110 }, { "epoch": 14.73, "learning_rate": 2.461597175842e-05, "loss": 1.6956, "step": 71115 }, { "epoch": 14.73, "learning_rate": 2.452056101517031e-05, "loss": 1.6997, "step": 71120 }, { "epoch": 14.73, "learning_rate": 2.4425150271920616e-05, "loss": 1.7023, "step": 71125 }, { "epoch": 14.74, "learning_rate": 2.432973952867093e-05, "loss": 1.6995, "step": 71130 }, { "epoch": 14.74, "learning_rate": 2.4234328785421237e-05, "loss": 1.6974, "step": 71135 }, { "epoch": 14.74, "learning_rate": 2.413891804217155e-05, "loss": 1.6982, "step": 71140 }, { "epoch": 14.74, "learning_rate": 2.4043507298921858e-05, "loss": 1.6981, "step": 71145 }, { "epoch": 14.74, "learning_rate": 2.394809655567217e-05, "loss": 1.7, "step": 71150 }, { "epoch": 14.74, "learning_rate": 2.3852685812422478e-05, "loss": 1.6977, "step": 71155 }, { "epoch": 14.74, "learning_rate": 2.3757275069172792e-05, "loss": 1.6946, "step": 71160 }, { "epoch": 14.74, "learning_rate": 2.36618643259231e-05, "loss": 1.7003, "step": 71165 }, { "epoch": 14.74, "learning_rate": 2.3566453582673412e-05, "loss": 1.6997, "step": 71170 }, { "epoch": 14.75, "learning_rate": 2.347104283942372e-05, "loss": 1.7013, "step": 71175 }, { "epoch": 14.75, "learning_rate": 2.3375632096174033e-05, "loss": 1.7051, "step": 71180 }, { "epoch": 14.75, "learning_rate": 2.328022135292434e-05, "loss": 1.6968, "step": 71185 }, { "epoch": 14.75, "learning_rate": 2.3184810609674647e-05, "loss": 1.6956, "step": 71190 }, { "epoch": 14.75, "learning_rate": 2.308939986642496e-05, "loss": 1.6997, "step": 71195 }, { "epoch": 14.75, "learning_rate": 2.2993989123175267e-05, "loss": 1.6987, "step": 71200 }, { "epoch": 14.75, "learning_rate": 2.289857837992558e-05, "loss": 1.6933, "step": 71205 }, { "epoch": 14.75, "learning_rate": 2.2803167636675888e-05, "loss": 1.6915, "step": 71210 }, { "epoch": 14.75, "learning_rate": 2.27077568934262e-05, "loss": 1.6987, "step": 71215 }, { "epoch": 14.75, "learning_rate": 2.261234615017651e-05, "loss": 1.6993, "step": 71220 }, { "epoch": 14.76, "learning_rate": 2.2516935406926822e-05, "loss": 1.6979, "step": 71225 }, { "epoch": 14.76, "learning_rate": 2.242152466367713e-05, "loss": 1.6909, "step": 71230 }, { "epoch": 14.76, "learning_rate": 2.2326113920427443e-05, "loss": 1.6964, "step": 71235 }, { "epoch": 14.76, "learning_rate": 2.223070317717775e-05, "loss": 1.7013, "step": 71240 }, { "epoch": 14.76, "learning_rate": 2.2135292433928063e-05, "loss": 1.694, "step": 71245 }, { "epoch": 14.76, "learning_rate": 2.203988169067837e-05, "loss": 1.704, "step": 71250 }, { "epoch": 14.76, "learning_rate": 2.194447094742868e-05, "loss": 1.6953, "step": 71255 }, { "epoch": 14.76, "learning_rate": 2.184906020417899e-05, "loss": 1.6979, "step": 71260 }, { "epoch": 14.76, "learning_rate": 2.17536494609293e-05, "loss": 1.7001, "step": 71265 }, { "epoch": 14.76, "learning_rate": 2.165823871767961e-05, "loss": 1.6962, "step": 71270 }, { "epoch": 14.77, "learning_rate": 2.156282797442992e-05, "loss": 1.6923, "step": 71275 }, { "epoch": 14.77, "learning_rate": 2.146741723118023e-05, "loss": 1.6945, "step": 71280 }, { "epoch": 14.77, "learning_rate": 2.1372006487930542e-05, "loss": 1.6995, "step": 71285 }, { "epoch": 14.77, "learning_rate": 2.1276595744680852e-05, "loss": 1.6983, "step": 71290 }, { "epoch": 14.77, "learning_rate": 2.1181185001431163e-05, "loss": 1.6934, "step": 71295 }, { "epoch": 14.77, "learning_rate": 2.1085774258181473e-05, "loss": 1.6964, "step": 71300 }, { "epoch": 14.77, "learning_rate": 2.0990363514931783e-05, "loss": 1.6959, "step": 71305 }, { "epoch": 14.77, "learning_rate": 2.089495277168209e-05, "loss": 1.6927, "step": 71310 }, { "epoch": 14.77, "learning_rate": 2.0799542028432404e-05, "loss": 1.6971, "step": 71315 }, { "epoch": 14.78, "learning_rate": 2.070413128518271e-05, "loss": 1.6956, "step": 71320 }, { "epoch": 14.78, "learning_rate": 2.0608720541933024e-05, "loss": 1.6932, "step": 71325 }, { "epoch": 14.78, "learning_rate": 2.051330979868333e-05, "loss": 1.6988, "step": 71330 }, { "epoch": 14.78, "learning_rate": 2.0417899055433645e-05, "loss": 1.6947, "step": 71335 }, { "epoch": 14.78, "learning_rate": 2.032248831218395e-05, "loss": 1.7008, "step": 71340 }, { "epoch": 14.78, "learning_rate": 2.0227077568934262e-05, "loss": 1.6969, "step": 71345 }, { "epoch": 14.78, "learning_rate": 2.0131666825684572e-05, "loss": 1.6985, "step": 71350 }, { "epoch": 14.78, "learning_rate": 2.0036256082434882e-05, "loss": 1.6987, "step": 71355 }, { "epoch": 14.78, "learning_rate": 1.9940845339185193e-05, "loss": 1.6986, "step": 71360 }, { "epoch": 14.78, "learning_rate": 1.9845434595935503e-05, "loss": 1.7036, "step": 71365 }, { "epoch": 14.79, "learning_rate": 1.9750023852685813e-05, "loss": 1.7004, "step": 71370 }, { "epoch": 14.79, "learning_rate": 1.965461310943612e-05, "loss": 1.6966, "step": 71375 }, { "epoch": 14.79, "learning_rate": 1.9559202366186434e-05, "loss": 1.694, "step": 71380 }, { "epoch": 14.79, "learning_rate": 1.946379162293674e-05, "loss": 1.6982, "step": 71385 }, { "epoch": 14.79, "learning_rate": 1.9368380879687054e-05, "loss": 1.695, "step": 71390 }, { "epoch": 14.79, "learning_rate": 1.927297013643736e-05, "loss": 1.6923, "step": 71395 }, { "epoch": 14.79, "learning_rate": 1.9177559393187675e-05, "loss": 1.6942, "step": 71400 }, { "epoch": 14.79, "learning_rate": 1.9082148649937982e-05, "loss": 1.7008, "step": 71405 }, { "epoch": 14.79, "learning_rate": 1.8986737906688295e-05, "loss": 1.6978, "step": 71410 }, { "epoch": 14.79, "learning_rate": 1.8891327163438602e-05, "loss": 1.6987, "step": 71415 }, { "epoch": 14.8, "learning_rate": 1.8795916420188916e-05, "loss": 1.6962, "step": 71420 }, { "epoch": 14.8, "learning_rate": 1.8700505676939223e-05, "loss": 1.6956, "step": 71425 }, { "epoch": 14.8, "learning_rate": 1.8605094933689533e-05, "loss": 1.7025, "step": 71430 }, { "epoch": 14.8, "learning_rate": 1.8509684190439843e-05, "loss": 1.6984, "step": 71435 }, { "epoch": 14.8, "learning_rate": 1.8414273447190154e-05, "loss": 1.6993, "step": 71440 }, { "epoch": 14.8, "learning_rate": 1.8318862703940464e-05, "loss": 1.6966, "step": 71445 }, { "epoch": 14.8, "learning_rate": 1.8223451960690774e-05, "loss": 1.7022, "step": 71450 }, { "epoch": 14.8, "learning_rate": 1.8128041217441085e-05, "loss": 1.6983, "step": 71455 }, { "epoch": 14.8, "learning_rate": 1.8032630474191395e-05, "loss": 1.6979, "step": 71460 }, { "epoch": 14.81, "learning_rate": 1.7937219730941705e-05, "loss": 1.7059, "step": 71465 }, { "epoch": 14.81, "learning_rate": 1.7841808987692015e-05, "loss": 1.6965, "step": 71470 }, { "epoch": 14.81, "learning_rate": 1.7746398244442326e-05, "loss": 1.6977, "step": 71475 }, { "epoch": 14.81, "learning_rate": 1.7650987501192636e-05, "loss": 1.7011, "step": 71480 }, { "epoch": 14.81, "learning_rate": 1.7555576757942946e-05, "loss": 1.7007, "step": 71485 }, { "epoch": 14.81, "learning_rate": 1.7460166014693253e-05, "loss": 1.6981, "step": 71490 }, { "epoch": 14.81, "learning_rate": 1.7364755271443563e-05, "loss": 1.7015, "step": 71495 }, { "epoch": 14.81, "learning_rate": 1.7269344528193874e-05, "loss": 1.6987, "step": 71500 }, { "epoch": 14.81, "learning_rate": 1.7173933784944184e-05, "loss": 1.7016, "step": 71505 }, { "epoch": 14.81, "learning_rate": 1.7078523041694494e-05, "loss": 1.6994, "step": 71510 }, { "epoch": 14.82, "learning_rate": 1.6983112298444805e-05, "loss": 1.7003, "step": 71515 }, { "epoch": 14.82, "learning_rate": 1.6887701555195115e-05, "loss": 1.7026, "step": 71520 }, { "epoch": 14.82, "learning_rate": 1.6792290811945425e-05, "loss": 1.6923, "step": 71525 }, { "epoch": 14.82, "learning_rate": 1.6696880068695735e-05, "loss": 1.6996, "step": 71530 }, { "epoch": 14.82, "learning_rate": 1.6601469325446046e-05, "loss": 1.7012, "step": 71535 }, { "epoch": 14.82, "learning_rate": 1.6506058582196356e-05, "loss": 1.6909, "step": 71540 }, { "epoch": 14.82, "learning_rate": 1.6410647838946666e-05, "loss": 1.6958, "step": 71545 }, { "epoch": 14.82, "learning_rate": 1.6315237095696976e-05, "loss": 1.6995, "step": 71550 }, { "epoch": 14.82, "learning_rate": 1.6219826352447287e-05, "loss": 1.6959, "step": 71555 }, { "epoch": 14.82, "learning_rate": 1.6124415609197594e-05, "loss": 1.7001, "step": 71560 }, { "epoch": 14.83, "learning_rate": 1.6029004865947907e-05, "loss": 1.6942, "step": 71565 }, { "epoch": 14.83, "learning_rate": 1.5933594122698214e-05, "loss": 1.6965, "step": 71570 }, { "epoch": 14.83, "learning_rate": 1.5838183379448528e-05, "loss": 1.6968, "step": 71575 }, { "epoch": 14.83, "learning_rate": 1.5742772636198835e-05, "loss": 1.6988, "step": 71580 }, { "epoch": 14.83, "learning_rate": 1.564736189294915e-05, "loss": 1.7001, "step": 71585 }, { "epoch": 14.83, "learning_rate": 1.5551951149699455e-05, "loss": 1.6939, "step": 71590 }, { "epoch": 14.83, "learning_rate": 1.5456540406449766e-05, "loss": 1.6945, "step": 71595 }, { "epoch": 14.83, "learning_rate": 1.5361129663200076e-05, "loss": 1.6973, "step": 71600 }, { "epoch": 14.83, "learning_rate": 1.5265718919950386e-05, "loss": 1.6939, "step": 71605 }, { "epoch": 14.84, "learning_rate": 1.5170308176700696e-05, "loss": 1.6966, "step": 71610 }, { "epoch": 14.84, "learning_rate": 1.5074897433451007e-05, "loss": 1.6956, "step": 71615 }, { "epoch": 14.84, "learning_rate": 1.4979486690201317e-05, "loss": 1.7004, "step": 71620 }, { "epoch": 14.84, "learning_rate": 1.4884075946951627e-05, "loss": 1.702, "step": 71625 }, { "epoch": 14.84, "learning_rate": 1.4788665203701938e-05, "loss": 1.6923, "step": 71630 }, { "epoch": 14.84, "learning_rate": 1.4693254460452248e-05, "loss": 1.7019, "step": 71635 }, { "epoch": 14.84, "learning_rate": 1.4597843717202558e-05, "loss": 1.6905, "step": 71640 }, { "epoch": 14.84, "learning_rate": 1.4502432973952867e-05, "loss": 1.6996, "step": 71645 }, { "epoch": 14.84, "learning_rate": 1.4407022230703177e-05, "loss": 1.6965, "step": 71650 }, { "epoch": 14.84, "learning_rate": 1.4311611487453487e-05, "loss": 1.6994, "step": 71655 }, { "epoch": 14.85, "learning_rate": 1.4216200744203797e-05, "loss": 1.7018, "step": 71660 }, { "epoch": 14.85, "learning_rate": 1.4120790000954108e-05, "loss": 1.6972, "step": 71665 }, { "epoch": 14.85, "learning_rate": 1.4025379257704418e-05, "loss": 1.6949, "step": 71670 }, { "epoch": 14.85, "learning_rate": 1.3929968514454728e-05, "loss": 1.6997, "step": 71675 }, { "epoch": 14.85, "learning_rate": 1.3834557771205039e-05, "loss": 1.6948, "step": 71680 }, { "epoch": 14.85, "learning_rate": 1.3739147027955349e-05, "loss": 1.6972, "step": 71685 }, { "epoch": 14.85, "learning_rate": 1.364373628470566e-05, "loss": 1.699, "step": 71690 }, { "epoch": 14.85, "learning_rate": 1.354832554145597e-05, "loss": 1.6965, "step": 71695 }, { "epoch": 14.85, "learning_rate": 1.345291479820628e-05, "loss": 1.6985, "step": 71700 }, { "epoch": 14.85, "learning_rate": 1.3357504054956588e-05, "loss": 1.6933, "step": 71705 }, { "epoch": 14.86, "learning_rate": 1.3262093311706899e-05, "loss": 1.6952, "step": 71710 }, { "epoch": 14.86, "learning_rate": 1.3166682568457209e-05, "loss": 1.6957, "step": 71715 }, { "epoch": 14.86, "learning_rate": 1.3071271825207517e-05, "loss": 1.6977, "step": 71720 }, { "epoch": 14.86, "learning_rate": 1.2975861081957828e-05, "loss": 1.6953, "step": 71725 }, { "epoch": 14.86, "learning_rate": 1.2880450338708138e-05, "loss": 1.6989, "step": 71730 }, { "epoch": 14.86, "learning_rate": 1.2785039595458448e-05, "loss": 1.6964, "step": 71735 }, { "epoch": 14.86, "learning_rate": 1.2689628852208759e-05, "loss": 1.696, "step": 71740 }, { "epoch": 14.86, "learning_rate": 1.2594218108959069e-05, "loss": 1.6934, "step": 71745 }, { "epoch": 14.86, "learning_rate": 1.2498807365709379e-05, "loss": 1.6942, "step": 71750 }, { "epoch": 14.87, "learning_rate": 1.240339662245969e-05, "loss": 1.6984, "step": 71755 }, { "epoch": 14.87, "learning_rate": 1.230798587921e-05, "loss": 1.6951, "step": 71760 }, { "epoch": 14.87, "learning_rate": 1.2212575135960308e-05, "loss": 1.7023, "step": 71765 }, { "epoch": 14.87, "learning_rate": 1.2117164392710619e-05, "loss": 1.7004, "step": 71770 }, { "epoch": 14.87, "learning_rate": 1.2021753649460929e-05, "loss": 1.7025, "step": 71775 }, { "epoch": 14.87, "learning_rate": 1.1926342906211239e-05, "loss": 1.6945, "step": 71780 }, { "epoch": 14.87, "learning_rate": 1.183093216296155e-05, "loss": 1.6922, "step": 71785 }, { "epoch": 14.87, "learning_rate": 1.173552141971186e-05, "loss": 1.6989, "step": 71790 }, { "epoch": 14.87, "learning_rate": 1.164011067646217e-05, "loss": 1.7027, "step": 71795 }, { "epoch": 14.87, "learning_rate": 1.154469993321248e-05, "loss": 1.6995, "step": 71800 }, { "epoch": 14.88, "learning_rate": 1.144928918996279e-05, "loss": 1.6969, "step": 71805 }, { "epoch": 14.88, "learning_rate": 1.13538784467131e-05, "loss": 1.6975, "step": 71810 }, { "epoch": 14.88, "learning_rate": 1.1258467703463411e-05, "loss": 1.6947, "step": 71815 }, { "epoch": 14.88, "learning_rate": 1.1163056960213721e-05, "loss": 1.7024, "step": 71820 }, { "epoch": 14.88, "learning_rate": 1.1067646216964032e-05, "loss": 1.6931, "step": 71825 }, { "epoch": 14.88, "learning_rate": 1.097223547371434e-05, "loss": 1.6957, "step": 71830 }, { "epoch": 14.88, "learning_rate": 1.087682473046465e-05, "loss": 1.694, "step": 71835 }, { "epoch": 14.88, "learning_rate": 1.078141398721496e-05, "loss": 1.6944, "step": 71840 }, { "epoch": 14.88, "learning_rate": 1.0686003243965271e-05, "loss": 1.6956, "step": 71845 }, { "epoch": 14.89, "learning_rate": 1.0590592500715581e-05, "loss": 1.6983, "step": 71850 }, { "epoch": 14.89, "learning_rate": 1.0495181757465892e-05, "loss": 1.6992, "step": 71855 }, { "epoch": 14.89, "learning_rate": 1.0399771014216202e-05, "loss": 1.6961, "step": 71860 }, { "epoch": 14.89, "learning_rate": 1.0304360270966512e-05, "loss": 1.6987, "step": 71865 }, { "epoch": 14.89, "learning_rate": 1.0208949527716822e-05, "loss": 1.6936, "step": 71870 }, { "epoch": 14.89, "learning_rate": 1.0113538784467131e-05, "loss": 1.694, "step": 71875 }, { "epoch": 14.89, "learning_rate": 1.0018128041217441e-05, "loss": 1.6981, "step": 71880 }, { "epoch": 14.89, "learning_rate": 9.922717297967751e-06, "loss": 1.7008, "step": 71885 }, { "epoch": 14.89, "learning_rate": 9.82730655471806e-06, "loss": 1.6955, "step": 71890 }, { "epoch": 14.89, "learning_rate": 9.73189581146837e-06, "loss": 1.6954, "step": 71895 }, { "epoch": 14.9, "learning_rate": 9.63648506821868e-06, "loss": 1.6957, "step": 71900 }, { "epoch": 14.9, "learning_rate": 9.541074324968991e-06, "loss": 1.6994, "step": 71905 }, { "epoch": 14.9, "learning_rate": 9.445663581719301e-06, "loss": 1.6984, "step": 71910 }, { "epoch": 14.9, "learning_rate": 9.350252838469611e-06, "loss": 1.6997, "step": 71915 }, { "epoch": 14.9, "learning_rate": 9.254842095219922e-06, "loss": 1.6942, "step": 71920 }, { "epoch": 14.9, "learning_rate": 9.159431351970232e-06, "loss": 1.6984, "step": 71925 }, { "epoch": 14.9, "learning_rate": 9.064020608720542e-06, "loss": 1.6941, "step": 71930 }, { "epoch": 14.9, "learning_rate": 8.968609865470853e-06, "loss": 1.6975, "step": 71935 }, { "epoch": 14.9, "learning_rate": 8.873199122221163e-06, "loss": 1.6948, "step": 71940 }, { "epoch": 14.9, "learning_rate": 8.777788378971473e-06, "loss": 1.693, "step": 71945 }, { "epoch": 14.91, "learning_rate": 8.682377635721782e-06, "loss": 1.6945, "step": 71950 }, { "epoch": 14.91, "learning_rate": 8.586966892472092e-06, "loss": 1.6978, "step": 71955 }, { "epoch": 14.91, "learning_rate": 8.491556149222402e-06, "loss": 1.6938, "step": 71960 }, { "epoch": 14.91, "learning_rate": 8.396145405972713e-06, "loss": 1.6977, "step": 71965 }, { "epoch": 14.91, "learning_rate": 8.300734662723023e-06, "loss": 1.6993, "step": 71970 }, { "epoch": 14.91, "learning_rate": 8.205323919473333e-06, "loss": 1.6911, "step": 71975 }, { "epoch": 14.91, "learning_rate": 8.109913176223643e-06, "loss": 1.699, "step": 71980 }, { "epoch": 14.91, "learning_rate": 8.014502432973954e-06, "loss": 1.6968, "step": 71985 }, { "epoch": 14.91, "learning_rate": 7.919091689724264e-06, "loss": 1.6956, "step": 71990 }, { "epoch": 14.92, "learning_rate": 7.823680946474574e-06, "loss": 1.6938, "step": 71995 }, { "epoch": 14.92, "learning_rate": 7.728270203224883e-06, "loss": 1.7001, "step": 72000 }, { "epoch": 14.92, "eval_accuracy": 0.5484183006535948, "eval_loss": 1.8950828313827515, "eval_runtime": 0.6476, "eval_samples_per_second": 231.625, "eval_steps_per_second": 1.544, "step": 72000 }, { "epoch": 14.92, "learning_rate": 7.632859459975193e-06, "loss": 1.6979, "step": 72005 }, { "epoch": 14.92, "learning_rate": 7.537448716725503e-06, "loss": 1.6957, "step": 72010 }, { "epoch": 14.92, "learning_rate": 7.442037973475814e-06, "loss": 1.6988, "step": 72015 }, { "epoch": 14.92, "learning_rate": 7.346627230226124e-06, "loss": 1.7012, "step": 72020 }, { "epoch": 14.92, "learning_rate": 7.251216486976433e-06, "loss": 1.6914, "step": 72025 }, { "epoch": 14.92, "learning_rate": 7.155805743726744e-06, "loss": 1.6984, "step": 72030 }, { "epoch": 14.92, "learning_rate": 7.060395000477054e-06, "loss": 1.702, "step": 72035 }, { "epoch": 14.92, "learning_rate": 6.964984257227364e-06, "loss": 1.699, "step": 72040 }, { "epoch": 14.93, "learning_rate": 6.8695735139776744e-06, "loss": 1.6986, "step": 72045 }, { "epoch": 14.93, "learning_rate": 6.774162770727985e-06, "loss": 1.6936, "step": 72050 }, { "epoch": 14.93, "learning_rate": 6.678752027478294e-06, "loss": 1.6977, "step": 72055 }, { "epoch": 14.93, "learning_rate": 6.5833412842286044e-06, "loss": 1.698, "step": 72060 }, { "epoch": 14.93, "learning_rate": 6.487930540978914e-06, "loss": 1.701, "step": 72065 }, { "epoch": 14.93, "learning_rate": 6.392519797729224e-06, "loss": 1.6964, "step": 72070 }, { "epoch": 14.93, "learning_rate": 6.297109054479534e-06, "loss": 1.6982, "step": 72075 }, { "epoch": 14.93, "learning_rate": 6.201698311229845e-06, "loss": 1.7009, "step": 72080 }, { "epoch": 14.93, "learning_rate": 6.106287567980154e-06, "loss": 1.6994, "step": 72085 }, { "epoch": 14.93, "learning_rate": 6.010876824730464e-06, "loss": 1.6973, "step": 72090 }, { "epoch": 14.94, "learning_rate": 5.915466081480775e-06, "loss": 1.6996, "step": 72095 }, { "epoch": 14.94, "learning_rate": 5.820055338231085e-06, "loss": 1.7019, "step": 72100 }, { "epoch": 14.94, "learning_rate": 5.724644594981395e-06, "loss": 1.6981, "step": 72105 }, { "epoch": 14.94, "learning_rate": 5.6292338517317055e-06, "loss": 1.698, "step": 72110 }, { "epoch": 14.94, "learning_rate": 5.533823108482016e-06, "loss": 1.6962, "step": 72115 }, { "epoch": 14.94, "learning_rate": 5.438412365232325e-06, "loss": 1.6949, "step": 72120 }, { "epoch": 14.94, "learning_rate": 5.3430016219826355e-06, "loss": 1.6965, "step": 72125 }, { "epoch": 14.94, "learning_rate": 5.247590878732946e-06, "loss": 1.6996, "step": 72130 }, { "epoch": 14.94, "learning_rate": 5.152180135483256e-06, "loss": 1.6987, "step": 72135 }, { "epoch": 14.95, "learning_rate": 5.0567693922335655e-06, "loss": 1.6993, "step": 72140 }, { "epoch": 14.95, "learning_rate": 4.961358648983876e-06, "loss": 1.6961, "step": 72145 }, { "epoch": 14.95, "learning_rate": 4.865947905734185e-06, "loss": 1.7003, "step": 72150 }, { "epoch": 14.95, "learning_rate": 4.7705371624844955e-06, "loss": 1.6965, "step": 72155 }, { "epoch": 14.95, "learning_rate": 4.675126419234806e-06, "loss": 1.699, "step": 72160 }, { "epoch": 14.95, "learning_rate": 4.579715675985116e-06, "loss": 1.6968, "step": 72165 }, { "epoch": 14.95, "learning_rate": 4.484304932735426e-06, "loss": 1.7018, "step": 72170 }, { "epoch": 14.95, "learning_rate": 4.3888941894857366e-06, "loss": 1.6981, "step": 72175 }, { "epoch": 14.95, "learning_rate": 4.293483446236046e-06, "loss": 1.6991, "step": 72180 }, { "epoch": 14.95, "learning_rate": 4.198072702986356e-06, "loss": 1.6993, "step": 72185 }, { "epoch": 14.96, "learning_rate": 4.1026619597366666e-06, "loss": 1.6933, "step": 72190 }, { "epoch": 14.96, "learning_rate": 4.007251216486977e-06, "loss": 1.6961, "step": 72195 }, { "epoch": 14.96, "learning_rate": 3.911840473237287e-06, "loss": 1.6935, "step": 72200 }, { "epoch": 14.96, "learning_rate": 3.8164297299875965e-06, "loss": 1.6993, "step": 72205 }, { "epoch": 14.96, "learning_rate": 3.721018986737907e-06, "loss": 1.6988, "step": 72210 }, { "epoch": 14.96, "learning_rate": 3.6256082434882167e-06, "loss": 1.6956, "step": 72215 }, { "epoch": 14.96, "learning_rate": 3.530197500238527e-06, "loss": 1.6969, "step": 72220 }, { "epoch": 14.96, "learning_rate": 3.4347867569888372e-06, "loss": 1.6939, "step": 72225 }, { "epoch": 14.96, "learning_rate": 3.339376013739147e-06, "loss": 1.7012, "step": 72230 }, { "epoch": 14.96, "learning_rate": 3.243965270489457e-06, "loss": 1.6959, "step": 72235 }, { "epoch": 14.97, "learning_rate": 3.148554527239767e-06, "loss": 1.6988, "step": 72240 }, { "epoch": 14.97, "learning_rate": 3.053143783990077e-06, "loss": 1.6934, "step": 72245 }, { "epoch": 14.97, "learning_rate": 2.9577330407403873e-06, "loss": 1.6944, "step": 72250 }, { "epoch": 14.97, "learning_rate": 2.8623222974906976e-06, "loss": 1.6947, "step": 72255 }, { "epoch": 14.97, "learning_rate": 2.766911554241008e-06, "loss": 1.6909, "step": 72260 }, { "epoch": 14.97, "learning_rate": 2.6715008109913177e-06, "loss": 1.7018, "step": 72265 }, { "epoch": 14.97, "learning_rate": 2.576090067741628e-06, "loss": 1.6945, "step": 72270 }, { "epoch": 14.97, "learning_rate": 2.480679324491938e-06, "loss": 1.6917, "step": 72275 }, { "epoch": 14.97, "learning_rate": 2.3852685812422477e-06, "loss": 1.7004, "step": 72280 }, { "epoch": 14.98, "learning_rate": 2.289857837992558e-06, "loss": 1.6969, "step": 72285 }, { "epoch": 14.98, "learning_rate": 2.1944470947428683e-06, "loss": 1.6974, "step": 72290 }, { "epoch": 14.98, "learning_rate": 2.099036351493178e-06, "loss": 1.697, "step": 72295 }, { "epoch": 14.98, "learning_rate": 2.0036256082434884e-06, "loss": 1.6957, "step": 72300 }, { "epoch": 14.98, "learning_rate": 1.9082148649937983e-06, "loss": 1.6994, "step": 72305 }, { "epoch": 14.98, "learning_rate": 1.8128041217441083e-06, "loss": 1.6994, "step": 72310 }, { "epoch": 14.98, "learning_rate": 1.7173933784944186e-06, "loss": 1.7002, "step": 72315 }, { "epoch": 14.98, "learning_rate": 1.6219826352447285e-06, "loss": 1.6981, "step": 72320 }, { "epoch": 14.98, "learning_rate": 1.5265718919950385e-06, "loss": 1.6994, "step": 72325 }, { "epoch": 14.98, "learning_rate": 1.4311611487453488e-06, "loss": 1.6986, "step": 72330 }, { "epoch": 14.99, "learning_rate": 1.3357504054956589e-06, "loss": 1.6944, "step": 72335 }, { "epoch": 14.99, "learning_rate": 1.240339662245969e-06, "loss": 1.6952, "step": 72340 }, { "epoch": 14.99, "learning_rate": 1.144928918996279e-06, "loss": 1.7018, "step": 72345 }, { "epoch": 14.99, "learning_rate": 1.049518175746589e-06, "loss": 1.6978, "step": 72350 }, { "epoch": 14.99, "learning_rate": 9.541074324968991e-07, "loss": 1.6936, "step": 72355 }, { "epoch": 14.99, "learning_rate": 8.586966892472093e-07, "loss": 1.699, "step": 72360 }, { "epoch": 14.99, "learning_rate": 7.632859459975193e-07, "loss": 1.6961, "step": 72365 }, { "epoch": 14.99, "learning_rate": 6.678752027478294e-07, "loss": 1.6998, "step": 72370 }, { "epoch": 14.99, "learning_rate": 5.724644594981395e-07, "loss": 1.7018, "step": 72375 }, { "epoch": 14.99, "learning_rate": 4.770537162484496e-07, "loss": 1.7019, "step": 72380 }, { "epoch": 15.0, "learning_rate": 3.8164297299875963e-07, "loss": 1.696, "step": 72385 }, { "epoch": 15.0, "learning_rate": 2.8623222974906975e-07, "loss": 1.6979, "step": 72390 }, { "epoch": 15.0, "learning_rate": 1.9082148649937982e-07, "loss": 1.698, "step": 72395 }, { "epoch": 15.0, "learning_rate": 9.541074324968991e-08, "loss": 1.7008, "step": 72400 }, { "epoch": 15.0, "learning_rate": 0.0, "loss": 1.7016, "step": 72405 }, { "epoch": 15.0, "step": 72405, "total_flos": 2.8720873805237453e+18, "train_loss": 1.825768414206222, "train_runtime": 33117.864, "train_samples_per_second": 1119.181, "train_steps_per_second": 2.186 } ], "max_steps": 72405, "num_train_epochs": 15, "total_flos": 2.8720873805237453e+18, "trial_name": null, "trial_params": null }