{ "best_metric": null, "best_model_checkpoint": null, "epoch": 9.999657530337105, "global_step": 218990, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.0000000000000002e-06, "loss": 10.6535, "step": 10 }, { "epoch": 0.0, "learning_rate": 2.0000000000000003e-06, "loss": 10.6545, "step": 20 }, { "epoch": 0.0, "learning_rate": 3e-06, "loss": 10.6543, "step": 30 }, { "epoch": 0.0, "learning_rate": 4.000000000000001e-06, "loss": 10.6501, "step": 40 }, { "epoch": 0.0, "learning_rate": 5e-06, "loss": 10.6485, "step": 50 }, { "epoch": 0.0, "learning_rate": 6e-06, "loss": 10.6453, "step": 60 }, { "epoch": 0.0, "learning_rate": 7.000000000000001e-06, "loss": 10.6321, "step": 70 }, { "epoch": 0.0, "learning_rate": 8.000000000000001e-06, "loss": 10.6263, "step": 80 }, { "epoch": 0.0, "learning_rate": 9e-06, "loss": 10.6127, "step": 90 }, { "epoch": 0.0, "learning_rate": 1e-05, "loss": 10.6117, "step": 100 }, { "epoch": 0.01, "learning_rate": 1.1000000000000001e-05, "loss": 10.5884, "step": 110 }, { "epoch": 0.01, "learning_rate": 1.2e-05, "loss": 10.5577, "step": 120 }, { "epoch": 0.01, "learning_rate": 1.3000000000000001e-05, "loss": 10.5188, "step": 130 }, { "epoch": 0.01, "learning_rate": 1.4000000000000001e-05, "loss": 10.4525, "step": 140 }, { "epoch": 0.01, "learning_rate": 1.5e-05, "loss": 10.3086, "step": 150 }, { "epoch": 0.01, "learning_rate": 1.6000000000000003e-05, "loss": 10.1167, "step": 160 }, { "epoch": 0.01, "learning_rate": 1.7000000000000003e-05, "loss": 9.9627, "step": 170 }, { "epoch": 0.01, "learning_rate": 1.8e-05, "loss": 9.7518, "step": 180 }, { "epoch": 0.01, "learning_rate": 1.9e-05, "loss": 9.5303, "step": 190 }, { "epoch": 0.01, "learning_rate": 2e-05, "loss": 9.3458, "step": 200 }, { "epoch": 0.01, "learning_rate": 2.1e-05, "loss": 9.1597, "step": 210 }, { "epoch": 0.01, "learning_rate": 2.2000000000000003e-05, "loss": 8.9126, "step": 220 }, { "epoch": 0.01, "learning_rate": 2.3000000000000003e-05, "loss": 8.6596, "step": 230 }, { "epoch": 0.01, "learning_rate": 2.4e-05, "loss": 8.4269, "step": 240 }, { "epoch": 0.01, "learning_rate": 2.5e-05, "loss": 8.075, "step": 250 }, { "epoch": 0.01, "learning_rate": 2.6000000000000002e-05, "loss": 7.8707, "step": 260 }, { "epoch": 0.01, "learning_rate": 2.7000000000000002e-05, "loss": 7.7206, "step": 270 }, { "epoch": 0.01, "learning_rate": 2.8000000000000003e-05, "loss": 7.4398, "step": 280 }, { "epoch": 0.01, "learning_rate": 2.9e-05, "loss": 7.2054, "step": 290 }, { "epoch": 0.01, "learning_rate": 3e-05, "loss": 7.037, "step": 300 }, { "epoch": 0.01, "learning_rate": 3.1e-05, "loss": 6.8984, "step": 310 }, { "epoch": 0.01, "learning_rate": 3.2000000000000005e-05, "loss": 6.7157, "step": 320 }, { "epoch": 0.02, "learning_rate": 3.3e-05, "loss": 6.7826, "step": 330 }, { "epoch": 0.02, "learning_rate": 3.4000000000000007e-05, "loss": 6.4694, "step": 340 }, { "epoch": 0.02, "learning_rate": 3.5e-05, "loss": 6.3988, "step": 350 }, { "epoch": 0.02, "learning_rate": 3.6e-05, "loss": 6.2823, "step": 360 }, { "epoch": 0.02, "learning_rate": 3.7e-05, "loss": 6.3748, "step": 370 }, { "epoch": 0.02, "learning_rate": 3.8e-05, "loss": 6.2463, "step": 380 }, { "epoch": 0.02, "learning_rate": 3.9000000000000006e-05, "loss": 6.3301, "step": 390 }, { "epoch": 0.02, "learning_rate": 4e-05, "loss": 6.2103, "step": 400 }, { "epoch": 0.02, "learning_rate": 4.1e-05, "loss": 6.2585, "step": 410 }, { "epoch": 0.02, "learning_rate": 4.2e-05, "loss": 6.0927, "step": 420 }, { "epoch": 0.02, "learning_rate": 4.3e-05, "loss": 6.0841, "step": 430 }, { "epoch": 0.02, "learning_rate": 4.4000000000000006e-05, "loss": 6.1767, "step": 440 }, { "epoch": 0.02, "learning_rate": 4.5e-05, "loss": 6.0357, "step": 450 }, { "epoch": 0.02, "learning_rate": 4.600000000000001e-05, "loss": 6.0245, "step": 460 }, { "epoch": 0.02, "learning_rate": 4.7e-05, "loss": 6.0581, "step": 470 }, { "epoch": 0.02, "learning_rate": 4.8e-05, "loss": 6.0957, "step": 480 }, { "epoch": 0.02, "learning_rate": 4.9e-05, "loss": 6.1967, "step": 490 }, { "epoch": 0.02, "learning_rate": 5e-05, "loss": 6.0921, "step": 500 }, { "epoch": 0.02, "learning_rate": 4.9997711565746717e-05, "loss": 5.988, "step": 510 }, { "epoch": 0.02, "learning_rate": 4.999542313149344e-05, "loss": 6.074, "step": 520 }, { "epoch": 0.02, "learning_rate": 4.999313469724015e-05, "loss": 6.0336, "step": 530 }, { "epoch": 0.02, "learning_rate": 4.9990846262986866e-05, "loss": 6.0146, "step": 540 }, { "epoch": 0.03, "learning_rate": 4.998855782873359e-05, "loss": 6.0141, "step": 550 }, { "epoch": 0.03, "learning_rate": 4.99862693944803e-05, "loss": 6.0994, "step": 560 }, { "epoch": 0.03, "learning_rate": 4.9983980960227015e-05, "loss": 6.0777, "step": 570 }, { "epoch": 0.03, "learning_rate": 4.9981692525973736e-05, "loss": 5.9907, "step": 580 }, { "epoch": 0.03, "learning_rate": 4.997940409172045e-05, "loss": 5.9432, "step": 590 }, { "epoch": 0.03, "learning_rate": 4.997711565746716e-05, "loss": 6.056, "step": 600 }, { "epoch": 0.03, "learning_rate": 4.997482722321388e-05, "loss": 6.0739, "step": 610 }, { "epoch": 0.03, "learning_rate": 4.997253878896059e-05, "loss": 6.0262, "step": 620 }, { "epoch": 0.03, "learning_rate": 4.9970250354707306e-05, "loss": 6.0187, "step": 630 }, { "epoch": 0.03, "learning_rate": 4.996796192045403e-05, "loss": 6.1239, "step": 640 }, { "epoch": 0.03, "learning_rate": 4.996567348620074e-05, "loss": 6.0736, "step": 650 }, { "epoch": 0.03, "learning_rate": 4.9963385051947456e-05, "loss": 5.9753, "step": 660 }, { "epoch": 0.03, "learning_rate": 4.9961096617694177e-05, "loss": 6.0379, "step": 670 }, { "epoch": 0.03, "learning_rate": 4.995880818344089e-05, "loss": 5.979, "step": 680 }, { "epoch": 0.03, "learning_rate": 4.9956519749187605e-05, "loss": 5.951, "step": 690 }, { "epoch": 0.03, "learning_rate": 4.9954231314934326e-05, "loss": 6.0342, "step": 700 }, { "epoch": 0.03, "learning_rate": 4.995194288068104e-05, "loss": 6.1239, "step": 710 }, { "epoch": 0.03, "learning_rate": 4.9949654446427754e-05, "loss": 5.9036, "step": 720 }, { "epoch": 0.03, "learning_rate": 4.9947366012174475e-05, "loss": 5.9669, "step": 730 }, { "epoch": 0.03, "learning_rate": 4.994507757792119e-05, "loss": 5.9677, "step": 740 }, { "epoch": 0.03, "learning_rate": 4.99427891436679e-05, "loss": 5.8733, "step": 750 }, { "epoch": 0.03, "learning_rate": 4.9940500709414624e-05, "loss": 5.9922, "step": 760 }, { "epoch": 0.04, "learning_rate": 4.993821227516134e-05, "loss": 5.9072, "step": 770 }, { "epoch": 0.04, "learning_rate": 4.993592384090805e-05, "loss": 5.9879, "step": 780 }, { "epoch": 0.04, "learning_rate": 4.993363540665477e-05, "loss": 5.9555, "step": 790 }, { "epoch": 0.04, "learning_rate": 4.993134697240148e-05, "loss": 5.8468, "step": 800 }, { "epoch": 0.04, "learning_rate": 4.99290585381482e-05, "loss": 5.8909, "step": 810 }, { "epoch": 0.04, "learning_rate": 4.9926770103894916e-05, "loss": 5.9029, "step": 820 }, { "epoch": 0.04, "learning_rate": 4.992448166964163e-05, "loss": 5.8483, "step": 830 }, { "epoch": 0.04, "learning_rate": 4.992219323538835e-05, "loss": 5.8909, "step": 840 }, { "epoch": 0.04, "learning_rate": 4.9919904801135065e-05, "loss": 5.9212, "step": 850 }, { "epoch": 0.04, "learning_rate": 4.991761636688178e-05, "loss": 5.9122, "step": 860 }, { "epoch": 0.04, "learning_rate": 4.99153279326285e-05, "loss": 5.883, "step": 870 }, { "epoch": 0.04, "learning_rate": 4.9913039498375214e-05, "loss": 5.94, "step": 880 }, { "epoch": 0.04, "learning_rate": 4.991075106412193e-05, "loss": 5.8643, "step": 890 }, { "epoch": 0.04, "learning_rate": 4.990846262986865e-05, "loss": 5.7655, "step": 900 }, { "epoch": 0.04, "learning_rate": 4.990617419561536e-05, "loss": 5.7773, "step": 910 }, { "epoch": 0.04, "learning_rate": 4.990388576136208e-05, "loss": 5.8555, "step": 920 }, { "epoch": 0.04, "learning_rate": 4.99015973271088e-05, "loss": 5.7987, "step": 930 }, { "epoch": 0.04, "learning_rate": 4.989930889285551e-05, "loss": 5.8616, "step": 940 }, { "epoch": 0.04, "learning_rate": 4.9897020458602226e-05, "loss": 5.8388, "step": 950 }, { "epoch": 0.04, "learning_rate": 4.989473202434895e-05, "loss": 5.658, "step": 960 }, { "epoch": 0.04, "learning_rate": 4.989244359009566e-05, "loss": 5.8243, "step": 970 }, { "epoch": 0.04, "learning_rate": 4.9890155155842376e-05, "loss": 5.8229, "step": 980 }, { "epoch": 0.05, "learning_rate": 4.9887866721589097e-05, "loss": 5.727, "step": 990 }, { "epoch": 0.05, "learning_rate": 4.9885578287335804e-05, "loss": 5.7183, "step": 1000 }, { "epoch": 0.05, "learning_rate": 4.988328985308252e-05, "loss": 5.764, "step": 1010 }, { "epoch": 0.05, "learning_rate": 4.988100141882924e-05, "loss": 5.679, "step": 1020 }, { "epoch": 0.05, "learning_rate": 4.987871298457595e-05, "loss": 5.7651, "step": 1030 }, { "epoch": 0.05, "learning_rate": 4.987642455032267e-05, "loss": 5.6807, "step": 1040 }, { "epoch": 0.05, "learning_rate": 4.987413611606939e-05, "loss": 5.5571, "step": 1050 }, { "epoch": 0.05, "learning_rate": 4.98718476818161e-05, "loss": 5.5794, "step": 1060 }, { "epoch": 0.05, "learning_rate": 4.9869559247562816e-05, "loss": 5.7086, "step": 1070 }, { "epoch": 0.05, "learning_rate": 4.986727081330954e-05, "loss": 5.5571, "step": 1080 }, { "epoch": 0.05, "learning_rate": 4.986498237905625e-05, "loss": 5.5325, "step": 1090 }, { "epoch": 0.05, "learning_rate": 4.9862693944802966e-05, "loss": 5.5889, "step": 1100 }, { "epoch": 0.05, "learning_rate": 4.9860405510549687e-05, "loss": 5.4592, "step": 1110 }, { "epoch": 0.05, "learning_rate": 4.98581170762964e-05, "loss": 5.6764, "step": 1120 }, { "epoch": 0.05, "learning_rate": 4.9855828642043115e-05, "loss": 5.5525, "step": 1130 }, { "epoch": 0.05, "learning_rate": 4.9853540207789836e-05, "loss": 5.522, "step": 1140 }, { "epoch": 0.05, "learning_rate": 4.985125177353655e-05, "loss": 5.4496, "step": 1150 }, { "epoch": 0.05, "learning_rate": 4.9848963339283264e-05, "loss": 5.5078, "step": 1160 }, { "epoch": 0.05, "learning_rate": 4.9846674905029985e-05, "loss": 5.4549, "step": 1170 }, { "epoch": 0.05, "learning_rate": 4.98443864707767e-05, "loss": 5.4451, "step": 1180 }, { "epoch": 0.05, "learning_rate": 4.984209803652341e-05, "loss": 5.3537, "step": 1190 }, { "epoch": 0.05, "learning_rate": 4.983980960227013e-05, "loss": 5.4138, "step": 1200 }, { "epoch": 0.06, "learning_rate": 4.983752116801684e-05, "loss": 5.4271, "step": 1210 }, { "epoch": 0.06, "learning_rate": 4.983523273376356e-05, "loss": 5.4297, "step": 1220 }, { "epoch": 0.06, "learning_rate": 4.9832944299510276e-05, "loss": 5.3199, "step": 1230 }, { "epoch": 0.06, "learning_rate": 4.983065586525699e-05, "loss": 5.3859, "step": 1240 }, { "epoch": 0.06, "learning_rate": 4.982836743100371e-05, "loss": 5.4898, "step": 1250 }, { "epoch": 0.06, "learning_rate": 4.9826078996750426e-05, "loss": 5.1768, "step": 1260 }, { "epoch": 0.06, "learning_rate": 4.982379056249714e-05, "loss": 5.3359, "step": 1270 }, { "epoch": 0.06, "learning_rate": 4.982150212824386e-05, "loss": 5.3701, "step": 1280 }, { "epoch": 0.06, "learning_rate": 4.9819213693990575e-05, "loss": 5.2188, "step": 1290 }, { "epoch": 0.06, "learning_rate": 4.981692525973729e-05, "loss": 5.2829, "step": 1300 }, { "epoch": 0.06, "learning_rate": 4.981463682548401e-05, "loss": 5.2108, "step": 1310 }, { "epoch": 0.06, "learning_rate": 4.9812348391230724e-05, "loss": 5.2823, "step": 1320 }, { "epoch": 0.06, "learning_rate": 4.981005995697744e-05, "loss": 5.2421, "step": 1330 }, { "epoch": 0.06, "learning_rate": 4.980777152272416e-05, "loss": 5.2308, "step": 1340 }, { "epoch": 0.06, "learning_rate": 4.980548308847087e-05, "loss": 5.4056, "step": 1350 }, { "epoch": 0.06, "learning_rate": 4.980319465421759e-05, "loss": 5.049, "step": 1360 }, { "epoch": 0.06, "learning_rate": 4.980090621996431e-05, "loss": 5.0622, "step": 1370 }, { "epoch": 0.06, "learning_rate": 4.979861778571102e-05, "loss": 4.9921, "step": 1380 }, { "epoch": 0.06, "learning_rate": 4.979632935145773e-05, "loss": 5.1221, "step": 1390 }, { "epoch": 0.06, "learning_rate": 4.979404091720445e-05, "loss": 4.8782, "step": 1400 }, { "epoch": 0.06, "learning_rate": 4.9791752482951165e-05, "loss": 5.148, "step": 1410 }, { "epoch": 0.06, "learning_rate": 4.978946404869788e-05, "loss": 5.0633, "step": 1420 }, { "epoch": 0.07, "learning_rate": 4.97871756144446e-05, "loss": 5.0251, "step": 1430 }, { "epoch": 0.07, "learning_rate": 4.9784887180191314e-05, "loss": 4.9976, "step": 1440 }, { "epoch": 0.07, "learning_rate": 4.978259874593803e-05, "loss": 4.9418, "step": 1450 }, { "epoch": 0.07, "learning_rate": 4.978031031168475e-05, "loss": 4.9549, "step": 1460 }, { "epoch": 0.07, "learning_rate": 4.977802187743146e-05, "loss": 4.9429, "step": 1470 }, { "epoch": 0.07, "learning_rate": 4.977573344317818e-05, "loss": 4.8295, "step": 1480 }, { "epoch": 0.07, "learning_rate": 4.97734450089249e-05, "loss": 5.0149, "step": 1490 }, { "epoch": 0.07, "learning_rate": 4.977115657467161e-05, "loss": 4.8961, "step": 1500 }, { "epoch": 0.07, "learning_rate": 4.9768868140418326e-05, "loss": 4.9209, "step": 1510 }, { "epoch": 0.07, "learning_rate": 4.976657970616505e-05, "loss": 4.9072, "step": 1520 }, { "epoch": 0.07, "learning_rate": 4.976429127191176e-05, "loss": 4.7414, "step": 1530 }, { "epoch": 0.07, "learning_rate": 4.9762002837658476e-05, "loss": 4.8278, "step": 1540 }, { "epoch": 0.07, "learning_rate": 4.9759714403405196e-05, "loss": 4.6391, "step": 1550 }, { "epoch": 0.07, "learning_rate": 4.975742596915191e-05, "loss": 4.7759, "step": 1560 }, { "epoch": 0.07, "learning_rate": 4.9755137534898625e-05, "loss": 4.8571, "step": 1570 }, { "epoch": 0.07, "learning_rate": 4.9752849100645346e-05, "loss": 4.8243, "step": 1580 }, { "epoch": 0.07, "learning_rate": 4.975056066639205e-05, "loss": 4.8325, "step": 1590 }, { "epoch": 0.07, "learning_rate": 4.9748272232138774e-05, "loss": 4.727, "step": 1600 }, { "epoch": 0.07, "learning_rate": 4.974598379788549e-05, "loss": 4.6942, "step": 1610 }, { "epoch": 0.07, "learning_rate": 4.97436953636322e-05, "loss": 4.6422, "step": 1620 }, { "epoch": 0.07, "learning_rate": 4.974140692937892e-05, "loss": 4.608, "step": 1630 }, { "epoch": 0.07, "learning_rate": 4.973911849512564e-05, "loss": 4.6126, "step": 1640 }, { "epoch": 0.08, "learning_rate": 4.973683006087235e-05, "loss": 4.6781, "step": 1650 }, { "epoch": 0.08, "learning_rate": 4.973454162661907e-05, "loss": 4.507, "step": 1660 }, { "epoch": 0.08, "learning_rate": 4.9732253192365786e-05, "loss": 4.7219, "step": 1670 }, { "epoch": 0.08, "learning_rate": 4.97299647581125e-05, "loss": 4.4521, "step": 1680 }, { "epoch": 0.08, "learning_rate": 4.9727676323859215e-05, "loss": 4.4993, "step": 1690 }, { "epoch": 0.08, "learning_rate": 4.9725387889605936e-05, "loss": 4.4399, "step": 1700 }, { "epoch": 0.08, "learning_rate": 4.972309945535265e-05, "loss": 4.436, "step": 1710 }, { "epoch": 0.08, "learning_rate": 4.9720811021099364e-05, "loss": 4.5127, "step": 1720 }, { "epoch": 0.08, "learning_rate": 4.9718522586846085e-05, "loss": 4.6519, "step": 1730 }, { "epoch": 0.08, "learning_rate": 4.97162341525928e-05, "loss": 4.4497, "step": 1740 }, { "epoch": 0.08, "learning_rate": 4.971394571833951e-05, "loss": 4.5627, "step": 1750 }, { "epoch": 0.08, "learning_rate": 4.9711657284086234e-05, "loss": 4.4867, "step": 1760 }, { "epoch": 0.08, "learning_rate": 4.970936884983295e-05, "loss": 4.3635, "step": 1770 }, { "epoch": 0.08, "learning_rate": 4.970708041557966e-05, "loss": 4.4096, "step": 1780 }, { "epoch": 0.08, "learning_rate": 4.9704791981326376e-05, "loss": 4.3766, "step": 1790 }, { "epoch": 0.08, "learning_rate": 4.970250354707309e-05, "loss": 4.4124, "step": 1800 }, { "epoch": 0.08, "learning_rate": 4.970021511281981e-05, "loss": 4.2501, "step": 1810 }, { "epoch": 0.08, "learning_rate": 4.9697926678566526e-05, "loss": 4.6005, "step": 1820 }, { "epoch": 0.08, "learning_rate": 4.969563824431324e-05, "loss": 4.2927, "step": 1830 }, { "epoch": 0.08, "learning_rate": 4.969334981005996e-05, "loss": 4.2544, "step": 1840 }, { "epoch": 0.08, "learning_rate": 4.9691061375806675e-05, "loss": 4.3561, "step": 1850 }, { "epoch": 0.08, "learning_rate": 4.968877294155339e-05, "loss": 4.2696, "step": 1860 }, { "epoch": 0.09, "learning_rate": 4.968648450730011e-05, "loss": 4.3995, "step": 1870 }, { "epoch": 0.09, "learning_rate": 4.9684196073046824e-05, "loss": 4.1225, "step": 1880 }, { "epoch": 0.09, "learning_rate": 4.968190763879354e-05, "loss": 4.2096, "step": 1890 }, { "epoch": 0.09, "learning_rate": 4.967961920454026e-05, "loss": 4.2434, "step": 1900 }, { "epoch": 0.09, "learning_rate": 4.967733077028697e-05, "loss": 4.1363, "step": 1910 }, { "epoch": 0.09, "learning_rate": 4.967504233603369e-05, "loss": 4.2996, "step": 1920 }, { "epoch": 0.09, "learning_rate": 4.967275390178041e-05, "loss": 4.1065, "step": 1930 }, { "epoch": 0.09, "learning_rate": 4.967046546752712e-05, "loss": 4.1084, "step": 1940 }, { "epoch": 0.09, "learning_rate": 4.9668177033273836e-05, "loss": 4.0974, "step": 1950 }, { "epoch": 0.09, "learning_rate": 4.966588859902056e-05, "loss": 4.3585, "step": 1960 }, { "epoch": 0.09, "learning_rate": 4.966360016476727e-05, "loss": 4.3232, "step": 1970 }, { "epoch": 0.09, "learning_rate": 4.9661311730513986e-05, "loss": 4.1274, "step": 1980 }, { "epoch": 0.09, "learning_rate": 4.96590232962607e-05, "loss": 4.1957, "step": 1990 }, { "epoch": 0.09, "learning_rate": 4.9656734862007414e-05, "loss": 4.0372, "step": 2000 }, { "epoch": 0.09, "learning_rate": 4.965444642775413e-05, "loss": 4.096, "step": 2010 }, { "epoch": 0.09, "learning_rate": 4.965215799350085e-05, "loss": 4.0857, "step": 2020 }, { "epoch": 0.09, "learning_rate": 4.964986955924756e-05, "loss": 4.063, "step": 2030 }, { "epoch": 0.09, "learning_rate": 4.964758112499428e-05, "loss": 4.051, "step": 2040 }, { "epoch": 0.09, "learning_rate": 4.9645292690741e-05, "loss": 4.026, "step": 2050 }, { "epoch": 0.09, "learning_rate": 4.964300425648771e-05, "loss": 3.9816, "step": 2060 }, { "epoch": 0.09, "learning_rate": 4.9640715822234426e-05, "loss": 4.1225, "step": 2070 }, { "epoch": 0.09, "learning_rate": 4.963842738798115e-05, "loss": 3.7683, "step": 2080 }, { "epoch": 0.1, "learning_rate": 4.963613895372786e-05, "loss": 3.9106, "step": 2090 }, { "epoch": 0.1, "learning_rate": 4.9633850519474575e-05, "loss": 4.0768, "step": 2100 }, { "epoch": 0.1, "learning_rate": 4.9631562085221296e-05, "loss": 3.9188, "step": 2110 }, { "epoch": 0.1, "learning_rate": 4.962927365096801e-05, "loss": 3.9896, "step": 2120 }, { "epoch": 0.1, "learning_rate": 4.9626985216714725e-05, "loss": 3.9591, "step": 2130 }, { "epoch": 0.1, "learning_rate": 4.9624696782461446e-05, "loss": 4.0163, "step": 2140 }, { "epoch": 0.1, "learning_rate": 4.962240834820816e-05, "loss": 4.0043, "step": 2150 }, { "epoch": 0.1, "learning_rate": 4.9620119913954874e-05, "loss": 3.8344, "step": 2160 }, { "epoch": 0.1, "learning_rate": 4.9617831479701595e-05, "loss": 3.8689, "step": 2170 }, { "epoch": 0.1, "learning_rate": 4.96155430454483e-05, "loss": 3.7816, "step": 2180 }, { "epoch": 0.1, "learning_rate": 4.961325461119502e-05, "loss": 3.969, "step": 2190 }, { "epoch": 0.1, "learning_rate": 4.961096617694174e-05, "loss": 3.7791, "step": 2200 }, { "epoch": 0.1, "learning_rate": 4.960867774268845e-05, "loss": 3.9908, "step": 2210 }, { "epoch": 0.1, "learning_rate": 4.960638930843517e-05, "loss": 3.9122, "step": 2220 }, { "epoch": 0.1, "learning_rate": 4.9604100874181886e-05, "loss": 3.6702, "step": 2230 }, { "epoch": 0.1, "learning_rate": 4.96018124399286e-05, "loss": 3.6511, "step": 2240 }, { "epoch": 0.1, "learning_rate": 4.959952400567532e-05, "loss": 3.908, "step": 2250 }, { "epoch": 0.1, "learning_rate": 4.9597235571422035e-05, "loss": 3.6058, "step": 2260 }, { "epoch": 0.1, "learning_rate": 4.959494713716875e-05, "loss": 3.5925, "step": 2270 }, { "epoch": 0.1, "learning_rate": 4.959265870291547e-05, "loss": 3.9557, "step": 2280 }, { "epoch": 0.1, "learning_rate": 4.9590370268662185e-05, "loss": 3.7079, "step": 2290 }, { "epoch": 0.11, "learning_rate": 4.95880818344089e-05, "loss": 3.7477, "step": 2300 }, { "epoch": 0.11, "learning_rate": 4.958579340015562e-05, "loss": 3.7145, "step": 2310 }, { "epoch": 0.11, "learning_rate": 4.9583504965902334e-05, "loss": 3.7743, "step": 2320 }, { "epoch": 0.11, "learning_rate": 4.958121653164905e-05, "loss": 3.6775, "step": 2330 }, { "epoch": 0.11, "learning_rate": 4.957892809739577e-05, "loss": 3.6982, "step": 2340 }, { "epoch": 0.11, "learning_rate": 4.957663966314248e-05, "loss": 3.6445, "step": 2350 }, { "epoch": 0.11, "learning_rate": 4.95743512288892e-05, "loss": 3.566, "step": 2360 }, { "epoch": 0.11, "learning_rate": 4.957206279463592e-05, "loss": 3.8203, "step": 2370 }, { "epoch": 0.11, "learning_rate": 4.9569774360382625e-05, "loss": 3.4788, "step": 2380 }, { "epoch": 0.11, "learning_rate": 4.956748592612934e-05, "loss": 3.8914, "step": 2390 }, { "epoch": 0.11, "learning_rate": 4.956519749187606e-05, "loss": 3.7016, "step": 2400 }, { "epoch": 0.11, "learning_rate": 4.9562909057622775e-05, "loss": 3.7977, "step": 2410 }, { "epoch": 0.11, "learning_rate": 4.956062062336949e-05, "loss": 3.6013, "step": 2420 }, { "epoch": 0.11, "learning_rate": 4.955833218911621e-05, "loss": 3.777, "step": 2430 }, { "epoch": 0.11, "learning_rate": 4.9556043754862924e-05, "loss": 3.6037, "step": 2440 }, { "epoch": 0.11, "learning_rate": 4.955375532060964e-05, "loss": 3.4694, "step": 2450 }, { "epoch": 0.11, "learning_rate": 4.955146688635636e-05, "loss": 3.5076, "step": 2460 }, { "epoch": 0.11, "learning_rate": 4.954917845210307e-05, "loss": 3.4825, "step": 2470 }, { "epoch": 0.11, "learning_rate": 4.954689001784979e-05, "loss": 3.5251, "step": 2480 }, { "epoch": 0.11, "learning_rate": 4.954460158359651e-05, "loss": 3.5612, "step": 2490 }, { "epoch": 0.11, "learning_rate": 4.954231314934322e-05, "loss": 3.6243, "step": 2500 }, { "epoch": 0.11, "learning_rate": 4.9540024715089936e-05, "loss": 3.4945, "step": 2510 }, { "epoch": 0.12, "learning_rate": 4.953773628083666e-05, "loss": 3.4449, "step": 2520 }, { "epoch": 0.12, "learning_rate": 4.953544784658337e-05, "loss": 3.424, "step": 2530 }, { "epoch": 0.12, "learning_rate": 4.9533159412330085e-05, "loss": 3.52, "step": 2540 }, { "epoch": 0.12, "learning_rate": 4.9530870978076806e-05, "loss": 3.5746, "step": 2550 }, { "epoch": 0.12, "learning_rate": 4.952858254382352e-05, "loss": 3.5421, "step": 2560 }, { "epoch": 0.12, "learning_rate": 4.9526294109570235e-05, "loss": 3.5144, "step": 2570 }, { "epoch": 0.12, "learning_rate": 4.952400567531695e-05, "loss": 3.5101, "step": 2580 }, { "epoch": 0.12, "learning_rate": 4.952171724106366e-05, "loss": 3.6193, "step": 2590 }, { "epoch": 0.12, "learning_rate": 4.9519428806810384e-05, "loss": 3.6216, "step": 2600 }, { "epoch": 0.12, "learning_rate": 4.95171403725571e-05, "loss": 3.4222, "step": 2610 }, { "epoch": 0.12, "learning_rate": 4.951485193830381e-05, "loss": 3.5583, "step": 2620 }, { "epoch": 0.12, "learning_rate": 4.951256350405053e-05, "loss": 3.4595, "step": 2630 }, { "epoch": 0.12, "learning_rate": 4.951027506979725e-05, "loss": 3.395, "step": 2640 }, { "epoch": 0.12, "learning_rate": 4.950798663554396e-05, "loss": 3.7061, "step": 2650 }, { "epoch": 0.12, "learning_rate": 4.950569820129068e-05, "loss": 3.4013, "step": 2660 }, { "epoch": 0.12, "learning_rate": 4.9503409767037396e-05, "loss": 3.367, "step": 2670 }, { "epoch": 0.12, "learning_rate": 4.950112133278411e-05, "loss": 3.5332, "step": 2680 }, { "epoch": 0.12, "learning_rate": 4.949883289853083e-05, "loss": 3.3396, "step": 2690 }, { "epoch": 0.12, "learning_rate": 4.9496544464277545e-05, "loss": 3.3743, "step": 2700 }, { "epoch": 0.12, "learning_rate": 4.949425603002426e-05, "loss": 3.4273, "step": 2710 }, { "epoch": 0.12, "learning_rate": 4.949196759577098e-05, "loss": 3.4509, "step": 2720 }, { "epoch": 0.12, "learning_rate": 4.9489679161517695e-05, "loss": 3.422, "step": 2730 }, { "epoch": 0.13, "learning_rate": 4.948739072726441e-05, "loss": 3.4445, "step": 2740 }, { "epoch": 0.13, "learning_rate": 4.948510229301113e-05, "loss": 3.5503, "step": 2750 }, { "epoch": 0.13, "learning_rate": 4.9482813858757844e-05, "loss": 3.3686, "step": 2760 }, { "epoch": 0.13, "learning_rate": 4.948052542450456e-05, "loss": 3.4081, "step": 2770 }, { "epoch": 0.13, "learning_rate": 4.947823699025127e-05, "loss": 3.2079, "step": 2780 }, { "epoch": 0.13, "learning_rate": 4.9475948555997986e-05, "loss": 3.3439, "step": 2790 }, { "epoch": 0.13, "learning_rate": 4.94736601217447e-05, "loss": 3.4725, "step": 2800 }, { "epoch": 0.13, "learning_rate": 4.947137168749142e-05, "loss": 3.278, "step": 2810 }, { "epoch": 0.13, "learning_rate": 4.9469083253238135e-05, "loss": 3.2594, "step": 2820 }, { "epoch": 0.13, "learning_rate": 4.946679481898485e-05, "loss": 3.2451, "step": 2830 }, { "epoch": 0.13, "learning_rate": 4.946450638473157e-05, "loss": 3.2331, "step": 2840 }, { "epoch": 0.13, "learning_rate": 4.9462217950478285e-05, "loss": 3.2726, "step": 2850 }, { "epoch": 0.13, "learning_rate": 4.9459929516225e-05, "loss": 3.2494, "step": 2860 }, { "epoch": 0.13, "learning_rate": 4.945764108197172e-05, "loss": 3.2049, "step": 2870 }, { "epoch": 0.13, "learning_rate": 4.9455352647718434e-05, "loss": 3.3036, "step": 2880 }, { "epoch": 0.13, "learning_rate": 4.945306421346515e-05, "loss": 3.3451, "step": 2890 }, { "epoch": 0.13, "learning_rate": 4.945077577921187e-05, "loss": 3.1735, "step": 2900 }, { "epoch": 0.13, "learning_rate": 4.944848734495858e-05, "loss": 3.3592, "step": 2910 }, { "epoch": 0.13, "learning_rate": 4.94461989107053e-05, "loss": 3.3001, "step": 2920 }, { "epoch": 0.13, "learning_rate": 4.944391047645202e-05, "loss": 3.3265, "step": 2930 }, { "epoch": 0.13, "learning_rate": 4.944162204219873e-05, "loss": 3.1976, "step": 2940 }, { "epoch": 0.13, "learning_rate": 4.9439333607945446e-05, "loss": 3.0769, "step": 2950 }, { "epoch": 0.14, "learning_rate": 4.943704517369217e-05, "loss": 3.2989, "step": 2960 }, { "epoch": 0.14, "learning_rate": 4.9434756739438874e-05, "loss": 3.2741, "step": 2970 }, { "epoch": 0.14, "learning_rate": 4.943246830518559e-05, "loss": 2.975, "step": 2980 }, { "epoch": 0.14, "learning_rate": 4.943017987093231e-05, "loss": 3.2092, "step": 2990 }, { "epoch": 0.14, "learning_rate": 4.9427891436679024e-05, "loss": 3.1664, "step": 3000 }, { "epoch": 0.14, "learning_rate": 4.942560300242574e-05, "loss": 3.1944, "step": 3010 }, { "epoch": 0.14, "learning_rate": 4.942331456817246e-05, "loss": 3.2398, "step": 3020 }, { "epoch": 0.14, "learning_rate": 4.942102613391917e-05, "loss": 3.3573, "step": 3030 }, { "epoch": 0.14, "learning_rate": 4.941873769966589e-05, "loss": 3.1986, "step": 3040 }, { "epoch": 0.14, "learning_rate": 4.941644926541261e-05, "loss": 3.2923, "step": 3050 }, { "epoch": 0.14, "learning_rate": 4.941416083115932e-05, "loss": 3.3199, "step": 3060 }, { "epoch": 0.14, "learning_rate": 4.9411872396906036e-05, "loss": 3.1774, "step": 3070 }, { "epoch": 0.14, "learning_rate": 4.940958396265276e-05, "loss": 3.356, "step": 3080 }, { "epoch": 0.14, "learning_rate": 4.940729552839947e-05, "loss": 3.2614, "step": 3090 }, { "epoch": 0.14, "learning_rate": 4.9405007094146185e-05, "loss": 3.335, "step": 3100 }, { "epoch": 0.14, "learning_rate": 4.9402718659892906e-05, "loss": 3.2341, "step": 3110 }, { "epoch": 0.14, "learning_rate": 4.940043022563962e-05, "loss": 3.0729, "step": 3120 }, { "epoch": 0.14, "learning_rate": 4.9398141791386335e-05, "loss": 3.1343, "step": 3130 }, { "epoch": 0.14, "learning_rate": 4.9395853357133055e-05, "loss": 3.4638, "step": 3140 }, { "epoch": 0.14, "learning_rate": 4.939356492287977e-05, "loss": 2.7906, "step": 3150 }, { "epoch": 0.14, "learning_rate": 4.9391276488626484e-05, "loss": 3.3873, "step": 3160 }, { "epoch": 0.14, "learning_rate": 4.93889880543732e-05, "loss": 3.0836, "step": 3170 }, { "epoch": 0.15, "learning_rate": 4.938669962011991e-05, "loss": 3.0945, "step": 3180 }, { "epoch": 0.15, "learning_rate": 4.938441118586663e-05, "loss": 3.2331, "step": 3190 }, { "epoch": 0.15, "learning_rate": 4.938212275161335e-05, "loss": 3.1057, "step": 3200 }, { "epoch": 0.15, "learning_rate": 4.937983431736006e-05, "loss": 3.1827, "step": 3210 }, { "epoch": 0.15, "learning_rate": 4.937754588310678e-05, "loss": 3.0959, "step": 3220 }, { "epoch": 0.15, "learning_rate": 4.9375257448853496e-05, "loss": 3.1203, "step": 3230 }, { "epoch": 0.15, "learning_rate": 4.937296901460021e-05, "loss": 3.1749, "step": 3240 }, { "epoch": 0.15, "learning_rate": 4.937068058034693e-05, "loss": 3.0787, "step": 3250 }, { "epoch": 0.15, "learning_rate": 4.9368392146093645e-05, "loss": 2.9263, "step": 3260 }, { "epoch": 0.15, "learning_rate": 4.936610371184036e-05, "loss": 3.0948, "step": 3270 }, { "epoch": 0.15, "learning_rate": 4.936381527758708e-05, "loss": 3.083, "step": 3280 }, { "epoch": 0.15, "learning_rate": 4.9361526843333795e-05, "loss": 3.1982, "step": 3290 }, { "epoch": 0.15, "learning_rate": 4.935923840908051e-05, "loss": 3.017, "step": 3300 }, { "epoch": 0.15, "learning_rate": 4.935694997482723e-05, "loss": 3.2065, "step": 3310 }, { "epoch": 0.15, "learning_rate": 4.9354661540573944e-05, "loss": 3.0802, "step": 3320 }, { "epoch": 0.15, "learning_rate": 4.935237310632066e-05, "loss": 3.0796, "step": 3330 }, { "epoch": 0.15, "learning_rate": 4.935008467206738e-05, "loss": 3.1716, "step": 3340 }, { "epoch": 0.15, "learning_rate": 4.934779623781409e-05, "loss": 3.0455, "step": 3350 }, { "epoch": 0.15, "learning_rate": 4.934550780356081e-05, "loss": 3.0642, "step": 3360 }, { "epoch": 0.15, "learning_rate": 4.934321936930752e-05, "loss": 3.0628, "step": 3370 }, { "epoch": 0.15, "learning_rate": 4.9340930935054235e-05, "loss": 2.9962, "step": 3380 }, { "epoch": 0.15, "learning_rate": 4.933864250080095e-05, "loss": 3.0136, "step": 3390 }, { "epoch": 0.16, "learning_rate": 4.933635406654767e-05, "loss": 3.2298, "step": 3400 }, { "epoch": 0.16, "learning_rate": 4.9334065632294384e-05, "loss": 3.1001, "step": 3410 }, { "epoch": 0.16, "learning_rate": 4.93317771980411e-05, "loss": 2.7845, "step": 3420 }, { "epoch": 0.16, "learning_rate": 4.932948876378782e-05, "loss": 3.0231, "step": 3430 }, { "epoch": 0.16, "learning_rate": 4.9327200329534534e-05, "loss": 2.9925, "step": 3440 }, { "epoch": 0.16, "learning_rate": 4.932491189528125e-05, "loss": 3.0164, "step": 3450 }, { "epoch": 0.16, "learning_rate": 4.932262346102797e-05, "loss": 3.0676, "step": 3460 }, { "epoch": 0.16, "learning_rate": 4.932033502677468e-05, "loss": 3.0277, "step": 3470 }, { "epoch": 0.16, "learning_rate": 4.93180465925214e-05, "loss": 3.2316, "step": 3480 }, { "epoch": 0.16, "learning_rate": 4.931575815826812e-05, "loss": 3.1856, "step": 3490 }, { "epoch": 0.16, "learning_rate": 4.931346972401483e-05, "loss": 2.8829, "step": 3500 }, { "epoch": 0.16, "learning_rate": 4.9311181289761546e-05, "loss": 2.9702, "step": 3510 }, { "epoch": 0.16, "learning_rate": 4.930889285550827e-05, "loss": 2.9771, "step": 3520 }, { "epoch": 0.16, "learning_rate": 4.930660442125498e-05, "loss": 3.1545, "step": 3530 }, { "epoch": 0.16, "learning_rate": 4.9304315987001695e-05, "loss": 3.2394, "step": 3540 }, { "epoch": 0.16, "learning_rate": 4.9302027552748416e-05, "loss": 3.0678, "step": 3550 }, { "epoch": 0.16, "learning_rate": 4.929973911849513e-05, "loss": 2.8968, "step": 3560 }, { "epoch": 0.16, "learning_rate": 4.9297450684241844e-05, "loss": 3.0891, "step": 3570 }, { "epoch": 0.16, "learning_rate": 4.929516224998856e-05, "loss": 3.2286, "step": 3580 }, { "epoch": 0.16, "learning_rate": 4.929287381573527e-05, "loss": 2.9442, "step": 3590 }, { "epoch": 0.16, "learning_rate": 4.9290585381481994e-05, "loss": 3.0781, "step": 3600 }, { "epoch": 0.16, "learning_rate": 4.928829694722871e-05, "loss": 2.9756, "step": 3610 }, { "epoch": 0.17, "learning_rate": 4.928600851297542e-05, "loss": 2.8923, "step": 3620 }, { "epoch": 0.17, "learning_rate": 4.928372007872214e-05, "loss": 3.1628, "step": 3630 }, { "epoch": 0.17, "learning_rate": 4.928143164446886e-05, "loss": 2.8878, "step": 3640 }, { "epoch": 0.17, "learning_rate": 4.927914321021557e-05, "loss": 3.0311, "step": 3650 }, { "epoch": 0.17, "learning_rate": 4.927685477596229e-05, "loss": 3.0148, "step": 3660 }, { "epoch": 0.17, "learning_rate": 4.9274566341709006e-05, "loss": 2.9176, "step": 3670 }, { "epoch": 0.17, "learning_rate": 4.927227790745572e-05, "loss": 2.8912, "step": 3680 }, { "epoch": 0.17, "learning_rate": 4.926998947320244e-05, "loss": 2.7215, "step": 3690 }, { "epoch": 0.17, "learning_rate": 4.9267701038949155e-05, "loss": 2.9225, "step": 3700 }, { "epoch": 0.17, "learning_rate": 4.926541260469587e-05, "loss": 3.1808, "step": 3710 }, { "epoch": 0.17, "learning_rate": 4.926312417044259e-05, "loss": 3.1542, "step": 3720 }, { "epoch": 0.17, "learning_rate": 4.9260835736189305e-05, "loss": 3.0091, "step": 3730 }, { "epoch": 0.17, "learning_rate": 4.925854730193602e-05, "loss": 3.1964, "step": 3740 }, { "epoch": 0.17, "learning_rate": 4.925625886768274e-05, "loss": 3.0998, "step": 3750 }, { "epoch": 0.17, "learning_rate": 4.925397043342945e-05, "loss": 2.7958, "step": 3760 }, { "epoch": 0.17, "learning_rate": 4.925168199917616e-05, "loss": 3.0299, "step": 3770 }, { "epoch": 0.17, "learning_rate": 4.924939356492288e-05, "loss": 2.832, "step": 3780 }, { "epoch": 0.17, "learning_rate": 4.9247105130669596e-05, "loss": 2.8723, "step": 3790 }, { "epoch": 0.17, "learning_rate": 4.924481669641631e-05, "loss": 2.8315, "step": 3800 }, { "epoch": 0.17, "learning_rate": 4.924252826216303e-05, "loss": 2.9206, "step": 3810 }, { "epoch": 0.17, "learning_rate": 4.9240239827909745e-05, "loss": 2.9637, "step": 3820 }, { "epoch": 0.17, "learning_rate": 4.923795139365646e-05, "loss": 3.0163, "step": 3830 }, { "epoch": 0.18, "learning_rate": 4.923566295940318e-05, "loss": 2.9165, "step": 3840 }, { "epoch": 0.18, "learning_rate": 4.9233374525149894e-05, "loss": 2.9646, "step": 3850 }, { "epoch": 0.18, "learning_rate": 4.923108609089661e-05, "loss": 2.8545, "step": 3860 }, { "epoch": 0.18, "learning_rate": 4.922879765664333e-05, "loss": 2.9464, "step": 3870 }, { "epoch": 0.18, "learning_rate": 4.9226509222390044e-05, "loss": 2.9661, "step": 3880 }, { "epoch": 0.18, "learning_rate": 4.922422078813676e-05, "loss": 2.7965, "step": 3890 }, { "epoch": 0.18, "learning_rate": 4.922193235388348e-05, "loss": 2.8137, "step": 3900 }, { "epoch": 0.18, "learning_rate": 4.921964391963019e-05, "loss": 2.8386, "step": 3910 }, { "epoch": 0.18, "learning_rate": 4.921735548537691e-05, "loss": 2.9837, "step": 3920 }, { "epoch": 0.18, "learning_rate": 4.921506705112363e-05, "loss": 2.9696, "step": 3930 }, { "epoch": 0.18, "learning_rate": 4.921277861687034e-05, "loss": 3.0475, "step": 3940 }, { "epoch": 0.18, "learning_rate": 4.9210490182617056e-05, "loss": 2.8714, "step": 3950 }, { "epoch": 0.18, "learning_rate": 4.920820174836377e-05, "loss": 2.9051, "step": 3960 }, { "epoch": 0.18, "learning_rate": 4.9205913314110484e-05, "loss": 2.7199, "step": 3970 }, { "epoch": 0.18, "learning_rate": 4.9203624879857205e-05, "loss": 2.8365, "step": 3980 }, { "epoch": 0.18, "learning_rate": 4.920133644560392e-05, "loss": 2.8849, "step": 3990 }, { "epoch": 0.18, "learning_rate": 4.9199048011350634e-05, "loss": 2.7023, "step": 4000 }, { "epoch": 0.18, "learning_rate": 4.919675957709735e-05, "loss": 2.8265, "step": 4010 }, { "epoch": 0.18, "learning_rate": 4.919447114284407e-05, "loss": 2.9894, "step": 4020 }, { "epoch": 0.18, "learning_rate": 4.919218270859078e-05, "loss": 2.9934, "step": 4030 }, { "epoch": 0.18, "learning_rate": 4.91898942743375e-05, "loss": 3.0031, "step": 4040 }, { "epoch": 0.18, "learning_rate": 4.918760584008422e-05, "loss": 2.9297, "step": 4050 }, { "epoch": 0.19, "learning_rate": 4.918531740583093e-05, "loss": 3.0047, "step": 4060 }, { "epoch": 0.19, "learning_rate": 4.9183028971577646e-05, "loss": 2.7442, "step": 4070 }, { "epoch": 0.19, "learning_rate": 4.918074053732437e-05, "loss": 2.9239, "step": 4080 }, { "epoch": 0.19, "learning_rate": 4.917845210307108e-05, "loss": 2.9997, "step": 4090 }, { "epoch": 0.19, "learning_rate": 4.9176163668817795e-05, "loss": 2.852, "step": 4100 }, { "epoch": 0.19, "learning_rate": 4.9173875234564516e-05, "loss": 2.9513, "step": 4110 }, { "epoch": 0.19, "learning_rate": 4.917158680031123e-05, "loss": 2.8418, "step": 4120 }, { "epoch": 0.19, "learning_rate": 4.9169298366057944e-05, "loss": 2.8771, "step": 4130 }, { "epoch": 0.19, "learning_rate": 4.9167009931804665e-05, "loss": 2.8899, "step": 4140 }, { "epoch": 0.19, "learning_rate": 4.916472149755138e-05, "loss": 2.9079, "step": 4150 }, { "epoch": 0.19, "learning_rate": 4.9162433063298094e-05, "loss": 2.7673, "step": 4160 }, { "epoch": 0.19, "learning_rate": 4.916014462904481e-05, "loss": 2.8205, "step": 4170 }, { "epoch": 0.19, "learning_rate": 4.915785619479152e-05, "loss": 2.9812, "step": 4180 }, { "epoch": 0.19, "learning_rate": 4.915556776053824e-05, "loss": 2.8188, "step": 4190 }, { "epoch": 0.19, "learning_rate": 4.915327932628496e-05, "loss": 2.75, "step": 4200 }, { "epoch": 0.19, "learning_rate": 4.915099089203167e-05, "loss": 3.0329, "step": 4210 }, { "epoch": 0.19, "learning_rate": 4.914870245777839e-05, "loss": 2.7095, "step": 4220 }, { "epoch": 0.19, "learning_rate": 4.9146414023525106e-05, "loss": 3.0441, "step": 4230 }, { "epoch": 0.19, "learning_rate": 4.914412558927182e-05, "loss": 2.968, "step": 4240 }, { "epoch": 0.19, "learning_rate": 4.914183715501854e-05, "loss": 2.7646, "step": 4250 }, { "epoch": 0.19, "learning_rate": 4.9139548720765255e-05, "loss": 2.8685, "step": 4260 }, { "epoch": 0.19, "learning_rate": 4.913726028651197e-05, "loss": 2.9205, "step": 4270 }, { "epoch": 0.2, "learning_rate": 4.913497185225869e-05, "loss": 2.8074, "step": 4280 }, { "epoch": 0.2, "learning_rate": 4.9132683418005404e-05, "loss": 2.8695, "step": 4290 }, { "epoch": 0.2, "learning_rate": 4.913039498375212e-05, "loss": 2.7838, "step": 4300 }, { "epoch": 0.2, "learning_rate": 4.912810654949884e-05, "loss": 2.8035, "step": 4310 }, { "epoch": 0.2, "learning_rate": 4.9125818115245554e-05, "loss": 2.9326, "step": 4320 }, { "epoch": 0.2, "learning_rate": 4.912352968099227e-05, "loss": 2.949, "step": 4330 }, { "epoch": 0.2, "learning_rate": 4.912124124673899e-05, "loss": 2.7554, "step": 4340 }, { "epoch": 0.2, "learning_rate": 4.91189528124857e-05, "loss": 2.7366, "step": 4350 }, { "epoch": 0.2, "learning_rate": 4.911666437823241e-05, "loss": 2.9128, "step": 4360 }, { "epoch": 0.2, "learning_rate": 4.911437594397913e-05, "loss": 2.9875, "step": 4370 }, { "epoch": 0.2, "learning_rate": 4.9112087509725845e-05, "loss": 2.9383, "step": 4380 }, { "epoch": 0.2, "learning_rate": 4.910979907547256e-05, "loss": 2.8565, "step": 4390 }, { "epoch": 0.2, "learning_rate": 4.910751064121928e-05, "loss": 2.7329, "step": 4400 }, { "epoch": 0.2, "learning_rate": 4.9105222206965994e-05, "loss": 2.8936, "step": 4410 }, { "epoch": 0.2, "learning_rate": 4.910293377271271e-05, "loss": 2.8167, "step": 4420 }, { "epoch": 0.2, "learning_rate": 4.910064533845943e-05, "loss": 2.8071, "step": 4430 }, { "epoch": 0.2, "learning_rate": 4.9098356904206144e-05, "loss": 2.6855, "step": 4440 }, { "epoch": 0.2, "learning_rate": 4.909606846995286e-05, "loss": 2.8504, "step": 4450 }, { "epoch": 0.2, "learning_rate": 4.909378003569958e-05, "loss": 2.9936, "step": 4460 }, { "epoch": 0.2, "learning_rate": 4.909149160144629e-05, "loss": 2.8114, "step": 4470 }, { "epoch": 0.2, "learning_rate": 4.908920316719301e-05, "loss": 2.8422, "step": 4480 }, { "epoch": 0.21, "learning_rate": 4.908691473293973e-05, "loss": 2.9536, "step": 4490 }, { "epoch": 0.21, "learning_rate": 4.908462629868644e-05, "loss": 2.936, "step": 4500 }, { "epoch": 0.21, "learning_rate": 4.9082337864433156e-05, "loss": 2.8765, "step": 4510 }, { "epoch": 0.21, "learning_rate": 4.908004943017988e-05, "loss": 2.8246, "step": 4520 }, { "epoch": 0.21, "learning_rate": 4.907776099592659e-05, "loss": 2.8646, "step": 4530 }, { "epoch": 0.21, "learning_rate": 4.9075472561673305e-05, "loss": 2.6812, "step": 4540 }, { "epoch": 0.21, "learning_rate": 4.907318412742002e-05, "loss": 2.8393, "step": 4550 }, { "epoch": 0.21, "learning_rate": 4.9070895693166733e-05, "loss": 2.9138, "step": 4560 }, { "epoch": 0.21, "learning_rate": 4.9068607258913454e-05, "loss": 2.5701, "step": 4570 }, { "epoch": 0.21, "learning_rate": 4.906631882466017e-05, "loss": 2.7563, "step": 4580 }, { "epoch": 0.21, "learning_rate": 4.906403039040688e-05, "loss": 2.9409, "step": 4590 }, { "epoch": 0.21, "learning_rate": 4.9061741956153604e-05, "loss": 3.0352, "step": 4600 }, { "epoch": 0.21, "learning_rate": 4.905945352190032e-05, "loss": 2.6059, "step": 4610 }, { "epoch": 0.21, "learning_rate": 4.905716508764703e-05, "loss": 2.7397, "step": 4620 }, { "epoch": 0.21, "learning_rate": 4.905487665339375e-05, "loss": 2.8225, "step": 4630 }, { "epoch": 0.21, "learning_rate": 4.905258821914047e-05, "loss": 2.803, "step": 4640 }, { "epoch": 0.21, "learning_rate": 4.905029978488718e-05, "loss": 2.6324, "step": 4650 }, { "epoch": 0.21, "learning_rate": 4.90480113506339e-05, "loss": 3.0109, "step": 4660 }, { "epoch": 0.21, "learning_rate": 4.9045722916380616e-05, "loss": 2.8453, "step": 4670 }, { "epoch": 0.21, "learning_rate": 4.904343448212733e-05, "loss": 2.7314, "step": 4680 }, { "epoch": 0.21, "learning_rate": 4.904114604787405e-05, "loss": 2.8761, "step": 4690 }, { "epoch": 0.21, "learning_rate": 4.9038857613620765e-05, "loss": 2.765, "step": 4700 }, { "epoch": 0.22, "learning_rate": 4.903656917936748e-05, "loss": 2.8205, "step": 4710 }, { "epoch": 0.22, "learning_rate": 4.90342807451142e-05, "loss": 2.6708, "step": 4720 }, { "epoch": 0.22, "learning_rate": 4.9031992310860914e-05, "loss": 2.8742, "step": 4730 }, { "epoch": 0.22, "learning_rate": 4.902970387660763e-05, "loss": 2.9178, "step": 4740 }, { "epoch": 0.22, "learning_rate": 4.902741544235434e-05, "loss": 2.7455, "step": 4750 }, { "epoch": 0.22, "learning_rate": 4.902512700810106e-05, "loss": 2.8388, "step": 4760 }, { "epoch": 0.22, "learning_rate": 4.902283857384777e-05, "loss": 2.748, "step": 4770 }, { "epoch": 0.22, "learning_rate": 4.902055013959449e-05, "loss": 2.7389, "step": 4780 }, { "epoch": 0.22, "learning_rate": 4.9018261705341206e-05, "loss": 2.6648, "step": 4790 }, { "epoch": 0.22, "learning_rate": 4.901597327108792e-05, "loss": 2.8394, "step": 4800 }, { "epoch": 0.22, "learning_rate": 4.901368483683464e-05, "loss": 2.9014, "step": 4810 }, { "epoch": 0.22, "learning_rate": 4.9011396402581355e-05, "loss": 2.7886, "step": 4820 }, { "epoch": 0.22, "learning_rate": 4.900910796832807e-05, "loss": 2.7742, "step": 4830 }, { "epoch": 0.22, "learning_rate": 4.900681953407479e-05, "loss": 2.6588, "step": 4840 }, { "epoch": 0.22, "learning_rate": 4.9004531099821504e-05, "loss": 2.9167, "step": 4850 }, { "epoch": 0.22, "learning_rate": 4.900224266556822e-05, "loss": 2.9949, "step": 4860 }, { "epoch": 0.22, "learning_rate": 4.899995423131494e-05, "loss": 2.8191, "step": 4870 }, { "epoch": 0.22, "learning_rate": 4.8997665797061653e-05, "loss": 2.7819, "step": 4880 }, { "epoch": 0.22, "learning_rate": 4.899537736280837e-05, "loss": 2.7227, "step": 4890 }, { "epoch": 0.22, "learning_rate": 4.899308892855509e-05, "loss": 2.8487, "step": 4900 }, { "epoch": 0.22, "learning_rate": 4.89908004943018e-05, "loss": 2.7469, "step": 4910 }, { "epoch": 0.22, "learning_rate": 4.898851206004852e-05, "loss": 2.9771, "step": 4920 }, { "epoch": 0.23, "learning_rate": 4.898622362579524e-05, "loss": 2.8447, "step": 4930 }, { "epoch": 0.23, "learning_rate": 4.898393519154195e-05, "loss": 2.856, "step": 4940 }, { "epoch": 0.23, "learning_rate": 4.8981646757288666e-05, "loss": 2.7367, "step": 4950 }, { "epoch": 0.23, "learning_rate": 4.897935832303538e-05, "loss": 2.7719, "step": 4960 }, { "epoch": 0.23, "learning_rate": 4.8977069888782094e-05, "loss": 2.7327, "step": 4970 }, { "epoch": 0.23, "learning_rate": 4.8974781454528815e-05, "loss": 2.7396, "step": 4980 }, { "epoch": 0.23, "learning_rate": 4.897249302027553e-05, "loss": 2.8463, "step": 4990 }, { "epoch": 0.23, "learning_rate": 4.8970204586022243e-05, "loss": 2.7592, "step": 5000 }, { "epoch": 0.23, "learning_rate": 4.8967916151768964e-05, "loss": 2.8151, "step": 5010 }, { "epoch": 0.23, "learning_rate": 4.896562771751568e-05, "loss": 2.6603, "step": 5020 }, { "epoch": 0.23, "learning_rate": 4.896333928326239e-05, "loss": 2.8547, "step": 5030 }, { "epoch": 0.23, "learning_rate": 4.8961050849009113e-05, "loss": 2.8018, "step": 5040 }, { "epoch": 0.23, "learning_rate": 4.895876241475583e-05, "loss": 2.7459, "step": 5050 }, { "epoch": 0.23, "learning_rate": 4.895647398050254e-05, "loss": 2.9486, "step": 5060 }, { "epoch": 0.23, "learning_rate": 4.895418554624926e-05, "loss": 2.8065, "step": 5070 }, { "epoch": 0.23, "learning_rate": 4.895189711199598e-05, "loss": 2.6049, "step": 5080 }, { "epoch": 0.23, "learning_rate": 4.894960867774269e-05, "loss": 3.0472, "step": 5090 }, { "epoch": 0.23, "learning_rate": 4.894732024348941e-05, "loss": 2.7234, "step": 5100 }, { "epoch": 0.23, "learning_rate": 4.8945031809236126e-05, "loss": 2.7381, "step": 5110 }, { "epoch": 0.23, "learning_rate": 4.894274337498284e-05, "loss": 2.7762, "step": 5120 }, { "epoch": 0.23, "learning_rate": 4.8940454940729554e-05, "loss": 2.8969, "step": 5130 }, { "epoch": 0.23, "learning_rate": 4.8938166506476275e-05, "loss": 2.5882, "step": 5140 }, { "epoch": 0.24, "learning_rate": 4.893587807222298e-05, "loss": 2.7469, "step": 5150 }, { "epoch": 0.24, "learning_rate": 4.8933589637969703e-05, "loss": 2.7946, "step": 5160 }, { "epoch": 0.24, "learning_rate": 4.893130120371642e-05, "loss": 2.6888, "step": 5170 }, { "epoch": 0.24, "learning_rate": 4.892901276946313e-05, "loss": 2.6751, "step": 5180 }, { "epoch": 0.24, "learning_rate": 4.892672433520985e-05, "loss": 2.7434, "step": 5190 }, { "epoch": 0.24, "learning_rate": 4.892443590095657e-05, "loss": 2.7763, "step": 5200 }, { "epoch": 0.24, "learning_rate": 4.892214746670328e-05, "loss": 2.752, "step": 5210 }, { "epoch": 0.24, "learning_rate": 4.891985903245e-05, "loss": 2.6629, "step": 5220 }, { "epoch": 0.24, "learning_rate": 4.8917570598196716e-05, "loss": 2.6436, "step": 5230 }, { "epoch": 0.24, "learning_rate": 4.891528216394343e-05, "loss": 2.5243, "step": 5240 }, { "epoch": 0.24, "learning_rate": 4.891299372969015e-05, "loss": 2.7908, "step": 5250 }, { "epoch": 0.24, "learning_rate": 4.8910705295436865e-05, "loss": 2.6459, "step": 5260 }, { "epoch": 0.24, "learning_rate": 4.890841686118358e-05, "loss": 2.5014, "step": 5270 }, { "epoch": 0.24, "learning_rate": 4.89061284269303e-05, "loss": 2.7325, "step": 5280 }, { "epoch": 0.24, "learning_rate": 4.8903839992677014e-05, "loss": 2.6554, "step": 5290 }, { "epoch": 0.24, "learning_rate": 4.890155155842373e-05, "loss": 2.6628, "step": 5300 }, { "epoch": 0.24, "learning_rate": 4.889926312417045e-05, "loss": 2.6414, "step": 5310 }, { "epoch": 0.24, "learning_rate": 4.8896974689917163e-05, "loss": 2.4808, "step": 5320 }, { "epoch": 0.24, "learning_rate": 4.889468625566388e-05, "loss": 2.6611, "step": 5330 }, { "epoch": 0.24, "learning_rate": 4.889239782141059e-05, "loss": 2.7178, "step": 5340 }, { "epoch": 0.24, "learning_rate": 4.8890109387157306e-05, "loss": 2.5934, "step": 5350 }, { "epoch": 0.24, "learning_rate": 4.888782095290402e-05, "loss": 2.6392, "step": 5360 }, { "epoch": 0.25, "learning_rate": 4.888553251865074e-05, "loss": 2.5781, "step": 5370 }, { "epoch": 0.25, "learning_rate": 4.8883244084397455e-05, "loss": 2.6093, "step": 5380 }, { "epoch": 0.25, "learning_rate": 4.888095565014417e-05, "loss": 2.6852, "step": 5390 }, { "epoch": 0.25, "learning_rate": 4.887866721589089e-05, "loss": 2.7037, "step": 5400 }, { "epoch": 0.25, "learning_rate": 4.8876378781637604e-05, "loss": 2.7337, "step": 5410 }, { "epoch": 0.25, "learning_rate": 4.887409034738432e-05, "loss": 2.8831, "step": 5420 }, { "epoch": 0.25, "learning_rate": 4.887180191313104e-05, "loss": 2.8424, "step": 5430 }, { "epoch": 0.25, "learning_rate": 4.886951347887775e-05, "loss": 2.605, "step": 5440 }, { "epoch": 0.25, "learning_rate": 4.886722504462447e-05, "loss": 2.636, "step": 5450 }, { "epoch": 0.25, "learning_rate": 4.886493661037119e-05, "loss": 2.7506, "step": 5460 }, { "epoch": 0.25, "learning_rate": 4.88626481761179e-05, "loss": 2.5908, "step": 5470 }, { "epoch": 0.25, "learning_rate": 4.886035974186462e-05, "loss": 2.7489, "step": 5480 }, { "epoch": 0.25, "learning_rate": 4.885807130761134e-05, "loss": 2.7053, "step": 5490 }, { "epoch": 0.25, "learning_rate": 4.885578287335805e-05, "loss": 2.5964, "step": 5500 }, { "epoch": 0.25, "learning_rate": 4.8853494439104766e-05, "loss": 2.6415, "step": 5510 }, { "epoch": 0.25, "learning_rate": 4.885120600485149e-05, "loss": 2.718, "step": 5520 }, { "epoch": 0.25, "learning_rate": 4.88489175705982e-05, "loss": 2.8281, "step": 5530 }, { "epoch": 0.25, "learning_rate": 4.8846629136344915e-05, "loss": 2.8703, "step": 5540 }, { "epoch": 0.25, "learning_rate": 4.884434070209163e-05, "loss": 2.8019, "step": 5550 }, { "epoch": 0.25, "learning_rate": 4.884205226783834e-05, "loss": 2.4182, "step": 5560 }, { "epoch": 0.25, "learning_rate": 4.8839763833585064e-05, "loss": 2.6893, "step": 5570 }, { "epoch": 0.25, "learning_rate": 4.883747539933178e-05, "loss": 2.5729, "step": 5580 }, { "epoch": 0.26, "learning_rate": 4.883518696507849e-05, "loss": 2.7926, "step": 5590 }, { "epoch": 0.26, "learning_rate": 4.8832898530825213e-05, "loss": 2.692, "step": 5600 }, { "epoch": 0.26, "learning_rate": 4.883061009657193e-05, "loss": 2.6656, "step": 5610 }, { "epoch": 0.26, "learning_rate": 4.882832166231864e-05, "loss": 2.641, "step": 5620 }, { "epoch": 0.26, "learning_rate": 4.882603322806536e-05, "loss": 2.6667, "step": 5630 }, { "epoch": 0.26, "learning_rate": 4.882374479381208e-05, "loss": 2.8071, "step": 5640 }, { "epoch": 0.26, "learning_rate": 4.882145635955879e-05, "loss": 2.7459, "step": 5650 }, { "epoch": 0.26, "learning_rate": 4.881916792530551e-05, "loss": 2.5697, "step": 5660 }, { "epoch": 0.26, "learning_rate": 4.8816879491052226e-05, "loss": 2.7447, "step": 5670 }, { "epoch": 0.26, "learning_rate": 4.881459105679894e-05, "loss": 2.7441, "step": 5680 }, { "epoch": 0.26, "learning_rate": 4.881230262254566e-05, "loss": 2.5097, "step": 5690 }, { "epoch": 0.26, "learning_rate": 4.8810014188292375e-05, "loss": 2.5627, "step": 5700 }, { "epoch": 0.26, "learning_rate": 4.880772575403909e-05, "loss": 2.8485, "step": 5710 }, { "epoch": 0.26, "learning_rate": 4.880543731978581e-05, "loss": 2.7696, "step": 5720 }, { "epoch": 0.26, "learning_rate": 4.8803148885532524e-05, "loss": 2.7177, "step": 5730 }, { "epoch": 0.26, "learning_rate": 4.880086045127923e-05, "loss": 2.713, "step": 5740 }, { "epoch": 0.26, "learning_rate": 4.879857201702595e-05, "loss": 2.5125, "step": 5750 }, { "epoch": 0.26, "learning_rate": 4.879628358277267e-05, "loss": 2.6921, "step": 5760 }, { "epoch": 0.26, "learning_rate": 4.879399514851938e-05, "loss": 2.6419, "step": 5770 }, { "epoch": 0.26, "learning_rate": 4.87917067142661e-05, "loss": 2.525, "step": 5780 }, { "epoch": 0.26, "learning_rate": 4.8789418280012816e-05, "loss": 2.6796, "step": 5790 }, { "epoch": 0.26, "learning_rate": 4.878712984575953e-05, "loss": 2.6179, "step": 5800 }, { "epoch": 0.27, "learning_rate": 4.878484141150625e-05, "loss": 2.8239, "step": 5810 }, { "epoch": 0.27, "learning_rate": 4.8782552977252965e-05, "loss": 2.4569, "step": 5820 }, { "epoch": 0.27, "learning_rate": 4.878026454299968e-05, "loss": 2.596, "step": 5830 }, { "epoch": 0.27, "learning_rate": 4.87779761087464e-05, "loss": 2.6486, "step": 5840 }, { "epoch": 0.27, "learning_rate": 4.8775687674493114e-05, "loss": 2.6741, "step": 5850 }, { "epoch": 0.27, "learning_rate": 4.877339924023983e-05, "loss": 2.7883, "step": 5860 }, { "epoch": 0.27, "learning_rate": 4.877111080598655e-05, "loss": 2.6912, "step": 5870 }, { "epoch": 0.27, "learning_rate": 4.876882237173326e-05, "loss": 2.7816, "step": 5880 }, { "epoch": 0.27, "learning_rate": 4.876653393747998e-05, "loss": 2.5583, "step": 5890 }, { "epoch": 0.27, "learning_rate": 4.87642455032267e-05, "loss": 2.7824, "step": 5900 }, { "epoch": 0.27, "learning_rate": 4.876195706897341e-05, "loss": 2.7493, "step": 5910 }, { "epoch": 0.27, "learning_rate": 4.875966863472013e-05, "loss": 2.6681, "step": 5920 }, { "epoch": 0.27, "learning_rate": 4.875738020046685e-05, "loss": 2.7218, "step": 5930 }, { "epoch": 0.27, "learning_rate": 4.8755091766213555e-05, "loss": 2.4283, "step": 5940 }, { "epoch": 0.27, "learning_rate": 4.8752803331960276e-05, "loss": 2.5835, "step": 5950 }, { "epoch": 0.27, "learning_rate": 4.875051489770699e-05, "loss": 2.9047, "step": 5960 }, { "epoch": 0.27, "learning_rate": 4.8748226463453704e-05, "loss": 2.607, "step": 5970 }, { "epoch": 0.27, "learning_rate": 4.8745938029200425e-05, "loss": 2.8565, "step": 5980 }, { "epoch": 0.27, "learning_rate": 4.874364959494714e-05, "loss": 2.6848, "step": 5990 }, { "epoch": 0.27, "learning_rate": 4.874136116069385e-05, "loss": 2.749, "step": 6000 }, { "epoch": 0.27, "learning_rate": 4.8739072726440574e-05, "loss": 2.7203, "step": 6010 }, { "epoch": 0.27, "learning_rate": 4.873678429218729e-05, "loss": 2.6606, "step": 6020 }, { "epoch": 0.28, "learning_rate": 4.8734495857934e-05, "loss": 2.604, "step": 6030 }, { "epoch": 0.28, "learning_rate": 4.873220742368072e-05, "loss": 2.5937, "step": 6040 }, { "epoch": 0.28, "learning_rate": 4.872991898942744e-05, "loss": 2.7573, "step": 6050 }, { "epoch": 0.28, "learning_rate": 4.872763055517415e-05, "loss": 2.6574, "step": 6060 }, { "epoch": 0.28, "learning_rate": 4.872534212092087e-05, "loss": 2.7203, "step": 6070 }, { "epoch": 0.28, "learning_rate": 4.872305368666759e-05, "loss": 2.5477, "step": 6080 }, { "epoch": 0.28, "learning_rate": 4.87207652524143e-05, "loss": 2.5107, "step": 6090 }, { "epoch": 0.28, "learning_rate": 4.871847681816102e-05, "loss": 2.4743, "step": 6100 }, { "epoch": 0.28, "learning_rate": 4.8716188383907736e-05, "loss": 2.6736, "step": 6110 }, { "epoch": 0.28, "learning_rate": 4.871389994965445e-05, "loss": 2.6276, "step": 6120 }, { "epoch": 0.28, "learning_rate": 4.871161151540117e-05, "loss": 2.8393, "step": 6130 }, { "epoch": 0.28, "learning_rate": 4.870932308114788e-05, "loss": 2.6897, "step": 6140 }, { "epoch": 0.28, "learning_rate": 4.870703464689459e-05, "loss": 2.5804, "step": 6150 }, { "epoch": 0.28, "learning_rate": 4.870474621264131e-05, "loss": 2.649, "step": 6160 }, { "epoch": 0.28, "learning_rate": 4.870245777838803e-05, "loss": 2.7493, "step": 6170 }, { "epoch": 0.28, "learning_rate": 4.870016934413474e-05, "loss": 2.7042, "step": 6180 }, { "epoch": 0.28, "learning_rate": 4.869788090988146e-05, "loss": 2.6509, "step": 6190 }, { "epoch": 0.28, "learning_rate": 4.8695592475628177e-05, "loss": 2.7049, "step": 6200 }, { "epoch": 0.28, "learning_rate": 4.869330404137489e-05, "loss": 2.625, "step": 6210 }, { "epoch": 0.28, "learning_rate": 4.869101560712161e-05, "loss": 2.5366, "step": 6220 }, { "epoch": 0.28, "learning_rate": 4.8688727172868326e-05, "loss": 2.6892, "step": 6230 }, { "epoch": 0.28, "learning_rate": 4.868643873861504e-05, "loss": 2.7161, "step": 6240 }, { "epoch": 0.29, "learning_rate": 4.868415030436176e-05, "loss": 2.5723, "step": 6250 }, { "epoch": 0.29, "learning_rate": 4.8681861870108475e-05, "loss": 2.7496, "step": 6260 }, { "epoch": 0.29, "learning_rate": 4.867957343585519e-05, "loss": 2.5203, "step": 6270 }, { "epoch": 0.29, "learning_rate": 4.867728500160191e-05, "loss": 2.6833, "step": 6280 }, { "epoch": 0.29, "learning_rate": 4.8674996567348624e-05, "loss": 2.66, "step": 6290 }, { "epoch": 0.29, "learning_rate": 4.867270813309534e-05, "loss": 2.6502, "step": 6300 }, { "epoch": 0.29, "learning_rate": 4.867041969884206e-05, "loss": 2.5152, "step": 6310 }, { "epoch": 0.29, "learning_rate": 4.866813126458877e-05, "loss": 2.613, "step": 6320 }, { "epoch": 0.29, "learning_rate": 4.866584283033549e-05, "loss": 2.8358, "step": 6330 }, { "epoch": 0.29, "learning_rate": 4.86635543960822e-05, "loss": 2.6996, "step": 6340 }, { "epoch": 0.29, "learning_rate": 4.8661265961828916e-05, "loss": 2.7579, "step": 6350 }, { "epoch": 0.29, "learning_rate": 4.865897752757563e-05, "loss": 2.5175, "step": 6360 }, { "epoch": 0.29, "learning_rate": 4.865668909332235e-05, "loss": 2.5989, "step": 6370 }, { "epoch": 0.29, "learning_rate": 4.8654400659069065e-05, "loss": 2.6577, "step": 6380 }, { "epoch": 0.29, "learning_rate": 4.865211222481578e-05, "loss": 2.6594, "step": 6390 }, { "epoch": 0.29, "learning_rate": 4.86498237905625e-05, "loss": 2.601, "step": 6400 }, { "epoch": 0.29, "learning_rate": 4.8647535356309214e-05, "loss": 2.6502, "step": 6410 }, { "epoch": 0.29, "learning_rate": 4.864524692205593e-05, "loss": 2.6603, "step": 6420 }, { "epoch": 0.29, "learning_rate": 4.864295848780265e-05, "loss": 2.5609, "step": 6430 }, { "epoch": 0.29, "learning_rate": 4.864067005354936e-05, "loss": 2.661, "step": 6440 }, { "epoch": 0.29, "learning_rate": 4.863838161929608e-05, "loss": 2.399, "step": 6450 }, { "epoch": 0.29, "learning_rate": 4.86360931850428e-05, "loss": 2.7491, "step": 6460 }, { "epoch": 0.3, "learning_rate": 4.863380475078951e-05, "loss": 2.7163, "step": 6470 }, { "epoch": 0.3, "learning_rate": 4.8631516316536227e-05, "loss": 2.7766, "step": 6480 }, { "epoch": 0.3, "learning_rate": 4.862922788228295e-05, "loss": 2.7443, "step": 6490 }, { "epoch": 0.3, "learning_rate": 4.862693944802966e-05, "loss": 2.6196, "step": 6500 }, { "epoch": 0.3, "learning_rate": 4.8624651013776376e-05, "loss": 2.5664, "step": 6510 }, { "epoch": 0.3, "learning_rate": 4.86223625795231e-05, "loss": 2.8527, "step": 6520 }, { "epoch": 0.3, "learning_rate": 4.8620074145269804e-05, "loss": 2.3511, "step": 6530 }, { "epoch": 0.3, "learning_rate": 4.8617785711016525e-05, "loss": 2.7464, "step": 6540 }, { "epoch": 0.3, "learning_rate": 4.861549727676324e-05, "loss": 2.7722, "step": 6550 }, { "epoch": 0.3, "learning_rate": 4.861320884250995e-05, "loss": 2.6868, "step": 6560 }, { "epoch": 0.3, "learning_rate": 4.8610920408256674e-05, "loss": 2.5773, "step": 6570 }, { "epoch": 0.3, "learning_rate": 4.860863197400339e-05, "loss": 2.4465, "step": 6580 }, { "epoch": 0.3, "learning_rate": 4.86063435397501e-05, "loss": 2.5659, "step": 6590 }, { "epoch": 0.3, "learning_rate": 4.860405510549682e-05, "loss": 2.5124, "step": 6600 }, { "epoch": 0.3, "learning_rate": 4.860176667124354e-05, "loss": 2.6732, "step": 6610 }, { "epoch": 0.3, "learning_rate": 4.859947823699025e-05, "loss": 2.7388, "step": 6620 }, { "epoch": 0.3, "learning_rate": 4.859718980273697e-05, "loss": 2.5931, "step": 6630 }, { "epoch": 0.3, "learning_rate": 4.8594901368483687e-05, "loss": 2.5704, "step": 6640 }, { "epoch": 0.3, "learning_rate": 4.85926129342304e-05, "loss": 2.6002, "step": 6650 }, { "epoch": 0.3, "learning_rate": 4.859032449997712e-05, "loss": 2.8469, "step": 6660 }, { "epoch": 0.3, "learning_rate": 4.8588036065723836e-05, "loss": 2.6524, "step": 6670 }, { "epoch": 0.31, "learning_rate": 4.858574763147055e-05, "loss": 2.7466, "step": 6680 }, { "epoch": 0.31, "learning_rate": 4.858345919721727e-05, "loss": 2.5216, "step": 6690 }, { "epoch": 0.31, "learning_rate": 4.8581170762963985e-05, "loss": 2.5961, "step": 6700 }, { "epoch": 0.31, "learning_rate": 4.85788823287107e-05, "loss": 2.6527, "step": 6710 }, { "epoch": 0.31, "learning_rate": 4.857659389445742e-05, "loss": 2.4777, "step": 6720 }, { "epoch": 0.31, "learning_rate": 4.857430546020413e-05, "loss": 2.7316, "step": 6730 }, { "epoch": 0.31, "learning_rate": 4.857201702595084e-05, "loss": 2.5516, "step": 6740 }, { "epoch": 0.31, "learning_rate": 4.856972859169756e-05, "loss": 2.5434, "step": 6750 }, { "epoch": 0.31, "learning_rate": 4.8567440157444276e-05, "loss": 2.7076, "step": 6760 }, { "epoch": 0.31, "learning_rate": 4.856515172319099e-05, "loss": 2.6194, "step": 6770 }, { "epoch": 0.31, "learning_rate": 4.856286328893771e-05, "loss": 2.5363, "step": 6780 }, { "epoch": 0.31, "learning_rate": 4.8560574854684426e-05, "loss": 2.6663, "step": 6790 }, { "epoch": 0.31, "learning_rate": 4.855828642043114e-05, "loss": 2.5188, "step": 6800 }, { "epoch": 0.31, "learning_rate": 4.855599798617786e-05, "loss": 2.6201, "step": 6810 }, { "epoch": 0.31, "learning_rate": 4.8553709551924575e-05, "loss": 2.7074, "step": 6820 }, { "epoch": 0.31, "learning_rate": 4.855142111767129e-05, "loss": 2.636, "step": 6830 }, { "epoch": 0.31, "learning_rate": 4.854913268341801e-05, "loss": 2.7397, "step": 6840 }, { "epoch": 0.31, "learning_rate": 4.8546844249164724e-05, "loss": 2.723, "step": 6850 }, { "epoch": 0.31, "learning_rate": 4.854455581491144e-05, "loss": 2.6131, "step": 6860 }, { "epoch": 0.31, "learning_rate": 4.854226738065816e-05, "loss": 2.6365, "step": 6870 }, { "epoch": 0.31, "learning_rate": 4.853997894640487e-05, "loss": 2.5725, "step": 6880 }, { "epoch": 0.31, "learning_rate": 4.853769051215159e-05, "loss": 2.6628, "step": 6890 }, { "epoch": 0.32, "learning_rate": 4.853540207789831e-05, "loss": 2.6222, "step": 6900 }, { "epoch": 0.32, "learning_rate": 4.853311364364502e-05, "loss": 2.6225, "step": 6910 }, { "epoch": 0.32, "learning_rate": 4.8530825209391737e-05, "loss": 2.5112, "step": 6920 }, { "epoch": 0.32, "learning_rate": 4.852853677513845e-05, "loss": 2.6407, "step": 6930 }, { "epoch": 0.32, "learning_rate": 4.8526248340885165e-05, "loss": 2.5387, "step": 6940 }, { "epoch": 0.32, "learning_rate": 4.8523959906631886e-05, "loss": 2.5629, "step": 6950 }, { "epoch": 0.32, "learning_rate": 4.85216714723786e-05, "loss": 2.5312, "step": 6960 }, { "epoch": 0.32, "learning_rate": 4.8519383038125314e-05, "loss": 2.5679, "step": 6970 }, { "epoch": 0.32, "learning_rate": 4.8517094603872035e-05, "loss": 2.7584, "step": 6980 }, { "epoch": 0.32, "learning_rate": 4.851480616961875e-05, "loss": 2.6335, "step": 6990 }, { "epoch": 0.32, "learning_rate": 4.851251773536546e-05, "loss": 2.6995, "step": 7000 }, { "epoch": 0.32, "learning_rate": 4.8510229301112184e-05, "loss": 2.7, "step": 7010 }, { "epoch": 0.32, "learning_rate": 4.85079408668589e-05, "loss": 2.6885, "step": 7020 }, { "epoch": 0.32, "learning_rate": 4.850565243260561e-05, "loss": 2.7304, "step": 7030 }, { "epoch": 0.32, "learning_rate": 4.850336399835233e-05, "loss": 2.64, "step": 7040 }, { "epoch": 0.32, "learning_rate": 4.850107556409905e-05, "loss": 2.5838, "step": 7050 }, { "epoch": 0.32, "learning_rate": 4.849878712984576e-05, "loss": 2.6501, "step": 7060 }, { "epoch": 0.32, "learning_rate": 4.849649869559248e-05, "loss": 2.6321, "step": 7070 }, { "epoch": 0.32, "learning_rate": 4.8494210261339197e-05, "loss": 2.5808, "step": 7080 }, { "epoch": 0.32, "learning_rate": 4.849192182708591e-05, "loss": 2.6379, "step": 7090 }, { "epoch": 0.32, "learning_rate": 4.848963339283263e-05, "loss": 2.7503, "step": 7100 }, { "epoch": 0.32, "learning_rate": 4.8487344958579346e-05, "loss": 2.6084, "step": 7110 }, { "epoch": 0.33, "learning_rate": 4.848505652432605e-05, "loss": 2.6344, "step": 7120 }, { "epoch": 0.33, "learning_rate": 4.8482768090072774e-05, "loss": 2.5074, "step": 7130 }, { "epoch": 0.33, "learning_rate": 4.848047965581949e-05, "loss": 2.595, "step": 7140 }, { "epoch": 0.33, "learning_rate": 4.84781912215662e-05, "loss": 2.6297, "step": 7150 }, { "epoch": 0.33, "learning_rate": 4.847590278731292e-05, "loss": 2.6597, "step": 7160 }, { "epoch": 0.33, "learning_rate": 4.847361435305964e-05, "loss": 2.6749, "step": 7170 }, { "epoch": 0.33, "learning_rate": 4.847132591880635e-05, "loss": 2.5787, "step": 7180 }, { "epoch": 0.33, "learning_rate": 4.846903748455307e-05, "loss": 2.4972, "step": 7190 }, { "epoch": 0.33, "learning_rate": 4.8466749050299786e-05, "loss": 2.5525, "step": 7200 }, { "epoch": 0.33, "learning_rate": 4.84644606160465e-05, "loss": 2.5593, "step": 7210 }, { "epoch": 0.33, "learning_rate": 4.846217218179322e-05, "loss": 2.7031, "step": 7220 }, { "epoch": 0.33, "learning_rate": 4.8459883747539936e-05, "loss": 2.5279, "step": 7230 }, { "epoch": 0.33, "learning_rate": 4.845759531328665e-05, "loss": 2.8, "step": 7240 }, { "epoch": 0.33, "learning_rate": 4.845530687903337e-05, "loss": 2.5257, "step": 7250 }, { "epoch": 0.33, "learning_rate": 4.8453018444780085e-05, "loss": 2.5536, "step": 7260 }, { "epoch": 0.33, "learning_rate": 4.84507300105268e-05, "loss": 2.5473, "step": 7270 }, { "epoch": 0.33, "learning_rate": 4.844844157627352e-05, "loss": 2.5072, "step": 7280 }, { "epoch": 0.33, "learning_rate": 4.8446153142020234e-05, "loss": 2.4878, "step": 7290 }, { "epoch": 0.33, "learning_rate": 4.844386470776695e-05, "loss": 2.6505, "step": 7300 }, { "epoch": 0.33, "learning_rate": 4.844157627351367e-05, "loss": 2.6653, "step": 7310 }, { "epoch": 0.33, "learning_rate": 4.8439287839260376e-05, "loss": 2.512, "step": 7320 }, { "epoch": 0.33, "learning_rate": 4.84369994050071e-05, "loss": 2.5574, "step": 7330 }, { "epoch": 0.34, "learning_rate": 4.843471097075381e-05, "loss": 2.6409, "step": 7340 }, { "epoch": 0.34, "learning_rate": 4.8432422536500526e-05, "loss": 2.5373, "step": 7350 }, { "epoch": 0.34, "learning_rate": 4.8430134102247246e-05, "loss": 2.4427, "step": 7360 }, { "epoch": 0.34, "learning_rate": 4.842784566799396e-05, "loss": 2.462, "step": 7370 }, { "epoch": 0.34, "learning_rate": 4.8425557233740675e-05, "loss": 2.4723, "step": 7380 }, { "epoch": 0.34, "learning_rate": 4.8423268799487396e-05, "loss": 2.6746, "step": 7390 }, { "epoch": 0.34, "learning_rate": 4.842098036523411e-05, "loss": 2.4742, "step": 7400 }, { "epoch": 0.34, "learning_rate": 4.8418691930980824e-05, "loss": 2.4023, "step": 7410 }, { "epoch": 0.34, "learning_rate": 4.8416403496727545e-05, "loss": 2.3752, "step": 7420 }, { "epoch": 0.34, "learning_rate": 4.841411506247426e-05, "loss": 2.5018, "step": 7430 }, { "epoch": 0.34, "learning_rate": 4.841182662822097e-05, "loss": 2.5592, "step": 7440 }, { "epoch": 0.34, "learning_rate": 4.8409538193967694e-05, "loss": 2.7585, "step": 7450 }, { "epoch": 0.34, "learning_rate": 4.840724975971441e-05, "loss": 2.4744, "step": 7460 }, { "epoch": 0.34, "learning_rate": 4.840496132546112e-05, "loss": 2.4881, "step": 7470 }, { "epoch": 0.34, "learning_rate": 4.8402672891207836e-05, "loss": 2.5161, "step": 7480 }, { "epoch": 0.34, "learning_rate": 4.840038445695456e-05, "loss": 2.4615, "step": 7490 }, { "epoch": 0.34, "learning_rate": 4.839809602270127e-05, "loss": 2.5196, "step": 7500 }, { "epoch": 0.34, "learning_rate": 4.8395807588447986e-05, "loss": 2.602, "step": 7510 }, { "epoch": 0.34, "learning_rate": 4.83935191541947e-05, "loss": 2.4739, "step": 7520 }, { "epoch": 0.34, "learning_rate": 4.8391230719941414e-05, "loss": 2.5139, "step": 7530 }, { "epoch": 0.34, "learning_rate": 4.8388942285688135e-05, "loss": 2.5748, "step": 7540 }, { "epoch": 0.34, "learning_rate": 4.838665385143485e-05, "loss": 2.5106, "step": 7550 }, { "epoch": 0.35, "learning_rate": 4.838436541718156e-05, "loss": 2.7197, "step": 7560 }, { "epoch": 0.35, "learning_rate": 4.8382076982928284e-05, "loss": 2.6796, "step": 7570 }, { "epoch": 0.35, "learning_rate": 4.8379788548675e-05, "loss": 2.5667, "step": 7580 }, { "epoch": 0.35, "learning_rate": 4.837750011442171e-05, "loss": 2.633, "step": 7590 }, { "epoch": 0.35, "learning_rate": 4.837521168016843e-05, "loss": 2.4773, "step": 7600 }, { "epoch": 0.35, "learning_rate": 4.837292324591515e-05, "loss": 2.6842, "step": 7610 }, { "epoch": 0.35, "learning_rate": 4.837063481166186e-05, "loss": 2.669, "step": 7620 }, { "epoch": 0.35, "learning_rate": 4.836834637740858e-05, "loss": 2.6445, "step": 7630 }, { "epoch": 0.35, "learning_rate": 4.8366057943155296e-05, "loss": 2.6097, "step": 7640 }, { "epoch": 0.35, "learning_rate": 4.836376950890201e-05, "loss": 2.5689, "step": 7650 }, { "epoch": 0.35, "learning_rate": 4.836148107464873e-05, "loss": 2.6344, "step": 7660 }, { "epoch": 0.35, "learning_rate": 4.8359192640395446e-05, "loss": 2.5654, "step": 7670 }, { "epoch": 0.35, "learning_rate": 4.835690420614216e-05, "loss": 2.5571, "step": 7680 }, { "epoch": 0.35, "learning_rate": 4.835461577188888e-05, "loss": 2.5867, "step": 7690 }, { "epoch": 0.35, "learning_rate": 4.8352327337635595e-05, "loss": 2.6721, "step": 7700 }, { "epoch": 0.35, "learning_rate": 4.835003890338231e-05, "loss": 2.5663, "step": 7710 }, { "epoch": 0.35, "learning_rate": 4.834775046912902e-05, "loss": 2.5552, "step": 7720 }, { "epoch": 0.35, "learning_rate": 4.834546203487574e-05, "loss": 2.6109, "step": 7730 }, { "epoch": 0.35, "learning_rate": 4.834317360062245e-05, "loss": 2.523, "step": 7740 }, { "epoch": 0.35, "learning_rate": 4.834088516636917e-05, "loss": 2.568, "step": 7750 }, { "epoch": 0.35, "learning_rate": 4.8338596732115886e-05, "loss": 2.6206, "step": 7760 }, { "epoch": 0.35, "learning_rate": 4.83363082978626e-05, "loss": 2.5241, "step": 7770 }, { "epoch": 0.36, "learning_rate": 4.833401986360932e-05, "loss": 2.5747, "step": 7780 }, { "epoch": 0.36, "learning_rate": 4.8331731429356036e-05, "loss": 2.677, "step": 7790 }, { "epoch": 0.36, "learning_rate": 4.832944299510275e-05, "loss": 2.5761, "step": 7800 }, { "epoch": 0.36, "learning_rate": 4.832715456084947e-05, "loss": 2.4517, "step": 7810 }, { "epoch": 0.36, "learning_rate": 4.8324866126596185e-05, "loss": 2.6228, "step": 7820 }, { "epoch": 0.36, "learning_rate": 4.83225776923429e-05, "loss": 2.7089, "step": 7830 }, { "epoch": 0.36, "learning_rate": 4.832028925808962e-05, "loss": 2.5465, "step": 7840 }, { "epoch": 0.36, "learning_rate": 4.8318000823836334e-05, "loss": 2.4523, "step": 7850 }, { "epoch": 0.36, "learning_rate": 4.831571238958305e-05, "loss": 2.4675, "step": 7860 }, { "epoch": 0.36, "learning_rate": 4.831342395532977e-05, "loss": 2.5328, "step": 7870 }, { "epoch": 0.36, "learning_rate": 4.831113552107648e-05, "loss": 2.6169, "step": 7880 }, { "epoch": 0.36, "learning_rate": 4.83088470868232e-05, "loss": 2.442, "step": 7890 }, { "epoch": 0.36, "learning_rate": 4.830655865256992e-05, "loss": 2.5522, "step": 7900 }, { "epoch": 0.36, "learning_rate": 4.8304270218316625e-05, "loss": 2.5453, "step": 7910 }, { "epoch": 0.36, "learning_rate": 4.8301981784063346e-05, "loss": 2.5584, "step": 7920 }, { "epoch": 0.36, "learning_rate": 4.829969334981006e-05, "loss": 2.6463, "step": 7930 }, { "epoch": 0.36, "learning_rate": 4.8297404915556775e-05, "loss": 2.6636, "step": 7940 }, { "epoch": 0.36, "learning_rate": 4.8295116481303496e-05, "loss": 2.6556, "step": 7950 }, { "epoch": 0.36, "learning_rate": 4.829282804705021e-05, "loss": 2.6531, "step": 7960 }, { "epoch": 0.36, "learning_rate": 4.8290539612796924e-05, "loss": 2.485, "step": 7970 }, { "epoch": 0.36, "learning_rate": 4.8288251178543645e-05, "loss": 2.5574, "step": 7980 }, { "epoch": 0.36, "learning_rate": 4.828596274429036e-05, "loss": 2.6102, "step": 7990 }, { "epoch": 0.37, "learning_rate": 4.828367431003707e-05, "loss": 2.7291, "step": 8000 }, { "epoch": 0.37, "learning_rate": 4.8281385875783794e-05, "loss": 2.4075, "step": 8010 }, { "epoch": 0.37, "learning_rate": 4.827909744153051e-05, "loss": 2.4394, "step": 8020 }, { "epoch": 0.37, "learning_rate": 4.827680900727722e-05, "loss": 2.5503, "step": 8030 }, { "epoch": 0.37, "learning_rate": 4.827452057302394e-05, "loss": 2.5505, "step": 8040 }, { "epoch": 0.37, "learning_rate": 4.827223213877066e-05, "loss": 2.5633, "step": 8050 }, { "epoch": 0.37, "learning_rate": 4.826994370451737e-05, "loss": 2.6635, "step": 8060 }, { "epoch": 0.37, "learning_rate": 4.826765527026409e-05, "loss": 2.6484, "step": 8070 }, { "epoch": 0.37, "learning_rate": 4.8265366836010806e-05, "loss": 2.6176, "step": 8080 }, { "epoch": 0.37, "learning_rate": 4.826307840175752e-05, "loss": 2.5308, "step": 8090 }, { "epoch": 0.37, "learning_rate": 4.826078996750424e-05, "loss": 2.5419, "step": 8100 }, { "epoch": 0.37, "learning_rate": 4.825850153325095e-05, "loss": 2.5851, "step": 8110 }, { "epoch": 0.37, "learning_rate": 4.825621309899766e-05, "loss": 2.5353, "step": 8120 }, { "epoch": 0.37, "learning_rate": 4.8253924664744384e-05, "loss": 2.6167, "step": 8130 }, { "epoch": 0.37, "learning_rate": 4.82516362304911e-05, "loss": 2.622, "step": 8140 }, { "epoch": 0.37, "learning_rate": 4.824934779623781e-05, "loss": 2.5547, "step": 8150 }, { "epoch": 0.37, "learning_rate": 4.824705936198453e-05, "loss": 2.7017, "step": 8160 }, { "epoch": 0.37, "learning_rate": 4.824477092773125e-05, "loss": 2.5649, "step": 8170 }, { "epoch": 0.37, "learning_rate": 4.824248249347796e-05, "loss": 2.4745, "step": 8180 }, { "epoch": 0.37, "learning_rate": 4.824019405922468e-05, "loss": 2.6349, "step": 8190 }, { "epoch": 0.37, "learning_rate": 4.8237905624971396e-05, "loss": 2.5403, "step": 8200 }, { "epoch": 0.37, "learning_rate": 4.823561719071811e-05, "loss": 2.6282, "step": 8210 }, { "epoch": 0.38, "learning_rate": 4.823332875646483e-05, "loss": 2.4393, "step": 8220 }, { "epoch": 0.38, "learning_rate": 4.8231040322211546e-05, "loss": 2.6335, "step": 8230 }, { "epoch": 0.38, "learning_rate": 4.822875188795826e-05, "loss": 2.5529, "step": 8240 }, { "epoch": 0.38, "learning_rate": 4.822646345370498e-05, "loss": 2.6188, "step": 8250 }, { "epoch": 0.38, "learning_rate": 4.8224175019451695e-05, "loss": 2.5472, "step": 8260 }, { "epoch": 0.38, "learning_rate": 4.822188658519841e-05, "loss": 2.4341, "step": 8270 }, { "epoch": 0.38, "learning_rate": 4.821959815094513e-05, "loss": 2.5995, "step": 8280 }, { "epoch": 0.38, "learning_rate": 4.8217309716691844e-05, "loss": 2.7862, "step": 8290 }, { "epoch": 0.38, "learning_rate": 4.821502128243856e-05, "loss": 2.4802, "step": 8300 }, { "epoch": 0.38, "learning_rate": 4.821273284818527e-05, "loss": 2.5694, "step": 8310 }, { "epoch": 0.38, "learning_rate": 4.8210444413931986e-05, "loss": 2.4583, "step": 8320 }, { "epoch": 0.38, "learning_rate": 4.820815597967871e-05, "loss": 2.4739, "step": 8330 }, { "epoch": 0.38, "learning_rate": 4.820586754542542e-05, "loss": 2.4861, "step": 8340 }, { "epoch": 0.38, "learning_rate": 4.8203579111172135e-05, "loss": 2.6221, "step": 8350 }, { "epoch": 0.38, "learning_rate": 4.8201290676918856e-05, "loss": 2.4695, "step": 8360 }, { "epoch": 0.38, "learning_rate": 4.819900224266557e-05, "loss": 2.6758, "step": 8370 }, { "epoch": 0.38, "learning_rate": 4.8196713808412285e-05, "loss": 2.5065, "step": 8380 }, { "epoch": 0.38, "learning_rate": 4.8194425374159006e-05, "loss": 2.5691, "step": 8390 }, { "epoch": 0.38, "learning_rate": 4.819213693990572e-05, "loss": 2.6554, "step": 8400 }, { "epoch": 0.38, "learning_rate": 4.8189848505652434e-05, "loss": 2.5186, "step": 8410 }, { "epoch": 0.38, "learning_rate": 4.8187560071399155e-05, "loss": 2.5893, "step": 8420 }, { "epoch": 0.38, "learning_rate": 4.818527163714587e-05, "loss": 2.5439, "step": 8430 }, { "epoch": 0.39, "learning_rate": 4.818298320289258e-05, "loss": 2.4492, "step": 8440 }, { "epoch": 0.39, "learning_rate": 4.8180694768639304e-05, "loss": 2.5261, "step": 8450 }, { "epoch": 0.39, "learning_rate": 4.817840633438602e-05, "loss": 2.5481, "step": 8460 }, { "epoch": 0.39, "learning_rate": 4.817611790013273e-05, "loss": 2.5239, "step": 8470 }, { "epoch": 0.39, "learning_rate": 4.817382946587945e-05, "loss": 2.579, "step": 8480 }, { "epoch": 0.39, "learning_rate": 4.817154103162617e-05, "loss": 2.5448, "step": 8490 }, { "epoch": 0.39, "learning_rate": 4.816925259737288e-05, "loss": 2.4754, "step": 8500 }, { "epoch": 0.39, "learning_rate": 4.8166964163119595e-05, "loss": 2.5759, "step": 8510 }, { "epoch": 0.39, "learning_rate": 4.816467572886631e-05, "loss": 2.7286, "step": 8520 }, { "epoch": 0.39, "learning_rate": 4.8162387294613024e-05, "loss": 2.5925, "step": 8530 }, { "epoch": 0.39, "learning_rate": 4.8160098860359745e-05, "loss": 2.5367, "step": 8540 }, { "epoch": 0.39, "learning_rate": 4.815781042610646e-05, "loss": 2.5697, "step": 8550 }, { "epoch": 0.39, "learning_rate": 4.815552199185317e-05, "loss": 2.5477, "step": 8560 }, { "epoch": 0.39, "learning_rate": 4.8153233557599894e-05, "loss": 2.4684, "step": 8570 }, { "epoch": 0.39, "learning_rate": 4.815094512334661e-05, "loss": 2.531, "step": 8580 }, { "epoch": 0.39, "learning_rate": 4.814865668909332e-05, "loss": 2.4954, "step": 8590 }, { "epoch": 0.39, "learning_rate": 4.814636825484004e-05, "loss": 2.6341, "step": 8600 }, { "epoch": 0.39, "learning_rate": 4.814407982058676e-05, "loss": 2.5244, "step": 8610 }, { "epoch": 0.39, "learning_rate": 4.814179138633347e-05, "loss": 2.4567, "step": 8620 }, { "epoch": 0.39, "learning_rate": 4.813950295208019e-05, "loss": 2.5251, "step": 8630 }, { "epoch": 0.39, "learning_rate": 4.8137214517826906e-05, "loss": 2.5444, "step": 8640 }, { "epoch": 0.39, "learning_rate": 4.813492608357362e-05, "loss": 2.3958, "step": 8650 }, { "epoch": 0.4, "learning_rate": 4.813263764932034e-05, "loss": 2.4682, "step": 8660 }, { "epoch": 0.4, "learning_rate": 4.8130349215067055e-05, "loss": 2.6955, "step": 8670 }, { "epoch": 0.4, "learning_rate": 4.812806078081377e-05, "loss": 2.4918, "step": 8680 }, { "epoch": 0.4, "learning_rate": 4.812577234656049e-05, "loss": 2.6071, "step": 8690 }, { "epoch": 0.4, "learning_rate": 4.81234839123072e-05, "loss": 2.4898, "step": 8700 }, { "epoch": 0.4, "learning_rate": 4.812119547805391e-05, "loss": 2.4275, "step": 8710 }, { "epoch": 0.4, "learning_rate": 4.811890704380063e-05, "loss": 2.4922, "step": 8720 }, { "epoch": 0.4, "learning_rate": 4.811661860954735e-05, "loss": 2.3803, "step": 8730 }, { "epoch": 0.4, "learning_rate": 4.811433017529406e-05, "loss": 2.3979, "step": 8740 }, { "epoch": 0.4, "learning_rate": 4.811204174104078e-05, "loss": 2.5462, "step": 8750 }, { "epoch": 0.4, "learning_rate": 4.8109753306787496e-05, "loss": 2.5365, "step": 8760 }, { "epoch": 0.4, "learning_rate": 4.810746487253421e-05, "loss": 2.4659, "step": 8770 }, { "epoch": 0.4, "learning_rate": 4.810517643828093e-05, "loss": 2.5076, "step": 8780 }, { "epoch": 0.4, "learning_rate": 4.8102888004027645e-05, "loss": 2.4665, "step": 8790 }, { "epoch": 0.4, "learning_rate": 4.810059956977436e-05, "loss": 2.4905, "step": 8800 }, { "epoch": 0.4, "learning_rate": 4.809831113552108e-05, "loss": 2.5918, "step": 8810 }, { "epoch": 0.4, "learning_rate": 4.8096022701267795e-05, "loss": 2.4508, "step": 8820 }, { "epoch": 0.4, "learning_rate": 4.809373426701451e-05, "loss": 2.4389, "step": 8830 }, { "epoch": 0.4, "learning_rate": 4.809144583276123e-05, "loss": 2.4034, "step": 8840 }, { "epoch": 0.4, "learning_rate": 4.8089157398507944e-05, "loss": 2.5264, "step": 8850 }, { "epoch": 0.4, "learning_rate": 4.808686896425466e-05, "loss": 2.5054, "step": 8860 }, { "epoch": 0.41, "learning_rate": 4.808458053000138e-05, "loss": 2.4104, "step": 8870 }, { "epoch": 0.41, "learning_rate": 4.808229209574809e-05, "loss": 2.3915, "step": 8880 }, { "epoch": 0.41, "learning_rate": 4.808000366149481e-05, "loss": 2.5778, "step": 8890 }, { "epoch": 0.41, "learning_rate": 4.807771522724152e-05, "loss": 2.6478, "step": 8900 }, { "epoch": 0.41, "learning_rate": 4.8075426792988235e-05, "loss": 2.6366, "step": 8910 }, { "epoch": 0.41, "learning_rate": 4.8073138358734956e-05, "loss": 2.6483, "step": 8920 }, { "epoch": 0.41, "learning_rate": 4.807084992448167e-05, "loss": 2.652, "step": 8930 }, { "epoch": 0.41, "learning_rate": 4.8068561490228385e-05, "loss": 2.6069, "step": 8940 }, { "epoch": 0.41, "learning_rate": 4.8066273055975105e-05, "loss": 2.6071, "step": 8950 }, { "epoch": 0.41, "learning_rate": 4.806398462172182e-05, "loss": 2.495, "step": 8960 }, { "epoch": 0.41, "learning_rate": 4.8061696187468534e-05, "loss": 2.4157, "step": 8970 }, { "epoch": 0.41, "learning_rate": 4.8059407753215255e-05, "loss": 2.4023, "step": 8980 }, { "epoch": 0.41, "learning_rate": 4.805711931896197e-05, "loss": 2.4809, "step": 8990 }, { "epoch": 0.41, "learning_rate": 4.805483088470868e-05, "loss": 2.396, "step": 9000 }, { "epoch": 0.41, "learning_rate": 4.8052542450455404e-05, "loss": 2.7206, "step": 9010 }, { "epoch": 0.41, "learning_rate": 4.805025401620212e-05, "loss": 2.5681, "step": 9020 }, { "epoch": 0.41, "learning_rate": 4.804796558194883e-05, "loss": 2.5723, "step": 9030 }, { "epoch": 0.41, "learning_rate": 4.804567714769555e-05, "loss": 2.5191, "step": 9040 }, { "epoch": 0.41, "learning_rate": 4.804338871344227e-05, "loss": 2.5276, "step": 9050 }, { "epoch": 0.41, "learning_rate": 4.804110027918898e-05, "loss": 2.4477, "step": 9060 }, { "epoch": 0.41, "learning_rate": 4.80388118449357e-05, "loss": 2.4986, "step": 9070 }, { "epoch": 0.41, "learning_rate": 4.8036523410682416e-05, "loss": 2.5803, "step": 9080 }, { "epoch": 0.42, "learning_rate": 4.803423497642913e-05, "loss": 2.5081, "step": 9090 }, { "epoch": 0.42, "learning_rate": 4.8031946542175845e-05, "loss": 2.5978, "step": 9100 }, { "epoch": 0.42, "learning_rate": 4.802965810792256e-05, "loss": 2.5181, "step": 9110 }, { "epoch": 0.42, "learning_rate": 4.802736967366927e-05, "loss": 2.6178, "step": 9120 }, { "epoch": 0.42, "learning_rate": 4.8025081239415994e-05, "loss": 2.4637, "step": 9130 }, { "epoch": 0.42, "learning_rate": 4.802279280516271e-05, "loss": 2.4851, "step": 9140 }, { "epoch": 0.42, "learning_rate": 4.802050437090942e-05, "loss": 2.3544, "step": 9150 }, { "epoch": 0.42, "learning_rate": 4.801821593665614e-05, "loss": 2.4827, "step": 9160 }, { "epoch": 0.42, "learning_rate": 4.801592750240286e-05, "loss": 2.4446, "step": 9170 }, { "epoch": 0.42, "learning_rate": 4.801363906814957e-05, "loss": 2.528, "step": 9180 }, { "epoch": 0.42, "learning_rate": 4.801135063389629e-05, "loss": 2.6581, "step": 9190 }, { "epoch": 0.42, "learning_rate": 4.8009062199643006e-05, "loss": 2.4954, "step": 9200 }, { "epoch": 0.42, "learning_rate": 4.800677376538972e-05, "loss": 2.5625, "step": 9210 }, { "epoch": 0.42, "learning_rate": 4.800448533113644e-05, "loss": 2.4081, "step": 9220 }, { "epoch": 0.42, "learning_rate": 4.8002196896883155e-05, "loss": 2.4785, "step": 9230 }, { "epoch": 0.42, "learning_rate": 4.799990846262987e-05, "loss": 2.3104, "step": 9240 }, { "epoch": 0.42, "learning_rate": 4.799762002837659e-05, "loss": 2.5631, "step": 9250 }, { "epoch": 0.42, "learning_rate": 4.7995331594123305e-05, "loss": 2.3723, "step": 9260 }, { "epoch": 0.42, "learning_rate": 4.799304315987002e-05, "loss": 2.5787, "step": 9270 }, { "epoch": 0.42, "learning_rate": 4.799075472561674e-05, "loss": 2.4058, "step": 9280 }, { "epoch": 0.42, "learning_rate": 4.7988466291363454e-05, "loss": 2.5328, "step": 9290 }, { "epoch": 0.42, "learning_rate": 4.798617785711017e-05, "loss": 2.4113, "step": 9300 }, { "epoch": 0.43, "learning_rate": 4.798388942285688e-05, "loss": 2.3761, "step": 9310 }, { "epoch": 0.43, "learning_rate": 4.7981600988603596e-05, "loss": 2.372, "step": 9320 }, { "epoch": 0.43, "learning_rate": 4.797931255435032e-05, "loss": 2.5813, "step": 9330 }, { "epoch": 0.43, "learning_rate": 4.797702412009703e-05, "loss": 2.5153, "step": 9340 }, { "epoch": 0.43, "learning_rate": 4.7974735685843745e-05, "loss": 2.3823, "step": 9350 }, { "epoch": 0.43, "learning_rate": 4.7972447251590466e-05, "loss": 2.3528, "step": 9360 }, { "epoch": 0.43, "learning_rate": 4.797015881733718e-05, "loss": 2.6451, "step": 9370 }, { "epoch": 0.43, "learning_rate": 4.7967870383083894e-05, "loss": 2.4253, "step": 9380 }, { "epoch": 0.43, "learning_rate": 4.7965581948830615e-05, "loss": 2.372, "step": 9390 }, { "epoch": 0.43, "learning_rate": 4.796329351457733e-05, "loss": 2.5262, "step": 9400 }, { "epoch": 0.43, "learning_rate": 4.7961005080324044e-05, "loss": 2.6468, "step": 9410 }, { "epoch": 0.43, "learning_rate": 4.7958716646070765e-05, "loss": 2.642, "step": 9420 }, { "epoch": 0.43, "learning_rate": 4.795642821181748e-05, "loss": 2.5203, "step": 9430 }, { "epoch": 0.43, "learning_rate": 4.795413977756419e-05, "loss": 2.5061, "step": 9440 }, { "epoch": 0.43, "learning_rate": 4.7951851343310914e-05, "loss": 2.6211, "step": 9450 }, { "epoch": 0.43, "learning_rate": 4.794956290905763e-05, "loss": 2.5407, "step": 9460 }, { "epoch": 0.43, "learning_rate": 4.794727447480434e-05, "loss": 2.4666, "step": 9470 }, { "epoch": 0.43, "learning_rate": 4.794498604055106e-05, "loss": 2.6163, "step": 9480 }, { "epoch": 0.43, "learning_rate": 4.794269760629777e-05, "loss": 2.5505, "step": 9490 }, { "epoch": 0.43, "learning_rate": 4.7940409172044484e-05, "loss": 2.5365, "step": 9500 }, { "epoch": 0.43, "learning_rate": 4.7938120737791205e-05, "loss": 2.4028, "step": 9510 }, { "epoch": 0.43, "learning_rate": 4.793583230353792e-05, "loss": 2.6578, "step": 9520 }, { "epoch": 0.44, "learning_rate": 4.7933543869284634e-05, "loss": 2.5215, "step": 9530 }, { "epoch": 0.44, "learning_rate": 4.7931255435031355e-05, "loss": 2.3621, "step": 9540 }, { "epoch": 0.44, "learning_rate": 4.792896700077807e-05, "loss": 2.3827, "step": 9550 }, { "epoch": 0.44, "learning_rate": 4.792667856652478e-05, "loss": 2.38, "step": 9560 }, { "epoch": 0.44, "learning_rate": 4.7924390132271504e-05, "loss": 2.4158, "step": 9570 }, { "epoch": 0.44, "learning_rate": 4.792210169801822e-05, "loss": 2.5125, "step": 9580 }, { "epoch": 0.44, "learning_rate": 4.791981326376493e-05, "loss": 2.5445, "step": 9590 }, { "epoch": 0.44, "learning_rate": 4.791752482951165e-05, "loss": 2.5762, "step": 9600 }, { "epoch": 0.44, "learning_rate": 4.791523639525837e-05, "loss": 2.2317, "step": 9610 }, { "epoch": 0.44, "learning_rate": 4.791294796100508e-05, "loss": 2.5806, "step": 9620 }, { "epoch": 0.44, "learning_rate": 4.79106595267518e-05, "loss": 2.3484, "step": 9630 }, { "epoch": 0.44, "learning_rate": 4.7908371092498516e-05, "loss": 2.5404, "step": 9640 }, { "epoch": 0.44, "learning_rate": 4.790608265824523e-05, "loss": 2.382, "step": 9650 }, { "epoch": 0.44, "learning_rate": 4.790379422399195e-05, "loss": 2.5583, "step": 9660 }, { "epoch": 0.44, "learning_rate": 4.7901505789738665e-05, "loss": 2.4588, "step": 9670 }, { "epoch": 0.44, "learning_rate": 4.789921735548538e-05, "loss": 2.6046, "step": 9680 }, { "epoch": 0.44, "learning_rate": 4.7896928921232094e-05, "loss": 2.4481, "step": 9690 }, { "epoch": 0.44, "learning_rate": 4.789464048697881e-05, "loss": 2.4581, "step": 9700 }, { "epoch": 0.44, "learning_rate": 4.789235205272553e-05, "loss": 2.4924, "step": 9710 }, { "epoch": 0.44, "learning_rate": 4.789006361847224e-05, "loss": 2.6689, "step": 9720 }, { "epoch": 0.44, "learning_rate": 4.788777518421896e-05, "loss": 2.5128, "step": 9730 }, { "epoch": 0.44, "learning_rate": 4.788548674996568e-05, "loss": 2.4566, "step": 9740 }, { "epoch": 0.45, "learning_rate": 4.788319831571239e-05, "loss": 2.4166, "step": 9750 }, { "epoch": 0.45, "learning_rate": 4.7880909881459106e-05, "loss": 2.4673, "step": 9760 }, { "epoch": 0.45, "learning_rate": 4.787862144720583e-05, "loss": 2.4211, "step": 9770 }, { "epoch": 0.45, "learning_rate": 4.787633301295254e-05, "loss": 2.5236, "step": 9780 }, { "epoch": 0.45, "learning_rate": 4.7874044578699255e-05, "loss": 2.7309, "step": 9790 }, { "epoch": 0.45, "learning_rate": 4.787175614444597e-05, "loss": 2.4628, "step": 9800 }, { "epoch": 0.45, "learning_rate": 4.786946771019269e-05, "loss": 2.3173, "step": 9810 }, { "epoch": 0.45, "learning_rate": 4.7867179275939404e-05, "loss": 2.669, "step": 9820 }, { "epoch": 0.45, "learning_rate": 4.786489084168612e-05, "loss": 2.4429, "step": 9830 }, { "epoch": 0.45, "learning_rate": 4.786260240743284e-05, "loss": 2.5846, "step": 9840 }, { "epoch": 0.45, "learning_rate": 4.7860313973179554e-05, "loss": 2.7104, "step": 9850 }, { "epoch": 0.45, "learning_rate": 4.785802553892627e-05, "loss": 2.5761, "step": 9860 }, { "epoch": 0.45, "learning_rate": 4.785573710467299e-05, "loss": 2.601, "step": 9870 }, { "epoch": 0.45, "learning_rate": 4.78534486704197e-05, "loss": 2.4738, "step": 9880 }, { "epoch": 0.45, "learning_rate": 4.785116023616642e-05, "loss": 2.5727, "step": 9890 }, { "epoch": 0.45, "learning_rate": 4.784887180191313e-05, "loss": 2.4928, "step": 9900 }, { "epoch": 0.45, "learning_rate": 4.7846583367659845e-05, "loss": 2.4299, "step": 9910 }, { "epoch": 0.45, "learning_rate": 4.7844294933406566e-05, "loss": 2.3991, "step": 9920 }, { "epoch": 0.45, "learning_rate": 4.784200649915328e-05, "loss": 2.3427, "step": 9930 }, { "epoch": 0.45, "learning_rate": 4.7839718064899994e-05, "loss": 2.5343, "step": 9940 }, { "epoch": 0.45, "learning_rate": 4.7837429630646715e-05, "loss": 2.6352, "step": 9950 }, { "epoch": 0.45, "learning_rate": 4.783514119639343e-05, "loss": 2.5982, "step": 9960 }, { "epoch": 0.46, "learning_rate": 4.7832852762140144e-05, "loss": 2.5139, "step": 9970 }, { "epoch": 0.46, "learning_rate": 4.7830564327886864e-05, "loss": 2.5408, "step": 9980 }, { "epoch": 0.46, "learning_rate": 4.782827589363358e-05, "loss": 2.6568, "step": 9990 }, { "epoch": 0.46, "learning_rate": 4.782598745938029e-05, "loss": 2.6921, "step": 10000 }, { "epoch": 0.46, "learning_rate": 4.7823699025127014e-05, "loss": 2.5756, "step": 10010 }, { "epoch": 0.46, "learning_rate": 4.782141059087373e-05, "loss": 2.4315, "step": 10020 }, { "epoch": 0.46, "learning_rate": 4.781912215662044e-05, "loss": 2.2912, "step": 10030 }, { "epoch": 0.46, "learning_rate": 4.781683372236716e-05, "loss": 2.5367, "step": 10040 }, { "epoch": 0.46, "learning_rate": 4.781454528811388e-05, "loss": 2.678, "step": 10050 }, { "epoch": 0.46, "learning_rate": 4.781225685386059e-05, "loss": 2.6353, "step": 10060 }, { "epoch": 0.46, "learning_rate": 4.780996841960731e-05, "loss": 2.4273, "step": 10070 }, { "epoch": 0.46, "learning_rate": 4.7807679985354026e-05, "loss": 2.4503, "step": 10080 }, { "epoch": 0.46, "learning_rate": 4.7805391551100733e-05, "loss": 2.7163, "step": 10090 }, { "epoch": 0.46, "learning_rate": 4.7803103116847454e-05, "loss": 2.4007, "step": 10100 }, { "epoch": 0.46, "learning_rate": 4.780081468259417e-05, "loss": 2.5005, "step": 10110 }, { "epoch": 0.46, "learning_rate": 4.779852624834088e-05, "loss": 2.427, "step": 10120 }, { "epoch": 0.46, "learning_rate": 4.7796237814087604e-05, "loss": 2.4569, "step": 10130 }, { "epoch": 0.46, "learning_rate": 4.779394937983432e-05, "loss": 2.5551, "step": 10140 }, { "epoch": 0.46, "learning_rate": 4.779166094558103e-05, "loss": 2.3396, "step": 10150 }, { "epoch": 0.46, "learning_rate": 4.778937251132775e-05, "loss": 2.406, "step": 10160 }, { "epoch": 0.46, "learning_rate": 4.778708407707447e-05, "loss": 2.4444, "step": 10170 }, { "epoch": 0.46, "learning_rate": 4.778479564282118e-05, "loss": 2.4139, "step": 10180 }, { "epoch": 0.47, "learning_rate": 4.77825072085679e-05, "loss": 2.477, "step": 10190 }, { "epoch": 0.47, "learning_rate": 4.7780218774314616e-05, "loss": 2.5395, "step": 10200 }, { "epoch": 0.47, "learning_rate": 4.777793034006133e-05, "loss": 2.4311, "step": 10210 }, { "epoch": 0.47, "learning_rate": 4.777564190580805e-05, "loss": 2.533, "step": 10220 }, { "epoch": 0.47, "learning_rate": 4.7773353471554765e-05, "loss": 2.5356, "step": 10230 }, { "epoch": 0.47, "learning_rate": 4.777106503730148e-05, "loss": 2.4705, "step": 10240 }, { "epoch": 0.47, "learning_rate": 4.77687766030482e-05, "loss": 2.4284, "step": 10250 }, { "epoch": 0.47, "learning_rate": 4.7766488168794914e-05, "loss": 2.5561, "step": 10260 }, { "epoch": 0.47, "learning_rate": 4.776419973454163e-05, "loss": 2.5751, "step": 10270 }, { "epoch": 0.47, "learning_rate": 4.776191130028834e-05, "loss": 2.5288, "step": 10280 }, { "epoch": 0.47, "learning_rate": 4.775962286603506e-05, "loss": 2.6286, "step": 10290 }, { "epoch": 0.47, "learning_rate": 4.775733443178178e-05, "loss": 2.5164, "step": 10300 }, { "epoch": 0.47, "learning_rate": 4.775504599752849e-05, "loss": 2.4941, "step": 10310 }, { "epoch": 0.47, "learning_rate": 4.7752757563275206e-05, "loss": 2.5549, "step": 10320 }, { "epoch": 0.47, "learning_rate": 4.775046912902193e-05, "loss": 2.3522, "step": 10330 }, { "epoch": 0.47, "learning_rate": 4.774818069476864e-05, "loss": 2.4286, "step": 10340 }, { "epoch": 0.47, "learning_rate": 4.7745892260515355e-05, "loss": 2.3991, "step": 10350 }, { "epoch": 0.47, "learning_rate": 4.7743603826262076e-05, "loss": 2.2895, "step": 10360 }, { "epoch": 0.47, "learning_rate": 4.774131539200879e-05, "loss": 2.4932, "step": 10370 }, { "epoch": 0.47, "learning_rate": 4.7739026957755504e-05, "loss": 2.4832, "step": 10380 }, { "epoch": 0.47, "learning_rate": 4.7736738523502225e-05, "loss": 2.307, "step": 10390 }, { "epoch": 0.47, "learning_rate": 4.773445008924894e-05, "loss": 2.5521, "step": 10400 }, { "epoch": 0.48, "learning_rate": 4.7732161654995654e-05, "loss": 2.4974, "step": 10410 }, { "epoch": 0.48, "learning_rate": 4.7729873220742374e-05, "loss": 2.4039, "step": 10420 }, { "epoch": 0.48, "learning_rate": 4.772758478648909e-05, "loss": 2.6266, "step": 10430 }, { "epoch": 0.48, "learning_rate": 4.77252963522358e-05, "loss": 2.5492, "step": 10440 }, { "epoch": 0.48, "learning_rate": 4.7723007917982524e-05, "loss": 2.4616, "step": 10450 }, { "epoch": 0.48, "learning_rate": 4.772071948372924e-05, "loss": 2.4308, "step": 10460 }, { "epoch": 0.48, "learning_rate": 4.771843104947595e-05, "loss": 2.3388, "step": 10470 }, { "epoch": 0.48, "learning_rate": 4.7716142615222666e-05, "loss": 2.4147, "step": 10480 }, { "epoch": 0.48, "learning_rate": 4.771385418096938e-05, "loss": 2.5359, "step": 10490 }, { "epoch": 0.48, "learning_rate": 4.7711565746716094e-05, "loss": 2.4057, "step": 10500 }, { "epoch": 0.48, "learning_rate": 4.7709277312462815e-05, "loss": 2.4677, "step": 10510 }, { "epoch": 0.48, "learning_rate": 4.770698887820953e-05, "loss": 2.4335, "step": 10520 }, { "epoch": 0.48, "learning_rate": 4.7704700443956243e-05, "loss": 2.4574, "step": 10530 }, { "epoch": 0.48, "learning_rate": 4.7702412009702964e-05, "loss": 2.4509, "step": 10540 }, { "epoch": 0.48, "learning_rate": 4.770012357544968e-05, "loss": 2.2875, "step": 10550 }, { "epoch": 0.48, "learning_rate": 4.769783514119639e-05, "loss": 2.3658, "step": 10560 }, { "epoch": 0.48, "learning_rate": 4.7695546706943114e-05, "loss": 2.484, "step": 10570 }, { "epoch": 0.48, "learning_rate": 4.769325827268983e-05, "loss": 2.3696, "step": 10580 }, { "epoch": 0.48, "learning_rate": 4.769096983843654e-05, "loss": 2.6086, "step": 10590 }, { "epoch": 0.48, "learning_rate": 4.768868140418326e-05, "loss": 2.5265, "step": 10600 }, { "epoch": 0.48, "learning_rate": 4.768639296992998e-05, "loss": 2.4433, "step": 10610 }, { "epoch": 0.48, "learning_rate": 4.768410453567669e-05, "loss": 2.4744, "step": 10620 }, { "epoch": 0.49, "learning_rate": 4.768181610142341e-05, "loss": 2.4922, "step": 10630 }, { "epoch": 0.49, "learning_rate": 4.7679527667170126e-05, "loss": 2.5169, "step": 10640 }, { "epoch": 0.49, "learning_rate": 4.767723923291684e-05, "loss": 2.4901, "step": 10650 }, { "epoch": 0.49, "learning_rate": 4.767495079866356e-05, "loss": 2.4366, "step": 10660 }, { "epoch": 0.49, "learning_rate": 4.7672662364410275e-05, "loss": 2.5217, "step": 10670 }, { "epoch": 0.49, "learning_rate": 4.767037393015699e-05, "loss": 2.4166, "step": 10680 }, { "epoch": 0.49, "learning_rate": 4.7668085495903703e-05, "loss": 2.3496, "step": 10690 }, { "epoch": 0.49, "learning_rate": 4.766579706165042e-05, "loss": 2.2735, "step": 10700 }, { "epoch": 0.49, "learning_rate": 4.766350862739714e-05, "loss": 2.4062, "step": 10710 }, { "epoch": 0.49, "learning_rate": 4.766122019314385e-05, "loss": 2.4433, "step": 10720 }, { "epoch": 0.49, "learning_rate": 4.765893175889057e-05, "loss": 2.376, "step": 10730 }, { "epoch": 0.49, "learning_rate": 4.765664332463729e-05, "loss": 2.5182, "step": 10740 }, { "epoch": 0.49, "learning_rate": 4.7654354890384e-05, "loss": 2.4026, "step": 10750 }, { "epoch": 0.49, "learning_rate": 4.7652066456130716e-05, "loss": 2.4828, "step": 10760 }, { "epoch": 0.49, "learning_rate": 4.764977802187744e-05, "loss": 2.4481, "step": 10770 }, { "epoch": 0.49, "learning_rate": 4.764748958762415e-05, "loss": 2.539, "step": 10780 }, { "epoch": 0.49, "learning_rate": 4.7645201153370865e-05, "loss": 2.6396, "step": 10790 }, { "epoch": 0.49, "learning_rate": 4.7642912719117586e-05, "loss": 2.3183, "step": 10800 }, { "epoch": 0.49, "learning_rate": 4.76406242848643e-05, "loss": 2.4742, "step": 10810 }, { "epoch": 0.49, "learning_rate": 4.7638335850611014e-05, "loss": 2.4569, "step": 10820 }, { "epoch": 0.49, "learning_rate": 4.7636047416357735e-05, "loss": 2.3883, "step": 10830 }, { "epoch": 0.49, "learning_rate": 4.763375898210445e-05, "loss": 2.5301, "step": 10840 }, { "epoch": 0.5, "learning_rate": 4.7631470547851163e-05, "loss": 2.4566, "step": 10850 }, { "epoch": 0.5, "learning_rate": 4.7629182113597884e-05, "loss": 2.3007, "step": 10860 }, { "epoch": 0.5, "learning_rate": 4.76268936793446e-05, "loss": 2.2616, "step": 10870 }, { "epoch": 0.5, "learning_rate": 4.7624605245091306e-05, "loss": 2.3835, "step": 10880 }, { "epoch": 0.5, "learning_rate": 4.762231681083803e-05, "loss": 2.6098, "step": 10890 }, { "epoch": 0.5, "learning_rate": 4.762002837658474e-05, "loss": 2.3931, "step": 10900 }, { "epoch": 0.5, "learning_rate": 4.7617739942331455e-05, "loss": 2.4885, "step": 10910 }, { "epoch": 0.5, "learning_rate": 4.7615451508078176e-05, "loss": 2.4658, "step": 10920 }, { "epoch": 0.5, "learning_rate": 4.761316307382489e-05, "loss": 2.3699, "step": 10930 }, { "epoch": 0.5, "learning_rate": 4.7610874639571604e-05, "loss": 2.4824, "step": 10940 }, { "epoch": 0.5, "learning_rate": 4.7608586205318325e-05, "loss": 2.3861, "step": 10950 }, { "epoch": 0.5, "learning_rate": 4.760629777106504e-05, "loss": 2.4707, "step": 10960 }, { "epoch": 0.5, "learning_rate": 4.7604009336811753e-05, "loss": 2.6573, "step": 10970 }, { "epoch": 0.5, "learning_rate": 4.7601720902558474e-05, "loss": 2.3454, "step": 10980 }, { "epoch": 0.5, "learning_rate": 4.759943246830519e-05, "loss": 2.421, "step": 10990 }, { "epoch": 0.5, "learning_rate": 4.75971440340519e-05, "loss": 2.5401, "step": 11000 }, { "epoch": 0.5, "learning_rate": 4.7594855599798624e-05, "loss": 2.5423, "step": 11010 }, { "epoch": 0.5, "learning_rate": 4.759256716554534e-05, "loss": 2.61, "step": 11020 }, { "epoch": 0.5, "learning_rate": 4.759027873129205e-05, "loss": 2.3941, "step": 11030 }, { "epoch": 0.5, "learning_rate": 4.758799029703877e-05, "loss": 2.3131, "step": 11040 }, { "epoch": 0.5, "learning_rate": 4.758570186278549e-05, "loss": 2.3777, "step": 11050 }, { "epoch": 0.51, "learning_rate": 4.75834134285322e-05, "loss": 2.4009, "step": 11060 }, { "epoch": 0.51, "learning_rate": 4.7581124994278915e-05, "loss": 2.4921, "step": 11070 }, { "epoch": 0.51, "learning_rate": 4.757883656002563e-05, "loss": 2.2727, "step": 11080 }, { "epoch": 0.51, "learning_rate": 4.757654812577234e-05, "loss": 2.3952, "step": 11090 }, { "epoch": 0.51, "learning_rate": 4.7574259691519064e-05, "loss": 2.4766, "step": 11100 }, { "epoch": 0.51, "learning_rate": 4.757197125726578e-05, "loss": 2.5213, "step": 11110 }, { "epoch": 0.51, "learning_rate": 4.756968282301249e-05, "loss": 2.4827, "step": 11120 }, { "epoch": 0.51, "learning_rate": 4.7567394388759213e-05, "loss": 2.5186, "step": 11130 }, { "epoch": 0.51, "learning_rate": 4.756510595450593e-05, "loss": 2.2893, "step": 11140 }, { "epoch": 0.51, "learning_rate": 4.756281752025264e-05, "loss": 2.3513, "step": 11150 }, { "epoch": 0.51, "learning_rate": 4.756052908599936e-05, "loss": 2.4828, "step": 11160 }, { "epoch": 0.51, "learning_rate": 4.755824065174608e-05, "loss": 2.4114, "step": 11170 }, { "epoch": 0.51, "learning_rate": 4.755595221749279e-05, "loss": 2.6145, "step": 11180 }, { "epoch": 0.51, "learning_rate": 4.755366378323951e-05, "loss": 2.5496, "step": 11190 }, { "epoch": 0.51, "learning_rate": 4.7551375348986226e-05, "loss": 2.4833, "step": 11200 }, { "epoch": 0.51, "learning_rate": 4.754908691473294e-05, "loss": 2.5613, "step": 11210 }, { "epoch": 0.51, "learning_rate": 4.754679848047966e-05, "loss": 2.6483, "step": 11220 }, { "epoch": 0.51, "learning_rate": 4.7544510046226375e-05, "loss": 2.4704, "step": 11230 }, { "epoch": 0.51, "learning_rate": 4.754222161197309e-05, "loss": 2.3643, "step": 11240 }, { "epoch": 0.51, "learning_rate": 4.753993317771981e-05, "loss": 2.4422, "step": 11250 }, { "epoch": 0.51, "learning_rate": 4.7537644743466524e-05, "loss": 2.4202, "step": 11260 }, { "epoch": 0.51, "learning_rate": 4.753535630921324e-05, "loss": 2.3858, "step": 11270 }, { "epoch": 0.52, "learning_rate": 4.753306787495995e-05, "loss": 2.3994, "step": 11280 }, { "epoch": 0.52, "learning_rate": 4.753077944070667e-05, "loss": 2.2757, "step": 11290 }, { "epoch": 0.52, "learning_rate": 4.752849100645339e-05, "loss": 2.4172, "step": 11300 }, { "epoch": 0.52, "learning_rate": 4.75262025722001e-05, "loss": 2.6364, "step": 11310 }, { "epoch": 0.52, "learning_rate": 4.7523914137946816e-05, "loss": 2.4696, "step": 11320 }, { "epoch": 0.52, "learning_rate": 4.752162570369354e-05, "loss": 2.5582, "step": 11330 }, { "epoch": 0.52, "learning_rate": 4.751933726944025e-05, "loss": 2.4945, "step": 11340 }, { "epoch": 0.52, "learning_rate": 4.7517048835186965e-05, "loss": 2.4436, "step": 11350 }, { "epoch": 0.52, "learning_rate": 4.7514760400933686e-05, "loss": 2.2703, "step": 11360 }, { "epoch": 0.52, "learning_rate": 4.75124719666804e-05, "loss": 2.5689, "step": 11370 }, { "epoch": 0.52, "learning_rate": 4.7510183532427114e-05, "loss": 2.4244, "step": 11380 }, { "epoch": 0.52, "learning_rate": 4.7507895098173835e-05, "loss": 2.4548, "step": 11390 }, { "epoch": 0.52, "learning_rate": 4.750560666392055e-05, "loss": 2.4732, "step": 11400 }, { "epoch": 0.52, "learning_rate": 4.7503318229667263e-05, "loss": 2.4402, "step": 11410 }, { "epoch": 0.52, "learning_rate": 4.7501029795413984e-05, "loss": 2.3447, "step": 11420 }, { "epoch": 0.52, "learning_rate": 4.74987413611607e-05, "loss": 2.4685, "step": 11430 }, { "epoch": 0.52, "learning_rate": 4.749645292690741e-05, "loss": 2.2933, "step": 11440 }, { "epoch": 0.52, "learning_rate": 4.7494164492654133e-05, "loss": 2.4714, "step": 11450 }, { "epoch": 0.52, "learning_rate": 4.749187605840085e-05, "loss": 2.3394, "step": 11460 }, { "epoch": 0.52, "learning_rate": 4.7489587624147555e-05, "loss": 2.5297, "step": 11470 }, { "epoch": 0.52, "learning_rate": 4.7487299189894276e-05, "loss": 2.4085, "step": 11480 }, { "epoch": 0.52, "learning_rate": 4.748501075564099e-05, "loss": 2.456, "step": 11490 }, { "epoch": 0.53, "learning_rate": 4.7482722321387704e-05, "loss": 2.4312, "step": 11500 }, { "epoch": 0.53, "learning_rate": 4.7480433887134425e-05, "loss": 2.4696, "step": 11510 }, { "epoch": 0.53, "learning_rate": 4.747814545288114e-05, "loss": 2.3348, "step": 11520 }, { "epoch": 0.53, "learning_rate": 4.747585701862785e-05, "loss": 2.4323, "step": 11530 }, { "epoch": 0.53, "learning_rate": 4.7473568584374574e-05, "loss": 2.3642, "step": 11540 }, { "epoch": 0.53, "learning_rate": 4.747128015012129e-05, "loss": 2.4267, "step": 11550 }, { "epoch": 0.53, "learning_rate": 4.7468991715868e-05, "loss": 2.3515, "step": 11560 }, { "epoch": 0.53, "learning_rate": 4.7466703281614723e-05, "loss": 2.3153, "step": 11570 }, { "epoch": 0.53, "learning_rate": 4.746441484736144e-05, "loss": 2.3999, "step": 11580 }, { "epoch": 0.53, "learning_rate": 4.746212641310815e-05, "loss": 2.2643, "step": 11590 }, { "epoch": 0.53, "learning_rate": 4.745983797885487e-05, "loss": 2.4395, "step": 11600 }, { "epoch": 0.53, "learning_rate": 4.745754954460159e-05, "loss": 2.549, "step": 11610 }, { "epoch": 0.53, "learning_rate": 4.74552611103483e-05, "loss": 2.4347, "step": 11620 }, { "epoch": 0.53, "learning_rate": 4.745297267609502e-05, "loss": 2.4279, "step": 11630 }, { "epoch": 0.53, "learning_rate": 4.7450684241841736e-05, "loss": 2.4202, "step": 11640 }, { "epoch": 0.53, "learning_rate": 4.744839580758845e-05, "loss": 2.3504, "step": 11650 }, { "epoch": 0.53, "learning_rate": 4.744610737333517e-05, "loss": 2.5737, "step": 11660 }, { "epoch": 0.53, "learning_rate": 4.744381893908188e-05, "loss": 2.3118, "step": 11670 }, { "epoch": 0.53, "learning_rate": 4.74415305048286e-05, "loss": 2.2911, "step": 11680 }, { "epoch": 0.53, "learning_rate": 4.743924207057531e-05, "loss": 2.6042, "step": 11690 }, { "epoch": 0.53, "learning_rate": 4.743695363632203e-05, "loss": 2.4479, "step": 11700 }, { "epoch": 0.53, "learning_rate": 4.743466520206875e-05, "loss": 2.4711, "step": 11710 }, { "epoch": 0.54, "learning_rate": 4.743237676781546e-05, "loss": 2.5825, "step": 11720 }, { "epoch": 0.54, "learning_rate": 4.743008833356218e-05, "loss": 2.424, "step": 11730 }, { "epoch": 0.54, "learning_rate": 4.74277998993089e-05, "loss": 2.4019, "step": 11740 }, { "epoch": 0.54, "learning_rate": 4.742551146505561e-05, "loss": 2.4366, "step": 11750 }, { "epoch": 0.54, "learning_rate": 4.7423223030802326e-05, "loss": 2.4076, "step": 11760 }, { "epoch": 0.54, "learning_rate": 4.742093459654905e-05, "loss": 2.4222, "step": 11770 }, { "epoch": 0.54, "learning_rate": 4.741864616229576e-05, "loss": 2.4884, "step": 11780 }, { "epoch": 0.54, "learning_rate": 4.7416357728042475e-05, "loss": 2.2208, "step": 11790 }, { "epoch": 0.54, "learning_rate": 4.7414069293789196e-05, "loss": 2.3723, "step": 11800 }, { "epoch": 0.54, "learning_rate": 4.741178085953591e-05, "loss": 2.4978, "step": 11810 }, { "epoch": 0.54, "learning_rate": 4.7409492425282624e-05, "loss": 2.447, "step": 11820 }, { "epoch": 0.54, "learning_rate": 4.7407203991029345e-05, "loss": 2.3151, "step": 11830 }, { "epoch": 0.54, "learning_rate": 4.740491555677606e-05, "loss": 2.3134, "step": 11840 }, { "epoch": 0.54, "learning_rate": 4.740262712252277e-05, "loss": 2.5769, "step": 11850 }, { "epoch": 0.54, "learning_rate": 4.740033868826949e-05, "loss": 2.5419, "step": 11860 }, { "epoch": 0.54, "learning_rate": 4.73980502540162e-05, "loss": 2.61, "step": 11870 }, { "epoch": 0.54, "learning_rate": 4.7395761819762916e-05, "loss": 2.4659, "step": 11880 }, { "epoch": 0.54, "learning_rate": 4.739347338550964e-05, "loss": 2.3641, "step": 11890 }, { "epoch": 0.54, "learning_rate": 4.739118495125635e-05, "loss": 2.3181, "step": 11900 }, { "epoch": 0.54, "learning_rate": 4.7388896517003065e-05, "loss": 2.5049, "step": 11910 }, { "epoch": 0.54, "learning_rate": 4.7386608082749786e-05, "loss": 2.4481, "step": 11920 }, { "epoch": 0.54, "learning_rate": 4.73843196484965e-05, "loss": 2.2855, "step": 11930 }, { "epoch": 0.55, "learning_rate": 4.7382031214243214e-05, "loss": 2.5272, "step": 11940 }, { "epoch": 0.55, "learning_rate": 4.7379742779989935e-05, "loss": 2.4384, "step": 11950 }, { "epoch": 0.55, "learning_rate": 4.737745434573665e-05, "loss": 2.3597, "step": 11960 }, { "epoch": 0.55, "learning_rate": 4.737516591148336e-05, "loss": 2.4213, "step": 11970 }, { "epoch": 0.55, "learning_rate": 4.7372877477230084e-05, "loss": 2.3495, "step": 11980 }, { "epoch": 0.55, "learning_rate": 4.73705890429768e-05, "loss": 2.3827, "step": 11990 }, { "epoch": 0.55, "learning_rate": 4.736830060872351e-05, "loss": 2.5026, "step": 12000 }, { "epoch": 0.55, "learning_rate": 4.736601217447023e-05, "loss": 2.5919, "step": 12010 }, { "epoch": 0.55, "learning_rate": 4.736372374021695e-05, "loss": 2.5067, "step": 12020 }, { "epoch": 0.55, "learning_rate": 4.736143530596366e-05, "loss": 2.3059, "step": 12030 }, { "epoch": 0.55, "learning_rate": 4.735914687171038e-05, "loss": 2.4974, "step": 12040 }, { "epoch": 0.55, "learning_rate": 4.73568584374571e-05, "loss": 2.5015, "step": 12050 }, { "epoch": 0.55, "learning_rate": 4.735457000320381e-05, "loss": 2.5349, "step": 12060 }, { "epoch": 0.55, "learning_rate": 4.7352281568950525e-05, "loss": 2.4997, "step": 12070 }, { "epoch": 0.55, "learning_rate": 4.734999313469724e-05, "loss": 2.4808, "step": 12080 }, { "epoch": 0.55, "learning_rate": 4.734770470044396e-05, "loss": 2.4436, "step": 12090 }, { "epoch": 0.55, "learning_rate": 4.7345416266190674e-05, "loss": 2.4498, "step": 12100 }, { "epoch": 0.55, "learning_rate": 4.734312783193739e-05, "loss": 2.5492, "step": 12110 }, { "epoch": 0.55, "learning_rate": 4.734083939768411e-05, "loss": 2.3897, "step": 12120 }, { "epoch": 0.55, "learning_rate": 4.733855096343082e-05, "loss": 2.3728, "step": 12130 }, { "epoch": 0.55, "learning_rate": 4.733626252917754e-05, "loss": 2.3654, "step": 12140 }, { "epoch": 0.55, "learning_rate": 4.733397409492425e-05, "loss": 2.3108, "step": 12150 }, { "epoch": 0.56, "learning_rate": 4.733168566067097e-05, "loss": 2.2933, "step": 12160 }, { "epoch": 0.56, "learning_rate": 4.732939722641769e-05, "loss": 2.5426, "step": 12170 }, { "epoch": 0.56, "learning_rate": 4.73271087921644e-05, "loss": 2.3619, "step": 12180 }, { "epoch": 0.56, "learning_rate": 4.732482035791112e-05, "loss": 2.4508, "step": 12190 }, { "epoch": 0.56, "learning_rate": 4.7322531923657836e-05, "loss": 2.4075, "step": 12200 }, { "epoch": 0.56, "learning_rate": 4.732024348940455e-05, "loss": 2.3518, "step": 12210 }, { "epoch": 0.56, "learning_rate": 4.731795505515127e-05, "loss": 2.2717, "step": 12220 }, { "epoch": 0.56, "learning_rate": 4.7315666620897985e-05, "loss": 2.4343, "step": 12230 }, { "epoch": 0.56, "learning_rate": 4.73133781866447e-05, "loss": 2.3564, "step": 12240 }, { "epoch": 0.56, "learning_rate": 4.731108975239142e-05, "loss": 2.5528, "step": 12250 }, { "epoch": 0.56, "learning_rate": 4.730880131813813e-05, "loss": 2.5302, "step": 12260 }, { "epoch": 0.56, "learning_rate": 4.730651288388485e-05, "loss": 2.4023, "step": 12270 }, { "epoch": 0.56, "learning_rate": 4.730422444963156e-05, "loss": 2.3957, "step": 12280 }, { "epoch": 0.56, "learning_rate": 4.7301936015378277e-05, "loss": 2.4041, "step": 12290 }, { "epoch": 0.56, "learning_rate": 4.7299647581125e-05, "loss": 2.591, "step": 12300 }, { "epoch": 0.56, "learning_rate": 4.729735914687171e-05, "loss": 2.4178, "step": 12310 }, { "epoch": 0.56, "learning_rate": 4.7295070712618426e-05, "loss": 2.5649, "step": 12320 }, { "epoch": 0.56, "learning_rate": 4.729278227836515e-05, "loss": 2.4743, "step": 12330 }, { "epoch": 0.56, "learning_rate": 4.729049384411186e-05, "loss": 2.5173, "step": 12340 }, { "epoch": 0.56, "learning_rate": 4.7288205409858575e-05, "loss": 2.2351, "step": 12350 }, { "epoch": 0.56, "learning_rate": 4.7285916975605296e-05, "loss": 2.3114, "step": 12360 }, { "epoch": 0.56, "learning_rate": 4.728362854135201e-05, "loss": 2.4263, "step": 12370 }, { "epoch": 0.57, "learning_rate": 4.7281340107098724e-05, "loss": 2.5831, "step": 12380 }, { "epoch": 0.57, "learning_rate": 4.7279051672845445e-05, "loss": 2.5293, "step": 12390 }, { "epoch": 0.57, "learning_rate": 4.727676323859216e-05, "loss": 2.5993, "step": 12400 }, { "epoch": 0.57, "learning_rate": 4.727447480433887e-05, "loss": 2.4313, "step": 12410 }, { "epoch": 0.57, "learning_rate": 4.7272186370085594e-05, "loss": 2.531, "step": 12420 }, { "epoch": 0.57, "learning_rate": 4.726989793583231e-05, "loss": 2.3311, "step": 12430 }, { "epoch": 0.57, "learning_rate": 4.726760950157902e-05, "loss": 2.5777, "step": 12440 }, { "epoch": 0.57, "learning_rate": 4.726532106732574e-05, "loss": 2.6227, "step": 12450 }, { "epoch": 0.57, "learning_rate": 4.726303263307245e-05, "loss": 2.3775, "step": 12460 }, { "epoch": 0.57, "learning_rate": 4.7260744198819165e-05, "loss": 2.4367, "step": 12470 }, { "epoch": 0.57, "learning_rate": 4.7258455764565886e-05, "loss": 2.5348, "step": 12480 }, { "epoch": 0.57, "learning_rate": 4.72561673303126e-05, "loss": 2.5143, "step": 12490 }, { "epoch": 0.57, "learning_rate": 4.7253878896059314e-05, "loss": 2.5832, "step": 12500 }, { "epoch": 0.57, "learning_rate": 4.7251590461806035e-05, "loss": 2.4652, "step": 12510 }, { "epoch": 0.57, "learning_rate": 4.724930202755275e-05, "loss": 2.4311, "step": 12520 }, { "epoch": 0.57, "learning_rate": 4.724701359329946e-05, "loss": 2.457, "step": 12530 }, { "epoch": 0.57, "learning_rate": 4.7244725159046184e-05, "loss": 2.2281, "step": 12540 }, { "epoch": 0.57, "learning_rate": 4.72424367247929e-05, "loss": 2.5141, "step": 12550 }, { "epoch": 0.57, "learning_rate": 4.724014829053961e-05, "loss": 2.3885, "step": 12560 }, { "epoch": 0.57, "learning_rate": 4.723785985628633e-05, "loss": 2.6585, "step": 12570 }, { "epoch": 0.57, "learning_rate": 4.723557142203305e-05, "loss": 2.4089, "step": 12580 }, { "epoch": 0.57, "learning_rate": 4.723328298777976e-05, "loss": 2.4899, "step": 12590 }, { "epoch": 0.58, "learning_rate": 4.723099455352648e-05, "loss": 2.4599, "step": 12600 }, { "epoch": 0.58, "learning_rate": 4.7228706119273197e-05, "loss": 2.3667, "step": 12610 }, { "epoch": 0.58, "learning_rate": 4.722641768501991e-05, "loss": 2.3911, "step": 12620 }, { "epoch": 0.58, "learning_rate": 4.722412925076663e-05, "loss": 2.3319, "step": 12630 }, { "epoch": 0.58, "learning_rate": 4.7221840816513346e-05, "loss": 2.5307, "step": 12640 }, { "epoch": 0.58, "learning_rate": 4.721955238226006e-05, "loss": 2.3653, "step": 12650 }, { "epoch": 0.58, "learning_rate": 4.7217263948006774e-05, "loss": 2.4029, "step": 12660 }, { "epoch": 0.58, "learning_rate": 4.721497551375349e-05, "loss": 2.4838, "step": 12670 }, { "epoch": 0.58, "learning_rate": 4.721268707950021e-05, "loss": 2.5288, "step": 12680 }, { "epoch": 0.58, "learning_rate": 4.721039864524692e-05, "loss": 2.3846, "step": 12690 }, { "epoch": 0.58, "learning_rate": 4.720811021099364e-05, "loss": 2.4621, "step": 12700 }, { "epoch": 0.58, "learning_rate": 4.720582177674036e-05, "loss": 2.426, "step": 12710 }, { "epoch": 0.58, "learning_rate": 4.720353334248707e-05, "loss": 2.4894, "step": 12720 }, { "epoch": 0.58, "learning_rate": 4.7201244908233787e-05, "loss": 2.5271, "step": 12730 }, { "epoch": 0.58, "learning_rate": 4.719895647398051e-05, "loss": 2.4397, "step": 12740 }, { "epoch": 0.58, "learning_rate": 4.719666803972722e-05, "loss": 2.6166, "step": 12750 }, { "epoch": 0.58, "learning_rate": 4.7194379605473936e-05, "loss": 2.4764, "step": 12760 }, { "epoch": 0.58, "learning_rate": 4.7192091171220657e-05, "loss": 2.4938, "step": 12770 }, { "epoch": 0.58, "learning_rate": 4.718980273696737e-05, "loss": 2.4394, "step": 12780 }, { "epoch": 0.58, "learning_rate": 4.7187514302714085e-05, "loss": 2.4149, "step": 12790 }, { "epoch": 0.58, "learning_rate": 4.7185225868460806e-05, "loss": 2.5059, "step": 12800 }, { "epoch": 0.58, "learning_rate": 4.718293743420752e-05, "loss": 2.5776, "step": 12810 }, { "epoch": 0.59, "learning_rate": 4.7180648999954234e-05, "loss": 2.5157, "step": 12820 }, { "epoch": 0.59, "learning_rate": 4.7178360565700955e-05, "loss": 2.3999, "step": 12830 }, { "epoch": 0.59, "learning_rate": 4.717607213144767e-05, "loss": 2.4311, "step": 12840 }, { "epoch": 0.59, "learning_rate": 4.7173783697194376e-05, "loss": 2.4564, "step": 12850 }, { "epoch": 0.59, "learning_rate": 4.71714952629411e-05, "loss": 2.4986, "step": 12860 }, { "epoch": 0.59, "learning_rate": 4.716920682868781e-05, "loss": 2.4192, "step": 12870 }, { "epoch": 0.59, "learning_rate": 4.7166918394434526e-05, "loss": 2.4194, "step": 12880 }, { "epoch": 0.59, "learning_rate": 4.7164629960181247e-05, "loss": 2.3728, "step": 12890 }, { "epoch": 0.59, "learning_rate": 4.716234152592796e-05, "loss": 2.511, "step": 12900 }, { "epoch": 0.59, "learning_rate": 4.7160053091674675e-05, "loss": 2.3901, "step": 12910 }, { "epoch": 0.59, "learning_rate": 4.7157764657421396e-05, "loss": 2.4688, "step": 12920 }, { "epoch": 0.59, "learning_rate": 4.715547622316811e-05, "loss": 2.3671, "step": 12930 }, { "epoch": 0.59, "learning_rate": 4.7153187788914824e-05, "loss": 2.3911, "step": 12940 }, { "epoch": 0.59, "learning_rate": 4.7150899354661545e-05, "loss": 2.4779, "step": 12950 }, { "epoch": 0.59, "learning_rate": 4.714861092040826e-05, "loss": 2.3795, "step": 12960 }, { "epoch": 0.59, "learning_rate": 4.714632248615497e-05, "loss": 2.5118, "step": 12970 }, { "epoch": 0.59, "learning_rate": 4.7144034051901694e-05, "loss": 2.2978, "step": 12980 }, { "epoch": 0.59, "learning_rate": 4.714174561764841e-05, "loss": 2.3281, "step": 12990 }, { "epoch": 0.59, "learning_rate": 4.713945718339512e-05, "loss": 2.3664, "step": 13000 }, { "epoch": 0.59, "learning_rate": 4.713716874914184e-05, "loss": 2.3019, "step": 13010 }, { "epoch": 0.59, "learning_rate": 4.713488031488856e-05, "loss": 2.3822, "step": 13020 }, { "epoch": 0.59, "learning_rate": 4.713259188063527e-05, "loss": 2.2404, "step": 13030 }, { "epoch": 0.6, "learning_rate": 4.713030344638199e-05, "loss": 2.4952, "step": 13040 }, { "epoch": 0.6, "learning_rate": 4.71280150121287e-05, "loss": 2.3787, "step": 13050 }, { "epoch": 0.6, "learning_rate": 4.712572657787542e-05, "loss": 2.468, "step": 13060 }, { "epoch": 0.6, "learning_rate": 4.7123438143622135e-05, "loss": 2.5079, "step": 13070 }, { "epoch": 0.6, "learning_rate": 4.712114970936885e-05, "loss": 2.4373, "step": 13080 }, { "epoch": 0.6, "learning_rate": 4.711886127511557e-05, "loss": 2.4144, "step": 13090 }, { "epoch": 0.6, "learning_rate": 4.7116572840862284e-05, "loss": 2.3762, "step": 13100 }, { "epoch": 0.6, "learning_rate": 4.7114284406609e-05, "loss": 2.613, "step": 13110 }, { "epoch": 0.6, "learning_rate": 4.711199597235572e-05, "loss": 2.3593, "step": 13120 }, { "epoch": 0.6, "learning_rate": 4.710970753810243e-05, "loss": 2.2552, "step": 13130 }, { "epoch": 0.6, "learning_rate": 4.710741910384915e-05, "loss": 2.4709, "step": 13140 }, { "epoch": 0.6, "learning_rate": 4.710513066959587e-05, "loss": 2.4704, "step": 13150 }, { "epoch": 0.6, "learning_rate": 4.710284223534258e-05, "loss": 2.34, "step": 13160 }, { "epoch": 0.6, "learning_rate": 4.7100553801089296e-05, "loss": 2.2642, "step": 13170 }, { "epoch": 0.6, "learning_rate": 4.709826536683602e-05, "loss": 2.4649, "step": 13180 }, { "epoch": 0.6, "learning_rate": 4.709597693258273e-05, "loss": 2.2601, "step": 13190 }, { "epoch": 0.6, "learning_rate": 4.7093688498329446e-05, "loss": 2.2888, "step": 13200 }, { "epoch": 0.6, "learning_rate": 4.7091400064076167e-05, "loss": 2.3968, "step": 13210 }, { "epoch": 0.6, "learning_rate": 4.708911162982288e-05, "loss": 2.5123, "step": 13220 }, { "epoch": 0.6, "learning_rate": 4.7086823195569595e-05, "loss": 2.3063, "step": 13230 }, { "epoch": 0.6, "learning_rate": 4.708453476131631e-05, "loss": 2.2631, "step": 13240 }, { "epoch": 0.61, "learning_rate": 4.708224632706302e-05, "loss": 2.4412, "step": 13250 }, { "epoch": 0.61, "learning_rate": 4.707995789280974e-05, "loss": 2.3373, "step": 13260 }, { "epoch": 0.61, "learning_rate": 4.707766945855646e-05, "loss": 2.5071, "step": 13270 }, { "epoch": 0.61, "learning_rate": 4.707538102430317e-05, "loss": 2.6473, "step": 13280 }, { "epoch": 0.61, "learning_rate": 4.7073092590049886e-05, "loss": 2.4809, "step": 13290 }, { "epoch": 0.61, "learning_rate": 4.707080415579661e-05, "loss": 2.371, "step": 13300 }, { "epoch": 0.61, "learning_rate": 4.706851572154332e-05, "loss": 2.5814, "step": 13310 }, { "epoch": 0.61, "learning_rate": 4.7066227287290036e-05, "loss": 2.4376, "step": 13320 }, { "epoch": 0.61, "learning_rate": 4.7063938853036757e-05, "loss": 2.4493, "step": 13330 }, { "epoch": 0.61, "learning_rate": 4.706165041878347e-05, "loss": 2.2823, "step": 13340 }, { "epoch": 0.61, "learning_rate": 4.7059361984530185e-05, "loss": 2.4304, "step": 13350 }, { "epoch": 0.61, "learning_rate": 4.7057073550276906e-05, "loss": 2.4563, "step": 13360 }, { "epoch": 0.61, "learning_rate": 4.705478511602362e-05, "loss": 2.3565, "step": 13370 }, { "epoch": 0.61, "learning_rate": 4.7052496681770334e-05, "loss": 2.3452, "step": 13380 }, { "epoch": 0.61, "learning_rate": 4.7050208247517055e-05, "loss": 2.4727, "step": 13390 }, { "epoch": 0.61, "learning_rate": 4.704791981326377e-05, "loss": 2.3361, "step": 13400 }, { "epoch": 0.61, "learning_rate": 4.704563137901048e-05, "loss": 2.4596, "step": 13410 }, { "epoch": 0.61, "learning_rate": 4.7043342944757204e-05, "loss": 2.3252, "step": 13420 }, { "epoch": 0.61, "learning_rate": 4.704105451050392e-05, "loss": 2.3091, "step": 13430 }, { "epoch": 0.61, "learning_rate": 4.7038766076250626e-05, "loss": 2.4012, "step": 13440 }, { "epoch": 0.61, "learning_rate": 4.7036477641997346e-05, "loss": 2.4278, "step": 13450 }, { "epoch": 0.61, "learning_rate": 4.703418920774406e-05, "loss": 2.2113, "step": 13460 }, { "epoch": 0.62, "learning_rate": 4.7031900773490775e-05, "loss": 2.3031, "step": 13470 }, { "epoch": 0.62, "learning_rate": 4.7029612339237496e-05, "loss": 2.388, "step": 13480 }, { "epoch": 0.62, "learning_rate": 4.702732390498421e-05, "loss": 2.3116, "step": 13490 }, { "epoch": 0.62, "learning_rate": 4.7025035470730924e-05, "loss": 2.4656, "step": 13500 }, { "epoch": 0.62, "learning_rate": 4.7022747036477645e-05, "loss": 2.381, "step": 13510 }, { "epoch": 0.62, "learning_rate": 4.702045860222436e-05, "loss": 2.3562, "step": 13520 }, { "epoch": 0.62, "learning_rate": 4.701817016797107e-05, "loss": 2.4568, "step": 13530 }, { "epoch": 0.62, "learning_rate": 4.7015881733717794e-05, "loss": 2.522, "step": 13540 }, { "epoch": 0.62, "learning_rate": 4.701359329946451e-05, "loss": 2.5587, "step": 13550 }, { "epoch": 0.62, "learning_rate": 4.701130486521122e-05, "loss": 2.5116, "step": 13560 }, { "epoch": 0.62, "learning_rate": 4.700901643095794e-05, "loss": 2.3076, "step": 13570 }, { "epoch": 0.62, "learning_rate": 4.700672799670466e-05, "loss": 2.5793, "step": 13580 }, { "epoch": 0.62, "learning_rate": 4.700443956245137e-05, "loss": 2.536, "step": 13590 }, { "epoch": 0.62, "learning_rate": 4.700215112819809e-05, "loss": 2.3936, "step": 13600 }, { "epoch": 0.62, "learning_rate": 4.6999862693944806e-05, "loss": 2.4403, "step": 13610 }, { "epoch": 0.62, "learning_rate": 4.699757425969152e-05, "loss": 2.4257, "step": 13620 }, { "epoch": 0.62, "learning_rate": 4.699528582543824e-05, "loss": 2.4848, "step": 13630 }, { "epoch": 0.62, "learning_rate": 4.699299739118495e-05, "loss": 2.3471, "step": 13640 }, { "epoch": 0.62, "learning_rate": 4.699070895693167e-05, "loss": 2.3906, "step": 13650 }, { "epoch": 0.62, "learning_rate": 4.6988420522678384e-05, "loss": 2.4023, "step": 13660 }, { "epoch": 0.62, "learning_rate": 4.69861320884251e-05, "loss": 2.4061, "step": 13670 }, { "epoch": 0.62, "learning_rate": 4.698384365417182e-05, "loss": 2.3973, "step": 13680 }, { "epoch": 0.63, "learning_rate": 4.698155521991853e-05, "loss": 2.2813, "step": 13690 }, { "epoch": 0.63, "learning_rate": 4.697926678566525e-05, "loss": 2.3191, "step": 13700 }, { "epoch": 0.63, "learning_rate": 4.697697835141197e-05, "loss": 2.4205, "step": 13710 }, { "epoch": 0.63, "learning_rate": 4.697468991715868e-05, "loss": 2.3915, "step": 13720 }, { "epoch": 0.63, "learning_rate": 4.6972401482905396e-05, "loss": 2.6193, "step": 13730 }, { "epoch": 0.63, "learning_rate": 4.697011304865212e-05, "loss": 2.3897, "step": 13740 }, { "epoch": 0.63, "learning_rate": 4.696782461439883e-05, "loss": 2.3718, "step": 13750 }, { "epoch": 0.63, "learning_rate": 4.6965536180145546e-05, "loss": 2.3739, "step": 13760 }, { "epoch": 0.63, "learning_rate": 4.6963247745892266e-05, "loss": 2.4432, "step": 13770 }, { "epoch": 0.63, "learning_rate": 4.696095931163898e-05, "loss": 2.306, "step": 13780 }, { "epoch": 0.63, "learning_rate": 4.6958670877385695e-05, "loss": 2.3025, "step": 13790 }, { "epoch": 0.63, "learning_rate": 4.6956382443132416e-05, "loss": 2.2138, "step": 13800 }, { "epoch": 0.63, "learning_rate": 4.695409400887913e-05, "loss": 2.4047, "step": 13810 }, { "epoch": 0.63, "learning_rate": 4.6951805574625844e-05, "loss": 2.397, "step": 13820 }, { "epoch": 0.63, "learning_rate": 4.6949517140372565e-05, "loss": 2.3772, "step": 13830 }, { "epoch": 0.63, "learning_rate": 4.694722870611927e-05, "loss": 2.295, "step": 13840 }, { "epoch": 0.63, "learning_rate": 4.6944940271865986e-05, "loss": 2.2977, "step": 13850 }, { "epoch": 0.63, "learning_rate": 4.694265183761271e-05, "loss": 2.4982, "step": 13860 }, { "epoch": 0.63, "learning_rate": 4.694036340335942e-05, "loss": 2.2954, "step": 13870 }, { "epoch": 0.63, "learning_rate": 4.6938074969106135e-05, "loss": 2.3595, "step": 13880 }, { "epoch": 0.63, "learning_rate": 4.6935786534852856e-05, "loss": 2.3563, "step": 13890 }, { "epoch": 0.63, "learning_rate": 4.693349810059957e-05, "loss": 2.3239, "step": 13900 }, { "epoch": 0.64, "learning_rate": 4.6931209666346285e-05, "loss": 2.462, "step": 13910 }, { "epoch": 0.64, "learning_rate": 4.6928921232093006e-05, "loss": 2.2887, "step": 13920 }, { "epoch": 0.64, "learning_rate": 4.692663279783972e-05, "loss": 2.3845, "step": 13930 }, { "epoch": 0.64, "learning_rate": 4.6924344363586434e-05, "loss": 2.38, "step": 13940 }, { "epoch": 0.64, "learning_rate": 4.6922055929333155e-05, "loss": 2.2663, "step": 13950 }, { "epoch": 0.64, "learning_rate": 4.691976749507987e-05, "loss": 2.4002, "step": 13960 }, { "epoch": 0.64, "learning_rate": 4.691747906082658e-05, "loss": 2.3482, "step": 13970 }, { "epoch": 0.64, "learning_rate": 4.6915190626573304e-05, "loss": 2.4592, "step": 13980 }, { "epoch": 0.64, "learning_rate": 4.691290219232002e-05, "loss": 2.4105, "step": 13990 }, { "epoch": 0.64, "learning_rate": 4.691061375806673e-05, "loss": 2.3587, "step": 14000 }, { "epoch": 0.64, "learning_rate": 4.690832532381345e-05, "loss": 2.4029, "step": 14010 }, { "epoch": 0.64, "learning_rate": 4.690603688956017e-05, "loss": 2.5026, "step": 14020 }, { "epoch": 0.64, "learning_rate": 4.690374845530688e-05, "loss": 2.4067, "step": 14030 }, { "epoch": 0.64, "learning_rate": 4.6901460021053596e-05, "loss": 2.4352, "step": 14040 }, { "epoch": 0.64, "learning_rate": 4.689917158680031e-05, "loss": 2.2441, "step": 14050 }, { "epoch": 0.64, "learning_rate": 4.689688315254703e-05, "loss": 2.4022, "step": 14060 }, { "epoch": 0.64, "learning_rate": 4.6894594718293745e-05, "loss": 2.2769, "step": 14070 }, { "epoch": 0.64, "learning_rate": 4.689230628404046e-05, "loss": 2.5606, "step": 14080 }, { "epoch": 0.64, "learning_rate": 4.689001784978718e-05, "loss": 2.3677, "step": 14090 }, { "epoch": 0.64, "learning_rate": 4.6887729415533894e-05, "loss": 2.3254, "step": 14100 }, { "epoch": 0.64, "learning_rate": 4.688544098128061e-05, "loss": 2.2992, "step": 14110 }, { "epoch": 0.64, "learning_rate": 4.688315254702733e-05, "loss": 2.3105, "step": 14120 }, { "epoch": 0.65, "learning_rate": 4.688086411277404e-05, "loss": 2.3507, "step": 14130 }, { "epoch": 0.65, "learning_rate": 4.687857567852076e-05, "loss": 2.3509, "step": 14140 }, { "epoch": 0.65, "learning_rate": 4.687628724426748e-05, "loss": 2.432, "step": 14150 }, { "epoch": 0.65, "learning_rate": 4.687399881001419e-05, "loss": 2.5383, "step": 14160 }, { "epoch": 0.65, "learning_rate": 4.6871710375760906e-05, "loss": 2.2634, "step": 14170 }, { "epoch": 0.65, "learning_rate": 4.686942194150763e-05, "loss": 2.317, "step": 14180 }, { "epoch": 0.65, "learning_rate": 4.686713350725434e-05, "loss": 2.4011, "step": 14190 }, { "epoch": 0.65, "learning_rate": 4.6864845073001056e-05, "loss": 2.3166, "step": 14200 }, { "epoch": 0.65, "learning_rate": 4.6862556638747776e-05, "loss": 2.33, "step": 14210 }, { "epoch": 0.65, "learning_rate": 4.686026820449449e-05, "loss": 2.4077, "step": 14220 }, { "epoch": 0.65, "learning_rate": 4.68579797702412e-05, "loss": 2.3746, "step": 14230 }, { "epoch": 0.65, "learning_rate": 4.685569133598792e-05, "loss": 2.3436, "step": 14240 }, { "epoch": 0.65, "learning_rate": 4.685340290173463e-05, "loss": 2.4641, "step": 14250 }, { "epoch": 0.65, "learning_rate": 4.685111446748135e-05, "loss": 2.56, "step": 14260 }, { "epoch": 0.65, "learning_rate": 4.684882603322807e-05, "loss": 2.4065, "step": 14270 }, { "epoch": 0.65, "learning_rate": 4.684653759897478e-05, "loss": 2.3915, "step": 14280 }, { "epoch": 0.65, "learning_rate": 4.6844249164721496e-05, "loss": 2.4588, "step": 14290 }, { "epoch": 0.65, "learning_rate": 4.684196073046822e-05, "loss": 2.4519, "step": 14300 }, { "epoch": 0.65, "learning_rate": 4.683967229621493e-05, "loss": 2.2927, "step": 14310 }, { "epoch": 0.65, "learning_rate": 4.6837383861961645e-05, "loss": 2.3492, "step": 14320 }, { "epoch": 0.65, "learning_rate": 4.6835095427708366e-05, "loss": 2.4536, "step": 14330 }, { "epoch": 0.65, "learning_rate": 4.683280699345508e-05, "loss": 2.3817, "step": 14340 }, { "epoch": 0.66, "learning_rate": 4.6830518559201795e-05, "loss": 2.527, "step": 14350 }, { "epoch": 0.66, "learning_rate": 4.6828230124948516e-05, "loss": 2.3977, "step": 14360 }, { "epoch": 0.66, "learning_rate": 4.682594169069523e-05, "loss": 2.4685, "step": 14370 }, { "epoch": 0.66, "learning_rate": 4.6823653256441944e-05, "loss": 2.4156, "step": 14380 }, { "epoch": 0.66, "learning_rate": 4.6821364822188665e-05, "loss": 2.3928, "step": 14390 }, { "epoch": 0.66, "learning_rate": 4.681907638793538e-05, "loss": 2.3526, "step": 14400 }, { "epoch": 0.66, "learning_rate": 4.681678795368209e-05, "loss": 2.3613, "step": 14410 }, { "epoch": 0.66, "learning_rate": 4.6814499519428814e-05, "loss": 2.3831, "step": 14420 }, { "epoch": 0.66, "learning_rate": 4.681221108517552e-05, "loss": 2.4877, "step": 14430 }, { "epoch": 0.66, "learning_rate": 4.680992265092224e-05, "loss": 2.4699, "step": 14440 }, { "epoch": 0.66, "learning_rate": 4.6807634216668956e-05, "loss": 2.5817, "step": 14450 }, { "epoch": 0.66, "learning_rate": 4.680534578241567e-05, "loss": 2.4337, "step": 14460 }, { "epoch": 0.66, "learning_rate": 4.680305734816239e-05, "loss": 2.303, "step": 14470 }, { "epoch": 0.66, "learning_rate": 4.6800768913909105e-05, "loss": 2.3502, "step": 14480 }, { "epoch": 0.66, "learning_rate": 4.679848047965582e-05, "loss": 2.3948, "step": 14490 }, { "epoch": 0.66, "learning_rate": 4.6796192045402534e-05, "loss": 2.4909, "step": 14500 }, { "epoch": 0.66, "learning_rate": 4.6793903611149255e-05, "loss": 2.2963, "step": 14510 }, { "epoch": 0.66, "learning_rate": 4.679161517689597e-05, "loss": 2.197, "step": 14520 }, { "epoch": 0.66, "learning_rate": 4.678932674264268e-05, "loss": 2.373, "step": 14530 }, { "epoch": 0.66, "learning_rate": 4.6787038308389404e-05, "loss": 2.5156, "step": 14540 }, { "epoch": 0.66, "learning_rate": 4.678474987413612e-05, "loss": 2.4052, "step": 14550 }, { "epoch": 0.66, "learning_rate": 4.678246143988283e-05, "loss": 2.3359, "step": 14560 }, { "epoch": 0.67, "learning_rate": 4.678017300562955e-05, "loss": 2.2341, "step": 14570 }, { "epoch": 0.67, "learning_rate": 4.677788457137627e-05, "loss": 2.5551, "step": 14580 }, { "epoch": 0.67, "learning_rate": 4.677559613712298e-05, "loss": 2.3083, "step": 14590 }, { "epoch": 0.67, "learning_rate": 4.67733077028697e-05, "loss": 2.4535, "step": 14600 }, { "epoch": 0.67, "learning_rate": 4.6771019268616416e-05, "loss": 2.4152, "step": 14610 }, { "epoch": 0.67, "learning_rate": 4.676873083436313e-05, "loss": 2.3883, "step": 14620 }, { "epoch": 0.67, "learning_rate": 4.6766442400109845e-05, "loss": 2.3874, "step": 14630 }, { "epoch": 0.67, "learning_rate": 4.676415396585656e-05, "loss": 2.3082, "step": 14640 }, { "epoch": 0.67, "learning_rate": 4.676186553160328e-05, "loss": 2.4622, "step": 14650 }, { "epoch": 0.67, "learning_rate": 4.6759577097349994e-05, "loss": 2.3399, "step": 14660 }, { "epoch": 0.67, "learning_rate": 4.675728866309671e-05, "loss": 2.3526, "step": 14670 }, { "epoch": 0.67, "learning_rate": 4.675500022884343e-05, "loss": 2.2419, "step": 14680 }, { "epoch": 0.67, "learning_rate": 4.675271179459014e-05, "loss": 2.387, "step": 14690 }, { "epoch": 0.67, "learning_rate": 4.675042336033686e-05, "loss": 2.2683, "step": 14700 }, { "epoch": 0.67, "learning_rate": 4.674813492608358e-05, "loss": 2.4183, "step": 14710 }, { "epoch": 0.67, "learning_rate": 4.674584649183029e-05, "loss": 2.2953, "step": 14720 }, { "epoch": 0.67, "learning_rate": 4.6743558057577006e-05, "loss": 2.4397, "step": 14730 }, { "epoch": 0.67, "learning_rate": 4.674126962332373e-05, "loss": 2.6142, "step": 14740 }, { "epoch": 0.67, "learning_rate": 4.673898118907044e-05, "loss": 2.4156, "step": 14750 }, { "epoch": 0.67, "learning_rate": 4.6736692754817155e-05, "loss": 2.4214, "step": 14760 }, { "epoch": 0.67, "learning_rate": 4.6734404320563876e-05, "loss": 2.288, "step": 14770 }, { "epoch": 0.67, "learning_rate": 4.673211588631059e-05, "loss": 2.4573, "step": 14780 }, { "epoch": 0.68, "learning_rate": 4.6729827452057305e-05, "loss": 2.4438, "step": 14790 }, { "epoch": 0.68, "learning_rate": 4.6727539017804026e-05, "loss": 2.4005, "step": 14800 }, { "epoch": 0.68, "learning_rate": 4.672525058355074e-05, "loss": 2.3407, "step": 14810 }, { "epoch": 0.68, "learning_rate": 4.6722962149297454e-05, "loss": 2.259, "step": 14820 }, { "epoch": 0.68, "learning_rate": 4.672067371504417e-05, "loss": 2.3452, "step": 14830 }, { "epoch": 0.68, "learning_rate": 4.671838528079088e-05, "loss": 2.307, "step": 14840 }, { "epoch": 0.68, "learning_rate": 4.6716096846537596e-05, "loss": 2.275, "step": 14850 }, { "epoch": 0.68, "learning_rate": 4.671380841228432e-05, "loss": 2.4423, "step": 14860 }, { "epoch": 0.68, "learning_rate": 4.671151997803103e-05, "loss": 2.3737, "step": 14870 }, { "epoch": 0.68, "learning_rate": 4.6709231543777745e-05, "loss": 2.4105, "step": 14880 }, { "epoch": 0.68, "learning_rate": 4.6706943109524466e-05, "loss": 2.4471, "step": 14890 }, { "epoch": 0.68, "learning_rate": 4.670465467527118e-05, "loss": 2.3884, "step": 14900 }, { "epoch": 0.68, "learning_rate": 4.6702366241017895e-05, "loss": 2.483, "step": 14910 }, { "epoch": 0.68, "learning_rate": 4.6700077806764615e-05, "loss": 2.4747, "step": 14920 }, { "epoch": 0.68, "learning_rate": 4.669778937251133e-05, "loss": 2.3079, "step": 14930 }, { "epoch": 0.68, "learning_rate": 4.6695500938258044e-05, "loss": 2.3872, "step": 14940 }, { "epoch": 0.68, "learning_rate": 4.6693212504004765e-05, "loss": 2.315, "step": 14950 }, { "epoch": 0.68, "learning_rate": 4.669092406975148e-05, "loss": 2.4301, "step": 14960 }, { "epoch": 0.68, "learning_rate": 4.668863563549819e-05, "loss": 2.485, "step": 14970 }, { "epoch": 0.68, "learning_rate": 4.6686347201244914e-05, "loss": 2.2959, "step": 14980 }, { "epoch": 0.68, "learning_rate": 4.668405876699163e-05, "loss": 2.4074, "step": 14990 }, { "epoch": 0.68, "learning_rate": 4.668177033273834e-05, "loss": 2.4591, "step": 15000 }, { "epoch": 0.69, "learning_rate": 4.667948189848506e-05, "loss": 2.3066, "step": 15010 }, { "epoch": 0.69, "learning_rate": 4.667719346423177e-05, "loss": 2.4861, "step": 15020 }, { "epoch": 0.69, "learning_rate": 4.667490502997849e-05, "loss": 2.3683, "step": 15030 }, { "epoch": 0.69, "learning_rate": 4.6672616595725205e-05, "loss": 2.413, "step": 15040 }, { "epoch": 0.69, "learning_rate": 4.667032816147192e-05, "loss": 2.2871, "step": 15050 }, { "epoch": 0.69, "learning_rate": 4.666803972721864e-05, "loss": 2.211, "step": 15060 }, { "epoch": 0.69, "learning_rate": 4.6665751292965355e-05, "loss": 2.2942, "step": 15070 }, { "epoch": 0.69, "learning_rate": 4.666346285871207e-05, "loss": 2.1498, "step": 15080 }, { "epoch": 0.69, "learning_rate": 4.666117442445879e-05, "loss": 2.5205, "step": 15090 }, { "epoch": 0.69, "learning_rate": 4.6658885990205504e-05, "loss": 2.3344, "step": 15100 }, { "epoch": 0.69, "learning_rate": 4.665659755595222e-05, "loss": 2.4032, "step": 15110 }, { "epoch": 0.69, "learning_rate": 4.665430912169894e-05, "loss": 2.4167, "step": 15120 }, { "epoch": 0.69, "learning_rate": 4.665202068744565e-05, "loss": 2.3759, "step": 15130 }, { "epoch": 0.69, "learning_rate": 4.664973225319237e-05, "loss": 2.27, "step": 15140 }, { "epoch": 0.69, "learning_rate": 4.664744381893909e-05, "loss": 2.3502, "step": 15150 }, { "epoch": 0.69, "learning_rate": 4.66451553846858e-05, "loss": 2.3773, "step": 15160 }, { "epoch": 0.69, "learning_rate": 4.6642866950432516e-05, "loss": 2.4371, "step": 15170 }, { "epoch": 0.69, "learning_rate": 4.664057851617924e-05, "loss": 2.3263, "step": 15180 }, { "epoch": 0.69, "learning_rate": 4.663829008192595e-05, "loss": 2.4648, "step": 15190 }, { "epoch": 0.69, "learning_rate": 4.6636001647672665e-05, "loss": 2.166, "step": 15200 }, { "epoch": 0.69, "learning_rate": 4.6633713213419386e-05, "loss": 2.3958, "step": 15210 }, { "epoch": 0.69, "learning_rate": 4.6631424779166094e-05, "loss": 2.3558, "step": 15220 }, { "epoch": 0.7, "learning_rate": 4.662913634491281e-05, "loss": 2.3543, "step": 15230 }, { "epoch": 0.7, "learning_rate": 4.662684791065953e-05, "loss": 2.3908, "step": 15240 }, { "epoch": 0.7, "learning_rate": 4.662455947640624e-05, "loss": 2.3875, "step": 15250 }, { "epoch": 0.7, "learning_rate": 4.662227104215296e-05, "loss": 2.4013, "step": 15260 }, { "epoch": 0.7, "learning_rate": 4.661998260789968e-05, "loss": 2.4291, "step": 15270 }, { "epoch": 0.7, "learning_rate": 4.661769417364639e-05, "loss": 2.4806, "step": 15280 }, { "epoch": 0.7, "learning_rate": 4.6615405739393106e-05, "loss": 2.4099, "step": 15290 }, { "epoch": 0.7, "learning_rate": 4.661311730513983e-05, "loss": 2.3547, "step": 15300 }, { "epoch": 0.7, "learning_rate": 4.661082887088654e-05, "loss": 2.4373, "step": 15310 }, { "epoch": 0.7, "learning_rate": 4.6608540436633255e-05, "loss": 2.3793, "step": 15320 }, { "epoch": 0.7, "learning_rate": 4.6606252002379976e-05, "loss": 2.3273, "step": 15330 }, { "epoch": 0.7, "learning_rate": 4.660396356812669e-05, "loss": 2.3817, "step": 15340 }, { "epoch": 0.7, "learning_rate": 4.6601675133873405e-05, "loss": 2.4413, "step": 15350 }, { "epoch": 0.7, "learning_rate": 4.6599386699620125e-05, "loss": 2.3436, "step": 15360 }, { "epoch": 0.7, "learning_rate": 4.659709826536684e-05, "loss": 2.3553, "step": 15370 }, { "epoch": 0.7, "learning_rate": 4.6594809831113554e-05, "loss": 2.5079, "step": 15380 }, { "epoch": 0.7, "learning_rate": 4.6592521396860275e-05, "loss": 2.3864, "step": 15390 }, { "epoch": 0.7, "learning_rate": 4.659023296260699e-05, "loss": 2.5834, "step": 15400 }, { "epoch": 0.7, "learning_rate": 4.65879445283537e-05, "loss": 2.2449, "step": 15410 }, { "epoch": 0.7, "learning_rate": 4.658565609410042e-05, "loss": 2.3418, "step": 15420 }, { "epoch": 0.7, "learning_rate": 4.658336765984713e-05, "loss": 2.331, "step": 15430 }, { "epoch": 0.71, "learning_rate": 4.658107922559385e-05, "loss": 2.3331, "step": 15440 }, { "epoch": 0.71, "learning_rate": 4.6578790791340566e-05, "loss": 2.2398, "step": 15450 }, { "epoch": 0.71, "learning_rate": 4.657650235708728e-05, "loss": 2.3635, "step": 15460 }, { "epoch": 0.71, "learning_rate": 4.6574213922834e-05, "loss": 2.2644, "step": 15470 }, { "epoch": 0.71, "learning_rate": 4.6571925488580715e-05, "loss": 2.4189, "step": 15480 }, { "epoch": 0.71, "learning_rate": 4.656963705432743e-05, "loss": 2.4264, "step": 15490 }, { "epoch": 0.71, "learning_rate": 4.656734862007415e-05, "loss": 2.3512, "step": 15500 }, { "epoch": 0.71, "learning_rate": 4.6565060185820865e-05, "loss": 2.5336, "step": 15510 }, { "epoch": 0.71, "learning_rate": 4.656277175156758e-05, "loss": 2.4266, "step": 15520 }, { "epoch": 0.71, "learning_rate": 4.65604833173143e-05, "loss": 2.4172, "step": 15530 }, { "epoch": 0.71, "learning_rate": 4.6558194883061014e-05, "loss": 2.2988, "step": 15540 }, { "epoch": 0.71, "learning_rate": 4.655590644880773e-05, "loss": 2.3799, "step": 15550 }, { "epoch": 0.71, "learning_rate": 4.655361801455445e-05, "loss": 2.4761, "step": 15560 }, { "epoch": 0.71, "learning_rate": 4.655132958030116e-05, "loss": 2.3709, "step": 15570 }, { "epoch": 0.71, "learning_rate": 4.654904114604788e-05, "loss": 2.331, "step": 15580 }, { "epoch": 0.71, "learning_rate": 4.654675271179459e-05, "loss": 2.4743, "step": 15590 }, { "epoch": 0.71, "learning_rate": 4.654446427754131e-05, "loss": 2.5322, "step": 15600 }, { "epoch": 0.71, "learning_rate": 4.6542175843288026e-05, "loss": 2.3404, "step": 15610 }, { "epoch": 0.71, "learning_rate": 4.653988740903474e-05, "loss": 2.3035, "step": 15620 }, { "epoch": 0.71, "learning_rate": 4.6537598974781454e-05, "loss": 2.4517, "step": 15630 }, { "epoch": 0.71, "learning_rate": 4.653531054052817e-05, "loss": 2.3575, "step": 15640 }, { "epoch": 0.71, "learning_rate": 4.653302210627489e-05, "loss": 2.4012, "step": 15650 }, { "epoch": 0.72, "learning_rate": 4.6530733672021604e-05, "loss": 2.2439, "step": 15660 }, { "epoch": 0.72, "learning_rate": 4.652844523776832e-05, "loss": 2.4144, "step": 15670 }, { "epoch": 0.72, "learning_rate": 4.652615680351504e-05, "loss": 2.4316, "step": 15680 }, { "epoch": 0.72, "learning_rate": 4.652386836926175e-05, "loss": 2.2541, "step": 15690 }, { "epoch": 0.72, "learning_rate": 4.652157993500847e-05, "loss": 2.3032, "step": 15700 }, { "epoch": 0.72, "learning_rate": 4.651929150075519e-05, "loss": 2.3731, "step": 15710 }, { "epoch": 0.72, "learning_rate": 4.65170030665019e-05, "loss": 2.4096, "step": 15720 }, { "epoch": 0.72, "learning_rate": 4.6514714632248616e-05, "loss": 2.4353, "step": 15730 }, { "epoch": 0.72, "learning_rate": 4.651242619799534e-05, "loss": 2.2664, "step": 15740 }, { "epoch": 0.72, "learning_rate": 4.651013776374205e-05, "loss": 2.3466, "step": 15750 }, { "epoch": 0.72, "learning_rate": 4.6507849329488765e-05, "loss": 2.3243, "step": 15760 }, { "epoch": 0.72, "learning_rate": 4.6505560895235486e-05, "loss": 2.4402, "step": 15770 }, { "epoch": 0.72, "learning_rate": 4.65032724609822e-05, "loss": 2.3982, "step": 15780 }, { "epoch": 0.72, "learning_rate": 4.6500984026728914e-05, "loss": 2.3177, "step": 15790 }, { "epoch": 0.72, "learning_rate": 4.6498695592475635e-05, "loss": 2.5616, "step": 15800 }, { "epoch": 0.72, "learning_rate": 4.649640715822235e-05, "loss": 2.3458, "step": 15810 }, { "epoch": 0.72, "learning_rate": 4.649411872396906e-05, "loss": 2.5409, "step": 15820 }, { "epoch": 0.72, "learning_rate": 4.649183028971578e-05, "loss": 2.3858, "step": 15830 }, { "epoch": 0.72, "learning_rate": 4.648954185546249e-05, "loss": 2.3554, "step": 15840 }, { "epoch": 0.72, "learning_rate": 4.6487253421209206e-05, "loss": 2.3944, "step": 15850 }, { "epoch": 0.72, "learning_rate": 4.648496498695593e-05, "loss": 2.3858, "step": 15860 }, { "epoch": 0.72, "learning_rate": 4.648267655270264e-05, "loss": 2.4616, "step": 15870 }, { "epoch": 0.73, "learning_rate": 4.6480388118449355e-05, "loss": 2.3196, "step": 15880 }, { "epoch": 0.73, "learning_rate": 4.6478099684196076e-05, "loss": 2.4085, "step": 15890 }, { "epoch": 0.73, "learning_rate": 4.647581124994279e-05, "loss": 2.4985, "step": 15900 }, { "epoch": 0.73, "learning_rate": 4.6473522815689504e-05, "loss": 2.367, "step": 15910 }, { "epoch": 0.73, "learning_rate": 4.6471234381436225e-05, "loss": 2.4053, "step": 15920 }, { "epoch": 0.73, "learning_rate": 4.646894594718294e-05, "loss": 2.5016, "step": 15930 }, { "epoch": 0.73, "learning_rate": 4.6466657512929654e-05, "loss": 2.3756, "step": 15940 }, { "epoch": 0.73, "learning_rate": 4.6464369078676374e-05, "loss": 2.3226, "step": 15950 }, { "epoch": 0.73, "learning_rate": 4.646208064442309e-05, "loss": 2.3489, "step": 15960 }, { "epoch": 0.73, "learning_rate": 4.64597922101698e-05, "loss": 2.1129, "step": 15970 }, { "epoch": 0.73, "learning_rate": 4.6457503775916524e-05, "loss": 2.3738, "step": 15980 }, { "epoch": 0.73, "learning_rate": 4.645521534166324e-05, "loss": 2.2788, "step": 15990 }, { "epoch": 0.73, "learning_rate": 4.645292690740995e-05, "loss": 2.2725, "step": 16000 }, { "epoch": 0.73, "learning_rate": 4.6450638473156666e-05, "loss": 2.3492, "step": 16010 }, { "epoch": 0.73, "learning_rate": 4.644835003890338e-05, "loss": 2.2839, "step": 16020 }, { "epoch": 0.73, "learning_rate": 4.64460616046501e-05, "loss": 2.5665, "step": 16030 }, { "epoch": 0.73, "learning_rate": 4.6443773170396815e-05, "loss": 2.24, "step": 16040 }, { "epoch": 0.73, "learning_rate": 4.644148473614353e-05, "loss": 2.3066, "step": 16050 }, { "epoch": 0.73, "learning_rate": 4.643919630189025e-05, "loss": 2.3532, "step": 16060 }, { "epoch": 0.73, "learning_rate": 4.6436907867636964e-05, "loss": 2.3299, "step": 16070 }, { "epoch": 0.73, "learning_rate": 4.643461943338368e-05, "loss": 2.4247, "step": 16080 }, { "epoch": 0.73, "learning_rate": 4.64323309991304e-05, "loss": 2.4267, "step": 16090 }, { "epoch": 0.74, "learning_rate": 4.6430042564877114e-05, "loss": 2.2134, "step": 16100 }, { "epoch": 0.74, "learning_rate": 4.642775413062383e-05, "loss": 2.4165, "step": 16110 }, { "epoch": 0.74, "learning_rate": 4.642546569637055e-05, "loss": 2.4107, "step": 16120 }, { "epoch": 0.74, "learning_rate": 4.642317726211726e-05, "loss": 2.4527, "step": 16130 }, { "epoch": 0.74, "learning_rate": 4.642088882786398e-05, "loss": 2.5759, "step": 16140 }, { "epoch": 0.74, "learning_rate": 4.64186003936107e-05, "loss": 2.4375, "step": 16150 }, { "epoch": 0.74, "learning_rate": 4.641631195935741e-05, "loss": 2.569, "step": 16160 }, { "epoch": 0.74, "learning_rate": 4.6414023525104126e-05, "loss": 2.4935, "step": 16170 }, { "epoch": 0.74, "learning_rate": 4.641173509085085e-05, "loss": 2.4303, "step": 16180 }, { "epoch": 0.74, "learning_rate": 4.640944665659756e-05, "loss": 2.4646, "step": 16190 }, { "epoch": 0.74, "learning_rate": 4.6407158222344275e-05, "loss": 2.3895, "step": 16200 }, { "epoch": 0.74, "learning_rate": 4.640486978809099e-05, "loss": 2.2805, "step": 16210 }, { "epoch": 0.74, "learning_rate": 4.6402581353837704e-05, "loss": 2.4092, "step": 16220 }, { "epoch": 0.74, "learning_rate": 4.640029291958442e-05, "loss": 2.4711, "step": 16230 }, { "epoch": 0.74, "learning_rate": 4.639800448533114e-05, "loss": 2.5324, "step": 16240 }, { "epoch": 0.74, "learning_rate": 4.639571605107785e-05, "loss": 2.3944, "step": 16250 }, { "epoch": 0.74, "learning_rate": 4.639342761682457e-05, "loss": 2.4637, "step": 16260 }, { "epoch": 0.74, "learning_rate": 4.639113918257129e-05, "loss": 2.3906, "step": 16270 }, { "epoch": 0.74, "learning_rate": 4.6388850748318e-05, "loss": 2.4916, "step": 16280 }, { "epoch": 0.74, "learning_rate": 4.6386562314064716e-05, "loss": 2.5098, "step": 16290 }, { "epoch": 0.74, "learning_rate": 4.638427387981144e-05, "loss": 2.2877, "step": 16300 }, { "epoch": 0.74, "learning_rate": 4.638198544555815e-05, "loss": 2.394, "step": 16310 }, { "epoch": 0.75, "learning_rate": 4.6379697011304865e-05, "loss": 2.4074, "step": 16320 }, { "epoch": 0.75, "learning_rate": 4.6377408577051586e-05, "loss": 2.1584, "step": 16330 }, { "epoch": 0.75, "learning_rate": 4.63751201427983e-05, "loss": 2.4774, "step": 16340 }, { "epoch": 0.75, "learning_rate": 4.6372831708545014e-05, "loss": 2.3202, "step": 16350 }, { "epoch": 0.75, "learning_rate": 4.6370543274291735e-05, "loss": 2.2768, "step": 16360 }, { "epoch": 0.75, "learning_rate": 4.636825484003845e-05, "loss": 2.3717, "step": 16370 }, { "epoch": 0.75, "learning_rate": 4.6365966405785164e-05, "loss": 2.3367, "step": 16380 }, { "epoch": 0.75, "learning_rate": 4.6363677971531884e-05, "loss": 2.3935, "step": 16390 }, { "epoch": 0.75, "learning_rate": 4.63613895372786e-05, "loss": 2.2864, "step": 16400 }, { "epoch": 0.75, "learning_rate": 4.635910110302531e-05, "loss": 2.2258, "step": 16410 }, { "epoch": 0.75, "learning_rate": 4.635681266877203e-05, "loss": 2.2879, "step": 16420 }, { "epoch": 0.75, "learning_rate": 4.635452423451874e-05, "loss": 2.4122, "step": 16430 }, { "epoch": 0.75, "learning_rate": 4.635223580026546e-05, "loss": 2.4568, "step": 16440 }, { "epoch": 0.75, "learning_rate": 4.6349947366012176e-05, "loss": 2.3877, "step": 16450 }, { "epoch": 0.75, "learning_rate": 4.634765893175889e-05, "loss": 2.3506, "step": 16460 }, { "epoch": 0.75, "learning_rate": 4.634537049750561e-05, "loss": 2.5383, "step": 16470 }, { "epoch": 0.75, "learning_rate": 4.6343082063252325e-05, "loss": 2.4364, "step": 16480 }, { "epoch": 0.75, "learning_rate": 4.634079362899904e-05, "loss": 2.364, "step": 16490 }, { "epoch": 0.75, "learning_rate": 4.633850519474576e-05, "loss": 2.4602, "step": 16500 }, { "epoch": 0.75, "learning_rate": 4.6336216760492474e-05, "loss": 2.4902, "step": 16510 }, { "epoch": 0.75, "learning_rate": 4.633392832623919e-05, "loss": 2.3852, "step": 16520 }, { "epoch": 0.75, "learning_rate": 4.633163989198591e-05, "loss": 2.4795, "step": 16530 }, { "epoch": 0.76, "learning_rate": 4.6329351457732624e-05, "loss": 2.4878, "step": 16540 }, { "epoch": 0.76, "learning_rate": 4.632706302347934e-05, "loss": 2.3741, "step": 16550 }, { "epoch": 0.76, "learning_rate": 4.632477458922606e-05, "loss": 2.2636, "step": 16560 }, { "epoch": 0.76, "learning_rate": 4.632248615497277e-05, "loss": 2.3355, "step": 16570 }, { "epoch": 0.76, "learning_rate": 4.632019772071949e-05, "loss": 2.385, "step": 16580 }, { "epoch": 0.76, "learning_rate": 4.631790928646621e-05, "loss": 2.4162, "step": 16590 }, { "epoch": 0.76, "learning_rate": 4.631562085221292e-05, "loss": 2.5351, "step": 16600 }, { "epoch": 0.76, "learning_rate": 4.631333241795963e-05, "loss": 2.3955, "step": 16610 }, { "epoch": 0.76, "learning_rate": 4.631104398370635e-05, "loss": 2.3148, "step": 16620 }, { "epoch": 0.76, "learning_rate": 4.6308755549453064e-05, "loss": 2.3832, "step": 16630 }, { "epoch": 0.76, "learning_rate": 4.630646711519978e-05, "loss": 2.3024, "step": 16640 }, { "epoch": 0.76, "learning_rate": 4.63041786809465e-05, "loss": 2.3351, "step": 16650 }, { "epoch": 0.76, "learning_rate": 4.6301890246693213e-05, "loss": 2.1833, "step": 16660 }, { "epoch": 0.76, "learning_rate": 4.629960181243993e-05, "loss": 2.398, "step": 16670 }, { "epoch": 0.76, "learning_rate": 4.629731337818665e-05, "loss": 2.4518, "step": 16680 }, { "epoch": 0.76, "learning_rate": 4.629502494393336e-05, "loss": 2.3167, "step": 16690 }, { "epoch": 0.76, "learning_rate": 4.629273650968008e-05, "loss": 2.3545, "step": 16700 }, { "epoch": 0.76, "learning_rate": 4.62904480754268e-05, "loss": 2.1911, "step": 16710 }, { "epoch": 0.76, "learning_rate": 4.628815964117351e-05, "loss": 2.3844, "step": 16720 }, { "epoch": 0.76, "learning_rate": 4.6285871206920226e-05, "loss": 2.1957, "step": 16730 }, { "epoch": 0.76, "learning_rate": 4.628358277266695e-05, "loss": 2.1394, "step": 16740 }, { "epoch": 0.76, "learning_rate": 4.628129433841366e-05, "loss": 2.4045, "step": 16750 }, { "epoch": 0.77, "learning_rate": 4.6279005904160375e-05, "loss": 2.2976, "step": 16760 }, { "epoch": 0.77, "learning_rate": 4.6276717469907096e-05, "loss": 2.5967, "step": 16770 }, { "epoch": 0.77, "learning_rate": 4.627442903565381e-05, "loss": 2.2735, "step": 16780 }, { "epoch": 0.77, "learning_rate": 4.6272140601400524e-05, "loss": 2.2542, "step": 16790 }, { "epoch": 0.77, "learning_rate": 4.626985216714724e-05, "loss": 2.2948, "step": 16800 }, { "epoch": 0.77, "learning_rate": 4.626756373289395e-05, "loss": 2.5646, "step": 16810 }, { "epoch": 0.77, "learning_rate": 4.626527529864067e-05, "loss": 2.2125, "step": 16820 }, { "epoch": 0.77, "learning_rate": 4.626298686438739e-05, "loss": 2.356, "step": 16830 }, { "epoch": 0.77, "learning_rate": 4.62606984301341e-05, "loss": 2.4147, "step": 16840 }, { "epoch": 0.77, "learning_rate": 4.6258409995880816e-05, "loss": 2.3257, "step": 16850 }, { "epoch": 0.77, "learning_rate": 4.625612156162754e-05, "loss": 2.1663, "step": 16860 }, { "epoch": 0.77, "learning_rate": 4.625383312737425e-05, "loss": 2.2445, "step": 16870 }, { "epoch": 0.77, "learning_rate": 4.6251544693120965e-05, "loss": 2.4191, "step": 16880 }, { "epoch": 0.77, "learning_rate": 4.6249256258867686e-05, "loss": 2.4502, "step": 16890 }, { "epoch": 0.77, "learning_rate": 4.62469678246144e-05, "loss": 2.3249, "step": 16900 }, { "epoch": 0.77, "learning_rate": 4.6244679390361114e-05, "loss": 2.3145, "step": 16910 }, { "epoch": 0.77, "learning_rate": 4.6242390956107835e-05, "loss": 2.2404, "step": 16920 }, { "epoch": 0.77, "learning_rate": 4.624010252185455e-05, "loss": 2.4423, "step": 16930 }, { "epoch": 0.77, "learning_rate": 4.6237814087601263e-05, "loss": 2.3639, "step": 16940 }, { "epoch": 0.77, "learning_rate": 4.6235525653347984e-05, "loss": 2.3134, "step": 16950 }, { "epoch": 0.77, "learning_rate": 4.62332372190947e-05, "loss": 2.2573, "step": 16960 }, { "epoch": 0.77, "learning_rate": 4.623094878484141e-05, "loss": 2.3208, "step": 16970 }, { "epoch": 0.78, "learning_rate": 4.6228660350588134e-05, "loss": 2.4194, "step": 16980 }, { "epoch": 0.78, "learning_rate": 4.622637191633485e-05, "loss": 2.4172, "step": 16990 }, { "epoch": 0.78, "learning_rate": 4.622408348208156e-05, "loss": 2.269, "step": 17000 }, { "epoch": 0.78, "learning_rate": 4.6221795047828276e-05, "loss": 2.2758, "step": 17010 }, { "epoch": 0.78, "learning_rate": 4.621950661357499e-05, "loss": 2.361, "step": 17020 }, { "epoch": 0.78, "learning_rate": 4.621721817932171e-05, "loss": 2.1942, "step": 17030 }, { "epoch": 0.78, "learning_rate": 4.6214929745068425e-05, "loss": 2.3396, "step": 17040 }, { "epoch": 0.78, "learning_rate": 4.621264131081514e-05, "loss": 2.2668, "step": 17050 }, { "epoch": 0.78, "learning_rate": 4.621035287656186e-05, "loss": 2.432, "step": 17060 }, { "epoch": 0.78, "learning_rate": 4.6208064442308574e-05, "loss": 2.4733, "step": 17070 }, { "epoch": 0.78, "learning_rate": 4.620577600805529e-05, "loss": 2.2557, "step": 17080 }, { "epoch": 0.78, "learning_rate": 4.620348757380201e-05, "loss": 2.408, "step": 17090 }, { "epoch": 0.78, "learning_rate": 4.6201199139548723e-05, "loss": 2.3755, "step": 17100 }, { "epoch": 0.78, "learning_rate": 4.619891070529544e-05, "loss": 2.4023, "step": 17110 }, { "epoch": 0.78, "learning_rate": 4.619662227104216e-05, "loss": 2.3953, "step": 17120 }, { "epoch": 0.78, "learning_rate": 4.619433383678887e-05, "loss": 2.4761, "step": 17130 }, { "epoch": 0.78, "learning_rate": 4.619204540253559e-05, "loss": 2.5409, "step": 17140 }, { "epoch": 0.78, "learning_rate": 4.618975696828231e-05, "loss": 2.1053, "step": 17150 }, { "epoch": 0.78, "learning_rate": 4.618746853402902e-05, "loss": 2.462, "step": 17160 }, { "epoch": 0.78, "learning_rate": 4.6185180099775736e-05, "loss": 2.215, "step": 17170 }, { "epoch": 0.78, "learning_rate": 4.618289166552246e-05, "loss": 2.3834, "step": 17180 }, { "epoch": 0.78, "learning_rate": 4.618060323126917e-05, "loss": 2.3652, "step": 17190 }, { "epoch": 0.79, "learning_rate": 4.617831479701588e-05, "loss": 2.2649, "step": 17200 }, { "epoch": 0.79, "learning_rate": 4.61760263627626e-05, "loss": 2.2971, "step": 17210 }, { "epoch": 0.79, "learning_rate": 4.6173737928509313e-05, "loss": 2.3035, "step": 17220 }, { "epoch": 0.79, "learning_rate": 4.617144949425603e-05, "loss": 2.4591, "step": 17230 }, { "epoch": 0.79, "learning_rate": 4.616916106000275e-05, "loss": 2.2772, "step": 17240 }, { "epoch": 0.79, "learning_rate": 4.616687262574946e-05, "loss": 2.4092, "step": 17250 }, { "epoch": 0.79, "learning_rate": 4.616458419149618e-05, "loss": 2.4173, "step": 17260 }, { "epoch": 0.79, "learning_rate": 4.61622957572429e-05, "loss": 2.3974, "step": 17270 }, { "epoch": 0.79, "learning_rate": 4.616000732298961e-05, "loss": 2.1957, "step": 17280 }, { "epoch": 0.79, "learning_rate": 4.6157718888736326e-05, "loss": 2.2745, "step": 17290 }, { "epoch": 0.79, "learning_rate": 4.615543045448305e-05, "loss": 2.3664, "step": 17300 }, { "epoch": 0.79, "learning_rate": 4.615314202022976e-05, "loss": 2.3128, "step": 17310 }, { "epoch": 0.79, "learning_rate": 4.6150853585976475e-05, "loss": 2.329, "step": 17320 }, { "epoch": 0.79, "learning_rate": 4.6148565151723196e-05, "loss": 2.2692, "step": 17330 }, { "epoch": 0.79, "learning_rate": 4.614627671746991e-05, "loss": 2.2669, "step": 17340 }, { "epoch": 0.79, "learning_rate": 4.6143988283216624e-05, "loss": 2.3085, "step": 17350 }, { "epoch": 0.79, "learning_rate": 4.6141699848963345e-05, "loss": 2.3425, "step": 17360 }, { "epoch": 0.79, "learning_rate": 4.613941141471006e-05, "loss": 2.3644, "step": 17370 }, { "epoch": 0.79, "learning_rate": 4.6137122980456773e-05, "loss": 2.2267, "step": 17380 }, { "epoch": 0.79, "learning_rate": 4.6134834546203494e-05, "loss": 2.3482, "step": 17390 }, { "epoch": 0.79, "learning_rate": 4.61325461119502e-05, "loss": 2.3961, "step": 17400 }, { "epoch": 0.79, "learning_rate": 4.613025767769692e-05, "loss": 2.4142, "step": 17410 }, { "epoch": 0.8, "learning_rate": 4.612796924344364e-05, "loss": 2.3755, "step": 17420 }, { "epoch": 0.8, "learning_rate": 4.612568080919035e-05, "loss": 2.2872, "step": 17430 }, { "epoch": 0.8, "learning_rate": 4.612339237493707e-05, "loss": 2.425, "step": 17440 }, { "epoch": 0.8, "learning_rate": 4.6121103940683786e-05, "loss": 2.3519, "step": 17450 }, { "epoch": 0.8, "learning_rate": 4.61188155064305e-05, "loss": 2.4243, "step": 17460 }, { "epoch": 0.8, "learning_rate": 4.611652707217722e-05, "loss": 2.2972, "step": 17470 }, { "epoch": 0.8, "learning_rate": 4.6114238637923935e-05, "loss": 2.5213, "step": 17480 }, { "epoch": 0.8, "learning_rate": 4.611195020367065e-05, "loss": 2.2946, "step": 17490 }, { "epoch": 0.8, "learning_rate": 4.610966176941737e-05, "loss": 2.4006, "step": 17500 }, { "epoch": 0.8, "learning_rate": 4.6107373335164084e-05, "loss": 2.4552, "step": 17510 }, { "epoch": 0.8, "learning_rate": 4.61050849009108e-05, "loss": 2.1953, "step": 17520 }, { "epoch": 0.8, "learning_rate": 4.610279646665752e-05, "loss": 2.3774, "step": 17530 }, { "epoch": 0.8, "learning_rate": 4.6100508032404233e-05, "loss": 2.4001, "step": 17540 }, { "epoch": 0.8, "learning_rate": 4.609821959815095e-05, "loss": 2.4302, "step": 17550 }, { "epoch": 0.8, "learning_rate": 4.609593116389767e-05, "loss": 2.3782, "step": 17560 }, { "epoch": 0.8, "learning_rate": 4.609364272964438e-05, "loss": 2.3486, "step": 17570 }, { "epoch": 0.8, "learning_rate": 4.60913542953911e-05, "loss": 2.2413, "step": 17580 }, { "epoch": 0.8, "learning_rate": 4.608906586113781e-05, "loss": 2.2826, "step": 17590 }, { "epoch": 0.8, "learning_rate": 4.6086777426884525e-05, "loss": 2.3459, "step": 17600 }, { "epoch": 0.8, "learning_rate": 4.608448899263124e-05, "loss": 2.3541, "step": 17610 }, { "epoch": 0.8, "learning_rate": 4.608220055837796e-05, "loss": 2.3837, "step": 17620 }, { "epoch": 0.81, "learning_rate": 4.6079912124124674e-05, "loss": 2.2997, "step": 17630 }, { "epoch": 0.81, "learning_rate": 4.607762368987139e-05, "loss": 2.391, "step": 17640 }, { "epoch": 0.81, "learning_rate": 4.607533525561811e-05, "loss": 2.3092, "step": 17650 }, { "epoch": 0.81, "learning_rate": 4.607304682136482e-05, "loss": 2.1578, "step": 17660 }, { "epoch": 0.81, "learning_rate": 4.607075838711154e-05, "loss": 2.4328, "step": 17670 }, { "epoch": 0.81, "learning_rate": 4.606846995285826e-05, "loss": 2.3255, "step": 17680 }, { "epoch": 0.81, "learning_rate": 4.606618151860497e-05, "loss": 2.3593, "step": 17690 }, { "epoch": 0.81, "learning_rate": 4.606389308435169e-05, "loss": 2.4442, "step": 17700 }, { "epoch": 0.81, "learning_rate": 4.606160465009841e-05, "loss": 2.3751, "step": 17710 }, { "epoch": 0.81, "learning_rate": 4.605931621584512e-05, "loss": 2.3036, "step": 17720 }, { "epoch": 0.81, "learning_rate": 4.6057027781591836e-05, "loss": 2.2323, "step": 17730 }, { "epoch": 0.81, "learning_rate": 4.605473934733856e-05, "loss": 2.2709, "step": 17740 }, { "epoch": 0.81, "learning_rate": 4.605245091308527e-05, "loss": 2.2969, "step": 17750 }, { "epoch": 0.81, "learning_rate": 4.6050162478831985e-05, "loss": 2.3487, "step": 17760 }, { "epoch": 0.81, "learning_rate": 4.6047874044578706e-05, "loss": 2.243, "step": 17770 }, { "epoch": 0.81, "learning_rate": 4.604558561032542e-05, "loss": 2.2702, "step": 17780 }, { "epoch": 0.81, "learning_rate": 4.6043297176072134e-05, "loss": 2.2527, "step": 17790 }, { "epoch": 0.81, "learning_rate": 4.604100874181885e-05, "loss": 2.3007, "step": 17800 }, { "epoch": 0.81, "learning_rate": 4.603872030756556e-05, "loss": 2.305, "step": 17810 }, { "epoch": 0.81, "learning_rate": 4.603643187331228e-05, "loss": 2.3892, "step": 17820 }, { "epoch": 0.81, "learning_rate": 4.6034143439059e-05, "loss": 2.2753, "step": 17830 }, { "epoch": 0.81, "learning_rate": 4.603185500480571e-05, "loss": 2.3494, "step": 17840 }, { "epoch": 0.82, "learning_rate": 4.602956657055243e-05, "loss": 2.5659, "step": 17850 }, { "epoch": 0.82, "learning_rate": 4.602727813629915e-05, "loss": 2.1927, "step": 17860 }, { "epoch": 0.82, "learning_rate": 4.602498970204586e-05, "loss": 2.4403, "step": 17870 }, { "epoch": 0.82, "learning_rate": 4.602270126779258e-05, "loss": 2.3447, "step": 17880 }, { "epoch": 0.82, "learning_rate": 4.6020412833539296e-05, "loss": 2.4206, "step": 17890 }, { "epoch": 0.82, "learning_rate": 4.601812439928601e-05, "loss": 2.446, "step": 17900 }, { "epoch": 0.82, "learning_rate": 4.601583596503273e-05, "loss": 2.3623, "step": 17910 }, { "epoch": 0.82, "learning_rate": 4.6013547530779445e-05, "loss": 2.2477, "step": 17920 }, { "epoch": 0.82, "learning_rate": 4.601125909652616e-05, "loss": 2.1787, "step": 17930 }, { "epoch": 0.82, "learning_rate": 4.600897066227287e-05, "loss": 2.1811, "step": 17940 }, { "epoch": 0.82, "learning_rate": 4.6006682228019594e-05, "loss": 2.2929, "step": 17950 }, { "epoch": 0.82, "learning_rate": 4.600439379376631e-05, "loss": 2.4133, "step": 17960 }, { "epoch": 0.82, "learning_rate": 4.600210535951302e-05, "loss": 2.3875, "step": 17970 }, { "epoch": 0.82, "learning_rate": 4.5999816925259743e-05, "loss": 2.1042, "step": 17980 }, { "epoch": 0.82, "learning_rate": 4.599752849100645e-05, "loss": 2.3107, "step": 17990 }, { "epoch": 0.82, "learning_rate": 4.599524005675317e-05, "loss": 2.1866, "step": 18000 }, { "epoch": 0.82, "learning_rate": 4.5992951622499886e-05, "loss": 2.4401, "step": 18010 }, { "epoch": 0.82, "learning_rate": 4.59906631882466e-05, "loss": 2.3454, "step": 18020 }, { "epoch": 0.82, "learning_rate": 4.598837475399332e-05, "loss": 2.1255, "step": 18030 }, { "epoch": 0.82, "learning_rate": 4.5986086319740035e-05, "loss": 2.3717, "step": 18040 }, { "epoch": 0.82, "learning_rate": 4.598379788548675e-05, "loss": 2.2764, "step": 18050 }, { "epoch": 0.82, "learning_rate": 4.598150945123347e-05, "loss": 2.3793, "step": 18060 }, { "epoch": 0.83, "learning_rate": 4.5979221016980184e-05, "loss": 2.3187, "step": 18070 }, { "epoch": 0.83, "learning_rate": 4.59769325827269e-05, "loss": 2.2405, "step": 18080 }, { "epoch": 0.83, "learning_rate": 4.597464414847362e-05, "loss": 2.3413, "step": 18090 }, { "epoch": 0.83, "learning_rate": 4.597235571422033e-05, "loss": 2.1229, "step": 18100 }, { "epoch": 0.83, "learning_rate": 4.597006727996705e-05, "loss": 2.3021, "step": 18110 }, { "epoch": 0.83, "learning_rate": 4.596777884571377e-05, "loss": 2.3206, "step": 18120 }, { "epoch": 0.83, "learning_rate": 4.596549041146048e-05, "loss": 2.3168, "step": 18130 }, { "epoch": 0.83, "learning_rate": 4.59632019772072e-05, "loss": 2.3795, "step": 18140 }, { "epoch": 0.83, "learning_rate": 4.596091354295392e-05, "loss": 2.4483, "step": 18150 }, { "epoch": 0.83, "learning_rate": 4.595862510870063e-05, "loss": 2.3686, "step": 18160 }, { "epoch": 0.83, "learning_rate": 4.5956336674447346e-05, "loss": 2.3939, "step": 18170 }, { "epoch": 0.83, "learning_rate": 4.595404824019407e-05, "loss": 2.3371, "step": 18180 }, { "epoch": 0.83, "learning_rate": 4.5951759805940774e-05, "loss": 2.1701, "step": 18190 }, { "epoch": 0.83, "learning_rate": 4.594947137168749e-05, "loss": 2.5501, "step": 18200 }, { "epoch": 0.83, "learning_rate": 4.594718293743421e-05, "loss": 2.4197, "step": 18210 }, { "epoch": 0.83, "learning_rate": 4.594489450318092e-05, "loss": 2.5387, "step": 18220 }, { "epoch": 0.83, "learning_rate": 4.594260606892764e-05, "loss": 2.3584, "step": 18230 }, { "epoch": 0.83, "learning_rate": 4.594031763467436e-05, "loss": 2.3796, "step": 18240 }, { "epoch": 0.83, "learning_rate": 4.593802920042107e-05, "loss": 2.2724, "step": 18250 }, { "epoch": 0.83, "learning_rate": 4.5935740766167787e-05, "loss": 2.4183, "step": 18260 }, { "epoch": 0.83, "learning_rate": 4.593345233191451e-05, "loss": 2.5297, "step": 18270 }, { "epoch": 0.83, "learning_rate": 4.593116389766122e-05, "loss": 2.4938, "step": 18280 }, { "epoch": 0.84, "learning_rate": 4.5928875463407936e-05, "loss": 2.3037, "step": 18290 }, { "epoch": 0.84, "learning_rate": 4.592658702915466e-05, "loss": 2.3448, "step": 18300 }, { "epoch": 0.84, "learning_rate": 4.592429859490137e-05, "loss": 2.5717, "step": 18310 }, { "epoch": 0.84, "learning_rate": 4.5922010160648085e-05, "loss": 2.4244, "step": 18320 }, { "epoch": 0.84, "learning_rate": 4.5919721726394806e-05, "loss": 2.3476, "step": 18330 }, { "epoch": 0.84, "learning_rate": 4.591743329214152e-05, "loss": 2.2817, "step": 18340 }, { "epoch": 0.84, "learning_rate": 4.5915144857888234e-05, "loss": 2.1066, "step": 18350 }, { "epoch": 0.84, "learning_rate": 4.5912856423634955e-05, "loss": 2.2452, "step": 18360 }, { "epoch": 0.84, "learning_rate": 4.591056798938167e-05, "loss": 2.3587, "step": 18370 }, { "epoch": 0.84, "learning_rate": 4.590827955512838e-05, "loss": 2.2548, "step": 18380 }, { "epoch": 0.84, "learning_rate": 4.59059911208751e-05, "loss": 2.5253, "step": 18390 }, { "epoch": 0.84, "learning_rate": 4.590370268662181e-05, "loss": 2.3307, "step": 18400 }, { "epoch": 0.84, "learning_rate": 4.590141425236853e-05, "loss": 2.4063, "step": 18410 }, { "epoch": 0.84, "learning_rate": 4.5899125818115247e-05, "loss": 2.2313, "step": 18420 }, { "epoch": 0.84, "learning_rate": 4.589683738386196e-05, "loss": 2.3987, "step": 18430 }, { "epoch": 0.84, "learning_rate": 4.589454894960868e-05, "loss": 2.2711, "step": 18440 }, { "epoch": 0.84, "learning_rate": 4.5892260515355396e-05, "loss": 2.367, "step": 18450 }, { "epoch": 0.84, "learning_rate": 4.588997208110211e-05, "loss": 2.2311, "step": 18460 }, { "epoch": 0.84, "learning_rate": 4.588768364684883e-05, "loss": 2.4789, "step": 18470 }, { "epoch": 0.84, "learning_rate": 4.5885395212595545e-05, "loss": 2.3807, "step": 18480 }, { "epoch": 0.84, "learning_rate": 4.588310677834226e-05, "loss": 2.4491, "step": 18490 }, { "epoch": 0.84, "learning_rate": 4.588081834408898e-05, "loss": 2.4512, "step": 18500 }, { "epoch": 0.85, "learning_rate": 4.5878529909835694e-05, "loss": 2.3526, "step": 18510 }, { "epoch": 0.85, "learning_rate": 4.587624147558241e-05, "loss": 2.2566, "step": 18520 }, { "epoch": 0.85, "learning_rate": 4.587395304132913e-05, "loss": 2.3285, "step": 18530 }, { "epoch": 0.85, "learning_rate": 4.587166460707584e-05, "loss": 2.1635, "step": 18540 }, { "epoch": 0.85, "learning_rate": 4.586937617282256e-05, "loss": 2.3393, "step": 18550 }, { "epoch": 0.85, "learning_rate": 4.586708773856928e-05, "loss": 2.2156, "step": 18560 }, { "epoch": 0.85, "learning_rate": 4.586479930431599e-05, "loss": 2.3665, "step": 18570 }, { "epoch": 0.85, "learning_rate": 4.58625108700627e-05, "loss": 2.403, "step": 18580 }, { "epoch": 0.85, "learning_rate": 4.586022243580942e-05, "loss": 2.3131, "step": 18590 }, { "epoch": 0.85, "learning_rate": 4.5857934001556135e-05, "loss": 2.1956, "step": 18600 }, { "epoch": 0.85, "learning_rate": 4.585564556730285e-05, "loss": 2.3568, "step": 18610 }, { "epoch": 0.85, "learning_rate": 4.585335713304957e-05, "loss": 2.289, "step": 18620 }, { "epoch": 0.85, "learning_rate": 4.5851068698796284e-05, "loss": 2.5158, "step": 18630 }, { "epoch": 0.85, "learning_rate": 4.5848780264543e-05, "loss": 2.0364, "step": 18640 }, { "epoch": 0.85, "learning_rate": 4.584649183028972e-05, "loss": 2.3353, "step": 18650 }, { "epoch": 0.85, "learning_rate": 4.584420339603643e-05, "loss": 2.2314, "step": 18660 }, { "epoch": 0.85, "learning_rate": 4.584191496178315e-05, "loss": 2.1996, "step": 18670 }, { "epoch": 0.85, "learning_rate": 4.583962652752987e-05, "loss": 2.3896, "step": 18680 }, { "epoch": 0.85, "learning_rate": 4.583733809327658e-05, "loss": 2.3192, "step": 18690 }, { "epoch": 0.85, "learning_rate": 4.5835049659023297e-05, "loss": 2.4071, "step": 18700 }, { "epoch": 0.85, "learning_rate": 4.583276122477002e-05, "loss": 2.3846, "step": 18710 }, { "epoch": 0.85, "learning_rate": 4.583047279051673e-05, "loss": 2.3816, "step": 18720 }, { "epoch": 0.86, "learning_rate": 4.5828184356263446e-05, "loss": 2.2255, "step": 18730 }, { "epoch": 0.86, "learning_rate": 4.582589592201017e-05, "loss": 2.2504, "step": 18740 }, { "epoch": 0.86, "learning_rate": 4.582360748775688e-05, "loss": 2.4081, "step": 18750 }, { "epoch": 0.86, "learning_rate": 4.5821319053503595e-05, "loss": 2.2791, "step": 18760 }, { "epoch": 0.86, "learning_rate": 4.5819030619250316e-05, "loss": 2.34, "step": 18770 }, { "epoch": 0.86, "learning_rate": 4.581674218499702e-05, "loss": 2.4302, "step": 18780 }, { "epoch": 0.86, "learning_rate": 4.5814453750743744e-05, "loss": 2.3657, "step": 18790 }, { "epoch": 0.86, "learning_rate": 4.581216531649046e-05, "loss": 2.29, "step": 18800 }, { "epoch": 0.86, "learning_rate": 4.580987688223717e-05, "loss": 2.3074, "step": 18810 }, { "epoch": 0.86, "learning_rate": 4.580758844798389e-05, "loss": 2.317, "step": 18820 }, { "epoch": 0.86, "learning_rate": 4.580530001373061e-05, "loss": 2.3815, "step": 18830 }, { "epoch": 0.86, "learning_rate": 4.580301157947732e-05, "loss": 2.372, "step": 18840 }, { "epoch": 0.86, "learning_rate": 4.580072314522404e-05, "loss": 2.1267, "step": 18850 }, { "epoch": 0.86, "learning_rate": 4.5798434710970757e-05, "loss": 2.2348, "step": 18860 }, { "epoch": 0.86, "learning_rate": 4.579614627671747e-05, "loss": 2.446, "step": 18870 }, { "epoch": 0.86, "learning_rate": 4.579385784246419e-05, "loss": 2.4357, "step": 18880 }, { "epoch": 0.86, "learning_rate": 4.5791569408210906e-05, "loss": 2.4249, "step": 18890 }, { "epoch": 0.86, "learning_rate": 4.578928097395762e-05, "loss": 2.2817, "step": 18900 }, { "epoch": 0.86, "learning_rate": 4.578699253970434e-05, "loss": 2.219, "step": 18910 }, { "epoch": 0.86, "learning_rate": 4.5784704105451055e-05, "loss": 2.3065, "step": 18920 }, { "epoch": 0.86, "learning_rate": 4.578241567119777e-05, "loss": 2.3389, "step": 18930 }, { "epoch": 0.86, "learning_rate": 4.578012723694449e-05, "loss": 2.3475, "step": 18940 }, { "epoch": 0.87, "learning_rate": 4.5777838802691204e-05, "loss": 2.2921, "step": 18950 }, { "epoch": 0.87, "learning_rate": 4.577555036843792e-05, "loss": 2.4542, "step": 18960 }, { "epoch": 0.87, "learning_rate": 4.577326193418464e-05, "loss": 2.2383, "step": 18970 }, { "epoch": 0.87, "learning_rate": 4.5770973499931346e-05, "loss": 2.4686, "step": 18980 }, { "epoch": 0.87, "learning_rate": 4.576868506567806e-05, "loss": 2.2811, "step": 18990 }, { "epoch": 0.87, "learning_rate": 4.576639663142478e-05, "loss": 2.266, "step": 19000 }, { "epoch": 0.87, "learning_rate": 4.5764108197171496e-05, "loss": 2.3875, "step": 19010 }, { "epoch": 0.87, "learning_rate": 4.576181976291821e-05, "loss": 2.4062, "step": 19020 }, { "epoch": 0.87, "learning_rate": 4.575953132866493e-05, "loss": 2.3431, "step": 19030 }, { "epoch": 0.87, "learning_rate": 4.5757242894411645e-05, "loss": 2.3336, "step": 19040 }, { "epoch": 0.87, "learning_rate": 4.575495446015836e-05, "loss": 2.2658, "step": 19050 }, { "epoch": 0.87, "learning_rate": 4.575266602590508e-05, "loss": 2.306, "step": 19060 }, { "epoch": 0.87, "learning_rate": 4.5750377591651794e-05, "loss": 2.3204, "step": 19070 }, { "epoch": 0.87, "learning_rate": 4.574808915739851e-05, "loss": 2.2405, "step": 19080 }, { "epoch": 0.87, "learning_rate": 4.574580072314523e-05, "loss": 2.4545, "step": 19090 }, { "epoch": 0.87, "learning_rate": 4.574351228889194e-05, "loss": 2.2886, "step": 19100 }, { "epoch": 0.87, "learning_rate": 4.574122385463866e-05, "loss": 2.2922, "step": 19110 }, { "epoch": 0.87, "learning_rate": 4.573893542038538e-05, "loss": 2.1888, "step": 19120 }, { "epoch": 0.87, "learning_rate": 4.573664698613209e-05, "loss": 2.318, "step": 19130 }, { "epoch": 0.87, "learning_rate": 4.5734358551878807e-05, "loss": 2.4085, "step": 19140 }, { "epoch": 0.87, "learning_rate": 4.573207011762553e-05, "loss": 2.0829, "step": 19150 }, { "epoch": 0.87, "learning_rate": 4.572978168337224e-05, "loss": 2.2676, "step": 19160 }, { "epoch": 0.88, "learning_rate": 4.572749324911895e-05, "loss": 2.3501, "step": 19170 }, { "epoch": 0.88, "learning_rate": 4.572520481486567e-05, "loss": 2.2972, "step": 19180 }, { "epoch": 0.88, "learning_rate": 4.5722916380612384e-05, "loss": 2.2125, "step": 19190 }, { "epoch": 0.88, "learning_rate": 4.57206279463591e-05, "loss": 2.2552, "step": 19200 }, { "epoch": 0.88, "learning_rate": 4.571833951210582e-05, "loss": 2.3906, "step": 19210 }, { "epoch": 0.88, "learning_rate": 4.571605107785253e-05, "loss": 2.3477, "step": 19220 }, { "epoch": 0.88, "learning_rate": 4.571376264359925e-05, "loss": 2.4612, "step": 19230 }, { "epoch": 0.88, "learning_rate": 4.571147420934597e-05, "loss": 2.1379, "step": 19240 }, { "epoch": 0.88, "learning_rate": 4.570918577509268e-05, "loss": 2.444, "step": 19250 }, { "epoch": 0.88, "learning_rate": 4.5706897340839396e-05, "loss": 2.6329, "step": 19260 }, { "epoch": 0.88, "learning_rate": 4.570460890658612e-05, "loss": 2.2478, "step": 19270 }, { "epoch": 0.88, "learning_rate": 4.570232047233283e-05, "loss": 2.3719, "step": 19280 }, { "epoch": 0.88, "learning_rate": 4.5700032038079546e-05, "loss": 2.3404, "step": 19290 }, { "epoch": 0.88, "learning_rate": 4.5697743603826267e-05, "loss": 2.2772, "step": 19300 }, { "epoch": 0.88, "learning_rate": 4.569545516957298e-05, "loss": 2.2984, "step": 19310 }, { "epoch": 0.88, "learning_rate": 4.5693166735319695e-05, "loss": 2.3506, "step": 19320 }, { "epoch": 0.88, "learning_rate": 4.5690878301066416e-05, "loss": 2.4665, "step": 19330 }, { "epoch": 0.88, "learning_rate": 4.568858986681313e-05, "loss": 2.2764, "step": 19340 }, { "epoch": 0.88, "learning_rate": 4.5686301432559844e-05, "loss": 2.3375, "step": 19350 }, { "epoch": 0.88, "learning_rate": 4.5684012998306565e-05, "loss": 2.3852, "step": 19360 }, { "epoch": 0.88, "learning_rate": 4.568172456405327e-05, "loss": 2.2154, "step": 19370 }, { "epoch": 0.88, "learning_rate": 4.567943612979999e-05, "loss": 2.2933, "step": 19380 }, { "epoch": 0.89, "learning_rate": 4.567714769554671e-05, "loss": 2.2738, "step": 19390 }, { "epoch": 0.89, "learning_rate": 4.567485926129342e-05, "loss": 2.3635, "step": 19400 }, { "epoch": 0.89, "learning_rate": 4.567257082704014e-05, "loss": 2.397, "step": 19410 }, { "epoch": 0.89, "learning_rate": 4.5670282392786856e-05, "loss": 2.4506, "step": 19420 }, { "epoch": 0.89, "learning_rate": 4.566799395853357e-05, "loss": 2.4695, "step": 19430 }, { "epoch": 0.89, "learning_rate": 4.566570552428029e-05, "loss": 2.4033, "step": 19440 }, { "epoch": 0.89, "learning_rate": 4.5663417090027006e-05, "loss": 2.3628, "step": 19450 }, { "epoch": 0.89, "learning_rate": 4.566112865577372e-05, "loss": 2.257, "step": 19460 }, { "epoch": 0.89, "learning_rate": 4.565884022152044e-05, "loss": 2.1301, "step": 19470 }, { "epoch": 0.89, "learning_rate": 4.5656551787267155e-05, "loss": 2.2549, "step": 19480 }, { "epoch": 0.89, "learning_rate": 4.565426335301387e-05, "loss": 2.2006, "step": 19490 }, { "epoch": 0.89, "learning_rate": 4.565197491876059e-05, "loss": 2.2957, "step": 19500 }, { "epoch": 0.89, "learning_rate": 4.5649686484507304e-05, "loss": 2.3068, "step": 19510 }, { "epoch": 0.89, "learning_rate": 4.564739805025402e-05, "loss": 2.4617, "step": 19520 }, { "epoch": 0.89, "learning_rate": 4.564510961600074e-05, "loss": 2.3057, "step": 19530 }, { "epoch": 0.89, "learning_rate": 4.564282118174745e-05, "loss": 2.3083, "step": 19540 }, { "epoch": 0.89, "learning_rate": 4.564053274749417e-05, "loss": 2.2808, "step": 19550 }, { "epoch": 0.89, "learning_rate": 4.563824431324089e-05, "loss": 2.3768, "step": 19560 }, { "epoch": 0.89, "learning_rate": 4.5635955878987596e-05, "loss": 2.4568, "step": 19570 }, { "epoch": 0.89, "learning_rate": 4.563366744473431e-05, "loss": 2.2106, "step": 19580 }, { "epoch": 0.89, "learning_rate": 4.563137901048103e-05, "loss": 2.367, "step": 19590 }, { "epoch": 0.89, "learning_rate": 4.5629090576227745e-05, "loss": 2.427, "step": 19600 }, { "epoch": 0.9, "learning_rate": 4.562680214197446e-05, "loss": 2.2411, "step": 19610 }, { "epoch": 0.9, "learning_rate": 4.562451370772118e-05, "loss": 2.4255, "step": 19620 }, { "epoch": 0.9, "learning_rate": 4.5622225273467894e-05, "loss": 2.3805, "step": 19630 }, { "epoch": 0.9, "learning_rate": 4.561993683921461e-05, "loss": 2.3214, "step": 19640 }, { "epoch": 0.9, "learning_rate": 4.561764840496133e-05, "loss": 2.332, "step": 19650 }, { "epoch": 0.9, "learning_rate": 4.561535997070804e-05, "loss": 2.3175, "step": 19660 }, { "epoch": 0.9, "learning_rate": 4.561307153645476e-05, "loss": 2.368, "step": 19670 }, { "epoch": 0.9, "learning_rate": 4.561078310220148e-05, "loss": 2.4446, "step": 19680 }, { "epoch": 0.9, "learning_rate": 4.560849466794819e-05, "loss": 2.3791, "step": 19690 }, { "epoch": 0.9, "learning_rate": 4.5606206233694906e-05, "loss": 2.2314, "step": 19700 }, { "epoch": 0.9, "learning_rate": 4.560391779944163e-05, "loss": 2.2174, "step": 19710 }, { "epoch": 0.9, "learning_rate": 4.560162936518834e-05, "loss": 2.1577, "step": 19720 }, { "epoch": 0.9, "learning_rate": 4.5599340930935056e-05, "loss": 2.393, "step": 19730 }, { "epoch": 0.9, "learning_rate": 4.5597052496681776e-05, "loss": 2.3185, "step": 19740 }, { "epoch": 0.9, "learning_rate": 4.559476406242849e-05, "loss": 2.3551, "step": 19750 }, { "epoch": 0.9, "learning_rate": 4.5592475628175205e-05, "loss": 2.5459, "step": 19760 }, { "epoch": 0.9, "learning_rate": 4.559018719392192e-05, "loss": 2.4101, "step": 19770 }, { "epoch": 0.9, "learning_rate": 4.558789875966863e-05, "loss": 2.3341, "step": 19780 }, { "epoch": 0.9, "learning_rate": 4.5585610325415354e-05, "loss": 2.3461, "step": 19790 }, { "epoch": 0.9, "learning_rate": 4.558332189116207e-05, "loss": 2.3305, "step": 19800 }, { "epoch": 0.9, "learning_rate": 4.558103345690878e-05, "loss": 2.3045, "step": 19810 }, { "epoch": 0.91, "learning_rate": 4.55787450226555e-05, "loss": 2.3633, "step": 19820 }, { "epoch": 0.91, "learning_rate": 4.557645658840222e-05, "loss": 2.3211, "step": 19830 }, { "epoch": 0.91, "learning_rate": 4.557416815414893e-05, "loss": 2.362, "step": 19840 }, { "epoch": 0.91, "learning_rate": 4.557187971989565e-05, "loss": 2.3323, "step": 19850 }, { "epoch": 0.91, "learning_rate": 4.5569591285642366e-05, "loss": 2.3098, "step": 19860 }, { "epoch": 0.91, "learning_rate": 4.556730285138908e-05, "loss": 2.2962, "step": 19870 }, { "epoch": 0.91, "learning_rate": 4.55650144171358e-05, "loss": 2.3087, "step": 19880 }, { "epoch": 0.91, "learning_rate": 4.5562725982882516e-05, "loss": 2.4064, "step": 19890 }, { "epoch": 0.91, "learning_rate": 4.556043754862923e-05, "loss": 2.1603, "step": 19900 }, { "epoch": 0.91, "learning_rate": 4.555814911437595e-05, "loss": 2.4047, "step": 19910 }, { "epoch": 0.91, "learning_rate": 4.5555860680122665e-05, "loss": 2.546, "step": 19920 }, { "epoch": 0.91, "learning_rate": 4.555357224586938e-05, "loss": 2.3444, "step": 19930 }, { "epoch": 0.91, "learning_rate": 4.55512838116161e-05, "loss": 2.5271, "step": 19940 }, { "epoch": 0.91, "learning_rate": 4.5548995377362814e-05, "loss": 2.3113, "step": 19950 }, { "epoch": 0.91, "learning_rate": 4.554670694310952e-05, "loss": 2.1889, "step": 19960 }, { "epoch": 0.91, "learning_rate": 4.554441850885624e-05, "loss": 2.3636, "step": 19970 }, { "epoch": 0.91, "learning_rate": 4.5542130074602956e-05, "loss": 2.2404, "step": 19980 }, { "epoch": 0.91, "learning_rate": 4.553984164034967e-05, "loss": 2.4596, "step": 19990 }, { "epoch": 0.91, "learning_rate": 4.553755320609639e-05, "loss": 2.4119, "step": 20000 }, { "epoch": 0.91, "learning_rate": 4.5535264771843106e-05, "loss": 2.1942, "step": 20010 }, { "epoch": 0.91, "learning_rate": 4.553297633758982e-05, "loss": 2.3621, "step": 20020 }, { "epoch": 0.91, "learning_rate": 4.553068790333654e-05, "loss": 2.3445, "step": 20030 }, { "epoch": 0.92, "learning_rate": 4.5528399469083255e-05, "loss": 2.3516, "step": 20040 }, { "epoch": 0.92, "learning_rate": 4.552611103482997e-05, "loss": 2.284, "step": 20050 }, { "epoch": 0.92, "learning_rate": 4.552382260057669e-05, "loss": 2.3861, "step": 20060 }, { "epoch": 0.92, "learning_rate": 4.5521534166323404e-05, "loss": 2.384, "step": 20070 }, { "epoch": 0.92, "learning_rate": 4.551924573207012e-05, "loss": 2.2449, "step": 20080 }, { "epoch": 0.92, "learning_rate": 4.551695729781684e-05, "loss": 2.4798, "step": 20090 }, { "epoch": 0.92, "learning_rate": 4.551466886356355e-05, "loss": 2.4549, "step": 20100 }, { "epoch": 0.92, "learning_rate": 4.551238042931027e-05, "loss": 2.2388, "step": 20110 }, { "epoch": 0.92, "learning_rate": 4.551009199505699e-05, "loss": 2.2409, "step": 20120 }, { "epoch": 0.92, "learning_rate": 4.55078035608037e-05, "loss": 2.3194, "step": 20130 }, { "epoch": 0.92, "learning_rate": 4.5505515126550416e-05, "loss": 2.3702, "step": 20140 }, { "epoch": 0.92, "learning_rate": 4.550322669229714e-05, "loss": 2.326, "step": 20150 }, { "epoch": 0.92, "learning_rate": 4.5500938258043845e-05, "loss": 2.3426, "step": 20160 }, { "epoch": 0.92, "learning_rate": 4.5498649823790566e-05, "loss": 2.461, "step": 20170 }, { "epoch": 0.92, "learning_rate": 4.549636138953728e-05, "loss": 2.2618, "step": 20180 }, { "epoch": 0.92, "learning_rate": 4.5494072955283994e-05, "loss": 2.1909, "step": 20190 }, { "epoch": 0.92, "learning_rate": 4.5491784521030715e-05, "loss": 2.356, "step": 20200 }, { "epoch": 0.92, "learning_rate": 4.548949608677743e-05, "loss": 2.238, "step": 20210 }, { "epoch": 0.92, "learning_rate": 4.548720765252414e-05, "loss": 2.2661, "step": 20220 }, { "epoch": 0.92, "learning_rate": 4.5484919218270864e-05, "loss": 2.3312, "step": 20230 }, { "epoch": 0.92, "learning_rate": 4.548263078401758e-05, "loss": 2.2985, "step": 20240 }, { "epoch": 0.92, "learning_rate": 4.548034234976429e-05, "loss": 2.2254, "step": 20250 }, { "epoch": 0.93, "learning_rate": 4.5478053915511006e-05, "loss": 2.1759, "step": 20260 }, { "epoch": 0.93, "learning_rate": 4.547576548125773e-05, "loss": 2.2515, "step": 20270 }, { "epoch": 0.93, "learning_rate": 4.547347704700444e-05, "loss": 2.3056, "step": 20280 }, { "epoch": 0.93, "learning_rate": 4.5471188612751155e-05, "loss": 2.4453, "step": 20290 }, { "epoch": 0.93, "learning_rate": 4.5468900178497876e-05, "loss": 2.2814, "step": 20300 }, { "epoch": 0.93, "learning_rate": 4.546661174424459e-05, "loss": 2.2557, "step": 20310 }, { "epoch": 0.93, "learning_rate": 4.5464323309991305e-05, "loss": 2.412, "step": 20320 }, { "epoch": 0.93, "learning_rate": 4.5462034875738026e-05, "loss": 2.4694, "step": 20330 }, { "epoch": 0.93, "learning_rate": 4.545974644148474e-05, "loss": 2.213, "step": 20340 }, { "epoch": 0.93, "learning_rate": 4.5457458007231454e-05, "loss": 2.4175, "step": 20350 }, { "epoch": 0.93, "learning_rate": 4.545516957297817e-05, "loss": 2.3917, "step": 20360 }, { "epoch": 0.93, "learning_rate": 4.545288113872488e-05, "loss": 2.241, "step": 20370 }, { "epoch": 0.93, "learning_rate": 4.54505927044716e-05, "loss": 2.3658, "step": 20380 }, { "epoch": 0.93, "learning_rate": 4.544830427021832e-05, "loss": 2.3818, "step": 20390 }, { "epoch": 0.93, "learning_rate": 4.544601583596503e-05, "loss": 2.4471, "step": 20400 }, { "epoch": 0.93, "learning_rate": 4.544372740171175e-05, "loss": 2.2252, "step": 20410 }, { "epoch": 0.93, "learning_rate": 4.5441438967458466e-05, "loss": 2.5253, "step": 20420 }, { "epoch": 0.93, "learning_rate": 4.543915053320518e-05, "loss": 2.3198, "step": 20430 }, { "epoch": 0.93, "learning_rate": 4.54368620989519e-05, "loss": 2.3176, "step": 20440 }, { "epoch": 0.93, "learning_rate": 4.5434573664698616e-05, "loss": 2.3801, "step": 20450 }, { "epoch": 0.93, "learning_rate": 4.543228523044533e-05, "loss": 2.5452, "step": 20460 }, { "epoch": 0.93, "learning_rate": 4.542999679619205e-05, "loss": 2.5314, "step": 20470 }, { "epoch": 0.94, "learning_rate": 4.5427708361938765e-05, "loss": 2.302, "step": 20480 }, { "epoch": 0.94, "learning_rate": 4.542541992768548e-05, "loss": 2.1671, "step": 20490 }, { "epoch": 0.94, "learning_rate": 4.54231314934322e-05, "loss": 2.2751, "step": 20500 }, { "epoch": 0.94, "learning_rate": 4.5420843059178914e-05, "loss": 2.2784, "step": 20510 }, { "epoch": 0.94, "learning_rate": 4.541855462492563e-05, "loss": 2.4393, "step": 20520 }, { "epoch": 0.94, "learning_rate": 4.541626619067235e-05, "loss": 2.459, "step": 20530 }, { "epoch": 0.94, "learning_rate": 4.541397775641906e-05, "loss": 2.2623, "step": 20540 }, { "epoch": 0.94, "learning_rate": 4.541168932216578e-05, "loss": 2.3569, "step": 20550 }, { "epoch": 0.94, "learning_rate": 4.540940088791249e-05, "loss": 2.2569, "step": 20560 }, { "epoch": 0.94, "learning_rate": 4.5407112453659205e-05, "loss": 2.2054, "step": 20570 }, { "epoch": 0.94, "learning_rate": 4.540482401940592e-05, "loss": 2.2561, "step": 20580 }, { "epoch": 0.94, "learning_rate": 4.540253558515264e-05, "loss": 2.255, "step": 20590 }, { "epoch": 0.94, "learning_rate": 4.5400247150899355e-05, "loss": 2.4229, "step": 20600 }, { "epoch": 0.94, "learning_rate": 4.539795871664607e-05, "loss": 2.2383, "step": 20610 }, { "epoch": 0.94, "learning_rate": 4.539567028239279e-05, "loss": 2.3779, "step": 20620 }, { "epoch": 0.94, "learning_rate": 4.5393381848139504e-05, "loss": 2.3753, "step": 20630 }, { "epoch": 0.94, "learning_rate": 4.539109341388622e-05, "loss": 2.2796, "step": 20640 }, { "epoch": 0.94, "learning_rate": 4.538880497963294e-05, "loss": 2.3429, "step": 20650 }, { "epoch": 0.94, "learning_rate": 4.538651654537965e-05, "loss": 2.3673, "step": 20660 }, { "epoch": 0.94, "learning_rate": 4.538422811112637e-05, "loss": 2.4409, "step": 20670 }, { "epoch": 0.94, "learning_rate": 4.538193967687309e-05, "loss": 2.2527, "step": 20680 }, { "epoch": 0.94, "learning_rate": 4.53796512426198e-05, "loss": 2.1832, "step": 20690 }, { "epoch": 0.95, "learning_rate": 4.5377362808366516e-05, "loss": 2.3227, "step": 20700 }, { "epoch": 0.95, "learning_rate": 4.537507437411324e-05, "loss": 2.2251, "step": 20710 }, { "epoch": 0.95, "learning_rate": 4.537278593985995e-05, "loss": 2.2902, "step": 20720 }, { "epoch": 0.95, "learning_rate": 4.5370497505606665e-05, "loss": 2.1874, "step": 20730 }, { "epoch": 0.95, "learning_rate": 4.5368209071353386e-05, "loss": 2.2552, "step": 20740 }, { "epoch": 0.95, "learning_rate": 4.5365920637100094e-05, "loss": 2.3071, "step": 20750 }, { "epoch": 0.95, "learning_rate": 4.5363632202846815e-05, "loss": 2.2363, "step": 20760 }, { "epoch": 0.95, "learning_rate": 4.536134376859353e-05, "loss": 2.3809, "step": 20770 }, { "epoch": 0.95, "learning_rate": 4.535905533434024e-05, "loss": 2.2887, "step": 20780 }, { "epoch": 0.95, "learning_rate": 4.5356766900086964e-05, "loss": 2.3122, "step": 20790 }, { "epoch": 0.95, "learning_rate": 4.535447846583368e-05, "loss": 2.2747, "step": 20800 }, { "epoch": 0.95, "learning_rate": 4.535219003158039e-05, "loss": 2.375, "step": 20810 }, { "epoch": 0.95, "learning_rate": 4.534990159732711e-05, "loss": 2.3258, "step": 20820 }, { "epoch": 0.95, "learning_rate": 4.534761316307383e-05, "loss": 2.3469, "step": 20830 }, { "epoch": 0.95, "learning_rate": 4.534532472882054e-05, "loss": 2.487, "step": 20840 }, { "epoch": 0.95, "learning_rate": 4.534303629456726e-05, "loss": 2.3965, "step": 20850 }, { "epoch": 0.95, "learning_rate": 4.5340747860313976e-05, "loss": 2.2865, "step": 20860 }, { "epoch": 0.95, "learning_rate": 4.533845942606069e-05, "loss": 2.3393, "step": 20870 }, { "epoch": 0.95, "learning_rate": 4.533617099180741e-05, "loss": 2.3584, "step": 20880 }, { "epoch": 0.95, "learning_rate": 4.5333882557554125e-05, "loss": 2.2174, "step": 20890 }, { "epoch": 0.95, "learning_rate": 4.533159412330084e-05, "loss": 2.5349, "step": 20900 }, { "epoch": 0.95, "learning_rate": 4.532930568904756e-05, "loss": 2.3475, "step": 20910 }, { "epoch": 0.96, "learning_rate": 4.5327017254794275e-05, "loss": 2.2508, "step": 20920 }, { "epoch": 0.96, "learning_rate": 4.532472882054099e-05, "loss": 2.4167, "step": 20930 }, { "epoch": 0.96, "learning_rate": 4.532244038628771e-05, "loss": 2.2625, "step": 20940 }, { "epoch": 0.96, "learning_rate": 4.532015195203442e-05, "loss": 2.3363, "step": 20950 }, { "epoch": 0.96, "learning_rate": 4.531786351778113e-05, "loss": 2.3302, "step": 20960 }, { "epoch": 0.96, "learning_rate": 4.531557508352785e-05, "loss": 2.3186, "step": 20970 }, { "epoch": 0.96, "learning_rate": 4.5313286649274566e-05, "loss": 2.3864, "step": 20980 }, { "epoch": 0.96, "learning_rate": 4.531099821502128e-05, "loss": 2.3227, "step": 20990 }, { "epoch": 0.96, "learning_rate": 4.5308709780768e-05, "loss": 2.2577, "step": 21000 }, { "epoch": 0.96, "learning_rate": 4.5306421346514715e-05, "loss": 2.2942, "step": 21010 }, { "epoch": 0.96, "learning_rate": 4.530413291226143e-05, "loss": 2.2774, "step": 21020 }, { "epoch": 0.96, "learning_rate": 4.530184447800815e-05, "loss": 2.3066, "step": 21030 }, { "epoch": 0.96, "learning_rate": 4.5299556043754865e-05, "loss": 2.336, "step": 21040 }, { "epoch": 0.96, "learning_rate": 4.529726760950158e-05, "loss": 2.3569, "step": 21050 }, { "epoch": 0.96, "learning_rate": 4.52949791752483e-05, "loss": 2.3581, "step": 21060 }, { "epoch": 0.96, "learning_rate": 4.5292690740995014e-05, "loss": 2.3838, "step": 21070 }, { "epoch": 0.96, "learning_rate": 4.529040230674173e-05, "loss": 2.3881, "step": 21080 }, { "epoch": 0.96, "learning_rate": 4.528811387248845e-05, "loss": 2.1888, "step": 21090 }, { "epoch": 0.96, "learning_rate": 4.528582543823516e-05, "loss": 2.2905, "step": 21100 }, { "epoch": 0.96, "learning_rate": 4.528353700398188e-05, "loss": 2.3091, "step": 21110 }, { "epoch": 0.96, "learning_rate": 4.52812485697286e-05, "loss": 2.3714, "step": 21120 }, { "epoch": 0.96, "learning_rate": 4.527896013547531e-05, "loss": 2.3256, "step": 21130 }, { "epoch": 0.97, "learning_rate": 4.5276671701222026e-05, "loss": 2.1732, "step": 21140 }, { "epoch": 0.97, "learning_rate": 4.527438326696874e-05, "loss": 2.4391, "step": 21150 }, { "epoch": 0.97, "learning_rate": 4.5272094832715455e-05, "loss": 2.342, "step": 21160 }, { "epoch": 0.97, "learning_rate": 4.5269806398462175e-05, "loss": 2.4677, "step": 21170 }, { "epoch": 0.97, "learning_rate": 4.526751796420889e-05, "loss": 2.419, "step": 21180 }, { "epoch": 0.97, "learning_rate": 4.5265229529955604e-05, "loss": 2.3068, "step": 21190 }, { "epoch": 0.97, "learning_rate": 4.5262941095702325e-05, "loss": 2.3427, "step": 21200 }, { "epoch": 0.97, "learning_rate": 4.526065266144904e-05, "loss": 2.2866, "step": 21210 }, { "epoch": 0.97, "learning_rate": 4.525836422719575e-05, "loss": 2.3299, "step": 21220 }, { "epoch": 0.97, "learning_rate": 4.5256075792942474e-05, "loss": 2.1424, "step": 21230 }, { "epoch": 0.97, "learning_rate": 4.525378735868919e-05, "loss": 2.2744, "step": 21240 }, { "epoch": 0.97, "learning_rate": 4.52514989244359e-05, "loss": 2.618, "step": 21250 }, { "epoch": 0.97, "learning_rate": 4.524921049018262e-05, "loss": 2.2943, "step": 21260 }, { "epoch": 0.97, "learning_rate": 4.524692205592934e-05, "loss": 2.225, "step": 21270 }, { "epoch": 0.97, "learning_rate": 4.524463362167605e-05, "loss": 2.264, "step": 21280 }, { "epoch": 0.97, "learning_rate": 4.524234518742277e-05, "loss": 2.2313, "step": 21290 }, { "epoch": 0.97, "learning_rate": 4.5240056753169486e-05, "loss": 2.2675, "step": 21300 }, { "epoch": 0.97, "learning_rate": 4.52377683189162e-05, "loss": 2.2618, "step": 21310 }, { "epoch": 0.97, "learning_rate": 4.523547988466292e-05, "loss": 2.3336, "step": 21320 }, { "epoch": 0.97, "learning_rate": 4.5233191450409635e-05, "loss": 2.315, "step": 21330 }, { "epoch": 0.97, "learning_rate": 4.523090301615635e-05, "loss": 2.2581, "step": 21340 }, { "epoch": 0.97, "learning_rate": 4.5228614581903064e-05, "loss": 2.1762, "step": 21350 }, { "epoch": 0.98, "learning_rate": 4.522632614764978e-05, "loss": 2.2606, "step": 21360 }, { "epoch": 0.98, "learning_rate": 4.522403771339649e-05, "loss": 2.1977, "step": 21370 }, { "epoch": 0.98, "learning_rate": 4.522174927914321e-05, "loss": 2.3725, "step": 21380 }, { "epoch": 0.98, "learning_rate": 4.521946084488993e-05, "loss": 2.4273, "step": 21390 }, { "epoch": 0.98, "learning_rate": 4.521717241063664e-05, "loss": 2.3961, "step": 21400 }, { "epoch": 0.98, "learning_rate": 4.521488397638336e-05, "loss": 2.3151, "step": 21410 }, { "epoch": 0.98, "learning_rate": 4.5212595542130076e-05, "loss": 2.3598, "step": 21420 }, { "epoch": 0.98, "learning_rate": 4.521030710787679e-05, "loss": 2.3156, "step": 21430 }, { "epoch": 0.98, "learning_rate": 4.520801867362351e-05, "loss": 2.2962, "step": 21440 }, { "epoch": 0.98, "learning_rate": 4.5205730239370225e-05, "loss": 2.3455, "step": 21450 }, { "epoch": 0.98, "learning_rate": 4.520344180511694e-05, "loss": 2.1982, "step": 21460 }, { "epoch": 0.98, "learning_rate": 4.520115337086366e-05, "loss": 2.389, "step": 21470 }, { "epoch": 0.98, "learning_rate": 4.5198864936610375e-05, "loss": 2.3785, "step": 21480 }, { "epoch": 0.98, "learning_rate": 4.519657650235709e-05, "loss": 2.5595, "step": 21490 }, { "epoch": 0.98, "learning_rate": 4.519428806810381e-05, "loss": 2.2921, "step": 21500 }, { "epoch": 0.98, "learning_rate": 4.5191999633850524e-05, "loss": 2.3122, "step": 21510 }, { "epoch": 0.98, "learning_rate": 4.518971119959724e-05, "loss": 2.1961, "step": 21520 }, { "epoch": 0.98, "learning_rate": 4.518742276534396e-05, "loss": 2.3397, "step": 21530 }, { "epoch": 0.98, "learning_rate": 4.5185134331090666e-05, "loss": 2.3062, "step": 21540 }, { "epoch": 0.98, "learning_rate": 4.518284589683738e-05, "loss": 2.1492, "step": 21550 }, { "epoch": 0.98, "learning_rate": 4.51805574625841e-05, "loss": 2.2735, "step": 21560 }, { "epoch": 0.98, "learning_rate": 4.5178269028330815e-05, "loss": 2.4553, "step": 21570 }, { "epoch": 0.99, "learning_rate": 4.517598059407753e-05, "loss": 2.1891, "step": 21580 }, { "epoch": 0.99, "learning_rate": 4.517369215982425e-05, "loss": 2.1508, "step": 21590 }, { "epoch": 0.99, "learning_rate": 4.5171403725570964e-05, "loss": 2.2515, "step": 21600 }, { "epoch": 0.99, "learning_rate": 4.516911529131768e-05, "loss": 2.331, "step": 21610 }, { "epoch": 0.99, "learning_rate": 4.51668268570644e-05, "loss": 2.1907, "step": 21620 }, { "epoch": 0.99, "learning_rate": 4.5164538422811114e-05, "loss": 2.2457, "step": 21630 }, { "epoch": 0.99, "learning_rate": 4.516224998855783e-05, "loss": 2.3335, "step": 21640 }, { "epoch": 0.99, "learning_rate": 4.515996155430455e-05, "loss": 2.3939, "step": 21650 }, { "epoch": 0.99, "learning_rate": 4.515767312005126e-05, "loss": 2.4316, "step": 21660 }, { "epoch": 0.99, "learning_rate": 4.515538468579798e-05, "loss": 2.0806, "step": 21670 }, { "epoch": 0.99, "learning_rate": 4.51530962515447e-05, "loss": 2.4001, "step": 21680 }, { "epoch": 0.99, "learning_rate": 4.515080781729141e-05, "loss": 2.5283, "step": 21690 }, { "epoch": 0.99, "learning_rate": 4.5148519383038126e-05, "loss": 2.34, "step": 21700 }, { "epoch": 0.99, "learning_rate": 4.514623094878485e-05, "loss": 2.4191, "step": 21710 }, { "epoch": 0.99, "learning_rate": 4.514394251453156e-05, "loss": 2.3545, "step": 21720 }, { "epoch": 0.99, "learning_rate": 4.5141654080278275e-05, "loss": 2.3177, "step": 21730 }, { "epoch": 0.99, "learning_rate": 4.513936564602499e-05, "loss": 2.1934, "step": 21740 }, { "epoch": 0.99, "learning_rate": 4.5137077211771704e-05, "loss": 2.389, "step": 21750 }, { "epoch": 0.99, "learning_rate": 4.5134788777518424e-05, "loss": 2.2787, "step": 21760 }, { "epoch": 0.99, "learning_rate": 4.513250034326514e-05, "loss": 2.34, "step": 21770 }, { "epoch": 0.99, "learning_rate": 4.513021190901185e-05, "loss": 2.3498, "step": 21780 }, { "epoch": 0.99, "learning_rate": 4.5127923474758574e-05, "loss": 2.3854, "step": 21790 }, { "epoch": 1.0, "learning_rate": 4.512563504050529e-05, "loss": 2.3477, "step": 21800 }, { "epoch": 1.0, "learning_rate": 4.5123346606252e-05, "loss": 2.2619, "step": 21810 }, { "epoch": 1.0, "learning_rate": 4.512105817199872e-05, "loss": 2.3444, "step": 21820 }, { "epoch": 1.0, "learning_rate": 4.511876973774544e-05, "loss": 2.3916, "step": 21830 }, { "epoch": 1.0, "learning_rate": 4.511648130349215e-05, "loss": 2.5205, "step": 21840 }, { "epoch": 1.0, "learning_rate": 4.511419286923887e-05, "loss": 2.3267, "step": 21850 }, { "epoch": 1.0, "learning_rate": 4.5111904434985586e-05, "loss": 2.2666, "step": 21860 }, { "epoch": 1.0, "learning_rate": 4.51096160007323e-05, "loss": 2.2716, "step": 21870 }, { "epoch": 1.0, "learning_rate": 4.510732756647902e-05, "loss": 2.3064, "step": 21880 }, { "epoch": 1.0, "learning_rate": 4.5105039132225735e-05, "loss": 2.4477, "step": 21890 }, { "epoch": 1.0, "eval_cer": 0.6812600435222144, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 2.216987371444702, "eval_runtime": 2827.7326, "eval_samples_per_second": 3.738, "eval_steps_per_second": 1.869, "eval_wer": 0.9927152317880795, "step": 21899 }, { "epoch": 1.0, "learning_rate": 4.510275069797245e-05, "loss": 2.2591, "step": 21900 }, { "epoch": 1.0, "learning_rate": 4.510046226371917e-05, "loss": 2.4198, "step": 21910 }, { "epoch": 1.0, "learning_rate": 4.5098173829465885e-05, "loss": 2.3095, "step": 21920 }, { "epoch": 1.0, "learning_rate": 4.50958853952126e-05, "loss": 2.2072, "step": 21930 }, { "epoch": 1.0, "learning_rate": 4.509359696095931e-05, "loss": 2.4082, "step": 21940 }, { "epoch": 1.0, "learning_rate": 4.509130852670603e-05, "loss": 2.4049, "step": 21950 }, { "epoch": 1.0, "learning_rate": 4.508902009245274e-05, "loss": 2.278, "step": 21960 }, { "epoch": 1.0, "learning_rate": 4.508673165819946e-05, "loss": 2.1943, "step": 21970 }, { "epoch": 1.0, "learning_rate": 4.5084443223946176e-05, "loss": 2.3004, "step": 21980 }, { "epoch": 1.0, "learning_rate": 4.508215478969289e-05, "loss": 2.339, "step": 21990 }, { "epoch": 1.0, "learning_rate": 4.507986635543961e-05, "loss": 2.3528, "step": 22000 }, { "epoch": 1.01, "learning_rate": 4.5077577921186325e-05, "loss": 2.3098, "step": 22010 }, { "epoch": 1.01, "learning_rate": 4.507528948693304e-05, "loss": 2.322, "step": 22020 }, { "epoch": 1.01, "learning_rate": 4.507300105267976e-05, "loss": 2.3117, "step": 22030 }, { "epoch": 1.01, "learning_rate": 4.5070712618426474e-05, "loss": 2.2396, "step": 22040 }, { "epoch": 1.01, "learning_rate": 4.506842418417319e-05, "loss": 2.41, "step": 22050 }, { "epoch": 1.01, "learning_rate": 4.506613574991991e-05, "loss": 2.3135, "step": 22060 }, { "epoch": 1.01, "learning_rate": 4.5063847315666624e-05, "loss": 2.2508, "step": 22070 }, { "epoch": 1.01, "learning_rate": 4.506155888141334e-05, "loss": 2.2564, "step": 22080 }, { "epoch": 1.01, "learning_rate": 4.505927044716006e-05, "loss": 2.3663, "step": 22090 }, { "epoch": 1.01, "learning_rate": 4.505698201290677e-05, "loss": 2.3373, "step": 22100 }, { "epoch": 1.01, "learning_rate": 4.505469357865349e-05, "loss": 2.3727, "step": 22110 }, { "epoch": 1.01, "learning_rate": 4.505240514440021e-05, "loss": 2.3013, "step": 22120 }, { "epoch": 1.01, "learning_rate": 4.505011671014692e-05, "loss": 2.3857, "step": 22130 }, { "epoch": 1.01, "learning_rate": 4.5047828275893636e-05, "loss": 2.3795, "step": 22140 }, { "epoch": 1.01, "learning_rate": 4.504553984164035e-05, "loss": 2.1462, "step": 22150 }, { "epoch": 1.01, "learning_rate": 4.5043251407387064e-05, "loss": 2.2378, "step": 22160 }, { "epoch": 1.01, "learning_rate": 4.5040962973133785e-05, "loss": 2.2895, "step": 22170 }, { "epoch": 1.01, "learning_rate": 4.50386745388805e-05, "loss": 2.2271, "step": 22180 }, { "epoch": 1.01, "learning_rate": 4.5036386104627214e-05, "loss": 2.2596, "step": 22190 }, { "epoch": 1.01, "learning_rate": 4.5034097670373934e-05, "loss": 2.2243, "step": 22200 }, { "epoch": 1.01, "learning_rate": 4.503180923612065e-05, "loss": 2.417, "step": 22210 }, { "epoch": 1.01, "learning_rate": 4.502952080186736e-05, "loss": 2.2767, "step": 22220 }, { "epoch": 1.02, "learning_rate": 4.5027232367614084e-05, "loss": 2.4716, "step": 22230 }, { "epoch": 1.02, "learning_rate": 4.50249439333608e-05, "loss": 2.2412, "step": 22240 }, { "epoch": 1.02, "learning_rate": 4.502265549910751e-05, "loss": 2.1819, "step": 22250 }, { "epoch": 1.02, "learning_rate": 4.502036706485423e-05, "loss": 2.1152, "step": 22260 }, { "epoch": 1.02, "learning_rate": 4.501807863060095e-05, "loss": 2.3394, "step": 22270 }, { "epoch": 1.02, "learning_rate": 4.501579019634766e-05, "loss": 2.3747, "step": 22280 }, { "epoch": 1.02, "learning_rate": 4.501350176209438e-05, "loss": 2.2888, "step": 22290 }, { "epoch": 1.02, "learning_rate": 4.5011213327841096e-05, "loss": 2.1831, "step": 22300 }, { "epoch": 1.02, "learning_rate": 4.500892489358781e-05, "loss": 2.1955, "step": 22310 }, { "epoch": 1.02, "learning_rate": 4.500663645933453e-05, "loss": 2.1928, "step": 22320 }, { "epoch": 1.02, "learning_rate": 4.500434802508124e-05, "loss": 2.3824, "step": 22330 }, { "epoch": 1.02, "learning_rate": 4.500205959082795e-05, "loss": 2.319, "step": 22340 }, { "epoch": 1.02, "learning_rate": 4.4999771156574674e-05, "loss": 2.1891, "step": 22350 }, { "epoch": 1.02, "learning_rate": 4.499748272232139e-05, "loss": 2.2493, "step": 22360 }, { "epoch": 1.02, "learning_rate": 4.49951942880681e-05, "loss": 2.3903, "step": 22370 }, { "epoch": 1.02, "learning_rate": 4.499290585381482e-05, "loss": 2.3518, "step": 22380 }, { "epoch": 1.02, "learning_rate": 4.499061741956154e-05, "loss": 2.2863, "step": 22390 }, { "epoch": 1.02, "learning_rate": 4.498832898530825e-05, "loss": 2.4015, "step": 22400 }, { "epoch": 1.02, "learning_rate": 4.498604055105497e-05, "loss": 2.2452, "step": 22410 }, { "epoch": 1.02, "learning_rate": 4.4983752116801686e-05, "loss": 2.4249, "step": 22420 }, { "epoch": 1.02, "learning_rate": 4.49814636825484e-05, "loss": 2.3144, "step": 22430 }, { "epoch": 1.02, "learning_rate": 4.497917524829512e-05, "loss": 2.2673, "step": 22440 }, { "epoch": 1.03, "learning_rate": 4.4976886814041835e-05, "loss": 2.5026, "step": 22450 }, { "epoch": 1.03, "learning_rate": 4.497459837978855e-05, "loss": 2.1159, "step": 22460 }, { "epoch": 1.03, "learning_rate": 4.497230994553527e-05, "loss": 2.2959, "step": 22470 }, { "epoch": 1.03, "learning_rate": 4.4970021511281984e-05, "loss": 2.3364, "step": 22480 }, { "epoch": 1.03, "learning_rate": 4.49677330770287e-05, "loss": 2.3494, "step": 22490 }, { "epoch": 1.03, "learning_rate": 4.496544464277542e-05, "loss": 2.2194, "step": 22500 }, { "epoch": 1.03, "learning_rate": 4.4963156208522134e-05, "loss": 2.42, "step": 22510 }, { "epoch": 1.03, "learning_rate": 4.496086777426885e-05, "loss": 2.2227, "step": 22520 }, { "epoch": 1.03, "learning_rate": 4.495857934001556e-05, "loss": 2.2182, "step": 22530 }, { "epoch": 1.03, "learning_rate": 4.4956290905762276e-05, "loss": 2.4551, "step": 22540 }, { "epoch": 1.03, "learning_rate": 4.4954002471509e-05, "loss": 2.1658, "step": 22550 }, { "epoch": 1.03, "learning_rate": 4.495171403725571e-05, "loss": 2.2068, "step": 22560 }, { "epoch": 1.03, "learning_rate": 4.4949425603002425e-05, "loss": 2.3336, "step": 22570 }, { "epoch": 1.03, "learning_rate": 4.4947137168749146e-05, "loss": 2.3748, "step": 22580 }, { "epoch": 1.03, "learning_rate": 4.494484873449586e-05, "loss": 2.3007, "step": 22590 }, { "epoch": 1.03, "learning_rate": 4.4942560300242574e-05, "loss": 2.1025, "step": 22600 }, { "epoch": 1.03, "learning_rate": 4.494027186598929e-05, "loss": 2.3296, "step": 22610 }, { "epoch": 1.03, "learning_rate": 4.493798343173601e-05, "loss": 2.2967, "step": 22620 }, { "epoch": 1.03, "learning_rate": 4.4935694997482724e-05, "loss": 2.2729, "step": 22630 }, { "epoch": 1.03, "learning_rate": 4.493340656322944e-05, "loss": 2.2964, "step": 22640 }, { "epoch": 1.03, "learning_rate": 4.493111812897616e-05, "loss": 2.3236, "step": 22650 }, { "epoch": 1.03, "learning_rate": 4.492882969472287e-05, "loss": 2.2824, "step": 22660 }, { "epoch": 1.04, "learning_rate": 4.492654126046959e-05, "loss": 2.4738, "step": 22670 }, { "epoch": 1.04, "learning_rate": 4.492425282621631e-05, "loss": 2.333, "step": 22680 }, { "epoch": 1.04, "learning_rate": 4.492196439196302e-05, "loss": 2.1323, "step": 22690 }, { "epoch": 1.04, "learning_rate": 4.4919675957709736e-05, "loss": 2.295, "step": 22700 }, { "epoch": 1.04, "learning_rate": 4.491738752345646e-05, "loss": 2.2812, "step": 22710 }, { "epoch": 1.04, "learning_rate": 4.491509908920317e-05, "loss": 2.352, "step": 22720 }, { "epoch": 1.04, "learning_rate": 4.4912810654949885e-05, "loss": 2.2512, "step": 22730 }, { "epoch": 1.04, "learning_rate": 4.49105222206966e-05, "loss": 2.2468, "step": 22740 }, { "epoch": 1.04, "learning_rate": 4.4908233786443313e-05, "loss": 2.181, "step": 22750 }, { "epoch": 1.04, "learning_rate": 4.4905945352190034e-05, "loss": 2.3713, "step": 22760 }, { "epoch": 1.04, "learning_rate": 4.490365691793675e-05, "loss": 2.2591, "step": 22770 }, { "epoch": 1.04, "learning_rate": 4.490136848368346e-05, "loss": 2.272, "step": 22780 }, { "epoch": 1.04, "learning_rate": 4.4899080049430184e-05, "loss": 2.2271, "step": 22790 }, { "epoch": 1.04, "learning_rate": 4.48967916151769e-05, "loss": 2.249, "step": 22800 }, { "epoch": 1.04, "learning_rate": 4.489450318092361e-05, "loss": 2.2281, "step": 22810 }, { "epoch": 1.04, "learning_rate": 4.489221474667033e-05, "loss": 2.313, "step": 22820 }, { "epoch": 1.04, "learning_rate": 4.488992631241705e-05, "loss": 2.2367, "step": 22830 }, { "epoch": 1.04, "learning_rate": 4.488763787816376e-05, "loss": 2.2601, "step": 22840 }, { "epoch": 1.04, "learning_rate": 4.488534944391048e-05, "loss": 2.3087, "step": 22850 }, { "epoch": 1.04, "learning_rate": 4.4883061009657196e-05, "loss": 2.2942, "step": 22860 }, { "epoch": 1.04, "learning_rate": 4.488077257540391e-05, "loss": 2.2147, "step": 22870 }, { "epoch": 1.04, "learning_rate": 4.487848414115063e-05, "loss": 2.2291, "step": 22880 }, { "epoch": 1.05, "learning_rate": 4.4876195706897345e-05, "loss": 2.327, "step": 22890 }, { "epoch": 1.05, "learning_rate": 4.487390727264406e-05, "loss": 2.2733, "step": 22900 }, { "epoch": 1.05, "learning_rate": 4.487161883839078e-05, "loss": 2.2619, "step": 22910 }, { "epoch": 1.05, "learning_rate": 4.4869330404137494e-05, "loss": 2.4188, "step": 22920 }, { "epoch": 1.05, "learning_rate": 4.48670419698842e-05, "loss": 2.3818, "step": 22930 }, { "epoch": 1.05, "learning_rate": 4.486475353563092e-05, "loss": 2.2136, "step": 22940 }, { "epoch": 1.05, "learning_rate": 4.486246510137764e-05, "loss": 2.2647, "step": 22950 }, { "epoch": 1.05, "learning_rate": 4.486017666712435e-05, "loss": 2.3816, "step": 22960 }, { "epoch": 1.05, "learning_rate": 4.485788823287107e-05, "loss": 2.2459, "step": 22970 }, { "epoch": 1.05, "learning_rate": 4.4855599798617786e-05, "loss": 2.2887, "step": 22980 }, { "epoch": 1.05, "learning_rate": 4.48533113643645e-05, "loss": 2.2426, "step": 22990 }, { "epoch": 1.05, "learning_rate": 4.485102293011122e-05, "loss": 2.2112, "step": 23000 }, { "epoch": 1.05, "learning_rate": 4.4848734495857935e-05, "loss": 2.3734, "step": 23010 }, { "epoch": 1.05, "learning_rate": 4.484644606160465e-05, "loss": 2.2343, "step": 23020 }, { "epoch": 1.05, "learning_rate": 4.484415762735137e-05, "loss": 2.2753, "step": 23030 }, { "epoch": 1.05, "learning_rate": 4.4841869193098084e-05, "loss": 2.2911, "step": 23040 }, { "epoch": 1.05, "learning_rate": 4.48395807588448e-05, "loss": 2.4989, "step": 23050 }, { "epoch": 1.05, "learning_rate": 4.483729232459152e-05, "loss": 2.3807, "step": 23060 }, { "epoch": 1.05, "learning_rate": 4.4835003890338233e-05, "loss": 2.2831, "step": 23070 }, { "epoch": 1.05, "learning_rate": 4.483271545608495e-05, "loss": 2.3815, "step": 23080 }, { "epoch": 1.05, "learning_rate": 4.483042702183167e-05, "loss": 2.2975, "step": 23090 }, { "epoch": 1.05, "learning_rate": 4.482813858757838e-05, "loss": 2.2835, "step": 23100 }, { "epoch": 1.06, "learning_rate": 4.48258501533251e-05, "loss": 2.2485, "step": 23110 }, { "epoch": 1.06, "learning_rate": 4.482356171907181e-05, "loss": 2.3783, "step": 23120 }, { "epoch": 1.06, "learning_rate": 4.4821273284818525e-05, "loss": 2.183, "step": 23130 }, { "epoch": 1.06, "learning_rate": 4.4818984850565246e-05, "loss": 2.1901, "step": 23140 }, { "epoch": 1.06, "learning_rate": 4.481669641631196e-05, "loss": 2.2445, "step": 23150 }, { "epoch": 1.06, "learning_rate": 4.4814407982058674e-05, "loss": 2.375, "step": 23160 }, { "epoch": 1.06, "learning_rate": 4.4812119547805395e-05, "loss": 2.2891, "step": 23170 }, { "epoch": 1.06, "learning_rate": 4.480983111355211e-05, "loss": 2.441, "step": 23180 }, { "epoch": 1.06, "learning_rate": 4.4807542679298823e-05, "loss": 2.246, "step": 23190 }, { "epoch": 1.06, "learning_rate": 4.4805254245045544e-05, "loss": 2.2423, "step": 23200 }, { "epoch": 1.06, "learning_rate": 4.480296581079226e-05, "loss": 2.289, "step": 23210 }, { "epoch": 1.06, "learning_rate": 4.480067737653897e-05, "loss": 2.2892, "step": 23220 }, { "epoch": 1.06, "learning_rate": 4.4798388942285694e-05, "loss": 2.3209, "step": 23230 }, { "epoch": 1.06, "learning_rate": 4.479610050803241e-05, "loss": 2.197, "step": 23240 }, { "epoch": 1.06, "learning_rate": 4.479381207377912e-05, "loss": 2.678, "step": 23250 }, { "epoch": 1.06, "learning_rate": 4.479152363952584e-05, "loss": 2.323, "step": 23260 }, { "epoch": 1.06, "learning_rate": 4.478923520527256e-05, "loss": 2.4899, "step": 23270 }, { "epoch": 1.06, "learning_rate": 4.478694677101927e-05, "loss": 2.2662, "step": 23280 }, { "epoch": 1.06, "learning_rate": 4.478465833676599e-05, "loss": 2.0991, "step": 23290 }, { "epoch": 1.06, "learning_rate": 4.4782369902512706e-05, "loss": 2.2687, "step": 23300 }, { "epoch": 1.06, "learning_rate": 4.478008146825942e-05, "loss": 2.3687, "step": 23310 }, { "epoch": 1.06, "learning_rate": 4.4777793034006134e-05, "loss": 2.318, "step": 23320 }, { "epoch": 1.07, "learning_rate": 4.477550459975285e-05, "loss": 2.1377, "step": 23330 }, { "epoch": 1.07, "learning_rate": 4.477321616549956e-05, "loss": 2.2664, "step": 23340 }, { "epoch": 1.07, "learning_rate": 4.4770927731246283e-05, "loss": 2.3058, "step": 23350 }, { "epoch": 1.07, "learning_rate": 4.4768639296993e-05, "loss": 2.329, "step": 23360 }, { "epoch": 1.07, "learning_rate": 4.476635086273971e-05, "loss": 2.2265, "step": 23370 }, { "epoch": 1.07, "learning_rate": 4.476406242848643e-05, "loss": 2.3483, "step": 23380 }, { "epoch": 1.07, "learning_rate": 4.476177399423315e-05, "loss": 2.2715, "step": 23390 }, { "epoch": 1.07, "learning_rate": 4.475948555997986e-05, "loss": 2.2603, "step": 23400 }, { "epoch": 1.07, "learning_rate": 4.475719712572658e-05, "loss": 2.2793, "step": 23410 }, { "epoch": 1.07, "learning_rate": 4.4754908691473296e-05, "loss": 2.1362, "step": 23420 }, { "epoch": 1.07, "learning_rate": 4.475262025722001e-05, "loss": 2.1412, "step": 23430 }, { "epoch": 1.07, "learning_rate": 4.475033182296673e-05, "loss": 2.2475, "step": 23440 }, { "epoch": 1.07, "learning_rate": 4.4748043388713445e-05, "loss": 2.3936, "step": 23450 }, { "epoch": 1.07, "learning_rate": 4.474575495446016e-05, "loss": 2.4458, "step": 23460 }, { "epoch": 1.07, "learning_rate": 4.474346652020688e-05, "loss": 2.0833, "step": 23470 }, { "epoch": 1.07, "learning_rate": 4.4741178085953594e-05, "loss": 2.2319, "step": 23480 }, { "epoch": 1.07, "learning_rate": 4.473888965170031e-05, "loss": 2.2271, "step": 23490 }, { "epoch": 1.07, "learning_rate": 4.473660121744703e-05, "loss": 2.3031, "step": 23500 }, { "epoch": 1.07, "learning_rate": 4.4734312783193743e-05, "loss": 2.3666, "step": 23510 }, { "epoch": 1.07, "learning_rate": 4.473202434894046e-05, "loss": 2.2167, "step": 23520 }, { "epoch": 1.07, "learning_rate": 4.472973591468717e-05, "loss": 2.3349, "step": 23530 }, { "epoch": 1.07, "learning_rate": 4.4727447480433886e-05, "loss": 2.2888, "step": 23540 }, { "epoch": 1.08, "learning_rate": 4.472515904618061e-05, "loss": 2.3128, "step": 23550 }, { "epoch": 1.08, "learning_rate": 4.472287061192732e-05, "loss": 2.3149, "step": 23560 }, { "epoch": 1.08, "learning_rate": 4.4720582177674035e-05, "loss": 2.2801, "step": 23570 }, { "epoch": 1.08, "learning_rate": 4.4718293743420756e-05, "loss": 2.3798, "step": 23580 }, { "epoch": 1.08, "learning_rate": 4.471600530916747e-05, "loss": 2.2215, "step": 23590 }, { "epoch": 1.08, "learning_rate": 4.4713716874914184e-05, "loss": 2.2952, "step": 23600 }, { "epoch": 1.08, "learning_rate": 4.4711428440660905e-05, "loss": 2.3043, "step": 23610 }, { "epoch": 1.08, "learning_rate": 4.470914000640762e-05, "loss": 2.3361, "step": 23620 }, { "epoch": 1.08, "learning_rate": 4.470685157215433e-05, "loss": 2.3266, "step": 23630 }, { "epoch": 1.08, "learning_rate": 4.4704563137901054e-05, "loss": 2.2586, "step": 23640 }, { "epoch": 1.08, "learning_rate": 4.470227470364777e-05, "loss": 2.2866, "step": 23650 }, { "epoch": 1.08, "learning_rate": 4.469998626939448e-05, "loss": 2.2354, "step": 23660 }, { "epoch": 1.08, "learning_rate": 4.4697697835141203e-05, "loss": 2.313, "step": 23670 }, { "epoch": 1.08, "learning_rate": 4.469540940088792e-05, "loss": 2.2785, "step": 23680 }, { "epoch": 1.08, "learning_rate": 4.469312096663463e-05, "loss": 2.1694, "step": 23690 }, { "epoch": 1.08, "learning_rate": 4.469083253238135e-05, "loss": 2.2827, "step": 23700 }, { "epoch": 1.08, "learning_rate": 4.468854409812807e-05, "loss": 2.2527, "step": 23710 }, { "epoch": 1.08, "learning_rate": 4.4686255663874774e-05, "loss": 2.2837, "step": 23720 }, { "epoch": 1.08, "learning_rate": 4.4683967229621495e-05, "loss": 2.2601, "step": 23730 }, { "epoch": 1.08, "learning_rate": 4.468167879536821e-05, "loss": 2.2779, "step": 23740 }, { "epoch": 1.08, "learning_rate": 4.467939036111492e-05, "loss": 2.4629, "step": 23750 }, { "epoch": 1.08, "learning_rate": 4.4677101926861644e-05, "loss": 2.1741, "step": 23760 }, { "epoch": 1.09, "learning_rate": 4.467481349260836e-05, "loss": 2.4115, "step": 23770 }, { "epoch": 1.09, "learning_rate": 4.467252505835507e-05, "loss": 2.2655, "step": 23780 }, { "epoch": 1.09, "learning_rate": 4.4670236624101793e-05, "loss": 2.5191, "step": 23790 }, { "epoch": 1.09, "learning_rate": 4.466794818984851e-05, "loss": 2.3079, "step": 23800 }, { "epoch": 1.09, "learning_rate": 4.466565975559522e-05, "loss": 2.3611, "step": 23810 }, { "epoch": 1.09, "learning_rate": 4.466337132134194e-05, "loss": 2.3314, "step": 23820 }, { "epoch": 1.09, "learning_rate": 4.466108288708866e-05, "loss": 2.3499, "step": 23830 }, { "epoch": 1.09, "learning_rate": 4.465879445283537e-05, "loss": 2.3212, "step": 23840 }, { "epoch": 1.09, "learning_rate": 4.465650601858209e-05, "loss": 2.4589, "step": 23850 }, { "epoch": 1.09, "learning_rate": 4.4654217584328806e-05, "loss": 2.1917, "step": 23860 }, { "epoch": 1.09, "learning_rate": 4.465192915007552e-05, "loss": 2.1829, "step": 23870 }, { "epoch": 1.09, "learning_rate": 4.464964071582224e-05, "loss": 2.2347, "step": 23880 }, { "epoch": 1.09, "learning_rate": 4.4647352281568955e-05, "loss": 2.2641, "step": 23890 }, { "epoch": 1.09, "learning_rate": 4.464506384731567e-05, "loss": 2.2234, "step": 23900 }, { "epoch": 1.09, "learning_rate": 4.464277541306238e-05, "loss": 2.1802, "step": 23910 }, { "epoch": 1.09, "learning_rate": 4.46404869788091e-05, "loss": 2.2339, "step": 23920 }, { "epoch": 1.09, "learning_rate": 4.463819854455581e-05, "loss": 2.2941, "step": 23930 }, { "epoch": 1.09, "learning_rate": 4.463591011030253e-05, "loss": 2.3591, "step": 23940 }, { "epoch": 1.09, "learning_rate": 4.463362167604925e-05, "loss": 2.2954, "step": 23950 }, { "epoch": 1.09, "learning_rate": 4.463133324179596e-05, "loss": 2.1463, "step": 23960 }, { "epoch": 1.09, "learning_rate": 4.462904480754268e-05, "loss": 2.4745, "step": 23970 }, { "epoch": 1.09, "learning_rate": 4.4626756373289396e-05, "loss": 2.2623, "step": 23980 }, { "epoch": 1.1, "learning_rate": 4.462446793903611e-05, "loss": 2.237, "step": 23990 }, { "epoch": 1.1, "learning_rate": 4.462217950478283e-05, "loss": 2.1265, "step": 24000 }, { "epoch": 1.1, "learning_rate": 4.4619891070529545e-05, "loss": 2.2779, "step": 24010 }, { "epoch": 1.1, "learning_rate": 4.461760263627626e-05, "loss": 2.2308, "step": 24020 }, { "epoch": 1.1, "learning_rate": 4.461531420202298e-05, "loss": 2.2316, "step": 24030 }, { "epoch": 1.1, "learning_rate": 4.4613025767769694e-05, "loss": 2.1925, "step": 24040 }, { "epoch": 1.1, "learning_rate": 4.461073733351641e-05, "loss": 2.274, "step": 24050 }, { "epoch": 1.1, "learning_rate": 4.460844889926313e-05, "loss": 2.3622, "step": 24060 }, { "epoch": 1.1, "learning_rate": 4.460616046500984e-05, "loss": 2.3371, "step": 24070 }, { "epoch": 1.1, "learning_rate": 4.460387203075656e-05, "loss": 2.1992, "step": 24080 }, { "epoch": 1.1, "learning_rate": 4.460158359650328e-05, "loss": 2.355, "step": 24090 }, { "epoch": 1.1, "learning_rate": 4.459929516224999e-05, "loss": 2.1597, "step": 24100 }, { "epoch": 1.1, "learning_rate": 4.459700672799671e-05, "loss": 2.243, "step": 24110 }, { "epoch": 1.1, "learning_rate": 4.459471829374342e-05, "loss": 2.2384, "step": 24120 }, { "epoch": 1.1, "learning_rate": 4.4592429859490135e-05, "loss": 2.2699, "step": 24130 }, { "epoch": 1.1, "learning_rate": 4.4590141425236856e-05, "loss": 2.2844, "step": 24140 }, { "epoch": 1.1, "learning_rate": 4.458785299098357e-05, "loss": 2.3402, "step": 24150 }, { "epoch": 1.1, "learning_rate": 4.4585564556730284e-05, "loss": 2.2894, "step": 24160 }, { "epoch": 1.1, "learning_rate": 4.4583276122477005e-05, "loss": 2.2904, "step": 24170 }, { "epoch": 1.1, "learning_rate": 4.458098768822372e-05, "loss": 2.3202, "step": 24180 }, { "epoch": 1.1, "learning_rate": 4.457869925397043e-05, "loss": 2.3415, "step": 24190 }, { "epoch": 1.11, "learning_rate": 4.4576410819717154e-05, "loss": 2.2552, "step": 24200 }, { "epoch": 1.11, "learning_rate": 4.457412238546387e-05, "loss": 2.26, "step": 24210 }, { "epoch": 1.11, "learning_rate": 4.457183395121058e-05, "loss": 2.3254, "step": 24220 }, { "epoch": 1.11, "learning_rate": 4.45695455169573e-05, "loss": 2.2538, "step": 24230 }, { "epoch": 1.11, "learning_rate": 4.456725708270402e-05, "loss": 2.3127, "step": 24240 }, { "epoch": 1.11, "learning_rate": 4.456496864845073e-05, "loss": 2.2534, "step": 24250 }, { "epoch": 1.11, "learning_rate": 4.456268021419745e-05, "loss": 2.3047, "step": 24260 }, { "epoch": 1.11, "learning_rate": 4.456039177994417e-05, "loss": 2.1579, "step": 24270 }, { "epoch": 1.11, "learning_rate": 4.455810334569088e-05, "loss": 2.3842, "step": 24280 }, { "epoch": 1.11, "learning_rate": 4.45558149114376e-05, "loss": 2.3417, "step": 24290 }, { "epoch": 1.11, "learning_rate": 4.4553526477184316e-05, "loss": 2.2697, "step": 24300 }, { "epoch": 1.11, "learning_rate": 4.455123804293102e-05, "loss": 2.2501, "step": 24310 }, { "epoch": 1.11, "learning_rate": 4.4548949608677744e-05, "loss": 2.1765, "step": 24320 }, { "epoch": 1.11, "learning_rate": 4.454666117442446e-05, "loss": 2.2067, "step": 24330 }, { "epoch": 1.11, "learning_rate": 4.454437274017117e-05, "loss": 2.2983, "step": 24340 }, { "epoch": 1.11, "learning_rate": 4.454208430591789e-05, "loss": 2.1894, "step": 24350 }, { "epoch": 1.11, "learning_rate": 4.453979587166461e-05, "loss": 2.1605, "step": 24360 }, { "epoch": 1.11, "learning_rate": 4.453750743741132e-05, "loss": 2.2, "step": 24370 }, { "epoch": 1.11, "learning_rate": 4.453521900315804e-05, "loss": 2.1718, "step": 24380 }, { "epoch": 1.11, "learning_rate": 4.453293056890476e-05, "loss": 2.308, "step": 24390 }, { "epoch": 1.11, "learning_rate": 4.453064213465147e-05, "loss": 2.2556, "step": 24400 }, { "epoch": 1.11, "learning_rate": 4.452835370039819e-05, "loss": 2.3674, "step": 24410 }, { "epoch": 1.12, "learning_rate": 4.4526065266144906e-05, "loss": 2.12, "step": 24420 }, { "epoch": 1.12, "learning_rate": 4.452377683189162e-05, "loss": 2.2895, "step": 24430 }, { "epoch": 1.12, "learning_rate": 4.452148839763834e-05, "loss": 2.1805, "step": 24440 }, { "epoch": 1.12, "learning_rate": 4.4519199963385055e-05, "loss": 2.2168, "step": 24450 }, { "epoch": 1.12, "learning_rate": 4.451691152913177e-05, "loss": 2.3636, "step": 24460 }, { "epoch": 1.12, "learning_rate": 4.451462309487849e-05, "loss": 2.2259, "step": 24470 }, { "epoch": 1.12, "learning_rate": 4.4512334660625204e-05, "loss": 2.1238, "step": 24480 }, { "epoch": 1.12, "learning_rate": 4.451004622637192e-05, "loss": 2.2621, "step": 24490 }, { "epoch": 1.12, "learning_rate": 4.450775779211864e-05, "loss": 2.1443, "step": 24500 }, { "epoch": 1.12, "learning_rate": 4.4505469357865347e-05, "loss": 2.2466, "step": 24510 }, { "epoch": 1.12, "learning_rate": 4.450318092361207e-05, "loss": 2.1482, "step": 24520 }, { "epoch": 1.12, "learning_rate": 4.450089248935878e-05, "loss": 2.2417, "step": 24530 }, { "epoch": 1.12, "learning_rate": 4.4498604055105496e-05, "loss": 2.1101, "step": 24540 }, { "epoch": 1.12, "learning_rate": 4.449631562085222e-05, "loss": 2.2117, "step": 24550 }, { "epoch": 1.12, "learning_rate": 4.449402718659893e-05, "loss": 2.2603, "step": 24560 }, { "epoch": 1.12, "learning_rate": 4.4491738752345645e-05, "loss": 2.2421, "step": 24570 }, { "epoch": 1.12, "learning_rate": 4.4489450318092366e-05, "loss": 2.1981, "step": 24580 }, { "epoch": 1.12, "learning_rate": 4.448716188383908e-05, "loss": 2.3348, "step": 24590 }, { "epoch": 1.12, "learning_rate": 4.4484873449585794e-05, "loss": 2.1115, "step": 24600 }, { "epoch": 1.12, "learning_rate": 4.4482585015332515e-05, "loss": 2.2848, "step": 24610 }, { "epoch": 1.12, "learning_rate": 4.448029658107923e-05, "loss": 2.2957, "step": 24620 }, { "epoch": 1.12, "learning_rate": 4.447800814682594e-05, "loss": 2.2366, "step": 24630 }, { "epoch": 1.13, "learning_rate": 4.4475719712572664e-05, "loss": 2.1722, "step": 24640 }, { "epoch": 1.13, "learning_rate": 4.447343127831938e-05, "loss": 2.2916, "step": 24650 }, { "epoch": 1.13, "learning_rate": 4.447114284406609e-05, "loss": 2.1432, "step": 24660 }, { "epoch": 1.13, "learning_rate": 4.446885440981281e-05, "loss": 2.2057, "step": 24670 }, { "epoch": 1.13, "learning_rate": 4.446656597555953e-05, "loss": 2.4253, "step": 24680 }, { "epoch": 1.13, "learning_rate": 4.446427754130624e-05, "loss": 2.2717, "step": 24690 }, { "epoch": 1.13, "learning_rate": 4.4461989107052956e-05, "loss": 2.2812, "step": 24700 }, { "epoch": 1.13, "learning_rate": 4.445970067279967e-05, "loss": 2.4403, "step": 24710 }, { "epoch": 1.13, "learning_rate": 4.4457412238546384e-05, "loss": 2.4119, "step": 24720 }, { "epoch": 1.13, "learning_rate": 4.4455123804293105e-05, "loss": 2.2077, "step": 24730 }, { "epoch": 1.13, "learning_rate": 4.445283537003982e-05, "loss": 2.1861, "step": 24740 }, { "epoch": 1.13, "learning_rate": 4.445054693578653e-05, "loss": 2.3251, "step": 24750 }, { "epoch": 1.13, "learning_rate": 4.4448258501533254e-05, "loss": 2.3128, "step": 24760 }, { "epoch": 1.13, "learning_rate": 4.444597006727997e-05, "loss": 2.1976, "step": 24770 }, { "epoch": 1.13, "learning_rate": 4.444368163302668e-05, "loss": 2.412, "step": 24780 }, { "epoch": 1.13, "learning_rate": 4.44413931987734e-05, "loss": 2.1352, "step": 24790 }, { "epoch": 1.13, "learning_rate": 4.443910476452012e-05, "loss": 2.2214, "step": 24800 }, { "epoch": 1.13, "learning_rate": 4.443681633026683e-05, "loss": 2.271, "step": 24810 }, { "epoch": 1.13, "learning_rate": 4.443452789601355e-05, "loss": 2.4274, "step": 24820 }, { "epoch": 1.13, "learning_rate": 4.4432239461760267e-05, "loss": 2.4716, "step": 24830 }, { "epoch": 1.13, "learning_rate": 4.442995102750698e-05, "loss": 2.3675, "step": 24840 }, { "epoch": 1.13, "learning_rate": 4.44276625932537e-05, "loss": 2.1959, "step": 24850 }, { "epoch": 1.14, "learning_rate": 4.4425374159000416e-05, "loss": 2.3692, "step": 24860 }, { "epoch": 1.14, "learning_rate": 4.442308572474713e-05, "loss": 2.0722, "step": 24870 }, { "epoch": 1.14, "learning_rate": 4.442079729049385e-05, "loss": 2.1957, "step": 24880 }, { "epoch": 1.14, "learning_rate": 4.4418508856240565e-05, "loss": 2.2773, "step": 24890 }, { "epoch": 1.14, "learning_rate": 4.441622042198728e-05, "loss": 2.1805, "step": 24900 }, { "epoch": 1.14, "learning_rate": 4.441393198773399e-05, "loss": 2.4135, "step": 24910 }, { "epoch": 1.14, "learning_rate": 4.441164355348071e-05, "loss": 2.2132, "step": 24920 }, { "epoch": 1.14, "learning_rate": 4.440935511922743e-05, "loss": 2.2404, "step": 24930 }, { "epoch": 1.14, "learning_rate": 4.440706668497414e-05, "loss": 2.286, "step": 24940 }, { "epoch": 1.14, "learning_rate": 4.4404778250720857e-05, "loss": 2.1767, "step": 24950 }, { "epoch": 1.14, "learning_rate": 4.440248981646757e-05, "loss": 2.2111, "step": 24960 }, { "epoch": 1.14, "learning_rate": 4.440020138221429e-05, "loss": 2.3314, "step": 24970 }, { "epoch": 1.14, "learning_rate": 4.4397912947961006e-05, "loss": 2.2525, "step": 24980 }, { "epoch": 1.14, "learning_rate": 4.439562451370772e-05, "loss": 2.2481, "step": 24990 }, { "epoch": 1.14, "learning_rate": 4.439333607945444e-05, "loss": 2.407, "step": 25000 }, { "epoch": 1.14, "learning_rate": 4.4391047645201155e-05, "loss": 2.3791, "step": 25010 }, { "epoch": 1.14, "learning_rate": 4.438875921094787e-05, "loss": 2.2098, "step": 25020 }, { "epoch": 1.14, "learning_rate": 4.438647077669459e-05, "loss": 2.4213, "step": 25030 }, { "epoch": 1.14, "learning_rate": 4.4384182342441304e-05, "loss": 2.3225, "step": 25040 }, { "epoch": 1.14, "learning_rate": 4.438189390818802e-05, "loss": 2.2848, "step": 25050 }, { "epoch": 1.14, "learning_rate": 4.437960547393474e-05, "loss": 2.2503, "step": 25060 }, { "epoch": 1.14, "learning_rate": 4.437731703968145e-05, "loss": 2.1931, "step": 25070 }, { "epoch": 1.15, "learning_rate": 4.437502860542817e-05, "loss": 2.4089, "step": 25080 }, { "epoch": 1.15, "learning_rate": 4.437274017117489e-05, "loss": 2.2853, "step": 25090 }, { "epoch": 1.15, "learning_rate": 4.4370451736921596e-05, "loss": 2.21, "step": 25100 }, { "epoch": 1.15, "learning_rate": 4.4368163302668317e-05, "loss": 2.3173, "step": 25110 }, { "epoch": 1.15, "learning_rate": 4.436587486841503e-05, "loss": 2.2235, "step": 25120 }, { "epoch": 1.15, "learning_rate": 4.4363586434161745e-05, "loss": 2.1741, "step": 25130 }, { "epoch": 1.15, "learning_rate": 4.4361297999908466e-05, "loss": 2.2183, "step": 25140 }, { "epoch": 1.15, "learning_rate": 4.435900956565518e-05, "loss": 2.293, "step": 25150 }, { "epoch": 1.15, "learning_rate": 4.4356721131401894e-05, "loss": 2.1829, "step": 25160 }, { "epoch": 1.15, "learning_rate": 4.4354432697148615e-05, "loss": 2.4141, "step": 25170 }, { "epoch": 1.15, "learning_rate": 4.435214426289533e-05, "loss": 2.4056, "step": 25180 }, { "epoch": 1.15, "learning_rate": 4.434985582864204e-05, "loss": 2.3391, "step": 25190 }, { "epoch": 1.15, "learning_rate": 4.4347567394388764e-05, "loss": 2.185, "step": 25200 }, { "epoch": 1.15, "learning_rate": 4.434527896013548e-05, "loss": 2.1198, "step": 25210 }, { "epoch": 1.15, "learning_rate": 4.434299052588219e-05, "loss": 2.2703, "step": 25220 }, { "epoch": 1.15, "learning_rate": 4.434070209162891e-05, "loss": 2.3002, "step": 25230 }, { "epoch": 1.15, "learning_rate": 4.433841365737563e-05, "loss": 2.2303, "step": 25240 }, { "epoch": 1.15, "learning_rate": 4.433612522312234e-05, "loss": 2.2628, "step": 25250 }, { "epoch": 1.15, "learning_rate": 4.433383678886906e-05, "loss": 2.1709, "step": 25260 }, { "epoch": 1.15, "learning_rate": 4.4331548354615777e-05, "loss": 2.0933, "step": 25270 }, { "epoch": 1.15, "learning_rate": 4.432925992036249e-05, "loss": 2.3047, "step": 25280 }, { "epoch": 1.15, "learning_rate": 4.432697148610921e-05, "loss": 2.1012, "step": 25290 }, { "epoch": 1.16, "learning_rate": 4.432468305185592e-05, "loss": 2.207, "step": 25300 }, { "epoch": 1.16, "learning_rate": 4.432239461760263e-05, "loss": 2.3077, "step": 25310 }, { "epoch": 1.16, "learning_rate": 4.4320106183349354e-05, "loss": 2.2752, "step": 25320 }, { "epoch": 1.16, "learning_rate": 4.431781774909607e-05, "loss": 2.3259, "step": 25330 }, { "epoch": 1.16, "learning_rate": 4.431552931484278e-05, "loss": 2.3119, "step": 25340 }, { "epoch": 1.16, "learning_rate": 4.43132408805895e-05, "loss": 2.1607, "step": 25350 }, { "epoch": 1.16, "learning_rate": 4.431095244633622e-05, "loss": 2.2641, "step": 25360 }, { "epoch": 1.16, "learning_rate": 4.430866401208293e-05, "loss": 2.2454, "step": 25370 }, { "epoch": 1.16, "learning_rate": 4.430637557782965e-05, "loss": 2.2134, "step": 25380 }, { "epoch": 1.16, "learning_rate": 4.4304087143576366e-05, "loss": 2.2452, "step": 25390 }, { "epoch": 1.16, "learning_rate": 4.430179870932308e-05, "loss": 2.206, "step": 25400 }, { "epoch": 1.16, "learning_rate": 4.42995102750698e-05, "loss": 2.2359, "step": 25410 }, { "epoch": 1.16, "learning_rate": 4.4297221840816516e-05, "loss": 2.3762, "step": 25420 }, { "epoch": 1.16, "learning_rate": 4.429493340656323e-05, "loss": 2.1174, "step": 25430 }, { "epoch": 1.16, "learning_rate": 4.429264497230995e-05, "loss": 2.2291, "step": 25440 }, { "epoch": 1.16, "learning_rate": 4.4290356538056665e-05, "loss": 2.2838, "step": 25450 }, { "epoch": 1.16, "learning_rate": 4.428806810380338e-05, "loss": 2.5555, "step": 25460 }, { "epoch": 1.16, "learning_rate": 4.42857796695501e-05, "loss": 2.2093, "step": 25470 }, { "epoch": 1.16, "learning_rate": 4.4283491235296814e-05, "loss": 2.311, "step": 25480 }, { "epoch": 1.16, "learning_rate": 4.428120280104353e-05, "loss": 2.154, "step": 25490 }, { "epoch": 1.16, "learning_rate": 4.427891436679024e-05, "loss": 2.2113, "step": 25500 }, { "epoch": 1.16, "learning_rate": 4.4276625932536956e-05, "loss": 2.2696, "step": 25510 }, { "epoch": 1.17, "learning_rate": 4.427433749828368e-05, "loss": 2.3319, "step": 25520 }, { "epoch": 1.17, "learning_rate": 4.427204906403039e-05, "loss": 2.3323, "step": 25530 }, { "epoch": 1.17, "learning_rate": 4.4269760629777106e-05, "loss": 2.231, "step": 25540 }, { "epoch": 1.17, "learning_rate": 4.4267472195523826e-05, "loss": 2.2312, "step": 25550 }, { "epoch": 1.17, "learning_rate": 4.426518376127054e-05, "loss": 2.2823, "step": 25560 }, { "epoch": 1.17, "learning_rate": 4.4262895327017255e-05, "loss": 2.429, "step": 25570 }, { "epoch": 1.17, "learning_rate": 4.4260606892763976e-05, "loss": 2.2516, "step": 25580 }, { "epoch": 1.17, "learning_rate": 4.425831845851069e-05, "loss": 2.2214, "step": 25590 }, { "epoch": 1.17, "learning_rate": 4.4256030024257404e-05, "loss": 2.3549, "step": 25600 }, { "epoch": 1.17, "learning_rate": 4.4253741590004125e-05, "loss": 2.1681, "step": 25610 }, { "epoch": 1.17, "learning_rate": 4.425145315575084e-05, "loss": 2.3195, "step": 25620 }, { "epoch": 1.17, "learning_rate": 4.424916472149755e-05, "loss": 2.2599, "step": 25630 }, { "epoch": 1.17, "learning_rate": 4.4246876287244274e-05, "loss": 2.2339, "step": 25640 }, { "epoch": 1.17, "learning_rate": 4.424458785299099e-05, "loss": 2.3069, "step": 25650 }, { "epoch": 1.17, "learning_rate": 4.42422994187377e-05, "loss": 2.2547, "step": 25660 }, { "epoch": 1.17, "learning_rate": 4.424001098448442e-05, "loss": 2.286, "step": 25670 }, { "epoch": 1.17, "learning_rate": 4.423772255023114e-05, "loss": 2.2125, "step": 25680 }, { "epoch": 1.17, "learning_rate": 4.4235434115977845e-05, "loss": 2.1015, "step": 25690 }, { "epoch": 1.17, "learning_rate": 4.4233145681724566e-05, "loss": 2.2143, "step": 25700 }, { "epoch": 1.17, "learning_rate": 4.423085724747128e-05, "loss": 2.3687, "step": 25710 }, { "epoch": 1.17, "learning_rate": 4.4228568813217994e-05, "loss": 2.3254, "step": 25720 }, { "epoch": 1.17, "learning_rate": 4.4226280378964715e-05, "loss": 2.4107, "step": 25730 }, { "epoch": 1.18, "learning_rate": 4.422399194471143e-05, "loss": 2.281, "step": 25740 }, { "epoch": 1.18, "learning_rate": 4.422170351045814e-05, "loss": 2.1766, "step": 25750 }, { "epoch": 1.18, "learning_rate": 4.4219415076204864e-05, "loss": 2.2925, "step": 25760 }, { "epoch": 1.18, "learning_rate": 4.421712664195158e-05, "loss": 2.1612, "step": 25770 }, { "epoch": 1.18, "learning_rate": 4.421483820769829e-05, "loss": 2.2816, "step": 25780 }, { "epoch": 1.18, "learning_rate": 4.421254977344501e-05, "loss": 2.1386, "step": 25790 }, { "epoch": 1.18, "learning_rate": 4.421026133919173e-05, "loss": 2.2635, "step": 25800 }, { "epoch": 1.18, "learning_rate": 4.420797290493844e-05, "loss": 2.3868, "step": 25810 }, { "epoch": 1.18, "learning_rate": 4.420568447068516e-05, "loss": 2.2585, "step": 25820 }, { "epoch": 1.18, "learning_rate": 4.4203396036431876e-05, "loss": 2.1868, "step": 25830 }, { "epoch": 1.18, "learning_rate": 4.420110760217859e-05, "loss": 2.3129, "step": 25840 }, { "epoch": 1.18, "learning_rate": 4.419881916792531e-05, "loss": 2.4701, "step": 25850 }, { "epoch": 1.18, "learning_rate": 4.4196530733672026e-05, "loss": 2.1514, "step": 25860 }, { "epoch": 1.18, "learning_rate": 4.419424229941874e-05, "loss": 2.2171, "step": 25870 }, { "epoch": 1.18, "learning_rate": 4.419195386516546e-05, "loss": 2.4684, "step": 25880 }, { "epoch": 1.18, "learning_rate": 4.418966543091217e-05, "loss": 2.4818, "step": 25890 }, { "epoch": 1.18, "learning_rate": 4.418737699665889e-05, "loss": 2.2998, "step": 25900 }, { "epoch": 1.18, "learning_rate": 4.41850885624056e-05, "loss": 2.0959, "step": 25910 }, { "epoch": 1.18, "learning_rate": 4.418280012815232e-05, "loss": 2.196, "step": 25920 }, { "epoch": 1.18, "learning_rate": 4.418051169389904e-05, "loss": 2.0867, "step": 25930 }, { "epoch": 1.18, "learning_rate": 4.417822325964575e-05, "loss": 2.2175, "step": 25940 }, { "epoch": 1.18, "learning_rate": 4.4175934825392466e-05, "loss": 2.1216, "step": 25950 }, { "epoch": 1.19, "learning_rate": 4.417364639113919e-05, "loss": 2.2976, "step": 25960 }, { "epoch": 1.19, "learning_rate": 4.41713579568859e-05, "loss": 2.2606, "step": 25970 }, { "epoch": 1.19, "learning_rate": 4.4169069522632616e-05, "loss": 2.2901, "step": 25980 }, { "epoch": 1.19, "learning_rate": 4.4166781088379336e-05, "loss": 2.4321, "step": 25990 }, { "epoch": 1.19, "learning_rate": 4.416449265412605e-05, "loss": 2.1803, "step": 26000 }, { "epoch": 1.19, "learning_rate": 4.4162204219872765e-05, "loss": 2.2246, "step": 26010 }, { "epoch": 1.19, "learning_rate": 4.4159915785619486e-05, "loss": 2.1376, "step": 26020 }, { "epoch": 1.19, "learning_rate": 4.41576273513662e-05, "loss": 2.1696, "step": 26030 }, { "epoch": 1.19, "learning_rate": 4.4155338917112914e-05, "loss": 2.1131, "step": 26040 }, { "epoch": 1.19, "learning_rate": 4.415305048285963e-05, "loss": 2.3651, "step": 26050 }, { "epoch": 1.19, "learning_rate": 4.415076204860635e-05, "loss": 2.2635, "step": 26060 }, { "epoch": 1.19, "learning_rate": 4.414847361435306e-05, "loss": 2.2658, "step": 26070 }, { "epoch": 1.19, "learning_rate": 4.414618518009978e-05, "loss": 2.2257, "step": 26080 }, { "epoch": 1.19, "learning_rate": 4.414389674584649e-05, "loss": 2.3441, "step": 26090 }, { "epoch": 1.19, "learning_rate": 4.4141608311593205e-05, "loss": 2.1286, "step": 26100 }, { "epoch": 1.19, "learning_rate": 4.4139319877339926e-05, "loss": 2.2776, "step": 26110 }, { "epoch": 1.19, "learning_rate": 4.413703144308664e-05, "loss": 2.4866, "step": 26120 }, { "epoch": 1.19, "learning_rate": 4.4134743008833355e-05, "loss": 2.2957, "step": 26130 }, { "epoch": 1.19, "learning_rate": 4.4132454574580076e-05, "loss": 2.3248, "step": 26140 }, { "epoch": 1.19, "learning_rate": 4.413016614032679e-05, "loss": 2.2739, "step": 26150 }, { "epoch": 1.19, "learning_rate": 4.4127877706073504e-05, "loss": 2.3452, "step": 26160 }, { "epoch": 1.19, "learning_rate": 4.4125589271820225e-05, "loss": 2.2233, "step": 26170 }, { "epoch": 1.2, "learning_rate": 4.412330083756694e-05, "loss": 2.1568, "step": 26180 }, { "epoch": 1.2, "learning_rate": 4.412101240331365e-05, "loss": 2.1327, "step": 26190 }, { "epoch": 1.2, "learning_rate": 4.4118723969060374e-05, "loss": 2.3223, "step": 26200 }, { "epoch": 1.2, "learning_rate": 4.411643553480709e-05, "loss": 2.3189, "step": 26210 }, { "epoch": 1.2, "learning_rate": 4.41141471005538e-05, "loss": 2.2446, "step": 26220 }, { "epoch": 1.2, "learning_rate": 4.411185866630052e-05, "loss": 2.4132, "step": 26230 }, { "epoch": 1.2, "learning_rate": 4.410957023204724e-05, "loss": 2.087, "step": 26240 }, { "epoch": 1.2, "learning_rate": 4.410728179779395e-05, "loss": 2.1813, "step": 26250 }, { "epoch": 1.2, "learning_rate": 4.410499336354067e-05, "loss": 2.265, "step": 26260 }, { "epoch": 1.2, "learning_rate": 4.4102704929287386e-05, "loss": 2.2892, "step": 26270 }, { "epoch": 1.2, "learning_rate": 4.41004164950341e-05, "loss": 2.2969, "step": 26280 }, { "epoch": 1.2, "learning_rate": 4.4098128060780815e-05, "loss": 2.1804, "step": 26290 }, { "epoch": 1.2, "learning_rate": 4.409583962652753e-05, "loss": 2.3962, "step": 26300 }, { "epoch": 1.2, "learning_rate": 4.409355119227424e-05, "loss": 2.1938, "step": 26310 }, { "epoch": 1.2, "learning_rate": 4.4091262758020964e-05, "loss": 2.2774, "step": 26320 }, { "epoch": 1.2, "learning_rate": 4.408897432376768e-05, "loss": 2.1946, "step": 26330 }, { "epoch": 1.2, "learning_rate": 4.408668588951439e-05, "loss": 2.2167, "step": 26340 }, { "epoch": 1.2, "learning_rate": 4.408439745526111e-05, "loss": 2.3304, "step": 26350 }, { "epoch": 1.2, "learning_rate": 4.408210902100783e-05, "loss": 2.1969, "step": 26360 }, { "epoch": 1.2, "learning_rate": 4.407982058675454e-05, "loss": 2.1895, "step": 26370 }, { "epoch": 1.2, "learning_rate": 4.407753215250126e-05, "loss": 2.3256, "step": 26380 }, { "epoch": 1.21, "learning_rate": 4.4075243718247976e-05, "loss": 2.1157, "step": 26390 }, { "epoch": 1.21, "learning_rate": 4.407295528399469e-05, "loss": 2.3553, "step": 26400 }, { "epoch": 1.21, "learning_rate": 4.407066684974141e-05, "loss": 2.1631, "step": 26410 }, { "epoch": 1.21, "learning_rate": 4.4068378415488126e-05, "loss": 2.2225, "step": 26420 }, { "epoch": 1.21, "learning_rate": 4.406608998123484e-05, "loss": 2.1178, "step": 26430 }, { "epoch": 1.21, "learning_rate": 4.406380154698156e-05, "loss": 2.0904, "step": 26440 }, { "epoch": 1.21, "learning_rate": 4.4061513112728275e-05, "loss": 2.262, "step": 26450 }, { "epoch": 1.21, "learning_rate": 4.405922467847499e-05, "loss": 2.4527, "step": 26460 }, { "epoch": 1.21, "learning_rate": 4.405693624422171e-05, "loss": 2.2938, "step": 26470 }, { "epoch": 1.21, "learning_rate": 4.405464780996842e-05, "loss": 2.2061, "step": 26480 }, { "epoch": 1.21, "learning_rate": 4.405235937571514e-05, "loss": 2.3058, "step": 26490 }, { "epoch": 1.21, "learning_rate": 4.405007094146185e-05, "loss": 2.2888, "step": 26500 }, { "epoch": 1.21, "learning_rate": 4.4047782507208566e-05, "loss": 2.263, "step": 26510 }, { "epoch": 1.21, "learning_rate": 4.404549407295529e-05, "loss": 2.3494, "step": 26520 }, { "epoch": 1.21, "learning_rate": 4.4043205638702e-05, "loss": 2.2392, "step": 26530 }, { "epoch": 1.21, "learning_rate": 4.4040917204448715e-05, "loss": 2.3692, "step": 26540 }, { "epoch": 1.21, "learning_rate": 4.4038628770195436e-05, "loss": 2.3075, "step": 26550 }, { "epoch": 1.21, "learning_rate": 4.403634033594215e-05, "loss": 2.2145, "step": 26560 }, { "epoch": 1.21, "learning_rate": 4.4034051901688865e-05, "loss": 2.1777, "step": 26570 }, { "epoch": 1.21, "learning_rate": 4.4031763467435586e-05, "loss": 2.2728, "step": 26580 }, { "epoch": 1.21, "learning_rate": 4.40294750331823e-05, "loss": 2.3397, "step": 26590 }, { "epoch": 1.21, "learning_rate": 4.4027186598929014e-05, "loss": 2.285, "step": 26600 }, { "epoch": 1.22, "learning_rate": 4.4024898164675735e-05, "loss": 2.2215, "step": 26610 }, { "epoch": 1.22, "learning_rate": 4.402260973042245e-05, "loss": 2.4202, "step": 26620 }, { "epoch": 1.22, "learning_rate": 4.402032129616916e-05, "loss": 2.2297, "step": 26630 }, { "epoch": 1.22, "learning_rate": 4.4018032861915884e-05, "loss": 2.1319, "step": 26640 }, { "epoch": 1.22, "learning_rate": 4.40157444276626e-05, "loss": 2.2711, "step": 26650 }, { "epoch": 1.22, "learning_rate": 4.401345599340931e-05, "loss": 2.2423, "step": 26660 }, { "epoch": 1.22, "learning_rate": 4.401116755915603e-05, "loss": 2.3069, "step": 26670 }, { "epoch": 1.22, "learning_rate": 4.400887912490274e-05, "loss": 2.2616, "step": 26680 }, { "epoch": 1.22, "learning_rate": 4.4006590690649455e-05, "loss": 2.3976, "step": 26690 }, { "epoch": 1.22, "learning_rate": 4.4004302256396175e-05, "loss": 2.0984, "step": 26700 }, { "epoch": 1.22, "learning_rate": 4.400201382214289e-05, "loss": 2.3967, "step": 26710 }, { "epoch": 1.22, "learning_rate": 4.3999725387889604e-05, "loss": 2.2418, "step": 26720 }, { "epoch": 1.22, "learning_rate": 4.3997436953636325e-05, "loss": 2.1088, "step": 26730 }, { "epoch": 1.22, "learning_rate": 4.399514851938304e-05, "loss": 2.2707, "step": 26740 }, { "epoch": 1.22, "learning_rate": 4.399286008512975e-05, "loss": 2.1806, "step": 26750 }, { "epoch": 1.22, "learning_rate": 4.3990571650876474e-05, "loss": 2.1841, "step": 26760 }, { "epoch": 1.22, "learning_rate": 4.398828321662319e-05, "loss": 2.1766, "step": 26770 }, { "epoch": 1.22, "learning_rate": 4.39859947823699e-05, "loss": 2.3445, "step": 26780 }, { "epoch": 1.22, "learning_rate": 4.398370634811662e-05, "loss": 2.1316, "step": 26790 }, { "epoch": 1.22, "learning_rate": 4.398141791386334e-05, "loss": 2.2149, "step": 26800 }, { "epoch": 1.22, "learning_rate": 4.397912947961005e-05, "loss": 2.2385, "step": 26810 }, { "epoch": 1.22, "learning_rate": 4.397684104535677e-05, "loss": 2.4115, "step": 26820 }, { "epoch": 1.23, "learning_rate": 4.3974552611103486e-05, "loss": 2.1622, "step": 26830 }, { "epoch": 1.23, "learning_rate": 4.39722641768502e-05, "loss": 2.2148, "step": 26840 }, { "epoch": 1.23, "learning_rate": 4.396997574259692e-05, "loss": 2.1589, "step": 26850 }, { "epoch": 1.23, "learning_rate": 4.3967687308343635e-05, "loss": 2.0701, "step": 26860 }, { "epoch": 1.23, "learning_rate": 4.396539887409035e-05, "loss": 2.3327, "step": 26870 }, { "epoch": 1.23, "learning_rate": 4.3963110439837064e-05, "loss": 2.2854, "step": 26880 }, { "epoch": 1.23, "learning_rate": 4.396082200558378e-05, "loss": 2.1899, "step": 26890 }, { "epoch": 1.23, "learning_rate": 4.39585335713305e-05, "loss": 2.2247, "step": 26900 }, { "epoch": 1.23, "learning_rate": 4.395624513707721e-05, "loss": 2.1226, "step": 26910 }, { "epoch": 1.23, "learning_rate": 4.395395670282393e-05, "loss": 2.4006, "step": 26920 }, { "epoch": 1.23, "learning_rate": 4.395166826857065e-05, "loss": 2.3373, "step": 26930 }, { "epoch": 1.23, "learning_rate": 4.394937983431736e-05, "loss": 2.2674, "step": 26940 }, { "epoch": 1.23, "learning_rate": 4.3947091400064076e-05, "loss": 2.2889, "step": 26950 }, { "epoch": 1.23, "learning_rate": 4.39448029658108e-05, "loss": 2.25, "step": 26960 }, { "epoch": 1.23, "learning_rate": 4.394251453155751e-05, "loss": 2.3141, "step": 26970 }, { "epoch": 1.23, "learning_rate": 4.3940226097304225e-05, "loss": 2.2247, "step": 26980 }, { "epoch": 1.23, "learning_rate": 4.3937937663050946e-05, "loss": 2.2992, "step": 26990 }, { "epoch": 1.23, "learning_rate": 4.393564922879766e-05, "loss": 2.2444, "step": 27000 }, { "epoch": 1.23, "learning_rate": 4.3933360794544375e-05, "loss": 2.2624, "step": 27010 }, { "epoch": 1.23, "learning_rate": 4.3931072360291096e-05, "loss": 2.1961, "step": 27020 }, { "epoch": 1.23, "learning_rate": 4.392878392603781e-05, "loss": 2.2417, "step": 27030 }, { "epoch": 1.23, "learning_rate": 4.3926495491784524e-05, "loss": 2.2027, "step": 27040 }, { "epoch": 1.24, "learning_rate": 4.3924207057531245e-05, "loss": 2.1876, "step": 27050 }, { "epoch": 1.24, "learning_rate": 4.392191862327796e-05, "loss": 2.315, "step": 27060 }, { "epoch": 1.24, "learning_rate": 4.391963018902467e-05, "loss": 2.1736, "step": 27070 }, { "epoch": 1.24, "learning_rate": 4.391734175477139e-05, "loss": 2.1438, "step": 27080 }, { "epoch": 1.24, "learning_rate": 4.39150533205181e-05, "loss": 2.4215, "step": 27090 }, { "epoch": 1.24, "learning_rate": 4.3912764886264815e-05, "loss": 2.3451, "step": 27100 }, { "epoch": 1.24, "learning_rate": 4.3910476452011536e-05, "loss": 2.2109, "step": 27110 }, { "epoch": 1.24, "learning_rate": 4.390818801775825e-05, "loss": 2.0923, "step": 27120 }, { "epoch": 1.24, "learning_rate": 4.3905899583504965e-05, "loss": 2.2853, "step": 27130 }, { "epoch": 1.24, "learning_rate": 4.3903611149251685e-05, "loss": 2.2471, "step": 27140 }, { "epoch": 1.24, "learning_rate": 4.39013227149984e-05, "loss": 2.2293, "step": 27150 }, { "epoch": 1.24, "learning_rate": 4.3899034280745114e-05, "loss": 2.4008, "step": 27160 }, { "epoch": 1.24, "learning_rate": 4.3896745846491835e-05, "loss": 2.2199, "step": 27170 }, { "epoch": 1.24, "learning_rate": 4.389445741223855e-05, "loss": 2.3108, "step": 27180 }, { "epoch": 1.24, "learning_rate": 4.389216897798526e-05, "loss": 2.2503, "step": 27190 }, { "epoch": 1.24, "learning_rate": 4.3889880543731984e-05, "loss": 2.2272, "step": 27200 }, { "epoch": 1.24, "learning_rate": 4.38875921094787e-05, "loss": 2.2547, "step": 27210 }, { "epoch": 1.24, "learning_rate": 4.388530367522541e-05, "loss": 2.477, "step": 27220 }, { "epoch": 1.24, "learning_rate": 4.388301524097213e-05, "loss": 2.3031, "step": 27230 }, { "epoch": 1.24, "learning_rate": 4.388072680671885e-05, "loss": 2.2003, "step": 27240 }, { "epoch": 1.24, "learning_rate": 4.387843837246556e-05, "loss": 2.2378, "step": 27250 }, { "epoch": 1.24, "learning_rate": 4.387614993821228e-05, "loss": 2.2173, "step": 27260 }, { "epoch": 1.25, "learning_rate": 4.387386150395899e-05, "loss": 2.3765, "step": 27270 }, { "epoch": 1.25, "learning_rate": 4.3871573069705704e-05, "loss": 2.3576, "step": 27280 }, { "epoch": 1.25, "learning_rate": 4.3869284635452425e-05, "loss": 2.3882, "step": 27290 }, { "epoch": 1.25, "learning_rate": 4.386699620119914e-05, "loss": 2.2403, "step": 27300 }, { "epoch": 1.25, "learning_rate": 4.386470776694585e-05, "loss": 2.324, "step": 27310 }, { "epoch": 1.25, "learning_rate": 4.3862419332692574e-05, "loss": 2.1997, "step": 27320 }, { "epoch": 1.25, "learning_rate": 4.386013089843929e-05, "loss": 2.346, "step": 27330 }, { "epoch": 1.25, "learning_rate": 4.3857842464186e-05, "loss": 2.1446, "step": 27340 }, { "epoch": 1.25, "learning_rate": 4.385555402993272e-05, "loss": 2.2656, "step": 27350 }, { "epoch": 1.25, "learning_rate": 4.385326559567944e-05, "loss": 2.1279, "step": 27360 }, { "epoch": 1.25, "learning_rate": 4.385097716142615e-05, "loss": 2.1334, "step": 27370 }, { "epoch": 1.25, "learning_rate": 4.384868872717287e-05, "loss": 2.3549, "step": 27380 }, { "epoch": 1.25, "learning_rate": 4.3846400292919586e-05, "loss": 2.281, "step": 27390 }, { "epoch": 1.25, "learning_rate": 4.38441118586663e-05, "loss": 2.3362, "step": 27400 }, { "epoch": 1.25, "learning_rate": 4.384182342441302e-05, "loss": 2.2119, "step": 27410 }, { "epoch": 1.25, "learning_rate": 4.3839534990159735e-05, "loss": 2.3014, "step": 27420 }, { "epoch": 1.25, "learning_rate": 4.383724655590645e-05, "loss": 2.242, "step": 27430 }, { "epoch": 1.25, "learning_rate": 4.383495812165317e-05, "loss": 2.2062, "step": 27440 }, { "epoch": 1.25, "learning_rate": 4.3832669687399885e-05, "loss": 2.0871, "step": 27450 }, { "epoch": 1.25, "learning_rate": 4.38303812531466e-05, "loss": 2.1938, "step": 27460 }, { "epoch": 1.25, "learning_rate": 4.382809281889331e-05, "loss": 2.2278, "step": 27470 }, { "epoch": 1.25, "learning_rate": 4.382580438464003e-05, "loss": 2.2791, "step": 27480 }, { "epoch": 1.26, "learning_rate": 4.382351595038675e-05, "loss": 2.1439, "step": 27490 }, { "epoch": 1.26, "learning_rate": 4.382122751613346e-05, "loss": 2.3436, "step": 27500 }, { "epoch": 1.26, "learning_rate": 4.3818939081880176e-05, "loss": 2.3063, "step": 27510 }, { "epoch": 1.26, "learning_rate": 4.38166506476269e-05, "loss": 2.3423, "step": 27520 }, { "epoch": 1.26, "learning_rate": 4.381436221337361e-05, "loss": 2.3007, "step": 27530 }, { "epoch": 1.26, "learning_rate": 4.3812073779120325e-05, "loss": 2.2031, "step": 27540 }, { "epoch": 1.26, "learning_rate": 4.3809785344867046e-05, "loss": 2.1918, "step": 27550 }, { "epoch": 1.26, "learning_rate": 4.380749691061376e-05, "loss": 2.4466, "step": 27560 }, { "epoch": 1.26, "learning_rate": 4.3805208476360474e-05, "loss": 2.0855, "step": 27570 }, { "epoch": 1.26, "learning_rate": 4.3802920042107195e-05, "loss": 2.2359, "step": 27580 }, { "epoch": 1.26, "learning_rate": 4.380063160785391e-05, "loss": 2.449, "step": 27590 }, { "epoch": 1.26, "learning_rate": 4.3798343173600624e-05, "loss": 2.2113, "step": 27600 }, { "epoch": 1.26, "learning_rate": 4.3796054739347345e-05, "loss": 2.1644, "step": 27610 }, { "epoch": 1.26, "learning_rate": 4.379376630509406e-05, "loss": 2.1646, "step": 27620 }, { "epoch": 1.26, "learning_rate": 4.379147787084077e-05, "loss": 2.298, "step": 27630 }, { "epoch": 1.26, "learning_rate": 4.3789189436587494e-05, "loss": 2.4107, "step": 27640 }, { "epoch": 1.26, "learning_rate": 4.378690100233421e-05, "loss": 2.208, "step": 27650 }, { "epoch": 1.26, "learning_rate": 4.378461256808092e-05, "loss": 2.2146, "step": 27660 }, { "epoch": 1.26, "learning_rate": 4.3782324133827636e-05, "loss": 2.1965, "step": 27670 }, { "epoch": 1.26, "learning_rate": 4.378003569957435e-05, "loss": 2.4224, "step": 27680 }, { "epoch": 1.26, "learning_rate": 4.3777747265321064e-05, "loss": 2.2417, "step": 27690 }, { "epoch": 1.26, "learning_rate": 4.3775458831067785e-05, "loss": 2.2306, "step": 27700 }, { "epoch": 1.27, "learning_rate": 4.37731703968145e-05, "loss": 2.2862, "step": 27710 }, { "epoch": 1.27, "learning_rate": 4.3770881962561214e-05, "loss": 2.188, "step": 27720 }, { "epoch": 1.27, "learning_rate": 4.3768593528307935e-05, "loss": 2.2644, "step": 27730 }, { "epoch": 1.27, "learning_rate": 4.376630509405465e-05, "loss": 2.4373, "step": 27740 }, { "epoch": 1.27, "learning_rate": 4.376401665980136e-05, "loss": 2.359, "step": 27750 }, { "epoch": 1.27, "learning_rate": 4.3761728225548084e-05, "loss": 2.1842, "step": 27760 }, { "epoch": 1.27, "learning_rate": 4.37594397912948e-05, "loss": 2.3219, "step": 27770 }, { "epoch": 1.27, "learning_rate": 4.375715135704151e-05, "loss": 2.273, "step": 27780 }, { "epoch": 1.27, "learning_rate": 4.375486292278823e-05, "loss": 2.1229, "step": 27790 }, { "epoch": 1.27, "learning_rate": 4.375257448853495e-05, "loss": 2.3548, "step": 27800 }, { "epoch": 1.27, "learning_rate": 4.375028605428166e-05, "loss": 2.2345, "step": 27810 }, { "epoch": 1.27, "learning_rate": 4.374799762002838e-05, "loss": 2.2788, "step": 27820 }, { "epoch": 1.27, "learning_rate": 4.3745709185775096e-05, "loss": 2.3188, "step": 27830 }, { "epoch": 1.27, "learning_rate": 4.374342075152181e-05, "loss": 2.2311, "step": 27840 }, { "epoch": 1.27, "learning_rate": 4.374113231726853e-05, "loss": 2.3526, "step": 27850 }, { "epoch": 1.27, "learning_rate": 4.3738843883015245e-05, "loss": 2.2601, "step": 27860 }, { "epoch": 1.27, "learning_rate": 4.373655544876196e-05, "loss": 2.2664, "step": 27870 }, { "epoch": 1.27, "learning_rate": 4.3734267014508674e-05, "loss": 2.2438, "step": 27880 }, { "epoch": 1.27, "learning_rate": 4.373197858025539e-05, "loss": 2.0447, "step": 27890 }, { "epoch": 1.27, "learning_rate": 4.372969014600211e-05, "loss": 2.1705, "step": 27900 }, { "epoch": 1.27, "learning_rate": 4.372740171174882e-05, "loss": 2.4013, "step": 27910 }, { "epoch": 1.27, "learning_rate": 4.372511327749554e-05, "loss": 2.3222, "step": 27920 }, { "epoch": 1.28, "learning_rate": 4.372282484324226e-05, "loss": 2.111, "step": 27930 }, { "epoch": 1.28, "learning_rate": 4.372053640898897e-05, "loss": 2.2961, "step": 27940 }, { "epoch": 1.28, "learning_rate": 4.3718247974735686e-05, "loss": 2.2416, "step": 27950 }, { "epoch": 1.28, "learning_rate": 4.371595954048241e-05, "loss": 2.1324, "step": 27960 }, { "epoch": 1.28, "learning_rate": 4.371367110622912e-05, "loss": 2.2349, "step": 27970 }, { "epoch": 1.28, "learning_rate": 4.3711382671975835e-05, "loss": 2.2425, "step": 27980 }, { "epoch": 1.28, "learning_rate": 4.3709094237722556e-05, "loss": 2.2818, "step": 27990 }, { "epoch": 1.28, "learning_rate": 4.370680580346927e-05, "loss": 2.1498, "step": 28000 }, { "epoch": 1.28, "learning_rate": 4.3704517369215984e-05, "loss": 2.2779, "step": 28010 }, { "epoch": 1.28, "learning_rate": 4.3702228934962705e-05, "loss": 2.442, "step": 28020 }, { "epoch": 1.28, "learning_rate": 4.369994050070942e-05, "loss": 2.2039, "step": 28030 }, { "epoch": 1.28, "learning_rate": 4.3697652066456134e-05, "loss": 2.1959, "step": 28040 }, { "epoch": 1.28, "learning_rate": 4.3695363632202855e-05, "loss": 2.2546, "step": 28050 }, { "epoch": 1.28, "learning_rate": 4.369307519794956e-05, "loss": 2.26, "step": 28060 }, { "epoch": 1.28, "learning_rate": 4.3690786763696276e-05, "loss": 2.1541, "step": 28070 }, { "epoch": 1.28, "learning_rate": 4.3688498329443e-05, "loss": 2.1262, "step": 28080 }, { "epoch": 1.28, "learning_rate": 4.368620989518971e-05, "loss": 2.2887, "step": 28090 }, { "epoch": 1.28, "learning_rate": 4.3683921460936425e-05, "loss": 2.0707, "step": 28100 }, { "epoch": 1.28, "learning_rate": 4.3681633026683146e-05, "loss": 2.3619, "step": 28110 }, { "epoch": 1.28, "learning_rate": 4.367934459242986e-05, "loss": 2.2052, "step": 28120 }, { "epoch": 1.28, "learning_rate": 4.3677056158176574e-05, "loss": 2.2818, "step": 28130 }, { "epoch": 1.28, "learning_rate": 4.3674767723923295e-05, "loss": 2.2512, "step": 28140 }, { "epoch": 1.29, "learning_rate": 4.367247928967001e-05, "loss": 2.3241, "step": 28150 }, { "epoch": 1.29, "learning_rate": 4.3670190855416724e-05, "loss": 2.2301, "step": 28160 }, { "epoch": 1.29, "learning_rate": 4.3667902421163444e-05, "loss": 2.3547, "step": 28170 }, { "epoch": 1.29, "learning_rate": 4.366561398691016e-05, "loss": 2.3055, "step": 28180 }, { "epoch": 1.29, "learning_rate": 4.366332555265687e-05, "loss": 2.2154, "step": 28190 }, { "epoch": 1.29, "learning_rate": 4.3661037118403594e-05, "loss": 2.1461, "step": 28200 }, { "epoch": 1.29, "learning_rate": 4.365874868415031e-05, "loss": 2.0899, "step": 28210 }, { "epoch": 1.29, "learning_rate": 4.365646024989702e-05, "loss": 2.3074, "step": 28220 }, { "epoch": 1.29, "learning_rate": 4.365417181564374e-05, "loss": 2.3143, "step": 28230 }, { "epoch": 1.29, "learning_rate": 4.365188338139046e-05, "loss": 2.2347, "step": 28240 }, { "epoch": 1.29, "learning_rate": 4.364959494713717e-05, "loss": 2.1442, "step": 28250 }, { "epoch": 1.29, "learning_rate": 4.3647306512883885e-05, "loss": 2.2549, "step": 28260 }, { "epoch": 1.29, "learning_rate": 4.36450180786306e-05, "loss": 2.1933, "step": 28270 }, { "epoch": 1.29, "learning_rate": 4.364272964437732e-05, "loss": 2.342, "step": 28280 }, { "epoch": 1.29, "learning_rate": 4.3640441210124034e-05, "loss": 2.3343, "step": 28290 }, { "epoch": 1.29, "learning_rate": 4.363815277587075e-05, "loss": 2.3618, "step": 28300 }, { "epoch": 1.29, "learning_rate": 4.363586434161747e-05, "loss": 2.0271, "step": 28310 }, { "epoch": 1.29, "learning_rate": 4.3633575907364184e-05, "loss": 2.1905, "step": 28320 }, { "epoch": 1.29, "learning_rate": 4.36312874731109e-05, "loss": 2.2374, "step": 28330 }, { "epoch": 1.29, "learning_rate": 4.362899903885762e-05, "loss": 2.24, "step": 28340 }, { "epoch": 1.29, "learning_rate": 4.362671060460433e-05, "loss": 2.3614, "step": 28350 }, { "epoch": 1.29, "learning_rate": 4.362442217035105e-05, "loss": 2.1461, "step": 28360 }, { "epoch": 1.3, "learning_rate": 4.362213373609777e-05, "loss": 2.1817, "step": 28370 }, { "epoch": 1.3, "learning_rate": 4.361984530184448e-05, "loss": 2.3251, "step": 28380 }, { "epoch": 1.3, "learning_rate": 4.3617556867591196e-05, "loss": 2.1738, "step": 28390 }, { "epoch": 1.3, "learning_rate": 4.361526843333791e-05, "loss": 2.3139, "step": 28400 }, { "epoch": 1.3, "learning_rate": 4.361297999908463e-05, "loss": 2.3526, "step": 28410 }, { "epoch": 1.3, "learning_rate": 4.3610691564831345e-05, "loss": 2.1556, "step": 28420 }, { "epoch": 1.3, "learning_rate": 4.360840313057806e-05, "loss": 2.1654, "step": 28430 }, { "epoch": 1.3, "learning_rate": 4.360611469632478e-05, "loss": 2.235, "step": 28440 }, { "epoch": 1.3, "learning_rate": 4.3603826262071494e-05, "loss": 2.2458, "step": 28450 }, { "epoch": 1.3, "learning_rate": 4.360153782781821e-05, "loss": 2.2912, "step": 28460 }, { "epoch": 1.3, "learning_rate": 4.359924939356492e-05, "loss": 2.1334, "step": 28470 }, { "epoch": 1.3, "learning_rate": 4.359696095931164e-05, "loss": 2.3474, "step": 28480 }, { "epoch": 1.3, "learning_rate": 4.359467252505836e-05, "loss": 2.1353, "step": 28490 }, { "epoch": 1.3, "learning_rate": 4.359238409080507e-05, "loss": 2.238, "step": 28500 }, { "epoch": 1.3, "learning_rate": 4.3590095656551786e-05, "loss": 2.2878, "step": 28510 }, { "epoch": 1.3, "learning_rate": 4.358780722229851e-05, "loss": 2.2388, "step": 28520 }, { "epoch": 1.3, "learning_rate": 4.358551878804522e-05, "loss": 2.2853, "step": 28530 }, { "epoch": 1.3, "learning_rate": 4.3583230353791935e-05, "loss": 2.1752, "step": 28540 }, { "epoch": 1.3, "learning_rate": 4.3580941919538656e-05, "loss": 2.2086, "step": 28550 }, { "epoch": 1.3, "learning_rate": 4.357865348528537e-05, "loss": 2.2478, "step": 28560 }, { "epoch": 1.3, "learning_rate": 4.3576365051032084e-05, "loss": 2.1211, "step": 28570 }, { "epoch": 1.31, "learning_rate": 4.3574076616778805e-05, "loss": 2.3341, "step": 28580 }, { "epoch": 1.31, "learning_rate": 4.357178818252552e-05, "loss": 2.2607, "step": 28590 }, { "epoch": 1.31, "learning_rate": 4.3569499748272234e-05, "loss": 2.3735, "step": 28600 }, { "epoch": 1.31, "learning_rate": 4.3567211314018954e-05, "loss": 2.127, "step": 28610 }, { "epoch": 1.31, "learning_rate": 4.356492287976567e-05, "loss": 2.1962, "step": 28620 }, { "epoch": 1.31, "learning_rate": 4.356263444551238e-05, "loss": 2.2349, "step": 28630 }, { "epoch": 1.31, "learning_rate": 4.3560346011259104e-05, "loss": 2.1938, "step": 28640 }, { "epoch": 1.31, "learning_rate": 4.355805757700582e-05, "loss": 2.3543, "step": 28650 }, { "epoch": 1.31, "learning_rate": 4.3555769142752525e-05, "loss": 2.286, "step": 28660 }, { "epoch": 1.31, "learning_rate": 4.3553480708499246e-05, "loss": 2.2165, "step": 28670 }, { "epoch": 1.31, "learning_rate": 4.355119227424596e-05, "loss": 2.1705, "step": 28680 }, { "epoch": 1.31, "learning_rate": 4.3548903839992674e-05, "loss": 2.2773, "step": 28690 }, { "epoch": 1.31, "learning_rate": 4.3546615405739395e-05, "loss": 2.2345, "step": 28700 }, { "epoch": 1.31, "learning_rate": 4.354432697148611e-05, "loss": 2.1773, "step": 28710 }, { "epoch": 1.31, "learning_rate": 4.3542038537232823e-05, "loss": 2.3121, "step": 28720 }, { "epoch": 1.31, "learning_rate": 4.3539750102979544e-05, "loss": 2.2116, "step": 28730 }, { "epoch": 1.31, "learning_rate": 4.353746166872626e-05, "loss": 2.1755, "step": 28740 }, { "epoch": 1.31, "learning_rate": 4.353517323447297e-05, "loss": 2.2201, "step": 28750 }, { "epoch": 1.31, "learning_rate": 4.3532884800219694e-05, "loss": 2.044, "step": 28760 }, { "epoch": 1.31, "learning_rate": 4.353059636596641e-05, "loss": 2.2299, "step": 28770 }, { "epoch": 1.31, "learning_rate": 4.352830793171312e-05, "loss": 2.313, "step": 28780 }, { "epoch": 1.31, "learning_rate": 4.352601949745984e-05, "loss": 2.2275, "step": 28790 }, { "epoch": 1.32, "learning_rate": 4.352373106320656e-05, "loss": 2.2114, "step": 28800 }, { "epoch": 1.32, "learning_rate": 4.352144262895327e-05, "loss": 2.1888, "step": 28810 }, { "epoch": 1.32, "learning_rate": 4.351915419469999e-05, "loss": 2.3009, "step": 28820 }, { "epoch": 1.32, "learning_rate": 4.3516865760446706e-05, "loss": 2.156, "step": 28830 }, { "epoch": 1.32, "learning_rate": 4.351457732619342e-05, "loss": 2.3943, "step": 28840 }, { "epoch": 1.32, "learning_rate": 4.3512288891940134e-05, "loss": 2.2082, "step": 28850 }, { "epoch": 1.32, "learning_rate": 4.351000045768685e-05, "loss": 2.2063, "step": 28860 }, { "epoch": 1.32, "learning_rate": 4.350771202343357e-05, "loss": 2.1456, "step": 28870 }, { "epoch": 1.32, "learning_rate": 4.3505423589180283e-05, "loss": 2.315, "step": 28880 }, { "epoch": 1.32, "learning_rate": 4.3503135154927e-05, "loss": 2.2108, "step": 28890 }, { "epoch": 1.32, "learning_rate": 4.350084672067372e-05, "loss": 2.1591, "step": 28900 }, { "epoch": 1.32, "learning_rate": 4.349855828642043e-05, "loss": 2.3843, "step": 28910 }, { "epoch": 1.32, "learning_rate": 4.349626985216715e-05, "loss": 2.2507, "step": 28920 }, { "epoch": 1.32, "learning_rate": 4.349398141791387e-05, "loss": 2.258, "step": 28930 }, { "epoch": 1.32, "learning_rate": 4.349169298366058e-05, "loss": 2.2978, "step": 28940 }, { "epoch": 1.32, "learning_rate": 4.3489404549407296e-05, "loss": 2.2403, "step": 28950 }, { "epoch": 1.32, "learning_rate": 4.348711611515402e-05, "loss": 2.1843, "step": 28960 }, { "epoch": 1.32, "learning_rate": 4.348482768090073e-05, "loss": 2.2447, "step": 28970 }, { "epoch": 1.32, "learning_rate": 4.3482539246647445e-05, "loss": 2.2934, "step": 28980 }, { "epoch": 1.32, "learning_rate": 4.3480250812394166e-05, "loss": 2.2509, "step": 28990 }, { "epoch": 1.32, "learning_rate": 4.347796237814088e-05, "loss": 2.3124, "step": 29000 }, { "epoch": 1.32, "learning_rate": 4.3475673943887594e-05, "loss": 2.2266, "step": 29010 }, { "epoch": 1.33, "learning_rate": 4.3473385509634315e-05, "loss": 2.2617, "step": 29020 }, { "epoch": 1.33, "learning_rate": 4.347109707538103e-05, "loss": 2.1944, "step": 29030 }, { "epoch": 1.33, "learning_rate": 4.3468808641127744e-05, "loss": 2.18, "step": 29040 }, { "epoch": 1.33, "learning_rate": 4.346652020687446e-05, "loss": 2.258, "step": 29050 }, { "epoch": 1.33, "learning_rate": 4.346423177262117e-05, "loss": 2.1956, "step": 29060 }, { "epoch": 1.33, "learning_rate": 4.3461943338367886e-05, "loss": 2.2789, "step": 29070 }, { "epoch": 1.33, "learning_rate": 4.345965490411461e-05, "loss": 2.3498, "step": 29080 }, { "epoch": 1.33, "learning_rate": 4.345736646986132e-05, "loss": 2.1664, "step": 29090 }, { "epoch": 1.33, "learning_rate": 4.3455078035608035e-05, "loss": 2.2124, "step": 29100 }, { "epoch": 1.33, "learning_rate": 4.3452789601354756e-05, "loss": 2.088, "step": 29110 }, { "epoch": 1.33, "learning_rate": 4.345050116710147e-05, "loss": 2.2165, "step": 29120 }, { "epoch": 1.33, "learning_rate": 4.3448212732848184e-05, "loss": 2.3367, "step": 29130 }, { "epoch": 1.33, "learning_rate": 4.3445924298594905e-05, "loss": 2.2032, "step": 29140 }, { "epoch": 1.33, "learning_rate": 4.344363586434162e-05, "loss": 2.1787, "step": 29150 }, { "epoch": 1.33, "learning_rate": 4.3441347430088333e-05, "loss": 2.4806, "step": 29160 }, { "epoch": 1.33, "learning_rate": 4.3439058995835054e-05, "loss": 2.1903, "step": 29170 }, { "epoch": 1.33, "learning_rate": 4.343677056158177e-05, "loss": 2.3536, "step": 29180 }, { "epoch": 1.33, "learning_rate": 4.343448212732848e-05, "loss": 2.2347, "step": 29190 }, { "epoch": 1.33, "learning_rate": 4.3432193693075204e-05, "loss": 2.3333, "step": 29200 }, { "epoch": 1.33, "learning_rate": 4.342990525882192e-05, "loss": 2.0875, "step": 29210 }, { "epoch": 1.33, "learning_rate": 4.342761682456863e-05, "loss": 2.3561, "step": 29220 }, { "epoch": 1.33, "learning_rate": 4.342532839031535e-05, "loss": 2.3866, "step": 29230 }, { "epoch": 1.34, "learning_rate": 4.342303995606207e-05, "loss": 2.2822, "step": 29240 }, { "epoch": 1.34, "learning_rate": 4.342075152180878e-05, "loss": 2.2339, "step": 29250 }, { "epoch": 1.34, "learning_rate": 4.3418463087555495e-05, "loss": 2.1681, "step": 29260 }, { "epoch": 1.34, "learning_rate": 4.341617465330221e-05, "loss": 2.198, "step": 29270 }, { "epoch": 1.34, "learning_rate": 4.341388621904893e-05, "loss": 2.3421, "step": 29280 }, { "epoch": 1.34, "learning_rate": 4.3411597784795644e-05, "loss": 2.1258, "step": 29290 }, { "epoch": 1.34, "learning_rate": 4.340930935054236e-05, "loss": 2.0828, "step": 29300 }, { "epoch": 1.34, "learning_rate": 4.340702091628908e-05, "loss": 2.2138, "step": 29310 }, { "epoch": 1.34, "learning_rate": 4.3404732482035793e-05, "loss": 2.3421, "step": 29320 }, { "epoch": 1.34, "learning_rate": 4.340244404778251e-05, "loss": 2.1044, "step": 29330 }, { "epoch": 1.34, "learning_rate": 4.340015561352923e-05, "loss": 2.2872, "step": 29340 }, { "epoch": 1.34, "learning_rate": 4.339786717927594e-05, "loss": 2.229, "step": 29350 }, { "epoch": 1.34, "learning_rate": 4.339557874502266e-05, "loss": 2.1892, "step": 29360 }, { "epoch": 1.34, "learning_rate": 4.339329031076938e-05, "loss": 2.2239, "step": 29370 }, { "epoch": 1.34, "learning_rate": 4.339100187651609e-05, "loss": 2.3071, "step": 29380 }, { "epoch": 1.34, "learning_rate": 4.3388713442262806e-05, "loss": 2.156, "step": 29390 }, { "epoch": 1.34, "learning_rate": 4.338642500800953e-05, "loss": 2.3141, "step": 29400 }, { "epoch": 1.34, "learning_rate": 4.338413657375624e-05, "loss": 2.2447, "step": 29410 }, { "epoch": 1.34, "learning_rate": 4.3381848139502955e-05, "loss": 2.3828, "step": 29420 }, { "epoch": 1.34, "learning_rate": 4.3379559705249676e-05, "loss": 2.1898, "step": 29430 }, { "epoch": 1.34, "learning_rate": 4.337727127099639e-05, "loss": 2.3228, "step": 29440 }, { "epoch": 1.34, "learning_rate": 4.33749828367431e-05, "loss": 2.1424, "step": 29450 }, { "epoch": 1.35, "learning_rate": 4.337269440248982e-05, "loss": 2.1589, "step": 29460 }, { "epoch": 1.35, "learning_rate": 4.337040596823653e-05, "loss": 2.2187, "step": 29470 }, { "epoch": 1.35, "learning_rate": 4.336811753398325e-05, "loss": 2.4889, "step": 29480 }, { "epoch": 1.35, "learning_rate": 4.336582909972997e-05, "loss": 2.272, "step": 29490 }, { "epoch": 1.35, "learning_rate": 4.336354066547668e-05, "loss": 2.2914, "step": 29500 }, { "epoch": 1.35, "learning_rate": 4.3361252231223396e-05, "loss": 2.2631, "step": 29510 }, { "epoch": 1.35, "learning_rate": 4.335896379697012e-05, "loss": 2.4491, "step": 29520 }, { "epoch": 1.35, "learning_rate": 4.335667536271683e-05, "loss": 2.396, "step": 29530 }, { "epoch": 1.35, "learning_rate": 4.3354386928463545e-05, "loss": 2.1834, "step": 29540 }, { "epoch": 1.35, "learning_rate": 4.3352098494210266e-05, "loss": 2.1647, "step": 29550 }, { "epoch": 1.35, "learning_rate": 4.334981005995698e-05, "loss": 2.3895, "step": 29560 }, { "epoch": 1.35, "learning_rate": 4.3347521625703694e-05, "loss": 2.2374, "step": 29570 }, { "epoch": 1.35, "learning_rate": 4.3345233191450415e-05, "loss": 2.4335, "step": 29580 }, { "epoch": 1.35, "learning_rate": 4.334294475719713e-05, "loss": 2.1876, "step": 29590 }, { "epoch": 1.35, "learning_rate": 4.3340656322943843e-05, "loss": 2.2366, "step": 29600 }, { "epoch": 1.35, "learning_rate": 4.3338367888690564e-05, "loss": 2.1536, "step": 29610 }, { "epoch": 1.35, "learning_rate": 4.333607945443728e-05, "loss": 2.2232, "step": 29620 }, { "epoch": 1.35, "learning_rate": 4.333379102018399e-05, "loss": 2.2074, "step": 29630 }, { "epoch": 1.35, "learning_rate": 4.333150258593071e-05, "loss": 2.1544, "step": 29640 }, { "epoch": 1.35, "learning_rate": 4.332921415167742e-05, "loss": 2.1627, "step": 29650 }, { "epoch": 1.35, "learning_rate": 4.3326925717424135e-05, "loss": 2.2281, "step": 29660 }, { "epoch": 1.35, "learning_rate": 4.3324637283170856e-05, "loss": 2.2996, "step": 29670 }, { "epoch": 1.36, "learning_rate": 4.332234884891757e-05, "loss": 2.2479, "step": 29680 }, { "epoch": 1.36, "learning_rate": 4.3320060414664284e-05, "loss": 2.2395, "step": 29690 }, { "epoch": 1.36, "learning_rate": 4.3317771980411005e-05, "loss": 2.1291, "step": 29700 }, { "epoch": 1.36, "learning_rate": 4.331548354615772e-05, "loss": 2.2037, "step": 29710 }, { "epoch": 1.36, "learning_rate": 4.331319511190443e-05, "loss": 2.1927, "step": 29720 }, { "epoch": 1.36, "learning_rate": 4.3310906677651154e-05, "loss": 2.2686, "step": 29730 }, { "epoch": 1.36, "learning_rate": 4.330861824339787e-05, "loss": 2.1958, "step": 29740 }, { "epoch": 1.36, "learning_rate": 4.330632980914458e-05, "loss": 2.2295, "step": 29750 }, { "epoch": 1.36, "learning_rate": 4.3304041374891303e-05, "loss": 2.1458, "step": 29760 }, { "epoch": 1.36, "learning_rate": 4.330175294063802e-05, "loss": 2.2021, "step": 29770 }, { "epoch": 1.36, "learning_rate": 4.329946450638473e-05, "loss": 2.1875, "step": 29780 }, { "epoch": 1.36, "learning_rate": 4.329717607213145e-05, "loss": 2.3641, "step": 29790 }, { "epoch": 1.36, "learning_rate": 4.329488763787817e-05, "loss": 2.2303, "step": 29800 }, { "epoch": 1.36, "learning_rate": 4.329259920362488e-05, "loss": 2.2166, "step": 29810 }, { "epoch": 1.36, "learning_rate": 4.32903107693716e-05, "loss": 2.3041, "step": 29820 }, { "epoch": 1.36, "learning_rate": 4.3288022335118316e-05, "loss": 2.2859, "step": 29830 }, { "epoch": 1.36, "learning_rate": 4.328573390086503e-05, "loss": 2.186, "step": 29840 }, { "epoch": 1.36, "learning_rate": 4.3283445466611744e-05, "loss": 2.0582, "step": 29850 }, { "epoch": 1.36, "learning_rate": 4.328115703235846e-05, "loss": 2.0965, "step": 29860 }, { "epoch": 1.36, "learning_rate": 4.327886859810518e-05, "loss": 2.3519, "step": 29870 }, { "epoch": 1.36, "learning_rate": 4.327658016385189e-05, "loss": 2.0033, "step": 29880 }, { "epoch": 1.36, "learning_rate": 4.327429172959861e-05, "loss": 2.1667, "step": 29890 }, { "epoch": 1.37, "learning_rate": 4.327200329534533e-05, "loss": 2.2485, "step": 29900 }, { "epoch": 1.37, "learning_rate": 4.326971486109204e-05, "loss": 2.2295, "step": 29910 }, { "epoch": 1.37, "learning_rate": 4.326742642683876e-05, "loss": 2.2631, "step": 29920 }, { "epoch": 1.37, "learning_rate": 4.326513799258548e-05, "loss": 2.1324, "step": 29930 }, { "epoch": 1.37, "learning_rate": 4.326284955833219e-05, "loss": 2.1154, "step": 29940 }, { "epoch": 1.37, "learning_rate": 4.3260561124078906e-05, "loss": 2.1114, "step": 29950 }, { "epoch": 1.37, "learning_rate": 4.325827268982563e-05, "loss": 2.0828, "step": 29960 }, { "epoch": 1.37, "learning_rate": 4.325598425557234e-05, "loss": 2.181, "step": 29970 }, { "epoch": 1.37, "learning_rate": 4.3253695821319055e-05, "loss": 2.167, "step": 29980 }, { "epoch": 1.37, "learning_rate": 4.3251407387065776e-05, "loss": 2.1646, "step": 29990 }, { "epoch": 1.37, "learning_rate": 4.324911895281249e-05, "loss": 2.4273, "step": 30000 }, { "epoch": 1.37, "learning_rate": 4.3246830518559204e-05, "loss": 2.1838, "step": 30010 }, { "epoch": 1.37, "learning_rate": 4.3244542084305925e-05, "loss": 2.1798, "step": 30020 }, { "epoch": 1.37, "learning_rate": 4.324225365005264e-05, "loss": 2.1461, "step": 30030 }, { "epoch": 1.37, "learning_rate": 4.3239965215799347e-05, "loss": 2.2598, "step": 30040 }, { "epoch": 1.37, "learning_rate": 4.323767678154607e-05, "loss": 2.3127, "step": 30050 }, { "epoch": 1.37, "learning_rate": 4.323538834729278e-05, "loss": 2.224, "step": 30060 }, { "epoch": 1.37, "learning_rate": 4.3233099913039496e-05, "loss": 2.1416, "step": 30070 }, { "epoch": 1.37, "learning_rate": 4.323081147878622e-05, "loss": 2.2131, "step": 30080 }, { "epoch": 1.37, "learning_rate": 4.322852304453293e-05, "loss": 2.2283, "step": 30090 }, { "epoch": 1.37, "learning_rate": 4.3226234610279645e-05, "loss": 2.2609, "step": 30100 }, { "epoch": 1.37, "learning_rate": 4.3223946176026366e-05, "loss": 2.369, "step": 30110 }, { "epoch": 1.38, "learning_rate": 4.322165774177308e-05, "loss": 2.302, "step": 30120 }, { "epoch": 1.38, "learning_rate": 4.3219369307519794e-05, "loss": 2.1069, "step": 30130 }, { "epoch": 1.38, "learning_rate": 4.3217080873266515e-05, "loss": 2.1844, "step": 30140 }, { "epoch": 1.38, "learning_rate": 4.321479243901323e-05, "loss": 2.1821, "step": 30150 }, { "epoch": 1.38, "learning_rate": 4.321250400475994e-05, "loss": 2.2828, "step": 30160 }, { "epoch": 1.38, "learning_rate": 4.3210215570506664e-05, "loss": 2.1138, "step": 30170 }, { "epoch": 1.38, "learning_rate": 4.320792713625338e-05, "loss": 2.1709, "step": 30180 }, { "epoch": 1.38, "learning_rate": 4.320563870200009e-05, "loss": 2.2687, "step": 30190 }, { "epoch": 1.38, "learning_rate": 4.3203350267746813e-05, "loss": 2.2764, "step": 30200 }, { "epoch": 1.38, "learning_rate": 4.320106183349353e-05, "loss": 2.1376, "step": 30210 }, { "epoch": 1.38, "learning_rate": 4.319877339924024e-05, "loss": 2.21, "step": 30220 }, { "epoch": 1.38, "learning_rate": 4.319648496498696e-05, "loss": 2.3394, "step": 30230 }, { "epoch": 1.38, "learning_rate": 4.319419653073367e-05, "loss": 2.2004, "step": 30240 }, { "epoch": 1.38, "learning_rate": 4.319190809648039e-05, "loss": 2.2415, "step": 30250 }, { "epoch": 1.38, "learning_rate": 4.3189619662227105e-05, "loss": 2.2223, "step": 30260 }, { "epoch": 1.38, "learning_rate": 4.318733122797382e-05, "loss": 2.2056, "step": 30270 }, { "epoch": 1.38, "learning_rate": 4.318504279372054e-05, "loss": 2.1739, "step": 30280 }, { "epoch": 1.38, "learning_rate": 4.3182754359467254e-05, "loss": 2.2513, "step": 30290 }, { "epoch": 1.38, "learning_rate": 4.318046592521397e-05, "loss": 2.2285, "step": 30300 }, { "epoch": 1.38, "learning_rate": 4.317817749096069e-05, "loss": 2.1973, "step": 30310 }, { "epoch": 1.38, "learning_rate": 4.31758890567074e-05, "loss": 2.288, "step": 30320 }, { "epoch": 1.38, "learning_rate": 4.317360062245412e-05, "loss": 2.222, "step": 30330 }, { "epoch": 1.39, "learning_rate": 4.317131218820084e-05, "loss": 2.2129, "step": 30340 }, { "epoch": 1.39, "learning_rate": 4.316902375394755e-05, "loss": 2.1939, "step": 30350 }, { "epoch": 1.39, "learning_rate": 4.316673531969427e-05, "loss": 2.1453, "step": 30360 }, { "epoch": 1.39, "learning_rate": 4.316444688544099e-05, "loss": 2.2643, "step": 30370 }, { "epoch": 1.39, "learning_rate": 4.31621584511877e-05, "loss": 2.2076, "step": 30380 }, { "epoch": 1.39, "learning_rate": 4.3159870016934416e-05, "loss": 2.2992, "step": 30390 }, { "epoch": 1.39, "learning_rate": 4.315758158268114e-05, "loss": 2.1558, "step": 30400 }, { "epoch": 1.39, "learning_rate": 4.315529314842785e-05, "loss": 2.1643, "step": 30410 }, { "epoch": 1.39, "learning_rate": 4.3153004714174565e-05, "loss": 2.2879, "step": 30420 }, { "epoch": 1.39, "learning_rate": 4.315071627992128e-05, "loss": 2.1673, "step": 30430 }, { "epoch": 1.39, "learning_rate": 4.314842784566799e-05, "loss": 2.2692, "step": 30440 }, { "epoch": 1.39, "learning_rate": 4.314613941141471e-05, "loss": 2.1402, "step": 30450 }, { "epoch": 1.39, "learning_rate": 4.314385097716143e-05, "loss": 2.0736, "step": 30460 }, { "epoch": 1.39, "learning_rate": 4.314156254290814e-05, "loss": 1.974, "step": 30470 }, { "epoch": 1.39, "learning_rate": 4.3139274108654857e-05, "loss": 2.1676, "step": 30480 }, { "epoch": 1.39, "learning_rate": 4.313698567440158e-05, "loss": 2.4785, "step": 30490 }, { "epoch": 1.39, "learning_rate": 4.313469724014829e-05, "loss": 2.3165, "step": 30500 }, { "epoch": 1.39, "learning_rate": 4.3132408805895006e-05, "loss": 2.1718, "step": 30510 }, { "epoch": 1.39, "learning_rate": 4.313012037164173e-05, "loss": 2.1832, "step": 30520 }, { "epoch": 1.39, "learning_rate": 4.312783193738844e-05, "loss": 2.1106, "step": 30530 }, { "epoch": 1.39, "learning_rate": 4.3125543503135155e-05, "loss": 2.2157, "step": 30540 }, { "epoch": 1.39, "learning_rate": 4.3123255068881876e-05, "loss": 2.1361, "step": 30550 }, { "epoch": 1.4, "learning_rate": 4.312096663462859e-05, "loss": 2.2359, "step": 30560 }, { "epoch": 1.4, "learning_rate": 4.3118678200375304e-05, "loss": 2.3474, "step": 30570 }, { "epoch": 1.4, "learning_rate": 4.3116389766122025e-05, "loss": 2.3103, "step": 30580 }, { "epoch": 1.4, "learning_rate": 4.311410133186874e-05, "loss": 2.3129, "step": 30590 }, { "epoch": 1.4, "learning_rate": 4.311181289761545e-05, "loss": 2.3058, "step": 30600 }, { "epoch": 1.4, "learning_rate": 4.3109524463362174e-05, "loss": 2.1802, "step": 30610 }, { "epoch": 1.4, "learning_rate": 4.310723602910889e-05, "loss": 2.2355, "step": 30620 }, { "epoch": 1.4, "learning_rate": 4.31049475948556e-05, "loss": 2.1984, "step": 30630 }, { "epoch": 1.4, "learning_rate": 4.3102659160602317e-05, "loss": 2.2107, "step": 30640 }, { "epoch": 1.4, "learning_rate": 4.310037072634903e-05, "loss": 2.2247, "step": 30650 }, { "epoch": 1.4, "learning_rate": 4.309808229209575e-05, "loss": 2.1505, "step": 30660 }, { "epoch": 1.4, "learning_rate": 4.3095793857842466e-05, "loss": 2.0614, "step": 30670 }, { "epoch": 1.4, "learning_rate": 4.309350542358918e-05, "loss": 2.1895, "step": 30680 }, { "epoch": 1.4, "learning_rate": 4.30912169893359e-05, "loss": 2.3373, "step": 30690 }, { "epoch": 1.4, "learning_rate": 4.3088928555082615e-05, "loss": 2.278, "step": 30700 }, { "epoch": 1.4, "learning_rate": 4.308664012082933e-05, "loss": 2.2681, "step": 30710 }, { "epoch": 1.4, "learning_rate": 4.308435168657604e-05, "loss": 2.1067, "step": 30720 }, { "epoch": 1.4, "learning_rate": 4.3082063252322764e-05, "loss": 2.1806, "step": 30730 }, { "epoch": 1.4, "learning_rate": 4.307977481806948e-05, "loss": 2.3632, "step": 30740 }, { "epoch": 1.4, "learning_rate": 4.307748638381619e-05, "loss": 2.2345, "step": 30750 }, { "epoch": 1.4, "learning_rate": 4.307519794956291e-05, "loss": 2.1244, "step": 30760 }, { "epoch": 1.41, "learning_rate": 4.307290951530963e-05, "loss": 2.3158, "step": 30770 }, { "epoch": 1.41, "learning_rate": 4.307062108105634e-05, "loss": 2.2439, "step": 30780 }, { "epoch": 1.41, "learning_rate": 4.306833264680306e-05, "loss": 2.2354, "step": 30790 }, { "epoch": 1.41, "learning_rate": 4.3066044212549777e-05, "loss": 2.1096, "step": 30800 }, { "epoch": 1.41, "learning_rate": 4.306375577829649e-05, "loss": 2.1907, "step": 30810 }, { "epoch": 1.41, "learning_rate": 4.306146734404321e-05, "loss": 2.3055, "step": 30820 }, { "epoch": 1.41, "learning_rate": 4.305917890978992e-05, "loss": 2.1593, "step": 30830 }, { "epoch": 1.41, "learning_rate": 4.305689047553664e-05, "loss": 2.3347, "step": 30840 }, { "epoch": 1.41, "learning_rate": 4.3054602041283354e-05, "loss": 2.2102, "step": 30850 }, { "epoch": 1.41, "learning_rate": 4.305231360703007e-05, "loss": 2.1912, "step": 30860 }, { "epoch": 1.41, "learning_rate": 4.305002517277679e-05, "loss": 2.1009, "step": 30870 }, { "epoch": 1.41, "learning_rate": 4.30477367385235e-05, "loss": 2.2457, "step": 30880 }, { "epoch": 1.41, "learning_rate": 4.304544830427022e-05, "loss": 2.188, "step": 30890 }, { "epoch": 1.41, "learning_rate": 4.304315987001694e-05, "loss": 2.1745, "step": 30900 }, { "epoch": 1.41, "learning_rate": 4.304087143576365e-05, "loss": 2.2953, "step": 30910 }, { "epoch": 1.41, "learning_rate": 4.3038583001510367e-05, "loss": 2.2876, "step": 30920 }, { "epoch": 1.41, "learning_rate": 4.303629456725709e-05, "loss": 2.1985, "step": 30930 }, { "epoch": 1.41, "learning_rate": 4.30340061330038e-05, "loss": 2.3028, "step": 30940 }, { "epoch": 1.41, "learning_rate": 4.3031717698750516e-05, "loss": 2.2545, "step": 30950 }, { "epoch": 1.41, "learning_rate": 4.302942926449724e-05, "loss": 2.187, "step": 30960 }, { "epoch": 1.41, "learning_rate": 4.302714083024395e-05, "loss": 2.3894, "step": 30970 }, { "epoch": 1.41, "learning_rate": 4.3024852395990665e-05, "loss": 2.2724, "step": 30980 }, { "epoch": 1.42, "learning_rate": 4.3022563961737386e-05, "loss": 2.2302, "step": 30990 }, { "epoch": 1.42, "learning_rate": 4.30202755274841e-05, "loss": 2.1978, "step": 31000 }, { "epoch": 1.42, "learning_rate": 4.3017987093230814e-05, "loss": 2.3603, "step": 31010 }, { "epoch": 1.42, "learning_rate": 4.3015698658977535e-05, "loss": 2.4779, "step": 31020 }, { "epoch": 1.42, "learning_rate": 4.301341022472424e-05, "loss": 2.2738, "step": 31030 }, { "epoch": 1.42, "learning_rate": 4.3011121790470956e-05, "loss": 2.1416, "step": 31040 }, { "epoch": 1.42, "learning_rate": 4.300883335621768e-05, "loss": 2.3144, "step": 31050 }, { "epoch": 1.42, "learning_rate": 4.300654492196439e-05, "loss": 2.1115, "step": 31060 }, { "epoch": 1.42, "learning_rate": 4.3004256487711106e-05, "loss": 2.1508, "step": 31070 }, { "epoch": 1.42, "learning_rate": 4.3001968053457827e-05, "loss": 2.1838, "step": 31080 }, { "epoch": 1.42, "learning_rate": 4.299967961920454e-05, "loss": 2.3693, "step": 31090 }, { "epoch": 1.42, "learning_rate": 4.2997391184951255e-05, "loss": 2.2568, "step": 31100 }, { "epoch": 1.42, "learning_rate": 4.2995102750697976e-05, "loss": 2.3192, "step": 31110 }, { "epoch": 1.42, "learning_rate": 4.299281431644469e-05, "loss": 2.4779, "step": 31120 }, { "epoch": 1.42, "learning_rate": 4.2990525882191404e-05, "loss": 2.1924, "step": 31130 }, { "epoch": 1.42, "learning_rate": 4.2988237447938125e-05, "loss": 2.3117, "step": 31140 }, { "epoch": 1.42, "learning_rate": 4.298594901368484e-05, "loss": 2.0065, "step": 31150 }, { "epoch": 1.42, "learning_rate": 4.298366057943155e-05, "loss": 2.1335, "step": 31160 }, { "epoch": 1.42, "learning_rate": 4.2981372145178274e-05, "loss": 1.9879, "step": 31170 }, { "epoch": 1.42, "learning_rate": 4.297908371092499e-05, "loss": 2.2162, "step": 31180 }, { "epoch": 1.42, "learning_rate": 4.29767952766717e-05, "loss": 2.2648, "step": 31190 }, { "epoch": 1.42, "learning_rate": 4.297450684241842e-05, "loss": 2.2867, "step": 31200 }, { "epoch": 1.43, "learning_rate": 4.297221840816514e-05, "loss": 2.2847, "step": 31210 }, { "epoch": 1.43, "learning_rate": 4.296992997391185e-05, "loss": 2.1235, "step": 31220 }, { "epoch": 1.43, "learning_rate": 4.2967641539658566e-05, "loss": 2.3444, "step": 31230 }, { "epoch": 1.43, "learning_rate": 4.296535310540528e-05, "loss": 2.2229, "step": 31240 }, { "epoch": 1.43, "learning_rate": 4.2963064671152e-05, "loss": 1.9664, "step": 31250 }, { "epoch": 1.43, "learning_rate": 4.2960776236898715e-05, "loss": 2.1325, "step": 31260 }, { "epoch": 1.43, "learning_rate": 4.295848780264543e-05, "loss": 2.1716, "step": 31270 }, { "epoch": 1.43, "learning_rate": 4.295619936839215e-05, "loss": 2.1697, "step": 31280 }, { "epoch": 1.43, "learning_rate": 4.2953910934138864e-05, "loss": 2.1955, "step": 31290 }, { "epoch": 1.43, "learning_rate": 4.295162249988558e-05, "loss": 2.2008, "step": 31300 }, { "epoch": 1.43, "learning_rate": 4.29493340656323e-05, "loss": 2.2629, "step": 31310 }, { "epoch": 1.43, "learning_rate": 4.294704563137901e-05, "loss": 2.2488, "step": 31320 }, { "epoch": 1.43, "learning_rate": 4.294475719712573e-05, "loss": 2.4432, "step": 31330 }, { "epoch": 1.43, "learning_rate": 4.294246876287245e-05, "loss": 2.3888, "step": 31340 }, { "epoch": 1.43, "learning_rate": 4.294018032861916e-05, "loss": 2.1607, "step": 31350 }, { "epoch": 1.43, "learning_rate": 4.2937891894365876e-05, "loss": 2.1428, "step": 31360 }, { "epoch": 1.43, "learning_rate": 4.29356034601126e-05, "loss": 2.4004, "step": 31370 }, { "epoch": 1.43, "learning_rate": 4.293331502585931e-05, "loss": 2.2973, "step": 31380 }, { "epoch": 1.43, "learning_rate": 4.2931026591606026e-05, "loss": 2.3542, "step": 31390 }, { "epoch": 1.43, "learning_rate": 4.2928738157352747e-05, "loss": 2.2205, "step": 31400 }, { "epoch": 1.43, "learning_rate": 4.292644972309946e-05, "loss": 2.3896, "step": 31410 }, { "epoch": 1.43, "learning_rate": 4.292416128884617e-05, "loss": 2.2465, "step": 31420 }, { "epoch": 1.44, "learning_rate": 4.292187285459289e-05, "loss": 2.273, "step": 31430 }, { "epoch": 1.44, "learning_rate": 4.29195844203396e-05, "loss": 2.1914, "step": 31440 }, { "epoch": 1.44, "learning_rate": 4.291729598608632e-05, "loss": 2.2173, "step": 31450 }, { "epoch": 1.44, "learning_rate": 4.291500755183304e-05, "loss": 2.3386, "step": 31460 }, { "epoch": 1.44, "learning_rate": 4.291271911757975e-05, "loss": 2.2413, "step": 31470 }, { "epoch": 1.44, "learning_rate": 4.2910430683326466e-05, "loss": 2.311, "step": 31480 }, { "epoch": 1.44, "learning_rate": 4.290814224907319e-05, "loss": 2.1829, "step": 31490 }, { "epoch": 1.44, "learning_rate": 4.29058538148199e-05, "loss": 2.1876, "step": 31500 }, { "epoch": 1.44, "learning_rate": 4.2903565380566616e-05, "loss": 2.2679, "step": 31510 }, { "epoch": 1.44, "learning_rate": 4.2901276946313337e-05, "loss": 2.093, "step": 31520 }, { "epoch": 1.44, "learning_rate": 4.289898851206005e-05, "loss": 2.2558, "step": 31530 }, { "epoch": 1.44, "learning_rate": 4.2896700077806765e-05, "loss": 2.2189, "step": 31540 }, { "epoch": 1.44, "learning_rate": 4.2894411643553486e-05, "loss": 2.2589, "step": 31550 }, { "epoch": 1.44, "learning_rate": 4.28921232093002e-05, "loss": 2.1485, "step": 31560 }, { "epoch": 1.44, "learning_rate": 4.2889834775046914e-05, "loss": 2.1215, "step": 31570 }, { "epoch": 1.44, "learning_rate": 4.2887546340793635e-05, "loss": 2.2167, "step": 31580 }, { "epoch": 1.44, "learning_rate": 4.288525790654035e-05, "loss": 2.1047, "step": 31590 }, { "epoch": 1.44, "learning_rate": 4.288296947228706e-05, "loss": 2.234, "step": 31600 }, { "epoch": 1.44, "learning_rate": 4.2880681038033784e-05, "loss": 2.1413, "step": 31610 }, { "epoch": 1.44, "learning_rate": 4.287839260378049e-05, "loss": 2.3551, "step": 31620 }, { "epoch": 1.44, "learning_rate": 4.287610416952721e-05, "loss": 2.2624, "step": 31630 }, { "epoch": 1.44, "learning_rate": 4.2873815735273926e-05, "loss": 2.2554, "step": 31640 }, { "epoch": 1.45, "learning_rate": 4.287152730102064e-05, "loss": 2.2238, "step": 31650 }, { "epoch": 1.45, "learning_rate": 4.286923886676736e-05, "loss": 2.1791, "step": 31660 }, { "epoch": 1.45, "learning_rate": 4.2866950432514076e-05, "loss": 2.2204, "step": 31670 }, { "epoch": 1.45, "learning_rate": 4.286466199826079e-05, "loss": 2.1995, "step": 31680 }, { "epoch": 1.45, "learning_rate": 4.286237356400751e-05, "loss": 2.3055, "step": 31690 }, { "epoch": 1.45, "learning_rate": 4.2860085129754225e-05, "loss": 2.347, "step": 31700 }, { "epoch": 1.45, "learning_rate": 4.285779669550094e-05, "loss": 2.3063, "step": 31710 }, { "epoch": 1.45, "learning_rate": 4.285550826124766e-05, "loss": 2.1583, "step": 31720 }, { "epoch": 1.45, "learning_rate": 4.2853219826994374e-05, "loss": 2.255, "step": 31730 }, { "epoch": 1.45, "learning_rate": 4.285093139274109e-05, "loss": 2.2679, "step": 31740 }, { "epoch": 1.45, "learning_rate": 4.284864295848781e-05, "loss": 2.1864, "step": 31750 }, { "epoch": 1.45, "learning_rate": 4.284635452423452e-05, "loss": 2.1921, "step": 31760 }, { "epoch": 1.45, "learning_rate": 4.284406608998124e-05, "loss": 2.2157, "step": 31770 }, { "epoch": 1.45, "learning_rate": 4.284177765572796e-05, "loss": 2.0777, "step": 31780 }, { "epoch": 1.45, "learning_rate": 4.283948922147467e-05, "loss": 2.1361, "step": 31790 }, { "epoch": 1.45, "learning_rate": 4.2837200787221386e-05, "loss": 2.1517, "step": 31800 }, { "epoch": 1.45, "learning_rate": 4.283491235296811e-05, "loss": 2.1932, "step": 31810 }, { "epoch": 1.45, "learning_rate": 4.2832623918714815e-05, "loss": 2.3012, "step": 31820 }, { "epoch": 1.45, "learning_rate": 4.283033548446153e-05, "loss": 2.1053, "step": 31830 }, { "epoch": 1.45, "learning_rate": 4.282804705020825e-05, "loss": 2.3736, "step": 31840 }, { "epoch": 1.45, "learning_rate": 4.2825758615954964e-05, "loss": 2.3986, "step": 31850 }, { "epoch": 1.45, "learning_rate": 4.282347018170168e-05, "loss": 2.1427, "step": 31860 }, { "epoch": 1.46, "learning_rate": 4.28211817474484e-05, "loss": 2.231, "step": 31870 }, { "epoch": 1.46, "learning_rate": 4.281889331319511e-05, "loss": 2.2593, "step": 31880 }, { "epoch": 1.46, "learning_rate": 4.281660487894183e-05, "loss": 2.3056, "step": 31890 }, { "epoch": 1.46, "learning_rate": 4.281431644468855e-05, "loss": 2.3066, "step": 31900 }, { "epoch": 1.46, "learning_rate": 4.281202801043526e-05, "loss": 2.2162, "step": 31910 }, { "epoch": 1.46, "learning_rate": 4.2809739576181976e-05, "loss": 2.1342, "step": 31920 }, { "epoch": 1.46, "learning_rate": 4.28074511419287e-05, "loss": 2.3457, "step": 31930 }, { "epoch": 1.46, "learning_rate": 4.280516270767541e-05, "loss": 2.389, "step": 31940 }, { "epoch": 1.46, "learning_rate": 4.2802874273422126e-05, "loss": 2.2048, "step": 31950 }, { "epoch": 1.46, "learning_rate": 4.2800585839168846e-05, "loss": 2.151, "step": 31960 }, { "epoch": 1.46, "learning_rate": 4.279829740491556e-05, "loss": 2.4466, "step": 31970 }, { "epoch": 1.46, "learning_rate": 4.2796008970662275e-05, "loss": 2.2355, "step": 31980 }, { "epoch": 1.46, "learning_rate": 4.2793720536408996e-05, "loss": 2.2525, "step": 31990 }, { "epoch": 1.46, "learning_rate": 4.279143210215571e-05, "loss": 2.2034, "step": 32000 }, { "epoch": 1.46, "learning_rate": 4.278914366790242e-05, "loss": 2.0604, "step": 32010 }, { "epoch": 1.46, "learning_rate": 4.278685523364914e-05, "loss": 2.2791, "step": 32020 }, { "epoch": 1.46, "learning_rate": 4.278456679939585e-05, "loss": 2.2555, "step": 32030 }, { "epoch": 1.46, "learning_rate": 4.2782278365142566e-05, "loss": 2.1505, "step": 32040 }, { "epoch": 1.46, "learning_rate": 4.277998993088929e-05, "loss": 2.2419, "step": 32050 }, { "epoch": 1.46, "learning_rate": 4.2777701496636e-05, "loss": 2.3066, "step": 32060 }, { "epoch": 1.46, "learning_rate": 4.2775413062382716e-05, "loss": 2.1971, "step": 32070 }, { "epoch": 1.46, "learning_rate": 4.2773124628129436e-05, "loss": 2.1851, "step": 32080 }, { "epoch": 1.47, "learning_rate": 4.277083619387615e-05, "loss": 2.1003, "step": 32090 }, { "epoch": 1.47, "learning_rate": 4.2768547759622865e-05, "loss": 2.3021, "step": 32100 }, { "epoch": 1.47, "learning_rate": 4.2766259325369586e-05, "loss": 2.2298, "step": 32110 }, { "epoch": 1.47, "learning_rate": 4.27639708911163e-05, "loss": 2.233, "step": 32120 }, { "epoch": 1.47, "learning_rate": 4.2761682456863014e-05, "loss": 2.2092, "step": 32130 }, { "epoch": 1.47, "learning_rate": 4.2759394022609735e-05, "loss": 2.3636, "step": 32140 }, { "epoch": 1.47, "learning_rate": 4.275710558835645e-05, "loss": 2.2813, "step": 32150 }, { "epoch": 1.47, "learning_rate": 4.275481715410316e-05, "loss": 2.2029, "step": 32160 }, { "epoch": 1.47, "learning_rate": 4.2752528719849884e-05, "loss": 2.2327, "step": 32170 }, { "epoch": 1.47, "learning_rate": 4.27502402855966e-05, "loss": 2.1501, "step": 32180 }, { "epoch": 1.47, "learning_rate": 4.274795185134331e-05, "loss": 2.1567, "step": 32190 }, { "epoch": 1.47, "learning_rate": 4.274566341709003e-05, "loss": 2.3492, "step": 32200 }, { "epoch": 1.47, "learning_rate": 4.274337498283674e-05, "loss": 2.0717, "step": 32210 }, { "epoch": 1.47, "learning_rate": 4.274108654858346e-05, "loss": 2.3169, "step": 32220 }, { "epoch": 1.47, "learning_rate": 4.2738798114330176e-05, "loss": 2.1344, "step": 32230 }, { "epoch": 1.47, "learning_rate": 4.273650968007689e-05, "loss": 2.3019, "step": 32240 }, { "epoch": 1.47, "learning_rate": 4.273422124582361e-05, "loss": 2.1252, "step": 32250 }, { "epoch": 1.47, "learning_rate": 4.2731932811570325e-05, "loss": 2.2579, "step": 32260 }, { "epoch": 1.47, "learning_rate": 4.272964437731704e-05, "loss": 2.2233, "step": 32270 }, { "epoch": 1.47, "learning_rate": 4.272735594306376e-05, "loss": 2.2057, "step": 32280 }, { "epoch": 1.47, "learning_rate": 4.2725067508810474e-05, "loss": 2.0583, "step": 32290 }, { "epoch": 1.47, "learning_rate": 4.272277907455719e-05, "loss": 2.1692, "step": 32300 }, { "epoch": 1.48, "learning_rate": 4.272049064030391e-05, "loss": 2.13, "step": 32310 }, { "epoch": 1.48, "learning_rate": 4.271820220605062e-05, "loss": 2.31, "step": 32320 }, { "epoch": 1.48, "learning_rate": 4.271591377179734e-05, "loss": 2.2885, "step": 32330 }, { "epoch": 1.48, "learning_rate": 4.271362533754406e-05, "loss": 2.1345, "step": 32340 }, { "epoch": 1.48, "learning_rate": 4.271133690329077e-05, "loss": 2.2834, "step": 32350 }, { "epoch": 1.48, "learning_rate": 4.2709048469037486e-05, "loss": 2.1406, "step": 32360 }, { "epoch": 1.48, "learning_rate": 4.270676003478421e-05, "loss": 2.1692, "step": 32370 }, { "epoch": 1.48, "learning_rate": 4.270447160053092e-05, "loss": 2.0842, "step": 32380 }, { "epoch": 1.48, "learning_rate": 4.2702183166277636e-05, "loss": 2.4615, "step": 32390 }, { "epoch": 1.48, "learning_rate": 4.2699894732024356e-05, "loss": 2.3487, "step": 32400 }, { "epoch": 1.48, "learning_rate": 4.2697606297771064e-05, "loss": 2.3381, "step": 32410 }, { "epoch": 1.48, "learning_rate": 4.269531786351778e-05, "loss": 2.0452, "step": 32420 }, { "epoch": 1.48, "learning_rate": 4.26930294292645e-05, "loss": 2.2379, "step": 32430 }, { "epoch": 1.48, "learning_rate": 4.269074099501121e-05, "loss": 2.1313, "step": 32440 }, { "epoch": 1.48, "learning_rate": 4.268845256075793e-05, "loss": 2.2193, "step": 32450 }, { "epoch": 1.48, "learning_rate": 4.268616412650465e-05, "loss": 2.1174, "step": 32460 }, { "epoch": 1.48, "learning_rate": 4.268387569225136e-05, "loss": 2.1612, "step": 32470 }, { "epoch": 1.48, "learning_rate": 4.2681587257998076e-05, "loss": 2.1723, "step": 32480 }, { "epoch": 1.48, "learning_rate": 4.26792988237448e-05, "loss": 2.2586, "step": 32490 }, { "epoch": 1.48, "learning_rate": 4.267701038949151e-05, "loss": 2.4147, "step": 32500 }, { "epoch": 1.48, "learning_rate": 4.2674721955238225e-05, "loss": 2.1713, "step": 32510 }, { "epoch": 1.48, "learning_rate": 4.2672433520984946e-05, "loss": 2.1519, "step": 32520 }, { "epoch": 1.49, "learning_rate": 4.267014508673166e-05, "loss": 2.1388, "step": 32530 }, { "epoch": 1.49, "learning_rate": 4.2667856652478375e-05, "loss": 2.104, "step": 32540 }, { "epoch": 1.49, "learning_rate": 4.2665568218225096e-05, "loss": 2.3845, "step": 32550 }, { "epoch": 1.49, "learning_rate": 4.266327978397181e-05, "loss": 2.2161, "step": 32560 }, { "epoch": 1.49, "learning_rate": 4.2660991349718524e-05, "loss": 2.2173, "step": 32570 }, { "epoch": 1.49, "learning_rate": 4.2658702915465245e-05, "loss": 2.2043, "step": 32580 }, { "epoch": 1.49, "learning_rate": 4.265641448121196e-05, "loss": 2.0207, "step": 32590 }, { "epoch": 1.49, "learning_rate": 4.265412604695867e-05, "loss": 2.2986, "step": 32600 }, { "epoch": 1.49, "learning_rate": 4.265183761270539e-05, "loss": 2.2634, "step": 32610 }, { "epoch": 1.49, "learning_rate": 4.26495491784521e-05, "loss": 2.1476, "step": 32620 }, { "epoch": 1.49, "learning_rate": 4.264726074419882e-05, "loss": 2.1256, "step": 32630 }, { "epoch": 1.49, "learning_rate": 4.2644972309945536e-05, "loss": 2.3349, "step": 32640 }, { "epoch": 1.49, "learning_rate": 4.264268387569225e-05, "loss": 2.2284, "step": 32650 }, { "epoch": 1.49, "learning_rate": 4.264039544143897e-05, "loss": 2.2046, "step": 32660 }, { "epoch": 1.49, "learning_rate": 4.2638107007185685e-05, "loss": 2.2313, "step": 32670 }, { "epoch": 1.49, "learning_rate": 4.26358185729324e-05, "loss": 2.2101, "step": 32680 }, { "epoch": 1.49, "learning_rate": 4.263353013867912e-05, "loss": 2.0471, "step": 32690 }, { "epoch": 1.49, "learning_rate": 4.2631241704425835e-05, "loss": 2.2273, "step": 32700 }, { "epoch": 1.49, "learning_rate": 4.262895327017255e-05, "loss": 2.4085, "step": 32710 }, { "epoch": 1.49, "learning_rate": 4.262666483591927e-05, "loss": 2.1995, "step": 32720 }, { "epoch": 1.49, "learning_rate": 4.2624376401665984e-05, "loss": 2.2503, "step": 32730 }, { "epoch": 1.49, "learning_rate": 4.26220879674127e-05, "loss": 2.2267, "step": 32740 }, { "epoch": 1.5, "learning_rate": 4.261979953315942e-05, "loss": 2.1581, "step": 32750 }, { "epoch": 1.5, "learning_rate": 4.261751109890613e-05, "loss": 2.1856, "step": 32760 }, { "epoch": 1.5, "learning_rate": 4.261522266465285e-05, "loss": 2.0782, "step": 32770 }, { "epoch": 1.5, "learning_rate": 4.261293423039957e-05, "loss": 2.3296, "step": 32780 }, { "epoch": 1.5, "learning_rate": 4.261064579614628e-05, "loss": 2.2135, "step": 32790 }, { "epoch": 1.5, "learning_rate": 4.260835736189299e-05, "loss": 2.2302, "step": 32800 }, { "epoch": 1.5, "learning_rate": 4.260606892763971e-05, "loss": 2.2826, "step": 32810 }, { "epoch": 1.5, "learning_rate": 4.2603780493386425e-05, "loss": 2.0461, "step": 32820 }, { "epoch": 1.5, "learning_rate": 4.260149205913314e-05, "loss": 2.1862, "step": 32830 }, { "epoch": 1.5, "learning_rate": 4.259920362487986e-05, "loss": 2.1002, "step": 32840 }, { "epoch": 1.5, "learning_rate": 4.2596915190626574e-05, "loss": 2.2922, "step": 32850 }, { "epoch": 1.5, "learning_rate": 4.259462675637329e-05, "loss": 2.3698, "step": 32860 }, { "epoch": 1.5, "learning_rate": 4.259233832212001e-05, "loss": 2.3093, "step": 32870 }, { "epoch": 1.5, "learning_rate": 4.259004988786672e-05, "loss": 2.1976, "step": 32880 }, { "epoch": 1.5, "learning_rate": 4.258776145361344e-05, "loss": 2.2558, "step": 32890 }, { "epoch": 1.5, "learning_rate": 4.258547301936016e-05, "loss": 2.1742, "step": 32900 }, { "epoch": 1.5, "learning_rate": 4.258318458510687e-05, "loss": 2.1748, "step": 32910 }, { "epoch": 1.5, "learning_rate": 4.2580896150853586e-05, "loss": 2.2561, "step": 32920 }, { "epoch": 1.5, "learning_rate": 4.257860771660031e-05, "loss": 2.2606, "step": 32930 }, { "epoch": 1.5, "learning_rate": 4.257631928234702e-05, "loss": 2.2333, "step": 32940 }, { "epoch": 1.5, "learning_rate": 4.2574030848093735e-05, "loss": 2.1043, "step": 32950 }, { "epoch": 1.51, "learning_rate": 4.2571742413840456e-05, "loss": 2.202, "step": 32960 }, { "epoch": 1.51, "learning_rate": 4.256945397958717e-05, "loss": 2.2024, "step": 32970 }, { "epoch": 1.51, "learning_rate": 4.2567165545333885e-05, "loss": 2.2767, "step": 32980 }, { "epoch": 1.51, "learning_rate": 4.2564877111080606e-05, "loss": 2.2455, "step": 32990 }, { "epoch": 1.51, "learning_rate": 4.256258867682731e-05, "loss": 2.3282, "step": 33000 }, { "epoch": 1.51, "learning_rate": 4.2560300242574034e-05, "loss": 2.3156, "step": 33010 }, { "epoch": 1.51, "learning_rate": 4.255801180832075e-05, "loss": 2.1635, "step": 33020 }, { "epoch": 1.51, "learning_rate": 4.255572337406746e-05, "loss": 2.11, "step": 33030 }, { "epoch": 1.51, "learning_rate": 4.255343493981418e-05, "loss": 2.2586, "step": 33040 }, { "epoch": 1.51, "learning_rate": 4.25511465055609e-05, "loss": 2.1521, "step": 33050 }, { "epoch": 1.51, "learning_rate": 4.254885807130761e-05, "loss": 2.2598, "step": 33060 }, { "epoch": 1.51, "learning_rate": 4.2546569637054325e-05, "loss": 2.1127, "step": 33070 }, { "epoch": 1.51, "learning_rate": 4.2544281202801046e-05, "loss": 2.2963, "step": 33080 }, { "epoch": 1.51, "learning_rate": 4.254199276854776e-05, "loss": 2.2106, "step": 33090 }, { "epoch": 1.51, "learning_rate": 4.2539704334294475e-05, "loss": 2.1254, "step": 33100 }, { "epoch": 1.51, "learning_rate": 4.2537415900041195e-05, "loss": 2.081, "step": 33110 }, { "epoch": 1.51, "learning_rate": 4.253512746578791e-05, "loss": 2.0497, "step": 33120 }, { "epoch": 1.51, "learning_rate": 4.2532839031534624e-05, "loss": 2.2062, "step": 33130 }, { "epoch": 1.51, "learning_rate": 4.2530550597281345e-05, "loss": 2.2268, "step": 33140 }, { "epoch": 1.51, "learning_rate": 4.252826216302806e-05, "loss": 2.3673, "step": 33150 }, { "epoch": 1.51, "learning_rate": 4.252597372877477e-05, "loss": 2.1283, "step": 33160 }, { "epoch": 1.51, "learning_rate": 4.2523685294521494e-05, "loss": 2.1327, "step": 33170 }, { "epoch": 1.52, "learning_rate": 4.252139686026821e-05, "loss": 2.3224, "step": 33180 }, { "epoch": 1.52, "learning_rate": 4.251910842601492e-05, "loss": 2.467, "step": 33190 }, { "epoch": 1.52, "learning_rate": 4.2516819991761636e-05, "loss": 2.159, "step": 33200 }, { "epoch": 1.52, "learning_rate": 4.251453155750835e-05, "loss": 2.1181, "step": 33210 }, { "epoch": 1.52, "learning_rate": 4.251224312325507e-05, "loss": 2.162, "step": 33220 }, { "epoch": 1.52, "learning_rate": 4.2509954689001785e-05, "loss": 2.0516, "step": 33230 }, { "epoch": 1.52, "learning_rate": 4.25076662547485e-05, "loss": 2.2369, "step": 33240 }, { "epoch": 1.52, "learning_rate": 4.250537782049522e-05, "loss": 2.1377, "step": 33250 }, { "epoch": 1.52, "learning_rate": 4.2503089386241935e-05, "loss": 2.2446, "step": 33260 }, { "epoch": 1.52, "learning_rate": 4.250080095198865e-05, "loss": 2.0305, "step": 33270 }, { "epoch": 1.52, "learning_rate": 4.249851251773537e-05, "loss": 2.2006, "step": 33280 }, { "epoch": 1.52, "learning_rate": 4.2496224083482084e-05, "loss": 2.3457, "step": 33290 }, { "epoch": 1.52, "learning_rate": 4.24939356492288e-05, "loss": 2.105, "step": 33300 }, { "epoch": 1.52, "learning_rate": 4.249164721497552e-05, "loss": 2.1621, "step": 33310 }, { "epoch": 1.52, "learning_rate": 4.248935878072223e-05, "loss": 2.1932, "step": 33320 }, { "epoch": 1.52, "learning_rate": 4.248707034646895e-05, "loss": 2.2909, "step": 33330 }, { "epoch": 1.52, "learning_rate": 4.248478191221567e-05, "loss": 2.2923, "step": 33340 }, { "epoch": 1.52, "learning_rate": 4.248249347796238e-05, "loss": 2.3214, "step": 33350 }, { "epoch": 1.52, "learning_rate": 4.2480205043709096e-05, "loss": 2.0169, "step": 33360 }, { "epoch": 1.52, "learning_rate": 4.247791660945582e-05, "loss": 2.2668, "step": 33370 }, { "epoch": 1.52, "learning_rate": 4.247562817520253e-05, "loss": 2.1797, "step": 33380 }, { "epoch": 1.52, "learning_rate": 4.2473339740949245e-05, "loss": 2.0257, "step": 33390 }, { "epoch": 1.53, "learning_rate": 4.247105130669596e-05, "loss": 2.1342, "step": 33400 }, { "epoch": 1.53, "learning_rate": 4.2468762872442674e-05, "loss": 2.3197, "step": 33410 }, { "epoch": 1.53, "learning_rate": 4.246647443818939e-05, "loss": 2.2724, "step": 33420 }, { "epoch": 1.53, "learning_rate": 4.246418600393611e-05, "loss": 2.2019, "step": 33430 }, { "epoch": 1.53, "learning_rate": 4.246189756968282e-05, "loss": 2.4028, "step": 33440 }, { "epoch": 1.53, "learning_rate": 4.245960913542954e-05, "loss": 2.1496, "step": 33450 }, { "epoch": 1.53, "learning_rate": 4.245732070117626e-05, "loss": 2.2774, "step": 33460 }, { "epoch": 1.53, "learning_rate": 4.245503226692297e-05, "loss": 2.2141, "step": 33470 }, { "epoch": 1.53, "learning_rate": 4.2452743832669686e-05, "loss": 2.1019, "step": 33480 }, { "epoch": 1.53, "learning_rate": 4.245045539841641e-05, "loss": 2.252, "step": 33490 }, { "epoch": 1.53, "learning_rate": 4.244816696416312e-05, "loss": 2.0488, "step": 33500 }, { "epoch": 1.53, "learning_rate": 4.2445878529909835e-05, "loss": 2.2232, "step": 33510 }, { "epoch": 1.53, "learning_rate": 4.2443590095656556e-05, "loss": 2.2495, "step": 33520 }, { "epoch": 1.53, "learning_rate": 4.244130166140327e-05, "loss": 2.3106, "step": 33530 }, { "epoch": 1.53, "learning_rate": 4.2439013227149985e-05, "loss": 2.0621, "step": 33540 }, { "epoch": 1.53, "learning_rate": 4.2436724792896705e-05, "loss": 2.0273, "step": 33550 }, { "epoch": 1.53, "learning_rate": 4.243443635864342e-05, "loss": 2.2839, "step": 33560 }, { "epoch": 1.53, "learning_rate": 4.2432147924390134e-05, "loss": 2.2526, "step": 33570 }, { "epoch": 1.53, "learning_rate": 4.2429859490136855e-05, "loss": 2.2216, "step": 33580 }, { "epoch": 1.53, "learning_rate": 4.242757105588356e-05, "loss": 2.1581, "step": 33590 }, { "epoch": 1.53, "learning_rate": 4.242528262163028e-05, "loss": 2.2139, "step": 33600 }, { "epoch": 1.53, "learning_rate": 4.2422994187377e-05, "loss": 2.2398, "step": 33610 }, { "epoch": 1.54, "learning_rate": 4.242070575312371e-05, "loss": 2.2713, "step": 33620 }, { "epoch": 1.54, "learning_rate": 4.241841731887043e-05, "loss": 2.1006, "step": 33630 }, { "epoch": 1.54, "learning_rate": 4.2416128884617146e-05, "loss": 2.0642, "step": 33640 }, { "epoch": 1.54, "learning_rate": 4.241384045036386e-05, "loss": 2.2479, "step": 33650 }, { "epoch": 1.54, "learning_rate": 4.241155201611058e-05, "loss": 2.2609, "step": 33660 }, { "epoch": 1.54, "learning_rate": 4.2409263581857295e-05, "loss": 2.214, "step": 33670 }, { "epoch": 1.54, "learning_rate": 4.240697514760401e-05, "loss": 2.2433, "step": 33680 }, { "epoch": 1.54, "learning_rate": 4.240468671335073e-05, "loss": 2.1583, "step": 33690 }, { "epoch": 1.54, "learning_rate": 4.2402398279097445e-05, "loss": 2.2093, "step": 33700 }, { "epoch": 1.54, "learning_rate": 4.240010984484416e-05, "loss": 2.1702, "step": 33710 }, { "epoch": 1.54, "learning_rate": 4.239782141059088e-05, "loss": 2.2934, "step": 33720 }, { "epoch": 1.54, "learning_rate": 4.2395532976337594e-05, "loss": 2.1997, "step": 33730 }, { "epoch": 1.54, "learning_rate": 4.239324454208431e-05, "loss": 2.094, "step": 33740 }, { "epoch": 1.54, "learning_rate": 4.239095610783103e-05, "loss": 2.1744, "step": 33750 }, { "epoch": 1.54, "learning_rate": 4.238866767357774e-05, "loss": 2.3094, "step": 33760 }, { "epoch": 1.54, "learning_rate": 4.238637923932446e-05, "loss": 2.232, "step": 33770 }, { "epoch": 1.54, "learning_rate": 4.238409080507118e-05, "loss": 2.1756, "step": 33780 }, { "epoch": 1.54, "learning_rate": 4.2381802370817885e-05, "loss": 2.0997, "step": 33790 }, { "epoch": 1.54, "learning_rate": 4.23795139365646e-05, "loss": 2.1897, "step": 33800 }, { "epoch": 1.54, "learning_rate": 4.237722550231132e-05, "loss": 2.285, "step": 33810 }, { "epoch": 1.54, "learning_rate": 4.2374937068058034e-05, "loss": 2.2082, "step": 33820 }, { "epoch": 1.54, "learning_rate": 4.237264863380475e-05, "loss": 2.1572, "step": 33830 }, { "epoch": 1.55, "learning_rate": 4.237036019955147e-05, "loss": 2.2119, "step": 33840 }, { "epoch": 1.55, "learning_rate": 4.2368071765298184e-05, "loss": 2.2487, "step": 33850 }, { "epoch": 1.55, "learning_rate": 4.23657833310449e-05, "loss": 2.1925, "step": 33860 }, { "epoch": 1.55, "learning_rate": 4.236349489679162e-05, "loss": 2.0484, "step": 33870 }, { "epoch": 1.55, "learning_rate": 4.236120646253833e-05, "loss": 2.2433, "step": 33880 }, { "epoch": 1.55, "learning_rate": 4.235891802828505e-05, "loss": 2.2933, "step": 33890 }, { "epoch": 1.55, "learning_rate": 4.235662959403177e-05, "loss": 2.0565, "step": 33900 }, { "epoch": 1.55, "learning_rate": 4.235434115977848e-05, "loss": 2.3206, "step": 33910 }, { "epoch": 1.55, "learning_rate": 4.2352052725525196e-05, "loss": 2.2032, "step": 33920 }, { "epoch": 1.55, "learning_rate": 4.234976429127192e-05, "loss": 2.3766, "step": 33930 }, { "epoch": 1.55, "learning_rate": 4.234747585701863e-05, "loss": 2.2283, "step": 33940 }, { "epoch": 1.55, "learning_rate": 4.2345187422765345e-05, "loss": 2.2293, "step": 33950 }, { "epoch": 1.55, "learning_rate": 4.2342898988512066e-05, "loss": 2.1158, "step": 33960 }, { "epoch": 1.55, "learning_rate": 4.234061055425878e-05, "loss": 2.2487, "step": 33970 }, { "epoch": 1.55, "learning_rate": 4.2338322120005494e-05, "loss": 2.266, "step": 33980 }, { "epoch": 1.55, "learning_rate": 4.233603368575221e-05, "loss": 2.2612, "step": 33990 }, { "epoch": 1.55, "learning_rate": 4.233374525149892e-05, "loss": 2.2426, "step": 34000 }, { "epoch": 1.55, "learning_rate": 4.2331456817245644e-05, "loss": 2.1276, "step": 34010 }, { "epoch": 1.55, "learning_rate": 4.232916838299236e-05, "loss": 2.124, "step": 34020 }, { "epoch": 1.55, "learning_rate": 4.232687994873907e-05, "loss": 2.159, "step": 34030 }, { "epoch": 1.55, "learning_rate": 4.232459151448579e-05, "loss": 2.1321, "step": 34040 }, { "epoch": 1.55, "learning_rate": 4.232230308023251e-05, "loss": 2.2457, "step": 34050 }, { "epoch": 1.56, "learning_rate": 4.232001464597922e-05, "loss": 2.3734, "step": 34060 }, { "epoch": 1.56, "learning_rate": 4.231772621172594e-05, "loss": 2.2072, "step": 34070 }, { "epoch": 1.56, "learning_rate": 4.2315437777472656e-05, "loss": 2.2281, "step": 34080 }, { "epoch": 1.56, "learning_rate": 4.231314934321937e-05, "loss": 2.2532, "step": 34090 }, { "epoch": 1.56, "learning_rate": 4.231086090896609e-05, "loss": 2.2016, "step": 34100 }, { "epoch": 1.56, "learning_rate": 4.2308572474712805e-05, "loss": 2.2411, "step": 34110 }, { "epoch": 1.56, "learning_rate": 4.230628404045952e-05, "loss": 2.2548, "step": 34120 }, { "epoch": 1.56, "learning_rate": 4.230399560620624e-05, "loss": 2.1081, "step": 34130 }, { "epoch": 1.56, "learning_rate": 4.2301707171952955e-05, "loss": 2.1899, "step": 34140 }, { "epoch": 1.56, "learning_rate": 4.229941873769967e-05, "loss": 2.2682, "step": 34150 }, { "epoch": 1.56, "learning_rate": 4.229713030344639e-05, "loss": 2.0997, "step": 34160 }, { "epoch": 1.56, "learning_rate": 4.2294841869193104e-05, "loss": 2.454, "step": 34170 }, { "epoch": 1.56, "learning_rate": 4.229255343493982e-05, "loss": 2.2565, "step": 34180 }, { "epoch": 1.56, "learning_rate": 4.229026500068653e-05, "loss": 2.1417, "step": 34190 }, { "epoch": 1.56, "learning_rate": 4.2287976566433246e-05, "loss": 2.1992, "step": 34200 }, { "epoch": 1.56, "learning_rate": 4.228568813217996e-05, "loss": 2.2322, "step": 34210 }, { "epoch": 1.56, "learning_rate": 4.228339969792668e-05, "loss": 2.1396, "step": 34220 }, { "epoch": 1.56, "learning_rate": 4.2281111263673395e-05, "loss": 2.2887, "step": 34230 }, { "epoch": 1.56, "learning_rate": 4.227882282942011e-05, "loss": 2.2736, "step": 34240 }, { "epoch": 1.56, "learning_rate": 4.227653439516683e-05, "loss": 2.2381, "step": 34250 }, { "epoch": 1.56, "learning_rate": 4.2274245960913544e-05, "loss": 2.2593, "step": 34260 }, { "epoch": 1.56, "learning_rate": 4.227195752666026e-05, "loss": 2.284, "step": 34270 }, { "epoch": 1.57, "learning_rate": 4.226966909240698e-05, "loss": 2.2125, "step": 34280 }, { "epoch": 1.57, "learning_rate": 4.2267380658153694e-05, "loss": 2.1411, "step": 34290 }, { "epoch": 1.57, "learning_rate": 4.226509222390041e-05, "loss": 2.1484, "step": 34300 }, { "epoch": 1.57, "learning_rate": 4.226280378964713e-05, "loss": 2.2067, "step": 34310 }, { "epoch": 1.57, "learning_rate": 4.226051535539384e-05, "loss": 2.1431, "step": 34320 }, { "epoch": 1.57, "learning_rate": 4.225822692114056e-05, "loss": 2.4763, "step": 34330 }, { "epoch": 1.57, "learning_rate": 4.225593848688728e-05, "loss": 2.2519, "step": 34340 }, { "epoch": 1.57, "learning_rate": 4.225365005263399e-05, "loss": 2.1382, "step": 34350 }, { "epoch": 1.57, "learning_rate": 4.2251361618380706e-05, "loss": 2.167, "step": 34360 }, { "epoch": 1.57, "learning_rate": 4.224907318412743e-05, "loss": 2.1383, "step": 34370 }, { "epoch": 1.57, "learning_rate": 4.2246784749874134e-05, "loss": 2.1782, "step": 34380 }, { "epoch": 1.57, "learning_rate": 4.224449631562085e-05, "loss": 2.371, "step": 34390 }, { "epoch": 1.57, "learning_rate": 4.224220788136757e-05, "loss": 2.2796, "step": 34400 }, { "epoch": 1.57, "learning_rate": 4.2239919447114284e-05, "loss": 2.0964, "step": 34410 }, { "epoch": 1.57, "learning_rate": 4.2237631012861e-05, "loss": 2.1689, "step": 34420 }, { "epoch": 1.57, "learning_rate": 4.223534257860772e-05, "loss": 2.1862, "step": 34430 }, { "epoch": 1.57, "learning_rate": 4.223305414435443e-05, "loss": 2.2037, "step": 34440 }, { "epoch": 1.57, "learning_rate": 4.223076571010115e-05, "loss": 2.0545, "step": 34450 }, { "epoch": 1.57, "learning_rate": 4.222847727584787e-05, "loss": 2.212, "step": 34460 }, { "epoch": 1.57, "learning_rate": 4.222618884159458e-05, "loss": 2.2131, "step": 34470 }, { "epoch": 1.57, "learning_rate": 4.2223900407341296e-05, "loss": 2.2166, "step": 34480 }, { "epoch": 1.57, "learning_rate": 4.222161197308802e-05, "loss": 2.2752, "step": 34490 }, { "epoch": 1.58, "learning_rate": 4.221932353883473e-05, "loss": 2.1559, "step": 34500 }, { "epoch": 1.58, "learning_rate": 4.2217035104581445e-05, "loss": 2.1911, "step": 34510 }, { "epoch": 1.58, "learning_rate": 4.2214746670328166e-05, "loss": 2.3834, "step": 34520 }, { "epoch": 1.58, "learning_rate": 4.221245823607488e-05, "loss": 2.2949, "step": 34530 }, { "epoch": 1.58, "learning_rate": 4.2210169801821594e-05, "loss": 2.1558, "step": 34540 }, { "epoch": 1.58, "learning_rate": 4.2207881367568315e-05, "loss": 2.1988, "step": 34550 }, { "epoch": 1.58, "learning_rate": 4.220559293331503e-05, "loss": 2.176, "step": 34560 }, { "epoch": 1.58, "learning_rate": 4.2203304499061744e-05, "loss": 2.0811, "step": 34570 }, { "epoch": 1.58, "learning_rate": 4.220101606480846e-05, "loss": 2.1244, "step": 34580 }, { "epoch": 1.58, "learning_rate": 4.219872763055517e-05, "loss": 2.2562, "step": 34590 }, { "epoch": 1.58, "learning_rate": 4.219643919630189e-05, "loss": 2.1444, "step": 34600 }, { "epoch": 1.58, "learning_rate": 4.219415076204861e-05, "loss": 2.379, "step": 34610 }, { "epoch": 1.58, "learning_rate": 4.219186232779532e-05, "loss": 2.1902, "step": 34620 }, { "epoch": 1.58, "learning_rate": 4.218957389354204e-05, "loss": 2.1007, "step": 34630 }, { "epoch": 1.58, "learning_rate": 4.2187285459288756e-05, "loss": 2.1554, "step": 34640 }, { "epoch": 1.58, "learning_rate": 4.218499702503547e-05, "loss": 2.3309, "step": 34650 }, { "epoch": 1.58, "learning_rate": 4.218270859078219e-05, "loss": 2.084, "step": 34660 }, { "epoch": 1.58, "learning_rate": 4.2180420156528905e-05, "loss": 2.2329, "step": 34670 }, { "epoch": 1.58, "learning_rate": 4.217813172227562e-05, "loss": 2.2609, "step": 34680 }, { "epoch": 1.58, "learning_rate": 4.217584328802234e-05, "loss": 2.3442, "step": 34690 }, { "epoch": 1.58, "learning_rate": 4.2173554853769054e-05, "loss": 2.0973, "step": 34700 }, { "epoch": 1.58, "learning_rate": 4.217126641951577e-05, "loss": 2.2005, "step": 34710 }, { "epoch": 1.59, "learning_rate": 4.216897798526249e-05, "loss": 2.0873, "step": 34720 }, { "epoch": 1.59, "learning_rate": 4.2166689551009204e-05, "loss": 2.1809, "step": 34730 }, { "epoch": 1.59, "learning_rate": 4.216440111675592e-05, "loss": 2.1069, "step": 34740 }, { "epoch": 1.59, "learning_rate": 4.216211268250264e-05, "loss": 2.3623, "step": 34750 }, { "epoch": 1.59, "learning_rate": 4.215982424824935e-05, "loss": 2.2243, "step": 34760 }, { "epoch": 1.59, "learning_rate": 4.215753581399607e-05, "loss": 2.217, "step": 34770 }, { "epoch": 1.59, "learning_rate": 4.215524737974278e-05, "loss": 2.0778, "step": 34780 }, { "epoch": 1.59, "learning_rate": 4.2152958945489495e-05, "loss": 2.2595, "step": 34790 }, { "epoch": 1.59, "learning_rate": 4.215067051123621e-05, "loss": 1.9682, "step": 34800 }, { "epoch": 1.59, "learning_rate": 4.214838207698293e-05, "loss": 2.1947, "step": 34810 }, { "epoch": 1.59, "learning_rate": 4.2146093642729644e-05, "loss": 2.3725, "step": 34820 }, { "epoch": 1.59, "learning_rate": 4.214380520847636e-05, "loss": 2.4304, "step": 34830 }, { "epoch": 1.59, "learning_rate": 4.214151677422308e-05, "loss": 2.2787, "step": 34840 }, { "epoch": 1.59, "learning_rate": 4.2139228339969794e-05, "loss": 2.1856, "step": 34850 }, { "epoch": 1.59, "learning_rate": 4.213693990571651e-05, "loss": 2.2886, "step": 34860 }, { "epoch": 1.59, "learning_rate": 4.213465147146323e-05, "loss": 2.3824, "step": 34870 }, { "epoch": 1.59, "learning_rate": 4.213236303720994e-05, "loss": 2.0741, "step": 34880 }, { "epoch": 1.59, "learning_rate": 4.213007460295666e-05, "loss": 2.1743, "step": 34890 }, { "epoch": 1.59, "learning_rate": 4.212778616870338e-05, "loss": 2.0799, "step": 34900 }, { "epoch": 1.59, "learning_rate": 4.212549773445009e-05, "loss": 2.2189, "step": 34910 }, { "epoch": 1.59, "learning_rate": 4.2123209300196806e-05, "loss": 2.2201, "step": 34920 }, { "epoch": 1.59, "learning_rate": 4.212092086594353e-05, "loss": 2.0891, "step": 34930 }, { "epoch": 1.6, "learning_rate": 4.211863243169024e-05, "loss": 2.1851, "step": 34940 }, { "epoch": 1.6, "learning_rate": 4.2116343997436955e-05, "loss": 2.2383, "step": 34950 }, { "epoch": 1.6, "learning_rate": 4.2114055563183676e-05, "loss": 2.0705, "step": 34960 }, { "epoch": 1.6, "learning_rate": 4.211176712893039e-05, "loss": 2.1513, "step": 34970 }, { "epoch": 1.6, "learning_rate": 4.2109478694677104e-05, "loss": 2.1618, "step": 34980 }, { "epoch": 1.6, "learning_rate": 4.210719026042382e-05, "loss": 2.1557, "step": 34990 }, { "epoch": 1.6, "learning_rate": 4.210490182617053e-05, "loss": 2.2126, "step": 35000 }, { "epoch": 1.6, "learning_rate": 4.2102613391917254e-05, "loss": 2.2068, "step": 35010 }, { "epoch": 1.6, "learning_rate": 4.210032495766397e-05, "loss": 2.2336, "step": 35020 }, { "epoch": 1.6, "learning_rate": 4.209803652341068e-05, "loss": 2.2016, "step": 35030 }, { "epoch": 1.6, "learning_rate": 4.20957480891574e-05, "loss": 2.2519, "step": 35040 }, { "epoch": 1.6, "learning_rate": 4.209345965490412e-05, "loss": 2.0474, "step": 35050 }, { "epoch": 1.6, "learning_rate": 4.209117122065083e-05, "loss": 2.171, "step": 35060 }, { "epoch": 1.6, "learning_rate": 4.208888278639755e-05, "loss": 2.3663, "step": 35070 }, { "epoch": 1.6, "learning_rate": 4.2086594352144266e-05, "loss": 2.3593, "step": 35080 }, { "epoch": 1.6, "learning_rate": 4.208430591789098e-05, "loss": 2.0857, "step": 35090 }, { "epoch": 1.6, "learning_rate": 4.20820174836377e-05, "loss": 2.2116, "step": 35100 }, { "epoch": 1.6, "learning_rate": 4.2079729049384415e-05, "loss": 2.2121, "step": 35110 }, { "epoch": 1.6, "learning_rate": 4.207744061513113e-05, "loss": 2.3355, "step": 35120 }, { "epoch": 1.6, "learning_rate": 4.207515218087785e-05, "loss": 2.2311, "step": 35130 }, { "epoch": 1.6, "learning_rate": 4.2072863746624564e-05, "loss": 2.1859, "step": 35140 }, { "epoch": 1.61, "learning_rate": 4.207057531237128e-05, "loss": 2.2529, "step": 35150 }, { "epoch": 1.61, "learning_rate": 4.2068286878118e-05, "loss": 2.3917, "step": 35160 }, { "epoch": 1.61, "learning_rate": 4.206599844386471e-05, "loss": 2.241, "step": 35170 }, { "epoch": 1.61, "learning_rate": 4.206371000961142e-05, "loss": 2.1115, "step": 35180 }, { "epoch": 1.61, "learning_rate": 4.206142157535814e-05, "loss": 2.1953, "step": 35190 }, { "epoch": 1.61, "learning_rate": 4.2059133141104856e-05, "loss": 2.2976, "step": 35200 }, { "epoch": 1.61, "learning_rate": 4.205684470685157e-05, "loss": 2.0723, "step": 35210 }, { "epoch": 1.61, "learning_rate": 4.205455627259829e-05, "loss": 2.2534, "step": 35220 }, { "epoch": 1.61, "learning_rate": 4.2052267838345005e-05, "loss": 2.1852, "step": 35230 }, { "epoch": 1.61, "learning_rate": 4.204997940409172e-05, "loss": 2.1851, "step": 35240 }, { "epoch": 1.61, "learning_rate": 4.204769096983844e-05, "loss": 2.2331, "step": 35250 }, { "epoch": 1.61, "learning_rate": 4.2045402535585154e-05, "loss": 2.1456, "step": 35260 }, { "epoch": 1.61, "learning_rate": 4.204311410133187e-05, "loss": 2.2374, "step": 35270 }, { "epoch": 1.61, "learning_rate": 4.204082566707859e-05, "loss": 2.3179, "step": 35280 }, { "epoch": 1.61, "learning_rate": 4.2038537232825303e-05, "loss": 2.1439, "step": 35290 }, { "epoch": 1.61, "learning_rate": 4.203624879857202e-05, "loss": 2.3669, "step": 35300 }, { "epoch": 1.61, "learning_rate": 4.203396036431874e-05, "loss": 2.2819, "step": 35310 }, { "epoch": 1.61, "learning_rate": 4.203167193006545e-05, "loss": 2.1746, "step": 35320 }, { "epoch": 1.61, "learning_rate": 4.202938349581217e-05, "loss": 2.2366, "step": 35330 }, { "epoch": 1.61, "learning_rate": 4.202709506155889e-05, "loss": 2.2126, "step": 35340 }, { "epoch": 1.61, "learning_rate": 4.20248066273056e-05, "loss": 2.2901, "step": 35350 }, { "epoch": 1.61, "learning_rate": 4.2022518193052316e-05, "loss": 2.0831, "step": 35360 }, { "epoch": 1.62, "learning_rate": 4.202022975879903e-05, "loss": 2.0942, "step": 35370 }, { "epoch": 1.62, "learning_rate": 4.2017941324545744e-05, "loss": 2.2299, "step": 35380 }, { "epoch": 1.62, "learning_rate": 4.2015652890292465e-05, "loss": 2.1724, "step": 35390 }, { "epoch": 1.62, "learning_rate": 4.201336445603918e-05, "loss": 2.252, "step": 35400 }, { "epoch": 1.62, "learning_rate": 4.2011076021785893e-05, "loss": 2.1923, "step": 35410 }, { "epoch": 1.62, "learning_rate": 4.200878758753261e-05, "loss": 2.1875, "step": 35420 }, { "epoch": 1.62, "learning_rate": 4.200649915327933e-05, "loss": 2.2891, "step": 35430 }, { "epoch": 1.62, "learning_rate": 4.200421071902604e-05, "loss": 2.1241, "step": 35440 }, { "epoch": 1.62, "learning_rate": 4.200192228477276e-05, "loss": 2.1854, "step": 35450 }, { "epoch": 1.62, "learning_rate": 4.199963385051948e-05, "loss": 2.2258, "step": 35460 }, { "epoch": 1.62, "learning_rate": 4.199734541626619e-05, "loss": 2.3075, "step": 35470 }, { "epoch": 1.62, "learning_rate": 4.1995056982012906e-05, "loss": 2.2127, "step": 35480 }, { "epoch": 1.62, "learning_rate": 4.199276854775963e-05, "loss": 2.261, "step": 35490 }, { "epoch": 1.62, "learning_rate": 4.199048011350634e-05, "loss": 2.1515, "step": 35500 }, { "epoch": 1.62, "learning_rate": 4.1988191679253055e-05, "loss": 2.0054, "step": 35510 }, { "epoch": 1.62, "learning_rate": 4.1985903244999776e-05, "loss": 2.1728, "step": 35520 }, { "epoch": 1.62, "learning_rate": 4.198361481074649e-05, "loss": 2.3121, "step": 35530 }, { "epoch": 1.62, "learning_rate": 4.1981326376493204e-05, "loss": 2.4936, "step": 35540 }, { "epoch": 1.62, "learning_rate": 4.1979037942239925e-05, "loss": 2.1637, "step": 35550 }, { "epoch": 1.62, "learning_rate": 4.197674950798664e-05, "loss": 2.184, "step": 35560 }, { "epoch": 1.62, "learning_rate": 4.1974461073733353e-05, "loss": 2.2197, "step": 35570 }, { "epoch": 1.62, "learning_rate": 4.197217263948007e-05, "loss": 2.2452, "step": 35580 }, { "epoch": 1.63, "learning_rate": 4.196988420522678e-05, "loss": 2.2798, "step": 35590 }, { "epoch": 1.63, "learning_rate": 4.19675957709735e-05, "loss": 2.2312, "step": 35600 }, { "epoch": 1.63, "learning_rate": 4.196530733672022e-05, "loss": 2.0036, "step": 35610 }, { "epoch": 1.63, "learning_rate": 4.196301890246693e-05, "loss": 2.4411, "step": 35620 }, { "epoch": 1.63, "learning_rate": 4.196073046821365e-05, "loss": 2.1033, "step": 35630 }, { "epoch": 1.63, "learning_rate": 4.1958442033960366e-05, "loss": 2.1701, "step": 35640 }, { "epoch": 1.63, "learning_rate": 4.195615359970708e-05, "loss": 2.2869, "step": 35650 }, { "epoch": 1.63, "learning_rate": 4.19538651654538e-05, "loss": 2.2763, "step": 35660 }, { "epoch": 1.63, "learning_rate": 4.1951576731200515e-05, "loss": 2.1927, "step": 35670 }, { "epoch": 1.63, "learning_rate": 4.194928829694723e-05, "loss": 2.2236, "step": 35680 }, { "epoch": 1.63, "learning_rate": 4.194699986269395e-05, "loss": 2.2426, "step": 35690 }, { "epoch": 1.63, "learning_rate": 4.1944711428440664e-05, "loss": 2.2397, "step": 35700 }, { "epoch": 1.63, "learning_rate": 4.194242299418738e-05, "loss": 2.2929, "step": 35710 }, { "epoch": 1.63, "learning_rate": 4.19401345599341e-05, "loss": 2.1915, "step": 35720 }, { "epoch": 1.63, "learning_rate": 4.1937846125680813e-05, "loss": 2.2102, "step": 35730 }, { "epoch": 1.63, "learning_rate": 4.193555769142753e-05, "loss": 2.1248, "step": 35740 }, { "epoch": 1.63, "learning_rate": 4.193326925717425e-05, "loss": 2.1097, "step": 35750 }, { "epoch": 1.63, "learning_rate": 4.193098082292096e-05, "loss": 2.1823, "step": 35760 }, { "epoch": 1.63, "learning_rate": 4.192869238866767e-05, "loss": 2.2032, "step": 35770 }, { "epoch": 1.63, "learning_rate": 4.192640395441439e-05, "loss": 2.1623, "step": 35780 }, { "epoch": 1.63, "learning_rate": 4.1924115520161105e-05, "loss": 2.3874, "step": 35790 }, { "epoch": 1.63, "learning_rate": 4.192182708590782e-05, "loss": 2.1291, "step": 35800 }, { "epoch": 1.64, "learning_rate": 4.191953865165454e-05, "loss": 2.195, "step": 35810 }, { "epoch": 1.64, "learning_rate": 4.1917250217401254e-05, "loss": 2.0351, "step": 35820 }, { "epoch": 1.64, "learning_rate": 4.191496178314797e-05, "loss": 2.0678, "step": 35830 }, { "epoch": 1.64, "learning_rate": 4.191267334889469e-05, "loss": 2.1443, "step": 35840 }, { "epoch": 1.64, "learning_rate": 4.19103849146414e-05, "loss": 2.1792, "step": 35850 }, { "epoch": 1.64, "learning_rate": 4.190809648038812e-05, "loss": 2.1718, "step": 35860 }, { "epoch": 1.64, "learning_rate": 4.190580804613484e-05, "loss": 2.0006, "step": 35870 }, { "epoch": 1.64, "learning_rate": 4.190351961188155e-05, "loss": 2.1257, "step": 35880 }, { "epoch": 1.64, "learning_rate": 4.190123117762827e-05, "loss": 2.0348, "step": 35890 }, { "epoch": 1.64, "learning_rate": 4.189894274337499e-05, "loss": 2.2895, "step": 35900 }, { "epoch": 1.64, "learning_rate": 4.18966543091217e-05, "loss": 2.0166, "step": 35910 }, { "epoch": 1.64, "learning_rate": 4.1894365874868416e-05, "loss": 2.1938, "step": 35920 }, { "epoch": 1.64, "learning_rate": 4.189207744061514e-05, "loss": 2.2063, "step": 35930 }, { "epoch": 1.64, "learning_rate": 4.188978900636185e-05, "loss": 2.2252, "step": 35940 }, { "epoch": 1.64, "learning_rate": 4.1887500572108565e-05, "loss": 2.1081, "step": 35950 }, { "epoch": 1.64, "learning_rate": 4.1885212137855286e-05, "loss": 2.2486, "step": 35960 }, { "epoch": 1.64, "learning_rate": 4.188292370360199e-05, "loss": 2.3068, "step": 35970 }, { "epoch": 1.64, "learning_rate": 4.1880635269348714e-05, "loss": 2.1951, "step": 35980 }, { "epoch": 1.64, "learning_rate": 4.187834683509543e-05, "loss": 2.3024, "step": 35990 }, { "epoch": 1.64, "learning_rate": 4.187605840084214e-05, "loss": 2.1668, "step": 36000 }, { "epoch": 1.64, "learning_rate": 4.1873769966588863e-05, "loss": 2.2558, "step": 36010 }, { "epoch": 1.64, "learning_rate": 4.187148153233558e-05, "loss": 2.2067, "step": 36020 }, { "epoch": 1.65, "learning_rate": 4.186919309808229e-05, "loss": 2.2907, "step": 36030 }, { "epoch": 1.65, "learning_rate": 4.186690466382901e-05, "loss": 2.106, "step": 36040 }, { "epoch": 1.65, "learning_rate": 4.186461622957573e-05, "loss": 2.243, "step": 36050 }, { "epoch": 1.65, "learning_rate": 4.186232779532244e-05, "loss": 2.1728, "step": 36060 }, { "epoch": 1.65, "learning_rate": 4.186003936106916e-05, "loss": 2.2161, "step": 36070 }, { "epoch": 1.65, "learning_rate": 4.1857750926815876e-05, "loss": 2.2722, "step": 36080 }, { "epoch": 1.65, "learning_rate": 4.185546249256259e-05, "loss": 2.2647, "step": 36090 }, { "epoch": 1.65, "learning_rate": 4.185317405830931e-05, "loss": 2.3383, "step": 36100 }, { "epoch": 1.65, "learning_rate": 4.1850885624056025e-05, "loss": 2.3532, "step": 36110 }, { "epoch": 1.65, "learning_rate": 4.184859718980274e-05, "loss": 2.2017, "step": 36120 }, { "epoch": 1.65, "learning_rate": 4.184630875554946e-05, "loss": 2.1743, "step": 36130 }, { "epoch": 1.65, "learning_rate": 4.1844020321296174e-05, "loss": 2.1506, "step": 36140 }, { "epoch": 1.65, "learning_rate": 4.184173188704289e-05, "loss": 2.1734, "step": 36150 }, { "epoch": 1.65, "learning_rate": 4.18394434527896e-05, "loss": 2.2374, "step": 36160 }, { "epoch": 1.65, "learning_rate": 4.183715501853632e-05, "loss": 2.1629, "step": 36170 }, { "epoch": 1.65, "learning_rate": 4.183486658428303e-05, "loss": 2.1897, "step": 36180 }, { "epoch": 1.65, "learning_rate": 4.183257815002975e-05, "loss": 2.1835, "step": 36190 }, { "epoch": 1.65, "learning_rate": 4.1830289715776466e-05, "loss": 2.1762, "step": 36200 }, { "epoch": 1.65, "learning_rate": 4.182800128152318e-05, "loss": 2.0737, "step": 36210 }, { "epoch": 1.65, "learning_rate": 4.18257128472699e-05, "loss": 2.1702, "step": 36220 }, { "epoch": 1.65, "learning_rate": 4.1823424413016615e-05, "loss": 2.1275, "step": 36230 }, { "epoch": 1.65, "learning_rate": 4.182113597876333e-05, "loss": 2.1688, "step": 36240 }, { "epoch": 1.66, "learning_rate": 4.181884754451005e-05, "loss": 2.1524, "step": 36250 }, { "epoch": 1.66, "learning_rate": 4.1816559110256764e-05, "loss": 2.1609, "step": 36260 }, { "epoch": 1.66, "learning_rate": 4.181427067600348e-05, "loss": 2.26, "step": 36270 }, { "epoch": 1.66, "learning_rate": 4.18119822417502e-05, "loss": 2.1251, "step": 36280 }, { "epoch": 1.66, "learning_rate": 4.180969380749691e-05, "loss": 2.3092, "step": 36290 }, { "epoch": 1.66, "learning_rate": 4.180740537324363e-05, "loss": 2.1452, "step": 36300 }, { "epoch": 1.66, "learning_rate": 4.180511693899035e-05, "loss": 2.2021, "step": 36310 }, { "epoch": 1.66, "learning_rate": 4.180282850473706e-05, "loss": 2.1021, "step": 36320 }, { "epoch": 1.66, "learning_rate": 4.180054007048378e-05, "loss": 2.2232, "step": 36330 }, { "epoch": 1.66, "learning_rate": 4.17982516362305e-05, "loss": 2.3769, "step": 36340 }, { "epoch": 1.66, "learning_rate": 4.179596320197721e-05, "loss": 2.1612, "step": 36350 }, { "epoch": 1.66, "learning_rate": 4.1793674767723926e-05, "loss": 2.1227, "step": 36360 }, { "epoch": 1.66, "learning_rate": 4.179138633347064e-05, "loss": 2.1427, "step": 36370 }, { "epoch": 1.66, "learning_rate": 4.1789097899217354e-05, "loss": 2.2312, "step": 36380 }, { "epoch": 1.66, "learning_rate": 4.1786809464964075e-05, "loss": 2.2784, "step": 36390 }, { "epoch": 1.66, "learning_rate": 4.178452103071079e-05, "loss": 2.128, "step": 36400 }, { "epoch": 1.66, "learning_rate": 4.17822325964575e-05, "loss": 2.2183, "step": 36410 }, { "epoch": 1.66, "learning_rate": 4.1779944162204224e-05, "loss": 2.2895, "step": 36420 }, { "epoch": 1.66, "learning_rate": 4.177765572795094e-05, "loss": 2.2259, "step": 36430 }, { "epoch": 1.66, "learning_rate": 4.177536729369765e-05, "loss": 2.2831, "step": 36440 }, { "epoch": 1.66, "learning_rate": 4.177307885944437e-05, "loss": 2.275, "step": 36450 }, { "epoch": 1.66, "learning_rate": 4.177079042519109e-05, "loss": 2.1505, "step": 36460 }, { "epoch": 1.67, "learning_rate": 4.17685019909378e-05, "loss": 2.313, "step": 36470 }, { "epoch": 1.67, "learning_rate": 4.176621355668452e-05, "loss": 2.2903, "step": 36480 }, { "epoch": 1.67, "learning_rate": 4.176392512243124e-05, "loss": 2.1324, "step": 36490 }, { "epoch": 1.67, "learning_rate": 4.176163668817795e-05, "loss": 2.336, "step": 36500 }, { "epoch": 1.67, "learning_rate": 4.1759348253924665e-05, "loss": 2.2516, "step": 36510 }, { "epoch": 1.67, "learning_rate": 4.1757059819671386e-05, "loss": 2.2412, "step": 36520 }, { "epoch": 1.67, "learning_rate": 4.17547713854181e-05, "loss": 2.2775, "step": 36530 }, { "epoch": 1.67, "learning_rate": 4.1752482951164814e-05, "loss": 2.2012, "step": 36540 }, { "epoch": 1.67, "learning_rate": 4.1750194516911535e-05, "loss": 2.2878, "step": 36550 }, { "epoch": 1.67, "learning_rate": 4.174790608265824e-05, "loss": 2.2492, "step": 36560 }, { "epoch": 1.67, "learning_rate": 4.174561764840496e-05, "loss": 2.0116, "step": 36570 }, { "epoch": 1.67, "learning_rate": 4.174332921415168e-05, "loss": 2.3563, "step": 36580 }, { "epoch": 1.67, "learning_rate": 4.174104077989839e-05, "loss": 2.089, "step": 36590 }, { "epoch": 1.67, "learning_rate": 4.173875234564511e-05, "loss": 2.2298, "step": 36600 }, { "epoch": 1.67, "learning_rate": 4.1736463911391827e-05, "loss": 2.2384, "step": 36610 }, { "epoch": 1.67, "learning_rate": 4.173417547713854e-05, "loss": 2.1789, "step": 36620 }, { "epoch": 1.67, "learning_rate": 4.173188704288526e-05, "loss": 2.1691, "step": 36630 }, { "epoch": 1.67, "learning_rate": 4.1729598608631976e-05, "loss": 2.1376, "step": 36640 }, { "epoch": 1.67, "learning_rate": 4.172731017437869e-05, "loss": 2.2581, "step": 36650 }, { "epoch": 1.67, "learning_rate": 4.172502174012541e-05, "loss": 1.9213, "step": 36660 }, { "epoch": 1.67, "learning_rate": 4.1722733305872125e-05, "loss": 2.1391, "step": 36670 }, { "epoch": 1.67, "learning_rate": 4.172044487161884e-05, "loss": 2.1524, "step": 36680 }, { "epoch": 1.68, "learning_rate": 4.171815643736556e-05, "loss": 2.1828, "step": 36690 }, { "epoch": 1.68, "learning_rate": 4.1715868003112274e-05, "loss": 2.3586, "step": 36700 }, { "epoch": 1.68, "learning_rate": 4.171357956885899e-05, "loss": 2.2254, "step": 36710 }, { "epoch": 1.68, "learning_rate": 4.171129113460571e-05, "loss": 2.2589, "step": 36720 }, { "epoch": 1.68, "learning_rate": 4.170900270035242e-05, "loss": 2.155, "step": 36730 }, { "epoch": 1.68, "learning_rate": 4.170671426609914e-05, "loss": 2.2564, "step": 36740 }, { "epoch": 1.68, "learning_rate": 4.170442583184586e-05, "loss": 2.2918, "step": 36750 }, { "epoch": 1.68, "learning_rate": 4.1702137397592566e-05, "loss": 2.1779, "step": 36760 }, { "epoch": 1.68, "learning_rate": 4.169984896333928e-05, "loss": 2.1449, "step": 36770 }, { "epoch": 1.68, "learning_rate": 4.1697560529086e-05, "loss": 2.1618, "step": 36780 }, { "epoch": 1.68, "learning_rate": 4.1695272094832715e-05, "loss": 2.0229, "step": 36790 }, { "epoch": 1.68, "learning_rate": 4.169298366057943e-05, "loss": 2.0338, "step": 36800 }, { "epoch": 1.68, "learning_rate": 4.169069522632615e-05, "loss": 2.1515, "step": 36810 }, { "epoch": 1.68, "learning_rate": 4.1688406792072864e-05, "loss": 2.1868, "step": 36820 }, { "epoch": 1.68, "learning_rate": 4.168611835781958e-05, "loss": 2.1733, "step": 36830 }, { "epoch": 1.68, "learning_rate": 4.16838299235663e-05, "loss": 2.2094, "step": 36840 }, { "epoch": 1.68, "learning_rate": 4.168154148931301e-05, "loss": 2.2269, "step": 36850 }, { "epoch": 1.68, "learning_rate": 4.167925305505973e-05, "loss": 2.3105, "step": 36860 }, { "epoch": 1.68, "learning_rate": 4.167696462080645e-05, "loss": 2.2296, "step": 36870 }, { "epoch": 1.68, "learning_rate": 4.167467618655316e-05, "loss": 2.3046, "step": 36880 }, { "epoch": 1.68, "learning_rate": 4.1672387752299877e-05, "loss": 2.2956, "step": 36890 }, { "epoch": 1.68, "learning_rate": 4.16700993180466e-05, "loss": 2.1695, "step": 36900 }, { "epoch": 1.69, "learning_rate": 4.166781088379331e-05, "loss": 2.3136, "step": 36910 }, { "epoch": 1.69, "learning_rate": 4.1665522449540026e-05, "loss": 2.2184, "step": 36920 }, { "epoch": 1.69, "learning_rate": 4.166323401528675e-05, "loss": 2.2107, "step": 36930 }, { "epoch": 1.69, "learning_rate": 4.166094558103346e-05, "loss": 2.1386, "step": 36940 }, { "epoch": 1.69, "learning_rate": 4.1658657146780175e-05, "loss": 2.1379, "step": 36950 }, { "epoch": 1.69, "learning_rate": 4.165636871252689e-05, "loss": 2.2487, "step": 36960 }, { "epoch": 1.69, "learning_rate": 4.16540802782736e-05, "loss": 2.2311, "step": 36970 }, { "epoch": 1.69, "learning_rate": 4.1651791844020324e-05, "loss": 2.1947, "step": 36980 }, { "epoch": 1.69, "learning_rate": 4.164950340976704e-05, "loss": 2.267, "step": 36990 }, { "epoch": 1.69, "learning_rate": 4.164721497551375e-05, "loss": 2.2799, "step": 37000 }, { "epoch": 1.69, "learning_rate": 4.164492654126047e-05, "loss": 2.2872, "step": 37010 }, { "epoch": 1.69, "learning_rate": 4.164263810700719e-05, "loss": 2.2747, "step": 37020 }, { "epoch": 1.69, "learning_rate": 4.16403496727539e-05, "loss": 2.1408, "step": 37030 }, { "epoch": 1.69, "learning_rate": 4.163806123850062e-05, "loss": 2.0996, "step": 37040 }, { "epoch": 1.69, "learning_rate": 4.1635772804247337e-05, "loss": 2.1772, "step": 37050 }, { "epoch": 1.69, "learning_rate": 4.163348436999405e-05, "loss": 2.132, "step": 37060 }, { "epoch": 1.69, "learning_rate": 4.163119593574077e-05, "loss": 2.1748, "step": 37070 }, { "epoch": 1.69, "learning_rate": 4.1628907501487486e-05, "loss": 2.2017, "step": 37080 }, { "epoch": 1.69, "learning_rate": 4.16266190672342e-05, "loss": 2.179, "step": 37090 }, { "epoch": 1.69, "learning_rate": 4.162433063298092e-05, "loss": 2.0368, "step": 37100 }, { "epoch": 1.69, "learning_rate": 4.1622042198727635e-05, "loss": 2.1831, "step": 37110 }, { "epoch": 1.69, "learning_rate": 4.161975376447435e-05, "loss": 2.278, "step": 37120 }, { "epoch": 1.7, "learning_rate": 4.161746533022107e-05, "loss": 2.2562, "step": 37130 }, { "epoch": 1.7, "learning_rate": 4.1615176895967784e-05, "loss": 2.1422, "step": 37140 }, { "epoch": 1.7, "learning_rate": 4.161288846171449e-05, "loss": 2.2831, "step": 37150 }, { "epoch": 1.7, "learning_rate": 4.161060002746121e-05, "loss": 2.2822, "step": 37160 }, { "epoch": 1.7, "learning_rate": 4.1608311593207927e-05, "loss": 2.3343, "step": 37170 }, { "epoch": 1.7, "learning_rate": 4.160602315895464e-05, "loss": 2.2404, "step": 37180 }, { "epoch": 1.7, "learning_rate": 4.160373472470136e-05, "loss": 2.1942, "step": 37190 }, { "epoch": 1.7, "learning_rate": 4.1601446290448076e-05, "loss": 2.3393, "step": 37200 }, { "epoch": 1.7, "learning_rate": 4.159915785619479e-05, "loss": 2.1314, "step": 37210 }, { "epoch": 1.7, "learning_rate": 4.159686942194151e-05, "loss": 2.0445, "step": 37220 }, { "epoch": 1.7, "learning_rate": 4.1594580987688225e-05, "loss": 2.1177, "step": 37230 }, { "epoch": 1.7, "learning_rate": 4.159229255343494e-05, "loss": 2.131, "step": 37240 }, { "epoch": 1.7, "learning_rate": 4.159000411918166e-05, "loss": 2.2651, "step": 37250 }, { "epoch": 1.7, "learning_rate": 4.1587715684928374e-05, "loss": 2.0805, "step": 37260 }, { "epoch": 1.7, "learning_rate": 4.158542725067509e-05, "loss": 2.2632, "step": 37270 }, { "epoch": 1.7, "learning_rate": 4.158313881642181e-05, "loss": 2.202, "step": 37280 }, { "epoch": 1.7, "learning_rate": 4.158085038216852e-05, "loss": 2.2129, "step": 37290 }, { "epoch": 1.7, "learning_rate": 4.157856194791524e-05, "loss": 2.1495, "step": 37300 }, { "epoch": 1.7, "learning_rate": 4.157627351366196e-05, "loss": 2.0718, "step": 37310 }, { "epoch": 1.7, "learning_rate": 4.157398507940867e-05, "loss": 2.3112, "step": 37320 }, { "epoch": 1.7, "learning_rate": 4.1571696645155387e-05, "loss": 2.1296, "step": 37330 }, { "epoch": 1.71, "learning_rate": 4.156940821090211e-05, "loss": 2.0855, "step": 37340 }, { "epoch": 1.71, "learning_rate": 4.1567119776648815e-05, "loss": 2.1491, "step": 37350 }, { "epoch": 1.71, "learning_rate": 4.1564831342395536e-05, "loss": 2.1027, "step": 37360 }, { "epoch": 1.71, "learning_rate": 4.156254290814225e-05, "loss": 2.1831, "step": 37370 }, { "epoch": 1.71, "learning_rate": 4.1560254473888964e-05, "loss": 2.2206, "step": 37380 }, { "epoch": 1.71, "learning_rate": 4.1557966039635685e-05, "loss": 2.3453, "step": 37390 }, { "epoch": 1.71, "learning_rate": 4.15556776053824e-05, "loss": 2.1525, "step": 37400 }, { "epoch": 1.71, "learning_rate": 4.155338917112911e-05, "loss": 2.3299, "step": 37410 }, { "epoch": 1.71, "learning_rate": 4.1551100736875834e-05, "loss": 2.2254, "step": 37420 }, { "epoch": 1.71, "learning_rate": 4.154881230262255e-05, "loss": 2.1341, "step": 37430 }, { "epoch": 1.71, "learning_rate": 4.154652386836926e-05, "loss": 2.2076, "step": 37440 }, { "epoch": 1.71, "learning_rate": 4.154423543411598e-05, "loss": 2.1984, "step": 37450 }, { "epoch": 1.71, "learning_rate": 4.15419469998627e-05, "loss": 2.1086, "step": 37460 }, { "epoch": 1.71, "learning_rate": 4.153965856560941e-05, "loss": 2.2669, "step": 37470 }, { "epoch": 1.71, "learning_rate": 4.153737013135613e-05, "loss": 2.2679, "step": 37480 }, { "epoch": 1.71, "learning_rate": 4.1535081697102847e-05, "loss": 2.1011, "step": 37490 }, { "epoch": 1.71, "learning_rate": 4.153279326284956e-05, "loss": 2.2693, "step": 37500 }, { "epoch": 1.71, "learning_rate": 4.153050482859628e-05, "loss": 2.056, "step": 37510 }, { "epoch": 1.71, "learning_rate": 4.1528216394342996e-05, "loss": 2.3404, "step": 37520 }, { "epoch": 1.71, "learning_rate": 4.152592796008971e-05, "loss": 2.312, "step": 37530 }, { "epoch": 1.71, "learning_rate": 4.152363952583643e-05, "loss": 2.174, "step": 37540 }, { "epoch": 1.71, "learning_rate": 4.152135109158314e-05, "loss": 2.2526, "step": 37550 }, { "epoch": 1.72, "learning_rate": 4.151906265732985e-05, "loss": 2.243, "step": 37560 }, { "epoch": 1.72, "learning_rate": 4.151677422307657e-05, "loss": 2.2495, "step": 37570 }, { "epoch": 1.72, "learning_rate": 4.151448578882329e-05, "loss": 2.2415, "step": 37580 }, { "epoch": 1.72, "learning_rate": 4.151219735457e-05, "loss": 2.3698, "step": 37590 }, { "epoch": 1.72, "learning_rate": 4.150990892031672e-05, "loss": 2.207, "step": 37600 }, { "epoch": 1.72, "learning_rate": 4.1507620486063436e-05, "loss": 2.028, "step": 37610 }, { "epoch": 1.72, "learning_rate": 4.150533205181015e-05, "loss": 2.2055, "step": 37620 }, { "epoch": 1.72, "learning_rate": 4.150304361755687e-05, "loss": 2.0987, "step": 37630 }, { "epoch": 1.72, "learning_rate": 4.1500755183303586e-05, "loss": 2.2206, "step": 37640 }, { "epoch": 1.72, "learning_rate": 4.14984667490503e-05, "loss": 2.2499, "step": 37650 }, { "epoch": 1.72, "learning_rate": 4.149617831479702e-05, "loss": 2.1183, "step": 37660 }, { "epoch": 1.72, "learning_rate": 4.1493889880543735e-05, "loss": 2.1184, "step": 37670 }, { "epoch": 1.72, "learning_rate": 4.149160144629045e-05, "loss": 2.2576, "step": 37680 }, { "epoch": 1.72, "learning_rate": 4.148931301203717e-05, "loss": 2.2855, "step": 37690 }, { "epoch": 1.72, "learning_rate": 4.1487024577783884e-05, "loss": 2.2388, "step": 37700 }, { "epoch": 1.72, "learning_rate": 4.14847361435306e-05, "loss": 2.207, "step": 37710 }, { "epoch": 1.72, "learning_rate": 4.148244770927732e-05, "loss": 2.2217, "step": 37720 }, { "epoch": 1.72, "learning_rate": 4.148015927502403e-05, "loss": 2.0881, "step": 37730 }, { "epoch": 1.72, "learning_rate": 4.147787084077074e-05, "loss": 2.2646, "step": 37740 }, { "epoch": 1.72, "learning_rate": 4.147558240651746e-05, "loss": 2.198, "step": 37750 }, { "epoch": 1.72, "learning_rate": 4.1473293972264176e-05, "loss": 2.1367, "step": 37760 }, { "epoch": 1.72, "learning_rate": 4.147100553801089e-05, "loss": 2.1073, "step": 37770 }, { "epoch": 1.73, "learning_rate": 4.146871710375761e-05, "loss": 2.2829, "step": 37780 }, { "epoch": 1.73, "learning_rate": 4.1466428669504325e-05, "loss": 2.2149, "step": 37790 }, { "epoch": 1.73, "learning_rate": 4.146414023525104e-05, "loss": 2.1057, "step": 37800 }, { "epoch": 1.73, "learning_rate": 4.146185180099776e-05, "loss": 2.1377, "step": 37810 }, { "epoch": 1.73, "learning_rate": 4.1459563366744474e-05, "loss": 2.0502, "step": 37820 }, { "epoch": 1.73, "learning_rate": 4.145727493249119e-05, "loss": 2.1293, "step": 37830 }, { "epoch": 1.73, "learning_rate": 4.145498649823791e-05, "loss": 2.2153, "step": 37840 }, { "epoch": 1.73, "learning_rate": 4.145269806398462e-05, "loss": 2.2339, "step": 37850 }, { "epoch": 1.73, "learning_rate": 4.145040962973134e-05, "loss": 2.2364, "step": 37860 }, { "epoch": 1.73, "learning_rate": 4.144812119547806e-05, "loss": 2.1943, "step": 37870 }, { "epoch": 1.73, "learning_rate": 4.144583276122477e-05, "loss": 2.2552, "step": 37880 }, { "epoch": 1.73, "learning_rate": 4.1443544326971486e-05, "loss": 2.1422, "step": 37890 }, { "epoch": 1.73, "learning_rate": 4.144125589271821e-05, "loss": 2.3014, "step": 37900 }, { "epoch": 1.73, "learning_rate": 4.143896745846492e-05, "loss": 2.2797, "step": 37910 }, { "epoch": 1.73, "learning_rate": 4.1436679024211636e-05, "loss": 2.0881, "step": 37920 }, { "epoch": 1.73, "learning_rate": 4.1434390589958357e-05, "loss": 2.1671, "step": 37930 }, { "epoch": 1.73, "learning_rate": 4.1432102155705064e-05, "loss": 2.1613, "step": 37940 }, { "epoch": 1.73, "learning_rate": 4.1429813721451785e-05, "loss": 2.0843, "step": 37950 }, { "epoch": 1.73, "learning_rate": 4.14275252871985e-05, "loss": 2.2516, "step": 37960 }, { "epoch": 1.73, "learning_rate": 4.142523685294521e-05, "loss": 2.1627, "step": 37970 }, { "epoch": 1.73, "learning_rate": 4.1422948418691934e-05, "loss": 2.2151, "step": 37980 }, { "epoch": 1.73, "learning_rate": 4.142065998443865e-05, "loss": 2.2374, "step": 37990 }, { "epoch": 1.74, "learning_rate": 4.141837155018536e-05, "loss": 2.1519, "step": 38000 }, { "epoch": 1.74, "learning_rate": 4.141608311593208e-05, "loss": 2.2167, "step": 38010 }, { "epoch": 1.74, "learning_rate": 4.14137946816788e-05, "loss": 2.2421, "step": 38020 }, { "epoch": 1.74, "learning_rate": 4.141150624742551e-05, "loss": 2.1591, "step": 38030 }, { "epoch": 1.74, "learning_rate": 4.140921781317223e-05, "loss": 2.0859, "step": 38040 }, { "epoch": 1.74, "learning_rate": 4.1406929378918946e-05, "loss": 2.0907, "step": 38050 }, { "epoch": 1.74, "learning_rate": 4.140464094466566e-05, "loss": 2.0643, "step": 38060 }, { "epoch": 1.74, "learning_rate": 4.140235251041238e-05, "loss": 2.281, "step": 38070 }, { "epoch": 1.74, "learning_rate": 4.1400064076159096e-05, "loss": 2.1834, "step": 38080 }, { "epoch": 1.74, "learning_rate": 4.139777564190581e-05, "loss": 2.2338, "step": 38090 }, { "epoch": 1.74, "learning_rate": 4.139548720765253e-05, "loss": 2.1992, "step": 38100 }, { "epoch": 1.74, "learning_rate": 4.1393198773399245e-05, "loss": 2.2269, "step": 38110 }, { "epoch": 1.74, "learning_rate": 4.139091033914596e-05, "loss": 2.1464, "step": 38120 }, { "epoch": 1.74, "learning_rate": 4.138862190489268e-05, "loss": 1.9402, "step": 38130 }, { "epoch": 1.74, "learning_rate": 4.138633347063939e-05, "loss": 2.2929, "step": 38140 }, { "epoch": 1.74, "learning_rate": 4.13840450363861e-05, "loss": 2.1427, "step": 38150 }, { "epoch": 1.74, "learning_rate": 4.138175660213282e-05, "loss": 2.1429, "step": 38160 }, { "epoch": 1.74, "learning_rate": 4.1379468167879536e-05, "loss": 2.0469, "step": 38170 }, { "epoch": 1.74, "learning_rate": 4.137717973362625e-05, "loss": 2.2284, "step": 38180 }, { "epoch": 1.74, "learning_rate": 4.137489129937297e-05, "loss": 2.1356, "step": 38190 }, { "epoch": 1.74, "learning_rate": 4.1372602865119686e-05, "loss": 2.1911, "step": 38200 }, { "epoch": 1.74, "learning_rate": 4.13703144308664e-05, "loss": 2.064, "step": 38210 }, { "epoch": 1.75, "learning_rate": 4.136802599661312e-05, "loss": 2.1332, "step": 38220 }, { "epoch": 1.75, "learning_rate": 4.1365737562359835e-05, "loss": 2.229, "step": 38230 }, { "epoch": 1.75, "learning_rate": 4.136344912810655e-05, "loss": 2.1753, "step": 38240 }, { "epoch": 1.75, "learning_rate": 4.136116069385327e-05, "loss": 2.1118, "step": 38250 }, { "epoch": 1.75, "learning_rate": 4.1358872259599984e-05, "loss": 2.039, "step": 38260 }, { "epoch": 1.75, "learning_rate": 4.13565838253467e-05, "loss": 2.321, "step": 38270 }, { "epoch": 1.75, "learning_rate": 4.135429539109342e-05, "loss": 2.186, "step": 38280 }, { "epoch": 1.75, "learning_rate": 4.135200695684013e-05, "loss": 2.1979, "step": 38290 }, { "epoch": 1.75, "learning_rate": 4.134971852258685e-05, "loss": 2.1619, "step": 38300 }, { "epoch": 1.75, "learning_rate": 4.134743008833357e-05, "loss": 2.1514, "step": 38310 }, { "epoch": 1.75, "learning_rate": 4.134514165408028e-05, "loss": 2.2131, "step": 38320 }, { "epoch": 1.75, "learning_rate": 4.1342853219826996e-05, "loss": 2.1808, "step": 38330 }, { "epoch": 1.75, "learning_rate": 4.134056478557371e-05, "loss": 2.1792, "step": 38340 }, { "epoch": 1.75, "learning_rate": 4.1338276351320425e-05, "loss": 2.2061, "step": 38350 }, { "epoch": 1.75, "learning_rate": 4.1335987917067146e-05, "loss": 2.2261, "step": 38360 }, { "epoch": 1.75, "learning_rate": 4.133369948281386e-05, "loss": 1.9967, "step": 38370 }, { "epoch": 1.75, "learning_rate": 4.1331411048560574e-05, "loss": 2.2079, "step": 38380 }, { "epoch": 1.75, "learning_rate": 4.1329122614307295e-05, "loss": 2.1245, "step": 38390 }, { "epoch": 1.75, "learning_rate": 4.132683418005401e-05, "loss": 2.272, "step": 38400 }, { "epoch": 1.75, "learning_rate": 4.132454574580072e-05, "loss": 2.2823, "step": 38410 }, { "epoch": 1.75, "learning_rate": 4.1322257311547444e-05, "loss": 2.0441, "step": 38420 }, { "epoch": 1.75, "learning_rate": 4.131996887729416e-05, "loss": 2.2316, "step": 38430 }, { "epoch": 1.76, "learning_rate": 4.131768044304087e-05, "loss": 2.1245, "step": 38440 }, { "epoch": 1.76, "learning_rate": 4.131539200878759e-05, "loss": 2.319, "step": 38450 }, { "epoch": 1.76, "learning_rate": 4.131310357453431e-05, "loss": 2.0164, "step": 38460 }, { "epoch": 1.76, "learning_rate": 4.131081514028102e-05, "loss": 2.0391, "step": 38470 }, { "epoch": 1.76, "learning_rate": 4.130852670602774e-05, "loss": 2.3564, "step": 38480 }, { "epoch": 1.76, "learning_rate": 4.1306238271774456e-05, "loss": 2.1674, "step": 38490 }, { "epoch": 1.76, "learning_rate": 4.130394983752117e-05, "loss": 2.1892, "step": 38500 }, { "epoch": 1.76, "learning_rate": 4.130166140326789e-05, "loss": 2.1581, "step": 38510 }, { "epoch": 1.76, "learning_rate": 4.1299372969014606e-05, "loss": 2.2574, "step": 38520 }, { "epoch": 1.76, "learning_rate": 4.129708453476131e-05, "loss": 2.1512, "step": 38530 }, { "epoch": 1.76, "learning_rate": 4.1294796100508034e-05, "loss": 2.1378, "step": 38540 }, { "epoch": 1.76, "learning_rate": 4.129250766625475e-05, "loss": 2.1524, "step": 38550 }, { "epoch": 1.76, "learning_rate": 4.129021923200146e-05, "loss": 2.3223, "step": 38560 }, { "epoch": 1.76, "learning_rate": 4.128793079774818e-05, "loss": 2.2442, "step": 38570 }, { "epoch": 1.76, "learning_rate": 4.12856423634949e-05, "loss": 2.2459, "step": 38580 }, { "epoch": 1.76, "learning_rate": 4.128335392924161e-05, "loss": 2.1992, "step": 38590 }, { "epoch": 1.76, "learning_rate": 4.128106549498833e-05, "loss": 2.156, "step": 38600 }, { "epoch": 1.76, "learning_rate": 4.1278777060735046e-05, "loss": 2.1905, "step": 38610 }, { "epoch": 1.76, "learning_rate": 4.127648862648176e-05, "loss": 2.2904, "step": 38620 }, { "epoch": 1.76, "learning_rate": 4.127420019222848e-05, "loss": 2.3478, "step": 38630 }, { "epoch": 1.76, "learning_rate": 4.1271911757975196e-05, "loss": 2.112, "step": 38640 }, { "epoch": 1.76, "learning_rate": 4.126962332372191e-05, "loss": 2.2066, "step": 38650 }, { "epoch": 1.77, "learning_rate": 4.126733488946863e-05, "loss": 2.1544, "step": 38660 }, { "epoch": 1.77, "learning_rate": 4.1265046455215345e-05, "loss": 2.1541, "step": 38670 }, { "epoch": 1.77, "learning_rate": 4.126275802096206e-05, "loss": 2.2422, "step": 38680 }, { "epoch": 1.77, "learning_rate": 4.126046958670878e-05, "loss": 2.2683, "step": 38690 }, { "epoch": 1.77, "learning_rate": 4.1258181152455494e-05, "loss": 2.0815, "step": 38700 }, { "epoch": 1.77, "learning_rate": 4.125589271820221e-05, "loss": 2.3379, "step": 38710 }, { "epoch": 1.77, "learning_rate": 4.125360428394893e-05, "loss": 2.1361, "step": 38720 }, { "epoch": 1.77, "learning_rate": 4.1251315849695636e-05, "loss": 2.141, "step": 38730 }, { "epoch": 1.77, "learning_rate": 4.124902741544236e-05, "loss": 2.2016, "step": 38740 }, { "epoch": 1.77, "learning_rate": 4.124673898118907e-05, "loss": 2.0977, "step": 38750 }, { "epoch": 1.77, "learning_rate": 4.1244450546935785e-05, "loss": 2.2267, "step": 38760 }, { "epoch": 1.77, "learning_rate": 4.1242162112682506e-05, "loss": 2.1789, "step": 38770 }, { "epoch": 1.77, "learning_rate": 4.123987367842922e-05, "loss": 2.2034, "step": 38780 }, { "epoch": 1.77, "learning_rate": 4.1237585244175935e-05, "loss": 2.1298, "step": 38790 }, { "epoch": 1.77, "learning_rate": 4.1235296809922656e-05, "loss": 2.2074, "step": 38800 }, { "epoch": 1.77, "learning_rate": 4.123300837566937e-05, "loss": 2.0893, "step": 38810 }, { "epoch": 1.77, "learning_rate": 4.1230719941416084e-05, "loss": 2.1876, "step": 38820 }, { "epoch": 1.77, "learning_rate": 4.1228431507162805e-05, "loss": 2.1834, "step": 38830 }, { "epoch": 1.77, "learning_rate": 4.122614307290952e-05, "loss": 2.3856, "step": 38840 }, { "epoch": 1.77, "learning_rate": 4.122385463865623e-05, "loss": 2.1541, "step": 38850 }, { "epoch": 1.77, "learning_rate": 4.122156620440295e-05, "loss": 2.1768, "step": 38860 }, { "epoch": 1.77, "learning_rate": 4.121927777014967e-05, "loss": 2.1351, "step": 38870 }, { "epoch": 1.78, "learning_rate": 4.121698933589638e-05, "loss": 2.1057, "step": 38880 }, { "epoch": 1.78, "learning_rate": 4.1214700901643096e-05, "loss": 2.3243, "step": 38890 }, { "epoch": 1.78, "learning_rate": 4.121241246738982e-05, "loss": 2.1536, "step": 38900 }, { "epoch": 1.78, "learning_rate": 4.121012403313653e-05, "loss": 2.1002, "step": 38910 }, { "epoch": 1.78, "learning_rate": 4.1207835598883245e-05, "loss": 2.1905, "step": 38920 }, { "epoch": 1.78, "learning_rate": 4.120554716462996e-05, "loss": 2.4109, "step": 38930 }, { "epoch": 1.78, "learning_rate": 4.1203258730376674e-05, "loss": 2.1665, "step": 38940 }, { "epoch": 1.78, "learning_rate": 4.1200970296123395e-05, "loss": 2.2572, "step": 38950 }, { "epoch": 1.78, "learning_rate": 4.119868186187011e-05, "loss": 2.217, "step": 38960 }, { "epoch": 1.78, "learning_rate": 4.119639342761682e-05, "loss": 2.2218, "step": 38970 }, { "epoch": 1.78, "learning_rate": 4.1194104993363544e-05, "loss": 2.1996, "step": 38980 }, { "epoch": 1.78, "learning_rate": 4.119181655911026e-05, "loss": 2.1562, "step": 38990 }, { "epoch": 1.78, "learning_rate": 4.118952812485697e-05, "loss": 2.0947, "step": 39000 }, { "epoch": 1.78, "learning_rate": 4.118723969060369e-05, "loss": 2.2666, "step": 39010 }, { "epoch": 1.78, "learning_rate": 4.118495125635041e-05, "loss": 2.2147, "step": 39020 }, { "epoch": 1.78, "learning_rate": 4.118266282209712e-05, "loss": 2.1357, "step": 39030 }, { "epoch": 1.78, "learning_rate": 4.118037438784384e-05, "loss": 2.3055, "step": 39040 }, { "epoch": 1.78, "learning_rate": 4.1178085953590556e-05, "loss": 2.1255, "step": 39050 }, { "epoch": 1.78, "learning_rate": 4.117579751933727e-05, "loss": 2.0706, "step": 39060 }, { "epoch": 1.78, "learning_rate": 4.117350908508399e-05, "loss": 2.2872, "step": 39070 }, { "epoch": 1.78, "learning_rate": 4.1171220650830705e-05, "loss": 2.1869, "step": 39080 }, { "epoch": 1.78, "learning_rate": 4.116893221657742e-05, "loss": 2.0666, "step": 39090 }, { "epoch": 1.79, "learning_rate": 4.116664378232414e-05, "loss": 2.0631, "step": 39100 }, { "epoch": 1.79, "learning_rate": 4.1164355348070855e-05, "loss": 2.2619, "step": 39110 }, { "epoch": 1.79, "learning_rate": 4.116206691381757e-05, "loss": 2.1801, "step": 39120 }, { "epoch": 1.79, "learning_rate": 4.115977847956428e-05, "loss": 2.2454, "step": 39130 }, { "epoch": 1.79, "learning_rate": 4.1157490045311e-05, "loss": 2.3209, "step": 39140 }, { "epoch": 1.79, "learning_rate": 4.115520161105771e-05, "loss": 2.1828, "step": 39150 }, { "epoch": 1.79, "learning_rate": 4.115291317680443e-05, "loss": 2.1665, "step": 39160 }, { "epoch": 1.79, "learning_rate": 4.1150624742551146e-05, "loss": 2.07, "step": 39170 }, { "epoch": 1.79, "learning_rate": 4.114833630829786e-05, "loss": 2.1646, "step": 39180 }, { "epoch": 1.79, "learning_rate": 4.114604787404458e-05, "loss": 2.2058, "step": 39190 }, { "epoch": 1.79, "learning_rate": 4.1143759439791295e-05, "loss": 2.1602, "step": 39200 }, { "epoch": 1.79, "learning_rate": 4.114147100553801e-05, "loss": 2.2457, "step": 39210 }, { "epoch": 1.79, "learning_rate": 4.113918257128473e-05, "loss": 2.2384, "step": 39220 }, { "epoch": 1.79, "learning_rate": 4.1136894137031445e-05, "loss": 2.2907, "step": 39230 }, { "epoch": 1.79, "learning_rate": 4.113460570277816e-05, "loss": 2.1987, "step": 39240 }, { "epoch": 1.79, "learning_rate": 4.113231726852488e-05, "loss": 2.3067, "step": 39250 }, { "epoch": 1.79, "learning_rate": 4.1130028834271594e-05, "loss": 2.1219, "step": 39260 }, { "epoch": 1.79, "learning_rate": 4.112774040001831e-05, "loss": 2.274, "step": 39270 }, { "epoch": 1.79, "learning_rate": 4.112545196576503e-05, "loss": 2.2913, "step": 39280 }, { "epoch": 1.79, "learning_rate": 4.112316353151174e-05, "loss": 2.1311, "step": 39290 }, { "epoch": 1.79, "learning_rate": 4.112087509725846e-05, "loss": 2.0901, "step": 39300 }, { "epoch": 1.79, "learning_rate": 4.111858666300518e-05, "loss": 2.143, "step": 39310 }, { "epoch": 1.8, "learning_rate": 4.1116298228751885e-05, "loss": 2.199, "step": 39320 }, { "epoch": 1.8, "learning_rate": 4.1114009794498606e-05, "loss": 2.0717, "step": 39330 }, { "epoch": 1.8, "learning_rate": 4.111172136024532e-05, "loss": 2.2176, "step": 39340 }, { "epoch": 1.8, "learning_rate": 4.1109432925992035e-05, "loss": 2.1655, "step": 39350 }, { "epoch": 1.8, "learning_rate": 4.1107144491738755e-05, "loss": 2.1517, "step": 39360 }, { "epoch": 1.8, "learning_rate": 4.110485605748547e-05, "loss": 2.1709, "step": 39370 }, { "epoch": 1.8, "learning_rate": 4.1102567623232184e-05, "loss": 2.0361, "step": 39380 }, { "epoch": 1.8, "learning_rate": 4.1100279188978905e-05, "loss": 2.1617, "step": 39390 }, { "epoch": 1.8, "learning_rate": 4.109799075472562e-05, "loss": 2.1292, "step": 39400 }, { "epoch": 1.8, "learning_rate": 4.109570232047233e-05, "loss": 2.2445, "step": 39410 }, { "epoch": 1.8, "learning_rate": 4.1093413886219054e-05, "loss": 2.3475, "step": 39420 }, { "epoch": 1.8, "learning_rate": 4.109112545196577e-05, "loss": 2.1955, "step": 39430 }, { "epoch": 1.8, "learning_rate": 4.108883701771248e-05, "loss": 2.2206, "step": 39440 }, { "epoch": 1.8, "learning_rate": 4.10865485834592e-05, "loss": 2.1371, "step": 39450 }, { "epoch": 1.8, "learning_rate": 4.108426014920592e-05, "loss": 2.2613, "step": 39460 }, { "epoch": 1.8, "learning_rate": 4.108197171495263e-05, "loss": 2.1521, "step": 39470 }, { "epoch": 1.8, "learning_rate": 4.107968328069935e-05, "loss": 2.258, "step": 39480 }, { "epoch": 1.8, "learning_rate": 4.1077394846446066e-05, "loss": 2.2545, "step": 39490 }, { "epoch": 1.8, "learning_rate": 4.107510641219278e-05, "loss": 2.2301, "step": 39500 }, { "epoch": 1.8, "learning_rate": 4.10728179779395e-05, "loss": 2.3515, "step": 39510 }, { "epoch": 1.8, "learning_rate": 4.107052954368621e-05, "loss": 2.1409, "step": 39520 }, { "epoch": 1.81, "learning_rate": 4.106824110943292e-05, "loss": 2.1947, "step": 39530 }, { "epoch": 1.81, "learning_rate": 4.1065952675179644e-05, "loss": 2.2916, "step": 39540 }, { "epoch": 1.81, "learning_rate": 4.106366424092636e-05, "loss": 2.2439, "step": 39550 }, { "epoch": 1.81, "learning_rate": 4.106137580667307e-05, "loss": 2.2, "step": 39560 }, { "epoch": 1.81, "learning_rate": 4.105908737241979e-05, "loss": 2.0028, "step": 39570 }, { "epoch": 1.81, "learning_rate": 4.105679893816651e-05, "loss": 2.1961, "step": 39580 }, { "epoch": 1.81, "learning_rate": 4.105451050391322e-05, "loss": 2.261, "step": 39590 }, { "epoch": 1.81, "learning_rate": 4.105222206965994e-05, "loss": 2.1028, "step": 39600 }, { "epoch": 1.81, "learning_rate": 4.1049933635406656e-05, "loss": 2.218, "step": 39610 }, { "epoch": 1.81, "learning_rate": 4.104764520115337e-05, "loss": 2.1983, "step": 39620 }, { "epoch": 1.81, "learning_rate": 4.104535676690009e-05, "loss": 2.2249, "step": 39630 }, { "epoch": 1.81, "learning_rate": 4.1043068332646805e-05, "loss": 2.3117, "step": 39640 }, { "epoch": 1.81, "learning_rate": 4.104077989839352e-05, "loss": 2.0847, "step": 39650 }, { "epoch": 1.81, "learning_rate": 4.103849146414024e-05, "loss": 2.1089, "step": 39660 }, { "epoch": 1.81, "learning_rate": 4.1036203029886955e-05, "loss": 2.3177, "step": 39670 }, { "epoch": 1.81, "learning_rate": 4.103391459563367e-05, "loss": 2.1705, "step": 39680 }, { "epoch": 1.81, "learning_rate": 4.103162616138039e-05, "loss": 2.2459, "step": 39690 }, { "epoch": 1.81, "learning_rate": 4.1029337727127104e-05, "loss": 2.2321, "step": 39700 }, { "epoch": 1.81, "learning_rate": 4.102704929287382e-05, "loss": 2.143, "step": 39710 }, { "epoch": 1.81, "learning_rate": 4.102476085862053e-05, "loss": 2.1193, "step": 39720 }, { "epoch": 1.81, "learning_rate": 4.1022472424367246e-05, "loss": 2.3632, "step": 39730 }, { "epoch": 1.81, "learning_rate": 4.102018399011397e-05, "loss": 2.3341, "step": 39740 }, { "epoch": 1.82, "learning_rate": 4.101789555586068e-05, "loss": 2.2155, "step": 39750 }, { "epoch": 1.82, "learning_rate": 4.1015607121607395e-05, "loss": 2.2907, "step": 39760 }, { "epoch": 1.82, "learning_rate": 4.1013318687354116e-05, "loss": 2.1452, "step": 39770 }, { "epoch": 1.82, "learning_rate": 4.101103025310083e-05, "loss": 2.1139, "step": 39780 }, { "epoch": 1.82, "learning_rate": 4.1008741818847544e-05, "loss": 2.24, "step": 39790 }, { "epoch": 1.82, "learning_rate": 4.1006453384594265e-05, "loss": 2.2145, "step": 39800 }, { "epoch": 1.82, "learning_rate": 4.100416495034098e-05, "loss": 2.1807, "step": 39810 }, { "epoch": 1.82, "learning_rate": 4.1001876516087694e-05, "loss": 2.1166, "step": 39820 }, { "epoch": 1.82, "learning_rate": 4.0999588081834415e-05, "loss": 2.1806, "step": 39830 }, { "epoch": 1.82, "learning_rate": 4.099729964758113e-05, "loss": 2.1754, "step": 39840 }, { "epoch": 1.82, "learning_rate": 4.099501121332784e-05, "loss": 2.2099, "step": 39850 }, { "epoch": 1.82, "learning_rate": 4.0992722779074564e-05, "loss": 2.1664, "step": 39860 }, { "epoch": 1.82, "learning_rate": 4.099043434482128e-05, "loss": 2.3004, "step": 39870 }, { "epoch": 1.82, "learning_rate": 4.098814591056799e-05, "loss": 2.2126, "step": 39880 }, { "epoch": 1.82, "learning_rate": 4.098585747631471e-05, "loss": 2.1226, "step": 39890 }, { "epoch": 1.82, "learning_rate": 4.098356904206143e-05, "loss": 2.4361, "step": 39900 }, { "epoch": 1.82, "learning_rate": 4.098128060780814e-05, "loss": 2.1184, "step": 39910 }, { "epoch": 1.82, "learning_rate": 4.0978992173554855e-05, "loss": 2.289, "step": 39920 }, { "epoch": 1.82, "learning_rate": 4.097670373930157e-05, "loss": 2.1198, "step": 39930 }, { "epoch": 1.82, "learning_rate": 4.0974415305048284e-05, "loss": 2.1545, "step": 39940 }, { "epoch": 1.82, "learning_rate": 4.0972126870795005e-05, "loss": 2.2121, "step": 39950 }, { "epoch": 1.82, "learning_rate": 4.096983843654172e-05, "loss": 2.2906, "step": 39960 }, { "epoch": 1.83, "learning_rate": 4.096755000228843e-05, "loss": 2.1927, "step": 39970 }, { "epoch": 1.83, "learning_rate": 4.0965261568035154e-05, "loss": 2.2119, "step": 39980 }, { "epoch": 1.83, "learning_rate": 4.096297313378187e-05, "loss": 2.3019, "step": 39990 }, { "epoch": 1.83, "learning_rate": 4.096068469952858e-05, "loss": 2.1829, "step": 40000 }, { "epoch": 1.83, "learning_rate": 4.09583962652753e-05, "loss": 2.341, "step": 40010 }, { "epoch": 1.83, "learning_rate": 4.095610783102202e-05, "loss": 2.0693, "step": 40020 }, { "epoch": 1.83, "learning_rate": 4.095381939676873e-05, "loss": 2.061, "step": 40030 }, { "epoch": 1.83, "learning_rate": 4.095153096251545e-05, "loss": 2.1245, "step": 40040 }, { "epoch": 1.83, "learning_rate": 4.0949242528262166e-05, "loss": 2.3334, "step": 40050 }, { "epoch": 1.83, "learning_rate": 4.094695409400888e-05, "loss": 2.239, "step": 40060 }, { "epoch": 1.83, "learning_rate": 4.09446656597556e-05, "loss": 2.2883, "step": 40070 }, { "epoch": 1.83, "learning_rate": 4.0942377225502315e-05, "loss": 2.0487, "step": 40080 }, { "epoch": 1.83, "learning_rate": 4.094008879124903e-05, "loss": 2.2817, "step": 40090 }, { "epoch": 1.83, "learning_rate": 4.093780035699575e-05, "loss": 2.1659, "step": 40100 }, { "epoch": 1.83, "learning_rate": 4.093551192274246e-05, "loss": 2.2554, "step": 40110 }, { "epoch": 1.83, "learning_rate": 4.093322348848917e-05, "loss": 2.1521, "step": 40120 }, { "epoch": 1.83, "learning_rate": 4.093093505423589e-05, "loss": 2.0554, "step": 40130 }, { "epoch": 1.83, "learning_rate": 4.092864661998261e-05, "loss": 2.2107, "step": 40140 }, { "epoch": 1.83, "learning_rate": 4.092635818572932e-05, "loss": 2.2115, "step": 40150 }, { "epoch": 1.83, "learning_rate": 4.092406975147604e-05, "loss": 2.0894, "step": 40160 }, { "epoch": 1.83, "learning_rate": 4.0921781317222756e-05, "loss": 2.2177, "step": 40170 }, { "epoch": 1.83, "learning_rate": 4.091949288296947e-05, "loss": 2.3488, "step": 40180 }, { "epoch": 1.84, "learning_rate": 4.091720444871619e-05, "loss": 2.2346, "step": 40190 }, { "epoch": 1.84, "learning_rate": 4.0914916014462905e-05, "loss": 2.1689, "step": 40200 }, { "epoch": 1.84, "learning_rate": 4.091262758020962e-05, "loss": 2.1302, "step": 40210 }, { "epoch": 1.84, "learning_rate": 4.091033914595634e-05, "loss": 2.1606, "step": 40220 }, { "epoch": 1.84, "learning_rate": 4.0908050711703054e-05, "loss": 2.1964, "step": 40230 }, { "epoch": 1.84, "learning_rate": 4.090576227744977e-05, "loss": 2.1216, "step": 40240 }, { "epoch": 1.84, "learning_rate": 4.090347384319649e-05, "loss": 2.2734, "step": 40250 }, { "epoch": 1.84, "learning_rate": 4.0901185408943204e-05, "loss": 2.2815, "step": 40260 }, { "epoch": 1.84, "learning_rate": 4.089889697468992e-05, "loss": 2.1951, "step": 40270 }, { "epoch": 1.84, "learning_rate": 4.089660854043664e-05, "loss": 2.2452, "step": 40280 }, { "epoch": 1.84, "learning_rate": 4.089432010618335e-05, "loss": 2.1403, "step": 40290 }, { "epoch": 1.84, "learning_rate": 4.089203167193007e-05, "loss": 2.2352, "step": 40300 }, { "epoch": 1.84, "learning_rate": 4.088974323767678e-05, "loss": 2.2708, "step": 40310 }, { "epoch": 1.84, "learning_rate": 4.0887454803423495e-05, "loss": 2.2047, "step": 40320 }, { "epoch": 1.84, "learning_rate": 4.0885166369170216e-05, "loss": 2.1222, "step": 40330 }, { "epoch": 1.84, "learning_rate": 4.088287793491693e-05, "loss": 2.2381, "step": 40340 }, { "epoch": 1.84, "learning_rate": 4.0880589500663644e-05, "loss": 2.0217, "step": 40350 }, { "epoch": 1.84, "learning_rate": 4.0878301066410365e-05, "loss": 2.1734, "step": 40360 }, { "epoch": 1.84, "learning_rate": 4.087601263215708e-05, "loss": 2.065, "step": 40370 }, { "epoch": 1.84, "learning_rate": 4.0873724197903794e-05, "loss": 2.1731, "step": 40380 }, { "epoch": 1.84, "learning_rate": 4.0871435763650514e-05, "loss": 2.1526, "step": 40390 }, { "epoch": 1.84, "learning_rate": 4.086914732939723e-05, "loss": 2.2855, "step": 40400 }, { "epoch": 1.85, "learning_rate": 4.086685889514394e-05, "loss": 2.0191, "step": 40410 }, { "epoch": 1.85, "learning_rate": 4.0864570460890664e-05, "loss": 2.2141, "step": 40420 }, { "epoch": 1.85, "learning_rate": 4.086228202663738e-05, "loss": 2.0797, "step": 40430 }, { "epoch": 1.85, "learning_rate": 4.085999359238409e-05, "loss": 2.1945, "step": 40440 }, { "epoch": 1.85, "learning_rate": 4.085770515813081e-05, "loss": 2.189, "step": 40450 }, { "epoch": 1.85, "learning_rate": 4.085541672387753e-05, "loss": 2.1006, "step": 40460 }, { "epoch": 1.85, "learning_rate": 4.085312828962424e-05, "loss": 2.2507, "step": 40470 }, { "epoch": 1.85, "learning_rate": 4.085083985537096e-05, "loss": 2.1423, "step": 40480 }, { "epoch": 1.85, "learning_rate": 4.0848551421117676e-05, "loss": 2.2095, "step": 40490 }, { "epoch": 1.85, "learning_rate": 4.084626298686439e-05, "loss": 2.1601, "step": 40500 }, { "epoch": 1.85, "learning_rate": 4.0843974552611104e-05, "loss": 2.3158, "step": 40510 }, { "epoch": 1.85, "learning_rate": 4.084168611835782e-05, "loss": 2.1528, "step": 40520 }, { "epoch": 1.85, "learning_rate": 4.083939768410453e-05, "loss": 2.0993, "step": 40530 }, { "epoch": 1.85, "learning_rate": 4.0837109249851254e-05, "loss": 2.0066, "step": 40540 }, { "epoch": 1.85, "learning_rate": 4.083482081559797e-05, "loss": 2.0454, "step": 40550 }, { "epoch": 1.85, "learning_rate": 4.083253238134468e-05, "loss": 2.1391, "step": 40560 }, { "epoch": 1.85, "learning_rate": 4.08302439470914e-05, "loss": 2.1545, "step": 40570 }, { "epoch": 1.85, "learning_rate": 4.082795551283812e-05, "loss": 2.1206, "step": 40580 }, { "epoch": 1.85, "learning_rate": 4.082566707858483e-05, "loss": 2.0886, "step": 40590 }, { "epoch": 1.85, "learning_rate": 4.082337864433155e-05, "loss": 2.2021, "step": 40600 }, { "epoch": 1.85, "learning_rate": 4.0821090210078266e-05, "loss": 2.2036, "step": 40610 }, { "epoch": 1.85, "learning_rate": 4.081880177582498e-05, "loss": 2.0806, "step": 40620 }, { "epoch": 1.86, "learning_rate": 4.08165133415717e-05, "loss": 2.105, "step": 40630 }, { "epoch": 1.86, "learning_rate": 4.0814224907318415e-05, "loss": 2.0902, "step": 40640 }, { "epoch": 1.86, "learning_rate": 4.081193647306513e-05, "loss": 2.3253, "step": 40650 }, { "epoch": 1.86, "learning_rate": 4.080964803881185e-05, "loss": 2.1818, "step": 40660 }, { "epoch": 1.86, "learning_rate": 4.0807359604558564e-05, "loss": 2.244, "step": 40670 }, { "epoch": 1.86, "learning_rate": 4.080507117030528e-05, "loss": 2.1826, "step": 40680 }, { "epoch": 1.86, "learning_rate": 4.0802782736052e-05, "loss": 2.178, "step": 40690 }, { "epoch": 1.86, "learning_rate": 4.0800494301798714e-05, "loss": 2.2487, "step": 40700 }, { "epoch": 1.86, "learning_rate": 4.079820586754543e-05, "loss": 2.2191, "step": 40710 }, { "epoch": 1.86, "learning_rate": 4.079591743329214e-05, "loss": 2.2198, "step": 40720 }, { "epoch": 1.86, "learning_rate": 4.0793628999038856e-05, "loss": 2.3713, "step": 40730 }, { "epoch": 1.86, "learning_rate": 4.079134056478558e-05, "loss": 2.1774, "step": 40740 }, { "epoch": 1.86, "learning_rate": 4.078905213053229e-05, "loss": 2.255, "step": 40750 }, { "epoch": 1.86, "learning_rate": 4.0786763696279005e-05, "loss": 2.2001, "step": 40760 }, { "epoch": 1.86, "learning_rate": 4.0784475262025726e-05, "loss": 2.2132, "step": 40770 }, { "epoch": 1.86, "learning_rate": 4.078218682777244e-05, "loss": 2.1164, "step": 40780 }, { "epoch": 1.86, "learning_rate": 4.0779898393519154e-05, "loss": 2.141, "step": 40790 }, { "epoch": 1.86, "learning_rate": 4.0777609959265875e-05, "loss": 2.0203, "step": 40800 }, { "epoch": 1.86, "learning_rate": 4.077532152501259e-05, "loss": 2.071, "step": 40810 }, { "epoch": 1.86, "learning_rate": 4.0773033090759304e-05, "loss": 2.1821, "step": 40820 }, { "epoch": 1.86, "learning_rate": 4.0770744656506024e-05, "loss": 2.0444, "step": 40830 }, { "epoch": 1.86, "learning_rate": 4.076845622225274e-05, "loss": 2.3109, "step": 40840 }, { "epoch": 1.87, "learning_rate": 4.076616778799945e-05, "loss": 2.1689, "step": 40850 }, { "epoch": 1.87, "learning_rate": 4.0763879353746174e-05, "loss": 2.3369, "step": 40860 }, { "epoch": 1.87, "learning_rate": 4.076159091949289e-05, "loss": 2.2408, "step": 40870 }, { "epoch": 1.87, "learning_rate": 4.07593024852396e-05, "loss": 2.1601, "step": 40880 }, { "epoch": 1.87, "learning_rate": 4.075701405098632e-05, "loss": 2.1734, "step": 40890 }, { "epoch": 1.87, "learning_rate": 4.075472561673303e-05, "loss": 2.2952, "step": 40900 }, { "epoch": 1.87, "learning_rate": 4.0752437182479744e-05, "loss": 1.9399, "step": 40910 }, { "epoch": 1.87, "learning_rate": 4.0750148748226465e-05, "loss": 2.2201, "step": 40920 }, { "epoch": 1.87, "learning_rate": 4.074786031397318e-05, "loss": 2.1456, "step": 40930 }, { "epoch": 1.87, "learning_rate": 4.0745571879719893e-05, "loss": 2.2002, "step": 40940 }, { "epoch": 1.87, "learning_rate": 4.0743283445466614e-05, "loss": 2.1608, "step": 40950 }, { "epoch": 1.87, "learning_rate": 4.074099501121333e-05, "loss": 2.1772, "step": 40960 }, { "epoch": 1.87, "learning_rate": 4.073870657696004e-05, "loss": 2.3051, "step": 40970 }, { "epoch": 1.87, "learning_rate": 4.0736418142706764e-05, "loss": 2.1599, "step": 40980 }, { "epoch": 1.87, "learning_rate": 4.073412970845348e-05, "loss": 2.1776, "step": 40990 }, { "epoch": 1.87, "learning_rate": 4.073184127420019e-05, "loss": 2.1604, "step": 41000 }, { "epoch": 1.87, "learning_rate": 4.072955283994691e-05, "loss": 2.2789, "step": 41010 }, { "epoch": 1.87, "learning_rate": 4.072726440569363e-05, "loss": 2.0522, "step": 41020 }, { "epoch": 1.87, "learning_rate": 4.072497597144034e-05, "loss": 2.321, "step": 41030 }, { "epoch": 1.87, "learning_rate": 4.072268753718706e-05, "loss": 2.095, "step": 41040 }, { "epoch": 1.87, "learning_rate": 4.0720399102933776e-05, "loss": 2.0929, "step": 41050 }, { "epoch": 1.87, "learning_rate": 4.071811066868049e-05, "loss": 2.155, "step": 41060 }, { "epoch": 1.88, "learning_rate": 4.071582223442721e-05, "loss": 2.0571, "step": 41070 }, { "epoch": 1.88, "learning_rate": 4.0713533800173925e-05, "loss": 2.0904, "step": 41080 }, { "epoch": 1.88, "learning_rate": 4.071124536592064e-05, "loss": 2.1352, "step": 41090 }, { "epoch": 1.88, "learning_rate": 4.0708956931667353e-05, "loss": 2.1028, "step": 41100 }, { "epoch": 1.88, "learning_rate": 4.070666849741407e-05, "loss": 2.1843, "step": 41110 }, { "epoch": 1.88, "learning_rate": 4.070438006316079e-05, "loss": 2.2124, "step": 41120 }, { "epoch": 1.88, "learning_rate": 4.07020916289075e-05, "loss": 2.196, "step": 41130 }, { "epoch": 1.88, "learning_rate": 4.069980319465422e-05, "loss": 2.1451, "step": 41140 }, { "epoch": 1.88, "learning_rate": 4.069751476040094e-05, "loss": 2.134, "step": 41150 }, { "epoch": 1.88, "learning_rate": 4.069522632614765e-05, "loss": 2.1653, "step": 41160 }, { "epoch": 1.88, "learning_rate": 4.0692937891894366e-05, "loss": 2.0819, "step": 41170 }, { "epoch": 1.88, "learning_rate": 4.069064945764109e-05, "loss": 2.2897, "step": 41180 }, { "epoch": 1.88, "learning_rate": 4.06883610233878e-05, "loss": 2.2486, "step": 41190 }, { "epoch": 1.88, "learning_rate": 4.0686072589134515e-05, "loss": 2.0868, "step": 41200 }, { "epoch": 1.88, "learning_rate": 4.068378415488123e-05, "loss": 2.1501, "step": 41210 }, { "epoch": 1.88, "learning_rate": 4.068149572062795e-05, "loss": 2.1173, "step": 41220 }, { "epoch": 1.88, "learning_rate": 4.0679207286374664e-05, "loss": 2.186, "step": 41230 }, { "epoch": 1.88, "learning_rate": 4.067691885212138e-05, "loss": 2.0271, "step": 41240 }, { "epoch": 1.88, "learning_rate": 4.06746304178681e-05, "loss": 2.1019, "step": 41250 }, { "epoch": 1.88, "learning_rate": 4.0672341983614813e-05, "loss": 2.2641, "step": 41260 }, { "epoch": 1.88, "learning_rate": 4.067005354936153e-05, "loss": 2.3506, "step": 41270 }, { "epoch": 1.88, "learning_rate": 4.066776511510825e-05, "loss": 2.2779, "step": 41280 }, { "epoch": 1.89, "learning_rate": 4.066547668085496e-05, "loss": 2.1735, "step": 41290 }, { "epoch": 1.89, "learning_rate": 4.066318824660168e-05, "loss": 2.0886, "step": 41300 }, { "epoch": 1.89, "learning_rate": 4.066089981234839e-05, "loss": 2.1239, "step": 41310 }, { "epoch": 1.89, "learning_rate": 4.0658611378095105e-05, "loss": 2.0914, "step": 41320 }, { "epoch": 1.89, "learning_rate": 4.0656322943841826e-05, "loss": 2.008, "step": 41330 }, { "epoch": 1.89, "learning_rate": 4.065403450958854e-05, "loss": 2.1932, "step": 41340 }, { "epoch": 1.89, "learning_rate": 4.0651746075335254e-05, "loss": 2.1264, "step": 41350 }, { "epoch": 1.89, "learning_rate": 4.0649457641081975e-05, "loss": 2.1698, "step": 41360 }, { "epoch": 1.89, "learning_rate": 4.064716920682869e-05, "loss": 2.1825, "step": 41370 }, { "epoch": 1.89, "learning_rate": 4.0644880772575403e-05, "loss": 2.1819, "step": 41380 }, { "epoch": 1.89, "learning_rate": 4.0642592338322124e-05, "loss": 2.2344, "step": 41390 }, { "epoch": 1.89, "learning_rate": 4.064030390406884e-05, "loss": 2.1793, "step": 41400 }, { "epoch": 1.89, "learning_rate": 4.063801546981555e-05, "loss": 2.2194, "step": 41410 }, { "epoch": 1.89, "learning_rate": 4.0635727035562274e-05, "loss": 2.2396, "step": 41420 }, { "epoch": 1.89, "learning_rate": 4.063343860130899e-05, "loss": 2.1989, "step": 41430 }, { "epoch": 1.89, "learning_rate": 4.06311501670557e-05, "loss": 2.3601, "step": 41440 }, { "epoch": 1.89, "learning_rate": 4.062886173280242e-05, "loss": 1.9623, "step": 41450 }, { "epoch": 1.89, "learning_rate": 4.062657329854914e-05, "loss": 2.075, "step": 41460 }, { "epoch": 1.89, "learning_rate": 4.062428486429585e-05, "loss": 1.9238, "step": 41470 }, { "epoch": 1.89, "learning_rate": 4.062199643004257e-05, "loss": 2.263, "step": 41480 }, { "epoch": 1.89, "learning_rate": 4.0619707995789286e-05, "loss": 2.0658, "step": 41490 }, { "epoch": 1.89, "learning_rate": 4.061741956153599e-05, "loss": 2.1168, "step": 41500 }, { "epoch": 1.9, "learning_rate": 4.0615131127282714e-05, "loss": 2.1317, "step": 41510 }, { "epoch": 1.9, "learning_rate": 4.061284269302943e-05, "loss": 2.1668, "step": 41520 }, { "epoch": 1.9, "learning_rate": 4.061055425877614e-05, "loss": 2.1895, "step": 41530 }, { "epoch": 1.9, "learning_rate": 4.0608265824522863e-05, "loss": 2.262, "step": 41540 }, { "epoch": 1.9, "learning_rate": 4.060597739026958e-05, "loss": 2.1322, "step": 41550 }, { "epoch": 1.9, "learning_rate": 4.060368895601629e-05, "loss": 2.1052, "step": 41560 }, { "epoch": 1.9, "learning_rate": 4.060140052176301e-05, "loss": 2.0297, "step": 41570 }, { "epoch": 1.9, "learning_rate": 4.059911208750973e-05, "loss": 2.2143, "step": 41580 }, { "epoch": 1.9, "learning_rate": 4.059682365325644e-05, "loss": 2.2045, "step": 41590 }, { "epoch": 1.9, "learning_rate": 4.059453521900316e-05, "loss": 2.2069, "step": 41600 }, { "epoch": 1.9, "learning_rate": 4.0592246784749876e-05, "loss": 2.271, "step": 41610 }, { "epoch": 1.9, "learning_rate": 4.058995835049659e-05, "loss": 2.2968, "step": 41620 }, { "epoch": 1.9, "learning_rate": 4.058766991624331e-05, "loss": 2.1401, "step": 41630 }, { "epoch": 1.9, "learning_rate": 4.0585381481990025e-05, "loss": 2.2264, "step": 41640 }, { "epoch": 1.9, "learning_rate": 4.058309304773674e-05, "loss": 2.0847, "step": 41650 }, { "epoch": 1.9, "learning_rate": 4.058080461348346e-05, "loss": 2.0326, "step": 41660 }, { "epoch": 1.9, "learning_rate": 4.0578516179230174e-05, "loss": 2.2799, "step": 41670 }, { "epoch": 1.9, "learning_rate": 4.057622774497689e-05, "loss": 2.2376, "step": 41680 }, { "epoch": 1.9, "learning_rate": 4.05739393107236e-05, "loss": 2.1654, "step": 41690 }, { "epoch": 1.9, "learning_rate": 4.057165087647032e-05, "loss": 2.3227, "step": 41700 }, { "epoch": 1.9, "learning_rate": 4.056936244221704e-05, "loss": 2.2554, "step": 41710 }, { "epoch": 1.91, "learning_rate": 4.056707400796375e-05, "loss": 2.3792, "step": 41720 }, { "epoch": 1.91, "learning_rate": 4.0564785573710466e-05, "loss": 2.3129, "step": 41730 }, { "epoch": 1.91, "learning_rate": 4.056249713945719e-05, "loss": 2.1024, "step": 41740 }, { "epoch": 1.91, "learning_rate": 4.05602087052039e-05, "loss": 2.1059, "step": 41750 }, { "epoch": 1.91, "learning_rate": 4.0557920270950615e-05, "loss": 2.2981, "step": 41760 }, { "epoch": 1.91, "learning_rate": 4.0555631836697336e-05, "loss": 2.1928, "step": 41770 }, { "epoch": 1.91, "learning_rate": 4.055334340244405e-05, "loss": 2.1051, "step": 41780 }, { "epoch": 1.91, "learning_rate": 4.0551054968190764e-05, "loss": 2.2797, "step": 41790 }, { "epoch": 1.91, "learning_rate": 4.0548766533937485e-05, "loss": 2.2193, "step": 41800 }, { "epoch": 1.91, "learning_rate": 4.05464780996842e-05, "loss": 2.2066, "step": 41810 }, { "epoch": 1.91, "learning_rate": 4.0544189665430913e-05, "loss": 2.1929, "step": 41820 }, { "epoch": 1.91, "learning_rate": 4.0541901231177634e-05, "loss": 2.1573, "step": 41830 }, { "epoch": 1.91, "learning_rate": 4.053961279692435e-05, "loss": 2.1956, "step": 41840 }, { "epoch": 1.91, "learning_rate": 4.053732436267106e-05, "loss": 1.935, "step": 41850 }, { "epoch": 1.91, "learning_rate": 4.0535035928417783e-05, "loss": 2.2141, "step": 41860 }, { "epoch": 1.91, "learning_rate": 4.05327474941645e-05, "loss": 2.2606, "step": 41870 }, { "epoch": 1.91, "learning_rate": 4.053045905991121e-05, "loss": 2.2217, "step": 41880 }, { "epoch": 1.91, "learning_rate": 4.0528170625657926e-05, "loss": 2.0802, "step": 41890 }, { "epoch": 1.91, "learning_rate": 4.052588219140464e-05, "loss": 2.2091, "step": 41900 }, { "epoch": 1.91, "learning_rate": 4.0523593757151354e-05, "loss": 2.1483, "step": 41910 }, { "epoch": 1.91, "learning_rate": 4.0521305322898075e-05, "loss": 2.2593, "step": 41920 }, { "epoch": 1.91, "learning_rate": 4.051901688864479e-05, "loss": 2.1803, "step": 41930 }, { "epoch": 1.92, "learning_rate": 4.05167284543915e-05, "loss": 2.1456, "step": 41940 }, { "epoch": 1.92, "learning_rate": 4.0514440020138224e-05, "loss": 2.2124, "step": 41950 }, { "epoch": 1.92, "learning_rate": 4.051215158588494e-05, "loss": 2.2063, "step": 41960 }, { "epoch": 1.92, "learning_rate": 4.050986315163165e-05, "loss": 2.1647, "step": 41970 }, { "epoch": 1.92, "learning_rate": 4.0507574717378373e-05, "loss": 2.271, "step": 41980 }, { "epoch": 1.92, "learning_rate": 4.050528628312509e-05, "loss": 2.2953, "step": 41990 }, { "epoch": 1.92, "learning_rate": 4.05029978488718e-05, "loss": 2.0924, "step": 42000 }, { "epoch": 1.92, "learning_rate": 4.050070941461852e-05, "loss": 2.2126, "step": 42010 }, { "epoch": 1.92, "learning_rate": 4.049842098036524e-05, "loss": 2.1472, "step": 42020 }, { "epoch": 1.92, "learning_rate": 4.049613254611195e-05, "loss": 2.2973, "step": 42030 }, { "epoch": 1.92, "learning_rate": 4.049384411185867e-05, "loss": 2.1755, "step": 42040 }, { "epoch": 1.92, "learning_rate": 4.0491555677605386e-05, "loss": 2.1004, "step": 42050 }, { "epoch": 1.92, "learning_rate": 4.04892672433521e-05, "loss": 2.1743, "step": 42060 }, { "epoch": 1.92, "learning_rate": 4.048697880909882e-05, "loss": 2.133, "step": 42070 }, { "epoch": 1.92, "learning_rate": 4.0484690374845535e-05, "loss": 2.2284, "step": 42080 }, { "epoch": 1.92, "learning_rate": 4.048240194059225e-05, "loss": 2.1581, "step": 42090 }, { "epoch": 1.92, "learning_rate": 4.048011350633896e-05, "loss": 2.0399, "step": 42100 }, { "epoch": 1.92, "learning_rate": 4.047782507208568e-05, "loss": 2.1348, "step": 42110 }, { "epoch": 1.92, "learning_rate": 4.04755366378324e-05, "loss": 2.11, "step": 42120 }, { "epoch": 1.92, "learning_rate": 4.047324820357911e-05, "loss": 2.2469, "step": 42130 }, { "epoch": 1.92, "learning_rate": 4.047095976932583e-05, "loss": 2.0559, "step": 42140 }, { "epoch": 1.92, "learning_rate": 4.046867133507255e-05, "loss": 2.0875, "step": 42150 }, { "epoch": 1.93, "learning_rate": 4.046638290081926e-05, "loss": 2.1698, "step": 42160 }, { "epoch": 1.93, "learning_rate": 4.0464094466565976e-05, "loss": 2.1737, "step": 42170 }, { "epoch": 1.93, "learning_rate": 4.04618060323127e-05, "loss": 2.1845, "step": 42180 }, { "epoch": 1.93, "learning_rate": 4.045951759805941e-05, "loss": 2.2396, "step": 42190 }, { "epoch": 1.93, "learning_rate": 4.0457229163806125e-05, "loss": 2.2289, "step": 42200 }, { "epoch": 1.93, "learning_rate": 4.0454940729552846e-05, "loss": 2.1019, "step": 42210 }, { "epoch": 1.93, "learning_rate": 4.045265229529956e-05, "loss": 2.2465, "step": 42220 }, { "epoch": 1.93, "learning_rate": 4.0450363861046274e-05, "loss": 2.2288, "step": 42230 }, { "epoch": 1.93, "learning_rate": 4.0448075426792995e-05, "loss": 2.1658, "step": 42240 }, { "epoch": 1.93, "learning_rate": 4.044578699253971e-05, "loss": 2.1097, "step": 42250 }, { "epoch": 1.93, "learning_rate": 4.044349855828642e-05, "loss": 2.1222, "step": 42260 }, { "epoch": 1.93, "learning_rate": 4.0441210124033144e-05, "loss": 2.1101, "step": 42270 }, { "epoch": 1.93, "learning_rate": 4.043892168977986e-05, "loss": 2.1275, "step": 42280 }, { "epoch": 1.93, "learning_rate": 4.0436633255526566e-05, "loss": 2.0859, "step": 42290 }, { "epoch": 1.93, "learning_rate": 4.043434482127329e-05, "loss": 2.318, "step": 42300 }, { "epoch": 1.93, "learning_rate": 4.043205638702e-05, "loss": 2.2837, "step": 42310 }, { "epoch": 1.93, "learning_rate": 4.0429767952766715e-05, "loss": 2.1775, "step": 42320 }, { "epoch": 1.93, "learning_rate": 4.0427479518513436e-05, "loss": 2.0615, "step": 42330 }, { "epoch": 1.93, "learning_rate": 4.042519108426015e-05, "loss": 2.2154, "step": 42340 }, { "epoch": 1.93, "learning_rate": 4.0422902650006864e-05, "loss": 2.1451, "step": 42350 }, { "epoch": 1.93, "learning_rate": 4.0420614215753585e-05, "loss": 2.1243, "step": 42360 }, { "epoch": 1.93, "learning_rate": 4.04183257815003e-05, "loss": 2.2148, "step": 42370 }, { "epoch": 1.94, "learning_rate": 4.041603734724701e-05, "loss": 2.069, "step": 42380 }, { "epoch": 1.94, "learning_rate": 4.0413748912993734e-05, "loss": 2.0855, "step": 42390 }, { "epoch": 1.94, "learning_rate": 4.041146047874045e-05, "loss": 2.1651, "step": 42400 }, { "epoch": 1.94, "learning_rate": 4.040917204448716e-05, "loss": 2.1149, "step": 42410 }, { "epoch": 1.94, "learning_rate": 4.040688361023388e-05, "loss": 2.0369, "step": 42420 }, { "epoch": 1.94, "learning_rate": 4.04045951759806e-05, "loss": 2.1743, "step": 42430 }, { "epoch": 1.94, "learning_rate": 4.040230674172731e-05, "loss": 2.2409, "step": 42440 }, { "epoch": 1.94, "learning_rate": 4.040001830747403e-05, "loss": 2.2042, "step": 42450 }, { "epoch": 1.94, "learning_rate": 4.039772987322075e-05, "loss": 2.102, "step": 42460 }, { "epoch": 1.94, "learning_rate": 4.039544143896746e-05, "loss": 2.1773, "step": 42470 }, { "epoch": 1.94, "learning_rate": 4.0393153004714175e-05, "loss": 2.1278, "step": 42480 }, { "epoch": 1.94, "learning_rate": 4.039086457046089e-05, "loss": 2.1783, "step": 42490 }, { "epoch": 1.94, "learning_rate": 4.03885761362076e-05, "loss": 2.136, "step": 42500 }, { "epoch": 1.94, "learning_rate": 4.0386287701954324e-05, "loss": 2.2291, "step": 42510 }, { "epoch": 1.94, "learning_rate": 4.038399926770104e-05, "loss": 2.2806, "step": 42520 }, { "epoch": 1.94, "learning_rate": 4.038171083344775e-05, "loss": 2.0148, "step": 42530 }, { "epoch": 1.94, "learning_rate": 4.037942239919447e-05, "loss": 2.132, "step": 42540 }, { "epoch": 1.94, "learning_rate": 4.037713396494119e-05, "loss": 2.1012, "step": 42550 }, { "epoch": 1.94, "learning_rate": 4.03748455306879e-05, "loss": 2.3138, "step": 42560 }, { "epoch": 1.94, "learning_rate": 4.037255709643462e-05, "loss": 2.0724, "step": 42570 }, { "epoch": 1.94, "learning_rate": 4.037026866218134e-05, "loss": 2.1757, "step": 42580 }, { "epoch": 1.94, "learning_rate": 4.036798022792805e-05, "loss": 2.1914, "step": 42590 }, { "epoch": 1.95, "learning_rate": 4.036569179367477e-05, "loss": 2.3242, "step": 42600 }, { "epoch": 1.95, "learning_rate": 4.0363403359421486e-05, "loss": 2.036, "step": 42610 }, { "epoch": 1.95, "learning_rate": 4.03611149251682e-05, "loss": 2.1436, "step": 42620 }, { "epoch": 1.95, "learning_rate": 4.035882649091492e-05, "loss": 2.2428, "step": 42630 }, { "epoch": 1.95, "learning_rate": 4.0356538056661635e-05, "loss": 2.276, "step": 42640 }, { "epoch": 1.95, "learning_rate": 4.035424962240835e-05, "loss": 2.1018, "step": 42650 }, { "epoch": 1.95, "learning_rate": 4.035196118815507e-05, "loss": 2.1965, "step": 42660 }, { "epoch": 1.95, "learning_rate": 4.0349672753901784e-05, "loss": 2.0684, "step": 42670 }, { "epoch": 1.95, "learning_rate": 4.03473843196485e-05, "loss": 2.1227, "step": 42680 }, { "epoch": 1.95, "learning_rate": 4.034509588539521e-05, "loss": 2.3443, "step": 42690 }, { "epoch": 1.95, "learning_rate": 4.0342807451141927e-05, "loss": 2.2827, "step": 42700 }, { "epoch": 1.95, "learning_rate": 4.034051901688865e-05, "loss": 2.0952, "step": 42710 }, { "epoch": 1.95, "learning_rate": 4.033823058263536e-05, "loss": 2.2469, "step": 42720 }, { "epoch": 1.95, "learning_rate": 4.0335942148382076e-05, "loss": 2.2902, "step": 42730 }, { "epoch": 1.95, "learning_rate": 4.03336537141288e-05, "loss": 2.2257, "step": 42740 }, { "epoch": 1.95, "learning_rate": 4.033136527987551e-05, "loss": 2.2488, "step": 42750 }, { "epoch": 1.95, "learning_rate": 4.0329076845622225e-05, "loss": 2.0987, "step": 42760 }, { "epoch": 1.95, "learning_rate": 4.0326788411368946e-05, "loss": 2.126, "step": 42770 }, { "epoch": 1.95, "learning_rate": 4.032449997711566e-05, "loss": 2.2212, "step": 42780 }, { "epoch": 1.95, "learning_rate": 4.0322211542862374e-05, "loss": 2.3507, "step": 42790 }, { "epoch": 1.95, "learning_rate": 4.0319923108609095e-05, "loss": 2.0813, "step": 42800 }, { "epoch": 1.95, "learning_rate": 4.031763467435581e-05, "loss": 2.3978, "step": 42810 }, { "epoch": 1.96, "learning_rate": 4.031534624010252e-05, "loss": 2.1602, "step": 42820 }, { "epoch": 1.96, "learning_rate": 4.0313057805849244e-05, "loss": 2.1339, "step": 42830 }, { "epoch": 1.96, "learning_rate": 4.031076937159596e-05, "loss": 2.0304, "step": 42840 }, { "epoch": 1.96, "learning_rate": 4.030848093734267e-05, "loss": 2.0869, "step": 42850 }, { "epoch": 1.96, "learning_rate": 4.030619250308939e-05, "loss": 2.2148, "step": 42860 }, { "epoch": 1.96, "learning_rate": 4.030390406883611e-05, "loss": 2.1834, "step": 42870 }, { "epoch": 1.96, "learning_rate": 4.0301615634582815e-05, "loss": 2.097, "step": 42880 }, { "epoch": 1.96, "learning_rate": 4.0299327200329536e-05, "loss": 2.1508, "step": 42890 }, { "epoch": 1.96, "learning_rate": 4.029703876607625e-05, "loss": 2.0811, "step": 42900 }, { "epoch": 1.96, "learning_rate": 4.0294750331822964e-05, "loss": 2.1622, "step": 42910 }, { "epoch": 1.96, "learning_rate": 4.0292461897569685e-05, "loss": 2.2195, "step": 42920 }, { "epoch": 1.96, "learning_rate": 4.02901734633164e-05, "loss": 1.9694, "step": 42930 }, { "epoch": 1.96, "learning_rate": 4.028788502906311e-05, "loss": 2.189, "step": 42940 }, { "epoch": 1.96, "learning_rate": 4.0285596594809834e-05, "loss": 2.1618, "step": 42950 }, { "epoch": 1.96, "learning_rate": 4.028330816055655e-05, "loss": 2.0701, "step": 42960 }, { "epoch": 1.96, "learning_rate": 4.028101972630326e-05, "loss": 2.1099, "step": 42970 }, { "epoch": 1.96, "learning_rate": 4.027873129204998e-05, "loss": 2.1185, "step": 42980 }, { "epoch": 1.96, "learning_rate": 4.02764428577967e-05, "loss": 2.1593, "step": 42990 }, { "epoch": 1.96, "learning_rate": 4.027415442354341e-05, "loss": 2.2668, "step": 43000 }, { "epoch": 1.96, "learning_rate": 4.027186598929013e-05, "loss": 2.1767, "step": 43010 }, { "epoch": 1.96, "learning_rate": 4.0269577555036847e-05, "loss": 1.9759, "step": 43020 }, { "epoch": 1.96, "learning_rate": 4.026728912078356e-05, "loss": 2.1312, "step": 43030 }, { "epoch": 1.97, "learning_rate": 4.026500068653028e-05, "loss": 2.2567, "step": 43040 }, { "epoch": 1.97, "learning_rate": 4.0262712252276996e-05, "loss": 2.179, "step": 43050 }, { "epoch": 1.97, "learning_rate": 4.026042381802371e-05, "loss": 2.1749, "step": 43060 }, { "epoch": 1.97, "learning_rate": 4.025813538377043e-05, "loss": 2.1401, "step": 43070 }, { "epoch": 1.97, "learning_rate": 4.025584694951714e-05, "loss": 2.0947, "step": 43080 }, { "epoch": 1.97, "learning_rate": 4.025355851526386e-05, "loss": 2.0982, "step": 43090 }, { "epoch": 1.97, "learning_rate": 4.025127008101057e-05, "loss": 2.1486, "step": 43100 }, { "epoch": 1.97, "learning_rate": 4.024898164675729e-05, "loss": 2.2884, "step": 43110 }, { "epoch": 1.97, "learning_rate": 4.024669321250401e-05, "loss": 2.1366, "step": 43120 }, { "epoch": 1.97, "learning_rate": 4.024440477825072e-05, "loss": 2.2929, "step": 43130 }, { "epoch": 1.97, "learning_rate": 4.0242116343997437e-05, "loss": 2.1275, "step": 43140 }, { "epoch": 1.97, "learning_rate": 4.023982790974416e-05, "loss": 2.2499, "step": 43150 }, { "epoch": 1.97, "learning_rate": 4.023753947549087e-05, "loss": 2.0502, "step": 43160 }, { "epoch": 1.97, "learning_rate": 4.0235251041237586e-05, "loss": 2.3014, "step": 43170 }, { "epoch": 1.97, "learning_rate": 4.0232962606984307e-05, "loss": 2.1715, "step": 43180 }, { "epoch": 1.97, "learning_rate": 4.023067417273102e-05, "loss": 2.2232, "step": 43190 }, { "epoch": 1.97, "learning_rate": 4.0228385738477735e-05, "loss": 2.1736, "step": 43200 }, { "epoch": 1.97, "learning_rate": 4.0226097304224456e-05, "loss": 2.2551, "step": 43210 }, { "epoch": 1.97, "learning_rate": 4.022380886997117e-05, "loss": 2.1863, "step": 43220 }, { "epoch": 1.97, "learning_rate": 4.0221520435717884e-05, "loss": 2.2494, "step": 43230 }, { "epoch": 1.97, "learning_rate": 4.0219232001464605e-05, "loss": 2.1525, "step": 43240 }, { "epoch": 1.97, "learning_rate": 4.021694356721132e-05, "loss": 2.3265, "step": 43250 }, { "epoch": 1.98, "learning_rate": 4.021465513295803e-05, "loss": 2.143, "step": 43260 }, { "epoch": 1.98, "learning_rate": 4.021236669870475e-05, "loss": 2.1343, "step": 43270 }, { "epoch": 1.98, "learning_rate": 4.021007826445146e-05, "loss": 2.1842, "step": 43280 }, { "epoch": 1.98, "learning_rate": 4.0207789830198176e-05, "loss": 2.0956, "step": 43290 }, { "epoch": 1.98, "learning_rate": 4.0205501395944897e-05, "loss": 2.0382, "step": 43300 }, { "epoch": 1.98, "learning_rate": 4.020321296169161e-05, "loss": 2.1307, "step": 43310 }, { "epoch": 1.98, "learning_rate": 4.0200924527438325e-05, "loss": 2.1187, "step": 43320 }, { "epoch": 1.98, "learning_rate": 4.0198636093185046e-05, "loss": 2.1707, "step": 43330 }, { "epoch": 1.98, "learning_rate": 4.019634765893176e-05, "loss": 2.2502, "step": 43340 }, { "epoch": 1.98, "learning_rate": 4.0194059224678474e-05, "loss": 2.1841, "step": 43350 }, { "epoch": 1.98, "learning_rate": 4.0191770790425195e-05, "loss": 2.2334, "step": 43360 }, { "epoch": 1.98, "learning_rate": 4.018948235617191e-05, "loss": 2.2402, "step": 43370 }, { "epoch": 1.98, "learning_rate": 4.018719392191862e-05, "loss": 2.018, "step": 43380 }, { "epoch": 1.98, "learning_rate": 4.0184905487665344e-05, "loss": 2.289, "step": 43390 }, { "epoch": 1.98, "learning_rate": 4.018261705341206e-05, "loss": 2.083, "step": 43400 }, { "epoch": 1.98, "learning_rate": 4.018032861915877e-05, "loss": 2.3531, "step": 43410 }, { "epoch": 1.98, "learning_rate": 4.017804018490549e-05, "loss": 2.3687, "step": 43420 }, { "epoch": 1.98, "learning_rate": 4.017575175065221e-05, "loss": 2.0136, "step": 43430 }, { "epoch": 1.98, "learning_rate": 4.017346331639892e-05, "loss": 2.1535, "step": 43440 }, { "epoch": 1.98, "learning_rate": 4.017117488214564e-05, "loss": 2.2436, "step": 43450 }, { "epoch": 1.98, "learning_rate": 4.0168886447892357e-05, "loss": 2.1815, "step": 43460 }, { "epoch": 1.98, "learning_rate": 4.016659801363907e-05, "loss": 2.1548, "step": 43470 }, { "epoch": 1.99, "learning_rate": 4.0164309579385785e-05, "loss": 2.1483, "step": 43480 }, { "epoch": 1.99, "learning_rate": 4.01620211451325e-05, "loss": 2.1549, "step": 43490 }, { "epoch": 1.99, "learning_rate": 4.015973271087922e-05, "loss": 2.1957, "step": 43500 }, { "epoch": 1.99, "learning_rate": 4.0157444276625934e-05, "loss": 2.0927, "step": 43510 }, { "epoch": 1.99, "learning_rate": 4.015515584237265e-05, "loss": 2.174, "step": 43520 }, { "epoch": 1.99, "learning_rate": 4.015286740811936e-05, "loss": 2.2174, "step": 43530 }, { "epoch": 1.99, "learning_rate": 4.015057897386608e-05, "loss": 2.1236, "step": 43540 }, { "epoch": 1.99, "learning_rate": 4.01482905396128e-05, "loss": 2.2223, "step": 43550 }, { "epoch": 1.99, "learning_rate": 4.014600210535951e-05, "loss": 2.2651, "step": 43560 }, { "epoch": 1.99, "learning_rate": 4.014371367110623e-05, "loss": 2.0787, "step": 43570 }, { "epoch": 1.99, "learning_rate": 4.0141425236852946e-05, "loss": 2.1835, "step": 43580 }, { "epoch": 1.99, "learning_rate": 4.013913680259966e-05, "loss": 2.2235, "step": 43590 }, { "epoch": 1.99, "learning_rate": 4.013684836834638e-05, "loss": 2.0336, "step": 43600 }, { "epoch": 1.99, "learning_rate": 4.0134559934093096e-05, "loss": 2.1468, "step": 43610 }, { "epoch": 1.99, "learning_rate": 4.013227149983981e-05, "loss": 2.0611, "step": 43620 }, { "epoch": 1.99, "learning_rate": 4.012998306558653e-05, "loss": 2.0624, "step": 43630 }, { "epoch": 1.99, "learning_rate": 4.0127694631333245e-05, "loss": 2.1521, "step": 43640 }, { "epoch": 1.99, "learning_rate": 4.012540619707996e-05, "loss": 2.2589, "step": 43650 }, { "epoch": 1.99, "learning_rate": 4.012311776282668e-05, "loss": 2.107, "step": 43660 }, { "epoch": 1.99, "learning_rate": 4.012082932857339e-05, "loss": 2.2437, "step": 43670 }, { "epoch": 1.99, "learning_rate": 4.011854089432011e-05, "loss": 2.2924, "step": 43680 }, { "epoch": 1.99, "learning_rate": 4.011625246006682e-05, "loss": 2.1233, "step": 43690 }, { "epoch": 2.0, "learning_rate": 4.0113964025813536e-05, "loss": 2.253, "step": 43700 }, { "epoch": 2.0, "learning_rate": 4.011167559156026e-05, "loss": 2.2086, "step": 43710 }, { "epoch": 2.0, "learning_rate": 4.010938715730697e-05, "loss": 2.1554, "step": 43720 }, { "epoch": 2.0, "learning_rate": 4.0107098723053686e-05, "loss": 2.1081, "step": 43730 }, { "epoch": 2.0, "learning_rate": 4.0104810288800407e-05, "loss": 2.1347, "step": 43740 }, { "epoch": 2.0, "learning_rate": 4.010252185454712e-05, "loss": 2.1036, "step": 43750 }, { "epoch": 2.0, "learning_rate": 4.0100233420293835e-05, "loss": 2.3397, "step": 43760 }, { "epoch": 2.0, "learning_rate": 4.0097944986040556e-05, "loss": 2.2225, "step": 43770 }, { "epoch": 2.0, "learning_rate": 4.009565655178727e-05, "loss": 2.0911, "step": 43780 }, { "epoch": 2.0, "learning_rate": 4.0093368117533984e-05, "loss": 2.1875, "step": 43790 }, { "epoch": 2.0, "eval_cer": 0.680135419659455, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 2.0956878662109375, "eval_runtime": 2681.6756, "eval_samples_per_second": 3.942, "eval_steps_per_second": 1.971, "eval_wer": 0.9927152317880795, "step": 43799 }, { "epoch": 2.0, "learning_rate": 4.0091079683280705e-05, "loss": 2.0824, "step": 43800 }, { "epoch": 2.0, "learning_rate": 4.008879124902742e-05, "loss": 2.0975, "step": 43810 }, { "epoch": 2.0, "learning_rate": 4.008650281477413e-05, "loss": 2.072, "step": 43820 }, { "epoch": 2.0, "learning_rate": 4.0084214380520854e-05, "loss": 2.2314, "step": 43830 }, { "epoch": 2.0, "learning_rate": 4.008192594626757e-05, "loss": 2.2502, "step": 43840 }, { "epoch": 2.0, "learning_rate": 4.007963751201428e-05, "loss": 2.1179, "step": 43850 }, { "epoch": 2.0, "learning_rate": 4.0077349077761e-05, "loss": 2.3007, "step": 43860 }, { "epoch": 2.0, "learning_rate": 4.007506064350771e-05, "loss": 2.169, "step": 43870 }, { "epoch": 2.0, "learning_rate": 4.0072772209254425e-05, "loss": 2.1677, "step": 43880 }, { "epoch": 2.0, "learning_rate": 4.0070483775001146e-05, "loss": 2.2465, "step": 43890 }, { "epoch": 2.0, "learning_rate": 4.006819534074786e-05, "loss": 2.1642, "step": 43900 }, { "epoch": 2.01, "learning_rate": 4.0065906906494574e-05, "loss": 2.2268, "step": 43910 }, { "epoch": 2.01, "learning_rate": 4.0063618472241295e-05, "loss": 2.2367, "step": 43920 }, { "epoch": 2.01, "learning_rate": 4.006133003798801e-05, "loss": 2.0834, "step": 43930 }, { "epoch": 2.01, "learning_rate": 4.005904160373472e-05, "loss": 2.0745, "step": 43940 }, { "epoch": 2.01, "learning_rate": 4.0056753169481444e-05, "loss": 2.1512, "step": 43950 }, { "epoch": 2.01, "learning_rate": 4.005446473522816e-05, "loss": 2.2177, "step": 43960 }, { "epoch": 2.01, "learning_rate": 4.005217630097487e-05, "loss": 2.2005, "step": 43970 }, { "epoch": 2.01, "learning_rate": 4.004988786672159e-05, "loss": 1.9887, "step": 43980 }, { "epoch": 2.01, "learning_rate": 4.004759943246831e-05, "loss": 1.991, "step": 43990 }, { "epoch": 2.01, "learning_rate": 4.004531099821502e-05, "loss": 2.1212, "step": 44000 }, { "epoch": 2.01, "learning_rate": 4.004302256396174e-05, "loss": 2.3222, "step": 44010 }, { "epoch": 2.01, "learning_rate": 4.0040734129708456e-05, "loss": 2.104, "step": 44020 }, { "epoch": 2.01, "learning_rate": 4.003844569545517e-05, "loss": 2.0894, "step": 44030 }, { "epoch": 2.01, "learning_rate": 4.003615726120189e-05, "loss": 2.3192, "step": 44040 }, { "epoch": 2.01, "learning_rate": 4.0033868826948606e-05, "loss": 2.181, "step": 44050 }, { "epoch": 2.01, "learning_rate": 4.003158039269532e-05, "loss": 2.1385, "step": 44060 }, { "epoch": 2.01, "learning_rate": 4.0029291958442034e-05, "loss": 1.9691, "step": 44070 }, { "epoch": 2.01, "learning_rate": 4.002700352418875e-05, "loss": 2.1769, "step": 44080 }, { "epoch": 2.01, "learning_rate": 4.002471508993547e-05, "loss": 2.1824, "step": 44090 }, { "epoch": 2.01, "learning_rate": 4.002242665568218e-05, "loss": 2.1489, "step": 44100 }, { "epoch": 2.01, "learning_rate": 4.00201382214289e-05, "loss": 2.0934, "step": 44110 }, { "epoch": 2.01, "learning_rate": 4.001784978717562e-05, "loss": 2.1289, "step": 44120 }, { "epoch": 2.02, "learning_rate": 4.001556135292233e-05, "loss": 2.2097, "step": 44130 }, { "epoch": 2.02, "learning_rate": 4.0013272918669046e-05, "loss": 2.1217, "step": 44140 }, { "epoch": 2.02, "learning_rate": 4.001098448441577e-05, "loss": 2.0581, "step": 44150 }, { "epoch": 2.02, "learning_rate": 4.000869605016248e-05, "loss": 2.1744, "step": 44160 }, { "epoch": 2.02, "learning_rate": 4.0006407615909196e-05, "loss": 2.196, "step": 44170 }, { "epoch": 2.02, "learning_rate": 4.0004119181655916e-05, "loss": 2.1109, "step": 44180 }, { "epoch": 2.02, "learning_rate": 4.000183074740263e-05, "loss": 2.1401, "step": 44190 }, { "epoch": 2.02, "learning_rate": 3.9999542313149345e-05, "loss": 2.2061, "step": 44200 }, { "epoch": 2.02, "learning_rate": 3.9997253878896066e-05, "loss": 2.3454, "step": 44210 }, { "epoch": 2.02, "learning_rate": 3.999496544464278e-05, "loss": 2.1054, "step": 44220 }, { "epoch": 2.02, "learning_rate": 3.9992677010389494e-05, "loss": 2.1811, "step": 44230 }, { "epoch": 2.02, "learning_rate": 3.9990388576136215e-05, "loss": 2.084, "step": 44240 }, { "epoch": 2.02, "learning_rate": 3.998810014188293e-05, "loss": 2.0839, "step": 44250 }, { "epoch": 2.02, "learning_rate": 3.9985811707629636e-05, "loss": 2.1792, "step": 44260 }, { "epoch": 2.02, "learning_rate": 3.998352327337636e-05, "loss": 1.9619, "step": 44270 }, { "epoch": 2.02, "learning_rate": 3.998123483912307e-05, "loss": 2.1215, "step": 44280 }, { "epoch": 2.02, "learning_rate": 3.9978946404869785e-05, "loss": 2.1764, "step": 44290 }, { "epoch": 2.02, "learning_rate": 3.9976657970616506e-05, "loss": 2.1256, "step": 44300 }, { "epoch": 2.02, "learning_rate": 3.997436953636322e-05, "loss": 2.2723, "step": 44310 }, { "epoch": 2.02, "learning_rate": 3.9972081102109935e-05, "loss": 2.0026, "step": 44320 }, { "epoch": 2.02, "learning_rate": 3.9969792667856656e-05, "loss": 2.159, "step": 44330 }, { "epoch": 2.02, "learning_rate": 3.996750423360337e-05, "loss": 2.2046, "step": 44340 }, { "epoch": 2.03, "learning_rate": 3.9965215799350084e-05, "loss": 2.1284, "step": 44350 }, { "epoch": 2.03, "learning_rate": 3.9962927365096805e-05, "loss": 2.1626, "step": 44360 }, { "epoch": 2.03, "learning_rate": 3.996063893084352e-05, "loss": 2.2281, "step": 44370 }, { "epoch": 2.03, "learning_rate": 3.995835049659023e-05, "loss": 2.0704, "step": 44380 }, { "epoch": 2.03, "learning_rate": 3.9956062062336954e-05, "loss": 2.0499, "step": 44390 }, { "epoch": 2.03, "learning_rate": 3.995377362808367e-05, "loss": 2.106, "step": 44400 }, { "epoch": 2.03, "learning_rate": 3.995148519383038e-05, "loss": 2.0186, "step": 44410 }, { "epoch": 2.03, "learning_rate": 3.99491967595771e-05, "loss": 1.9985, "step": 44420 }, { "epoch": 2.03, "learning_rate": 3.994690832532382e-05, "loss": 2.3175, "step": 44430 }, { "epoch": 2.03, "learning_rate": 3.994461989107053e-05, "loss": 2.1271, "step": 44440 }, { "epoch": 2.03, "learning_rate": 3.994233145681725e-05, "loss": 2.245, "step": 44450 }, { "epoch": 2.03, "learning_rate": 3.994004302256396e-05, "loss": 2.2828, "step": 44460 }, { "epoch": 2.03, "learning_rate": 3.993775458831068e-05, "loss": 2.3191, "step": 44470 }, { "epoch": 2.03, "learning_rate": 3.9935466154057395e-05, "loss": 2.1465, "step": 44480 }, { "epoch": 2.03, "learning_rate": 3.993317771980411e-05, "loss": 2.0234, "step": 44490 }, { "epoch": 2.03, "learning_rate": 3.993088928555083e-05, "loss": 2.1456, "step": 44500 }, { "epoch": 2.03, "learning_rate": 3.9928600851297544e-05, "loss": 2.1204, "step": 44510 }, { "epoch": 2.03, "learning_rate": 3.992631241704426e-05, "loss": 2.2853, "step": 44520 }, { "epoch": 2.03, "learning_rate": 3.992402398279098e-05, "loss": 2.101, "step": 44530 }, { "epoch": 2.03, "learning_rate": 3.992173554853769e-05, "loss": 2.1555, "step": 44540 }, { "epoch": 2.03, "learning_rate": 3.991944711428441e-05, "loss": 2.1132, "step": 44550 }, { "epoch": 2.03, "learning_rate": 3.991715868003113e-05, "loss": 2.1557, "step": 44560 }, { "epoch": 2.04, "learning_rate": 3.991487024577784e-05, "loss": 2.1715, "step": 44570 }, { "epoch": 2.04, "learning_rate": 3.9912581811524556e-05, "loss": 2.3596, "step": 44580 }, { "epoch": 2.04, "learning_rate": 3.991029337727128e-05, "loss": 2.1364, "step": 44590 }, { "epoch": 2.04, "learning_rate": 3.990800494301799e-05, "loss": 2.0409, "step": 44600 }, { "epoch": 2.04, "learning_rate": 3.9905716508764706e-05, "loss": 2.1795, "step": 44610 }, { "epoch": 2.04, "learning_rate": 3.9903428074511426e-05, "loss": 2.0934, "step": 44620 }, { "epoch": 2.04, "learning_rate": 3.990113964025814e-05, "loss": 2.1155, "step": 44630 }, { "epoch": 2.04, "learning_rate": 3.9898851206004855e-05, "loss": 2.0261, "step": 44640 }, { "epoch": 2.04, "learning_rate": 3.989656277175157e-05, "loss": 2.0064, "step": 44650 }, { "epoch": 2.04, "learning_rate": 3.989427433749828e-05, "loss": 2.1169, "step": 44660 }, { "epoch": 2.04, "learning_rate": 3.9891985903245e-05, "loss": 2.1003, "step": 44670 }, { "epoch": 2.04, "learning_rate": 3.988969746899172e-05, "loss": 2.1662, "step": 44680 }, { "epoch": 2.04, "learning_rate": 3.988740903473843e-05, "loss": 2.1959, "step": 44690 }, { "epoch": 2.04, "learning_rate": 3.9885120600485146e-05, "loss": 2.0825, "step": 44700 }, { "epoch": 2.04, "learning_rate": 3.988283216623187e-05, "loss": 2.1862, "step": 44710 }, { "epoch": 2.04, "learning_rate": 3.988054373197858e-05, "loss": 2.1137, "step": 44720 }, { "epoch": 2.04, "learning_rate": 3.9878255297725295e-05, "loss": 2.0358, "step": 44730 }, { "epoch": 2.04, "learning_rate": 3.9875966863472016e-05, "loss": 1.996, "step": 44740 }, { "epoch": 2.04, "learning_rate": 3.987367842921873e-05, "loss": 2.1267, "step": 44750 }, { "epoch": 2.04, "learning_rate": 3.9871389994965445e-05, "loss": 2.1516, "step": 44760 }, { "epoch": 2.04, "learning_rate": 3.9869101560712166e-05, "loss": 2.0732, "step": 44770 }, { "epoch": 2.04, "learning_rate": 3.986681312645888e-05, "loss": 2.1107, "step": 44780 }, { "epoch": 2.05, "learning_rate": 3.9864524692205594e-05, "loss": 2.1604, "step": 44790 }, { "epoch": 2.05, "learning_rate": 3.9862236257952315e-05, "loss": 2.3174, "step": 44800 }, { "epoch": 2.05, "learning_rate": 3.985994782369903e-05, "loss": 2.1976, "step": 44810 }, { "epoch": 2.05, "learning_rate": 3.985765938944574e-05, "loss": 2.1824, "step": 44820 }, { "epoch": 2.05, "learning_rate": 3.9855370955192464e-05, "loss": 2.199, "step": 44830 }, { "epoch": 2.05, "learning_rate": 3.985308252093918e-05, "loss": 2.0689, "step": 44840 }, { "epoch": 2.05, "learning_rate": 3.9850794086685885e-05, "loss": 2.1862, "step": 44850 }, { "epoch": 2.05, "learning_rate": 3.9848505652432606e-05, "loss": 2.0667, "step": 44860 }, { "epoch": 2.05, "learning_rate": 3.984621721817932e-05, "loss": 2.1532, "step": 44870 }, { "epoch": 2.05, "learning_rate": 3.9843928783926035e-05, "loss": 2.2103, "step": 44880 }, { "epoch": 2.05, "learning_rate": 3.9841640349672755e-05, "loss": 2.3692, "step": 44890 }, { "epoch": 2.05, "learning_rate": 3.983935191541947e-05, "loss": 2.062, "step": 44900 }, { "epoch": 2.05, "learning_rate": 3.9837063481166184e-05, "loss": 2.0982, "step": 44910 }, { "epoch": 2.05, "learning_rate": 3.9834775046912905e-05, "loss": 2.2211, "step": 44920 }, { "epoch": 2.05, "learning_rate": 3.983248661265962e-05, "loss": 2.2034, "step": 44930 }, { "epoch": 2.05, "learning_rate": 3.983019817840633e-05, "loss": 2.3138, "step": 44940 }, { "epoch": 2.05, "learning_rate": 3.9827909744153054e-05, "loss": 2.028, "step": 44950 }, { "epoch": 2.05, "learning_rate": 3.982562130989977e-05, "loss": 2.3425, "step": 44960 }, { "epoch": 2.05, "learning_rate": 3.982333287564648e-05, "loss": 2.1936, "step": 44970 }, { "epoch": 2.05, "learning_rate": 3.98210444413932e-05, "loss": 2.252, "step": 44980 }, { "epoch": 2.05, "learning_rate": 3.981875600713992e-05, "loss": 2.1121, "step": 44990 }, { "epoch": 2.05, "learning_rate": 3.981646757288663e-05, "loss": 2.2297, "step": 45000 }, { "epoch": 2.06, "learning_rate": 3.981417913863335e-05, "loss": 2.119, "step": 45010 }, { "epoch": 2.06, "learning_rate": 3.9811890704380066e-05, "loss": 2.1037, "step": 45020 }, { "epoch": 2.06, "learning_rate": 3.980960227012678e-05, "loss": 2.1192, "step": 45030 }, { "epoch": 2.06, "learning_rate": 3.98073138358735e-05, "loss": 2.1231, "step": 45040 }, { "epoch": 2.06, "learning_rate": 3.980502540162021e-05, "loss": 2.1726, "step": 45050 }, { "epoch": 2.06, "learning_rate": 3.980273696736693e-05, "loss": 2.1799, "step": 45060 }, { "epoch": 2.06, "learning_rate": 3.9800448533113644e-05, "loss": 2.2705, "step": 45070 }, { "epoch": 2.06, "learning_rate": 3.979816009886036e-05, "loss": 2.1278, "step": 45080 }, { "epoch": 2.06, "learning_rate": 3.979587166460708e-05, "loss": 1.9545, "step": 45090 }, { "epoch": 2.06, "learning_rate": 3.979358323035379e-05, "loss": 1.9625, "step": 45100 }, { "epoch": 2.06, "learning_rate": 3.979129479610051e-05, "loss": 2.2301, "step": 45110 }, { "epoch": 2.06, "learning_rate": 3.978900636184723e-05, "loss": 2.1039, "step": 45120 }, { "epoch": 2.06, "learning_rate": 3.978671792759394e-05, "loss": 2.2411, "step": 45130 }, { "epoch": 2.06, "learning_rate": 3.9784429493340656e-05, "loss": 2.1483, "step": 45140 }, { "epoch": 2.06, "learning_rate": 3.978214105908738e-05, "loss": 2.0924, "step": 45150 }, { "epoch": 2.06, "learning_rate": 3.977985262483409e-05, "loss": 2.1481, "step": 45160 }, { "epoch": 2.06, "learning_rate": 3.9777564190580805e-05, "loss": 2.2596, "step": 45170 }, { "epoch": 2.06, "learning_rate": 3.9775275756327526e-05, "loss": 2.0692, "step": 45180 }, { "epoch": 2.06, "learning_rate": 3.977298732207424e-05, "loss": 2.1347, "step": 45190 }, { "epoch": 2.06, "learning_rate": 3.9770698887820955e-05, "loss": 2.0605, "step": 45200 }, { "epoch": 2.06, "learning_rate": 3.9768410453567676e-05, "loss": 2.2014, "step": 45210 }, { "epoch": 2.06, "learning_rate": 3.976612201931439e-05, "loss": 2.0224, "step": 45220 }, { "epoch": 2.07, "learning_rate": 3.9763833585061104e-05, "loss": 2.1528, "step": 45230 }, { "epoch": 2.07, "learning_rate": 3.9761545150807825e-05, "loss": 1.9948, "step": 45240 }, { "epoch": 2.07, "learning_rate": 3.975925671655453e-05, "loss": 2.1645, "step": 45250 }, { "epoch": 2.07, "learning_rate": 3.9756968282301246e-05, "loss": 2.0905, "step": 45260 }, { "epoch": 2.07, "learning_rate": 3.975467984804797e-05, "loss": 2.1509, "step": 45270 }, { "epoch": 2.07, "learning_rate": 3.975239141379468e-05, "loss": 1.948, "step": 45280 }, { "epoch": 2.07, "learning_rate": 3.9750102979541395e-05, "loss": 2.1609, "step": 45290 }, { "epoch": 2.07, "learning_rate": 3.9747814545288116e-05, "loss": 2.334, "step": 45300 }, { "epoch": 2.07, "learning_rate": 3.974552611103483e-05, "loss": 2.2749, "step": 45310 }, { "epoch": 2.07, "learning_rate": 3.9743237676781545e-05, "loss": 2.1643, "step": 45320 }, { "epoch": 2.07, "learning_rate": 3.9740949242528265e-05, "loss": 2.1466, "step": 45330 }, { "epoch": 2.07, "learning_rate": 3.973866080827498e-05, "loss": 2.2207, "step": 45340 }, { "epoch": 2.07, "learning_rate": 3.9736372374021694e-05, "loss": 2.1142, "step": 45350 }, { "epoch": 2.07, "learning_rate": 3.9734083939768415e-05, "loss": 2.3272, "step": 45360 }, { "epoch": 2.07, "learning_rate": 3.973179550551513e-05, "loss": 2.0211, "step": 45370 }, { "epoch": 2.07, "learning_rate": 3.972950707126184e-05, "loss": 2.1944, "step": 45380 }, { "epoch": 2.07, "learning_rate": 3.9727218637008564e-05, "loss": 2.0634, "step": 45390 }, { "epoch": 2.07, "learning_rate": 3.972493020275528e-05, "loss": 2.2625, "step": 45400 }, { "epoch": 2.07, "learning_rate": 3.972264176850199e-05, "loss": 2.2093, "step": 45410 }, { "epoch": 2.07, "learning_rate": 3.972035333424871e-05, "loss": 2.1535, "step": 45420 }, { "epoch": 2.07, "learning_rate": 3.971806489999543e-05, "loss": 2.0183, "step": 45430 }, { "epoch": 2.07, "learning_rate": 3.971577646574214e-05, "loss": 2.0473, "step": 45440 }, { "epoch": 2.08, "learning_rate": 3.9713488031488855e-05, "loss": 2.0315, "step": 45450 }, { "epoch": 2.08, "learning_rate": 3.971119959723557e-05, "loss": 2.0762, "step": 45460 }, { "epoch": 2.08, "learning_rate": 3.970891116298229e-05, "loss": 2.1161, "step": 45470 }, { "epoch": 2.08, "learning_rate": 3.9706622728729005e-05, "loss": 2.2961, "step": 45480 }, { "epoch": 2.08, "learning_rate": 3.970433429447572e-05, "loss": 2.1737, "step": 45490 }, { "epoch": 2.08, "learning_rate": 3.970204586022244e-05, "loss": 2.1566, "step": 45500 }, { "epoch": 2.08, "learning_rate": 3.9699757425969154e-05, "loss": 2.1689, "step": 45510 }, { "epoch": 2.08, "learning_rate": 3.969746899171587e-05, "loss": 2.1833, "step": 45520 }, { "epoch": 2.08, "learning_rate": 3.969518055746259e-05, "loss": 2.0842, "step": 45530 }, { "epoch": 2.08, "learning_rate": 3.96928921232093e-05, "loss": 2.1655, "step": 45540 }, { "epoch": 2.08, "learning_rate": 3.969060368895602e-05, "loss": 2.1792, "step": 45550 }, { "epoch": 2.08, "learning_rate": 3.968831525470274e-05, "loss": 2.1377, "step": 45560 }, { "epoch": 2.08, "learning_rate": 3.968602682044945e-05, "loss": 2.2155, "step": 45570 }, { "epoch": 2.08, "learning_rate": 3.9683738386196166e-05, "loss": 2.2346, "step": 45580 }, { "epoch": 2.08, "learning_rate": 3.968144995194289e-05, "loss": 1.9833, "step": 45590 }, { "epoch": 2.08, "learning_rate": 3.96791615176896e-05, "loss": 2.2621, "step": 45600 }, { "epoch": 2.08, "learning_rate": 3.9676873083436315e-05, "loss": 2.1878, "step": 45610 }, { "epoch": 2.08, "learning_rate": 3.9674584649183036e-05, "loss": 2.3811, "step": 45620 }, { "epoch": 2.08, "learning_rate": 3.967229621492975e-05, "loss": 2.1332, "step": 45630 }, { "epoch": 2.08, "learning_rate": 3.9670007780676465e-05, "loss": 2.308, "step": 45640 }, { "epoch": 2.08, "learning_rate": 3.966771934642318e-05, "loss": 2.1387, "step": 45650 }, { "epoch": 2.08, "learning_rate": 3.966543091216989e-05, "loss": 2.1826, "step": 45660 }, { "epoch": 2.09, "learning_rate": 3.966314247791661e-05, "loss": 2.0949, "step": 45670 }, { "epoch": 2.09, "learning_rate": 3.966085404366333e-05, "loss": 2.2074, "step": 45680 }, { "epoch": 2.09, "learning_rate": 3.965856560941004e-05, "loss": 2.0315, "step": 45690 }, { "epoch": 2.09, "learning_rate": 3.9656277175156756e-05, "loss": 2.0851, "step": 45700 }, { "epoch": 2.09, "learning_rate": 3.965398874090348e-05, "loss": 2.062, "step": 45710 }, { "epoch": 2.09, "learning_rate": 3.965170030665019e-05, "loss": 2.1987, "step": 45720 }, { "epoch": 2.09, "learning_rate": 3.9649411872396905e-05, "loss": 2.1804, "step": 45730 }, { "epoch": 2.09, "learning_rate": 3.9647123438143626e-05, "loss": 2.0934, "step": 45740 }, { "epoch": 2.09, "learning_rate": 3.964483500389034e-05, "loss": 2.0914, "step": 45750 }, { "epoch": 2.09, "learning_rate": 3.9642546569637055e-05, "loss": 2.2276, "step": 45760 }, { "epoch": 2.09, "learning_rate": 3.9640258135383775e-05, "loss": 2.0468, "step": 45770 }, { "epoch": 2.09, "learning_rate": 3.963796970113049e-05, "loss": 2.1854, "step": 45780 }, { "epoch": 2.09, "learning_rate": 3.9635681266877204e-05, "loss": 2.3278, "step": 45790 }, { "epoch": 2.09, "learning_rate": 3.9633392832623925e-05, "loss": 2.078, "step": 45800 }, { "epoch": 2.09, "learning_rate": 3.963110439837064e-05, "loss": 2.2223, "step": 45810 }, { "epoch": 2.09, "learning_rate": 3.962881596411735e-05, "loss": 2.2042, "step": 45820 }, { "epoch": 2.09, "learning_rate": 3.9626527529864074e-05, "loss": 2.171, "step": 45830 }, { "epoch": 2.09, "learning_rate": 3.962423909561078e-05, "loss": 2.076, "step": 45840 }, { "epoch": 2.09, "learning_rate": 3.96219506613575e-05, "loss": 2.1144, "step": 45850 }, { "epoch": 2.09, "learning_rate": 3.9619662227104216e-05, "loss": 2.192, "step": 45860 }, { "epoch": 2.09, "learning_rate": 3.961737379285093e-05, "loss": 2.0828, "step": 45870 }, { "epoch": 2.1, "learning_rate": 3.9615085358597644e-05, "loss": 2.0794, "step": 45880 }, { "epoch": 2.1, "learning_rate": 3.9612796924344365e-05, "loss": 2.0732, "step": 45890 }, { "epoch": 2.1, "learning_rate": 3.961050849009108e-05, "loss": 2.2191, "step": 45900 }, { "epoch": 2.1, "learning_rate": 3.9608220055837794e-05, "loss": 2.2302, "step": 45910 }, { "epoch": 2.1, "learning_rate": 3.9605931621584515e-05, "loss": 2.2355, "step": 45920 }, { "epoch": 2.1, "learning_rate": 3.960364318733123e-05, "loss": 1.9952, "step": 45930 }, { "epoch": 2.1, "learning_rate": 3.960135475307794e-05, "loss": 2.2322, "step": 45940 }, { "epoch": 2.1, "learning_rate": 3.9599066318824664e-05, "loss": 2.184, "step": 45950 }, { "epoch": 2.1, "learning_rate": 3.959677788457138e-05, "loss": 2.0968, "step": 45960 }, { "epoch": 2.1, "learning_rate": 3.959448945031809e-05, "loss": 2.1616, "step": 45970 }, { "epoch": 2.1, "learning_rate": 3.959220101606481e-05, "loss": 2.0894, "step": 45980 }, { "epoch": 2.1, "learning_rate": 3.958991258181153e-05, "loss": 2.1424, "step": 45990 }, { "epoch": 2.1, "learning_rate": 3.958762414755824e-05, "loss": 2.0612, "step": 46000 }, { "epoch": 2.1, "learning_rate": 3.958533571330496e-05, "loss": 2.1469, "step": 46010 }, { "epoch": 2.1, "learning_rate": 3.9583047279051676e-05, "loss": 2.0869, "step": 46020 }, { "epoch": 2.1, "learning_rate": 3.958075884479839e-05, "loss": 2.0592, "step": 46030 }, { "epoch": 2.1, "learning_rate": 3.9578470410545104e-05, "loss": 2.1708, "step": 46040 }, { "epoch": 2.1, "learning_rate": 3.957618197629182e-05, "loss": 2.2477, "step": 46050 }, { "epoch": 2.1, "learning_rate": 3.957389354203854e-05, "loss": 2.0173, "step": 46060 }, { "epoch": 2.1, "learning_rate": 3.9571605107785254e-05, "loss": 1.9694, "step": 46070 }, { "epoch": 2.1, "learning_rate": 3.956931667353197e-05, "loss": 2.0489, "step": 46080 }, { "epoch": 2.1, "learning_rate": 3.956702823927869e-05, "loss": 2.0912, "step": 46090 }, { "epoch": 2.11, "learning_rate": 3.95647398050254e-05, "loss": 1.98, "step": 46100 }, { "epoch": 2.11, "learning_rate": 3.956245137077212e-05, "loss": 2.0921, "step": 46110 }, { "epoch": 2.11, "learning_rate": 3.956016293651884e-05, "loss": 2.1479, "step": 46120 }, { "epoch": 2.11, "learning_rate": 3.955787450226555e-05, "loss": 2.2746, "step": 46130 }, { "epoch": 2.11, "learning_rate": 3.9555586068012266e-05, "loss": 2.2822, "step": 46140 }, { "epoch": 2.11, "learning_rate": 3.955329763375899e-05, "loss": 2.089, "step": 46150 }, { "epoch": 2.11, "learning_rate": 3.95510091995057e-05, "loss": 2.1533, "step": 46160 }, { "epoch": 2.11, "learning_rate": 3.9548720765252415e-05, "loss": 2.2284, "step": 46170 }, { "epoch": 2.11, "learning_rate": 3.9546432330999136e-05, "loss": 2.1687, "step": 46180 }, { "epoch": 2.11, "learning_rate": 3.954414389674585e-05, "loss": 2.0608, "step": 46190 }, { "epoch": 2.11, "learning_rate": 3.9541855462492564e-05, "loss": 2.0276, "step": 46200 }, { "epoch": 2.11, "learning_rate": 3.9539567028239285e-05, "loss": 2.1002, "step": 46210 }, { "epoch": 2.11, "learning_rate": 3.9537278593986e-05, "loss": 2.2135, "step": 46220 }, { "epoch": 2.11, "learning_rate": 3.9534990159732714e-05, "loss": 2.1212, "step": 46230 }, { "epoch": 2.11, "learning_rate": 3.953270172547943e-05, "loss": 2.1821, "step": 46240 }, { "epoch": 2.11, "learning_rate": 3.953041329122614e-05, "loss": 2.3007, "step": 46250 }, { "epoch": 2.11, "learning_rate": 3.9528124856972856e-05, "loss": 1.916, "step": 46260 }, { "epoch": 2.11, "learning_rate": 3.952583642271958e-05, "loss": 2.1515, "step": 46270 }, { "epoch": 2.11, "learning_rate": 3.952354798846629e-05, "loss": 2.2486, "step": 46280 }, { "epoch": 2.11, "learning_rate": 3.9521259554213005e-05, "loss": 2.1519, "step": 46290 }, { "epoch": 2.11, "learning_rate": 3.9518971119959726e-05, "loss": 2.1047, "step": 46300 }, { "epoch": 2.11, "learning_rate": 3.951668268570644e-05, "loss": 2.183, "step": 46310 }, { "epoch": 2.12, "learning_rate": 3.9514394251453154e-05, "loss": 2.1666, "step": 46320 }, { "epoch": 2.12, "learning_rate": 3.9512105817199875e-05, "loss": 2.1896, "step": 46330 }, { "epoch": 2.12, "learning_rate": 3.950981738294659e-05, "loss": 2.1313, "step": 46340 }, { "epoch": 2.12, "learning_rate": 3.9507528948693304e-05, "loss": 1.9495, "step": 46350 }, { "epoch": 2.12, "learning_rate": 3.9505240514440024e-05, "loss": 2.3028, "step": 46360 }, { "epoch": 2.12, "learning_rate": 3.950295208018674e-05, "loss": 1.9351, "step": 46370 }, { "epoch": 2.12, "learning_rate": 3.950066364593345e-05, "loss": 2.1644, "step": 46380 }, { "epoch": 2.12, "learning_rate": 3.9498375211680174e-05, "loss": 2.1149, "step": 46390 }, { "epoch": 2.12, "learning_rate": 3.949608677742689e-05, "loss": 2.1061, "step": 46400 }, { "epoch": 2.12, "learning_rate": 3.94937983431736e-05, "loss": 2.2001, "step": 46410 }, { "epoch": 2.12, "learning_rate": 3.949150990892032e-05, "loss": 2.188, "step": 46420 }, { "epoch": 2.12, "learning_rate": 3.948922147466704e-05, "loss": 2.2021, "step": 46430 }, { "epoch": 2.12, "learning_rate": 3.948693304041375e-05, "loss": 2.168, "step": 46440 }, { "epoch": 2.12, "learning_rate": 3.9484644606160465e-05, "loss": 2.1711, "step": 46450 }, { "epoch": 2.12, "learning_rate": 3.948235617190718e-05, "loss": 2.1633, "step": 46460 }, { "epoch": 2.12, "learning_rate": 3.94800677376539e-05, "loss": 2.1563, "step": 46470 }, { "epoch": 2.12, "learning_rate": 3.9477779303400614e-05, "loss": 2.08, "step": 46480 }, { "epoch": 2.12, "learning_rate": 3.947549086914733e-05, "loss": 2.2079, "step": 46490 }, { "epoch": 2.12, "learning_rate": 3.947320243489405e-05, "loss": 2.0304, "step": 46500 }, { "epoch": 2.12, "learning_rate": 3.9470914000640764e-05, "loss": 2.0191, "step": 46510 }, { "epoch": 2.12, "learning_rate": 3.946862556638748e-05, "loss": 2.084, "step": 46520 }, { "epoch": 2.12, "learning_rate": 3.94663371321342e-05, "loss": 2.0885, "step": 46530 }, { "epoch": 2.13, "learning_rate": 3.946404869788091e-05, "loss": 2.4494, "step": 46540 }, { "epoch": 2.13, "learning_rate": 3.946176026362763e-05, "loss": 1.9912, "step": 46550 }, { "epoch": 2.13, "learning_rate": 3.945947182937435e-05, "loss": 2.1939, "step": 46560 }, { "epoch": 2.13, "learning_rate": 3.945718339512106e-05, "loss": 2.0044, "step": 46570 }, { "epoch": 2.13, "learning_rate": 3.9454894960867776e-05, "loss": 2.1658, "step": 46580 }, { "epoch": 2.13, "learning_rate": 3.94526065266145e-05, "loss": 2.2431, "step": 46590 }, { "epoch": 2.13, "learning_rate": 3.945031809236121e-05, "loss": 2.0955, "step": 46600 }, { "epoch": 2.13, "learning_rate": 3.9448029658107925e-05, "loss": 2.045, "step": 46610 }, { "epoch": 2.13, "learning_rate": 3.9445741223854646e-05, "loss": 2.1032, "step": 46620 }, { "epoch": 2.13, "learning_rate": 3.9443452789601354e-05, "loss": 2.0446, "step": 46630 }, { "epoch": 2.13, "learning_rate": 3.944116435534807e-05, "loss": 2.0986, "step": 46640 }, { "epoch": 2.13, "learning_rate": 3.943887592109479e-05, "loss": 1.9765, "step": 46650 }, { "epoch": 2.13, "learning_rate": 3.94365874868415e-05, "loss": 2.148, "step": 46660 }, { "epoch": 2.13, "learning_rate": 3.943429905258822e-05, "loss": 1.9933, "step": 46670 }, { "epoch": 2.13, "learning_rate": 3.943201061833494e-05, "loss": 2.0963, "step": 46680 }, { "epoch": 2.13, "learning_rate": 3.942972218408165e-05, "loss": 2.0708, "step": 46690 }, { "epoch": 2.13, "learning_rate": 3.9427433749828366e-05, "loss": 1.9849, "step": 46700 }, { "epoch": 2.13, "learning_rate": 3.942514531557509e-05, "loss": 2.1121, "step": 46710 }, { "epoch": 2.13, "learning_rate": 3.94228568813218e-05, "loss": 2.1779, "step": 46720 }, { "epoch": 2.13, "learning_rate": 3.9420568447068515e-05, "loss": 2.2018, "step": 46730 }, { "epoch": 2.13, "learning_rate": 3.9418280012815236e-05, "loss": 2.2037, "step": 46740 }, { "epoch": 2.13, "learning_rate": 3.941599157856195e-05, "loss": 2.2241, "step": 46750 }, { "epoch": 2.14, "learning_rate": 3.9413703144308664e-05, "loss": 2.0505, "step": 46760 }, { "epoch": 2.14, "learning_rate": 3.9411414710055385e-05, "loss": 2.183, "step": 46770 }, { "epoch": 2.14, "learning_rate": 3.94091262758021e-05, "loss": 1.9746, "step": 46780 }, { "epoch": 2.14, "learning_rate": 3.9406837841548814e-05, "loss": 2.1633, "step": 46790 }, { "epoch": 2.14, "learning_rate": 3.9404549407295534e-05, "loss": 2.1057, "step": 46800 }, { "epoch": 2.14, "learning_rate": 3.940226097304225e-05, "loss": 2.1056, "step": 46810 }, { "epoch": 2.14, "learning_rate": 3.939997253878896e-05, "loss": 2.199, "step": 46820 }, { "epoch": 2.14, "learning_rate": 3.939768410453568e-05, "loss": 2.1512, "step": 46830 }, { "epoch": 2.14, "learning_rate": 3.939539567028239e-05, "loss": 2.0565, "step": 46840 }, { "epoch": 2.14, "learning_rate": 3.939310723602911e-05, "loss": 2.336, "step": 46850 }, { "epoch": 2.14, "learning_rate": 3.9390818801775826e-05, "loss": 1.9625, "step": 46860 }, { "epoch": 2.14, "learning_rate": 3.938853036752254e-05, "loss": 2.1365, "step": 46870 }, { "epoch": 2.14, "learning_rate": 3.938624193326926e-05, "loss": 2.1577, "step": 46880 }, { "epoch": 2.14, "learning_rate": 3.9383953499015975e-05, "loss": 2.1248, "step": 46890 }, { "epoch": 2.14, "learning_rate": 3.938166506476269e-05, "loss": 2.2234, "step": 46900 }, { "epoch": 2.14, "learning_rate": 3.937937663050941e-05, "loss": 2.1015, "step": 46910 }, { "epoch": 2.14, "learning_rate": 3.9377088196256124e-05, "loss": 2.0193, "step": 46920 }, { "epoch": 2.14, "learning_rate": 3.937479976200284e-05, "loss": 2.2665, "step": 46930 }, { "epoch": 2.14, "learning_rate": 3.937251132774956e-05, "loss": 2.1795, "step": 46940 }, { "epoch": 2.14, "learning_rate": 3.9370222893496274e-05, "loss": 2.0992, "step": 46950 }, { "epoch": 2.14, "learning_rate": 3.936793445924299e-05, "loss": 2.1763, "step": 46960 }, { "epoch": 2.14, "learning_rate": 3.93656460249897e-05, "loss": 2.1102, "step": 46970 }, { "epoch": 2.15, "learning_rate": 3.936335759073642e-05, "loss": 2.2672, "step": 46980 }, { "epoch": 2.15, "learning_rate": 3.936106915648314e-05, "loss": 2.1492, "step": 46990 }, { "epoch": 2.15, "learning_rate": 3.935878072222985e-05, "loss": 2.0534, "step": 47000 }, { "epoch": 2.15, "learning_rate": 3.935649228797657e-05, "loss": 2.1169, "step": 47010 }, { "epoch": 2.15, "learning_rate": 3.9354203853723286e-05, "loss": 2.2396, "step": 47020 }, { "epoch": 2.15, "learning_rate": 3.935191541947e-05, "loss": 2.0358, "step": 47030 }, { "epoch": 2.15, "learning_rate": 3.9349626985216714e-05, "loss": 2.2458, "step": 47040 }, { "epoch": 2.15, "learning_rate": 3.934733855096343e-05, "loss": 2.2688, "step": 47050 }, { "epoch": 2.15, "learning_rate": 3.934505011671015e-05, "loss": 2.0575, "step": 47060 }, { "epoch": 2.15, "learning_rate": 3.9342761682456864e-05, "loss": 2.1679, "step": 47070 }, { "epoch": 2.15, "learning_rate": 3.934047324820358e-05, "loss": 2.1876, "step": 47080 }, { "epoch": 2.15, "learning_rate": 3.93381848139503e-05, "loss": 2.1035, "step": 47090 }, { "epoch": 2.15, "learning_rate": 3.933589637969701e-05, "loss": 2.108, "step": 47100 }, { "epoch": 2.15, "learning_rate": 3.933360794544373e-05, "loss": 2.0643, "step": 47110 }, { "epoch": 2.15, "learning_rate": 3.933131951119045e-05, "loss": 2.2889, "step": 47120 }, { "epoch": 2.15, "learning_rate": 3.932903107693716e-05, "loss": 2.2607, "step": 47130 }, { "epoch": 2.15, "learning_rate": 3.9326742642683876e-05, "loss": 2.0844, "step": 47140 }, { "epoch": 2.15, "learning_rate": 3.93244542084306e-05, "loss": 2.2411, "step": 47150 }, { "epoch": 2.15, "learning_rate": 3.932216577417731e-05, "loss": 2.102, "step": 47160 }, { "epoch": 2.15, "learning_rate": 3.9319877339924025e-05, "loss": 2.0864, "step": 47170 }, { "epoch": 2.15, "learning_rate": 3.9317588905670746e-05, "loss": 2.14, "step": 47180 }, { "epoch": 2.15, "learning_rate": 3.931530047141746e-05, "loss": 2.1261, "step": 47190 }, { "epoch": 2.16, "learning_rate": 3.9313012037164174e-05, "loss": 2.1892, "step": 47200 }, { "epoch": 2.16, "learning_rate": 3.9310723602910895e-05, "loss": 2.2853, "step": 47210 }, { "epoch": 2.16, "learning_rate": 3.930843516865761e-05, "loss": 2.0877, "step": 47220 }, { "epoch": 2.16, "learning_rate": 3.930614673440432e-05, "loss": 2.0588, "step": 47230 }, { "epoch": 2.16, "learning_rate": 3.930385830015104e-05, "loss": 2.0616, "step": 47240 }, { "epoch": 2.16, "learning_rate": 3.930156986589775e-05, "loss": 2.1913, "step": 47250 }, { "epoch": 2.16, "learning_rate": 3.9299281431644466e-05, "loss": 2.2928, "step": 47260 }, { "epoch": 2.16, "learning_rate": 3.929699299739119e-05, "loss": 2.1583, "step": 47270 }, { "epoch": 2.16, "learning_rate": 3.92947045631379e-05, "loss": 1.9818, "step": 47280 }, { "epoch": 2.16, "learning_rate": 3.9292416128884615e-05, "loss": 2.0686, "step": 47290 }, { "epoch": 2.16, "learning_rate": 3.9290127694631336e-05, "loss": 2.1113, "step": 47300 }, { "epoch": 2.16, "learning_rate": 3.928783926037805e-05, "loss": 2.1187, "step": 47310 }, { "epoch": 2.16, "learning_rate": 3.9285550826124764e-05, "loss": 2.1455, "step": 47320 }, { "epoch": 2.16, "learning_rate": 3.9283262391871485e-05, "loss": 2.0668, "step": 47330 }, { "epoch": 2.16, "learning_rate": 3.92809739576182e-05, "loss": 2.131, "step": 47340 }, { "epoch": 2.16, "learning_rate": 3.9278685523364913e-05, "loss": 2.1087, "step": 47350 }, { "epoch": 2.16, "learning_rate": 3.9276397089111634e-05, "loss": 2.0695, "step": 47360 }, { "epoch": 2.16, "learning_rate": 3.927410865485835e-05, "loss": 2.0888, "step": 47370 }, { "epoch": 2.16, "learning_rate": 3.927182022060506e-05, "loss": 2.1095, "step": 47380 }, { "epoch": 2.16, "learning_rate": 3.9269531786351784e-05, "loss": 2.058, "step": 47390 }, { "epoch": 2.16, "learning_rate": 3.92672433520985e-05, "loss": 2.0828, "step": 47400 }, { "epoch": 2.16, "learning_rate": 3.926495491784521e-05, "loss": 2.0943, "step": 47410 }, { "epoch": 2.17, "learning_rate": 3.9262666483591926e-05, "loss": 2.0832, "step": 47420 }, { "epoch": 2.17, "learning_rate": 3.926037804933864e-05, "loss": 2.1438, "step": 47430 }, { "epoch": 2.17, "learning_rate": 3.925808961508536e-05, "loss": 2.208, "step": 47440 }, { "epoch": 2.17, "learning_rate": 3.9255801180832075e-05, "loss": 2.0617, "step": 47450 }, { "epoch": 2.17, "learning_rate": 3.925351274657879e-05, "loss": 2.2469, "step": 47460 }, { "epoch": 2.17, "learning_rate": 3.925122431232551e-05, "loss": 2.1523, "step": 47470 }, { "epoch": 2.17, "learning_rate": 3.9248935878072224e-05, "loss": 2.1755, "step": 47480 }, { "epoch": 2.17, "learning_rate": 3.924664744381894e-05, "loss": 2.0853, "step": 47490 }, { "epoch": 2.17, "learning_rate": 3.924435900956566e-05, "loss": 2.1138, "step": 47500 }, { "epoch": 2.17, "learning_rate": 3.9242070575312373e-05, "loss": 2.0663, "step": 47510 }, { "epoch": 2.17, "learning_rate": 3.923978214105909e-05, "loss": 2.0726, "step": 47520 }, { "epoch": 2.17, "learning_rate": 3.923749370680581e-05, "loss": 2.1378, "step": 47530 }, { "epoch": 2.17, "learning_rate": 3.923520527255252e-05, "loss": 2.1881, "step": 47540 }, { "epoch": 2.17, "learning_rate": 3.923291683829924e-05, "loss": 2.0748, "step": 47550 }, { "epoch": 2.17, "learning_rate": 3.923062840404596e-05, "loss": 2.0349, "step": 47560 }, { "epoch": 2.17, "learning_rate": 3.922833996979267e-05, "loss": 2.1296, "step": 47570 }, { "epoch": 2.17, "learning_rate": 3.9226051535539386e-05, "loss": 2.0947, "step": 47580 }, { "epoch": 2.17, "learning_rate": 3.922376310128611e-05, "loss": 2.1624, "step": 47590 }, { "epoch": 2.17, "learning_rate": 3.922147466703282e-05, "loss": 2.1433, "step": 47600 }, { "epoch": 2.17, "learning_rate": 3.9219186232779535e-05, "loss": 2.1529, "step": 47610 }, { "epoch": 2.17, "learning_rate": 3.921689779852625e-05, "loss": 2.02, "step": 47620 }, { "epoch": 2.17, "learning_rate": 3.9214609364272963e-05, "loss": 2.1945, "step": 47630 }, { "epoch": 2.18, "learning_rate": 3.921232093001968e-05, "loss": 2.0972, "step": 47640 }, { "epoch": 2.18, "learning_rate": 3.92100324957664e-05, "loss": 2.1141, "step": 47650 }, { "epoch": 2.18, "learning_rate": 3.920774406151311e-05, "loss": 2.0805, "step": 47660 }, { "epoch": 2.18, "learning_rate": 3.920545562725983e-05, "loss": 2.0256, "step": 47670 }, { "epoch": 2.18, "learning_rate": 3.920316719300655e-05, "loss": 2.13, "step": 47680 }, { "epoch": 2.18, "learning_rate": 3.920087875875326e-05, "loss": 2.0583, "step": 47690 }, { "epoch": 2.18, "learning_rate": 3.9198590324499976e-05, "loss": 2.0189, "step": 47700 }, { "epoch": 2.18, "learning_rate": 3.91963018902467e-05, "loss": 2.0563, "step": 47710 }, { "epoch": 2.18, "learning_rate": 3.919401345599341e-05, "loss": 1.9533, "step": 47720 }, { "epoch": 2.18, "learning_rate": 3.9191725021740125e-05, "loss": 2.15, "step": 47730 }, { "epoch": 2.18, "learning_rate": 3.9189436587486846e-05, "loss": 2.3775, "step": 47740 }, { "epoch": 2.18, "learning_rate": 3.918714815323356e-05, "loss": 2.1496, "step": 47750 }, { "epoch": 2.18, "learning_rate": 3.9184859718980274e-05, "loss": 2.1677, "step": 47760 }, { "epoch": 2.18, "learning_rate": 3.9182571284726995e-05, "loss": 2.1913, "step": 47770 }, { "epoch": 2.18, "learning_rate": 3.918028285047371e-05, "loss": 2.0715, "step": 47780 }, { "epoch": 2.18, "learning_rate": 3.9177994416220423e-05, "loss": 2.005, "step": 47790 }, { "epoch": 2.18, "learning_rate": 3.9175705981967144e-05, "loss": 2.1421, "step": 47800 }, { "epoch": 2.18, "learning_rate": 3.917341754771386e-05, "loss": 2.0597, "step": 47810 }, { "epoch": 2.18, "learning_rate": 3.917112911346057e-05, "loss": 2.2259, "step": 47820 }, { "epoch": 2.18, "learning_rate": 3.916884067920729e-05, "loss": 2.2441, "step": 47830 }, { "epoch": 2.18, "learning_rate": 3.9166552244954e-05, "loss": 2.2166, "step": 47840 }, { "epoch": 2.18, "learning_rate": 3.916426381070072e-05, "loss": 2.1592, "step": 47850 }, { "epoch": 2.19, "learning_rate": 3.9161975376447436e-05, "loss": 2.2402, "step": 47860 }, { "epoch": 2.19, "learning_rate": 3.915968694219415e-05, "loss": 2.0995, "step": 47870 }, { "epoch": 2.19, "learning_rate": 3.915739850794087e-05, "loss": 2.0449, "step": 47880 }, { "epoch": 2.19, "learning_rate": 3.9155110073687585e-05, "loss": 2.0431, "step": 47890 }, { "epoch": 2.19, "learning_rate": 3.91528216394343e-05, "loss": 2.2361, "step": 47900 }, { "epoch": 2.19, "learning_rate": 3.915053320518102e-05, "loss": 2.0709, "step": 47910 }, { "epoch": 2.19, "learning_rate": 3.9148244770927734e-05, "loss": 2.2261, "step": 47920 }, { "epoch": 2.19, "learning_rate": 3.914595633667445e-05, "loss": 2.2203, "step": 47930 }, { "epoch": 2.19, "learning_rate": 3.914366790242117e-05, "loss": 2.2139, "step": 47940 }, { "epoch": 2.19, "learning_rate": 3.9141379468167883e-05, "loss": 2.1782, "step": 47950 }, { "epoch": 2.19, "learning_rate": 3.91390910339146e-05, "loss": 2.0185, "step": 47960 }, { "epoch": 2.19, "learning_rate": 3.913680259966132e-05, "loss": 1.9839, "step": 47970 }, { "epoch": 2.19, "learning_rate": 3.913451416540803e-05, "loss": 2.0227, "step": 47980 }, { "epoch": 2.19, "learning_rate": 3.913222573115475e-05, "loss": 2.0011, "step": 47990 }, { "epoch": 2.19, "learning_rate": 3.912993729690147e-05, "loss": 2.1363, "step": 48000 }, { "epoch": 2.19, "learning_rate": 3.912764886264818e-05, "loss": 2.1902, "step": 48010 }, { "epoch": 2.19, "learning_rate": 3.912536042839489e-05, "loss": 2.0656, "step": 48020 }, { "epoch": 2.19, "learning_rate": 3.912307199414161e-05, "loss": 2.0047, "step": 48030 }, { "epoch": 2.19, "learning_rate": 3.9120783559888324e-05, "loss": 2.1921, "step": 48040 }, { "epoch": 2.19, "learning_rate": 3.911849512563504e-05, "loss": 2.0716, "step": 48050 }, { "epoch": 2.19, "learning_rate": 3.911620669138176e-05, "loss": 2.0419, "step": 48060 }, { "epoch": 2.2, "learning_rate": 3.911391825712847e-05, "loss": 2.0318, "step": 48070 }, { "epoch": 2.2, "learning_rate": 3.911162982287519e-05, "loss": 2.2327, "step": 48080 }, { "epoch": 2.2, "learning_rate": 3.910934138862191e-05, "loss": 2.1396, "step": 48090 }, { "epoch": 2.2, "learning_rate": 3.910705295436862e-05, "loss": 2.0711, "step": 48100 }, { "epoch": 2.2, "learning_rate": 3.910476452011534e-05, "loss": 2.1159, "step": 48110 }, { "epoch": 2.2, "learning_rate": 3.910247608586206e-05, "loss": 2.1339, "step": 48120 }, { "epoch": 2.2, "learning_rate": 3.910018765160877e-05, "loss": 2.1594, "step": 48130 }, { "epoch": 2.2, "learning_rate": 3.9097899217355486e-05, "loss": 2.0592, "step": 48140 }, { "epoch": 2.2, "learning_rate": 3.909561078310221e-05, "loss": 2.1381, "step": 48150 }, { "epoch": 2.2, "learning_rate": 3.909332234884892e-05, "loss": 2.1409, "step": 48160 }, { "epoch": 2.2, "learning_rate": 3.9091033914595635e-05, "loss": 2.1093, "step": 48170 }, { "epoch": 2.2, "learning_rate": 3.9088745480342356e-05, "loss": 2.1258, "step": 48180 }, { "epoch": 2.2, "learning_rate": 3.908645704608907e-05, "loss": 2.2702, "step": 48190 }, { "epoch": 2.2, "learning_rate": 3.9084168611835784e-05, "loss": 1.8942, "step": 48200 }, { "epoch": 2.2, "learning_rate": 3.90818801775825e-05, "loss": 2.1024, "step": 48210 }, { "epoch": 2.2, "learning_rate": 3.907959174332921e-05, "loss": 2.0717, "step": 48220 }, { "epoch": 2.2, "learning_rate": 3.9077303309075927e-05, "loss": 2.1609, "step": 48230 }, { "epoch": 2.2, "learning_rate": 3.907501487482265e-05, "loss": 2.1352, "step": 48240 }, { "epoch": 2.2, "learning_rate": 3.907272644056936e-05, "loss": 2.0992, "step": 48250 }, { "epoch": 2.2, "learning_rate": 3.9070438006316076e-05, "loss": 2.2516, "step": 48260 }, { "epoch": 2.2, "learning_rate": 3.90681495720628e-05, "loss": 2.1619, "step": 48270 }, { "epoch": 2.2, "learning_rate": 3.906586113780951e-05, "loss": 2.1746, "step": 48280 }, { "epoch": 2.21, "learning_rate": 3.9063572703556225e-05, "loss": 2.2394, "step": 48290 }, { "epoch": 2.21, "learning_rate": 3.9061284269302946e-05, "loss": 2.0559, "step": 48300 }, { "epoch": 2.21, "learning_rate": 3.905899583504966e-05, "loss": 2.1084, "step": 48310 }, { "epoch": 2.21, "learning_rate": 3.9056707400796374e-05, "loss": 2.0959, "step": 48320 }, { "epoch": 2.21, "learning_rate": 3.9054418966543095e-05, "loss": 2.1186, "step": 48330 }, { "epoch": 2.21, "learning_rate": 3.905213053228981e-05, "loss": 2.263, "step": 48340 }, { "epoch": 2.21, "learning_rate": 3.904984209803652e-05, "loss": 2.1243, "step": 48350 }, { "epoch": 2.21, "learning_rate": 3.9047553663783244e-05, "loss": 2.2003, "step": 48360 }, { "epoch": 2.21, "learning_rate": 3.904526522952996e-05, "loss": 2.1139, "step": 48370 }, { "epoch": 2.21, "learning_rate": 3.904297679527667e-05, "loss": 1.9591, "step": 48380 }, { "epoch": 2.21, "learning_rate": 3.9040688361023393e-05, "loss": 2.1712, "step": 48390 }, { "epoch": 2.21, "learning_rate": 3.903839992677011e-05, "loss": 2.1501, "step": 48400 }, { "epoch": 2.21, "learning_rate": 3.903611149251682e-05, "loss": 2.0865, "step": 48410 }, { "epoch": 2.21, "learning_rate": 3.9033823058263536e-05, "loss": 2.1035, "step": 48420 }, { "epoch": 2.21, "learning_rate": 3.903153462401025e-05, "loss": 2.2172, "step": 48430 }, { "epoch": 2.21, "learning_rate": 3.902924618975697e-05, "loss": 2.2645, "step": 48440 }, { "epoch": 2.21, "learning_rate": 3.9026957755503685e-05, "loss": 2.2314, "step": 48450 }, { "epoch": 2.21, "learning_rate": 3.90246693212504e-05, "loss": 2.0323, "step": 48460 }, { "epoch": 2.21, "learning_rate": 3.902238088699712e-05, "loss": 2.2504, "step": 48470 }, { "epoch": 2.21, "learning_rate": 3.9020092452743834e-05, "loss": 2.1859, "step": 48480 }, { "epoch": 2.21, "learning_rate": 3.901780401849055e-05, "loss": 2.0596, "step": 48490 }, { "epoch": 2.21, "learning_rate": 3.901551558423727e-05, "loss": 2.0033, "step": 48500 }, { "epoch": 2.22, "learning_rate": 3.901322714998398e-05, "loss": 1.9937, "step": 48510 }, { "epoch": 2.22, "learning_rate": 3.90109387157307e-05, "loss": 2.1336, "step": 48520 }, { "epoch": 2.22, "learning_rate": 3.900865028147742e-05, "loss": 2.1271, "step": 48530 }, { "epoch": 2.22, "learning_rate": 3.900636184722413e-05, "loss": 2.1087, "step": 48540 }, { "epoch": 2.22, "learning_rate": 3.900407341297085e-05, "loss": 2.1079, "step": 48550 }, { "epoch": 2.22, "learning_rate": 3.900178497871757e-05, "loss": 2.1624, "step": 48560 }, { "epoch": 2.22, "learning_rate": 3.899949654446428e-05, "loss": 2.0368, "step": 48570 }, { "epoch": 2.22, "learning_rate": 3.8997208110210996e-05, "loss": 2.237, "step": 48580 }, { "epoch": 2.22, "learning_rate": 3.899491967595772e-05, "loss": 2.066, "step": 48590 }, { "epoch": 2.22, "learning_rate": 3.899263124170443e-05, "loss": 2.1748, "step": 48600 }, { "epoch": 2.22, "learning_rate": 3.899034280745114e-05, "loss": 2.2015, "step": 48610 }, { "epoch": 2.22, "learning_rate": 3.898805437319786e-05, "loss": 2.1545, "step": 48620 }, { "epoch": 2.22, "learning_rate": 3.898576593894457e-05, "loss": 2.1557, "step": 48630 }, { "epoch": 2.22, "learning_rate": 3.898347750469129e-05, "loss": 2.1663, "step": 48640 }, { "epoch": 2.22, "learning_rate": 3.898118907043801e-05, "loss": 2.0174, "step": 48650 }, { "epoch": 2.22, "learning_rate": 3.897890063618472e-05, "loss": 2.2883, "step": 48660 }, { "epoch": 2.22, "learning_rate": 3.8976612201931437e-05, "loss": 2.1671, "step": 48670 }, { "epoch": 2.22, "learning_rate": 3.897432376767816e-05, "loss": 2.2673, "step": 48680 }, { "epoch": 2.22, "learning_rate": 3.897203533342487e-05, "loss": 2.0963, "step": 48690 }, { "epoch": 2.22, "learning_rate": 3.8969746899171586e-05, "loss": 2.0347, "step": 48700 }, { "epoch": 2.22, "learning_rate": 3.896745846491831e-05, "loss": 2.0159, "step": 48710 }, { "epoch": 2.22, "learning_rate": 3.896517003066502e-05, "loss": 2.2117, "step": 48720 }, { "epoch": 2.23, "learning_rate": 3.8962881596411735e-05, "loss": 2.1757, "step": 48730 }, { "epoch": 2.23, "learning_rate": 3.8960593162158456e-05, "loss": 2.1983, "step": 48740 }, { "epoch": 2.23, "learning_rate": 3.895830472790517e-05, "loss": 2.1288, "step": 48750 }, { "epoch": 2.23, "learning_rate": 3.8956016293651884e-05, "loss": 2.1644, "step": 48760 }, { "epoch": 2.23, "learning_rate": 3.8953727859398605e-05, "loss": 2.0614, "step": 48770 }, { "epoch": 2.23, "learning_rate": 3.895143942514532e-05, "loss": 2.1273, "step": 48780 }, { "epoch": 2.23, "learning_rate": 3.894915099089203e-05, "loss": 2.2393, "step": 48790 }, { "epoch": 2.23, "learning_rate": 3.8946862556638754e-05, "loss": 2.1876, "step": 48800 }, { "epoch": 2.23, "learning_rate": 3.894457412238546e-05, "loss": 2.0957, "step": 48810 }, { "epoch": 2.23, "learning_rate": 3.894228568813218e-05, "loss": 2.112, "step": 48820 }, { "epoch": 2.23, "learning_rate": 3.8939997253878897e-05, "loss": 2.1378, "step": 48830 }, { "epoch": 2.23, "learning_rate": 3.893770881962561e-05, "loss": 2.036, "step": 48840 }, { "epoch": 2.23, "learning_rate": 3.893542038537233e-05, "loss": 2.1229, "step": 48850 }, { "epoch": 2.23, "learning_rate": 3.8933131951119046e-05, "loss": 2.0919, "step": 48860 }, { "epoch": 2.23, "learning_rate": 3.893084351686576e-05, "loss": 2.2298, "step": 48870 }, { "epoch": 2.23, "learning_rate": 3.892855508261248e-05, "loss": 2.0973, "step": 48880 }, { "epoch": 2.23, "learning_rate": 3.8926266648359195e-05, "loss": 2.0844, "step": 48890 }, { "epoch": 2.23, "learning_rate": 3.892397821410591e-05, "loss": 2.0528, "step": 48900 }, { "epoch": 2.23, "learning_rate": 3.892168977985263e-05, "loss": 2.0943, "step": 48910 }, { "epoch": 2.23, "learning_rate": 3.8919401345599344e-05, "loss": 2.2316, "step": 48920 }, { "epoch": 2.23, "learning_rate": 3.891711291134606e-05, "loss": 2.1718, "step": 48930 }, { "epoch": 2.23, "learning_rate": 3.891482447709278e-05, "loss": 2.2742, "step": 48940 }, { "epoch": 2.24, "learning_rate": 3.891253604283949e-05, "loss": 2.1673, "step": 48950 }, { "epoch": 2.24, "learning_rate": 3.891024760858621e-05, "loss": 2.1944, "step": 48960 }, { "epoch": 2.24, "learning_rate": 3.890795917433293e-05, "loss": 2.1426, "step": 48970 }, { "epoch": 2.24, "learning_rate": 3.890567074007964e-05, "loss": 2.2231, "step": 48980 }, { "epoch": 2.24, "learning_rate": 3.890338230582636e-05, "loss": 2.1334, "step": 48990 }, { "epoch": 2.24, "learning_rate": 3.890109387157307e-05, "loss": 2.1423, "step": 49000 }, { "epoch": 2.24, "learning_rate": 3.8898805437319785e-05, "loss": 2.1399, "step": 49010 }, { "epoch": 2.24, "learning_rate": 3.88965170030665e-05, "loss": 2.0515, "step": 49020 }, { "epoch": 2.24, "learning_rate": 3.889422856881322e-05, "loss": 2.1473, "step": 49030 }, { "epoch": 2.24, "learning_rate": 3.8891940134559934e-05, "loss": 1.9862, "step": 49040 }, { "epoch": 2.24, "learning_rate": 3.888965170030665e-05, "loss": 2.007, "step": 49050 }, { "epoch": 2.24, "learning_rate": 3.888736326605337e-05, "loss": 2.0234, "step": 49060 }, { "epoch": 2.24, "learning_rate": 3.888507483180008e-05, "loss": 2.1525, "step": 49070 }, { "epoch": 2.24, "learning_rate": 3.88827863975468e-05, "loss": 2.1528, "step": 49080 }, { "epoch": 2.24, "learning_rate": 3.888049796329352e-05, "loss": 2.0872, "step": 49090 }, { "epoch": 2.24, "learning_rate": 3.887820952904023e-05, "loss": 2.0793, "step": 49100 }, { "epoch": 2.24, "learning_rate": 3.8875921094786947e-05, "loss": 2.1127, "step": 49110 }, { "epoch": 2.24, "learning_rate": 3.887363266053367e-05, "loss": 2.1575, "step": 49120 }, { "epoch": 2.24, "learning_rate": 3.887134422628038e-05, "loss": 2.178, "step": 49130 }, { "epoch": 2.24, "learning_rate": 3.8869055792027096e-05, "loss": 2.1551, "step": 49140 }, { "epoch": 2.24, "learning_rate": 3.886676735777382e-05, "loss": 2.1074, "step": 49150 }, { "epoch": 2.24, "learning_rate": 3.886447892352053e-05, "loss": 2.1171, "step": 49160 }, { "epoch": 2.25, "learning_rate": 3.8862190489267245e-05, "loss": 2.1168, "step": 49170 }, { "epoch": 2.25, "learning_rate": 3.8859902055013966e-05, "loss": 2.1887, "step": 49180 }, { "epoch": 2.25, "learning_rate": 3.885761362076068e-05, "loss": 2.0825, "step": 49190 }, { "epoch": 2.25, "learning_rate": 3.8855325186507394e-05, "loss": 2.244, "step": 49200 }, { "epoch": 2.25, "learning_rate": 3.885303675225411e-05, "loss": 2.0515, "step": 49210 }, { "epoch": 2.25, "learning_rate": 3.885074831800082e-05, "loss": 2.1487, "step": 49220 }, { "epoch": 2.25, "learning_rate": 3.884845988374754e-05, "loss": 1.959, "step": 49230 }, { "epoch": 2.25, "learning_rate": 3.884617144949426e-05, "loss": 2.2422, "step": 49240 }, { "epoch": 2.25, "learning_rate": 3.884388301524097e-05, "loss": 2.1475, "step": 49250 }, { "epoch": 2.25, "learning_rate": 3.884159458098769e-05, "loss": 2.0983, "step": 49260 }, { "epoch": 2.25, "learning_rate": 3.8839306146734407e-05, "loss": 2.1701, "step": 49270 }, { "epoch": 2.25, "learning_rate": 3.883701771248112e-05, "loss": 2.1076, "step": 49280 }, { "epoch": 2.25, "learning_rate": 3.883472927822784e-05, "loss": 1.9721, "step": 49290 }, { "epoch": 2.25, "learning_rate": 3.8832440843974556e-05, "loss": 2.1291, "step": 49300 }, { "epoch": 2.25, "learning_rate": 3.883015240972127e-05, "loss": 2.0604, "step": 49310 }, { "epoch": 2.25, "learning_rate": 3.8827863975467984e-05, "loss": 2.1789, "step": 49320 }, { "epoch": 2.25, "learning_rate": 3.8825575541214705e-05, "loss": 2.1007, "step": 49330 }, { "epoch": 2.25, "learning_rate": 3.882328710696142e-05, "loss": 2.0326, "step": 49340 }, { "epoch": 2.25, "learning_rate": 3.882099867270813e-05, "loss": 2.1633, "step": 49350 }, { "epoch": 2.25, "learning_rate": 3.8818710238454854e-05, "loss": 2.2942, "step": 49360 }, { "epoch": 2.25, "learning_rate": 3.881642180420157e-05, "loss": 2.2437, "step": 49370 }, { "epoch": 2.25, "learning_rate": 3.881413336994828e-05, "loss": 2.058, "step": 49380 }, { "epoch": 2.26, "learning_rate": 3.8811844935695e-05, "loss": 2.1466, "step": 49390 }, { "epoch": 2.26, "learning_rate": 3.880955650144171e-05, "loss": 2.0724, "step": 49400 }, { "epoch": 2.26, "learning_rate": 3.880726806718843e-05, "loss": 2.1731, "step": 49410 }, { "epoch": 2.26, "learning_rate": 3.8804979632935146e-05, "loss": 2.1127, "step": 49420 }, { "epoch": 2.26, "learning_rate": 3.880269119868186e-05, "loss": 2.198, "step": 49430 }, { "epoch": 2.26, "learning_rate": 3.880040276442858e-05, "loss": 2.1682, "step": 49440 }, { "epoch": 2.26, "learning_rate": 3.8798114330175295e-05, "loss": 1.9835, "step": 49450 }, { "epoch": 2.26, "learning_rate": 3.879582589592201e-05, "loss": 2.2822, "step": 49460 }, { "epoch": 2.26, "learning_rate": 3.879353746166873e-05, "loss": 2.3392, "step": 49470 }, { "epoch": 2.26, "learning_rate": 3.8791249027415444e-05, "loss": 2.1467, "step": 49480 }, { "epoch": 2.26, "learning_rate": 3.878896059316216e-05, "loss": 2.1924, "step": 49490 }, { "epoch": 2.26, "learning_rate": 3.878667215890888e-05, "loss": 2.1228, "step": 49500 }, { "epoch": 2.26, "learning_rate": 3.878438372465559e-05, "loss": 2.2888, "step": 49510 }, { "epoch": 2.26, "learning_rate": 3.878209529040231e-05, "loss": 2.1766, "step": 49520 }, { "epoch": 2.26, "learning_rate": 3.877980685614903e-05, "loss": 2.1626, "step": 49530 }, { "epoch": 2.26, "learning_rate": 3.877751842189574e-05, "loss": 2.0765, "step": 49540 }, { "epoch": 2.26, "learning_rate": 3.8775229987642457e-05, "loss": 2.0538, "step": 49550 }, { "epoch": 2.26, "learning_rate": 3.877294155338918e-05, "loss": 2.2287, "step": 49560 }, { "epoch": 2.26, "learning_rate": 3.877065311913589e-05, "loss": 2.1659, "step": 49570 }, { "epoch": 2.26, "learning_rate": 3.8768364684882606e-05, "loss": 2.2998, "step": 49580 }, { "epoch": 2.26, "learning_rate": 3.8766076250629327e-05, "loss": 2.2435, "step": 49590 }, { "epoch": 2.26, "learning_rate": 3.8763787816376034e-05, "loss": 2.3722, "step": 49600 }, { "epoch": 2.27, "learning_rate": 3.876149938212275e-05, "loss": 2.1753, "step": 49610 }, { "epoch": 2.27, "learning_rate": 3.875921094786947e-05, "loss": 2.1153, "step": 49620 }, { "epoch": 2.27, "learning_rate": 3.875692251361618e-05, "loss": 2.273, "step": 49630 }, { "epoch": 2.27, "learning_rate": 3.87546340793629e-05, "loss": 2.1974, "step": 49640 }, { "epoch": 2.27, "learning_rate": 3.875234564510962e-05, "loss": 2.2859, "step": 49650 }, { "epoch": 2.27, "learning_rate": 3.875005721085633e-05, "loss": 2.1362, "step": 49660 }, { "epoch": 2.27, "learning_rate": 3.8747768776603046e-05, "loss": 2.2452, "step": 49670 }, { "epoch": 2.27, "learning_rate": 3.874548034234977e-05, "loss": 2.277, "step": 49680 }, { "epoch": 2.27, "learning_rate": 3.874319190809648e-05, "loss": 2.2082, "step": 49690 }, { "epoch": 2.27, "learning_rate": 3.8740903473843196e-05, "loss": 1.9919, "step": 49700 }, { "epoch": 2.27, "learning_rate": 3.8738615039589917e-05, "loss": 2.0804, "step": 49710 }, { "epoch": 2.27, "learning_rate": 3.873632660533663e-05, "loss": 2.0919, "step": 49720 }, { "epoch": 2.27, "learning_rate": 3.8734038171083345e-05, "loss": 2.1042, "step": 49730 }, { "epoch": 2.27, "learning_rate": 3.8731749736830066e-05, "loss": 2.0128, "step": 49740 }, { "epoch": 2.27, "learning_rate": 3.872946130257678e-05, "loss": 2.2389, "step": 49750 }, { "epoch": 2.27, "learning_rate": 3.8727172868323494e-05, "loss": 2.136, "step": 49760 }, { "epoch": 2.27, "learning_rate": 3.8724884434070215e-05, "loss": 2.2019, "step": 49770 }, { "epoch": 2.27, "learning_rate": 3.872259599981693e-05, "loss": 2.1538, "step": 49780 }, { "epoch": 2.27, "learning_rate": 3.872030756556364e-05, "loss": 2.209, "step": 49790 }, { "epoch": 2.27, "learning_rate": 3.871801913131036e-05, "loss": 2.1316, "step": 49800 }, { "epoch": 2.27, "learning_rate": 3.871573069705707e-05, "loss": 2.251, "step": 49810 }, { "epoch": 2.27, "learning_rate": 3.871344226280379e-05, "loss": 1.9359, "step": 49820 }, { "epoch": 2.28, "learning_rate": 3.8711153828550506e-05, "loss": 2.0987, "step": 49830 }, { "epoch": 2.28, "learning_rate": 3.870886539429722e-05, "loss": 2.0586, "step": 49840 }, { "epoch": 2.28, "learning_rate": 3.870657696004394e-05, "loss": 1.9723, "step": 49850 }, { "epoch": 2.28, "learning_rate": 3.8704288525790656e-05, "loss": 2.2038, "step": 49860 }, { "epoch": 2.28, "learning_rate": 3.870200009153737e-05, "loss": 2.2995, "step": 49870 }, { "epoch": 2.28, "learning_rate": 3.869971165728409e-05, "loss": 2.03, "step": 49880 }, { "epoch": 2.28, "learning_rate": 3.8697423223030805e-05, "loss": 2.3554, "step": 49890 }, { "epoch": 2.28, "learning_rate": 3.869513478877752e-05, "loss": 2.2072, "step": 49900 }, { "epoch": 2.28, "learning_rate": 3.869284635452424e-05, "loss": 2.1077, "step": 49910 }, { "epoch": 2.28, "learning_rate": 3.8690557920270954e-05, "loss": 2.082, "step": 49920 }, { "epoch": 2.28, "learning_rate": 3.868826948601767e-05, "loss": 2.2717, "step": 49930 }, { "epoch": 2.28, "learning_rate": 3.868598105176439e-05, "loss": 2.1762, "step": 49940 }, { "epoch": 2.28, "learning_rate": 3.86836926175111e-05, "loss": 2.1593, "step": 49950 }, { "epoch": 2.28, "learning_rate": 3.868140418325782e-05, "loss": 2.1236, "step": 49960 }, { "epoch": 2.28, "learning_rate": 3.867911574900454e-05, "loss": 2.1757, "step": 49970 }, { "epoch": 2.28, "learning_rate": 3.867682731475125e-05, "loss": 2.1358, "step": 49980 }, { "epoch": 2.28, "learning_rate": 3.867453888049796e-05, "loss": 2.1137, "step": 49990 }, { "epoch": 2.28, "learning_rate": 3.867225044624468e-05, "loss": 2.1309, "step": 50000 }, { "epoch": 2.28, "learning_rate": 3.8669962011991395e-05, "loss": 2.0035, "step": 50010 }, { "epoch": 2.28, "learning_rate": 3.866767357773811e-05, "loss": 2.2379, "step": 50020 }, { "epoch": 2.28, "learning_rate": 3.866538514348483e-05, "loss": 2.2221, "step": 50030 }, { "epoch": 2.28, "learning_rate": 3.8663096709231544e-05, "loss": 2.2735, "step": 50040 }, { "epoch": 2.29, "learning_rate": 3.866080827497826e-05, "loss": 2.0119, "step": 50050 }, { "epoch": 2.29, "learning_rate": 3.865851984072498e-05, "loss": 2.2294, "step": 50060 }, { "epoch": 2.29, "learning_rate": 3.865623140647169e-05, "loss": 2.1846, "step": 50070 }, { "epoch": 2.29, "learning_rate": 3.865394297221841e-05, "loss": 2.1814, "step": 50080 }, { "epoch": 2.29, "learning_rate": 3.865165453796513e-05, "loss": 1.9367, "step": 50090 }, { "epoch": 2.29, "learning_rate": 3.864936610371184e-05, "loss": 2.0914, "step": 50100 }, { "epoch": 2.29, "learning_rate": 3.8647077669458556e-05, "loss": 2.0809, "step": 50110 }, { "epoch": 2.29, "learning_rate": 3.864478923520528e-05, "loss": 2.1955, "step": 50120 }, { "epoch": 2.29, "learning_rate": 3.864250080095199e-05, "loss": 2.1443, "step": 50130 }, { "epoch": 2.29, "learning_rate": 3.8640212366698706e-05, "loss": 2.1334, "step": 50140 }, { "epoch": 2.29, "learning_rate": 3.8637923932445426e-05, "loss": 2.1085, "step": 50150 }, { "epoch": 2.29, "learning_rate": 3.863563549819214e-05, "loss": 2.1696, "step": 50160 }, { "epoch": 2.29, "learning_rate": 3.8633347063938855e-05, "loss": 2.1356, "step": 50170 }, { "epoch": 2.29, "learning_rate": 3.8631058629685576e-05, "loss": 2.0867, "step": 50180 }, { "epoch": 2.29, "learning_rate": 3.862877019543228e-05, "loss": 2.1916, "step": 50190 }, { "epoch": 2.29, "learning_rate": 3.8626481761179004e-05, "loss": 2.0148, "step": 50200 }, { "epoch": 2.29, "learning_rate": 3.862419332692572e-05, "loss": 2.0785, "step": 50210 }, { "epoch": 2.29, "learning_rate": 3.862190489267243e-05, "loss": 2.1941, "step": 50220 }, { "epoch": 2.29, "learning_rate": 3.861961645841915e-05, "loss": 2.018, "step": 50230 }, { "epoch": 2.29, "learning_rate": 3.861732802416587e-05, "loss": 1.9943, "step": 50240 }, { "epoch": 2.29, "learning_rate": 3.861503958991258e-05, "loss": 2.111, "step": 50250 }, { "epoch": 2.3, "learning_rate": 3.86127511556593e-05, "loss": 2.0055, "step": 50260 }, { "epoch": 2.3, "learning_rate": 3.8610462721406016e-05, "loss": 2.1013, "step": 50270 }, { "epoch": 2.3, "learning_rate": 3.860817428715273e-05, "loss": 1.9842, "step": 50280 }, { "epoch": 2.3, "learning_rate": 3.860588585289945e-05, "loss": 1.8978, "step": 50290 }, { "epoch": 2.3, "learning_rate": 3.8603597418646166e-05, "loss": 2.1542, "step": 50300 }, { "epoch": 2.3, "learning_rate": 3.860130898439288e-05, "loss": 2.0533, "step": 50310 }, { "epoch": 2.3, "learning_rate": 3.85990205501396e-05, "loss": 2.1246, "step": 50320 }, { "epoch": 2.3, "learning_rate": 3.8596732115886315e-05, "loss": 2.0492, "step": 50330 }, { "epoch": 2.3, "learning_rate": 3.859444368163303e-05, "loss": 2.0953, "step": 50340 }, { "epoch": 2.3, "learning_rate": 3.859215524737975e-05, "loss": 2.1383, "step": 50350 }, { "epoch": 2.3, "learning_rate": 3.8589866813126464e-05, "loss": 2.0521, "step": 50360 }, { "epoch": 2.3, "learning_rate": 3.858757837887318e-05, "loss": 2.1464, "step": 50370 }, { "epoch": 2.3, "learning_rate": 3.85852899446199e-05, "loss": 2.3048, "step": 50380 }, { "epoch": 2.3, "learning_rate": 3.8583001510366606e-05, "loss": 2.1927, "step": 50390 }, { "epoch": 2.3, "learning_rate": 3.858071307611332e-05, "loss": 2.0442, "step": 50400 }, { "epoch": 2.3, "learning_rate": 3.857842464186004e-05, "loss": 2.087, "step": 50410 }, { "epoch": 2.3, "learning_rate": 3.8576136207606756e-05, "loss": 2.0659, "step": 50420 }, { "epoch": 2.3, "learning_rate": 3.857384777335347e-05, "loss": 2.223, "step": 50430 }, { "epoch": 2.3, "learning_rate": 3.857155933910019e-05, "loss": 2.1183, "step": 50440 }, { "epoch": 2.3, "learning_rate": 3.8569270904846905e-05, "loss": 1.986, "step": 50450 }, { "epoch": 2.3, "learning_rate": 3.856698247059362e-05, "loss": 2.1476, "step": 50460 }, { "epoch": 2.3, "learning_rate": 3.856469403634034e-05, "loss": 2.183, "step": 50470 }, { "epoch": 2.31, "learning_rate": 3.8562405602087054e-05, "loss": 2.1317, "step": 50480 }, { "epoch": 2.31, "learning_rate": 3.856011716783377e-05, "loss": 2.1953, "step": 50490 }, { "epoch": 2.31, "learning_rate": 3.855782873358049e-05, "loss": 2.1058, "step": 50500 }, { "epoch": 2.31, "learning_rate": 3.85555402993272e-05, "loss": 2.124, "step": 50510 }, { "epoch": 2.31, "learning_rate": 3.855325186507392e-05, "loss": 2.2383, "step": 50520 }, { "epoch": 2.31, "learning_rate": 3.855096343082064e-05, "loss": 2.0143, "step": 50530 }, { "epoch": 2.31, "learning_rate": 3.854867499656735e-05, "loss": 2.0871, "step": 50540 }, { "epoch": 2.31, "learning_rate": 3.8546386562314066e-05, "loss": 2.2558, "step": 50550 }, { "epoch": 2.31, "learning_rate": 3.854409812806079e-05, "loss": 2.1423, "step": 50560 }, { "epoch": 2.31, "learning_rate": 3.85418096938075e-05, "loss": 2.2911, "step": 50570 }, { "epoch": 2.31, "learning_rate": 3.853952125955421e-05, "loss": 2.1866, "step": 50580 }, { "epoch": 2.31, "learning_rate": 3.853723282530093e-05, "loss": 2.0475, "step": 50590 }, { "epoch": 2.31, "learning_rate": 3.8534944391047644e-05, "loss": 2.1627, "step": 50600 }, { "epoch": 2.31, "learning_rate": 3.853265595679436e-05, "loss": 2.1219, "step": 50610 }, { "epoch": 2.31, "learning_rate": 3.853036752254108e-05, "loss": 2.1475, "step": 50620 }, { "epoch": 2.31, "learning_rate": 3.852807908828779e-05, "loss": 2.2287, "step": 50630 }, { "epoch": 2.31, "learning_rate": 3.852579065403451e-05, "loss": 2.1535, "step": 50640 }, { "epoch": 2.31, "learning_rate": 3.852350221978123e-05, "loss": 2.074, "step": 50650 }, { "epoch": 2.31, "learning_rate": 3.852121378552794e-05, "loss": 2.0873, "step": 50660 }, { "epoch": 2.31, "learning_rate": 3.8518925351274656e-05, "loss": 2.2379, "step": 50670 }, { "epoch": 2.31, "learning_rate": 3.851663691702138e-05, "loss": 2.0015, "step": 50680 }, { "epoch": 2.31, "learning_rate": 3.851434848276809e-05, "loss": 2.3016, "step": 50690 }, { "epoch": 2.32, "learning_rate": 3.8512060048514805e-05, "loss": 2.141, "step": 50700 }, { "epoch": 2.32, "learning_rate": 3.8509771614261526e-05, "loss": 2.2155, "step": 50710 }, { "epoch": 2.32, "learning_rate": 3.850748318000824e-05, "loss": 2.0505, "step": 50720 }, { "epoch": 2.32, "learning_rate": 3.8505194745754955e-05, "loss": 2.2509, "step": 50730 }, { "epoch": 2.32, "learning_rate": 3.8502906311501676e-05, "loss": 2.0956, "step": 50740 }, { "epoch": 2.32, "learning_rate": 3.850061787724839e-05, "loss": 2.2403, "step": 50750 }, { "epoch": 2.32, "learning_rate": 3.8498329442995104e-05, "loss": 2.1161, "step": 50760 }, { "epoch": 2.32, "learning_rate": 3.8496041008741825e-05, "loss": 2.1569, "step": 50770 }, { "epoch": 2.32, "learning_rate": 3.849375257448853e-05, "loss": 2.1278, "step": 50780 }, { "epoch": 2.32, "learning_rate": 3.849146414023525e-05, "loss": 2.134, "step": 50790 }, { "epoch": 2.32, "learning_rate": 3.848917570598197e-05, "loss": 2.0834, "step": 50800 }, { "epoch": 2.32, "learning_rate": 3.848688727172868e-05, "loss": 2.1361, "step": 50810 }, { "epoch": 2.32, "learning_rate": 3.84845988374754e-05, "loss": 2.1222, "step": 50820 }, { "epoch": 2.32, "learning_rate": 3.8482310403222116e-05, "loss": 2.1078, "step": 50830 }, { "epoch": 2.32, "learning_rate": 3.848002196896883e-05, "loss": 2.0577, "step": 50840 }, { "epoch": 2.32, "learning_rate": 3.847773353471555e-05, "loss": 2.1568, "step": 50850 }, { "epoch": 2.32, "learning_rate": 3.8475445100462266e-05, "loss": 2.1516, "step": 50860 }, { "epoch": 2.32, "learning_rate": 3.847315666620898e-05, "loss": 2.0898, "step": 50870 }, { "epoch": 2.32, "learning_rate": 3.84708682319557e-05, "loss": 2.0021, "step": 50880 }, { "epoch": 2.32, "learning_rate": 3.8468579797702415e-05, "loss": 2.0575, "step": 50890 }, { "epoch": 2.32, "learning_rate": 3.846629136344913e-05, "loss": 2.1807, "step": 50900 }, { "epoch": 2.32, "learning_rate": 3.846400292919585e-05, "loss": 2.1057, "step": 50910 }, { "epoch": 2.33, "learning_rate": 3.8461714494942564e-05, "loss": 2.1727, "step": 50920 }, { "epoch": 2.33, "learning_rate": 3.845942606068928e-05, "loss": 2.0194, "step": 50930 }, { "epoch": 2.33, "learning_rate": 3.8457137626436e-05, "loss": 2.2076, "step": 50940 }, { "epoch": 2.33, "learning_rate": 3.845484919218271e-05, "loss": 2.1016, "step": 50950 }, { "epoch": 2.33, "learning_rate": 3.845256075792943e-05, "loss": 2.1719, "step": 50960 }, { "epoch": 2.33, "learning_rate": 3.845027232367615e-05, "loss": 2.2632, "step": 50970 }, { "epoch": 2.33, "learning_rate": 3.8447983889422855e-05, "loss": 2.0295, "step": 50980 }, { "epoch": 2.33, "learning_rate": 3.844569545516957e-05, "loss": 2.0633, "step": 50990 }, { "epoch": 2.33, "learning_rate": 3.844340702091629e-05, "loss": 2.106, "step": 51000 }, { "epoch": 2.33, "learning_rate": 3.8441118586663005e-05, "loss": 2.1201, "step": 51010 }, { "epoch": 2.33, "learning_rate": 3.843883015240972e-05, "loss": 2.114, "step": 51020 }, { "epoch": 2.33, "learning_rate": 3.843654171815644e-05, "loss": 2.1593, "step": 51030 }, { "epoch": 2.33, "learning_rate": 3.8434253283903154e-05, "loss": 2.221, "step": 51040 }, { "epoch": 2.33, "learning_rate": 3.843196484964987e-05, "loss": 2.0297, "step": 51050 }, { "epoch": 2.33, "learning_rate": 3.842967641539659e-05, "loss": 2.3638, "step": 51060 }, { "epoch": 2.33, "learning_rate": 3.84273879811433e-05, "loss": 2.1625, "step": 51070 }, { "epoch": 2.33, "learning_rate": 3.842509954689002e-05, "loss": 2.0, "step": 51080 }, { "epoch": 2.33, "learning_rate": 3.842281111263674e-05, "loss": 2.0519, "step": 51090 }, { "epoch": 2.33, "learning_rate": 3.842052267838345e-05, "loss": 2.0963, "step": 51100 }, { "epoch": 2.33, "learning_rate": 3.8418234244130166e-05, "loss": 1.9579, "step": 51110 }, { "epoch": 2.33, "learning_rate": 3.841594580987689e-05, "loss": 2.0048, "step": 51120 }, { "epoch": 2.33, "learning_rate": 3.84136573756236e-05, "loss": 2.0916, "step": 51130 }, { "epoch": 2.34, "learning_rate": 3.8411368941370315e-05, "loss": 2.2481, "step": 51140 }, { "epoch": 2.34, "learning_rate": 3.8409080507117036e-05, "loss": 2.3728, "step": 51150 }, { "epoch": 2.34, "learning_rate": 3.840679207286375e-05, "loss": 2.1006, "step": 51160 }, { "epoch": 2.34, "learning_rate": 3.8404503638610465e-05, "loss": 2.1559, "step": 51170 }, { "epoch": 2.34, "learning_rate": 3.840221520435718e-05, "loss": 2.1227, "step": 51180 }, { "epoch": 2.34, "learning_rate": 3.839992677010389e-05, "loss": 2.0843, "step": 51190 }, { "epoch": 2.34, "learning_rate": 3.8397638335850614e-05, "loss": 2.1255, "step": 51200 }, { "epoch": 2.34, "learning_rate": 3.839534990159733e-05, "loss": 2.0101, "step": 51210 }, { "epoch": 2.34, "learning_rate": 3.839306146734404e-05, "loss": 2.1703, "step": 51220 }, { "epoch": 2.34, "learning_rate": 3.839077303309076e-05, "loss": 2.0992, "step": 51230 }, { "epoch": 2.34, "learning_rate": 3.838848459883748e-05, "loss": 2.2565, "step": 51240 }, { "epoch": 2.34, "learning_rate": 3.838619616458419e-05, "loss": 2.1334, "step": 51250 }, { "epoch": 2.34, "learning_rate": 3.838390773033091e-05, "loss": 2.1001, "step": 51260 }, { "epoch": 2.34, "learning_rate": 3.8381619296077626e-05, "loss": 2.0601, "step": 51270 }, { "epoch": 2.34, "learning_rate": 3.837933086182434e-05, "loss": 2.0718, "step": 51280 }, { "epoch": 2.34, "learning_rate": 3.837704242757106e-05, "loss": 2.1278, "step": 51290 }, { "epoch": 2.34, "learning_rate": 3.8374753993317775e-05, "loss": 2.0148, "step": 51300 }, { "epoch": 2.34, "learning_rate": 3.837246555906449e-05, "loss": 2.0419, "step": 51310 }, { "epoch": 2.34, "learning_rate": 3.837017712481121e-05, "loss": 2.1136, "step": 51320 }, { "epoch": 2.34, "learning_rate": 3.8367888690557925e-05, "loss": 2.1118, "step": 51330 }, { "epoch": 2.34, "learning_rate": 3.836560025630464e-05, "loss": 2.1448, "step": 51340 }, { "epoch": 2.34, "learning_rate": 3.836331182205136e-05, "loss": 1.9883, "step": 51350 }, { "epoch": 2.35, "learning_rate": 3.8361023387798074e-05, "loss": 2.1315, "step": 51360 }, { "epoch": 2.35, "learning_rate": 3.835873495354478e-05, "loss": 2.0632, "step": 51370 }, { "epoch": 2.35, "learning_rate": 3.83564465192915e-05, "loss": 2.2149, "step": 51380 }, { "epoch": 2.35, "learning_rate": 3.8354158085038216e-05, "loss": 2.3111, "step": 51390 }, { "epoch": 2.35, "learning_rate": 3.835186965078493e-05, "loss": 2.0395, "step": 51400 }, { "epoch": 2.35, "learning_rate": 3.834958121653165e-05, "loss": 2.2329, "step": 51410 }, { "epoch": 2.35, "learning_rate": 3.8347292782278365e-05, "loss": 2.0779, "step": 51420 }, { "epoch": 2.35, "learning_rate": 3.834500434802508e-05, "loss": 1.9463, "step": 51430 }, { "epoch": 2.35, "learning_rate": 3.83427159137718e-05, "loss": 2.2437, "step": 51440 }, { "epoch": 2.35, "learning_rate": 3.8340427479518515e-05, "loss": 2.1138, "step": 51450 }, { "epoch": 2.35, "learning_rate": 3.833813904526523e-05, "loss": 2.088, "step": 51460 }, { "epoch": 2.35, "learning_rate": 3.833585061101195e-05, "loss": 2.1089, "step": 51470 }, { "epoch": 2.35, "learning_rate": 3.8333562176758664e-05, "loss": 2.1177, "step": 51480 }, { "epoch": 2.35, "learning_rate": 3.833127374250538e-05, "loss": 1.9202, "step": 51490 }, { "epoch": 2.35, "learning_rate": 3.83289853082521e-05, "loss": 1.9617, "step": 51500 }, { "epoch": 2.35, "learning_rate": 3.832669687399881e-05, "loss": 2.1793, "step": 51510 }, { "epoch": 2.35, "learning_rate": 3.832440843974553e-05, "loss": 2.0522, "step": 51520 }, { "epoch": 2.35, "learning_rate": 3.832212000549225e-05, "loss": 2.1293, "step": 51530 }, { "epoch": 2.35, "learning_rate": 3.831983157123896e-05, "loss": 2.2129, "step": 51540 }, { "epoch": 2.35, "learning_rate": 3.8317543136985676e-05, "loss": 2.118, "step": 51550 }, { "epoch": 2.35, "learning_rate": 3.83152547027324e-05, "loss": 2.0781, "step": 51560 }, { "epoch": 2.35, "learning_rate": 3.8312966268479105e-05, "loss": 2.1309, "step": 51570 }, { "epoch": 2.36, "learning_rate": 3.8310677834225825e-05, "loss": 2.2173, "step": 51580 }, { "epoch": 2.36, "learning_rate": 3.830838939997254e-05, "loss": 2.2573, "step": 51590 }, { "epoch": 2.36, "learning_rate": 3.8306100965719254e-05, "loss": 2.154, "step": 51600 }, { "epoch": 2.36, "learning_rate": 3.8303812531465975e-05, "loss": 2.1075, "step": 51610 }, { "epoch": 2.36, "learning_rate": 3.830152409721269e-05, "loss": 2.0292, "step": 51620 }, { "epoch": 2.36, "learning_rate": 3.82992356629594e-05, "loss": 2.2528, "step": 51630 }, { "epoch": 2.36, "learning_rate": 3.8296947228706124e-05, "loss": 2.01, "step": 51640 }, { "epoch": 2.36, "learning_rate": 3.829465879445284e-05, "loss": 2.1908, "step": 51650 }, { "epoch": 2.36, "learning_rate": 3.829237036019955e-05, "loss": 2.1106, "step": 51660 }, { "epoch": 2.36, "learning_rate": 3.8290081925946266e-05, "loss": 2.1538, "step": 51670 }, { "epoch": 2.36, "learning_rate": 3.828779349169299e-05, "loss": 1.9758, "step": 51680 }, { "epoch": 2.36, "learning_rate": 3.82855050574397e-05, "loss": 2.1791, "step": 51690 }, { "epoch": 2.36, "learning_rate": 3.8283216623186415e-05, "loss": 2.0479, "step": 51700 }, { "epoch": 2.36, "learning_rate": 3.8280928188933136e-05, "loss": 2.2014, "step": 51710 }, { "epoch": 2.36, "learning_rate": 3.827863975467985e-05, "loss": 2.0415, "step": 51720 }, { "epoch": 2.36, "learning_rate": 3.8276351320426565e-05, "loss": 2.3208, "step": 51730 }, { "epoch": 2.36, "learning_rate": 3.8274062886173285e-05, "loss": 2.0764, "step": 51740 }, { "epoch": 2.36, "learning_rate": 3.827177445192e-05, "loss": 2.0477, "step": 51750 }, { "epoch": 2.36, "learning_rate": 3.8269486017666714e-05, "loss": 1.9327, "step": 51760 }, { "epoch": 2.36, "learning_rate": 3.826719758341343e-05, "loss": 2.0157, "step": 51770 }, { "epoch": 2.36, "learning_rate": 3.826490914916014e-05, "loss": 2.1025, "step": 51780 }, { "epoch": 2.36, "learning_rate": 3.826262071490686e-05, "loss": 2.1657, "step": 51790 }, { "epoch": 2.37, "learning_rate": 3.826033228065358e-05, "loss": 2.1988, "step": 51800 }, { "epoch": 2.37, "learning_rate": 3.825804384640029e-05, "loss": 2.1739, "step": 51810 }, { "epoch": 2.37, "learning_rate": 3.825575541214701e-05, "loss": 2.0205, "step": 51820 }, { "epoch": 2.37, "learning_rate": 3.8253466977893726e-05, "loss": 2.1086, "step": 51830 }, { "epoch": 2.37, "learning_rate": 3.825117854364044e-05, "loss": 2.0709, "step": 51840 }, { "epoch": 2.37, "learning_rate": 3.824889010938716e-05, "loss": 2.0273, "step": 51850 }, { "epoch": 2.37, "learning_rate": 3.8246601675133875e-05, "loss": 2.085, "step": 51860 }, { "epoch": 2.37, "learning_rate": 3.824431324088059e-05, "loss": 2.0723, "step": 51870 }, { "epoch": 2.37, "learning_rate": 3.824202480662731e-05, "loss": 2.0795, "step": 51880 }, { "epoch": 2.37, "learning_rate": 3.8239736372374025e-05, "loss": 2.1696, "step": 51890 }, { "epoch": 2.37, "learning_rate": 3.823744793812074e-05, "loss": 2.0655, "step": 51900 }, { "epoch": 2.37, "learning_rate": 3.823515950386746e-05, "loss": 2.0744, "step": 51910 }, { "epoch": 2.37, "learning_rate": 3.8232871069614174e-05, "loss": 2.0667, "step": 51920 }, { "epoch": 2.37, "learning_rate": 3.823058263536089e-05, "loss": 2.0487, "step": 51930 }, { "epoch": 2.37, "learning_rate": 3.822829420110761e-05, "loss": 2.0541, "step": 51940 }, { "epoch": 2.37, "learning_rate": 3.822600576685432e-05, "loss": 2.1059, "step": 51950 }, { "epoch": 2.37, "learning_rate": 3.822371733260104e-05, "loss": 2.0291, "step": 51960 }, { "epoch": 2.37, "learning_rate": 3.822142889834775e-05, "loss": 2.0588, "step": 51970 }, { "epoch": 2.37, "learning_rate": 3.8219140464094465e-05, "loss": 2.0627, "step": 51980 }, { "epoch": 2.37, "learning_rate": 3.821685202984118e-05, "loss": 2.0033, "step": 51990 }, { "epoch": 2.37, "learning_rate": 3.82145635955879e-05, "loss": 2.0788, "step": 52000 }, { "epoch": 2.37, "learning_rate": 3.8212275161334614e-05, "loss": 2.0446, "step": 52010 }, { "epoch": 2.38, "learning_rate": 3.820998672708133e-05, "loss": 2.0858, "step": 52020 }, { "epoch": 2.38, "learning_rate": 3.820769829282805e-05, "loss": 2.2729, "step": 52030 }, { "epoch": 2.38, "learning_rate": 3.8205409858574764e-05, "loss": 2.2889, "step": 52040 }, { "epoch": 2.38, "learning_rate": 3.820312142432148e-05, "loss": 2.0662, "step": 52050 }, { "epoch": 2.38, "learning_rate": 3.82008329900682e-05, "loss": 2.1831, "step": 52060 }, { "epoch": 2.38, "learning_rate": 3.819854455581491e-05, "loss": 2.0684, "step": 52070 }, { "epoch": 2.38, "learning_rate": 3.819625612156163e-05, "loss": 2.0144, "step": 52080 }, { "epoch": 2.38, "learning_rate": 3.819396768730835e-05, "loss": 2.1305, "step": 52090 }, { "epoch": 2.38, "learning_rate": 3.819167925305506e-05, "loss": 1.9998, "step": 52100 }, { "epoch": 2.38, "learning_rate": 3.8189390818801776e-05, "loss": 2.1834, "step": 52110 }, { "epoch": 2.38, "learning_rate": 3.81871023845485e-05, "loss": 2.0928, "step": 52120 }, { "epoch": 2.38, "learning_rate": 3.818481395029521e-05, "loss": 2.1475, "step": 52130 }, { "epoch": 2.38, "learning_rate": 3.8182525516041925e-05, "loss": 2.0182, "step": 52140 }, { "epoch": 2.38, "learning_rate": 3.8180237081788646e-05, "loss": 2.0495, "step": 52150 }, { "epoch": 2.38, "learning_rate": 3.8177948647535354e-05, "loss": 2.238, "step": 52160 }, { "epoch": 2.38, "learning_rate": 3.8175660213282074e-05, "loss": 2.1204, "step": 52170 }, { "epoch": 2.38, "learning_rate": 3.817337177902879e-05, "loss": 2.1291, "step": 52180 }, { "epoch": 2.38, "learning_rate": 3.81710833447755e-05, "loss": 2.1779, "step": 52190 }, { "epoch": 2.38, "learning_rate": 3.8168794910522224e-05, "loss": 2.2445, "step": 52200 }, { "epoch": 2.38, "learning_rate": 3.816650647626894e-05, "loss": 2.0125, "step": 52210 }, { "epoch": 2.38, "learning_rate": 3.816421804201565e-05, "loss": 2.0532, "step": 52220 }, { "epoch": 2.38, "learning_rate": 3.816192960776237e-05, "loss": 2.1227, "step": 52230 }, { "epoch": 2.39, "learning_rate": 3.815964117350909e-05, "loss": 2.0551, "step": 52240 }, { "epoch": 2.39, "learning_rate": 3.81573527392558e-05, "loss": 2.1314, "step": 52250 }, { "epoch": 2.39, "learning_rate": 3.815506430500252e-05, "loss": 1.9996, "step": 52260 }, { "epoch": 2.39, "learning_rate": 3.8152775870749236e-05, "loss": 2.1115, "step": 52270 }, { "epoch": 2.39, "learning_rate": 3.815048743649595e-05, "loss": 2.1565, "step": 52280 }, { "epoch": 2.39, "learning_rate": 3.814819900224267e-05, "loss": 2.2133, "step": 52290 }, { "epoch": 2.39, "learning_rate": 3.8145910567989385e-05, "loss": 2.0717, "step": 52300 }, { "epoch": 2.39, "learning_rate": 3.81436221337361e-05, "loss": 2.0733, "step": 52310 }, { "epoch": 2.39, "learning_rate": 3.814133369948282e-05, "loss": 2.0553, "step": 52320 }, { "epoch": 2.39, "learning_rate": 3.8139045265229535e-05, "loss": 1.8938, "step": 52330 }, { "epoch": 2.39, "learning_rate": 3.813675683097625e-05, "loss": 2.1768, "step": 52340 }, { "epoch": 2.39, "learning_rate": 3.813446839672297e-05, "loss": 2.1028, "step": 52350 }, { "epoch": 2.39, "learning_rate": 3.813217996246968e-05, "loss": 2.1877, "step": 52360 }, { "epoch": 2.39, "learning_rate": 3.812989152821639e-05, "loss": 2.1271, "step": 52370 }, { "epoch": 2.39, "learning_rate": 3.812760309396311e-05, "loss": 2.0148, "step": 52380 }, { "epoch": 2.39, "learning_rate": 3.8125314659709826e-05, "loss": 2.0807, "step": 52390 }, { "epoch": 2.39, "learning_rate": 3.812302622545654e-05, "loss": 2.0798, "step": 52400 }, { "epoch": 2.39, "learning_rate": 3.812073779120326e-05, "loss": 2.2705, "step": 52410 }, { "epoch": 2.39, "learning_rate": 3.8118449356949975e-05, "loss": 2.0094, "step": 52420 }, { "epoch": 2.39, "learning_rate": 3.811616092269669e-05, "loss": 2.0424, "step": 52430 }, { "epoch": 2.39, "learning_rate": 3.811387248844341e-05, "loss": 2.3294, "step": 52440 }, { "epoch": 2.4, "learning_rate": 3.8111584054190124e-05, "loss": 2.1514, "step": 52450 }, { "epoch": 2.4, "learning_rate": 3.810929561993684e-05, "loss": 2.1985, "step": 52460 }, { "epoch": 2.4, "learning_rate": 3.810700718568356e-05, "loss": 2.1759, "step": 52470 }, { "epoch": 2.4, "learning_rate": 3.8104718751430274e-05, "loss": 2.1286, "step": 52480 }, { "epoch": 2.4, "learning_rate": 3.810243031717699e-05, "loss": 2.1398, "step": 52490 }, { "epoch": 2.4, "learning_rate": 3.810014188292371e-05, "loss": 2.1973, "step": 52500 }, { "epoch": 2.4, "learning_rate": 3.809785344867042e-05, "loss": 2.2333, "step": 52510 }, { "epoch": 2.4, "learning_rate": 3.809556501441714e-05, "loss": 2.0727, "step": 52520 }, { "epoch": 2.4, "learning_rate": 3.809327658016386e-05, "loss": 2.1888, "step": 52530 }, { "epoch": 2.4, "learning_rate": 3.809098814591057e-05, "loss": 2.0733, "step": 52540 }, { "epoch": 2.4, "learning_rate": 3.8088699711657286e-05, "loss": 2.1076, "step": 52550 }, { "epoch": 2.4, "learning_rate": 3.8086411277404e-05, "loss": 2.0779, "step": 52560 }, { "epoch": 2.4, "learning_rate": 3.8084122843150714e-05, "loss": 2.1791, "step": 52570 }, { "epoch": 2.4, "learning_rate": 3.8081834408897435e-05, "loss": 2.1247, "step": 52580 }, { "epoch": 2.4, "learning_rate": 3.807954597464415e-05, "loss": 2.0842, "step": 52590 }, { "epoch": 2.4, "learning_rate": 3.8077257540390864e-05, "loss": 2.0796, "step": 52600 }, { "epoch": 2.4, "learning_rate": 3.8074969106137584e-05, "loss": 2.0742, "step": 52610 }, { "epoch": 2.4, "learning_rate": 3.80726806718843e-05, "loss": 2.078, "step": 52620 }, { "epoch": 2.4, "learning_rate": 3.807039223763101e-05, "loss": 2.1513, "step": 52630 }, { "epoch": 2.4, "learning_rate": 3.8068103803377734e-05, "loss": 2.0843, "step": 52640 }, { "epoch": 2.4, "learning_rate": 3.806581536912445e-05, "loss": 2.1033, "step": 52650 }, { "epoch": 2.4, "learning_rate": 3.806352693487116e-05, "loss": 2.2575, "step": 52660 }, { "epoch": 2.41, "learning_rate": 3.806123850061788e-05, "loss": 2.0291, "step": 52670 }, { "epoch": 2.41, "learning_rate": 3.80589500663646e-05, "loss": 2.2239, "step": 52680 }, { "epoch": 2.41, "learning_rate": 3.805666163211131e-05, "loss": 2.1779, "step": 52690 }, { "epoch": 2.41, "learning_rate": 3.805437319785803e-05, "loss": 2.2619, "step": 52700 }, { "epoch": 2.41, "learning_rate": 3.8052084763604746e-05, "loss": 2.1516, "step": 52710 }, { "epoch": 2.41, "learning_rate": 3.804979632935146e-05, "loss": 2.1331, "step": 52720 }, { "epoch": 2.41, "learning_rate": 3.804750789509818e-05, "loss": 2.0659, "step": 52730 }, { "epoch": 2.41, "learning_rate": 3.8045219460844895e-05, "loss": 2.1822, "step": 52740 }, { "epoch": 2.41, "learning_rate": 3.804293102659161e-05, "loss": 2.1659, "step": 52750 }, { "epoch": 2.41, "learning_rate": 3.8040642592338324e-05, "loss": 2.1424, "step": 52760 }, { "epoch": 2.41, "learning_rate": 3.803835415808504e-05, "loss": 1.9904, "step": 52770 }, { "epoch": 2.41, "learning_rate": 3.803606572383175e-05, "loss": 2.1114, "step": 52780 }, { "epoch": 2.41, "learning_rate": 3.803377728957847e-05, "loss": 2.0109, "step": 52790 }, { "epoch": 2.41, "learning_rate": 3.803148885532519e-05, "loss": 2.1658, "step": 52800 }, { "epoch": 2.41, "learning_rate": 3.80292004210719e-05, "loss": 2.1871, "step": 52810 }, { "epoch": 2.41, "learning_rate": 3.802691198681862e-05, "loss": 2.0582, "step": 52820 }, { "epoch": 2.41, "learning_rate": 3.8024623552565336e-05, "loss": 2.291, "step": 52830 }, { "epoch": 2.41, "learning_rate": 3.802233511831205e-05, "loss": 2.1873, "step": 52840 }, { "epoch": 2.41, "learning_rate": 3.802004668405877e-05, "loss": 2.0784, "step": 52850 }, { "epoch": 2.41, "learning_rate": 3.8017758249805485e-05, "loss": 2.1917, "step": 52860 }, { "epoch": 2.41, "learning_rate": 3.80154698155522e-05, "loss": 2.0327, "step": 52870 }, { "epoch": 2.41, "learning_rate": 3.801318138129892e-05, "loss": 2.1907, "step": 52880 }, { "epoch": 2.42, "learning_rate": 3.8010892947045634e-05, "loss": 2.1103, "step": 52890 }, { "epoch": 2.42, "learning_rate": 3.800860451279235e-05, "loss": 1.929, "step": 52900 }, { "epoch": 2.42, "learning_rate": 3.800631607853907e-05, "loss": 2.1073, "step": 52910 }, { "epoch": 2.42, "learning_rate": 3.8004027644285784e-05, "loss": 2.12, "step": 52920 }, { "epoch": 2.42, "learning_rate": 3.80017392100325e-05, "loss": 2.2031, "step": 52930 }, { "epoch": 2.42, "learning_rate": 3.799945077577922e-05, "loss": 2.0195, "step": 52940 }, { "epoch": 2.42, "learning_rate": 3.7997162341525926e-05, "loss": 2.0624, "step": 52950 }, { "epoch": 2.42, "learning_rate": 3.799487390727264e-05, "loss": 2.2197, "step": 52960 }, { "epoch": 2.42, "learning_rate": 3.799258547301936e-05, "loss": 2.1126, "step": 52970 }, { "epoch": 2.42, "learning_rate": 3.7990297038766075e-05, "loss": 2.0331, "step": 52980 }, { "epoch": 2.42, "learning_rate": 3.798800860451279e-05, "loss": 1.9307, "step": 52990 }, { "epoch": 2.42, "learning_rate": 3.798572017025951e-05, "loss": 2.0475, "step": 53000 }, { "epoch": 2.42, "learning_rate": 3.7983431736006224e-05, "loss": 2.2208, "step": 53010 }, { "epoch": 2.42, "learning_rate": 3.798114330175294e-05, "loss": 2.0825, "step": 53020 }, { "epoch": 2.42, "learning_rate": 3.797885486749966e-05, "loss": 2.1728, "step": 53030 }, { "epoch": 2.42, "learning_rate": 3.7976566433246374e-05, "loss": 2.0718, "step": 53040 }, { "epoch": 2.42, "learning_rate": 3.797427799899309e-05, "loss": 2.0701, "step": 53050 }, { "epoch": 2.42, "learning_rate": 3.797198956473981e-05, "loss": 2.2203, "step": 53060 }, { "epoch": 2.42, "learning_rate": 3.796970113048652e-05, "loss": 2.1153, "step": 53070 }, { "epoch": 2.42, "learning_rate": 3.796741269623324e-05, "loss": 2.0301, "step": 53080 }, { "epoch": 2.42, "learning_rate": 3.796512426197996e-05, "loss": 2.2341, "step": 53090 }, { "epoch": 2.42, "learning_rate": 3.796283582772667e-05, "loss": 2.0829, "step": 53100 }, { "epoch": 2.43, "learning_rate": 3.7960547393473386e-05, "loss": 2.1681, "step": 53110 }, { "epoch": 2.43, "learning_rate": 3.795825895922011e-05, "loss": 2.2194, "step": 53120 }, { "epoch": 2.43, "learning_rate": 3.795597052496682e-05, "loss": 2.1188, "step": 53130 }, { "epoch": 2.43, "learning_rate": 3.7953682090713535e-05, "loss": 2.1679, "step": 53140 }, { "epoch": 2.43, "learning_rate": 3.795139365646025e-05, "loss": 2.1072, "step": 53150 }, { "epoch": 2.43, "learning_rate": 3.7949105222206963e-05, "loss": 2.3261, "step": 53160 }, { "epoch": 2.43, "learning_rate": 3.7946816787953684e-05, "loss": 2.1357, "step": 53170 }, { "epoch": 2.43, "learning_rate": 3.79445283537004e-05, "loss": 2.0543, "step": 53180 }, { "epoch": 2.43, "learning_rate": 3.794223991944711e-05, "loss": 1.9741, "step": 53190 }, { "epoch": 2.43, "learning_rate": 3.7939951485193834e-05, "loss": 2.176, "step": 53200 }, { "epoch": 2.43, "learning_rate": 3.793766305094055e-05, "loss": 2.1456, "step": 53210 }, { "epoch": 2.43, "learning_rate": 3.793537461668726e-05, "loss": 2.1509, "step": 53220 }, { "epoch": 2.43, "learning_rate": 3.793308618243398e-05, "loss": 2.2333, "step": 53230 }, { "epoch": 2.43, "learning_rate": 3.79307977481807e-05, "loss": 2.1391, "step": 53240 }, { "epoch": 2.43, "learning_rate": 3.792850931392741e-05, "loss": 2.1944, "step": 53250 }, { "epoch": 2.43, "learning_rate": 3.792622087967413e-05, "loss": 2.1621, "step": 53260 }, { "epoch": 2.43, "learning_rate": 3.7923932445420846e-05, "loss": 2.1833, "step": 53270 }, { "epoch": 2.43, "learning_rate": 3.792164401116756e-05, "loss": 2.0843, "step": 53280 }, { "epoch": 2.43, "learning_rate": 3.791935557691428e-05, "loss": 2.1605, "step": 53290 }, { "epoch": 2.43, "learning_rate": 3.7917067142660995e-05, "loss": 2.0789, "step": 53300 }, { "epoch": 2.43, "learning_rate": 3.791477870840771e-05, "loss": 2.1625, "step": 53310 }, { "epoch": 2.43, "learning_rate": 3.791249027415443e-05, "loss": 2.0782, "step": 53320 }, { "epoch": 2.44, "learning_rate": 3.7910201839901144e-05, "loss": 2.1949, "step": 53330 }, { "epoch": 2.44, "learning_rate": 3.790791340564786e-05, "loss": 2.0308, "step": 53340 }, { "epoch": 2.44, "learning_rate": 3.790562497139457e-05, "loss": 1.9362, "step": 53350 }, { "epoch": 2.44, "learning_rate": 3.790333653714129e-05, "loss": 2.1088, "step": 53360 }, { "epoch": 2.44, "learning_rate": 3.7901048102888e-05, "loss": 2.0902, "step": 53370 }, { "epoch": 2.44, "learning_rate": 3.789875966863472e-05, "loss": 1.9888, "step": 53380 }, { "epoch": 2.44, "learning_rate": 3.7896471234381436e-05, "loss": 2.2595, "step": 53390 }, { "epoch": 2.44, "learning_rate": 3.789418280012815e-05, "loss": 2.1279, "step": 53400 }, { "epoch": 2.44, "learning_rate": 3.789189436587487e-05, "loss": 2.1651, "step": 53410 }, { "epoch": 2.44, "learning_rate": 3.7889605931621585e-05, "loss": 2.0457, "step": 53420 }, { "epoch": 2.44, "learning_rate": 3.78873174973683e-05, "loss": 2.244, "step": 53430 }, { "epoch": 2.44, "learning_rate": 3.788502906311502e-05, "loss": 2.0681, "step": 53440 }, { "epoch": 2.44, "learning_rate": 3.7882740628861734e-05, "loss": 2.2279, "step": 53450 }, { "epoch": 2.44, "learning_rate": 3.788045219460845e-05, "loss": 2.0687, "step": 53460 }, { "epoch": 2.44, "learning_rate": 3.787816376035517e-05, "loss": 2.1475, "step": 53470 }, { "epoch": 2.44, "learning_rate": 3.7875875326101883e-05, "loss": 2.0785, "step": 53480 }, { "epoch": 2.44, "learning_rate": 3.78735868918486e-05, "loss": 2.0496, "step": 53490 }, { "epoch": 2.44, "learning_rate": 3.787129845759532e-05, "loss": 2.0491, "step": 53500 }, { "epoch": 2.44, "learning_rate": 3.786901002334203e-05, "loss": 2.371, "step": 53510 }, { "epoch": 2.44, "learning_rate": 3.786672158908875e-05, "loss": 2.0653, "step": 53520 }, { "epoch": 2.44, "learning_rate": 3.786443315483547e-05, "loss": 2.2696, "step": 53530 }, { "epoch": 2.44, "learning_rate": 3.786214472058218e-05, "loss": 2.0634, "step": 53540 }, { "epoch": 2.45, "learning_rate": 3.7859856286328896e-05, "loss": 1.9371, "step": 53550 }, { "epoch": 2.45, "learning_rate": 3.785756785207561e-05, "loss": 2.2017, "step": 53560 }, { "epoch": 2.45, "learning_rate": 3.7855279417822324e-05, "loss": 2.2538, "step": 53570 }, { "epoch": 2.45, "learning_rate": 3.7852990983569045e-05, "loss": 2.1097, "step": 53580 }, { "epoch": 2.45, "learning_rate": 3.785070254931576e-05, "loss": 2.1349, "step": 53590 }, { "epoch": 2.45, "learning_rate": 3.7848414115062473e-05, "loss": 1.99, "step": 53600 }, { "epoch": 2.45, "learning_rate": 3.7846125680809194e-05, "loss": 2.0733, "step": 53610 }, { "epoch": 2.45, "learning_rate": 3.784383724655591e-05, "loss": 2.0347, "step": 53620 }, { "epoch": 2.45, "learning_rate": 3.784154881230262e-05, "loss": 2.1611, "step": 53630 }, { "epoch": 2.45, "learning_rate": 3.7839260378049344e-05, "loss": 2.2396, "step": 53640 }, { "epoch": 2.45, "learning_rate": 3.783697194379606e-05, "loss": 2.1437, "step": 53650 }, { "epoch": 2.45, "learning_rate": 3.783468350954277e-05, "loss": 2.2102, "step": 53660 }, { "epoch": 2.45, "learning_rate": 3.783239507528949e-05, "loss": 2.064, "step": 53670 }, { "epoch": 2.45, "learning_rate": 3.783010664103621e-05, "loss": 2.3024, "step": 53680 }, { "epoch": 2.45, "learning_rate": 3.782781820678292e-05, "loss": 2.1705, "step": 53690 }, { "epoch": 2.45, "learning_rate": 3.782552977252964e-05, "loss": 2.0891, "step": 53700 }, { "epoch": 2.45, "learning_rate": 3.7823241338276356e-05, "loss": 2.0778, "step": 53710 }, { "epoch": 2.45, "learning_rate": 3.782095290402307e-05, "loss": 2.2993, "step": 53720 }, { "epoch": 2.45, "learning_rate": 3.781866446976979e-05, "loss": 2.1216, "step": 53730 }, { "epoch": 2.45, "learning_rate": 3.78163760355165e-05, "loss": 1.9559, "step": 53740 }, { "epoch": 2.45, "learning_rate": 3.781408760126321e-05, "loss": 2.008, "step": 53750 }, { "epoch": 2.45, "learning_rate": 3.7811799167009933e-05, "loss": 2.1248, "step": 53760 }, { "epoch": 2.46, "learning_rate": 3.780951073275665e-05, "loss": 2.1724, "step": 53770 }, { "epoch": 2.46, "learning_rate": 3.780722229850336e-05, "loss": 2.0042, "step": 53780 }, { "epoch": 2.46, "learning_rate": 3.780493386425008e-05, "loss": 2.1415, "step": 53790 }, { "epoch": 2.46, "learning_rate": 3.78026454299968e-05, "loss": 2.0963, "step": 53800 }, { "epoch": 2.46, "learning_rate": 3.780035699574351e-05, "loss": 2.1548, "step": 53810 }, { "epoch": 2.46, "learning_rate": 3.779806856149023e-05, "loss": 2.0244, "step": 53820 }, { "epoch": 2.46, "learning_rate": 3.7795780127236946e-05, "loss": 2.3335, "step": 53830 }, { "epoch": 2.46, "learning_rate": 3.779349169298366e-05, "loss": 2.0449, "step": 53840 }, { "epoch": 2.46, "learning_rate": 3.779120325873038e-05, "loss": 2.1371, "step": 53850 }, { "epoch": 2.46, "learning_rate": 3.7788914824477095e-05, "loss": 2.146, "step": 53860 }, { "epoch": 2.46, "learning_rate": 3.778662639022381e-05, "loss": 2.1318, "step": 53870 }, { "epoch": 2.46, "learning_rate": 3.778433795597053e-05, "loss": 2.2394, "step": 53880 }, { "epoch": 2.46, "learning_rate": 3.7782049521717244e-05, "loss": 1.9614, "step": 53890 }, { "epoch": 2.46, "learning_rate": 3.777976108746396e-05, "loss": 2.1408, "step": 53900 }, { "epoch": 2.46, "learning_rate": 3.777747265321068e-05, "loss": 2.1683, "step": 53910 }, { "epoch": 2.46, "learning_rate": 3.7775184218957393e-05, "loss": 2.1511, "step": 53920 }, { "epoch": 2.46, "learning_rate": 3.777289578470411e-05, "loss": 2.1242, "step": 53930 }, { "epoch": 2.46, "learning_rate": 3.777060735045082e-05, "loss": 2.093, "step": 53940 }, { "epoch": 2.46, "learning_rate": 3.7768318916197536e-05, "loss": 2.0257, "step": 53950 }, { "epoch": 2.46, "learning_rate": 3.776603048194426e-05, "loss": 2.2051, "step": 53960 }, { "epoch": 2.46, "learning_rate": 3.776374204769097e-05, "loss": 1.8794, "step": 53970 }, { "epoch": 2.46, "learning_rate": 3.7761453613437685e-05, "loss": 2.1585, "step": 53980 }, { "epoch": 2.47, "learning_rate": 3.77591651791844e-05, "loss": 2.1476, "step": 53990 }, { "epoch": 2.47, "learning_rate": 3.775687674493112e-05, "loss": 2.187, "step": 54000 }, { "epoch": 2.47, "learning_rate": 3.7754588310677834e-05, "loss": 1.9884, "step": 54010 }, { "epoch": 2.47, "learning_rate": 3.775229987642455e-05, "loss": 2.2814, "step": 54020 }, { "epoch": 2.47, "learning_rate": 3.775001144217127e-05, "loss": 2.0072, "step": 54030 }, { "epoch": 2.47, "learning_rate": 3.7747723007917983e-05, "loss": 2.0974, "step": 54040 }, { "epoch": 2.47, "learning_rate": 3.77454345736647e-05, "loss": 2.1453, "step": 54050 }, { "epoch": 2.47, "learning_rate": 3.774314613941142e-05, "loss": 2.2102, "step": 54060 }, { "epoch": 2.47, "learning_rate": 3.774085770515813e-05, "loss": 2.0857, "step": 54070 }, { "epoch": 2.47, "learning_rate": 3.773856927090485e-05, "loss": 2.0816, "step": 54080 }, { "epoch": 2.47, "learning_rate": 3.773628083665157e-05, "loss": 2.1883, "step": 54090 }, { "epoch": 2.47, "learning_rate": 3.773399240239828e-05, "loss": 2.128, "step": 54100 }, { "epoch": 2.47, "learning_rate": 3.7731703968144996e-05, "loss": 2.1327, "step": 54110 }, { "epoch": 2.47, "learning_rate": 3.772941553389172e-05, "loss": 2.0472, "step": 54120 }, { "epoch": 2.47, "learning_rate": 3.772712709963843e-05, "loss": 2.282, "step": 54130 }, { "epoch": 2.47, "learning_rate": 3.7724838665385145e-05, "loss": 2.1409, "step": 54140 }, { "epoch": 2.47, "learning_rate": 3.772255023113186e-05, "loss": 2.23, "step": 54150 }, { "epoch": 2.47, "learning_rate": 3.772026179687857e-05, "loss": 2.0451, "step": 54160 }, { "epoch": 2.47, "learning_rate": 3.7717973362625294e-05, "loss": 2.0979, "step": 54170 }, { "epoch": 2.47, "learning_rate": 3.771568492837201e-05, "loss": 2.1663, "step": 54180 }, { "epoch": 2.47, "learning_rate": 3.771339649411872e-05, "loss": 2.0938, "step": 54190 }, { "epoch": 2.47, "learning_rate": 3.7711108059865443e-05, "loss": 2.0291, "step": 54200 }, { "epoch": 2.48, "learning_rate": 3.770881962561216e-05, "loss": 2.0964, "step": 54210 }, { "epoch": 2.48, "learning_rate": 3.770653119135887e-05, "loss": 2.0604, "step": 54220 }, { "epoch": 2.48, "learning_rate": 3.770424275710559e-05, "loss": 2.1846, "step": 54230 }, { "epoch": 2.48, "learning_rate": 3.770195432285231e-05, "loss": 2.1186, "step": 54240 }, { "epoch": 2.48, "learning_rate": 3.769966588859902e-05, "loss": 2.1838, "step": 54250 }, { "epoch": 2.48, "learning_rate": 3.769737745434574e-05, "loss": 2.257, "step": 54260 }, { "epoch": 2.48, "learning_rate": 3.7695089020092456e-05, "loss": 2.1841, "step": 54270 }, { "epoch": 2.48, "learning_rate": 3.769280058583917e-05, "loss": 2.2322, "step": 54280 }, { "epoch": 2.48, "learning_rate": 3.769051215158589e-05, "loss": 2.1207, "step": 54290 }, { "epoch": 2.48, "learning_rate": 3.7688223717332605e-05, "loss": 2.1201, "step": 54300 }, { "epoch": 2.48, "learning_rate": 3.768593528307932e-05, "loss": 2.1239, "step": 54310 }, { "epoch": 2.48, "learning_rate": 3.768364684882604e-05, "loss": 2.1198, "step": 54320 }, { "epoch": 2.48, "learning_rate": 3.7681358414572754e-05, "loss": 2.2291, "step": 54330 }, { "epoch": 2.48, "learning_rate": 3.767906998031946e-05, "loss": 2.2334, "step": 54340 }, { "epoch": 2.48, "learning_rate": 3.767678154606618e-05, "loss": 2.0215, "step": 54350 }, { "epoch": 2.48, "learning_rate": 3.76744931118129e-05, "loss": 2.0736, "step": 54360 }, { "epoch": 2.48, "learning_rate": 3.767220467755961e-05, "loss": 2.1758, "step": 54370 }, { "epoch": 2.48, "learning_rate": 3.766991624330633e-05, "loss": 2.1217, "step": 54380 }, { "epoch": 2.48, "learning_rate": 3.7667627809053046e-05, "loss": 2.0264, "step": 54390 }, { "epoch": 2.48, "learning_rate": 3.766533937479976e-05, "loss": 2.1568, "step": 54400 }, { "epoch": 2.48, "learning_rate": 3.766305094054648e-05, "loss": 2.1963, "step": 54410 }, { "epoch": 2.48, "learning_rate": 3.7660762506293195e-05, "loss": 2.0391, "step": 54420 }, { "epoch": 2.49, "learning_rate": 3.765847407203991e-05, "loss": 2.1109, "step": 54430 }, { "epoch": 2.49, "learning_rate": 3.765618563778663e-05, "loss": 2.0139, "step": 54440 }, { "epoch": 2.49, "learning_rate": 3.7653897203533344e-05, "loss": 1.9432, "step": 54450 }, { "epoch": 2.49, "learning_rate": 3.765160876928006e-05, "loss": 2.0076, "step": 54460 }, { "epoch": 2.49, "learning_rate": 3.764932033502678e-05, "loss": 2.0004, "step": 54470 }, { "epoch": 2.49, "learning_rate": 3.764703190077349e-05, "loss": 2.0229, "step": 54480 }, { "epoch": 2.49, "learning_rate": 3.764474346652021e-05, "loss": 2.139, "step": 54490 }, { "epoch": 2.49, "learning_rate": 3.764245503226693e-05, "loss": 2.2635, "step": 54500 }, { "epoch": 2.49, "learning_rate": 3.764016659801364e-05, "loss": 2.0478, "step": 54510 }, { "epoch": 2.49, "learning_rate": 3.763787816376036e-05, "loss": 2.1591, "step": 54520 }, { "epoch": 2.49, "learning_rate": 3.763558972950707e-05, "loss": 2.0413, "step": 54530 }, { "epoch": 2.49, "learning_rate": 3.7633301295253785e-05, "loss": 2.0933, "step": 54540 }, { "epoch": 2.49, "learning_rate": 3.7631012861000506e-05, "loss": 2.1289, "step": 54550 }, { "epoch": 2.49, "learning_rate": 3.762872442674722e-05, "loss": 2.066, "step": 54560 }, { "epoch": 2.49, "learning_rate": 3.7626435992493934e-05, "loss": 2.2209, "step": 54570 }, { "epoch": 2.49, "learning_rate": 3.7624147558240655e-05, "loss": 2.0381, "step": 54580 }, { "epoch": 2.49, "learning_rate": 3.762185912398737e-05, "loss": 2.2362, "step": 54590 }, { "epoch": 2.49, "learning_rate": 3.761957068973408e-05, "loss": 2.0625, "step": 54600 }, { "epoch": 2.49, "learning_rate": 3.7617282255480804e-05, "loss": 2.0333, "step": 54610 }, { "epoch": 2.49, "learning_rate": 3.761499382122752e-05, "loss": 2.2062, "step": 54620 }, { "epoch": 2.49, "learning_rate": 3.761270538697423e-05, "loss": 2.1475, "step": 54630 }, { "epoch": 2.5, "learning_rate": 3.761041695272095e-05, "loss": 2.0611, "step": 54640 }, { "epoch": 2.5, "learning_rate": 3.760812851846767e-05, "loss": 2.0139, "step": 54650 }, { "epoch": 2.5, "learning_rate": 3.760584008421438e-05, "loss": 2.0736, "step": 54660 }, { "epoch": 2.5, "learning_rate": 3.76035516499611e-05, "loss": 2.1659, "step": 54670 }, { "epoch": 2.5, "learning_rate": 3.760126321570782e-05, "loss": 1.9343, "step": 54680 }, { "epoch": 2.5, "learning_rate": 3.759897478145453e-05, "loss": 2.082, "step": 54690 }, { "epoch": 2.5, "learning_rate": 3.759668634720125e-05, "loss": 2.2516, "step": 54700 }, { "epoch": 2.5, "learning_rate": 3.7594397912947966e-05, "loss": 2.1011, "step": 54710 }, { "epoch": 2.5, "learning_rate": 3.759210947869468e-05, "loss": 2.058, "step": 54720 }, { "epoch": 2.5, "learning_rate": 3.7589821044441394e-05, "loss": 2.1, "step": 54730 }, { "epoch": 2.5, "learning_rate": 3.758753261018811e-05, "loss": 2.1412, "step": 54740 }, { "epoch": 2.5, "learning_rate": 3.758524417593482e-05, "loss": 2.0841, "step": 54750 }, { "epoch": 2.5, "learning_rate": 3.758295574168154e-05, "loss": 2.0763, "step": 54760 }, { "epoch": 2.5, "learning_rate": 3.758066730742826e-05, "loss": 2.0458, "step": 54770 }, { "epoch": 2.5, "learning_rate": 3.757837887317497e-05, "loss": 1.92, "step": 54780 }, { "epoch": 2.5, "learning_rate": 3.757609043892169e-05, "loss": 2.0207, "step": 54790 }, { "epoch": 2.5, "learning_rate": 3.757380200466841e-05, "loss": 2.3135, "step": 54800 }, { "epoch": 2.5, "learning_rate": 3.757151357041512e-05, "loss": 2.1754, "step": 54810 }, { "epoch": 2.5, "learning_rate": 3.756922513616184e-05, "loss": 2.2306, "step": 54820 }, { "epoch": 2.5, "learning_rate": 3.7566936701908556e-05, "loss": 2.1368, "step": 54830 }, { "epoch": 2.5, "learning_rate": 3.756464826765527e-05, "loss": 2.1794, "step": 54840 }, { "epoch": 2.5, "learning_rate": 3.756235983340199e-05, "loss": 2.0432, "step": 54850 }, { "epoch": 2.51, "learning_rate": 3.7560071399148705e-05, "loss": 2.102, "step": 54860 }, { "epoch": 2.51, "learning_rate": 3.755778296489542e-05, "loss": 2.0035, "step": 54870 }, { "epoch": 2.51, "learning_rate": 3.755549453064214e-05, "loss": 2.1105, "step": 54880 }, { "epoch": 2.51, "learning_rate": 3.7553206096388854e-05, "loss": 2.0933, "step": 54890 }, { "epoch": 2.51, "learning_rate": 3.755091766213557e-05, "loss": 2.1292, "step": 54900 }, { "epoch": 2.51, "learning_rate": 3.754862922788229e-05, "loss": 2.0668, "step": 54910 }, { "epoch": 2.51, "learning_rate": 3.7546340793629e-05, "loss": 2.0593, "step": 54920 }, { "epoch": 2.51, "learning_rate": 3.754405235937572e-05, "loss": 2.1375, "step": 54930 }, { "epoch": 2.51, "learning_rate": 3.754176392512243e-05, "loss": 2.1503, "step": 54940 }, { "epoch": 2.51, "learning_rate": 3.7539475490869146e-05, "loss": 2.1479, "step": 54950 }, { "epoch": 2.51, "learning_rate": 3.753718705661587e-05, "loss": 2.085, "step": 54960 }, { "epoch": 2.51, "learning_rate": 3.753489862236258e-05, "loss": 2.113, "step": 54970 }, { "epoch": 2.51, "learning_rate": 3.7532610188109295e-05, "loss": 2.0548, "step": 54980 }, { "epoch": 2.51, "learning_rate": 3.7530321753856016e-05, "loss": 1.9557, "step": 54990 }, { "epoch": 2.51, "learning_rate": 3.752803331960273e-05, "loss": 2.1054, "step": 55000 }, { "epoch": 2.51, "learning_rate": 3.7525744885349444e-05, "loss": 2.1471, "step": 55010 }, { "epoch": 2.51, "learning_rate": 3.7523456451096165e-05, "loss": 2.1722, "step": 55020 }, { "epoch": 2.51, "learning_rate": 3.752116801684288e-05, "loss": 2.1574, "step": 55030 }, { "epoch": 2.51, "learning_rate": 3.751887958258959e-05, "loss": 2.0194, "step": 55040 }, { "epoch": 2.51, "learning_rate": 3.7516591148336314e-05, "loss": 2.2728, "step": 55050 }, { "epoch": 2.51, "learning_rate": 3.751430271408303e-05, "loss": 2.1713, "step": 55060 }, { "epoch": 2.51, "learning_rate": 3.751201427982974e-05, "loss": 2.1289, "step": 55070 }, { "epoch": 2.52, "learning_rate": 3.750972584557646e-05, "loss": 2.1705, "step": 55080 }, { "epoch": 2.52, "learning_rate": 3.750743741132318e-05, "loss": 2.0242, "step": 55090 }, { "epoch": 2.52, "learning_rate": 3.750514897706989e-05, "loss": 2.172, "step": 55100 }, { "epoch": 2.52, "learning_rate": 3.7502860542816606e-05, "loss": 2.261, "step": 55110 }, { "epoch": 2.52, "learning_rate": 3.750057210856333e-05, "loss": 2.0891, "step": 55120 }, { "epoch": 2.52, "learning_rate": 3.7498283674310034e-05, "loss": 2.1263, "step": 55130 }, { "epoch": 2.52, "learning_rate": 3.7495995240056755e-05, "loss": 2.096, "step": 55140 }, { "epoch": 2.52, "learning_rate": 3.749370680580347e-05, "loss": 2.0259, "step": 55150 }, { "epoch": 2.52, "learning_rate": 3.749141837155018e-05, "loss": 2.1327, "step": 55160 }, { "epoch": 2.52, "learning_rate": 3.7489129937296904e-05, "loss": 2.2196, "step": 55170 }, { "epoch": 2.52, "learning_rate": 3.748684150304362e-05, "loss": 2.0359, "step": 55180 }, { "epoch": 2.52, "learning_rate": 3.748455306879033e-05, "loss": 2.0359, "step": 55190 }, { "epoch": 2.52, "learning_rate": 3.748226463453705e-05, "loss": 1.9704, "step": 55200 }, { "epoch": 2.52, "learning_rate": 3.747997620028377e-05, "loss": 2.1423, "step": 55210 }, { "epoch": 2.52, "learning_rate": 3.747768776603048e-05, "loss": 2.0366, "step": 55220 }, { "epoch": 2.52, "learning_rate": 3.74753993317772e-05, "loss": 2.0134, "step": 55230 }, { "epoch": 2.52, "learning_rate": 3.7473110897523917e-05, "loss": 2.1444, "step": 55240 }, { "epoch": 2.52, "learning_rate": 3.747082246327063e-05, "loss": 2.0472, "step": 55250 }, { "epoch": 2.52, "learning_rate": 3.746853402901735e-05, "loss": 2.0374, "step": 55260 }, { "epoch": 2.52, "learning_rate": 3.7466245594764066e-05, "loss": 2.1194, "step": 55270 }, { "epoch": 2.52, "learning_rate": 3.746395716051078e-05, "loss": 2.139, "step": 55280 }, { "epoch": 2.52, "learning_rate": 3.74616687262575e-05, "loss": 2.0818, "step": 55290 }, { "epoch": 2.53, "learning_rate": 3.7459380292004215e-05, "loss": 2.3483, "step": 55300 }, { "epoch": 2.53, "learning_rate": 3.745709185775093e-05, "loss": 2.1065, "step": 55310 }, { "epoch": 2.53, "learning_rate": 3.745480342349765e-05, "loss": 2.0943, "step": 55320 }, { "epoch": 2.53, "learning_rate": 3.745251498924436e-05, "loss": 2.2193, "step": 55330 }, { "epoch": 2.53, "learning_rate": 3.745022655499107e-05, "loss": 2.2056, "step": 55340 }, { "epoch": 2.53, "learning_rate": 3.744793812073779e-05, "loss": 2.0807, "step": 55350 }, { "epoch": 2.53, "learning_rate": 3.7445649686484507e-05, "loss": 2.2738, "step": 55360 }, { "epoch": 2.53, "learning_rate": 3.744336125223122e-05, "loss": 2.089, "step": 55370 }, { "epoch": 2.53, "learning_rate": 3.744107281797794e-05, "loss": 2.0134, "step": 55380 }, { "epoch": 2.53, "learning_rate": 3.7438784383724656e-05, "loss": 1.983, "step": 55390 }, { "epoch": 2.53, "learning_rate": 3.743649594947137e-05, "loss": 2.2485, "step": 55400 }, { "epoch": 2.53, "learning_rate": 3.743420751521809e-05, "loss": 2.1347, "step": 55410 }, { "epoch": 2.53, "learning_rate": 3.7431919080964805e-05, "loss": 2.1499, "step": 55420 }, { "epoch": 2.53, "learning_rate": 3.742963064671152e-05, "loss": 1.9851, "step": 55430 }, { "epoch": 2.53, "learning_rate": 3.742734221245824e-05, "loss": 2.1029, "step": 55440 }, { "epoch": 2.53, "learning_rate": 3.7425053778204954e-05, "loss": 2.08, "step": 55450 }, { "epoch": 2.53, "learning_rate": 3.742276534395167e-05, "loss": 2.0464, "step": 55460 }, { "epoch": 2.53, "learning_rate": 3.742047690969839e-05, "loss": 2.1049, "step": 55470 }, { "epoch": 2.53, "learning_rate": 3.74181884754451e-05, "loss": 2.0086, "step": 55480 }, { "epoch": 2.53, "learning_rate": 3.741590004119182e-05, "loss": 1.9812, "step": 55490 }, { "epoch": 2.53, "learning_rate": 3.741361160693854e-05, "loss": 2.1016, "step": 55500 }, { "epoch": 2.53, "learning_rate": 3.741132317268525e-05, "loss": 2.0955, "step": 55510 }, { "epoch": 2.54, "learning_rate": 3.7409034738431967e-05, "loss": 1.9562, "step": 55520 }, { "epoch": 2.54, "learning_rate": 3.740674630417868e-05, "loss": 2.1063, "step": 55530 }, { "epoch": 2.54, "learning_rate": 3.7404457869925395e-05, "loss": 2.1584, "step": 55540 }, { "epoch": 2.54, "learning_rate": 3.7402169435672116e-05, "loss": 2.0643, "step": 55550 }, { "epoch": 2.54, "learning_rate": 3.739988100141883e-05, "loss": 2.131, "step": 55560 }, { "epoch": 2.54, "learning_rate": 3.7397592567165544e-05, "loss": 2.2269, "step": 55570 }, { "epoch": 2.54, "learning_rate": 3.7395304132912265e-05, "loss": 2.1169, "step": 55580 }, { "epoch": 2.54, "learning_rate": 3.739301569865898e-05, "loss": 2.0759, "step": 55590 }, { "epoch": 2.54, "learning_rate": 3.739072726440569e-05, "loss": 2.1339, "step": 55600 }, { "epoch": 2.54, "learning_rate": 3.7388438830152414e-05, "loss": 2.1315, "step": 55610 }, { "epoch": 2.54, "learning_rate": 3.738615039589913e-05, "loss": 1.9543, "step": 55620 }, { "epoch": 2.54, "learning_rate": 3.738386196164584e-05, "loss": 2.061, "step": 55630 }, { "epoch": 2.54, "learning_rate": 3.738157352739256e-05, "loss": 2.1839, "step": 55640 }, { "epoch": 2.54, "learning_rate": 3.737928509313928e-05, "loss": 2.1556, "step": 55650 }, { "epoch": 2.54, "learning_rate": 3.737699665888599e-05, "loss": 2.0682, "step": 55660 }, { "epoch": 2.54, "learning_rate": 3.737470822463271e-05, "loss": 2.2796, "step": 55670 }, { "epoch": 2.54, "learning_rate": 3.7372419790379427e-05, "loss": 2.0511, "step": 55680 }, { "epoch": 2.54, "learning_rate": 3.737013135612614e-05, "loss": 2.2065, "step": 55690 }, { "epoch": 2.54, "learning_rate": 3.736784292187286e-05, "loss": 2.1125, "step": 55700 }, { "epoch": 2.54, "learning_rate": 3.7365554487619576e-05, "loss": 2.1026, "step": 55710 }, { "epoch": 2.54, "learning_rate": 3.736326605336628e-05, "loss": 2.2159, "step": 55720 }, { "epoch": 2.54, "learning_rate": 3.7360977619113004e-05, "loss": 2.1197, "step": 55730 }, { "epoch": 2.55, "learning_rate": 3.735868918485972e-05, "loss": 1.9935, "step": 55740 }, { "epoch": 2.55, "learning_rate": 3.735640075060643e-05, "loss": 2.1129, "step": 55750 }, { "epoch": 2.55, "learning_rate": 3.735411231635315e-05, "loss": 2.1198, "step": 55760 }, { "epoch": 2.55, "learning_rate": 3.735182388209987e-05, "loss": 2.0988, "step": 55770 }, { "epoch": 2.55, "learning_rate": 3.734953544784658e-05, "loss": 2.0689, "step": 55780 }, { "epoch": 2.55, "learning_rate": 3.73472470135933e-05, "loss": 2.0222, "step": 55790 }, { "epoch": 2.55, "learning_rate": 3.7344958579340016e-05, "loss": 2.0849, "step": 55800 }, { "epoch": 2.55, "learning_rate": 3.734267014508673e-05, "loss": 1.982, "step": 55810 }, { "epoch": 2.55, "learning_rate": 3.734038171083345e-05, "loss": 2.0699, "step": 55820 }, { "epoch": 2.55, "learning_rate": 3.7338093276580166e-05, "loss": 1.8595, "step": 55830 }, { "epoch": 2.55, "learning_rate": 3.733580484232688e-05, "loss": 2.139, "step": 55840 }, { "epoch": 2.55, "learning_rate": 3.73335164080736e-05, "loss": 2.0962, "step": 55850 }, { "epoch": 2.55, "learning_rate": 3.7331227973820315e-05, "loss": 2.1645, "step": 55860 }, { "epoch": 2.55, "learning_rate": 3.732893953956703e-05, "loss": 2.1424, "step": 55870 }, { "epoch": 2.55, "learning_rate": 3.732665110531375e-05, "loss": 2.1358, "step": 55880 }, { "epoch": 2.55, "learning_rate": 3.7324362671060464e-05, "loss": 2.1306, "step": 55890 }, { "epoch": 2.55, "learning_rate": 3.732207423680718e-05, "loss": 1.9823, "step": 55900 }, { "epoch": 2.55, "learning_rate": 3.73197858025539e-05, "loss": 2.3893, "step": 55910 }, { "epoch": 2.55, "learning_rate": 3.7317497368300606e-05, "loss": 2.1028, "step": 55920 }, { "epoch": 2.55, "learning_rate": 3.731520893404733e-05, "loss": 2.1897, "step": 55930 }, { "epoch": 2.55, "learning_rate": 3.731292049979404e-05, "loss": 2.216, "step": 55940 }, { "epoch": 2.55, "learning_rate": 3.7310632065540756e-05, "loss": 2.1686, "step": 55950 }, { "epoch": 2.56, "learning_rate": 3.7308343631287477e-05, "loss": 2.1201, "step": 55960 }, { "epoch": 2.56, "learning_rate": 3.730605519703419e-05, "loss": 1.9959, "step": 55970 }, { "epoch": 2.56, "learning_rate": 3.7303766762780905e-05, "loss": 2.1906, "step": 55980 }, { "epoch": 2.56, "learning_rate": 3.7301478328527626e-05, "loss": 2.1832, "step": 55990 }, { "epoch": 2.56, "learning_rate": 3.729918989427434e-05, "loss": 2.0154, "step": 56000 }, { "epoch": 2.56, "learning_rate": 3.7296901460021054e-05, "loss": 2.0906, "step": 56010 }, { "epoch": 2.56, "learning_rate": 3.7294613025767775e-05, "loss": 2.0976, "step": 56020 }, { "epoch": 2.56, "learning_rate": 3.729232459151449e-05, "loss": 1.9867, "step": 56030 }, { "epoch": 2.56, "learning_rate": 3.72900361572612e-05, "loss": 2.3639, "step": 56040 }, { "epoch": 2.56, "learning_rate": 3.7287747723007924e-05, "loss": 2.0905, "step": 56050 }, { "epoch": 2.56, "learning_rate": 3.728545928875464e-05, "loss": 2.0273, "step": 56060 }, { "epoch": 2.56, "learning_rate": 3.728317085450135e-05, "loss": 2.1819, "step": 56070 }, { "epoch": 2.56, "learning_rate": 3.728088242024807e-05, "loss": 2.126, "step": 56080 }, { "epoch": 2.56, "learning_rate": 3.727859398599479e-05, "loss": 2.3095, "step": 56090 }, { "epoch": 2.56, "learning_rate": 3.72763055517415e-05, "loss": 2.1854, "step": 56100 }, { "epoch": 2.56, "learning_rate": 3.727401711748822e-05, "loss": 2.0909, "step": 56110 }, { "epoch": 2.56, "learning_rate": 3.727172868323493e-05, "loss": 2.0859, "step": 56120 }, { "epoch": 2.56, "learning_rate": 3.7269440248981644e-05, "loss": 2.1535, "step": 56130 }, { "epoch": 2.56, "learning_rate": 3.7267151814728365e-05, "loss": 2.0597, "step": 56140 }, { "epoch": 2.56, "learning_rate": 3.726486338047508e-05, "loss": 2.1139, "step": 56150 }, { "epoch": 2.56, "learning_rate": 3.726257494622179e-05, "loss": 1.9371, "step": 56160 }, { "epoch": 2.56, "learning_rate": 3.7260286511968514e-05, "loss": 2.1455, "step": 56170 }, { "epoch": 2.57, "learning_rate": 3.725799807771523e-05, "loss": 2.1108, "step": 56180 }, { "epoch": 2.57, "learning_rate": 3.725570964346194e-05, "loss": 2.0544, "step": 56190 }, { "epoch": 2.57, "learning_rate": 3.725342120920866e-05, "loss": 2.2118, "step": 56200 }, { "epoch": 2.57, "learning_rate": 3.725113277495538e-05, "loss": 2.1087, "step": 56210 }, { "epoch": 2.57, "learning_rate": 3.724884434070209e-05, "loss": 2.1782, "step": 56220 }, { "epoch": 2.57, "learning_rate": 3.724655590644881e-05, "loss": 2.1361, "step": 56230 }, { "epoch": 2.57, "learning_rate": 3.7244267472195526e-05, "loss": 1.9604, "step": 56240 }, { "epoch": 2.57, "learning_rate": 3.724197903794224e-05, "loss": 2.0326, "step": 56250 }, { "epoch": 2.57, "learning_rate": 3.723969060368896e-05, "loss": 2.0931, "step": 56260 }, { "epoch": 2.57, "learning_rate": 3.7237402169435676e-05, "loss": 2.1684, "step": 56270 }, { "epoch": 2.57, "learning_rate": 3.723511373518239e-05, "loss": 2.0704, "step": 56280 }, { "epoch": 2.57, "learning_rate": 3.723282530092911e-05, "loss": 2.1083, "step": 56290 }, { "epoch": 2.57, "learning_rate": 3.7230536866675825e-05, "loss": 1.9887, "step": 56300 }, { "epoch": 2.57, "learning_rate": 3.722824843242254e-05, "loss": 2.0282, "step": 56310 }, { "epoch": 2.57, "learning_rate": 3.722595999816925e-05, "loss": 2.0284, "step": 56320 }, { "epoch": 2.57, "learning_rate": 3.722367156391597e-05, "loss": 2.0411, "step": 56330 }, { "epoch": 2.57, "learning_rate": 3.722138312966268e-05, "loss": 2.0316, "step": 56340 }, { "epoch": 2.57, "learning_rate": 3.72190946954094e-05, "loss": 2.1105, "step": 56350 }, { "epoch": 2.57, "learning_rate": 3.7216806261156116e-05, "loss": 2.0322, "step": 56360 }, { "epoch": 2.57, "learning_rate": 3.721451782690283e-05, "loss": 2.2606, "step": 56370 }, { "epoch": 2.57, "learning_rate": 3.721222939264955e-05, "loss": 2.1486, "step": 56380 }, { "epoch": 2.57, "learning_rate": 3.7209940958396266e-05, "loss": 2.1966, "step": 56390 }, { "epoch": 2.58, "learning_rate": 3.720765252414298e-05, "loss": 2.1207, "step": 56400 }, { "epoch": 2.58, "learning_rate": 3.72053640898897e-05, "loss": 2.0712, "step": 56410 }, { "epoch": 2.58, "learning_rate": 3.7203075655636415e-05, "loss": 1.9259, "step": 56420 }, { "epoch": 2.58, "learning_rate": 3.720078722138313e-05, "loss": 2.1587, "step": 56430 }, { "epoch": 2.58, "learning_rate": 3.719849878712985e-05, "loss": 1.9386, "step": 56440 }, { "epoch": 2.58, "learning_rate": 3.7196210352876564e-05, "loss": 2.1421, "step": 56450 }, { "epoch": 2.58, "learning_rate": 3.719392191862328e-05, "loss": 2.2357, "step": 56460 }, { "epoch": 2.58, "learning_rate": 3.719163348437e-05, "loss": 2.0748, "step": 56470 }, { "epoch": 2.58, "learning_rate": 3.718934505011671e-05, "loss": 2.0592, "step": 56480 }, { "epoch": 2.58, "learning_rate": 3.718705661586343e-05, "loss": 2.1674, "step": 56490 }, { "epoch": 2.58, "learning_rate": 3.718476818161015e-05, "loss": 1.9766, "step": 56500 }, { "epoch": 2.58, "learning_rate": 3.7182479747356855e-05, "loss": 2.0504, "step": 56510 }, { "epoch": 2.58, "learning_rate": 3.7180191313103576e-05, "loss": 2.0674, "step": 56520 }, { "epoch": 2.58, "learning_rate": 3.717790287885029e-05, "loss": 1.9916, "step": 56530 }, { "epoch": 2.58, "learning_rate": 3.7175614444597005e-05, "loss": 1.976, "step": 56540 }, { "epoch": 2.58, "learning_rate": 3.7173326010343726e-05, "loss": 2.058, "step": 56550 }, { "epoch": 2.58, "learning_rate": 3.717103757609044e-05, "loss": 2.0452, "step": 56560 }, { "epoch": 2.58, "learning_rate": 3.7168749141837154e-05, "loss": 2.289, "step": 56570 }, { "epoch": 2.58, "learning_rate": 3.7166460707583875e-05, "loss": 1.984, "step": 56580 }, { "epoch": 2.58, "learning_rate": 3.716417227333059e-05, "loss": 2.2293, "step": 56590 }, { "epoch": 2.58, "learning_rate": 3.71618838390773e-05, "loss": 2.0622, "step": 56600 }, { "epoch": 2.58, "learning_rate": 3.7159595404824024e-05, "loss": 2.0861, "step": 56610 }, { "epoch": 2.59, "learning_rate": 3.715730697057074e-05, "loss": 2.1458, "step": 56620 }, { "epoch": 2.59, "learning_rate": 3.715501853631745e-05, "loss": 2.1549, "step": 56630 }, { "epoch": 2.59, "learning_rate": 3.715273010206417e-05, "loss": 2.0968, "step": 56640 }, { "epoch": 2.59, "learning_rate": 3.715044166781089e-05, "loss": 2.0908, "step": 56650 }, { "epoch": 2.59, "learning_rate": 3.71481532335576e-05, "loss": 2.1658, "step": 56660 }, { "epoch": 2.59, "learning_rate": 3.714586479930432e-05, "loss": 2.0219, "step": 56670 }, { "epoch": 2.59, "learning_rate": 3.7143576365051036e-05, "loss": 1.9363, "step": 56680 }, { "epoch": 2.59, "learning_rate": 3.714128793079775e-05, "loss": 2.0062, "step": 56690 }, { "epoch": 2.59, "learning_rate": 3.713899949654447e-05, "loss": 2.1502, "step": 56700 }, { "epoch": 2.59, "learning_rate": 3.713671106229118e-05, "loss": 2.1248, "step": 56710 }, { "epoch": 2.59, "learning_rate": 3.713442262803789e-05, "loss": 2.1982, "step": 56720 }, { "epoch": 2.59, "learning_rate": 3.7132134193784614e-05, "loss": 2.1635, "step": 56730 }, { "epoch": 2.59, "learning_rate": 3.712984575953133e-05, "loss": 2.1156, "step": 56740 }, { "epoch": 2.59, "learning_rate": 3.712755732527804e-05, "loss": 2.0508, "step": 56750 }, { "epoch": 2.59, "learning_rate": 3.712526889102476e-05, "loss": 2.1805, "step": 56760 }, { "epoch": 2.59, "learning_rate": 3.712298045677148e-05, "loss": 2.0436, "step": 56770 }, { "epoch": 2.59, "learning_rate": 3.712069202251819e-05, "loss": 2.0156, "step": 56780 }, { "epoch": 2.59, "learning_rate": 3.711840358826491e-05, "loss": 2.1075, "step": 56790 }, { "epoch": 2.59, "learning_rate": 3.7116115154011626e-05, "loss": 2.1601, "step": 56800 }, { "epoch": 2.59, "learning_rate": 3.711382671975834e-05, "loss": 2.1399, "step": 56810 }, { "epoch": 2.59, "learning_rate": 3.711153828550506e-05, "loss": 2.016, "step": 56820 }, { "epoch": 2.6, "learning_rate": 3.7109249851251776e-05, "loss": 2.085, "step": 56830 }, { "epoch": 2.6, "learning_rate": 3.710696141699849e-05, "loss": 2.1813, "step": 56840 }, { "epoch": 2.6, "learning_rate": 3.710467298274521e-05, "loss": 2.1172, "step": 56850 }, { "epoch": 2.6, "learning_rate": 3.7102384548491925e-05, "loss": 2.1835, "step": 56860 }, { "epoch": 2.6, "learning_rate": 3.710009611423864e-05, "loss": 2.0947, "step": 56870 }, { "epoch": 2.6, "learning_rate": 3.709780767998536e-05, "loss": 2.1186, "step": 56880 }, { "epoch": 2.6, "learning_rate": 3.7095519245732074e-05, "loss": 2.1105, "step": 56890 }, { "epoch": 2.6, "learning_rate": 3.709323081147879e-05, "loss": 2.0552, "step": 56900 }, { "epoch": 2.6, "learning_rate": 3.70909423772255e-05, "loss": 2.1916, "step": 56910 }, { "epoch": 2.6, "learning_rate": 3.7088653942972216e-05, "loss": 2.0467, "step": 56920 }, { "epoch": 2.6, "learning_rate": 3.708636550871894e-05, "loss": 1.9734, "step": 56930 }, { "epoch": 2.6, "learning_rate": 3.708407707446565e-05, "loss": 2.0334, "step": 56940 }, { "epoch": 2.6, "learning_rate": 3.7081788640212365e-05, "loss": 2.1035, "step": 56950 }, { "epoch": 2.6, "learning_rate": 3.7079500205959086e-05, "loss": 2.2254, "step": 56960 }, { "epoch": 2.6, "learning_rate": 3.70772117717058e-05, "loss": 1.9858, "step": 56970 }, { "epoch": 2.6, "learning_rate": 3.7074923337452515e-05, "loss": 2.1075, "step": 56980 }, { "epoch": 2.6, "learning_rate": 3.7072634903199236e-05, "loss": 2.1691, "step": 56990 }, { "epoch": 2.6, "learning_rate": 3.707034646894595e-05, "loss": 2.1118, "step": 57000 }, { "epoch": 2.6, "learning_rate": 3.7068058034692664e-05, "loss": 2.1634, "step": 57010 }, { "epoch": 2.6, "learning_rate": 3.7065769600439385e-05, "loss": 1.988, "step": 57020 }, { "epoch": 2.6, "learning_rate": 3.70634811661861e-05, "loss": 2.0036, "step": 57030 }, { "epoch": 2.6, "learning_rate": 3.706119273193281e-05, "loss": 2.1752, "step": 57040 }, { "epoch": 2.61, "learning_rate": 3.7058904297679534e-05, "loss": 2.0812, "step": 57050 }, { "epoch": 2.61, "learning_rate": 3.705661586342625e-05, "loss": 2.2399, "step": 57060 }, { "epoch": 2.61, "learning_rate": 3.705432742917296e-05, "loss": 2.0739, "step": 57070 }, { "epoch": 2.61, "learning_rate": 3.705203899491968e-05, "loss": 2.2504, "step": 57080 }, { "epoch": 2.61, "learning_rate": 3.70497505606664e-05, "loss": 1.8811, "step": 57090 }, { "epoch": 2.61, "learning_rate": 3.7047462126413105e-05, "loss": 2.2315, "step": 57100 }, { "epoch": 2.61, "learning_rate": 3.7045173692159825e-05, "loss": 2.0574, "step": 57110 }, { "epoch": 2.61, "learning_rate": 3.704288525790654e-05, "loss": 2.1994, "step": 57120 }, { "epoch": 2.61, "learning_rate": 3.7040596823653254e-05, "loss": 2.1616, "step": 57130 }, { "epoch": 2.61, "learning_rate": 3.7038308389399975e-05, "loss": 2.0416, "step": 57140 }, { "epoch": 2.61, "learning_rate": 3.703601995514669e-05, "loss": 2.214, "step": 57150 }, { "epoch": 2.61, "learning_rate": 3.70337315208934e-05, "loss": 2.1747, "step": 57160 }, { "epoch": 2.61, "learning_rate": 3.7031443086640124e-05, "loss": 1.9889, "step": 57170 }, { "epoch": 2.61, "learning_rate": 3.702915465238684e-05, "loss": 2.1854, "step": 57180 }, { "epoch": 2.61, "learning_rate": 3.702686621813355e-05, "loss": 1.9573, "step": 57190 }, { "epoch": 2.61, "learning_rate": 3.702457778388027e-05, "loss": 2.0146, "step": 57200 }, { "epoch": 2.61, "learning_rate": 3.702228934962699e-05, "loss": 2.0408, "step": 57210 }, { "epoch": 2.61, "learning_rate": 3.70200009153737e-05, "loss": 2.2372, "step": 57220 }, { "epoch": 2.61, "learning_rate": 3.701771248112042e-05, "loss": 2.2005, "step": 57230 }, { "epoch": 2.61, "learning_rate": 3.7015424046867136e-05, "loss": 2.204, "step": 57240 }, { "epoch": 2.61, "learning_rate": 3.701313561261385e-05, "loss": 2.0166, "step": 57250 }, { "epoch": 2.61, "learning_rate": 3.701084717836057e-05, "loss": 2.1909, "step": 57260 }, { "epoch": 2.62, "learning_rate": 3.7008558744107285e-05, "loss": 2.0834, "step": 57270 }, { "epoch": 2.62, "learning_rate": 3.7006270309854e-05, "loss": 2.1852, "step": 57280 }, { "epoch": 2.62, "learning_rate": 3.700398187560072e-05, "loss": 2.2445, "step": 57290 }, { "epoch": 2.62, "learning_rate": 3.700169344134743e-05, "loss": 2.127, "step": 57300 }, { "epoch": 2.62, "learning_rate": 3.699940500709415e-05, "loss": 1.91, "step": 57310 }, { "epoch": 2.62, "learning_rate": 3.699711657284086e-05, "loss": 1.9992, "step": 57320 }, { "epoch": 2.62, "learning_rate": 3.699482813858758e-05, "loss": 2.1168, "step": 57330 }, { "epoch": 2.62, "learning_rate": 3.69925397043343e-05, "loss": 2.0821, "step": 57340 }, { "epoch": 2.62, "learning_rate": 3.699025127008101e-05, "loss": 2.0383, "step": 57350 }, { "epoch": 2.62, "learning_rate": 3.6987962835827726e-05, "loss": 2.0528, "step": 57360 }, { "epoch": 2.62, "learning_rate": 3.698567440157445e-05, "loss": 2.0891, "step": 57370 }, { "epoch": 2.62, "learning_rate": 3.698338596732116e-05, "loss": 2.1402, "step": 57380 }, { "epoch": 2.62, "learning_rate": 3.6981097533067875e-05, "loss": 2.2331, "step": 57390 }, { "epoch": 2.62, "learning_rate": 3.6978809098814596e-05, "loss": 2.1411, "step": 57400 }, { "epoch": 2.62, "learning_rate": 3.697652066456131e-05, "loss": 2.3804, "step": 57410 }, { "epoch": 2.62, "learning_rate": 3.6974232230308025e-05, "loss": 1.9957, "step": 57420 }, { "epoch": 2.62, "learning_rate": 3.697194379605474e-05, "loss": 2.1818, "step": 57430 }, { "epoch": 2.62, "learning_rate": 3.696965536180146e-05, "loss": 2.2472, "step": 57440 }, { "epoch": 2.62, "learning_rate": 3.6967366927548174e-05, "loss": 2.0423, "step": 57450 }, { "epoch": 2.62, "learning_rate": 3.696507849329489e-05, "loss": 1.9403, "step": 57460 }, { "epoch": 2.62, "learning_rate": 3.696279005904161e-05, "loss": 2.0496, "step": 57470 }, { "epoch": 2.62, "learning_rate": 3.696050162478832e-05, "loss": 2.1438, "step": 57480 }, { "epoch": 2.63, "learning_rate": 3.695821319053504e-05, "loss": 2.0219, "step": 57490 }, { "epoch": 2.63, "learning_rate": 3.695592475628175e-05, "loss": 2.1455, "step": 57500 }, { "epoch": 2.63, "learning_rate": 3.6953636322028465e-05, "loss": 2.0774, "step": 57510 }, { "epoch": 2.63, "learning_rate": 3.6951347887775186e-05, "loss": 2.236, "step": 57520 }, { "epoch": 2.63, "learning_rate": 3.69490594535219e-05, "loss": 2.0611, "step": 57530 }, { "epoch": 2.63, "learning_rate": 3.6946771019268615e-05, "loss": 1.9862, "step": 57540 }, { "epoch": 2.63, "learning_rate": 3.6944482585015335e-05, "loss": 2.1007, "step": 57550 }, { "epoch": 2.63, "learning_rate": 3.694219415076205e-05, "loss": 2.1897, "step": 57560 }, { "epoch": 2.63, "learning_rate": 3.6939905716508764e-05, "loss": 1.9959, "step": 57570 }, { "epoch": 2.63, "learning_rate": 3.6937617282255485e-05, "loss": 1.9568, "step": 57580 }, { "epoch": 2.63, "learning_rate": 3.69353288480022e-05, "loss": 2.1252, "step": 57590 }, { "epoch": 2.63, "learning_rate": 3.693304041374891e-05, "loss": 2.1866, "step": 57600 }, { "epoch": 2.63, "learning_rate": 3.6930751979495634e-05, "loss": 2.0599, "step": 57610 }, { "epoch": 2.63, "learning_rate": 3.692846354524235e-05, "loss": 2.1702, "step": 57620 }, { "epoch": 2.63, "learning_rate": 3.692617511098906e-05, "loss": 1.8841, "step": 57630 }, { "epoch": 2.63, "learning_rate": 3.692388667673578e-05, "loss": 2.062, "step": 57640 }, { "epoch": 2.63, "learning_rate": 3.69215982424825e-05, "loss": 2.1176, "step": 57650 }, { "epoch": 2.63, "learning_rate": 3.691930980822921e-05, "loss": 2.0277, "step": 57660 }, { "epoch": 2.63, "learning_rate": 3.691702137397593e-05, "loss": 2.1791, "step": 57670 }, { "epoch": 2.63, "learning_rate": 3.6914732939722646e-05, "loss": 2.1433, "step": 57680 }, { "epoch": 2.63, "learning_rate": 3.691244450546936e-05, "loss": 2.1961, "step": 57690 }, { "epoch": 2.63, "learning_rate": 3.6910156071216075e-05, "loss": 2.192, "step": 57700 }, { "epoch": 2.64, "learning_rate": 3.690786763696279e-05, "loss": 2.0802, "step": 57710 }, { "epoch": 2.64, "learning_rate": 3.69055792027095e-05, "loss": 2.1859, "step": 57720 }, { "epoch": 2.64, "learning_rate": 3.6903290768456224e-05, "loss": 2.1206, "step": 57730 }, { "epoch": 2.64, "learning_rate": 3.690100233420294e-05, "loss": 2.1893, "step": 57740 }, { "epoch": 2.64, "learning_rate": 3.689871389994965e-05, "loss": 2.2148, "step": 57750 }, { "epoch": 2.64, "learning_rate": 3.689642546569637e-05, "loss": 2.2051, "step": 57760 }, { "epoch": 2.64, "learning_rate": 3.689413703144309e-05, "loss": 2.1028, "step": 57770 }, { "epoch": 2.64, "learning_rate": 3.68918485971898e-05, "loss": 2.1035, "step": 57780 }, { "epoch": 2.64, "learning_rate": 3.688956016293652e-05, "loss": 2.0984, "step": 57790 }, { "epoch": 2.64, "learning_rate": 3.6887271728683236e-05, "loss": 2.2376, "step": 57800 }, { "epoch": 2.64, "learning_rate": 3.688498329442995e-05, "loss": 2.0674, "step": 57810 }, { "epoch": 2.64, "learning_rate": 3.688269486017667e-05, "loss": 2.0492, "step": 57820 }, { "epoch": 2.64, "learning_rate": 3.6880406425923385e-05, "loss": 2.0615, "step": 57830 }, { "epoch": 2.64, "learning_rate": 3.68781179916701e-05, "loss": 2.1742, "step": 57840 }, { "epoch": 2.64, "learning_rate": 3.687582955741682e-05, "loss": 2.1133, "step": 57850 }, { "epoch": 2.64, "learning_rate": 3.6873541123163535e-05, "loss": 2.0094, "step": 57860 }, { "epoch": 2.64, "learning_rate": 3.687125268891025e-05, "loss": 2.0493, "step": 57870 }, { "epoch": 2.64, "learning_rate": 3.686896425465697e-05, "loss": 2.0532, "step": 57880 }, { "epoch": 2.64, "learning_rate": 3.686667582040368e-05, "loss": 2.0554, "step": 57890 }, { "epoch": 2.64, "learning_rate": 3.68643873861504e-05, "loss": 2.1449, "step": 57900 }, { "epoch": 2.64, "learning_rate": 3.686209895189711e-05, "loss": 2.0511, "step": 57910 }, { "epoch": 2.64, "learning_rate": 3.6859810517643826e-05, "loss": 2.2339, "step": 57920 }, { "epoch": 2.65, "learning_rate": 3.685752208339055e-05, "loss": 1.9878, "step": 57930 }, { "epoch": 2.65, "learning_rate": 3.685523364913726e-05, "loss": 2.1305, "step": 57940 }, { "epoch": 2.65, "learning_rate": 3.6852945214883975e-05, "loss": 2.1652, "step": 57950 }, { "epoch": 2.65, "learning_rate": 3.6850656780630696e-05, "loss": 2.121, "step": 57960 }, { "epoch": 2.65, "learning_rate": 3.684836834637741e-05, "loss": 2.1322, "step": 57970 }, { "epoch": 2.65, "learning_rate": 3.6846079912124124e-05, "loss": 2.1208, "step": 57980 }, { "epoch": 2.65, "learning_rate": 3.6843791477870845e-05, "loss": 2.1509, "step": 57990 }, { "epoch": 2.65, "learning_rate": 3.684150304361756e-05, "loss": 2.0819, "step": 58000 }, { "epoch": 2.65, "learning_rate": 3.6839214609364274e-05, "loss": 1.9741, "step": 58010 }, { "epoch": 2.65, "learning_rate": 3.6836926175110995e-05, "loss": 2.1994, "step": 58020 }, { "epoch": 2.65, "learning_rate": 3.683463774085771e-05, "loss": 2.0395, "step": 58030 }, { "epoch": 2.65, "learning_rate": 3.683234930660442e-05, "loss": 2.0517, "step": 58040 }, { "epoch": 2.65, "learning_rate": 3.6830060872351144e-05, "loss": 2.1196, "step": 58050 }, { "epoch": 2.65, "learning_rate": 3.682777243809786e-05, "loss": 2.0322, "step": 58060 }, { "epoch": 2.65, "learning_rate": 3.682548400384457e-05, "loss": 2.1182, "step": 58070 }, { "epoch": 2.65, "learning_rate": 3.682319556959129e-05, "loss": 2.0767, "step": 58080 }, { "epoch": 2.65, "learning_rate": 3.6820907135338e-05, "loss": 2.0735, "step": 58090 }, { "epoch": 2.65, "learning_rate": 3.6818618701084714e-05, "loss": 2.1428, "step": 58100 }, { "epoch": 2.65, "learning_rate": 3.6816330266831435e-05, "loss": 2.1034, "step": 58110 }, { "epoch": 2.65, "learning_rate": 3.681404183257815e-05, "loss": 2.0918, "step": 58120 }, { "epoch": 2.65, "learning_rate": 3.6811753398324864e-05, "loss": 2.2802, "step": 58130 }, { "epoch": 2.65, "learning_rate": 3.6809464964071585e-05, "loss": 2.0129, "step": 58140 }, { "epoch": 2.66, "learning_rate": 3.68071765298183e-05, "loss": 1.9744, "step": 58150 }, { "epoch": 2.66, "learning_rate": 3.680488809556501e-05, "loss": 2.0948, "step": 58160 }, { "epoch": 2.66, "learning_rate": 3.6802599661311734e-05, "loss": 2.0691, "step": 58170 }, { "epoch": 2.66, "learning_rate": 3.680031122705845e-05, "loss": 2.035, "step": 58180 }, { "epoch": 2.66, "learning_rate": 3.679802279280516e-05, "loss": 2.0859, "step": 58190 }, { "epoch": 2.66, "learning_rate": 3.679573435855188e-05, "loss": 2.0879, "step": 58200 }, { "epoch": 2.66, "learning_rate": 3.67934459242986e-05, "loss": 2.0706, "step": 58210 }, { "epoch": 2.66, "learning_rate": 3.679115749004531e-05, "loss": 2.0104, "step": 58220 }, { "epoch": 2.66, "learning_rate": 3.678886905579203e-05, "loss": 2.1681, "step": 58230 }, { "epoch": 2.66, "learning_rate": 3.6786580621538746e-05, "loss": 2.0866, "step": 58240 }, { "epoch": 2.66, "learning_rate": 3.678429218728546e-05, "loss": 2.0445, "step": 58250 }, { "epoch": 2.66, "learning_rate": 3.678200375303218e-05, "loss": 2.1082, "step": 58260 }, { "epoch": 2.66, "learning_rate": 3.6779715318778895e-05, "loss": 2.074, "step": 58270 }, { "epoch": 2.66, "learning_rate": 3.677742688452561e-05, "loss": 1.9681, "step": 58280 }, { "epoch": 2.66, "learning_rate": 3.6775138450272324e-05, "loss": 2.0447, "step": 58290 }, { "epoch": 2.66, "learning_rate": 3.677285001601904e-05, "loss": 2.2198, "step": 58300 }, { "epoch": 2.66, "learning_rate": 3.677056158176576e-05, "loss": 2.0048, "step": 58310 }, { "epoch": 2.66, "learning_rate": 3.676827314751247e-05, "loss": 2.1358, "step": 58320 }, { "epoch": 2.66, "learning_rate": 3.676598471325919e-05, "loss": 2.0368, "step": 58330 }, { "epoch": 2.66, "learning_rate": 3.676369627900591e-05, "loss": 2.0333, "step": 58340 }, { "epoch": 2.66, "learning_rate": 3.676140784475262e-05, "loss": 2.0603, "step": 58350 }, { "epoch": 2.66, "learning_rate": 3.6759119410499336e-05, "loss": 2.079, "step": 58360 }, { "epoch": 2.67, "learning_rate": 3.675683097624606e-05, "loss": 2.2012, "step": 58370 }, { "epoch": 2.67, "learning_rate": 3.675454254199277e-05, "loss": 1.9965, "step": 58380 }, { "epoch": 2.67, "learning_rate": 3.6752254107739485e-05, "loss": 2.0978, "step": 58390 }, { "epoch": 2.67, "learning_rate": 3.6749965673486206e-05, "loss": 2.0873, "step": 58400 }, { "epoch": 2.67, "learning_rate": 3.674767723923292e-05, "loss": 2.111, "step": 58410 }, { "epoch": 2.67, "learning_rate": 3.6745388804979634e-05, "loss": 2.0398, "step": 58420 }, { "epoch": 2.67, "learning_rate": 3.6743100370726355e-05, "loss": 2.0211, "step": 58430 }, { "epoch": 2.67, "learning_rate": 3.674081193647307e-05, "loss": 1.9855, "step": 58440 }, { "epoch": 2.67, "learning_rate": 3.6738523502219784e-05, "loss": 1.9722, "step": 58450 }, { "epoch": 2.67, "learning_rate": 3.6736235067966505e-05, "loss": 1.9974, "step": 58460 }, { "epoch": 2.67, "learning_rate": 3.673394663371322e-05, "loss": 1.9914, "step": 58470 }, { "epoch": 2.67, "learning_rate": 3.673165819945993e-05, "loss": 2.0814, "step": 58480 }, { "epoch": 2.67, "learning_rate": 3.672936976520665e-05, "loss": 2.0255, "step": 58490 }, { "epoch": 2.67, "learning_rate": 3.672708133095336e-05, "loss": 2.0348, "step": 58500 }, { "epoch": 2.67, "learning_rate": 3.6724792896700075e-05, "loss": 1.9936, "step": 58510 }, { "epoch": 2.67, "learning_rate": 3.6722504462446796e-05, "loss": 2.086, "step": 58520 }, { "epoch": 2.67, "learning_rate": 3.672021602819351e-05, "loss": 2.1141, "step": 58530 }, { "epoch": 2.67, "learning_rate": 3.6717927593940224e-05, "loss": 2.0745, "step": 58540 }, { "epoch": 2.67, "learning_rate": 3.6715639159686945e-05, "loss": 2.0881, "step": 58550 }, { "epoch": 2.67, "learning_rate": 3.671335072543366e-05, "loss": 2.0319, "step": 58560 }, { "epoch": 2.67, "learning_rate": 3.6711062291180374e-05, "loss": 2.0382, "step": 58570 }, { "epoch": 2.67, "learning_rate": 3.6708773856927094e-05, "loss": 2.1146, "step": 58580 }, { "epoch": 2.68, "learning_rate": 3.670648542267381e-05, "loss": 2.0615, "step": 58590 }, { "epoch": 2.68, "learning_rate": 3.670419698842052e-05, "loss": 2.056, "step": 58600 }, { "epoch": 2.68, "learning_rate": 3.6701908554167244e-05, "loss": 2.0126, "step": 58610 }, { "epoch": 2.68, "learning_rate": 3.669962011991396e-05, "loss": 2.1085, "step": 58620 }, { "epoch": 2.68, "learning_rate": 3.669733168566067e-05, "loss": 2.2038, "step": 58630 }, { "epoch": 2.68, "learning_rate": 3.669504325140739e-05, "loss": 2.178, "step": 58640 }, { "epoch": 2.68, "learning_rate": 3.669275481715411e-05, "loss": 2.1549, "step": 58650 }, { "epoch": 2.68, "learning_rate": 3.669046638290082e-05, "loss": 2.0473, "step": 58660 }, { "epoch": 2.68, "learning_rate": 3.668817794864754e-05, "loss": 2.0742, "step": 58670 }, { "epoch": 2.68, "learning_rate": 3.668588951439425e-05, "loss": 2.0494, "step": 58680 }, { "epoch": 2.68, "learning_rate": 3.6683601080140964e-05, "loss": 2.1063, "step": 58690 }, { "epoch": 2.68, "learning_rate": 3.6681312645887684e-05, "loss": 2.1687, "step": 58700 }, { "epoch": 2.68, "learning_rate": 3.66790242116344e-05, "loss": 2.2443, "step": 58710 }, { "epoch": 2.68, "learning_rate": 3.667673577738111e-05, "loss": 2.11, "step": 58720 }, { "epoch": 2.68, "learning_rate": 3.6674447343127834e-05, "loss": 2.0691, "step": 58730 }, { "epoch": 2.68, "learning_rate": 3.667215890887455e-05, "loss": 2.0252, "step": 58740 }, { "epoch": 2.68, "learning_rate": 3.666987047462126e-05, "loss": 2.12, "step": 58750 }, { "epoch": 2.68, "learning_rate": 3.666758204036798e-05, "loss": 2.2248, "step": 58760 }, { "epoch": 2.68, "learning_rate": 3.66652936061147e-05, "loss": 2.0469, "step": 58770 }, { "epoch": 2.68, "learning_rate": 3.666300517186141e-05, "loss": 1.9935, "step": 58780 }, { "epoch": 2.68, "learning_rate": 3.666071673760813e-05, "loss": 2.1996, "step": 58790 }, { "epoch": 2.68, "learning_rate": 3.6658428303354846e-05, "loss": 2.0409, "step": 58800 }, { "epoch": 2.69, "learning_rate": 3.665613986910156e-05, "loss": 1.9754, "step": 58810 }, { "epoch": 2.69, "learning_rate": 3.665385143484828e-05, "loss": 2.1229, "step": 58820 }, { "epoch": 2.69, "learning_rate": 3.6651563000594995e-05, "loss": 2.1164, "step": 58830 }, { "epoch": 2.69, "learning_rate": 3.664927456634171e-05, "loss": 2.0143, "step": 58840 }, { "epoch": 2.69, "learning_rate": 3.664698613208843e-05, "loss": 2.2061, "step": 58850 }, { "epoch": 2.69, "learning_rate": 3.6644697697835144e-05, "loss": 2.0938, "step": 58860 }, { "epoch": 2.69, "learning_rate": 3.664240926358186e-05, "loss": 2.1975, "step": 58870 }, { "epoch": 2.69, "learning_rate": 3.664012082932857e-05, "loss": 2.1209, "step": 58880 }, { "epoch": 2.69, "learning_rate": 3.663783239507529e-05, "loss": 2.1489, "step": 58890 }, { "epoch": 2.69, "learning_rate": 3.663554396082201e-05, "loss": 2.0082, "step": 58900 }, { "epoch": 2.69, "learning_rate": 3.663325552656872e-05, "loss": 2.1673, "step": 58910 }, { "epoch": 2.69, "learning_rate": 3.6630967092315436e-05, "loss": 2.139, "step": 58920 }, { "epoch": 2.69, "learning_rate": 3.662867865806216e-05, "loss": 2.1193, "step": 58930 }, { "epoch": 2.69, "learning_rate": 3.662639022380887e-05, "loss": 2.1824, "step": 58940 }, { "epoch": 2.69, "learning_rate": 3.6624101789555585e-05, "loss": 2.0977, "step": 58950 }, { "epoch": 2.69, "learning_rate": 3.6621813355302306e-05, "loss": 2.1328, "step": 58960 }, { "epoch": 2.69, "learning_rate": 3.661952492104902e-05, "loss": 2.0682, "step": 58970 }, { "epoch": 2.69, "learning_rate": 3.6617236486795734e-05, "loss": 2.0382, "step": 58980 }, { "epoch": 2.69, "learning_rate": 3.6614948052542455e-05, "loss": 2.1347, "step": 58990 }, { "epoch": 2.69, "learning_rate": 3.661265961828917e-05, "loss": 2.0539, "step": 59000 }, { "epoch": 2.69, "learning_rate": 3.6610371184035884e-05, "loss": 2.0745, "step": 59010 }, { "epoch": 2.7, "learning_rate": 3.6608082749782604e-05, "loss": 2.1605, "step": 59020 }, { "epoch": 2.7, "learning_rate": 3.660579431552932e-05, "loss": 2.1843, "step": 59030 }, { "epoch": 2.7, "learning_rate": 3.660350588127603e-05, "loss": 2.2229, "step": 59040 }, { "epoch": 2.7, "learning_rate": 3.6601217447022754e-05, "loss": 1.9905, "step": 59050 }, { "epoch": 2.7, "learning_rate": 3.659892901276947e-05, "loss": 2.0043, "step": 59060 }, { "epoch": 2.7, "learning_rate": 3.659664057851618e-05, "loss": 1.9464, "step": 59070 }, { "epoch": 2.7, "learning_rate": 3.6594352144262896e-05, "loss": 2.065, "step": 59080 }, { "epoch": 2.7, "learning_rate": 3.659206371000961e-05, "loss": 2.1383, "step": 59090 }, { "epoch": 2.7, "learning_rate": 3.6589775275756324e-05, "loss": 2.0799, "step": 59100 }, { "epoch": 2.7, "learning_rate": 3.6587486841503045e-05, "loss": 1.8801, "step": 59110 }, { "epoch": 2.7, "learning_rate": 3.658519840724976e-05, "loss": 2.0405, "step": 59120 }, { "epoch": 2.7, "learning_rate": 3.6582909972996473e-05, "loss": 2.1671, "step": 59130 }, { "epoch": 2.7, "learning_rate": 3.6580621538743194e-05, "loss": 2.0298, "step": 59140 }, { "epoch": 2.7, "learning_rate": 3.657833310448991e-05, "loss": 2.1137, "step": 59150 }, { "epoch": 2.7, "learning_rate": 3.657604467023662e-05, "loss": 2.1289, "step": 59160 }, { "epoch": 2.7, "learning_rate": 3.6573756235983344e-05, "loss": 2.0186, "step": 59170 }, { "epoch": 2.7, "learning_rate": 3.657146780173006e-05, "loss": 2.1344, "step": 59180 }, { "epoch": 2.7, "learning_rate": 3.656917936747677e-05, "loss": 2.1645, "step": 59190 }, { "epoch": 2.7, "learning_rate": 3.656689093322349e-05, "loss": 2.0111, "step": 59200 }, { "epoch": 2.7, "learning_rate": 3.656460249897021e-05, "loss": 2.2152, "step": 59210 }, { "epoch": 2.7, "learning_rate": 3.656231406471692e-05, "loss": 1.9988, "step": 59220 }, { "epoch": 2.7, "learning_rate": 3.656002563046364e-05, "loss": 1.9755, "step": 59230 }, { "epoch": 2.71, "learning_rate": 3.6557737196210356e-05, "loss": 2.1448, "step": 59240 }, { "epoch": 2.71, "learning_rate": 3.655544876195707e-05, "loss": 1.9214, "step": 59250 }, { "epoch": 2.71, "learning_rate": 3.655316032770379e-05, "loss": 2.0891, "step": 59260 }, { "epoch": 2.71, "learning_rate": 3.6550871893450505e-05, "loss": 2.0588, "step": 59270 }, { "epoch": 2.71, "learning_rate": 3.654858345919722e-05, "loss": 2.0212, "step": 59280 }, { "epoch": 2.71, "learning_rate": 3.6546295024943933e-05, "loss": 1.8944, "step": 59290 }, { "epoch": 2.71, "learning_rate": 3.654400659069065e-05, "loss": 2.0865, "step": 59300 }, { "epoch": 2.71, "learning_rate": 3.654171815643737e-05, "loss": 2.1871, "step": 59310 }, { "epoch": 2.71, "learning_rate": 3.653942972218408e-05, "loss": 2.1397, "step": 59320 }, { "epoch": 2.71, "learning_rate": 3.65371412879308e-05, "loss": 2.0588, "step": 59330 }, { "epoch": 2.71, "learning_rate": 3.653485285367752e-05, "loss": 2.1032, "step": 59340 }, { "epoch": 2.71, "learning_rate": 3.653256441942423e-05, "loss": 2.1564, "step": 59350 }, { "epoch": 2.71, "learning_rate": 3.6530275985170946e-05, "loss": 2.0512, "step": 59360 }, { "epoch": 2.71, "learning_rate": 3.652798755091767e-05, "loss": 2.1372, "step": 59370 }, { "epoch": 2.71, "learning_rate": 3.652569911666438e-05, "loss": 2.2331, "step": 59380 }, { "epoch": 2.71, "learning_rate": 3.6523410682411095e-05, "loss": 1.9531, "step": 59390 }, { "epoch": 2.71, "learning_rate": 3.6521122248157816e-05, "loss": 2.0449, "step": 59400 }, { "epoch": 2.71, "learning_rate": 3.651883381390453e-05, "loss": 2.1435, "step": 59410 }, { "epoch": 2.71, "learning_rate": 3.6516545379651244e-05, "loss": 2.0352, "step": 59420 }, { "epoch": 2.71, "learning_rate": 3.6514256945397965e-05, "loss": 2.089, "step": 59430 }, { "epoch": 2.71, "learning_rate": 3.651196851114468e-05, "loss": 2.1351, "step": 59440 }, { "epoch": 2.71, "learning_rate": 3.6509680076891394e-05, "loss": 2.0181, "step": 59450 }, { "epoch": 2.72, "learning_rate": 3.6507391642638114e-05, "loss": 1.9916, "step": 59460 }, { "epoch": 2.72, "learning_rate": 3.650510320838482e-05, "loss": 2.0453, "step": 59470 }, { "epoch": 2.72, "learning_rate": 3.6502814774131536e-05, "loss": 1.9686, "step": 59480 }, { "epoch": 2.72, "learning_rate": 3.650052633987826e-05, "loss": 2.048, "step": 59490 }, { "epoch": 2.72, "learning_rate": 3.649823790562497e-05, "loss": 2.0175, "step": 59500 }, { "epoch": 2.72, "learning_rate": 3.6495949471371685e-05, "loss": 2.2435, "step": 59510 }, { "epoch": 2.72, "learning_rate": 3.6493661037118406e-05, "loss": 2.1001, "step": 59520 }, { "epoch": 2.72, "learning_rate": 3.649137260286512e-05, "loss": 2.03, "step": 59530 }, { "epoch": 2.72, "learning_rate": 3.6489084168611834e-05, "loss": 2.0178, "step": 59540 }, { "epoch": 2.72, "learning_rate": 3.6486795734358555e-05, "loss": 1.9812, "step": 59550 }, { "epoch": 2.72, "learning_rate": 3.648450730010527e-05, "loss": 2.0776, "step": 59560 }, { "epoch": 2.72, "learning_rate": 3.6482218865851983e-05, "loss": 2.1752, "step": 59570 }, { "epoch": 2.72, "learning_rate": 3.6479930431598704e-05, "loss": 2.055, "step": 59580 }, { "epoch": 2.72, "learning_rate": 3.647764199734542e-05, "loss": 2.2134, "step": 59590 }, { "epoch": 2.72, "learning_rate": 3.647535356309213e-05, "loss": 2.1623, "step": 59600 }, { "epoch": 2.72, "learning_rate": 3.6473065128838854e-05, "loss": 2.0111, "step": 59610 }, { "epoch": 2.72, "learning_rate": 3.647077669458557e-05, "loss": 2.0224, "step": 59620 }, { "epoch": 2.72, "learning_rate": 3.646848826033228e-05, "loss": 2.0551, "step": 59630 }, { "epoch": 2.72, "learning_rate": 3.6466199826079e-05, "loss": 2.0143, "step": 59640 }, { "epoch": 2.72, "learning_rate": 3.646391139182572e-05, "loss": 2.0714, "step": 59650 }, { "epoch": 2.72, "learning_rate": 3.646162295757243e-05, "loss": 1.9914, "step": 59660 }, { "epoch": 2.72, "learning_rate": 3.6459334523319145e-05, "loss": 2.0853, "step": 59670 }, { "epoch": 2.73, "learning_rate": 3.645704608906586e-05, "loss": 2.1028, "step": 59680 }, { "epoch": 2.73, "learning_rate": 3.645475765481258e-05, "loss": 2.0389, "step": 59690 }, { "epoch": 2.73, "learning_rate": 3.6452469220559294e-05, "loss": 2.0774, "step": 59700 }, { "epoch": 2.73, "learning_rate": 3.645018078630601e-05, "loss": 2.0565, "step": 59710 }, { "epoch": 2.73, "learning_rate": 3.644789235205273e-05, "loss": 2.213, "step": 59720 }, { "epoch": 2.73, "learning_rate": 3.6445603917799443e-05, "loss": 2.0281, "step": 59730 }, { "epoch": 2.73, "learning_rate": 3.644331548354616e-05, "loss": 2.3055, "step": 59740 }, { "epoch": 2.73, "learning_rate": 3.644102704929288e-05, "loss": 1.9844, "step": 59750 }, { "epoch": 2.73, "learning_rate": 3.643873861503959e-05, "loss": 2.1805, "step": 59760 }, { "epoch": 2.73, "learning_rate": 3.643645018078631e-05, "loss": 2.0794, "step": 59770 }, { "epoch": 2.73, "learning_rate": 3.643416174653302e-05, "loss": 1.9962, "step": 59780 }, { "epoch": 2.73, "learning_rate": 3.643187331227974e-05, "loss": 1.972, "step": 59790 }, { "epoch": 2.73, "learning_rate": 3.6429584878026456e-05, "loss": 2.0499, "step": 59800 }, { "epoch": 2.73, "learning_rate": 3.642729644377317e-05, "loss": 2.1964, "step": 59810 }, { "epoch": 2.73, "learning_rate": 3.642500800951989e-05, "loss": 1.9955, "step": 59820 }, { "epoch": 2.73, "learning_rate": 3.6422719575266605e-05, "loss": 2.1259, "step": 59830 }, { "epoch": 2.73, "learning_rate": 3.642043114101332e-05, "loss": 2.0424, "step": 59840 }, { "epoch": 2.73, "learning_rate": 3.641814270676004e-05, "loss": 2.0737, "step": 59850 }, { "epoch": 2.73, "learning_rate": 3.6415854272506754e-05, "loss": 2.1274, "step": 59860 }, { "epoch": 2.73, "learning_rate": 3.641356583825347e-05, "loss": 2.0519, "step": 59870 }, { "epoch": 2.73, "learning_rate": 3.641127740400018e-05, "loss": 2.0913, "step": 59880 }, { "epoch": 2.73, "learning_rate": 3.64089889697469e-05, "loss": 2.033, "step": 59890 }, { "epoch": 2.74, "learning_rate": 3.640670053549362e-05, "loss": 2.1777, "step": 59900 }, { "epoch": 2.74, "learning_rate": 3.640441210124033e-05, "loss": 2.0058, "step": 59910 }, { "epoch": 2.74, "learning_rate": 3.6402123666987046e-05, "loss": 2.1108, "step": 59920 }, { "epoch": 2.74, "learning_rate": 3.639983523273377e-05, "loss": 2.2178, "step": 59930 }, { "epoch": 2.74, "learning_rate": 3.639754679848048e-05, "loss": 1.9434, "step": 59940 }, { "epoch": 2.74, "learning_rate": 3.6395258364227195e-05, "loss": 2.1115, "step": 59950 }, { "epoch": 2.74, "learning_rate": 3.6392969929973916e-05, "loss": 1.9993, "step": 59960 }, { "epoch": 2.74, "learning_rate": 3.639068149572063e-05, "loss": 2.1368, "step": 59970 }, { "epoch": 2.74, "learning_rate": 3.6388393061467344e-05, "loss": 2.0492, "step": 59980 }, { "epoch": 2.74, "learning_rate": 3.6386104627214065e-05, "loss": 2.101, "step": 59990 }, { "epoch": 2.74, "learning_rate": 3.638381619296078e-05, "loss": 2.0305, "step": 60000 }, { "epoch": 2.74, "learning_rate": 3.6381527758707493e-05, "loss": 2.0161, "step": 60010 }, { "epoch": 2.74, "learning_rate": 3.6379239324454214e-05, "loss": 2.1533, "step": 60020 }, { "epoch": 2.74, "learning_rate": 3.637695089020093e-05, "loss": 2.1102, "step": 60030 }, { "epoch": 2.74, "learning_rate": 3.637466245594764e-05, "loss": 2.1066, "step": 60040 }, { "epoch": 2.74, "learning_rate": 3.6372374021694363e-05, "loss": 2.0991, "step": 60050 }, { "epoch": 2.74, "learning_rate": 3.637008558744108e-05, "loss": 2.0902, "step": 60060 }, { "epoch": 2.74, "learning_rate": 3.6367797153187785e-05, "loss": 2.1771, "step": 60070 }, { "epoch": 2.74, "learning_rate": 3.6365508718934506e-05, "loss": 1.9807, "step": 60080 }, { "epoch": 2.74, "learning_rate": 3.636322028468122e-05, "loss": 2.114, "step": 60090 }, { "epoch": 2.74, "learning_rate": 3.6360931850427934e-05, "loss": 2.1315, "step": 60100 }, { "epoch": 2.74, "learning_rate": 3.6358643416174655e-05, "loss": 1.9784, "step": 60110 }, { "epoch": 2.75, "learning_rate": 3.635635498192137e-05, "loss": 2.0314, "step": 60120 }, { "epoch": 2.75, "learning_rate": 3.635406654766808e-05, "loss": 1.9307, "step": 60130 }, { "epoch": 2.75, "learning_rate": 3.6351778113414804e-05, "loss": 2.0528, "step": 60140 }, { "epoch": 2.75, "learning_rate": 3.634948967916152e-05, "loss": 2.1447, "step": 60150 }, { "epoch": 2.75, "learning_rate": 3.634720124490823e-05, "loss": 2.0033, "step": 60160 }, { "epoch": 2.75, "learning_rate": 3.6344912810654953e-05, "loss": 1.8668, "step": 60170 }, { "epoch": 2.75, "learning_rate": 3.634262437640167e-05, "loss": 1.9926, "step": 60180 }, { "epoch": 2.75, "learning_rate": 3.634033594214838e-05, "loss": 2.0224, "step": 60190 }, { "epoch": 2.75, "learning_rate": 3.63380475078951e-05, "loss": 1.9147, "step": 60200 }, { "epoch": 2.75, "learning_rate": 3.633575907364182e-05, "loss": 2.111, "step": 60210 }, { "epoch": 2.75, "learning_rate": 3.633347063938853e-05, "loss": 1.877, "step": 60220 }, { "epoch": 2.75, "learning_rate": 3.633118220513525e-05, "loss": 2.2339, "step": 60230 }, { "epoch": 2.75, "learning_rate": 3.6328893770881966e-05, "loss": 2.19, "step": 60240 }, { "epoch": 2.75, "learning_rate": 3.632660533662868e-05, "loss": 1.9377, "step": 60250 }, { "epoch": 2.75, "learning_rate": 3.6324316902375394e-05, "loss": 1.9382, "step": 60260 }, { "epoch": 2.75, "learning_rate": 3.632202846812211e-05, "loss": 2.1229, "step": 60270 }, { "epoch": 2.75, "learning_rate": 3.631974003386883e-05, "loss": 2.1269, "step": 60280 }, { "epoch": 2.75, "learning_rate": 3.631745159961554e-05, "loss": 2.1148, "step": 60290 }, { "epoch": 2.75, "learning_rate": 3.631516316536226e-05, "loss": 1.9632, "step": 60300 }, { "epoch": 2.75, "learning_rate": 3.631287473110898e-05, "loss": 2.1192, "step": 60310 }, { "epoch": 2.75, "learning_rate": 3.631058629685569e-05, "loss": 2.0559, "step": 60320 }, { "epoch": 2.75, "learning_rate": 3.630829786260241e-05, "loss": 1.9684, "step": 60330 }, { "epoch": 2.76, "learning_rate": 3.630600942834913e-05, "loss": 2.1851, "step": 60340 }, { "epoch": 2.76, "learning_rate": 3.630372099409584e-05, "loss": 2.1684, "step": 60350 }, { "epoch": 2.76, "learning_rate": 3.6301432559842556e-05, "loss": 2.0476, "step": 60360 }, { "epoch": 2.76, "learning_rate": 3.629914412558928e-05, "loss": 2.0256, "step": 60370 }, { "epoch": 2.76, "learning_rate": 3.629685569133599e-05, "loss": 2.0592, "step": 60380 }, { "epoch": 2.76, "learning_rate": 3.6294567257082705e-05, "loss": 2.179, "step": 60390 }, { "epoch": 2.76, "learning_rate": 3.6292278822829426e-05, "loss": 2.0272, "step": 60400 }, { "epoch": 2.76, "learning_rate": 3.628999038857614e-05, "loss": 2.0962, "step": 60410 }, { "epoch": 2.76, "learning_rate": 3.6287701954322854e-05, "loss": 2.224, "step": 60420 }, { "epoch": 2.76, "learning_rate": 3.6285413520069575e-05, "loss": 2.0562, "step": 60430 }, { "epoch": 2.76, "learning_rate": 3.628312508581629e-05, "loss": 2.1457, "step": 60440 }, { "epoch": 2.76, "learning_rate": 3.6280836651563e-05, "loss": 2.0144, "step": 60450 }, { "epoch": 2.76, "learning_rate": 3.627854821730972e-05, "loss": 1.9404, "step": 60460 }, { "epoch": 2.76, "learning_rate": 3.627625978305643e-05, "loss": 2.0365, "step": 60470 }, { "epoch": 2.76, "learning_rate": 3.6273971348803146e-05, "loss": 2.1849, "step": 60480 }, { "epoch": 2.76, "learning_rate": 3.627168291454987e-05, "loss": 2.0779, "step": 60490 }, { "epoch": 2.76, "learning_rate": 3.626939448029658e-05, "loss": 2.0758, "step": 60500 }, { "epoch": 2.76, "learning_rate": 3.6267106046043295e-05, "loss": 2.1671, "step": 60510 }, { "epoch": 2.76, "learning_rate": 3.6264817611790016e-05, "loss": 2.0352, "step": 60520 }, { "epoch": 2.76, "learning_rate": 3.626252917753673e-05, "loss": 1.9913, "step": 60530 }, { "epoch": 2.76, "learning_rate": 3.6260240743283444e-05, "loss": 2.1064, "step": 60540 }, { "epoch": 2.76, "learning_rate": 3.6257952309030165e-05, "loss": 2.2619, "step": 60550 }, { "epoch": 2.77, "learning_rate": 3.625566387477688e-05, "loss": 2.1567, "step": 60560 }, { "epoch": 2.77, "learning_rate": 3.625337544052359e-05, "loss": 1.9256, "step": 60570 }, { "epoch": 2.77, "learning_rate": 3.6251087006270314e-05, "loss": 2.1652, "step": 60580 }, { "epoch": 2.77, "learning_rate": 3.624879857201703e-05, "loss": 2.1168, "step": 60590 }, { "epoch": 2.77, "learning_rate": 3.624651013776374e-05, "loss": 2.0702, "step": 60600 }, { "epoch": 2.77, "learning_rate": 3.6244221703510463e-05, "loss": 2.0997, "step": 60610 }, { "epoch": 2.77, "learning_rate": 3.624193326925718e-05, "loss": 2.0795, "step": 60620 }, { "epoch": 2.77, "learning_rate": 3.623964483500389e-05, "loss": 2.005, "step": 60630 }, { "epoch": 2.77, "learning_rate": 3.623735640075061e-05, "loss": 2.1349, "step": 60640 }, { "epoch": 2.77, "learning_rate": 3.623506796649733e-05, "loss": 2.0646, "step": 60650 }, { "epoch": 2.77, "learning_rate": 3.623277953224404e-05, "loss": 1.9596, "step": 60660 }, { "epoch": 2.77, "learning_rate": 3.6230491097990755e-05, "loss": 1.9213, "step": 60670 }, { "epoch": 2.77, "learning_rate": 3.622820266373747e-05, "loss": 2.0875, "step": 60680 }, { "epoch": 2.77, "learning_rate": 3.622591422948419e-05, "loss": 2.0627, "step": 60690 }, { "epoch": 2.77, "learning_rate": 3.6223625795230904e-05, "loss": 2.2612, "step": 60700 }, { "epoch": 2.77, "learning_rate": 3.622133736097762e-05, "loss": 2.143, "step": 60710 }, { "epoch": 2.77, "learning_rate": 3.621904892672434e-05, "loss": 2.0598, "step": 60720 }, { "epoch": 2.77, "learning_rate": 3.621676049247105e-05, "loss": 1.9329, "step": 60730 }, { "epoch": 2.77, "learning_rate": 3.621447205821777e-05, "loss": 1.9898, "step": 60740 }, { "epoch": 2.77, "learning_rate": 3.621218362396449e-05, "loss": 1.9124, "step": 60750 }, { "epoch": 2.77, "learning_rate": 3.62098951897112e-05, "loss": 2.0575, "step": 60760 }, { "epoch": 2.77, "learning_rate": 3.620760675545792e-05, "loss": 2.0517, "step": 60770 }, { "epoch": 2.78, "learning_rate": 3.620531832120464e-05, "loss": 2.1131, "step": 60780 }, { "epoch": 2.78, "learning_rate": 3.620302988695135e-05, "loss": 2.0444, "step": 60790 }, { "epoch": 2.78, "learning_rate": 3.6200741452698066e-05, "loss": 2.1761, "step": 60800 }, { "epoch": 2.78, "learning_rate": 3.619845301844479e-05, "loss": 2.0397, "step": 60810 }, { "epoch": 2.78, "learning_rate": 3.61961645841915e-05, "loss": 2.092, "step": 60820 }, { "epoch": 2.78, "learning_rate": 3.6193876149938215e-05, "loss": 2.0078, "step": 60830 }, { "epoch": 2.78, "learning_rate": 3.6191587715684936e-05, "loss": 2.1378, "step": 60840 }, { "epoch": 2.78, "learning_rate": 3.618929928143165e-05, "loss": 2.2174, "step": 60850 }, { "epoch": 2.78, "learning_rate": 3.618701084717836e-05, "loss": 2.0804, "step": 60860 }, { "epoch": 2.78, "learning_rate": 3.618472241292508e-05, "loss": 2.083, "step": 60870 }, { "epoch": 2.78, "learning_rate": 3.618243397867179e-05, "loss": 2.1303, "step": 60880 }, { "epoch": 2.78, "learning_rate": 3.6180145544418507e-05, "loss": 2.0519, "step": 60890 }, { "epoch": 2.78, "learning_rate": 3.617785711016523e-05, "loss": 2.1392, "step": 60900 }, { "epoch": 2.78, "learning_rate": 3.617556867591194e-05, "loss": 2.1118, "step": 60910 }, { "epoch": 2.78, "learning_rate": 3.6173280241658656e-05, "loss": 2.0594, "step": 60920 }, { "epoch": 2.78, "learning_rate": 3.617099180740538e-05, "loss": 1.9347, "step": 60930 }, { "epoch": 2.78, "learning_rate": 3.616870337315209e-05, "loss": 2.0556, "step": 60940 }, { "epoch": 2.78, "learning_rate": 3.6166414938898805e-05, "loss": 2.1246, "step": 60950 }, { "epoch": 2.78, "learning_rate": 3.6164126504645526e-05, "loss": 1.9343, "step": 60960 }, { "epoch": 2.78, "learning_rate": 3.616183807039224e-05, "loss": 2.0388, "step": 60970 }, { "epoch": 2.78, "learning_rate": 3.6159549636138954e-05, "loss": 2.0508, "step": 60980 }, { "epoch": 2.78, "learning_rate": 3.6157261201885675e-05, "loss": 2.0465, "step": 60990 }, { "epoch": 2.79, "learning_rate": 3.615497276763239e-05, "loss": 2.0423, "step": 61000 }, { "epoch": 2.79, "learning_rate": 3.61526843333791e-05, "loss": 2.0575, "step": 61010 }, { "epoch": 2.79, "learning_rate": 3.6150395899125824e-05, "loss": 2.0408, "step": 61020 }, { "epoch": 2.79, "learning_rate": 3.614810746487254e-05, "loss": 1.9494, "step": 61030 }, { "epoch": 2.79, "learning_rate": 3.614581903061925e-05, "loss": 2.0282, "step": 61040 }, { "epoch": 2.79, "learning_rate": 3.6143530596365967e-05, "loss": 2.0489, "step": 61050 }, { "epoch": 2.79, "learning_rate": 3.614124216211268e-05, "loss": 2.2202, "step": 61060 }, { "epoch": 2.79, "learning_rate": 3.6138953727859395e-05, "loss": 2.026, "step": 61070 }, { "epoch": 2.79, "learning_rate": 3.6136665293606116e-05, "loss": 2.1543, "step": 61080 }, { "epoch": 2.79, "learning_rate": 3.613437685935283e-05, "loss": 2.2253, "step": 61090 }, { "epoch": 2.79, "learning_rate": 3.6132088425099544e-05, "loss": 2.1242, "step": 61100 }, { "epoch": 2.79, "learning_rate": 3.6129799990846265e-05, "loss": 2.2438, "step": 61110 }, { "epoch": 2.79, "learning_rate": 3.612751155659298e-05, "loss": 2.0771, "step": 61120 }, { "epoch": 2.79, "learning_rate": 3.612522312233969e-05, "loss": 2.0125, "step": 61130 }, { "epoch": 2.79, "learning_rate": 3.6122934688086414e-05, "loss": 2.1274, "step": 61140 }, { "epoch": 2.79, "learning_rate": 3.612064625383313e-05, "loss": 2.0791, "step": 61150 }, { "epoch": 2.79, "learning_rate": 3.611835781957984e-05, "loss": 2.0529, "step": 61160 }, { "epoch": 2.79, "learning_rate": 3.611606938532656e-05, "loss": 1.9942, "step": 61170 }, { "epoch": 2.79, "learning_rate": 3.611378095107328e-05, "loss": 2.2288, "step": 61180 }, { "epoch": 2.79, "learning_rate": 3.611149251681999e-05, "loss": 1.9522, "step": 61190 }, { "epoch": 2.79, "learning_rate": 3.610920408256671e-05, "loss": 2.1996, "step": 61200 }, { "epoch": 2.8, "learning_rate": 3.6106915648313427e-05, "loss": 2.0818, "step": 61210 }, { "epoch": 2.8, "learning_rate": 3.610462721406014e-05, "loss": 2.0801, "step": 61220 }, { "epoch": 2.8, "learning_rate": 3.610233877980686e-05, "loss": 2.2194, "step": 61230 }, { "epoch": 2.8, "learning_rate": 3.6100050345553576e-05, "loss": 2.0135, "step": 61240 }, { "epoch": 2.8, "learning_rate": 3.609776191130029e-05, "loss": 2.0762, "step": 61250 }, { "epoch": 2.8, "learning_rate": 3.6095473477047004e-05, "loss": 2.2418, "step": 61260 }, { "epoch": 2.8, "learning_rate": 3.609318504279372e-05, "loss": 2.0411, "step": 61270 }, { "epoch": 2.8, "learning_rate": 3.609089660854044e-05, "loss": 2.0224, "step": 61280 }, { "epoch": 2.8, "learning_rate": 3.608860817428715e-05, "loss": 2.0435, "step": 61290 }, { "epoch": 2.8, "learning_rate": 3.608631974003387e-05, "loss": 2.0366, "step": 61300 }, { "epoch": 2.8, "learning_rate": 3.608403130578059e-05, "loss": 2.0107, "step": 61310 }, { "epoch": 2.8, "learning_rate": 3.60817428715273e-05, "loss": 2.1401, "step": 61320 }, { "epoch": 2.8, "learning_rate": 3.6079454437274017e-05, "loss": 2.1834, "step": 61330 }, { "epoch": 2.8, "learning_rate": 3.607716600302074e-05, "loss": 2.0824, "step": 61340 }, { "epoch": 2.8, "learning_rate": 3.607487756876745e-05, "loss": 1.9941, "step": 61350 }, { "epoch": 2.8, "learning_rate": 3.6072589134514166e-05, "loss": 2.0522, "step": 61360 }, { "epoch": 2.8, "learning_rate": 3.607030070026089e-05, "loss": 2.1684, "step": 61370 }, { "epoch": 2.8, "learning_rate": 3.60680122660076e-05, "loss": 2.0258, "step": 61380 }, { "epoch": 2.8, "learning_rate": 3.6065723831754315e-05, "loss": 2.1184, "step": 61390 }, { "epoch": 2.8, "learning_rate": 3.6063435397501036e-05, "loss": 2.2209, "step": 61400 }, { "epoch": 2.8, "learning_rate": 3.606114696324775e-05, "loss": 2.1374, "step": 61410 }, { "epoch": 2.8, "learning_rate": 3.6058858528994464e-05, "loss": 2.1611, "step": 61420 }, { "epoch": 2.81, "learning_rate": 3.6056570094741185e-05, "loss": 2.014, "step": 61430 }, { "epoch": 2.81, "learning_rate": 3.60542816604879e-05, "loss": 2.142, "step": 61440 }, { "epoch": 2.81, "learning_rate": 3.6051993226234606e-05, "loss": 2.1056, "step": 61450 }, { "epoch": 2.81, "learning_rate": 3.604970479198133e-05, "loss": 2.0169, "step": 61460 }, { "epoch": 2.81, "learning_rate": 3.604741635772804e-05, "loss": 2.1826, "step": 61470 }, { "epoch": 2.81, "learning_rate": 3.6045127923474756e-05, "loss": 2.1253, "step": 61480 }, { "epoch": 2.81, "learning_rate": 3.6042839489221477e-05, "loss": 2.1687, "step": 61490 }, { "epoch": 2.81, "learning_rate": 3.604055105496819e-05, "loss": 2.07, "step": 61500 }, { "epoch": 2.81, "learning_rate": 3.6038262620714905e-05, "loss": 2.0512, "step": 61510 }, { "epoch": 2.81, "learning_rate": 3.6035974186461626e-05, "loss": 2.1629, "step": 61520 }, { "epoch": 2.81, "learning_rate": 3.603368575220834e-05, "loss": 2.2406, "step": 61530 }, { "epoch": 2.81, "learning_rate": 3.6031397317955054e-05, "loss": 2.0456, "step": 61540 }, { "epoch": 2.81, "learning_rate": 3.6029108883701775e-05, "loss": 1.9176, "step": 61550 }, { "epoch": 2.81, "learning_rate": 3.602682044944849e-05, "loss": 1.9203, "step": 61560 }, { "epoch": 2.81, "learning_rate": 3.60245320151952e-05, "loss": 2.0302, "step": 61570 }, { "epoch": 2.81, "learning_rate": 3.6022243580941924e-05, "loss": 2.159, "step": 61580 }, { "epoch": 2.81, "learning_rate": 3.601995514668864e-05, "loss": 1.9458, "step": 61590 }, { "epoch": 2.81, "learning_rate": 3.601766671243535e-05, "loss": 2.0131, "step": 61600 }, { "epoch": 2.81, "learning_rate": 3.601537827818207e-05, "loss": 2.115, "step": 61610 }, { "epoch": 2.81, "learning_rate": 3.601308984392879e-05, "loss": 2.0531, "step": 61620 }, { "epoch": 2.81, "learning_rate": 3.60108014096755e-05, "loss": 2.0541, "step": 61630 }, { "epoch": 2.81, "learning_rate": 3.600851297542222e-05, "loss": 1.9562, "step": 61640 }, { "epoch": 2.82, "learning_rate": 3.600622454116893e-05, "loss": 1.9416, "step": 61650 }, { "epoch": 2.82, "learning_rate": 3.600393610691565e-05, "loss": 2.1065, "step": 61660 }, { "epoch": 2.82, "learning_rate": 3.6001647672662365e-05, "loss": 2.0799, "step": 61670 }, { "epoch": 2.82, "learning_rate": 3.599935923840908e-05, "loss": 2.0908, "step": 61680 }, { "epoch": 2.82, "learning_rate": 3.59970708041558e-05, "loss": 2.0908, "step": 61690 }, { "epoch": 2.82, "learning_rate": 3.5994782369902514e-05, "loss": 2.072, "step": 61700 }, { "epoch": 2.82, "learning_rate": 3.599249393564923e-05, "loss": 2.006, "step": 61710 }, { "epoch": 2.82, "learning_rate": 3.599020550139595e-05, "loss": 2.1644, "step": 61720 }, { "epoch": 2.82, "learning_rate": 3.598791706714266e-05, "loss": 2.073, "step": 61730 }, { "epoch": 2.82, "learning_rate": 3.598562863288938e-05, "loss": 1.992, "step": 61740 }, { "epoch": 2.82, "learning_rate": 3.59833401986361e-05, "loss": 2.0356, "step": 61750 }, { "epoch": 2.82, "learning_rate": 3.598105176438281e-05, "loss": 2.0737, "step": 61760 }, { "epoch": 2.82, "learning_rate": 3.5978763330129527e-05, "loss": 2.1922, "step": 61770 }, { "epoch": 2.82, "learning_rate": 3.597647489587625e-05, "loss": 2.0764, "step": 61780 }, { "epoch": 2.82, "learning_rate": 3.597418646162296e-05, "loss": 2.0701, "step": 61790 }, { "epoch": 2.82, "learning_rate": 3.5971898027369676e-05, "loss": 1.9975, "step": 61800 }, { "epoch": 2.82, "learning_rate": 3.5969609593116397e-05, "loss": 2.0847, "step": 61810 }, { "epoch": 2.82, "learning_rate": 3.596732115886311e-05, "loss": 2.0116, "step": 61820 }, { "epoch": 2.82, "learning_rate": 3.5965032724609825e-05, "loss": 2.073, "step": 61830 }, { "epoch": 2.82, "learning_rate": 3.596274429035654e-05, "loss": 2.112, "step": 61840 }, { "epoch": 2.82, "learning_rate": 3.596045585610325e-05, "loss": 1.9895, "step": 61850 }, { "epoch": 2.82, "learning_rate": 3.595816742184997e-05, "loss": 2.0722, "step": 61860 }, { "epoch": 2.83, "learning_rate": 3.595587898759669e-05, "loss": 2.103, "step": 61870 }, { "epoch": 2.83, "learning_rate": 3.59535905533434e-05, "loss": 1.9754, "step": 61880 }, { "epoch": 2.83, "learning_rate": 3.5951302119090116e-05, "loss": 2.1927, "step": 61890 }, { "epoch": 2.83, "learning_rate": 3.594901368483684e-05, "loss": 2.1118, "step": 61900 }, { "epoch": 2.83, "learning_rate": 3.594672525058355e-05, "loss": 2.0084, "step": 61910 }, { "epoch": 2.83, "learning_rate": 3.5944436816330266e-05, "loss": 2.0421, "step": 61920 }, { "epoch": 2.83, "learning_rate": 3.5942148382076987e-05, "loss": 1.9413, "step": 61930 }, { "epoch": 2.83, "learning_rate": 3.59398599478237e-05, "loss": 1.9866, "step": 61940 }, { "epoch": 2.83, "learning_rate": 3.5937571513570415e-05, "loss": 2.0762, "step": 61950 }, { "epoch": 2.83, "learning_rate": 3.5935283079317136e-05, "loss": 2.0876, "step": 61960 }, { "epoch": 2.83, "learning_rate": 3.593299464506385e-05, "loss": 2.1186, "step": 61970 }, { "epoch": 2.83, "learning_rate": 3.5930706210810564e-05, "loss": 2.0707, "step": 61980 }, { "epoch": 2.83, "learning_rate": 3.5928417776557285e-05, "loss": 1.955, "step": 61990 }, { "epoch": 2.83, "learning_rate": 3.5926129342304e-05, "loss": 2.0765, "step": 62000 }, { "epoch": 2.83, "learning_rate": 3.592384090805071e-05, "loss": 2.1751, "step": 62010 }, { "epoch": 2.83, "learning_rate": 3.5921552473797434e-05, "loss": 2.2334, "step": 62020 }, { "epoch": 2.83, "learning_rate": 3.591926403954415e-05, "loss": 2.1414, "step": 62030 }, { "epoch": 2.83, "learning_rate": 3.591697560529086e-05, "loss": 2.0269, "step": 62040 }, { "epoch": 2.83, "learning_rate": 3.5914687171037576e-05, "loss": 2.0158, "step": 62050 }, { "epoch": 2.83, "learning_rate": 3.591239873678429e-05, "loss": 2.0881, "step": 62060 }, { "epoch": 2.83, "learning_rate": 3.591011030253101e-05, "loss": 1.9904, "step": 62070 }, { "epoch": 2.83, "learning_rate": 3.5907821868277726e-05, "loss": 1.9143, "step": 62080 }, { "epoch": 2.84, "learning_rate": 3.590553343402444e-05, "loss": 2.0821, "step": 62090 }, { "epoch": 2.84, "learning_rate": 3.590324499977116e-05, "loss": 2.0648, "step": 62100 }, { "epoch": 2.84, "learning_rate": 3.5900956565517875e-05, "loss": 1.9907, "step": 62110 }, { "epoch": 2.84, "learning_rate": 3.589866813126459e-05, "loss": 2.081, "step": 62120 }, { "epoch": 2.84, "learning_rate": 3.58963796970113e-05, "loss": 2.0379, "step": 62130 }, { "epoch": 2.84, "learning_rate": 3.5894091262758024e-05, "loss": 2.1392, "step": 62140 }, { "epoch": 2.84, "learning_rate": 3.589180282850474e-05, "loss": 2.038, "step": 62150 }, { "epoch": 2.84, "learning_rate": 3.588951439425145e-05, "loss": 2.0979, "step": 62160 }, { "epoch": 2.84, "learning_rate": 3.588722595999817e-05, "loss": 2.0386, "step": 62170 }, { "epoch": 2.84, "learning_rate": 3.588493752574489e-05, "loss": 2.0755, "step": 62180 }, { "epoch": 2.84, "learning_rate": 3.58826490914916e-05, "loss": 2.0459, "step": 62190 }, { "epoch": 2.84, "learning_rate": 3.588036065723832e-05, "loss": 2.0614, "step": 62200 }, { "epoch": 2.84, "learning_rate": 3.5878072222985036e-05, "loss": 2.033, "step": 62210 }, { "epoch": 2.84, "learning_rate": 3.587578378873175e-05, "loss": 2.0498, "step": 62220 }, { "epoch": 2.84, "learning_rate": 3.587349535447847e-05, "loss": 2.0735, "step": 62230 }, { "epoch": 2.84, "learning_rate": 3.587120692022518e-05, "loss": 1.9863, "step": 62240 }, { "epoch": 2.84, "learning_rate": 3.58689184859719e-05, "loss": 2.138, "step": 62250 }, { "epoch": 2.84, "learning_rate": 3.5866630051718614e-05, "loss": 2.0097, "step": 62260 }, { "epoch": 2.84, "learning_rate": 3.586434161746533e-05, "loss": 2.1589, "step": 62270 }, { "epoch": 2.84, "learning_rate": 3.586205318321205e-05, "loss": 1.9319, "step": 62280 }, { "epoch": 2.84, "learning_rate": 3.585976474895876e-05, "loss": 2.1086, "step": 62290 }, { "epoch": 2.84, "learning_rate": 3.585747631470548e-05, "loss": 1.8963, "step": 62300 }, { "epoch": 2.85, "learning_rate": 3.58551878804522e-05, "loss": 1.9698, "step": 62310 }, { "epoch": 2.85, "learning_rate": 3.585289944619891e-05, "loss": 2.05, "step": 62320 }, { "epoch": 2.85, "learning_rate": 3.5850611011945626e-05, "loss": 2.0548, "step": 62330 }, { "epoch": 2.85, "learning_rate": 3.584832257769235e-05, "loss": 1.9455, "step": 62340 }, { "epoch": 2.85, "learning_rate": 3.584603414343906e-05, "loss": 2.1063, "step": 62350 }, { "epoch": 2.85, "learning_rate": 3.5843745709185776e-05, "loss": 2.126, "step": 62360 }, { "epoch": 2.85, "learning_rate": 3.5841457274932496e-05, "loss": 1.9633, "step": 62370 }, { "epoch": 2.85, "learning_rate": 3.583916884067921e-05, "loss": 2.0513, "step": 62380 }, { "epoch": 2.85, "learning_rate": 3.5836880406425925e-05, "loss": 1.9342, "step": 62390 }, { "epoch": 2.85, "learning_rate": 3.5834591972172646e-05, "loss": 2.1, "step": 62400 }, { "epoch": 2.85, "learning_rate": 3.583230353791936e-05, "loss": 2.2321, "step": 62410 }, { "epoch": 2.85, "learning_rate": 3.5830015103666074e-05, "loss": 2.0196, "step": 62420 }, { "epoch": 2.85, "learning_rate": 3.5827726669412795e-05, "loss": 2.0038, "step": 62430 }, { "epoch": 2.85, "learning_rate": 3.58254382351595e-05, "loss": 1.9807, "step": 62440 }, { "epoch": 2.85, "learning_rate": 3.5823149800906216e-05, "loss": 2.1738, "step": 62450 }, { "epoch": 2.85, "learning_rate": 3.582086136665294e-05, "loss": 2.0163, "step": 62460 }, { "epoch": 2.85, "learning_rate": 3.581857293239965e-05, "loss": 2.1249, "step": 62470 }, { "epoch": 2.85, "learning_rate": 3.5816284498146366e-05, "loss": 1.9522, "step": 62480 }, { "epoch": 2.85, "learning_rate": 3.5813996063893086e-05, "loss": 2.1161, "step": 62490 }, { "epoch": 2.85, "learning_rate": 3.58117076296398e-05, "loss": 2.0507, "step": 62500 }, { "epoch": 2.85, "learning_rate": 3.5809419195386515e-05, "loss": 1.9049, "step": 62510 }, { "epoch": 2.85, "learning_rate": 3.5807130761133236e-05, "loss": 2.0909, "step": 62520 }, { "epoch": 2.86, "learning_rate": 3.580484232687995e-05, "loss": 2.0415, "step": 62530 }, { "epoch": 2.86, "learning_rate": 3.5802553892626664e-05, "loss": 2.0288, "step": 62540 }, { "epoch": 2.86, "learning_rate": 3.5800265458373385e-05, "loss": 1.956, "step": 62550 }, { "epoch": 2.86, "learning_rate": 3.57979770241201e-05, "loss": 2.1722, "step": 62560 }, { "epoch": 2.86, "learning_rate": 3.579568858986681e-05, "loss": 2.0758, "step": 62570 }, { "epoch": 2.86, "learning_rate": 3.5793400155613534e-05, "loss": 2.0129, "step": 62580 }, { "epoch": 2.86, "learning_rate": 3.579111172136025e-05, "loss": 1.8652, "step": 62590 }, { "epoch": 2.86, "learning_rate": 3.578882328710696e-05, "loss": 1.892, "step": 62600 }, { "epoch": 2.86, "learning_rate": 3.578653485285368e-05, "loss": 1.9737, "step": 62610 }, { "epoch": 2.86, "learning_rate": 3.57842464186004e-05, "loss": 2.0779, "step": 62620 }, { "epoch": 2.86, "learning_rate": 3.578195798434711e-05, "loss": 2.115, "step": 62630 }, { "epoch": 2.86, "learning_rate": 3.5779669550093826e-05, "loss": 2.1474, "step": 62640 }, { "epoch": 2.86, "learning_rate": 3.577738111584054e-05, "loss": 2.2212, "step": 62650 }, { "epoch": 2.86, "learning_rate": 3.577509268158726e-05, "loss": 2.0687, "step": 62660 }, { "epoch": 2.86, "learning_rate": 3.5772804247333975e-05, "loss": 2.0448, "step": 62670 }, { "epoch": 2.86, "learning_rate": 3.577051581308069e-05, "loss": 2.0319, "step": 62680 }, { "epoch": 2.86, "learning_rate": 3.576822737882741e-05, "loss": 2.0426, "step": 62690 }, { "epoch": 2.86, "learning_rate": 3.5765938944574124e-05, "loss": 2.208, "step": 62700 }, { "epoch": 2.86, "learning_rate": 3.576365051032084e-05, "loss": 2.158, "step": 62710 }, { "epoch": 2.86, "learning_rate": 3.576136207606756e-05, "loss": 1.9946, "step": 62720 }, { "epoch": 2.86, "learning_rate": 3.575907364181427e-05, "loss": 2.2597, "step": 62730 }, { "epoch": 2.86, "learning_rate": 3.575678520756099e-05, "loss": 2.0419, "step": 62740 }, { "epoch": 2.87, "learning_rate": 3.575449677330771e-05, "loss": 2.0428, "step": 62750 }, { "epoch": 2.87, "learning_rate": 3.575220833905442e-05, "loss": 2.1067, "step": 62760 }, { "epoch": 2.87, "learning_rate": 3.5749919904801136e-05, "loss": 2.0472, "step": 62770 }, { "epoch": 2.87, "learning_rate": 3.574763147054786e-05, "loss": 2.0968, "step": 62780 }, { "epoch": 2.87, "learning_rate": 3.574534303629457e-05, "loss": 1.9835, "step": 62790 }, { "epoch": 2.87, "learning_rate": 3.5743054602041286e-05, "loss": 2.0849, "step": 62800 }, { "epoch": 2.87, "learning_rate": 3.5740766167788006e-05, "loss": 1.9041, "step": 62810 }, { "epoch": 2.87, "learning_rate": 3.573847773353472e-05, "loss": 2.0653, "step": 62820 }, { "epoch": 2.87, "learning_rate": 3.573618929928143e-05, "loss": 2.1614, "step": 62830 }, { "epoch": 2.87, "learning_rate": 3.573390086502815e-05, "loss": 2.0788, "step": 62840 }, { "epoch": 2.87, "learning_rate": 3.573161243077486e-05, "loss": 2.0272, "step": 62850 }, { "epoch": 2.87, "learning_rate": 3.572932399652158e-05, "loss": 1.9206, "step": 62860 }, { "epoch": 2.87, "learning_rate": 3.57270355622683e-05, "loss": 2.0647, "step": 62870 }, { "epoch": 2.87, "learning_rate": 3.572474712801501e-05, "loss": 2.0834, "step": 62880 }, { "epoch": 2.87, "learning_rate": 3.5722458693761726e-05, "loss": 1.9762, "step": 62890 }, { "epoch": 2.87, "learning_rate": 3.572017025950845e-05, "loss": 2.0124, "step": 62900 }, { "epoch": 2.87, "learning_rate": 3.571788182525516e-05, "loss": 2.0815, "step": 62910 }, { "epoch": 2.87, "learning_rate": 3.5715593391001875e-05, "loss": 2.1158, "step": 62920 }, { "epoch": 2.87, "learning_rate": 3.5713304956748596e-05, "loss": 2.0136, "step": 62930 }, { "epoch": 2.87, "learning_rate": 3.571101652249531e-05, "loss": 2.0134, "step": 62940 }, { "epoch": 2.87, "learning_rate": 3.5708728088242025e-05, "loss": 2.0911, "step": 62950 }, { "epoch": 2.87, "learning_rate": 3.5706439653988746e-05, "loss": 1.932, "step": 62960 }, { "epoch": 2.88, "learning_rate": 3.570415121973546e-05, "loss": 2.1232, "step": 62970 }, { "epoch": 2.88, "learning_rate": 3.5701862785482174e-05, "loss": 2.0812, "step": 62980 }, { "epoch": 2.88, "learning_rate": 3.5699574351228895e-05, "loss": 2.1117, "step": 62990 }, { "epoch": 2.88, "learning_rate": 3.569728591697561e-05, "loss": 1.973, "step": 63000 }, { "epoch": 2.88, "learning_rate": 3.569499748272232e-05, "loss": 2.1468, "step": 63010 }, { "epoch": 2.88, "learning_rate": 3.5692709048469044e-05, "loss": 2.0471, "step": 63020 }, { "epoch": 2.88, "learning_rate": 3.569042061421575e-05, "loss": 2.0349, "step": 63030 }, { "epoch": 2.88, "learning_rate": 3.568813217996247e-05, "loss": 1.9481, "step": 63040 }, { "epoch": 2.88, "learning_rate": 3.5685843745709186e-05, "loss": 2.1383, "step": 63050 }, { "epoch": 2.88, "learning_rate": 3.56835553114559e-05, "loss": 2.0239, "step": 63060 }, { "epoch": 2.88, "learning_rate": 3.568126687720262e-05, "loss": 2.1015, "step": 63070 }, { "epoch": 2.88, "learning_rate": 3.5678978442949335e-05, "loss": 1.9266, "step": 63080 }, { "epoch": 2.88, "learning_rate": 3.567669000869605e-05, "loss": 2.0377, "step": 63090 }, { "epoch": 2.88, "learning_rate": 3.567440157444277e-05, "loss": 1.9803, "step": 63100 }, { "epoch": 2.88, "learning_rate": 3.5672113140189485e-05, "loss": 1.8608, "step": 63110 }, { "epoch": 2.88, "learning_rate": 3.56698247059362e-05, "loss": 2.0109, "step": 63120 }, { "epoch": 2.88, "learning_rate": 3.566753627168292e-05, "loss": 2.1587, "step": 63130 }, { "epoch": 2.88, "learning_rate": 3.5665247837429634e-05, "loss": 1.9962, "step": 63140 }, { "epoch": 2.88, "learning_rate": 3.566295940317635e-05, "loss": 2.1283, "step": 63150 }, { "epoch": 2.88, "learning_rate": 3.566067096892307e-05, "loss": 2.0578, "step": 63160 }, { "epoch": 2.88, "learning_rate": 3.565838253466978e-05, "loss": 1.9371, "step": 63170 }, { "epoch": 2.88, "learning_rate": 3.56560941004165e-05, "loss": 1.9935, "step": 63180 }, { "epoch": 2.89, "learning_rate": 3.565380566616322e-05, "loss": 1.9682, "step": 63190 }, { "epoch": 2.89, "learning_rate": 3.565151723190993e-05, "loss": 2.0636, "step": 63200 }, { "epoch": 2.89, "learning_rate": 3.5649228797656646e-05, "loss": 2.1406, "step": 63210 }, { "epoch": 2.89, "learning_rate": 3.564694036340336e-05, "loss": 2.0555, "step": 63220 }, { "epoch": 2.89, "learning_rate": 3.5644651929150075e-05, "loss": 2.1357, "step": 63230 }, { "epoch": 2.89, "learning_rate": 3.564236349489679e-05, "loss": 2.0305, "step": 63240 }, { "epoch": 2.89, "learning_rate": 3.564007506064351e-05, "loss": 2.1598, "step": 63250 }, { "epoch": 2.89, "learning_rate": 3.5637786626390224e-05, "loss": 1.9139, "step": 63260 }, { "epoch": 2.89, "learning_rate": 3.563549819213694e-05, "loss": 2.2595, "step": 63270 }, { "epoch": 2.89, "learning_rate": 3.563320975788366e-05, "loss": 1.9769, "step": 63280 }, { "epoch": 2.89, "learning_rate": 3.563092132363037e-05, "loss": 1.9785, "step": 63290 }, { "epoch": 2.89, "learning_rate": 3.562863288937709e-05, "loss": 2.0169, "step": 63300 }, { "epoch": 2.89, "learning_rate": 3.562634445512381e-05, "loss": 1.8623, "step": 63310 }, { "epoch": 2.89, "learning_rate": 3.562405602087052e-05, "loss": 2.1043, "step": 63320 }, { "epoch": 2.89, "learning_rate": 3.5621767586617236e-05, "loss": 2.1931, "step": 63330 }, { "epoch": 2.89, "learning_rate": 3.561947915236396e-05, "loss": 2.2613, "step": 63340 }, { "epoch": 2.89, "learning_rate": 3.561719071811067e-05, "loss": 1.9621, "step": 63350 }, { "epoch": 2.89, "learning_rate": 3.5614902283857385e-05, "loss": 1.9415, "step": 63360 }, { "epoch": 2.89, "learning_rate": 3.5612613849604106e-05, "loss": 1.9886, "step": 63370 }, { "epoch": 2.89, "learning_rate": 3.561032541535082e-05, "loss": 2.1023, "step": 63380 }, { "epoch": 2.89, "learning_rate": 3.5608036981097535e-05, "loss": 2.1054, "step": 63390 }, { "epoch": 2.9, "learning_rate": 3.5605748546844256e-05, "loss": 1.9349, "step": 63400 }, { "epoch": 2.9, "learning_rate": 3.560346011259097e-05, "loss": 2.0969, "step": 63410 }, { "epoch": 2.9, "learning_rate": 3.560117167833768e-05, "loss": 1.9381, "step": 63420 }, { "epoch": 2.9, "learning_rate": 3.55988832440844e-05, "loss": 2.0702, "step": 63430 }, { "epoch": 2.9, "learning_rate": 3.559659480983111e-05, "loss": 2.0538, "step": 63440 }, { "epoch": 2.9, "learning_rate": 3.5594306375577826e-05, "loss": 2.0933, "step": 63450 }, { "epoch": 2.9, "learning_rate": 3.559201794132455e-05, "loss": 1.9987, "step": 63460 }, { "epoch": 2.9, "learning_rate": 3.558972950707126e-05, "loss": 2.1116, "step": 63470 }, { "epoch": 2.9, "learning_rate": 3.5587441072817975e-05, "loss": 2.1476, "step": 63480 }, { "epoch": 2.9, "learning_rate": 3.5585152638564696e-05, "loss": 2.0698, "step": 63490 }, { "epoch": 2.9, "learning_rate": 3.558286420431141e-05, "loss": 1.9406, "step": 63500 }, { "epoch": 2.9, "learning_rate": 3.5580575770058125e-05, "loss": 2.2915, "step": 63510 }, { "epoch": 2.9, "learning_rate": 3.5578287335804845e-05, "loss": 1.9602, "step": 63520 }, { "epoch": 2.9, "learning_rate": 3.557599890155156e-05, "loss": 2.0411, "step": 63530 }, { "epoch": 2.9, "learning_rate": 3.5573710467298274e-05, "loss": 2.2181, "step": 63540 }, { "epoch": 2.9, "learning_rate": 3.5571422033044995e-05, "loss": 2.0929, "step": 63550 }, { "epoch": 2.9, "learning_rate": 3.556913359879171e-05, "loss": 1.9836, "step": 63560 }, { "epoch": 2.9, "learning_rate": 3.556684516453842e-05, "loss": 2.1333, "step": 63570 }, { "epoch": 2.9, "learning_rate": 3.5564556730285144e-05, "loss": 2.0483, "step": 63580 }, { "epoch": 2.9, "learning_rate": 3.556226829603186e-05, "loss": 2.0807, "step": 63590 }, { "epoch": 2.9, "learning_rate": 3.555997986177857e-05, "loss": 2.0437, "step": 63600 }, { "epoch": 2.9, "learning_rate": 3.555769142752529e-05, "loss": 2.1643, "step": 63610 }, { "epoch": 2.91, "learning_rate": 3.5555402993272e-05, "loss": 2.0773, "step": 63620 }, { "epoch": 2.91, "learning_rate": 3.555311455901872e-05, "loss": 2.1694, "step": 63630 }, { "epoch": 2.91, "learning_rate": 3.5550826124765435e-05, "loss": 2.02, "step": 63640 }, { "epoch": 2.91, "learning_rate": 3.554853769051215e-05, "loss": 1.6502, "step": 63650 }, { "epoch": 2.91, "learning_rate": 3.554624925625887e-05, "loss": 2.0451, "step": 63660 }, { "epoch": 2.91, "learning_rate": 3.5543960822005585e-05, "loss": 2.1472, "step": 63670 }, { "epoch": 2.91, "learning_rate": 3.55416723877523e-05, "loss": 2.1481, "step": 63680 }, { "epoch": 2.91, "learning_rate": 3.553938395349902e-05, "loss": 2.0764, "step": 63690 }, { "epoch": 2.91, "learning_rate": 3.5537095519245734e-05, "loss": 2.0687, "step": 63700 }, { "epoch": 2.91, "learning_rate": 3.553480708499245e-05, "loss": 1.9178, "step": 63710 }, { "epoch": 2.91, "learning_rate": 3.553251865073917e-05, "loss": 1.9381, "step": 63720 }, { "epoch": 2.91, "learning_rate": 3.553023021648588e-05, "loss": 2.0969, "step": 63730 }, { "epoch": 2.91, "learning_rate": 3.55279417822326e-05, "loss": 2.0542, "step": 63740 }, { "epoch": 2.91, "learning_rate": 3.552565334797932e-05, "loss": 2.0708, "step": 63750 }, { "epoch": 2.91, "learning_rate": 3.552336491372603e-05, "loss": 1.9847, "step": 63760 }, { "epoch": 2.91, "learning_rate": 3.5521076479472746e-05, "loss": 2.0228, "step": 63770 }, { "epoch": 2.91, "learning_rate": 3.551878804521947e-05, "loss": 2.089, "step": 63780 }, { "epoch": 2.91, "learning_rate": 3.551649961096618e-05, "loss": 2.0991, "step": 63790 }, { "epoch": 2.91, "learning_rate": 3.5514211176712895e-05, "loss": 2.167, "step": 63800 }, { "epoch": 2.91, "learning_rate": 3.5511922742459616e-05, "loss": 2.0344, "step": 63810 }, { "epoch": 2.91, "learning_rate": 3.5509634308206324e-05, "loss": 2.0262, "step": 63820 }, { "epoch": 2.91, "learning_rate": 3.550734587395304e-05, "loss": 2.1095, "step": 63830 }, { "epoch": 2.92, "learning_rate": 3.550505743969976e-05, "loss": 2.168, "step": 63840 }, { "epoch": 2.92, "learning_rate": 3.550276900544647e-05, "loss": 2.0086, "step": 63850 }, { "epoch": 2.92, "learning_rate": 3.550048057119319e-05, "loss": 2.1382, "step": 63860 }, { "epoch": 2.92, "learning_rate": 3.549819213693991e-05, "loss": 1.8703, "step": 63870 }, { "epoch": 2.92, "learning_rate": 3.549590370268662e-05, "loss": 2.0239, "step": 63880 }, { "epoch": 2.92, "learning_rate": 3.5493615268433336e-05, "loss": 2.0816, "step": 63890 }, { "epoch": 2.92, "learning_rate": 3.549132683418006e-05, "loss": 1.9258, "step": 63900 }, { "epoch": 2.92, "learning_rate": 3.548903839992677e-05, "loss": 1.9615, "step": 63910 }, { "epoch": 2.92, "learning_rate": 3.5486749965673485e-05, "loss": 2.1112, "step": 63920 }, { "epoch": 2.92, "learning_rate": 3.5484461531420206e-05, "loss": 2.1691, "step": 63930 }, { "epoch": 2.92, "learning_rate": 3.548217309716692e-05, "loss": 2.0838, "step": 63940 }, { "epoch": 2.92, "learning_rate": 3.5479884662913635e-05, "loss": 2.0675, "step": 63950 }, { "epoch": 2.92, "learning_rate": 3.5477596228660355e-05, "loss": 2.1206, "step": 63960 }, { "epoch": 2.92, "learning_rate": 3.547530779440707e-05, "loss": 2.2043, "step": 63970 }, { "epoch": 2.92, "learning_rate": 3.5473019360153784e-05, "loss": 2.0469, "step": 63980 }, { "epoch": 2.92, "learning_rate": 3.5470730925900505e-05, "loss": 1.9647, "step": 63990 }, { "epoch": 2.92, "learning_rate": 3.546844249164722e-05, "loss": 2.0022, "step": 64000 }, { "epoch": 2.92, "learning_rate": 3.546615405739393e-05, "loss": 1.9386, "step": 64010 }, { "epoch": 2.92, "learning_rate": 3.546386562314065e-05, "loss": 1.9147, "step": 64020 }, { "epoch": 2.92, "learning_rate": 3.546157718888736e-05, "loss": 2.2908, "step": 64030 }, { "epoch": 2.92, "learning_rate": 3.545928875463408e-05, "loss": 2.092, "step": 64040 }, { "epoch": 2.92, "learning_rate": 3.5457000320380796e-05, "loss": 2.146, "step": 64050 }, { "epoch": 2.93, "learning_rate": 3.545471188612751e-05, "loss": 2.198, "step": 64060 }, { "epoch": 2.93, "learning_rate": 3.545242345187423e-05, "loss": 2.1352, "step": 64070 }, { "epoch": 2.93, "learning_rate": 3.5450135017620945e-05, "loss": 2.0261, "step": 64080 }, { "epoch": 2.93, "learning_rate": 3.544784658336766e-05, "loss": 2.0722, "step": 64090 }, { "epoch": 2.93, "learning_rate": 3.544555814911438e-05, "loss": 2.0247, "step": 64100 }, { "epoch": 2.93, "learning_rate": 3.5443269714861095e-05, "loss": 2.1175, "step": 64110 }, { "epoch": 2.93, "learning_rate": 3.544098128060781e-05, "loss": 2.0679, "step": 64120 }, { "epoch": 2.93, "learning_rate": 3.543869284635453e-05, "loss": 2.0412, "step": 64130 }, { "epoch": 2.93, "learning_rate": 3.5436404412101244e-05, "loss": 2.0443, "step": 64140 }, { "epoch": 2.93, "learning_rate": 3.543411597784796e-05, "loss": 2.0371, "step": 64150 }, { "epoch": 2.93, "learning_rate": 3.543182754359468e-05, "loss": 2.1423, "step": 64160 }, { "epoch": 2.93, "learning_rate": 3.542953910934139e-05, "loss": 2.2121, "step": 64170 }, { "epoch": 2.93, "learning_rate": 3.542725067508811e-05, "loss": 2.0293, "step": 64180 }, { "epoch": 2.93, "learning_rate": 3.542496224083483e-05, "loss": 2.0593, "step": 64190 }, { "epoch": 2.93, "learning_rate": 3.542267380658154e-05, "loss": 2.021, "step": 64200 }, { "epoch": 2.93, "learning_rate": 3.542038537232825e-05, "loss": 1.8308, "step": 64210 }, { "epoch": 2.93, "learning_rate": 3.541809693807497e-05, "loss": 2.0039, "step": 64220 }, { "epoch": 2.93, "learning_rate": 3.5415808503821684e-05, "loss": 2.0324, "step": 64230 }, { "epoch": 2.93, "learning_rate": 3.54135200695684e-05, "loss": 1.8653, "step": 64240 }, { "epoch": 2.93, "learning_rate": 3.541123163531512e-05, "loss": 2.0014, "step": 64250 }, { "epoch": 2.93, "learning_rate": 3.5408943201061834e-05, "loss": 1.9201, "step": 64260 }, { "epoch": 2.93, "learning_rate": 3.540665476680855e-05, "loss": 2.1074, "step": 64270 }, { "epoch": 2.94, "learning_rate": 3.540436633255527e-05, "loss": 2.1853, "step": 64280 }, { "epoch": 2.94, "learning_rate": 3.540207789830198e-05, "loss": 2.0957, "step": 64290 }, { "epoch": 2.94, "learning_rate": 3.53997894640487e-05, "loss": 2.1131, "step": 64300 }, { "epoch": 2.94, "learning_rate": 3.539750102979542e-05, "loss": 2.0407, "step": 64310 }, { "epoch": 2.94, "learning_rate": 3.539521259554213e-05, "loss": 1.9996, "step": 64320 }, { "epoch": 2.94, "learning_rate": 3.5392924161288846e-05, "loss": 2.0219, "step": 64330 }, { "epoch": 2.94, "learning_rate": 3.539063572703557e-05, "loss": 1.9493, "step": 64340 }, { "epoch": 2.94, "learning_rate": 3.538834729278228e-05, "loss": 2.1053, "step": 64350 }, { "epoch": 2.94, "learning_rate": 3.5386058858528995e-05, "loss": 1.9469, "step": 64360 }, { "epoch": 2.94, "learning_rate": 3.5383770424275716e-05, "loss": 2.0777, "step": 64370 }, { "epoch": 2.94, "learning_rate": 3.538148199002243e-05, "loss": 2.2915, "step": 64380 }, { "epoch": 2.94, "learning_rate": 3.5379193555769144e-05, "loss": 2.0676, "step": 64390 }, { "epoch": 2.94, "learning_rate": 3.5376905121515865e-05, "loss": 2.0919, "step": 64400 }, { "epoch": 2.94, "learning_rate": 3.537461668726257e-05, "loss": 1.9548, "step": 64410 }, { "epoch": 2.94, "learning_rate": 3.5372328253009294e-05, "loss": 2.2208, "step": 64420 }, { "epoch": 2.94, "learning_rate": 3.537003981875601e-05, "loss": 2.2031, "step": 64430 }, { "epoch": 2.94, "learning_rate": 3.536775138450272e-05, "loss": 2.0532, "step": 64440 }, { "epoch": 2.94, "learning_rate": 3.5365462950249436e-05, "loss": 2.0715, "step": 64450 }, { "epoch": 2.94, "learning_rate": 3.536317451599616e-05, "loss": 2.09, "step": 64460 }, { "epoch": 2.94, "learning_rate": 3.536088608174287e-05, "loss": 1.939, "step": 64470 }, { "epoch": 2.94, "learning_rate": 3.5358597647489585e-05, "loss": 2.042, "step": 64480 }, { "epoch": 2.94, "learning_rate": 3.5356309213236306e-05, "loss": 2.152, "step": 64490 }, { "epoch": 2.95, "learning_rate": 3.535402077898302e-05, "loss": 2.0898, "step": 64500 }, { "epoch": 2.95, "learning_rate": 3.5351732344729734e-05, "loss": 2.0689, "step": 64510 }, { "epoch": 2.95, "learning_rate": 3.5349443910476455e-05, "loss": 2.1836, "step": 64520 }, { "epoch": 2.95, "learning_rate": 3.534715547622317e-05, "loss": 2.2118, "step": 64530 }, { "epoch": 2.95, "learning_rate": 3.5344867041969884e-05, "loss": 2.1436, "step": 64540 }, { "epoch": 2.95, "learning_rate": 3.5342578607716605e-05, "loss": 2.0846, "step": 64550 }, { "epoch": 2.95, "learning_rate": 3.534029017346332e-05, "loss": 1.9308, "step": 64560 }, { "epoch": 2.95, "learning_rate": 3.533800173921003e-05, "loss": 2.0135, "step": 64570 }, { "epoch": 2.95, "learning_rate": 3.5335713304956754e-05, "loss": 2.0787, "step": 64580 }, { "epoch": 2.95, "learning_rate": 3.533342487070347e-05, "loss": 1.8509, "step": 64590 }, { "epoch": 2.95, "learning_rate": 3.533113643645018e-05, "loss": 2.0388, "step": 64600 }, { "epoch": 2.95, "learning_rate": 3.5328848002196896e-05, "loss": 2.0698, "step": 64610 }, { "epoch": 2.95, "learning_rate": 3.532655956794361e-05, "loss": 2.1212, "step": 64620 }, { "epoch": 2.95, "learning_rate": 3.532427113369033e-05, "loss": 2.1173, "step": 64630 }, { "epoch": 2.95, "learning_rate": 3.5321982699437045e-05, "loss": 1.8953, "step": 64640 }, { "epoch": 2.95, "learning_rate": 3.531969426518376e-05, "loss": 1.9969, "step": 64650 }, { "epoch": 2.95, "learning_rate": 3.531740583093048e-05, "loss": 2.1111, "step": 64660 }, { "epoch": 2.95, "learning_rate": 3.5315117396677194e-05, "loss": 2.0365, "step": 64670 }, { "epoch": 2.95, "learning_rate": 3.531282896242391e-05, "loss": 2.0742, "step": 64680 }, { "epoch": 2.95, "learning_rate": 3.531054052817063e-05, "loss": 2.1224, "step": 64690 }, { "epoch": 2.95, "learning_rate": 3.5308252093917344e-05, "loss": 2.1756, "step": 64700 }, { "epoch": 2.95, "learning_rate": 3.530596365966406e-05, "loss": 2.2193, "step": 64710 }, { "epoch": 2.96, "learning_rate": 3.530367522541078e-05, "loss": 2.0084, "step": 64720 }, { "epoch": 2.96, "learning_rate": 3.530138679115749e-05, "loss": 1.9547, "step": 64730 }, { "epoch": 2.96, "learning_rate": 3.529909835690421e-05, "loss": 2.1422, "step": 64740 }, { "epoch": 2.96, "learning_rate": 3.529680992265093e-05, "loss": 2.0158, "step": 64750 }, { "epoch": 2.96, "learning_rate": 3.529452148839764e-05, "loss": 2.2557, "step": 64760 }, { "epoch": 2.96, "learning_rate": 3.5292233054144356e-05, "loss": 1.9488, "step": 64770 }, { "epoch": 2.96, "learning_rate": 3.528994461989108e-05, "loss": 2.1303, "step": 64780 }, { "epoch": 2.96, "learning_rate": 3.528765618563779e-05, "loss": 1.9495, "step": 64790 }, { "epoch": 2.96, "learning_rate": 3.5285367751384505e-05, "loss": 1.9808, "step": 64800 }, { "epoch": 2.96, "learning_rate": 3.528307931713122e-05, "loss": 1.7677, "step": 64810 }, { "epoch": 2.96, "learning_rate": 3.5280790882877934e-05, "loss": 1.9339, "step": 64820 }, { "epoch": 2.96, "learning_rate": 3.527850244862465e-05, "loss": 2.1138, "step": 64830 }, { "epoch": 2.96, "learning_rate": 3.527621401437137e-05, "loss": 2.2336, "step": 64840 }, { "epoch": 2.96, "learning_rate": 3.527392558011808e-05, "loss": 1.8799, "step": 64850 }, { "epoch": 2.96, "learning_rate": 3.52716371458648e-05, "loss": 2.0519, "step": 64860 }, { "epoch": 2.96, "learning_rate": 3.526934871161152e-05, "loss": 2.0874, "step": 64870 }, { "epoch": 2.96, "learning_rate": 3.526706027735823e-05, "loss": 1.8718, "step": 64880 }, { "epoch": 2.96, "learning_rate": 3.5264771843104946e-05, "loss": 2.0125, "step": 64890 }, { "epoch": 2.96, "learning_rate": 3.526248340885167e-05, "loss": 2.0032, "step": 64900 }, { "epoch": 2.96, "learning_rate": 3.526019497459838e-05, "loss": 1.97, "step": 64910 }, { "epoch": 2.96, "learning_rate": 3.5257906540345095e-05, "loss": 2.1125, "step": 64920 }, { "epoch": 2.96, "learning_rate": 3.5255618106091816e-05, "loss": 2.0043, "step": 64930 }, { "epoch": 2.97, "learning_rate": 3.525332967183853e-05, "loss": 2.0069, "step": 64940 }, { "epoch": 2.97, "learning_rate": 3.5251041237585244e-05, "loss": 2.1616, "step": 64950 }, { "epoch": 2.97, "learning_rate": 3.5248752803331965e-05, "loss": 2.1043, "step": 64960 }, { "epoch": 2.97, "learning_rate": 3.524646436907868e-05, "loss": 1.8665, "step": 64970 }, { "epoch": 2.97, "learning_rate": 3.5244175934825394e-05, "loss": 1.9385, "step": 64980 }, { "epoch": 2.97, "learning_rate": 3.5241887500572114e-05, "loss": 1.9203, "step": 64990 }, { "epoch": 2.97, "learning_rate": 3.523959906631882e-05, "loss": 2.0301, "step": 65000 }, { "epoch": 2.97, "learning_rate": 3.523731063206554e-05, "loss": 1.9661, "step": 65010 }, { "epoch": 2.97, "learning_rate": 3.523502219781226e-05, "loss": 2.0065, "step": 65020 }, { "epoch": 2.97, "learning_rate": 3.523273376355897e-05, "loss": 1.9737, "step": 65030 }, { "epoch": 2.97, "learning_rate": 3.523044532930569e-05, "loss": 1.9764, "step": 65040 }, { "epoch": 2.97, "learning_rate": 3.5228156895052406e-05, "loss": 2.0034, "step": 65050 }, { "epoch": 2.97, "learning_rate": 3.522586846079912e-05, "loss": 2.0165, "step": 65060 }, { "epoch": 2.97, "learning_rate": 3.522358002654584e-05, "loss": 2.1622, "step": 65070 }, { "epoch": 2.97, "learning_rate": 3.5221291592292555e-05, "loss": 1.8919, "step": 65080 }, { "epoch": 2.97, "learning_rate": 3.521900315803927e-05, "loss": 2.0234, "step": 65090 }, { "epoch": 2.97, "learning_rate": 3.521671472378599e-05, "loss": 1.9994, "step": 65100 }, { "epoch": 2.97, "learning_rate": 3.5214426289532704e-05, "loss": 2.1417, "step": 65110 }, { "epoch": 2.97, "learning_rate": 3.521213785527942e-05, "loss": 2.0607, "step": 65120 }, { "epoch": 2.97, "learning_rate": 3.520984942102614e-05, "loss": 1.9436, "step": 65130 }, { "epoch": 2.97, "learning_rate": 3.5207560986772854e-05, "loss": 2.0158, "step": 65140 }, { "epoch": 2.97, "learning_rate": 3.520527255251957e-05, "loss": 2.1724, "step": 65150 }, { "epoch": 2.98, "learning_rate": 3.520298411826629e-05, "loss": 2.0314, "step": 65160 }, { "epoch": 2.98, "learning_rate": 3.5200695684013e-05, "loss": 1.853, "step": 65170 }, { "epoch": 2.98, "learning_rate": 3.519840724975972e-05, "loss": 1.8914, "step": 65180 }, { "epoch": 2.98, "learning_rate": 3.519611881550644e-05, "loss": 2.0688, "step": 65190 }, { "epoch": 2.98, "learning_rate": 3.5193830381253145e-05, "loss": 2.154, "step": 65200 }, { "epoch": 2.98, "learning_rate": 3.519154194699986e-05, "loss": 2.0105, "step": 65210 }, { "epoch": 2.98, "learning_rate": 3.518925351274658e-05, "loss": 1.8688, "step": 65220 }, { "epoch": 2.98, "learning_rate": 3.5186965078493294e-05, "loss": 1.9687, "step": 65230 }, { "epoch": 2.98, "learning_rate": 3.518467664424001e-05, "loss": 1.9426, "step": 65240 }, { "epoch": 2.98, "learning_rate": 3.518238820998673e-05, "loss": 1.9072, "step": 65250 }, { "epoch": 2.98, "learning_rate": 3.5180099775733444e-05, "loss": 2.072, "step": 65260 }, { "epoch": 2.98, "learning_rate": 3.517781134148016e-05, "loss": 1.9674, "step": 65270 }, { "epoch": 2.98, "learning_rate": 3.517552290722688e-05, "loss": 1.9922, "step": 65280 }, { "epoch": 2.98, "learning_rate": 3.517323447297359e-05, "loss": 1.8828, "step": 65290 }, { "epoch": 2.98, "learning_rate": 3.517094603872031e-05, "loss": 1.8896, "step": 65300 }, { "epoch": 2.98, "learning_rate": 3.516865760446703e-05, "loss": 1.9864, "step": 65310 }, { "epoch": 2.98, "learning_rate": 3.516636917021374e-05, "loss": 1.9561, "step": 65320 }, { "epoch": 2.98, "learning_rate": 3.5164080735960456e-05, "loss": 2.1277, "step": 65330 }, { "epoch": 2.98, "learning_rate": 3.516179230170718e-05, "loss": 1.9745, "step": 65340 }, { "epoch": 2.98, "learning_rate": 3.515950386745389e-05, "loss": 2.0006, "step": 65350 }, { "epoch": 2.98, "learning_rate": 3.5157215433200605e-05, "loss": 1.9846, "step": 65360 }, { "epoch": 2.98, "learning_rate": 3.5154926998947326e-05, "loss": 1.9987, "step": 65370 }, { "epoch": 2.99, "learning_rate": 3.515263856469404e-05, "loss": 1.9602, "step": 65380 }, { "epoch": 2.99, "learning_rate": 3.5150350130440754e-05, "loss": 2.1301, "step": 65390 }, { "epoch": 2.99, "learning_rate": 3.514806169618747e-05, "loss": 2.0459, "step": 65400 }, { "epoch": 2.99, "learning_rate": 3.514577326193418e-05, "loss": 2.0249, "step": 65410 }, { "epoch": 2.99, "learning_rate": 3.5143484827680904e-05, "loss": 2.0942, "step": 65420 }, { "epoch": 2.99, "learning_rate": 3.514119639342762e-05, "loss": 1.9021, "step": 65430 }, { "epoch": 2.99, "learning_rate": 3.513890795917433e-05, "loss": 1.9721, "step": 65440 }, { "epoch": 2.99, "learning_rate": 3.513661952492105e-05, "loss": 1.9177, "step": 65450 }, { "epoch": 2.99, "learning_rate": 3.513433109066777e-05, "loss": 2.1313, "step": 65460 }, { "epoch": 2.99, "learning_rate": 3.513204265641448e-05, "loss": 1.8833, "step": 65470 }, { "epoch": 2.99, "learning_rate": 3.51297542221612e-05, "loss": 1.8335, "step": 65480 }, { "epoch": 2.99, "learning_rate": 3.5127465787907916e-05, "loss": 2.0408, "step": 65490 }, { "epoch": 2.99, "learning_rate": 3.512517735365463e-05, "loss": 1.9036, "step": 65500 }, { "epoch": 2.99, "learning_rate": 3.512288891940135e-05, "loss": 2.0914, "step": 65510 }, { "epoch": 2.99, "learning_rate": 3.5120600485148065e-05, "loss": 1.9718, "step": 65520 }, { "epoch": 2.99, "learning_rate": 3.511831205089478e-05, "loss": 2.0254, "step": 65530 }, { "epoch": 2.99, "learning_rate": 3.51160236166415e-05, "loss": 2.0939, "step": 65540 }, { "epoch": 2.99, "learning_rate": 3.5113735182388214e-05, "loss": 1.9943, "step": 65550 }, { "epoch": 2.99, "learning_rate": 3.511144674813493e-05, "loss": 2.0423, "step": 65560 }, { "epoch": 2.99, "learning_rate": 3.510915831388164e-05, "loss": 2.0476, "step": 65570 }, { "epoch": 2.99, "learning_rate": 3.5106869879628364e-05, "loss": 2.0666, "step": 65580 }, { "epoch": 3.0, "learning_rate": 3.510458144537508e-05, "loss": 1.9764, "step": 65590 }, { "epoch": 3.0, "learning_rate": 3.510229301112179e-05, "loss": 2.1473, "step": 65600 }, { "epoch": 3.0, "learning_rate": 3.5100004576868506e-05, "loss": 1.9205, "step": 65610 }, { "epoch": 3.0, "learning_rate": 3.509771614261522e-05, "loss": 2.1119, "step": 65620 }, { "epoch": 3.0, "learning_rate": 3.509542770836194e-05, "loss": 1.9427, "step": 65630 }, { "epoch": 3.0, "learning_rate": 3.5093139274108655e-05, "loss": 1.9341, "step": 65640 }, { "epoch": 3.0, "learning_rate": 3.509085083985537e-05, "loss": 1.965, "step": 65650 }, { "epoch": 3.0, "learning_rate": 3.508856240560209e-05, "loss": 2.0833, "step": 65660 }, { "epoch": 3.0, "learning_rate": 3.5086273971348804e-05, "loss": 2.102, "step": 65670 }, { "epoch": 3.0, "learning_rate": 3.508398553709552e-05, "loss": 2.0989, "step": 65680 }, { "epoch": 3.0, "learning_rate": 3.508169710284224e-05, "loss": 2.035, "step": 65690 }, { "epoch": 3.0, "eval_cer": 0.6807407935661308, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.9044454097747803, "eval_runtime": 2633.3765, "eval_samples_per_second": 4.014, "eval_steps_per_second": 2.007, "eval_wer": 0.9927152317880795, "step": 65699 }, { "epoch": 3.0, "learning_rate": 3.5079408668588953e-05, "loss": 2.107, "step": 65700 }, { "epoch": 3.0, "learning_rate": 3.507712023433567e-05, "loss": 2.0731, "step": 65710 }, { "epoch": 3.0, "learning_rate": 3.507483180008239e-05, "loss": 1.959, "step": 65720 }, { "epoch": 3.0, "learning_rate": 3.50725433658291e-05, "loss": 2.0937, "step": 65730 }, { "epoch": 3.0, "learning_rate": 3.507025493157582e-05, "loss": 1.9316, "step": 65740 }, { "epoch": 3.0, "learning_rate": 3.506796649732254e-05, "loss": 1.9266, "step": 65750 }, { "epoch": 3.0, "learning_rate": 3.506567806306925e-05, "loss": 1.9143, "step": 65760 }, { "epoch": 3.0, "learning_rate": 3.5063389628815966e-05, "loss": 2.0249, "step": 65770 }, { "epoch": 3.0, "learning_rate": 3.506110119456269e-05, "loss": 1.8391, "step": 65780 }, { "epoch": 3.0, "learning_rate": 3.50588127603094e-05, "loss": 2.1696, "step": 65790 }, { "epoch": 3.0, "learning_rate": 3.505652432605611e-05, "loss": 2.0121, "step": 65800 }, { "epoch": 3.01, "learning_rate": 3.505423589180283e-05, "loss": 1.9284, "step": 65810 }, { "epoch": 3.01, "learning_rate": 3.5051947457549543e-05, "loss": 1.9831, "step": 65820 }, { "epoch": 3.01, "learning_rate": 3.504965902329626e-05, "loss": 2.0296, "step": 65830 }, { "epoch": 3.01, "learning_rate": 3.504737058904298e-05, "loss": 2.0328, "step": 65840 }, { "epoch": 3.01, "learning_rate": 3.504508215478969e-05, "loss": 1.9827, "step": 65850 }, { "epoch": 3.01, "learning_rate": 3.504279372053641e-05, "loss": 2.1162, "step": 65860 }, { "epoch": 3.01, "learning_rate": 3.504050528628313e-05, "loss": 1.9734, "step": 65870 }, { "epoch": 3.01, "learning_rate": 3.503821685202984e-05, "loss": 2.0136, "step": 65880 }, { "epoch": 3.01, "learning_rate": 3.5035928417776556e-05, "loss": 2.0476, "step": 65890 }, { "epoch": 3.01, "learning_rate": 3.503363998352328e-05, "loss": 2.0657, "step": 65900 }, { "epoch": 3.01, "learning_rate": 3.503135154926999e-05, "loss": 1.9619, "step": 65910 }, { "epoch": 3.01, "learning_rate": 3.5029063115016705e-05, "loss": 1.9462, "step": 65920 }, { "epoch": 3.01, "learning_rate": 3.5026774680763426e-05, "loss": 1.8008, "step": 65930 }, { "epoch": 3.01, "learning_rate": 3.502448624651014e-05, "loss": 1.8474, "step": 65940 }, { "epoch": 3.01, "learning_rate": 3.5022197812256854e-05, "loss": 2.1463, "step": 65950 }, { "epoch": 3.01, "learning_rate": 3.5019909378003575e-05, "loss": 1.822, "step": 65960 }, { "epoch": 3.01, "learning_rate": 3.501762094375029e-05, "loss": 2.104, "step": 65970 }, { "epoch": 3.01, "learning_rate": 3.5015332509497003e-05, "loss": 2.014, "step": 65980 }, { "epoch": 3.01, "learning_rate": 3.501304407524372e-05, "loss": 1.9058, "step": 65990 }, { "epoch": 3.01, "learning_rate": 3.501075564099043e-05, "loss": 2.0206, "step": 66000 }, { "epoch": 3.01, "learning_rate": 3.500846720673715e-05, "loss": 1.9975, "step": 66010 }, { "epoch": 3.01, "learning_rate": 3.500617877248387e-05, "loss": 1.8625, "step": 66020 }, { "epoch": 3.02, "learning_rate": 3.500389033823058e-05, "loss": 2.0558, "step": 66030 }, { "epoch": 3.02, "learning_rate": 3.50016019039773e-05, "loss": 2.0907, "step": 66040 }, { "epoch": 3.02, "learning_rate": 3.4999313469724016e-05, "loss": 2.0348, "step": 66050 }, { "epoch": 3.02, "learning_rate": 3.499702503547073e-05, "loss": 1.8939, "step": 66060 }, { "epoch": 3.02, "learning_rate": 3.499473660121745e-05, "loss": 2.0583, "step": 66070 }, { "epoch": 3.02, "learning_rate": 3.4992448166964165e-05, "loss": 2.0639, "step": 66080 }, { "epoch": 3.02, "learning_rate": 3.499015973271088e-05, "loss": 1.9499, "step": 66090 }, { "epoch": 3.02, "learning_rate": 3.49878712984576e-05, "loss": 1.9147, "step": 66100 }, { "epoch": 3.02, "learning_rate": 3.4985582864204314e-05, "loss": 1.9853, "step": 66110 }, { "epoch": 3.02, "learning_rate": 3.498329442995103e-05, "loss": 1.9574, "step": 66120 }, { "epoch": 3.02, "learning_rate": 3.498100599569775e-05, "loss": 1.8701, "step": 66130 }, { "epoch": 3.02, "learning_rate": 3.4978717561444463e-05, "loss": 1.9668, "step": 66140 }, { "epoch": 3.02, "learning_rate": 3.497642912719118e-05, "loss": 1.7449, "step": 66150 }, { "epoch": 3.02, "learning_rate": 3.49741406929379e-05, "loss": 1.9843, "step": 66160 }, { "epoch": 3.02, "learning_rate": 3.497185225868461e-05, "loss": 2.0896, "step": 66170 }, { "epoch": 3.02, "learning_rate": 3.496956382443133e-05, "loss": 1.8714, "step": 66180 }, { "epoch": 3.02, "learning_rate": 3.496727539017804e-05, "loss": 2.1349, "step": 66190 }, { "epoch": 3.02, "learning_rate": 3.4964986955924755e-05, "loss": 2.0456, "step": 66200 }, { "epoch": 3.02, "learning_rate": 3.496269852167147e-05, "loss": 2.0314, "step": 66210 }, { "epoch": 3.02, "learning_rate": 3.496041008741819e-05, "loss": 1.9114, "step": 66220 }, { "epoch": 3.02, "learning_rate": 3.4958121653164904e-05, "loss": 2.0461, "step": 66230 }, { "epoch": 3.02, "learning_rate": 3.495583321891162e-05, "loss": 2.1819, "step": 66240 }, { "epoch": 3.03, "learning_rate": 3.495354478465834e-05, "loss": 2.0584, "step": 66250 }, { "epoch": 3.03, "learning_rate": 3.495125635040505e-05, "loss": 1.9912, "step": 66260 }, { "epoch": 3.03, "learning_rate": 3.494896791615177e-05, "loss": 2.1467, "step": 66270 }, { "epoch": 3.03, "learning_rate": 3.494667948189849e-05, "loss": 2.1538, "step": 66280 }, { "epoch": 3.03, "learning_rate": 3.49443910476452e-05, "loss": 2.0525, "step": 66290 }, { "epoch": 3.03, "learning_rate": 3.494210261339192e-05, "loss": 2.0198, "step": 66300 }, { "epoch": 3.03, "learning_rate": 3.493981417913864e-05, "loss": 1.9498, "step": 66310 }, { "epoch": 3.03, "learning_rate": 3.493752574488535e-05, "loss": 1.9751, "step": 66320 }, { "epoch": 3.03, "learning_rate": 3.4935237310632066e-05, "loss": 2.1092, "step": 66330 }, { "epoch": 3.03, "learning_rate": 3.493294887637879e-05, "loss": 2.0874, "step": 66340 }, { "epoch": 3.03, "learning_rate": 3.49306604421255e-05, "loss": 1.8925, "step": 66350 }, { "epoch": 3.03, "learning_rate": 3.4928372007872215e-05, "loss": 2.0202, "step": 66360 }, { "epoch": 3.03, "learning_rate": 3.4926083573618936e-05, "loss": 1.7617, "step": 66370 }, { "epoch": 3.03, "learning_rate": 3.492379513936565e-05, "loss": 2.017, "step": 66380 }, { "epoch": 3.03, "learning_rate": 3.4921506705112364e-05, "loss": 1.9667, "step": 66390 }, { "epoch": 3.03, "learning_rate": 3.491921827085908e-05, "loss": 1.9339, "step": 66400 }, { "epoch": 3.03, "learning_rate": 3.491692983660579e-05, "loss": 2.0194, "step": 66410 }, { "epoch": 3.03, "learning_rate": 3.4914641402352513e-05, "loss": 1.926, "step": 66420 }, { "epoch": 3.03, "learning_rate": 3.491235296809923e-05, "loss": 2.0078, "step": 66430 }, { "epoch": 3.03, "learning_rate": 3.491006453384594e-05, "loss": 1.875, "step": 66440 }, { "epoch": 3.03, "learning_rate": 3.490777609959266e-05, "loss": 1.9195, "step": 66450 }, { "epoch": 3.03, "learning_rate": 3.490548766533938e-05, "loss": 2.1093, "step": 66460 }, { "epoch": 3.04, "learning_rate": 3.490319923108609e-05, "loss": 1.9178, "step": 66470 }, { "epoch": 3.04, "learning_rate": 3.490091079683281e-05, "loss": 1.9808, "step": 66480 }, { "epoch": 3.04, "learning_rate": 3.4898622362579526e-05, "loss": 1.9674, "step": 66490 }, { "epoch": 3.04, "learning_rate": 3.489633392832624e-05, "loss": 1.9658, "step": 66500 }, { "epoch": 3.04, "learning_rate": 3.489404549407296e-05, "loss": 2.0603, "step": 66510 }, { "epoch": 3.04, "learning_rate": 3.4891757059819675e-05, "loss": 2.0439, "step": 66520 }, { "epoch": 3.04, "learning_rate": 3.488946862556639e-05, "loss": 1.8842, "step": 66530 }, { "epoch": 3.04, "learning_rate": 3.488718019131311e-05, "loss": 2.0639, "step": 66540 }, { "epoch": 3.04, "learning_rate": 3.4884891757059824e-05, "loss": 1.9075, "step": 66550 }, { "epoch": 3.04, "learning_rate": 3.488260332280654e-05, "loss": 2.0809, "step": 66560 }, { "epoch": 3.04, "learning_rate": 3.488031488855326e-05, "loss": 1.8699, "step": 66570 }, { "epoch": 3.04, "learning_rate": 3.4878026454299973e-05, "loss": 2.0375, "step": 66580 }, { "epoch": 3.04, "learning_rate": 3.487573802004668e-05, "loss": 1.9963, "step": 66590 }, { "epoch": 3.04, "learning_rate": 3.48734495857934e-05, "loss": 2.0538, "step": 66600 }, { "epoch": 3.04, "learning_rate": 3.4871161151540116e-05, "loss": 2.0582, "step": 66610 }, { "epoch": 3.04, "learning_rate": 3.486887271728683e-05, "loss": 2.0269, "step": 66620 }, { "epoch": 3.04, "learning_rate": 3.486658428303355e-05, "loss": 2.0462, "step": 66630 }, { "epoch": 3.04, "learning_rate": 3.4864295848780265e-05, "loss": 1.9349, "step": 66640 }, { "epoch": 3.04, "learning_rate": 3.486200741452698e-05, "loss": 2.0604, "step": 66650 }, { "epoch": 3.04, "learning_rate": 3.48597189802737e-05, "loss": 1.955, "step": 66660 }, { "epoch": 3.04, "learning_rate": 3.4857430546020414e-05, "loss": 1.815, "step": 66670 }, { "epoch": 3.04, "learning_rate": 3.485514211176713e-05, "loss": 2.0069, "step": 66680 }, { "epoch": 3.05, "learning_rate": 3.485285367751385e-05, "loss": 2.0301, "step": 66690 }, { "epoch": 3.05, "learning_rate": 3.485056524326056e-05, "loss": 1.8433, "step": 66700 }, { "epoch": 3.05, "learning_rate": 3.484827680900728e-05, "loss": 1.8886, "step": 66710 }, { "epoch": 3.05, "learning_rate": 3.4845988374754e-05, "loss": 1.8832, "step": 66720 }, { "epoch": 3.05, "learning_rate": 3.484369994050071e-05, "loss": 1.942, "step": 66730 }, { "epoch": 3.05, "learning_rate": 3.484141150624743e-05, "loss": 1.8672, "step": 66740 }, { "epoch": 3.05, "learning_rate": 3.483912307199415e-05, "loss": 1.8246, "step": 66750 }, { "epoch": 3.05, "learning_rate": 3.483683463774086e-05, "loss": 1.8365, "step": 66760 }, { "epoch": 3.05, "learning_rate": 3.4834546203487576e-05, "loss": 2.0845, "step": 66770 }, { "epoch": 3.05, "learning_rate": 3.483225776923429e-05, "loss": 1.9951, "step": 66780 }, { "epoch": 3.05, "learning_rate": 3.4829969334981004e-05, "loss": 2.0649, "step": 66790 }, { "epoch": 3.05, "learning_rate": 3.482768090072772e-05, "loss": 2.0857, "step": 66800 }, { "epoch": 3.05, "learning_rate": 3.482539246647444e-05, "loss": 1.8852, "step": 66810 }, { "epoch": 3.05, "learning_rate": 3.482310403222115e-05, "loss": 2.159, "step": 66820 }, { "epoch": 3.05, "learning_rate": 3.482081559796787e-05, "loss": 2.1253, "step": 66830 }, { "epoch": 3.05, "learning_rate": 3.481852716371459e-05, "loss": 2.0227, "step": 66840 }, { "epoch": 3.05, "learning_rate": 3.48162387294613e-05, "loss": 2.0453, "step": 66850 }, { "epoch": 3.05, "learning_rate": 3.4813950295208017e-05, "loss": 2.0019, "step": 66860 }, { "epoch": 3.05, "learning_rate": 3.481166186095474e-05, "loss": 1.7736, "step": 66870 }, { "epoch": 3.05, "learning_rate": 3.480937342670145e-05, "loss": 2.0444, "step": 66880 }, { "epoch": 3.05, "learning_rate": 3.4807084992448166e-05, "loss": 1.9445, "step": 66890 }, { "epoch": 3.05, "learning_rate": 3.480479655819489e-05, "loss": 2.081, "step": 66900 }, { "epoch": 3.06, "learning_rate": 3.48025081239416e-05, "loss": 2.0239, "step": 66910 }, { "epoch": 3.06, "learning_rate": 3.4800219689688315e-05, "loss": 1.9294, "step": 66920 }, { "epoch": 3.06, "learning_rate": 3.4797931255435036e-05, "loss": 2.0187, "step": 66930 }, { "epoch": 3.06, "learning_rate": 3.479564282118175e-05, "loss": 2.0216, "step": 66940 }, { "epoch": 3.06, "learning_rate": 3.4793354386928464e-05, "loss": 1.8684, "step": 66950 }, { "epoch": 3.06, "learning_rate": 3.4791065952675185e-05, "loss": 2.0318, "step": 66960 }, { "epoch": 3.06, "learning_rate": 3.47887775184219e-05, "loss": 1.9717, "step": 66970 }, { "epoch": 3.06, "learning_rate": 3.478648908416861e-05, "loss": 1.6836, "step": 66980 }, { "epoch": 3.06, "learning_rate": 3.478420064991533e-05, "loss": 1.8963, "step": 66990 }, { "epoch": 3.06, "learning_rate": 3.478191221566204e-05, "loss": 2.0319, "step": 67000 }, { "epoch": 3.06, "learning_rate": 3.477962378140876e-05, "loss": 1.9713, "step": 67010 }, { "epoch": 3.06, "learning_rate": 3.4777335347155477e-05, "loss": 1.8088, "step": 67020 }, { "epoch": 3.06, "learning_rate": 3.477504691290219e-05, "loss": 2.0618, "step": 67030 }, { "epoch": 3.06, "learning_rate": 3.477275847864891e-05, "loss": 1.9863, "step": 67040 }, { "epoch": 3.06, "learning_rate": 3.4770470044395626e-05, "loss": 1.9362, "step": 67050 }, { "epoch": 3.06, "learning_rate": 3.476818161014234e-05, "loss": 1.9975, "step": 67060 }, { "epoch": 3.06, "learning_rate": 3.476589317588906e-05, "loss": 1.9041, "step": 67070 }, { "epoch": 3.06, "learning_rate": 3.4763604741635775e-05, "loss": 2.0651, "step": 67080 }, { "epoch": 3.06, "learning_rate": 3.476131630738249e-05, "loss": 2.0784, "step": 67090 }, { "epoch": 3.06, "learning_rate": 3.475902787312921e-05, "loss": 1.9664, "step": 67100 }, { "epoch": 3.06, "learning_rate": 3.4756739438875924e-05, "loss": 1.9294, "step": 67110 }, { "epoch": 3.06, "learning_rate": 3.475445100462264e-05, "loss": 1.9366, "step": 67120 }, { "epoch": 3.07, "learning_rate": 3.475216257036936e-05, "loss": 2.0381, "step": 67130 }, { "epoch": 3.07, "learning_rate": 3.474987413611607e-05, "loss": 1.9384, "step": 67140 }, { "epoch": 3.07, "learning_rate": 3.474758570186279e-05, "loss": 1.9048, "step": 67150 }, { "epoch": 3.07, "learning_rate": 3.474529726760951e-05, "loss": 1.9533, "step": 67160 }, { "epoch": 3.07, "learning_rate": 3.474300883335622e-05, "loss": 1.9307, "step": 67170 }, { "epoch": 3.07, "learning_rate": 3.474072039910293e-05, "loss": 1.9698, "step": 67180 }, { "epoch": 3.07, "learning_rate": 3.473843196484965e-05, "loss": 1.9995, "step": 67190 }, { "epoch": 3.07, "learning_rate": 3.4736143530596365e-05, "loss": 1.8949, "step": 67200 }, { "epoch": 3.07, "learning_rate": 3.473385509634308e-05, "loss": 1.8754, "step": 67210 }, { "epoch": 3.07, "learning_rate": 3.47315666620898e-05, "loss": 1.9892, "step": 67220 }, { "epoch": 3.07, "learning_rate": 3.4729278227836514e-05, "loss": 1.8586, "step": 67230 }, { "epoch": 3.07, "learning_rate": 3.472698979358323e-05, "loss": 1.9596, "step": 67240 }, { "epoch": 3.07, "learning_rate": 3.472470135932995e-05, "loss": 1.9756, "step": 67250 }, { "epoch": 3.07, "learning_rate": 3.472241292507666e-05, "loss": 2.104, "step": 67260 }, { "epoch": 3.07, "learning_rate": 3.472012449082338e-05, "loss": 2.0174, "step": 67270 }, { "epoch": 3.07, "learning_rate": 3.47178360565701e-05, "loss": 2.0657, "step": 67280 }, { "epoch": 3.07, "learning_rate": 3.471554762231681e-05, "loss": 1.9784, "step": 67290 }, { "epoch": 3.07, "learning_rate": 3.4713259188063527e-05, "loss": 2.0645, "step": 67300 }, { "epoch": 3.07, "learning_rate": 3.471097075381025e-05, "loss": 1.9296, "step": 67310 }, { "epoch": 3.07, "learning_rate": 3.470868231955696e-05, "loss": 2.0668, "step": 67320 }, { "epoch": 3.07, "learning_rate": 3.4706393885303676e-05, "loss": 1.8613, "step": 67330 }, { "epoch": 3.07, "learning_rate": 3.47041054510504e-05, "loss": 1.9852, "step": 67340 }, { "epoch": 3.08, "learning_rate": 3.470181701679711e-05, "loss": 2.0227, "step": 67350 }, { "epoch": 3.08, "learning_rate": 3.4699528582543825e-05, "loss": 1.8103, "step": 67360 }, { "epoch": 3.08, "learning_rate": 3.4697240148290546e-05, "loss": 2.0317, "step": 67370 }, { "epoch": 3.08, "learning_rate": 3.469495171403725e-05, "loss": 1.9637, "step": 67380 }, { "epoch": 3.08, "learning_rate": 3.4692663279783974e-05, "loss": 1.889, "step": 67390 }, { "epoch": 3.08, "learning_rate": 3.469037484553069e-05, "loss": 1.9187, "step": 67400 }, { "epoch": 3.08, "learning_rate": 3.46880864112774e-05, "loss": 1.8984, "step": 67410 }, { "epoch": 3.08, "learning_rate": 3.468579797702412e-05, "loss": 1.8989, "step": 67420 }, { "epoch": 3.08, "learning_rate": 3.468350954277084e-05, "loss": 1.9518, "step": 67430 }, { "epoch": 3.08, "learning_rate": 3.468122110851755e-05, "loss": 1.9443, "step": 67440 }, { "epoch": 3.08, "learning_rate": 3.467893267426427e-05, "loss": 1.9366, "step": 67450 }, { "epoch": 3.08, "learning_rate": 3.4676644240010987e-05, "loss": 1.9336, "step": 67460 }, { "epoch": 3.08, "learning_rate": 3.46743558057577e-05, "loss": 1.9706, "step": 67470 }, { "epoch": 3.08, "learning_rate": 3.467206737150442e-05, "loss": 2.0954, "step": 67480 }, { "epoch": 3.08, "learning_rate": 3.4669778937251136e-05, "loss": 2.0708, "step": 67490 }, { "epoch": 3.08, "learning_rate": 3.466749050299785e-05, "loss": 1.9713, "step": 67500 }, { "epoch": 3.08, "learning_rate": 3.466520206874457e-05, "loss": 1.8769, "step": 67510 }, { "epoch": 3.08, "learning_rate": 3.4662913634491285e-05, "loss": 2.0029, "step": 67520 }, { "epoch": 3.08, "learning_rate": 3.4660625200238e-05, "loss": 1.996, "step": 67530 }, { "epoch": 3.08, "learning_rate": 3.465833676598472e-05, "loss": 2.0497, "step": 67540 }, { "epoch": 3.08, "learning_rate": 3.4656048331731434e-05, "loss": 2.0408, "step": 67550 }, { "epoch": 3.08, "learning_rate": 3.465375989747815e-05, "loss": 2.0512, "step": 67560 }, { "epoch": 3.09, "learning_rate": 3.465147146322486e-05, "loss": 1.9651, "step": 67570 }, { "epoch": 3.09, "learning_rate": 3.4649183028971577e-05, "loss": 1.7901, "step": 67580 }, { "epoch": 3.09, "learning_rate": 3.464689459471829e-05, "loss": 2.013, "step": 67590 }, { "epoch": 3.09, "learning_rate": 3.464460616046501e-05, "loss": 2.095, "step": 67600 }, { "epoch": 3.09, "learning_rate": 3.4642317726211726e-05, "loss": 1.997, "step": 67610 }, { "epoch": 3.09, "learning_rate": 3.464002929195844e-05, "loss": 1.9377, "step": 67620 }, { "epoch": 3.09, "learning_rate": 3.463774085770516e-05, "loss": 2.0333, "step": 67630 }, { "epoch": 3.09, "learning_rate": 3.4635452423451875e-05, "loss": 1.9044, "step": 67640 }, { "epoch": 3.09, "learning_rate": 3.463316398919859e-05, "loss": 1.9072, "step": 67650 }, { "epoch": 3.09, "learning_rate": 3.463087555494531e-05, "loss": 1.8999, "step": 67660 }, { "epoch": 3.09, "learning_rate": 3.4628587120692024e-05, "loss": 1.8618, "step": 67670 }, { "epoch": 3.09, "learning_rate": 3.462629868643874e-05, "loss": 1.8487, "step": 67680 }, { "epoch": 3.09, "learning_rate": 3.462401025218546e-05, "loss": 1.8145, "step": 67690 }, { "epoch": 3.09, "learning_rate": 3.462172181793217e-05, "loss": 1.8964, "step": 67700 }, { "epoch": 3.09, "learning_rate": 3.461943338367889e-05, "loss": 1.9192, "step": 67710 }, { "epoch": 3.09, "learning_rate": 3.461714494942561e-05, "loss": 1.8118, "step": 67720 }, { "epoch": 3.09, "learning_rate": 3.461485651517232e-05, "loss": 1.7929, "step": 67730 }, { "epoch": 3.09, "learning_rate": 3.4612568080919037e-05, "loss": 1.9493, "step": 67740 }, { "epoch": 3.09, "learning_rate": 3.461027964666576e-05, "loss": 1.9062, "step": 67750 }, { "epoch": 3.09, "learning_rate": 3.460799121241247e-05, "loss": 2.011, "step": 67760 }, { "epoch": 3.09, "learning_rate": 3.4605702778159186e-05, "loss": 1.8861, "step": 67770 }, { "epoch": 3.1, "learning_rate": 3.46034143439059e-05, "loss": 1.9118, "step": 67780 }, { "epoch": 3.1, "learning_rate": 3.4601125909652614e-05, "loss": 2.0688, "step": 67790 }, { "epoch": 3.1, "learning_rate": 3.4598837475399335e-05, "loss": 2.0279, "step": 67800 }, { "epoch": 3.1, "learning_rate": 3.459654904114605e-05, "loss": 1.7467, "step": 67810 }, { "epoch": 3.1, "learning_rate": 3.459426060689276e-05, "loss": 2.0071, "step": 67820 }, { "epoch": 3.1, "learning_rate": 3.4591972172639484e-05, "loss": 1.9504, "step": 67830 }, { "epoch": 3.1, "learning_rate": 3.45896837383862e-05, "loss": 2.0166, "step": 67840 }, { "epoch": 3.1, "learning_rate": 3.458739530413291e-05, "loss": 1.896, "step": 67850 }, { "epoch": 3.1, "learning_rate": 3.458510686987963e-05, "loss": 1.9977, "step": 67860 }, { "epoch": 3.1, "learning_rate": 3.458281843562635e-05, "loss": 1.9626, "step": 67870 }, { "epoch": 3.1, "learning_rate": 3.458053000137306e-05, "loss": 1.8625, "step": 67880 }, { "epoch": 3.1, "learning_rate": 3.457824156711978e-05, "loss": 1.8109, "step": 67890 }, { "epoch": 3.1, "learning_rate": 3.4575953132866497e-05, "loss": 1.8577, "step": 67900 }, { "epoch": 3.1, "learning_rate": 3.457366469861321e-05, "loss": 2.107, "step": 67910 }, { "epoch": 3.1, "learning_rate": 3.4571376264359925e-05, "loss": 1.9389, "step": 67920 }, { "epoch": 3.1, "learning_rate": 3.4569087830106646e-05, "loss": 2.0676, "step": 67930 }, { "epoch": 3.1, "learning_rate": 3.456679939585336e-05, "loss": 1.7857, "step": 67940 }, { "epoch": 3.1, "learning_rate": 3.4564510961600074e-05, "loss": 1.9593, "step": 67950 }, { "epoch": 3.1, "learning_rate": 3.4562222527346795e-05, "loss": 1.9399, "step": 67960 }, { "epoch": 3.1, "learning_rate": 3.45599340930935e-05, "loss": 1.874, "step": 67970 }, { "epoch": 3.1, "learning_rate": 3.455764565884022e-05, "loss": 1.8528, "step": 67980 }, { "epoch": 3.1, "learning_rate": 3.455535722458694e-05, "loss": 1.8209, "step": 67990 }, { "epoch": 3.11, "learning_rate": 3.455306879033365e-05, "loss": 1.9549, "step": 68000 }, { "epoch": 3.11, "learning_rate": 3.455078035608037e-05, "loss": 1.871, "step": 68010 }, { "epoch": 3.11, "learning_rate": 3.4548491921827086e-05, "loss": 1.8469, "step": 68020 }, { "epoch": 3.11, "learning_rate": 3.45462034875738e-05, "loss": 1.8967, "step": 68030 }, { "epoch": 3.11, "learning_rate": 3.454391505332052e-05, "loss": 2.0962, "step": 68040 }, { "epoch": 3.11, "learning_rate": 3.4541626619067236e-05, "loss": 2.1714, "step": 68050 }, { "epoch": 3.11, "learning_rate": 3.453933818481395e-05, "loss": 1.9498, "step": 68060 }, { "epoch": 3.11, "learning_rate": 3.453704975056067e-05, "loss": 1.7697, "step": 68070 }, { "epoch": 3.11, "learning_rate": 3.4534761316307385e-05, "loss": 2.0137, "step": 68080 }, { "epoch": 3.11, "learning_rate": 3.45324728820541e-05, "loss": 1.9648, "step": 68090 }, { "epoch": 3.11, "learning_rate": 3.453018444780082e-05, "loss": 2.0049, "step": 68100 }, { "epoch": 3.11, "learning_rate": 3.4527896013547534e-05, "loss": 1.8349, "step": 68110 }, { "epoch": 3.11, "learning_rate": 3.452560757929425e-05, "loss": 2.031, "step": 68120 }, { "epoch": 3.11, "learning_rate": 3.452331914504097e-05, "loss": 1.907, "step": 68130 }, { "epoch": 3.11, "learning_rate": 3.452103071078768e-05, "loss": 1.9106, "step": 68140 }, { "epoch": 3.11, "learning_rate": 3.45187422765344e-05, "loss": 2.0069, "step": 68150 }, { "epoch": 3.11, "learning_rate": 3.451645384228112e-05, "loss": 1.9374, "step": 68160 }, { "epoch": 3.11, "learning_rate": 3.4514165408027826e-05, "loss": 1.9342, "step": 68170 }, { "epoch": 3.11, "learning_rate": 3.451187697377454e-05, "loss": 2.1232, "step": 68180 }, { "epoch": 3.11, "learning_rate": 3.450958853952126e-05, "loss": 2.0053, "step": 68190 }, { "epoch": 3.11, "learning_rate": 3.4507300105267975e-05, "loss": 2.0111, "step": 68200 }, { "epoch": 3.11, "learning_rate": 3.450501167101469e-05, "loss": 1.8756, "step": 68210 }, { "epoch": 3.12, "learning_rate": 3.450272323676141e-05, "loss": 1.9128, "step": 68220 }, { "epoch": 3.12, "learning_rate": 3.4500434802508124e-05, "loss": 1.8589, "step": 68230 }, { "epoch": 3.12, "learning_rate": 3.449814636825484e-05, "loss": 1.8766, "step": 68240 }, { "epoch": 3.12, "learning_rate": 3.449585793400156e-05, "loss": 1.9826, "step": 68250 }, { "epoch": 3.12, "learning_rate": 3.449356949974827e-05, "loss": 1.8844, "step": 68260 }, { "epoch": 3.12, "learning_rate": 3.449128106549499e-05, "loss": 1.9797, "step": 68270 }, { "epoch": 3.12, "learning_rate": 3.448899263124171e-05, "loss": 1.9575, "step": 68280 }, { "epoch": 3.12, "learning_rate": 3.448670419698842e-05, "loss": 1.8583, "step": 68290 }, { "epoch": 3.12, "learning_rate": 3.4484415762735136e-05, "loss": 1.8995, "step": 68300 }, { "epoch": 3.12, "learning_rate": 3.448212732848186e-05, "loss": 1.9959, "step": 68310 }, { "epoch": 3.12, "learning_rate": 3.447983889422857e-05, "loss": 2.0555, "step": 68320 }, { "epoch": 3.12, "learning_rate": 3.4477550459975286e-05, "loss": 1.9309, "step": 68330 }, { "epoch": 3.12, "learning_rate": 3.4475262025722007e-05, "loss": 1.978, "step": 68340 }, { "epoch": 3.12, "learning_rate": 3.447297359146872e-05, "loss": 1.8868, "step": 68350 }, { "epoch": 3.12, "learning_rate": 3.4470685157215435e-05, "loss": 1.907, "step": 68360 }, { "epoch": 3.12, "learning_rate": 3.446839672296215e-05, "loss": 2.007, "step": 68370 }, { "epoch": 3.12, "learning_rate": 3.446610828870886e-05, "loss": 1.8688, "step": 68380 }, { "epoch": 3.12, "learning_rate": 3.4463819854455584e-05, "loss": 1.7555, "step": 68390 }, { "epoch": 3.12, "learning_rate": 3.44615314202023e-05, "loss": 1.7576, "step": 68400 }, { "epoch": 3.12, "learning_rate": 3.445924298594901e-05, "loss": 1.8282, "step": 68410 }, { "epoch": 3.12, "learning_rate": 3.445695455169573e-05, "loss": 1.9164, "step": 68420 }, { "epoch": 3.12, "learning_rate": 3.445466611744245e-05, "loss": 2.0911, "step": 68430 }, { "epoch": 3.13, "learning_rate": 3.445237768318916e-05, "loss": 1.9692, "step": 68440 }, { "epoch": 3.13, "learning_rate": 3.445008924893588e-05, "loss": 1.9508, "step": 68450 }, { "epoch": 3.13, "learning_rate": 3.4447800814682596e-05, "loss": 1.8362, "step": 68460 }, { "epoch": 3.13, "learning_rate": 3.444551238042931e-05, "loss": 2.0548, "step": 68470 }, { "epoch": 3.13, "learning_rate": 3.444322394617603e-05, "loss": 1.8324, "step": 68480 }, { "epoch": 3.13, "learning_rate": 3.4440935511922746e-05, "loss": 1.8906, "step": 68490 }, { "epoch": 3.13, "learning_rate": 3.443864707766946e-05, "loss": 2.0041, "step": 68500 }, { "epoch": 3.13, "learning_rate": 3.443635864341618e-05, "loss": 2.0285, "step": 68510 }, { "epoch": 3.13, "learning_rate": 3.4434070209162895e-05, "loss": 1.845, "step": 68520 }, { "epoch": 3.13, "learning_rate": 3.443178177490961e-05, "loss": 1.8506, "step": 68530 }, { "epoch": 3.13, "learning_rate": 3.442949334065633e-05, "loss": 1.8243, "step": 68540 }, { "epoch": 3.13, "learning_rate": 3.4427204906403044e-05, "loss": 1.9337, "step": 68550 }, { "epoch": 3.13, "learning_rate": 3.442491647214975e-05, "loss": 2.0351, "step": 68560 }, { "epoch": 3.13, "learning_rate": 3.442262803789647e-05, "loss": 2.0327, "step": 68570 }, { "epoch": 3.13, "learning_rate": 3.4420339603643186e-05, "loss": 1.8768, "step": 68580 }, { "epoch": 3.13, "learning_rate": 3.44180511693899e-05, "loss": 1.7461, "step": 68590 }, { "epoch": 3.13, "learning_rate": 3.441576273513662e-05, "loss": 1.7976, "step": 68600 }, { "epoch": 3.13, "learning_rate": 3.4413474300883336e-05, "loss": 1.7489, "step": 68610 }, { "epoch": 3.13, "learning_rate": 3.441118586663005e-05, "loss": 1.9417, "step": 68620 }, { "epoch": 3.13, "learning_rate": 3.440889743237677e-05, "loss": 1.9101, "step": 68630 }, { "epoch": 3.13, "learning_rate": 3.4406608998123485e-05, "loss": 1.9977, "step": 68640 }, { "epoch": 3.13, "learning_rate": 3.44043205638702e-05, "loss": 2.051, "step": 68650 }, { "epoch": 3.14, "learning_rate": 3.440203212961692e-05, "loss": 1.8792, "step": 68660 }, { "epoch": 3.14, "learning_rate": 3.4399743695363634e-05, "loss": 1.8464, "step": 68670 }, { "epoch": 3.14, "learning_rate": 3.439745526111035e-05, "loss": 1.925, "step": 68680 }, { "epoch": 3.14, "learning_rate": 3.439516682685707e-05, "loss": 1.5927, "step": 68690 }, { "epoch": 3.14, "learning_rate": 3.439287839260378e-05, "loss": 1.9792, "step": 68700 }, { "epoch": 3.14, "learning_rate": 3.43905899583505e-05, "loss": 1.8917, "step": 68710 }, { "epoch": 3.14, "learning_rate": 3.438830152409722e-05, "loss": 1.8785, "step": 68720 }, { "epoch": 3.14, "learning_rate": 3.438601308984393e-05, "loss": 1.9446, "step": 68730 }, { "epoch": 3.14, "learning_rate": 3.4383724655590646e-05, "loss": 1.8427, "step": 68740 }, { "epoch": 3.14, "learning_rate": 3.438143622133737e-05, "loss": 2.0015, "step": 68750 }, { "epoch": 3.14, "learning_rate": 3.4379147787084075e-05, "loss": 1.8198, "step": 68760 }, { "epoch": 3.14, "learning_rate": 3.4376859352830796e-05, "loss": 1.9261, "step": 68770 }, { "epoch": 3.14, "learning_rate": 3.437457091857751e-05, "loss": 1.9547, "step": 68780 }, { "epoch": 3.14, "learning_rate": 3.4372282484324224e-05, "loss": 1.9496, "step": 68790 }, { "epoch": 3.14, "learning_rate": 3.4369994050070945e-05, "loss": 1.7985, "step": 68800 }, { "epoch": 3.14, "learning_rate": 3.436770561581766e-05, "loss": 1.8956, "step": 68810 }, { "epoch": 3.14, "learning_rate": 3.436541718156437e-05, "loss": 1.8118, "step": 68820 }, { "epoch": 3.14, "learning_rate": 3.4363128747311094e-05, "loss": 1.9331, "step": 68830 }, { "epoch": 3.14, "learning_rate": 3.436084031305781e-05, "loss": 1.8316, "step": 68840 }, { "epoch": 3.14, "learning_rate": 3.435855187880452e-05, "loss": 1.8871, "step": 68850 }, { "epoch": 3.14, "learning_rate": 3.435626344455124e-05, "loss": 1.9739, "step": 68860 }, { "epoch": 3.14, "learning_rate": 3.435397501029796e-05, "loss": 1.8121, "step": 68870 }, { "epoch": 3.15, "learning_rate": 3.435168657604467e-05, "loss": 1.7279, "step": 68880 }, { "epoch": 3.15, "learning_rate": 3.434939814179139e-05, "loss": 1.7876, "step": 68890 }, { "epoch": 3.15, "learning_rate": 3.4347109707538106e-05, "loss": 1.8701, "step": 68900 }, { "epoch": 3.15, "learning_rate": 3.434482127328482e-05, "loss": 1.9568, "step": 68910 }, { "epoch": 3.15, "learning_rate": 3.434253283903154e-05, "loss": 1.7387, "step": 68920 }, { "epoch": 3.15, "learning_rate": 3.4340244404778256e-05, "loss": 1.8844, "step": 68930 }, { "epoch": 3.15, "learning_rate": 3.433795597052497e-05, "loss": 2.0001, "step": 68940 }, { "epoch": 3.15, "learning_rate": 3.433566753627169e-05, "loss": 1.9382, "step": 68950 }, { "epoch": 3.15, "learning_rate": 3.43333791020184e-05, "loss": 1.866, "step": 68960 }, { "epoch": 3.15, "learning_rate": 3.433109066776511e-05, "loss": 1.9422, "step": 68970 }, { "epoch": 3.15, "learning_rate": 3.432880223351183e-05, "loss": 1.8856, "step": 68980 }, { "epoch": 3.15, "learning_rate": 3.432651379925855e-05, "loss": 2.2385, "step": 68990 }, { "epoch": 3.15, "learning_rate": 3.432422536500526e-05, "loss": 1.8883, "step": 69000 }, { "epoch": 3.15, "learning_rate": 3.432193693075198e-05, "loss": 1.8681, "step": 69010 }, { "epoch": 3.15, "learning_rate": 3.4319648496498696e-05, "loss": 1.7926, "step": 69020 }, { "epoch": 3.15, "learning_rate": 3.431736006224541e-05, "loss": 1.9513, "step": 69030 }, { "epoch": 3.15, "learning_rate": 3.431507162799213e-05, "loss": 1.9693, "step": 69040 }, { "epoch": 3.15, "learning_rate": 3.4312783193738846e-05, "loss": 1.7909, "step": 69050 }, { "epoch": 3.15, "learning_rate": 3.431049475948556e-05, "loss": 2.108, "step": 69060 }, { "epoch": 3.15, "learning_rate": 3.430820632523228e-05, "loss": 1.8949, "step": 69070 }, { "epoch": 3.15, "learning_rate": 3.4305917890978995e-05, "loss": 1.8987, "step": 69080 }, { "epoch": 3.15, "learning_rate": 3.430362945672571e-05, "loss": 1.8506, "step": 69090 }, { "epoch": 3.16, "learning_rate": 3.430134102247243e-05, "loss": 1.8609, "step": 69100 }, { "epoch": 3.16, "learning_rate": 3.4299052588219144e-05, "loss": 2.1109, "step": 69110 }, { "epoch": 3.16, "learning_rate": 3.429676415396586e-05, "loss": 2.0233, "step": 69120 }, { "epoch": 3.16, "learning_rate": 3.429447571971258e-05, "loss": 1.7129, "step": 69130 }, { "epoch": 3.16, "learning_rate": 3.429218728545929e-05, "loss": 1.9044, "step": 69140 }, { "epoch": 3.16, "learning_rate": 3.4289898851206e-05, "loss": 1.8898, "step": 69150 }, { "epoch": 3.16, "learning_rate": 3.428761041695272e-05, "loss": 1.9987, "step": 69160 }, { "epoch": 3.16, "learning_rate": 3.4285321982699435e-05, "loss": 1.8552, "step": 69170 }, { "epoch": 3.16, "learning_rate": 3.428303354844615e-05, "loss": 1.7914, "step": 69180 }, { "epoch": 3.16, "learning_rate": 3.428074511419287e-05, "loss": 1.7667, "step": 69190 }, { "epoch": 3.16, "learning_rate": 3.4278456679939585e-05, "loss": 1.9453, "step": 69200 }, { "epoch": 3.16, "learning_rate": 3.42761682456863e-05, "loss": 2.0066, "step": 69210 }, { "epoch": 3.16, "learning_rate": 3.427387981143302e-05, "loss": 1.9125, "step": 69220 }, { "epoch": 3.16, "learning_rate": 3.4271591377179734e-05, "loss": 1.9248, "step": 69230 }, { "epoch": 3.16, "learning_rate": 3.426930294292645e-05, "loss": 1.9429, "step": 69240 }, { "epoch": 3.16, "learning_rate": 3.426701450867317e-05, "loss": 1.7952, "step": 69250 }, { "epoch": 3.16, "learning_rate": 3.426472607441988e-05, "loss": 1.932, "step": 69260 }, { "epoch": 3.16, "learning_rate": 3.42624376401666e-05, "loss": 1.8909, "step": 69270 }, { "epoch": 3.16, "learning_rate": 3.426014920591332e-05, "loss": 1.7566, "step": 69280 }, { "epoch": 3.16, "learning_rate": 3.425786077166003e-05, "loss": 1.7209, "step": 69290 }, { "epoch": 3.16, "learning_rate": 3.4255572337406746e-05, "loss": 2.0393, "step": 69300 }, { "epoch": 3.16, "learning_rate": 3.425328390315347e-05, "loss": 1.8186, "step": 69310 }, { "epoch": 3.17, "learning_rate": 3.425099546890018e-05, "loss": 2.1273, "step": 69320 }, { "epoch": 3.17, "learning_rate": 3.4248707034646895e-05, "loss": 1.8763, "step": 69330 }, { "epoch": 3.17, "learning_rate": 3.4246418600393616e-05, "loss": 1.7876, "step": 69340 }, { "epoch": 3.17, "learning_rate": 3.4244130166140324e-05, "loss": 1.7963, "step": 69350 }, { "epoch": 3.17, "learning_rate": 3.4241841731887045e-05, "loss": 1.9211, "step": 69360 }, { "epoch": 3.17, "learning_rate": 3.423955329763376e-05, "loss": 1.9316, "step": 69370 }, { "epoch": 3.17, "learning_rate": 3.423726486338047e-05, "loss": 1.8071, "step": 69380 }, { "epoch": 3.17, "learning_rate": 3.4234976429127194e-05, "loss": 2.0688, "step": 69390 }, { "epoch": 3.17, "learning_rate": 3.423268799487391e-05, "loss": 1.7903, "step": 69400 }, { "epoch": 3.17, "learning_rate": 3.423039956062062e-05, "loss": 1.8879, "step": 69410 }, { "epoch": 3.17, "learning_rate": 3.422811112636734e-05, "loss": 1.8719, "step": 69420 }, { "epoch": 3.17, "learning_rate": 3.422582269211406e-05, "loss": 1.9561, "step": 69430 }, { "epoch": 3.17, "learning_rate": 3.422353425786077e-05, "loss": 1.9188, "step": 69440 }, { "epoch": 3.17, "learning_rate": 3.422124582360749e-05, "loss": 1.8296, "step": 69450 }, { "epoch": 3.17, "learning_rate": 3.4218957389354206e-05, "loss": 1.786, "step": 69460 }, { "epoch": 3.17, "learning_rate": 3.421666895510092e-05, "loss": 1.8896, "step": 69470 }, { "epoch": 3.17, "learning_rate": 3.421438052084764e-05, "loss": 1.906, "step": 69480 }, { "epoch": 3.17, "learning_rate": 3.4212092086594355e-05, "loss": 1.8455, "step": 69490 }, { "epoch": 3.17, "learning_rate": 3.420980365234107e-05, "loss": 1.7809, "step": 69500 }, { "epoch": 3.17, "learning_rate": 3.420751521808779e-05, "loss": 1.9155, "step": 69510 }, { "epoch": 3.17, "learning_rate": 3.4205226783834505e-05, "loss": 1.9465, "step": 69520 }, { "epoch": 3.17, "learning_rate": 3.420293834958122e-05, "loss": 1.8307, "step": 69530 }, { "epoch": 3.18, "learning_rate": 3.420064991532794e-05, "loss": 1.8141, "step": 69540 }, { "epoch": 3.18, "learning_rate": 3.419836148107465e-05, "loss": 1.8619, "step": 69550 }, { "epoch": 3.18, "learning_rate": 3.419607304682136e-05, "loss": 1.8946, "step": 69560 }, { "epoch": 3.18, "learning_rate": 3.419378461256808e-05, "loss": 1.8534, "step": 69570 }, { "epoch": 3.18, "learning_rate": 3.4191496178314796e-05, "loss": 1.8673, "step": 69580 }, { "epoch": 3.18, "learning_rate": 3.418920774406151e-05, "loss": 1.9139, "step": 69590 }, { "epoch": 3.18, "learning_rate": 3.418691930980823e-05, "loss": 1.8175, "step": 69600 }, { "epoch": 3.18, "learning_rate": 3.4184630875554945e-05, "loss": 1.874, "step": 69610 }, { "epoch": 3.18, "learning_rate": 3.418234244130166e-05, "loss": 1.7419, "step": 69620 }, { "epoch": 3.18, "learning_rate": 3.418005400704838e-05, "loss": 1.7028, "step": 69630 }, { "epoch": 3.18, "learning_rate": 3.4177765572795095e-05, "loss": 1.8253, "step": 69640 }, { "epoch": 3.18, "learning_rate": 3.417547713854181e-05, "loss": 1.8739, "step": 69650 }, { "epoch": 3.18, "learning_rate": 3.417318870428853e-05, "loss": 1.7084, "step": 69660 }, { "epoch": 3.18, "learning_rate": 3.4170900270035244e-05, "loss": 2.0393, "step": 69670 }, { "epoch": 3.18, "learning_rate": 3.416861183578196e-05, "loss": 1.9564, "step": 69680 }, { "epoch": 3.18, "learning_rate": 3.416632340152868e-05, "loss": 1.8065, "step": 69690 }, { "epoch": 3.18, "learning_rate": 3.416403496727539e-05, "loss": 1.9248, "step": 69700 }, { "epoch": 3.18, "learning_rate": 3.416174653302211e-05, "loss": 1.8477, "step": 69710 }, { "epoch": 3.18, "learning_rate": 3.415945809876883e-05, "loss": 1.7809, "step": 69720 }, { "epoch": 3.18, "learning_rate": 3.415716966451554e-05, "loss": 1.9822, "step": 69730 }, { "epoch": 3.18, "learning_rate": 3.4154881230262256e-05, "loss": 1.7488, "step": 69740 }, { "epoch": 3.18, "learning_rate": 3.415259279600897e-05, "loss": 1.7354, "step": 69750 }, { "epoch": 3.19, "learning_rate": 3.4150304361755685e-05, "loss": 1.6147, "step": 69760 }, { "epoch": 3.19, "learning_rate": 3.4148015927502405e-05, "loss": 1.8795, "step": 69770 }, { "epoch": 3.19, "learning_rate": 3.414572749324912e-05, "loss": 1.6938, "step": 69780 }, { "epoch": 3.19, "learning_rate": 3.4143439058995834e-05, "loss": 1.9051, "step": 69790 }, { "epoch": 3.19, "learning_rate": 3.4141150624742555e-05, "loss": 1.9292, "step": 69800 }, { "epoch": 3.19, "learning_rate": 3.413886219048927e-05, "loss": 1.9258, "step": 69810 }, { "epoch": 3.19, "learning_rate": 3.413657375623598e-05, "loss": 2.013, "step": 69820 }, { "epoch": 3.19, "learning_rate": 3.4134285321982704e-05, "loss": 1.8623, "step": 69830 }, { "epoch": 3.19, "learning_rate": 3.413199688772942e-05, "loss": 1.7683, "step": 69840 }, { "epoch": 3.19, "learning_rate": 3.412970845347613e-05, "loss": 2.0349, "step": 69850 }, { "epoch": 3.19, "learning_rate": 3.412742001922285e-05, "loss": 1.9867, "step": 69860 }, { "epoch": 3.19, "learning_rate": 3.412513158496957e-05, "loss": 1.8859, "step": 69870 }, { "epoch": 3.19, "learning_rate": 3.412284315071628e-05, "loss": 1.9733, "step": 69880 }, { "epoch": 3.19, "learning_rate": 3.4120554716463e-05, "loss": 1.8264, "step": 69890 }, { "epoch": 3.19, "learning_rate": 3.4118266282209716e-05, "loss": 1.8543, "step": 69900 }, { "epoch": 3.19, "learning_rate": 3.411597784795643e-05, "loss": 1.8103, "step": 69910 }, { "epoch": 3.19, "learning_rate": 3.411368941370315e-05, "loss": 1.9334, "step": 69920 }, { "epoch": 3.19, "learning_rate": 3.4111400979449865e-05, "loss": 2.0558, "step": 69930 }, { "epoch": 3.19, "learning_rate": 3.410911254519657e-05, "loss": 1.7231, "step": 69940 }, { "epoch": 3.19, "learning_rate": 3.4106824110943294e-05, "loss": 1.9122, "step": 69950 }, { "epoch": 3.19, "learning_rate": 3.410453567669001e-05, "loss": 1.7703, "step": 69960 }, { "epoch": 3.2, "learning_rate": 3.410224724243672e-05, "loss": 1.9077, "step": 69970 }, { "epoch": 3.2, "learning_rate": 3.409995880818344e-05, "loss": 1.7911, "step": 69980 }, { "epoch": 3.2, "learning_rate": 3.409767037393016e-05, "loss": 1.7911, "step": 69990 }, { "epoch": 3.2, "learning_rate": 3.409538193967687e-05, "loss": 1.8441, "step": 70000 }, { "epoch": 3.2, "learning_rate": 3.409309350542359e-05, "loss": 1.8042, "step": 70010 }, { "epoch": 3.2, "learning_rate": 3.4090805071170306e-05, "loss": 1.6474, "step": 70020 }, { "epoch": 3.2, "learning_rate": 3.408851663691702e-05, "loss": 1.9821, "step": 70030 }, { "epoch": 3.2, "learning_rate": 3.408622820266374e-05, "loss": 1.8762, "step": 70040 }, { "epoch": 3.2, "learning_rate": 3.4083939768410455e-05, "loss": 1.7427, "step": 70050 }, { "epoch": 3.2, "learning_rate": 3.408165133415717e-05, "loss": 1.9065, "step": 70060 }, { "epoch": 3.2, "learning_rate": 3.407936289990389e-05, "loss": 2.0114, "step": 70070 }, { "epoch": 3.2, "learning_rate": 3.4077074465650605e-05, "loss": 1.9294, "step": 70080 }, { "epoch": 3.2, "learning_rate": 3.407478603139732e-05, "loss": 1.8679, "step": 70090 }, { "epoch": 3.2, "learning_rate": 3.407249759714404e-05, "loss": 1.9439, "step": 70100 }, { "epoch": 3.2, "learning_rate": 3.4070209162890754e-05, "loss": 1.9301, "step": 70110 }, { "epoch": 3.2, "learning_rate": 3.406792072863747e-05, "loss": 1.865, "step": 70120 }, { "epoch": 3.2, "learning_rate": 3.406563229438419e-05, "loss": 2.023, "step": 70130 }, { "epoch": 3.2, "learning_rate": 3.4063343860130896e-05, "loss": 1.7643, "step": 70140 }, { "epoch": 3.2, "learning_rate": 3.406105542587762e-05, "loss": 1.7915, "step": 70150 }, { "epoch": 3.2, "learning_rate": 3.405876699162433e-05, "loss": 1.7115, "step": 70160 }, { "epoch": 3.2, "learning_rate": 3.4056478557371045e-05, "loss": 1.9546, "step": 70170 }, { "epoch": 3.2, "learning_rate": 3.4054190123117766e-05, "loss": 1.7444, "step": 70180 }, { "epoch": 3.21, "learning_rate": 3.405190168886448e-05, "loss": 1.808, "step": 70190 }, { "epoch": 3.21, "learning_rate": 3.4049613254611194e-05, "loss": 1.8266, "step": 70200 }, { "epoch": 3.21, "learning_rate": 3.4047324820357915e-05, "loss": 1.9437, "step": 70210 }, { "epoch": 3.21, "learning_rate": 3.404503638610463e-05, "loss": 1.72, "step": 70220 }, { "epoch": 3.21, "learning_rate": 3.4042747951851344e-05, "loss": 1.9058, "step": 70230 }, { "epoch": 3.21, "learning_rate": 3.404045951759806e-05, "loss": 1.8649, "step": 70240 }, { "epoch": 3.21, "learning_rate": 3.403817108334478e-05, "loss": 1.7414, "step": 70250 }, { "epoch": 3.21, "learning_rate": 3.403588264909149e-05, "loss": 1.9542, "step": 70260 }, { "epoch": 3.21, "learning_rate": 3.403359421483821e-05, "loss": 1.8546, "step": 70270 }, { "epoch": 3.21, "learning_rate": 3.403130578058493e-05, "loss": 1.8028, "step": 70280 }, { "epoch": 3.21, "learning_rate": 3.402901734633164e-05, "loss": 1.8737, "step": 70290 }, { "epoch": 3.21, "learning_rate": 3.4026728912078356e-05, "loss": 1.8843, "step": 70300 }, { "epoch": 3.21, "learning_rate": 3.402444047782508e-05, "loss": 2.064, "step": 70310 }, { "epoch": 3.21, "learning_rate": 3.402215204357179e-05, "loss": 1.8111, "step": 70320 }, { "epoch": 3.21, "learning_rate": 3.4019863609318505e-05, "loss": 1.8608, "step": 70330 }, { "epoch": 3.21, "learning_rate": 3.401757517506522e-05, "loss": 1.9539, "step": 70340 }, { "epoch": 3.21, "learning_rate": 3.4015286740811934e-05, "loss": 1.9956, "step": 70350 }, { "epoch": 3.21, "learning_rate": 3.4012998306558655e-05, "loss": 2.0633, "step": 70360 }, { "epoch": 3.21, "learning_rate": 3.401070987230537e-05, "loss": 1.9266, "step": 70370 }, { "epoch": 3.21, "learning_rate": 3.400842143805208e-05, "loss": 1.6105, "step": 70380 }, { "epoch": 3.21, "learning_rate": 3.4006133003798804e-05, "loss": 1.8648, "step": 70390 }, { "epoch": 3.21, "learning_rate": 3.400384456954552e-05, "loss": 1.8118, "step": 70400 }, { "epoch": 3.22, "learning_rate": 3.400155613529223e-05, "loss": 1.8153, "step": 70410 }, { "epoch": 3.22, "learning_rate": 3.399926770103895e-05, "loss": 1.875, "step": 70420 }, { "epoch": 3.22, "learning_rate": 3.399697926678567e-05, "loss": 2.0082, "step": 70430 }, { "epoch": 3.22, "learning_rate": 3.399469083253238e-05, "loss": 1.8243, "step": 70440 }, { "epoch": 3.22, "learning_rate": 3.39924023982791e-05, "loss": 1.9352, "step": 70450 }, { "epoch": 3.22, "learning_rate": 3.3990113964025816e-05, "loss": 1.7716, "step": 70460 }, { "epoch": 3.22, "learning_rate": 3.398782552977253e-05, "loss": 1.8692, "step": 70470 }, { "epoch": 3.22, "learning_rate": 3.398553709551925e-05, "loss": 1.8994, "step": 70480 }, { "epoch": 3.22, "learning_rate": 3.3983248661265965e-05, "loss": 1.7454, "step": 70490 }, { "epoch": 3.22, "learning_rate": 3.398096022701268e-05, "loss": 1.8502, "step": 70500 }, { "epoch": 3.22, "learning_rate": 3.39786717927594e-05, "loss": 1.9388, "step": 70510 }, { "epoch": 3.22, "learning_rate": 3.3976383358506115e-05, "loss": 1.889, "step": 70520 }, { "epoch": 3.22, "learning_rate": 3.397409492425283e-05, "loss": 1.8998, "step": 70530 }, { "epoch": 3.22, "learning_rate": 3.397180648999954e-05, "loss": 1.9041, "step": 70540 }, { "epoch": 3.22, "learning_rate": 3.396951805574626e-05, "loss": 1.7422, "step": 70550 }, { "epoch": 3.22, "learning_rate": 3.396722962149297e-05, "loss": 1.7404, "step": 70560 }, { "epoch": 3.22, "learning_rate": 3.396494118723969e-05, "loss": 1.792, "step": 70570 }, { "epoch": 3.22, "learning_rate": 3.3962652752986406e-05, "loss": 1.7157, "step": 70580 }, { "epoch": 3.22, "learning_rate": 3.396036431873312e-05, "loss": 1.8449, "step": 70590 }, { "epoch": 3.22, "learning_rate": 3.395807588447984e-05, "loss": 1.8265, "step": 70600 }, { "epoch": 3.22, "learning_rate": 3.3955787450226555e-05, "loss": 1.919, "step": 70610 }, { "epoch": 3.22, "learning_rate": 3.395349901597327e-05, "loss": 1.734, "step": 70620 }, { "epoch": 3.23, "learning_rate": 3.395121058171999e-05, "loss": 1.7148, "step": 70630 }, { "epoch": 3.23, "learning_rate": 3.3948922147466704e-05, "loss": 1.9871, "step": 70640 }, { "epoch": 3.23, "learning_rate": 3.394663371321342e-05, "loss": 1.8682, "step": 70650 }, { "epoch": 3.23, "learning_rate": 3.394434527896014e-05, "loss": 1.888, "step": 70660 }, { "epoch": 3.23, "learning_rate": 3.3942056844706854e-05, "loss": 1.8374, "step": 70670 }, { "epoch": 3.23, "learning_rate": 3.393976841045357e-05, "loss": 1.9295, "step": 70680 }, { "epoch": 3.23, "learning_rate": 3.393747997620029e-05, "loss": 1.8697, "step": 70690 }, { "epoch": 3.23, "learning_rate": 3.3935191541947e-05, "loss": 1.89, "step": 70700 }, { "epoch": 3.23, "learning_rate": 3.393290310769372e-05, "loss": 1.7549, "step": 70710 }, { "epoch": 3.23, "learning_rate": 3.393061467344044e-05, "loss": 1.9759, "step": 70720 }, { "epoch": 3.23, "learning_rate": 3.3928326239187145e-05, "loss": 1.827, "step": 70730 }, { "epoch": 3.23, "learning_rate": 3.3926037804933866e-05, "loss": 1.909, "step": 70740 }, { "epoch": 3.23, "learning_rate": 3.392374937068058e-05, "loss": 2.0358, "step": 70750 }, { "epoch": 3.23, "learning_rate": 3.3921460936427294e-05, "loss": 1.9508, "step": 70760 }, { "epoch": 3.23, "learning_rate": 3.3919172502174015e-05, "loss": 1.8825, "step": 70770 }, { "epoch": 3.23, "learning_rate": 3.391688406792073e-05, "loss": 1.7166, "step": 70780 }, { "epoch": 3.23, "learning_rate": 3.3914595633667444e-05, "loss": 1.7349, "step": 70790 }, { "epoch": 3.23, "learning_rate": 3.3912307199414164e-05, "loss": 1.7796, "step": 70800 }, { "epoch": 3.23, "learning_rate": 3.391001876516088e-05, "loss": 1.8508, "step": 70810 }, { "epoch": 3.23, "learning_rate": 3.390773033090759e-05, "loss": 1.7385, "step": 70820 }, { "epoch": 3.23, "learning_rate": 3.3905441896654314e-05, "loss": 1.9477, "step": 70830 }, { "epoch": 3.23, "learning_rate": 3.390315346240103e-05, "loss": 2.0637, "step": 70840 }, { "epoch": 3.24, "learning_rate": 3.390086502814774e-05, "loss": 1.8751, "step": 70850 }, { "epoch": 3.24, "learning_rate": 3.389857659389446e-05, "loss": 1.8473, "step": 70860 }, { "epoch": 3.24, "learning_rate": 3.389628815964118e-05, "loss": 1.8016, "step": 70870 }, { "epoch": 3.24, "learning_rate": 3.389399972538789e-05, "loss": 1.8337, "step": 70880 }, { "epoch": 3.24, "learning_rate": 3.389171129113461e-05, "loss": 1.7495, "step": 70890 }, { "epoch": 3.24, "learning_rate": 3.3889422856881326e-05, "loss": 1.757, "step": 70900 }, { "epoch": 3.24, "learning_rate": 3.388713442262804e-05, "loss": 1.8834, "step": 70910 }, { "epoch": 3.24, "learning_rate": 3.388484598837476e-05, "loss": 1.8268, "step": 70920 }, { "epoch": 3.24, "learning_rate": 3.388255755412147e-05, "loss": 1.9902, "step": 70930 }, { "epoch": 3.24, "learning_rate": 3.388026911986818e-05, "loss": 1.7495, "step": 70940 }, { "epoch": 3.24, "learning_rate": 3.3877980685614904e-05, "loss": 1.7832, "step": 70950 }, { "epoch": 3.24, "learning_rate": 3.387569225136162e-05, "loss": 1.7401, "step": 70960 }, { "epoch": 3.24, "learning_rate": 3.387340381710833e-05, "loss": 1.9663, "step": 70970 }, { "epoch": 3.24, "learning_rate": 3.387111538285505e-05, "loss": 1.7854, "step": 70980 }, { "epoch": 3.24, "learning_rate": 3.386882694860177e-05, "loss": 1.9471, "step": 70990 }, { "epoch": 3.24, "learning_rate": 3.386653851434848e-05, "loss": 1.8236, "step": 71000 }, { "epoch": 3.24, "learning_rate": 3.38642500800952e-05, "loss": 1.965, "step": 71010 }, { "epoch": 3.24, "learning_rate": 3.3861961645841916e-05, "loss": 1.9191, "step": 71020 }, { "epoch": 3.24, "learning_rate": 3.385967321158863e-05, "loss": 1.6991, "step": 71030 }, { "epoch": 3.24, "learning_rate": 3.385738477733535e-05, "loss": 1.7678, "step": 71040 }, { "epoch": 3.24, "learning_rate": 3.3855096343082065e-05, "loss": 1.9726, "step": 71050 }, { "epoch": 3.24, "learning_rate": 3.385280790882878e-05, "loss": 2.0536, "step": 71060 }, { "epoch": 3.25, "learning_rate": 3.38505194745755e-05, "loss": 1.8095, "step": 71070 }, { "epoch": 3.25, "learning_rate": 3.3848231040322214e-05, "loss": 1.888, "step": 71080 }, { "epoch": 3.25, "learning_rate": 3.384594260606893e-05, "loss": 1.9327, "step": 71090 }, { "epoch": 3.25, "learning_rate": 3.384365417181565e-05, "loss": 1.8454, "step": 71100 }, { "epoch": 3.25, "learning_rate": 3.3841365737562364e-05, "loss": 1.7704, "step": 71110 }, { "epoch": 3.25, "learning_rate": 3.383907730330908e-05, "loss": 2.0372, "step": 71120 }, { "epoch": 3.25, "learning_rate": 3.383678886905579e-05, "loss": 1.8633, "step": 71130 }, { "epoch": 3.25, "learning_rate": 3.3834500434802506e-05, "loss": 1.7845, "step": 71140 }, { "epoch": 3.25, "learning_rate": 3.383221200054923e-05, "loss": 1.9704, "step": 71150 }, { "epoch": 3.25, "learning_rate": 3.382992356629594e-05, "loss": 2.0493, "step": 71160 }, { "epoch": 3.25, "learning_rate": 3.3827635132042655e-05, "loss": 1.9545, "step": 71170 }, { "epoch": 3.25, "learning_rate": 3.3825346697789376e-05, "loss": 1.8082, "step": 71180 }, { "epoch": 3.25, "learning_rate": 3.382305826353609e-05, "loss": 1.8314, "step": 71190 }, { "epoch": 3.25, "learning_rate": 3.3820769829282804e-05, "loss": 1.8286, "step": 71200 }, { "epoch": 3.25, "learning_rate": 3.3818481395029525e-05, "loss": 1.6972, "step": 71210 }, { "epoch": 3.25, "learning_rate": 3.381619296077624e-05, "loss": 2.1128, "step": 71220 }, { "epoch": 3.25, "learning_rate": 3.3813904526522954e-05, "loss": 1.6995, "step": 71230 }, { "epoch": 3.25, "learning_rate": 3.3811616092269674e-05, "loss": 1.7086, "step": 71240 }, { "epoch": 3.25, "learning_rate": 3.380932765801639e-05, "loss": 1.8605, "step": 71250 }, { "epoch": 3.25, "learning_rate": 3.38070392237631e-05, "loss": 1.9066, "step": 71260 }, { "epoch": 3.25, "learning_rate": 3.3804750789509824e-05, "loss": 1.9044, "step": 71270 }, { "epoch": 3.25, "learning_rate": 3.380246235525654e-05, "loss": 1.8858, "step": 71280 }, { "epoch": 3.26, "learning_rate": 3.380017392100325e-05, "loss": 1.6293, "step": 71290 }, { "epoch": 3.26, "learning_rate": 3.379788548674997e-05, "loss": 1.8371, "step": 71300 }, { "epoch": 3.26, "learning_rate": 3.379559705249669e-05, "loss": 1.8686, "step": 71310 }, { "epoch": 3.26, "learning_rate": 3.37933086182434e-05, "loss": 1.7897, "step": 71320 }, { "epoch": 3.26, "learning_rate": 3.3791020183990115e-05, "loss": 1.9885, "step": 71330 }, { "epoch": 3.26, "learning_rate": 3.378873174973683e-05, "loss": 2.0261, "step": 71340 }, { "epoch": 3.26, "learning_rate": 3.3786443315483543e-05, "loss": 1.9735, "step": 71350 }, { "epoch": 3.26, "learning_rate": 3.3784154881230264e-05, "loss": 1.8958, "step": 71360 }, { "epoch": 3.26, "learning_rate": 3.378186644697698e-05, "loss": 1.8455, "step": 71370 }, { "epoch": 3.26, "learning_rate": 3.377957801272369e-05, "loss": 1.9019, "step": 71380 }, { "epoch": 3.26, "learning_rate": 3.3777289578470414e-05, "loss": 1.8084, "step": 71390 }, { "epoch": 3.26, "learning_rate": 3.377500114421713e-05, "loss": 1.7422, "step": 71400 }, { "epoch": 3.26, "learning_rate": 3.377271270996384e-05, "loss": 1.9514, "step": 71410 }, { "epoch": 3.26, "learning_rate": 3.377042427571056e-05, "loss": 1.8672, "step": 71420 }, { "epoch": 3.26, "learning_rate": 3.376813584145728e-05, "loss": 1.8779, "step": 71430 }, { "epoch": 3.26, "learning_rate": 3.376584740720399e-05, "loss": 1.856, "step": 71440 }, { "epoch": 3.26, "learning_rate": 3.376355897295071e-05, "loss": 1.9079, "step": 71450 }, { "epoch": 3.26, "learning_rate": 3.3761270538697426e-05, "loss": 1.8418, "step": 71460 }, { "epoch": 3.26, "learning_rate": 3.375898210444414e-05, "loss": 1.801, "step": 71470 }, { "epoch": 3.26, "learning_rate": 3.375669367019086e-05, "loss": 1.8715, "step": 71480 }, { "epoch": 3.26, "learning_rate": 3.3754405235937575e-05, "loss": 1.848, "step": 71490 }, { "epoch": 3.26, "learning_rate": 3.375211680168429e-05, "loss": 1.7985, "step": 71500 }, { "epoch": 3.27, "learning_rate": 3.374982836743101e-05, "loss": 1.6271, "step": 71510 }, { "epoch": 3.27, "learning_rate": 3.374753993317772e-05, "loss": 1.7732, "step": 71520 }, { "epoch": 3.27, "learning_rate": 3.374525149892443e-05, "loss": 1.795, "step": 71530 }, { "epoch": 3.27, "learning_rate": 3.374296306467115e-05, "loss": 1.9394, "step": 71540 }, { "epoch": 3.27, "learning_rate": 3.374067463041787e-05, "loss": 1.8908, "step": 71550 }, { "epoch": 3.27, "learning_rate": 3.373838619616458e-05, "loss": 1.8131, "step": 71560 }, { "epoch": 3.27, "learning_rate": 3.37360977619113e-05, "loss": 1.8756, "step": 71570 }, { "epoch": 3.27, "learning_rate": 3.3733809327658016e-05, "loss": 1.8894, "step": 71580 }, { "epoch": 3.27, "learning_rate": 3.373152089340473e-05, "loss": 1.8781, "step": 71590 }, { "epoch": 3.27, "learning_rate": 3.372923245915145e-05, "loss": 1.7495, "step": 71600 }, { "epoch": 3.27, "learning_rate": 3.3726944024898165e-05, "loss": 1.939, "step": 71610 }, { "epoch": 3.27, "learning_rate": 3.372465559064488e-05, "loss": 1.771, "step": 71620 }, { "epoch": 3.27, "learning_rate": 3.37223671563916e-05, "loss": 1.8835, "step": 71630 }, { "epoch": 3.27, "learning_rate": 3.3720078722138314e-05, "loss": 1.8647, "step": 71640 }, { "epoch": 3.27, "learning_rate": 3.371779028788503e-05, "loss": 1.9026, "step": 71650 }, { "epoch": 3.27, "learning_rate": 3.371550185363175e-05, "loss": 1.7075, "step": 71660 }, { "epoch": 3.27, "learning_rate": 3.3713213419378464e-05, "loss": 1.9236, "step": 71670 }, { "epoch": 3.27, "learning_rate": 3.371092498512518e-05, "loss": 2.0662, "step": 71680 }, { "epoch": 3.27, "learning_rate": 3.37086365508719e-05, "loss": 1.7241, "step": 71690 }, { "epoch": 3.27, "learning_rate": 3.370634811661861e-05, "loss": 1.8217, "step": 71700 }, { "epoch": 3.27, "learning_rate": 3.370405968236533e-05, "loss": 1.8917, "step": 71710 }, { "epoch": 3.27, "learning_rate": 3.370177124811204e-05, "loss": 1.7436, "step": 71720 }, { "epoch": 3.28, "learning_rate": 3.3699482813858755e-05, "loss": 1.6863, "step": 71730 }, { "epoch": 3.28, "learning_rate": 3.3697194379605476e-05, "loss": 1.6924, "step": 71740 }, { "epoch": 3.28, "learning_rate": 3.369490594535219e-05, "loss": 1.8922, "step": 71750 }, { "epoch": 3.28, "learning_rate": 3.3692617511098904e-05, "loss": 1.8053, "step": 71760 }, { "epoch": 3.28, "learning_rate": 3.3690329076845625e-05, "loss": 1.6764, "step": 71770 }, { "epoch": 3.28, "learning_rate": 3.368804064259234e-05, "loss": 1.7653, "step": 71780 }, { "epoch": 3.28, "learning_rate": 3.3685752208339053e-05, "loss": 2.0689, "step": 71790 }, { "epoch": 3.28, "learning_rate": 3.3683463774085774e-05, "loss": 1.7315, "step": 71800 }, { "epoch": 3.28, "learning_rate": 3.368117533983249e-05, "loss": 1.9051, "step": 71810 }, { "epoch": 3.28, "learning_rate": 3.36788869055792e-05, "loss": 1.6725, "step": 71820 }, { "epoch": 3.28, "learning_rate": 3.3676598471325924e-05, "loss": 1.7108, "step": 71830 }, { "epoch": 3.28, "learning_rate": 3.367431003707264e-05, "loss": 2.0016, "step": 71840 }, { "epoch": 3.28, "learning_rate": 3.367202160281935e-05, "loss": 1.9227, "step": 71850 }, { "epoch": 3.28, "learning_rate": 3.366973316856607e-05, "loss": 1.7558, "step": 71860 }, { "epoch": 3.28, "learning_rate": 3.366744473431279e-05, "loss": 1.709, "step": 71870 }, { "epoch": 3.28, "learning_rate": 3.36651563000595e-05, "loss": 1.6523, "step": 71880 }, { "epoch": 3.28, "learning_rate": 3.366286786580622e-05, "loss": 1.5478, "step": 71890 }, { "epoch": 3.28, "learning_rate": 3.3660579431552936e-05, "loss": 1.7681, "step": 71900 }, { "epoch": 3.28, "learning_rate": 3.365829099729965e-05, "loss": 1.727, "step": 71910 }, { "epoch": 3.28, "learning_rate": 3.3656002563046364e-05, "loss": 1.7737, "step": 71920 }, { "epoch": 3.28, "learning_rate": 3.365371412879308e-05, "loss": 1.6482, "step": 71930 }, { "epoch": 3.28, "learning_rate": 3.365142569453979e-05, "loss": 1.918, "step": 71940 }, { "epoch": 3.29, "learning_rate": 3.3649137260286513e-05, "loss": 1.9841, "step": 71950 }, { "epoch": 3.29, "learning_rate": 3.364684882603323e-05, "loss": 1.6951, "step": 71960 }, { "epoch": 3.29, "learning_rate": 3.364456039177994e-05, "loss": 1.7565, "step": 71970 }, { "epoch": 3.29, "learning_rate": 3.364227195752666e-05, "loss": 1.7301, "step": 71980 }, { "epoch": 3.29, "learning_rate": 3.363998352327338e-05, "loss": 1.9335, "step": 71990 }, { "epoch": 3.29, "learning_rate": 3.363769508902009e-05, "loss": 1.6163, "step": 72000 }, { "epoch": 3.29, "learning_rate": 3.363540665476681e-05, "loss": 1.8054, "step": 72010 }, { "epoch": 3.29, "learning_rate": 3.3633118220513526e-05, "loss": 1.7993, "step": 72020 }, { "epoch": 3.29, "learning_rate": 3.363082978626024e-05, "loss": 1.7257, "step": 72030 }, { "epoch": 3.29, "learning_rate": 3.362854135200696e-05, "loss": 1.8983, "step": 72040 }, { "epoch": 3.29, "learning_rate": 3.3626252917753675e-05, "loss": 1.8885, "step": 72050 }, { "epoch": 3.29, "learning_rate": 3.362396448350039e-05, "loss": 1.8426, "step": 72060 }, { "epoch": 3.29, "learning_rate": 3.362167604924711e-05, "loss": 1.7727, "step": 72070 }, { "epoch": 3.29, "learning_rate": 3.3619387614993824e-05, "loss": 1.8959, "step": 72080 }, { "epoch": 3.29, "learning_rate": 3.361709918074054e-05, "loss": 1.7633, "step": 72090 }, { "epoch": 3.29, "learning_rate": 3.361481074648726e-05, "loss": 1.8749, "step": 72100 }, { "epoch": 3.29, "learning_rate": 3.3612522312233973e-05, "loss": 1.7058, "step": 72110 }, { "epoch": 3.29, "learning_rate": 3.361023387798069e-05, "loss": 1.6834, "step": 72120 }, { "epoch": 3.29, "learning_rate": 3.36079454437274e-05, "loss": 1.8592, "step": 72130 }, { "epoch": 3.29, "learning_rate": 3.3605657009474116e-05, "loss": 1.885, "step": 72140 }, { "epoch": 3.29, "learning_rate": 3.360336857522084e-05, "loss": 1.7979, "step": 72150 }, { "epoch": 3.3, "learning_rate": 3.360108014096755e-05, "loss": 1.8312, "step": 72160 }, { "epoch": 3.3, "learning_rate": 3.3598791706714265e-05, "loss": 1.9579, "step": 72170 }, { "epoch": 3.3, "learning_rate": 3.3596503272460986e-05, "loss": 1.8537, "step": 72180 }, { "epoch": 3.3, "learning_rate": 3.35942148382077e-05, "loss": 1.672, "step": 72190 }, { "epoch": 3.3, "learning_rate": 3.3591926403954414e-05, "loss": 1.8843, "step": 72200 }, { "epoch": 3.3, "learning_rate": 3.3589637969701135e-05, "loss": 2.0139, "step": 72210 }, { "epoch": 3.3, "learning_rate": 3.358734953544785e-05, "loss": 1.7836, "step": 72220 }, { "epoch": 3.3, "learning_rate": 3.3585061101194563e-05, "loss": 2.09, "step": 72230 }, { "epoch": 3.3, "learning_rate": 3.3582772666941284e-05, "loss": 1.7532, "step": 72240 }, { "epoch": 3.3, "learning_rate": 3.3580484232688e-05, "loss": 1.7765, "step": 72250 }, { "epoch": 3.3, "learning_rate": 3.357819579843471e-05, "loss": 1.8023, "step": 72260 }, { "epoch": 3.3, "learning_rate": 3.3575907364181433e-05, "loss": 1.9269, "step": 72270 }, { "epoch": 3.3, "learning_rate": 3.357361892992815e-05, "loss": 1.9563, "step": 72280 }, { "epoch": 3.3, "learning_rate": 3.357133049567486e-05, "loss": 1.8074, "step": 72290 }, { "epoch": 3.3, "learning_rate": 3.356904206142158e-05, "loss": 1.8852, "step": 72300 }, { "epoch": 3.3, "learning_rate": 3.356675362716829e-05, "loss": 1.7794, "step": 72310 }, { "epoch": 3.3, "learning_rate": 3.3564465192915004e-05, "loss": 1.5949, "step": 72320 }, { "epoch": 3.3, "learning_rate": 3.3562176758661725e-05, "loss": 1.6001, "step": 72330 }, { "epoch": 3.3, "learning_rate": 3.355988832440844e-05, "loss": 1.8336, "step": 72340 }, { "epoch": 3.3, "learning_rate": 3.355759989015515e-05, "loss": 1.7395, "step": 72350 }, { "epoch": 3.3, "learning_rate": 3.3555311455901874e-05, "loss": 1.7977, "step": 72360 }, { "epoch": 3.3, "learning_rate": 3.355302302164859e-05, "loss": 1.8143, "step": 72370 }, { "epoch": 3.31, "learning_rate": 3.35507345873953e-05, "loss": 1.8063, "step": 72380 }, { "epoch": 3.31, "learning_rate": 3.3548446153142023e-05, "loss": 1.9174, "step": 72390 }, { "epoch": 3.31, "learning_rate": 3.354615771888874e-05, "loss": 1.7025, "step": 72400 }, { "epoch": 3.31, "learning_rate": 3.354386928463545e-05, "loss": 1.9079, "step": 72410 }, { "epoch": 3.31, "learning_rate": 3.354158085038217e-05, "loss": 1.733, "step": 72420 }, { "epoch": 3.31, "learning_rate": 3.353929241612889e-05, "loss": 1.792, "step": 72430 }, { "epoch": 3.31, "learning_rate": 3.35370039818756e-05, "loss": 1.8456, "step": 72440 }, { "epoch": 3.31, "learning_rate": 3.353471554762232e-05, "loss": 1.8311, "step": 72450 }, { "epoch": 3.31, "learning_rate": 3.3532427113369036e-05, "loss": 1.9866, "step": 72460 }, { "epoch": 3.31, "learning_rate": 3.353013867911575e-05, "loss": 1.8745, "step": 72470 }, { "epoch": 3.31, "learning_rate": 3.352785024486247e-05, "loss": 1.8425, "step": 72480 }, { "epoch": 3.31, "learning_rate": 3.3525561810609185e-05, "loss": 1.6923, "step": 72490 }, { "epoch": 3.31, "learning_rate": 3.35232733763559e-05, "loss": 1.7111, "step": 72500 }, { "epoch": 3.31, "learning_rate": 3.352098494210261e-05, "loss": 1.6661, "step": 72510 }, { "epoch": 3.31, "learning_rate": 3.351869650784933e-05, "loss": 1.8696, "step": 72520 }, { "epoch": 3.31, "learning_rate": 3.351640807359605e-05, "loss": 1.9338, "step": 72530 }, { "epoch": 3.31, "learning_rate": 3.351411963934276e-05, "loss": 1.8377, "step": 72540 }, { "epoch": 3.31, "learning_rate": 3.351183120508948e-05, "loss": 1.6937, "step": 72550 }, { "epoch": 3.31, "learning_rate": 3.35095427708362e-05, "loss": 1.8434, "step": 72560 }, { "epoch": 3.31, "learning_rate": 3.350725433658291e-05, "loss": 1.7158, "step": 72570 }, { "epoch": 3.31, "learning_rate": 3.3504965902329626e-05, "loss": 1.8947, "step": 72580 }, { "epoch": 3.31, "learning_rate": 3.350267746807634e-05, "loss": 1.7905, "step": 72590 }, { "epoch": 3.32, "learning_rate": 3.350038903382306e-05, "loss": 1.9005, "step": 72600 }, { "epoch": 3.32, "learning_rate": 3.3498100599569775e-05, "loss": 1.8687, "step": 72610 }, { "epoch": 3.32, "learning_rate": 3.349581216531649e-05, "loss": 1.7501, "step": 72620 }, { "epoch": 3.32, "learning_rate": 3.349352373106321e-05, "loss": 1.8634, "step": 72630 }, { "epoch": 3.32, "learning_rate": 3.3491235296809924e-05, "loss": 1.8562, "step": 72640 }, { "epoch": 3.32, "learning_rate": 3.348894686255664e-05, "loss": 1.7209, "step": 72650 }, { "epoch": 3.32, "learning_rate": 3.348665842830336e-05, "loss": 1.7648, "step": 72660 }, { "epoch": 3.32, "learning_rate": 3.348436999405007e-05, "loss": 1.6204, "step": 72670 }, { "epoch": 3.32, "learning_rate": 3.348208155979679e-05, "loss": 1.6637, "step": 72680 }, { "epoch": 3.32, "learning_rate": 3.347979312554351e-05, "loss": 1.7816, "step": 72690 }, { "epoch": 3.32, "learning_rate": 3.347750469129022e-05, "loss": 1.7225, "step": 72700 }, { "epoch": 3.32, "learning_rate": 3.347521625703694e-05, "loss": 1.7467, "step": 72710 }, { "epoch": 3.32, "learning_rate": 3.347292782278365e-05, "loss": 1.7927, "step": 72720 }, { "epoch": 3.32, "learning_rate": 3.3470639388530365e-05, "loss": 1.8587, "step": 72730 }, { "epoch": 3.32, "learning_rate": 3.3468350954277086e-05, "loss": 1.6598, "step": 72740 }, { "epoch": 3.32, "learning_rate": 3.34660625200238e-05, "loss": 1.8631, "step": 72750 }, { "epoch": 3.32, "learning_rate": 3.3463774085770514e-05, "loss": 1.8386, "step": 72760 }, { "epoch": 3.32, "learning_rate": 3.3461485651517235e-05, "loss": 1.8813, "step": 72770 }, { "epoch": 3.32, "learning_rate": 3.345919721726395e-05, "loss": 1.8267, "step": 72780 }, { "epoch": 3.32, "learning_rate": 3.345690878301066e-05, "loss": 1.7619, "step": 72790 }, { "epoch": 3.32, "learning_rate": 3.3454620348757384e-05, "loss": 1.8597, "step": 72800 }, { "epoch": 3.32, "learning_rate": 3.34523319145041e-05, "loss": 1.822, "step": 72810 }, { "epoch": 3.33, "learning_rate": 3.345004348025081e-05, "loss": 1.9154, "step": 72820 }, { "epoch": 3.33, "learning_rate": 3.344775504599753e-05, "loss": 1.6658, "step": 72830 }, { "epoch": 3.33, "learning_rate": 3.344546661174425e-05, "loss": 1.8988, "step": 72840 }, { "epoch": 3.33, "learning_rate": 3.344317817749096e-05, "loss": 1.7971, "step": 72850 }, { "epoch": 3.33, "learning_rate": 3.344088974323768e-05, "loss": 1.8287, "step": 72860 }, { "epoch": 3.33, "learning_rate": 3.34386013089844e-05, "loss": 1.7771, "step": 72870 }, { "epoch": 3.33, "learning_rate": 3.343631287473111e-05, "loss": 1.8522, "step": 72880 }, { "epoch": 3.33, "learning_rate": 3.343402444047783e-05, "loss": 1.7562, "step": 72890 }, { "epoch": 3.33, "learning_rate": 3.3431736006224546e-05, "loss": 1.6768, "step": 72900 }, { "epoch": 3.33, "learning_rate": 3.342944757197125e-05, "loss": 1.9143, "step": 72910 }, { "epoch": 3.33, "learning_rate": 3.3427159137717974e-05, "loss": 1.7089, "step": 72920 }, { "epoch": 3.33, "learning_rate": 3.342487070346469e-05, "loss": 1.7586, "step": 72930 }, { "epoch": 3.33, "learning_rate": 3.34225822692114e-05, "loss": 1.8987, "step": 72940 }, { "epoch": 3.33, "learning_rate": 3.342029383495812e-05, "loss": 1.7582, "step": 72950 }, { "epoch": 3.33, "learning_rate": 3.341800540070484e-05, "loss": 1.7725, "step": 72960 }, { "epoch": 3.33, "learning_rate": 3.341571696645155e-05, "loss": 1.7766, "step": 72970 }, { "epoch": 3.33, "learning_rate": 3.341342853219827e-05, "loss": 1.7568, "step": 72980 }, { "epoch": 3.33, "learning_rate": 3.341114009794499e-05, "loss": 1.7879, "step": 72990 }, { "epoch": 3.33, "learning_rate": 3.34088516636917e-05, "loss": 1.7551, "step": 73000 }, { "epoch": 3.33, "learning_rate": 3.340656322943842e-05, "loss": 1.8524, "step": 73010 }, { "epoch": 3.33, "learning_rate": 3.3404274795185136e-05, "loss": 1.8579, "step": 73020 }, { "epoch": 3.33, "learning_rate": 3.340198636093185e-05, "loss": 1.6459, "step": 73030 }, { "epoch": 3.34, "learning_rate": 3.339969792667857e-05, "loss": 1.7769, "step": 73040 }, { "epoch": 3.34, "learning_rate": 3.3397409492425285e-05, "loss": 1.715, "step": 73050 }, { "epoch": 3.34, "learning_rate": 3.3395121058172e-05, "loss": 1.9198, "step": 73060 }, { "epoch": 3.34, "learning_rate": 3.339283262391872e-05, "loss": 1.8866, "step": 73070 }, { "epoch": 3.34, "learning_rate": 3.3390544189665434e-05, "loss": 1.8641, "step": 73080 }, { "epoch": 3.34, "learning_rate": 3.338825575541215e-05, "loss": 1.8696, "step": 73090 }, { "epoch": 3.34, "learning_rate": 3.338596732115886e-05, "loss": 1.8783, "step": 73100 }, { "epoch": 3.34, "learning_rate": 3.3383678886905577e-05, "loss": 1.8695, "step": 73110 }, { "epoch": 3.34, "learning_rate": 3.33813904526523e-05, "loss": 1.7566, "step": 73120 }, { "epoch": 3.34, "learning_rate": 3.337910201839901e-05, "loss": 1.7221, "step": 73130 }, { "epoch": 3.34, "learning_rate": 3.3376813584145726e-05, "loss": 1.7738, "step": 73140 }, { "epoch": 3.34, "learning_rate": 3.337452514989245e-05, "loss": 1.7282, "step": 73150 }, { "epoch": 3.34, "learning_rate": 3.337223671563916e-05, "loss": 1.8969, "step": 73160 }, { "epoch": 3.34, "learning_rate": 3.3369948281385875e-05, "loss": 1.7956, "step": 73170 }, { "epoch": 3.34, "learning_rate": 3.3367659847132596e-05, "loss": 1.7557, "step": 73180 }, { "epoch": 3.34, "learning_rate": 3.336537141287931e-05, "loss": 1.8935, "step": 73190 }, { "epoch": 3.34, "learning_rate": 3.3363082978626024e-05, "loss": 1.8848, "step": 73200 }, { "epoch": 3.34, "learning_rate": 3.3360794544372745e-05, "loss": 1.7548, "step": 73210 }, { "epoch": 3.34, "learning_rate": 3.335850611011946e-05, "loss": 1.8492, "step": 73220 }, { "epoch": 3.34, "learning_rate": 3.335621767586617e-05, "loss": 1.8452, "step": 73230 }, { "epoch": 3.34, "learning_rate": 3.3353929241612894e-05, "loss": 1.8054, "step": 73240 }, { "epoch": 3.34, "learning_rate": 3.335164080735961e-05, "loss": 1.8607, "step": 73250 }, { "epoch": 3.35, "learning_rate": 3.334935237310632e-05, "loss": 1.7789, "step": 73260 }, { "epoch": 3.35, "learning_rate": 3.334706393885304e-05, "loss": 1.8026, "step": 73270 }, { "epoch": 3.35, "learning_rate": 3.334477550459976e-05, "loss": 1.7026, "step": 73280 }, { "epoch": 3.35, "learning_rate": 3.334248707034647e-05, "loss": 1.8408, "step": 73290 }, { "epoch": 3.35, "learning_rate": 3.3340198636093186e-05, "loss": 1.6272, "step": 73300 }, { "epoch": 3.35, "learning_rate": 3.33379102018399e-05, "loss": 1.8277, "step": 73310 }, { "epoch": 3.35, "learning_rate": 3.3335621767586614e-05, "loss": 1.7987, "step": 73320 }, { "epoch": 3.35, "learning_rate": 3.3333333333333335e-05, "loss": 1.8877, "step": 73330 }, { "epoch": 3.35, "learning_rate": 3.333104489908005e-05, "loss": 1.8281, "step": 73340 }, { "epoch": 3.35, "learning_rate": 3.332875646482676e-05, "loss": 2.0625, "step": 73350 }, { "epoch": 3.35, "learning_rate": 3.3326468030573484e-05, "loss": 1.7273, "step": 73360 }, { "epoch": 3.35, "learning_rate": 3.33241795963202e-05, "loss": 1.8177, "step": 73370 }, { "epoch": 3.35, "learning_rate": 3.332189116206691e-05, "loss": 1.7155, "step": 73380 }, { "epoch": 3.35, "learning_rate": 3.331960272781363e-05, "loss": 1.759, "step": 73390 }, { "epoch": 3.35, "learning_rate": 3.331731429356035e-05, "loss": 1.8176, "step": 73400 }, { "epoch": 3.35, "learning_rate": 3.331502585930706e-05, "loss": 1.8683, "step": 73410 }, { "epoch": 3.35, "learning_rate": 3.331273742505378e-05, "loss": 1.7765, "step": 73420 }, { "epoch": 3.35, "learning_rate": 3.3310448990800497e-05, "loss": 1.9418, "step": 73430 }, { "epoch": 3.35, "learning_rate": 3.330816055654721e-05, "loss": 1.7172, "step": 73440 }, { "epoch": 3.35, "learning_rate": 3.330587212229393e-05, "loss": 1.7666, "step": 73450 }, { "epoch": 3.35, "learning_rate": 3.3303583688040646e-05, "loss": 1.8922, "step": 73460 }, { "epoch": 3.35, "learning_rate": 3.330129525378736e-05, "loss": 1.9328, "step": 73470 }, { "epoch": 3.36, "learning_rate": 3.329900681953408e-05, "loss": 1.7588, "step": 73480 }, { "epoch": 3.36, "learning_rate": 3.3296718385280795e-05, "loss": 1.7592, "step": 73490 }, { "epoch": 3.36, "learning_rate": 3.329442995102751e-05, "loss": 1.8014, "step": 73500 }, { "epoch": 3.36, "learning_rate": 3.329214151677422e-05, "loss": 1.9071, "step": 73510 }, { "epoch": 3.36, "learning_rate": 3.328985308252094e-05, "loss": 1.8481, "step": 73520 }, { "epoch": 3.36, "learning_rate": 3.328756464826766e-05, "loss": 1.8849, "step": 73530 }, { "epoch": 3.36, "learning_rate": 3.328527621401437e-05, "loss": 1.6475, "step": 73540 }, { "epoch": 3.36, "learning_rate": 3.3282987779761087e-05, "loss": 1.8419, "step": 73550 }, { "epoch": 3.36, "learning_rate": 3.328069934550781e-05, "loss": 1.6943, "step": 73560 }, { "epoch": 3.36, "learning_rate": 3.327841091125452e-05, "loss": 1.6884, "step": 73570 }, { "epoch": 3.36, "learning_rate": 3.3276122477001236e-05, "loss": 1.7563, "step": 73580 }, { "epoch": 3.36, "learning_rate": 3.327383404274796e-05, "loss": 1.8463, "step": 73590 }, { "epoch": 3.36, "learning_rate": 3.327154560849467e-05, "loss": 1.8774, "step": 73600 }, { "epoch": 3.36, "learning_rate": 3.3269257174241385e-05, "loss": 1.6004, "step": 73610 }, { "epoch": 3.36, "learning_rate": 3.3266968739988106e-05, "loss": 1.9819, "step": 73620 }, { "epoch": 3.36, "learning_rate": 3.326468030573482e-05, "loss": 1.9582, "step": 73630 }, { "epoch": 3.36, "learning_rate": 3.3262391871481534e-05, "loss": 1.6502, "step": 73640 }, { "epoch": 3.36, "learning_rate": 3.3260103437228255e-05, "loss": 1.6714, "step": 73650 }, { "epoch": 3.36, "learning_rate": 3.325781500297497e-05, "loss": 1.8161, "step": 73660 }, { "epoch": 3.36, "learning_rate": 3.325552656872168e-05, "loss": 1.8185, "step": 73670 }, { "epoch": 3.36, "learning_rate": 3.32532381344684e-05, "loss": 1.8638, "step": 73680 }, { "epoch": 3.36, "learning_rate": 3.325094970021512e-05, "loss": 1.8703, "step": 73690 }, { "epoch": 3.37, "learning_rate": 3.3248661265961826e-05, "loss": 1.9487, "step": 73700 }, { "epoch": 3.37, "learning_rate": 3.3246372831708547e-05, "loss": 1.8714, "step": 73710 }, { "epoch": 3.37, "learning_rate": 3.324408439745526e-05, "loss": 1.6831, "step": 73720 }, { "epoch": 3.37, "learning_rate": 3.3241795963201975e-05, "loss": 1.7363, "step": 73730 }, { "epoch": 3.37, "learning_rate": 3.3239507528948696e-05, "loss": 1.8713, "step": 73740 }, { "epoch": 3.37, "learning_rate": 3.323721909469541e-05, "loss": 1.7476, "step": 73750 }, { "epoch": 3.37, "learning_rate": 3.3234930660442124e-05, "loss": 1.8529, "step": 73760 }, { "epoch": 3.37, "learning_rate": 3.3232642226188845e-05, "loss": 1.8871, "step": 73770 }, { "epoch": 3.37, "learning_rate": 3.323035379193556e-05, "loss": 1.7512, "step": 73780 }, { "epoch": 3.37, "learning_rate": 3.322806535768227e-05, "loss": 1.7359, "step": 73790 }, { "epoch": 3.37, "learning_rate": 3.3225776923428994e-05, "loss": 1.8482, "step": 73800 }, { "epoch": 3.37, "learning_rate": 3.322348848917571e-05, "loss": 1.8127, "step": 73810 }, { "epoch": 3.37, "learning_rate": 3.322120005492242e-05, "loss": 1.8053, "step": 73820 }, { "epoch": 3.37, "learning_rate": 3.321891162066914e-05, "loss": 1.7309, "step": 73830 }, { "epoch": 3.37, "learning_rate": 3.321662318641586e-05, "loss": 1.6914, "step": 73840 }, { "epoch": 3.37, "learning_rate": 3.321433475216257e-05, "loss": 1.7684, "step": 73850 }, { "epoch": 3.37, "learning_rate": 3.321204631790929e-05, "loss": 1.8188, "step": 73860 }, { "epoch": 3.37, "learning_rate": 3.3209757883656007e-05, "loss": 1.7737, "step": 73870 }, { "epoch": 3.37, "learning_rate": 3.320746944940272e-05, "loss": 1.6573, "step": 73880 }, { "epoch": 3.37, "learning_rate": 3.3205181015149435e-05, "loss": 1.7402, "step": 73890 }, { "epoch": 3.37, "learning_rate": 3.320289258089615e-05, "loss": 1.7622, "step": 73900 }, { "epoch": 3.37, "learning_rate": 3.320060414664286e-05, "loss": 1.8517, "step": 73910 }, { "epoch": 3.38, "learning_rate": 3.3198315712389584e-05, "loss": 1.9487, "step": 73920 }, { "epoch": 3.38, "learning_rate": 3.31960272781363e-05, "loss": 1.817, "step": 73930 }, { "epoch": 3.38, "learning_rate": 3.319373884388301e-05, "loss": 1.912, "step": 73940 }, { "epoch": 3.38, "learning_rate": 3.319145040962973e-05, "loss": 1.6862, "step": 73950 }, { "epoch": 3.38, "learning_rate": 3.318916197537645e-05, "loss": 1.6211, "step": 73960 }, { "epoch": 3.38, "learning_rate": 3.318687354112316e-05, "loss": 1.7484, "step": 73970 }, { "epoch": 3.38, "learning_rate": 3.318458510686988e-05, "loss": 1.8974, "step": 73980 }, { "epoch": 3.38, "learning_rate": 3.3182296672616596e-05, "loss": 1.7067, "step": 73990 }, { "epoch": 3.38, "learning_rate": 3.318000823836331e-05, "loss": 1.7026, "step": 74000 }, { "epoch": 3.38, "learning_rate": 3.317771980411003e-05, "loss": 1.7315, "step": 74010 }, { "epoch": 3.38, "learning_rate": 3.3175431369856746e-05, "loss": 1.8455, "step": 74020 }, { "epoch": 3.38, "learning_rate": 3.317314293560346e-05, "loss": 1.8886, "step": 74030 }, { "epoch": 3.38, "learning_rate": 3.317085450135018e-05, "loss": 1.7515, "step": 74040 }, { "epoch": 3.38, "learning_rate": 3.3168566067096895e-05, "loss": 1.7133, "step": 74050 }, { "epoch": 3.38, "learning_rate": 3.316627763284361e-05, "loss": 1.8496, "step": 74060 }, { "epoch": 3.38, "learning_rate": 3.316398919859033e-05, "loss": 1.9104, "step": 74070 }, { "epoch": 3.38, "learning_rate": 3.3161700764337044e-05, "loss": 1.9238, "step": 74080 }, { "epoch": 3.38, "learning_rate": 3.315941233008376e-05, "loss": 1.8051, "step": 74090 }, { "epoch": 3.38, "learning_rate": 3.315712389583047e-05, "loss": 1.8098, "step": 74100 }, { "epoch": 3.38, "learning_rate": 3.3154835461577186e-05, "loss": 1.856, "step": 74110 }, { "epoch": 3.38, "learning_rate": 3.315254702732391e-05, "loss": 1.7388, "step": 74120 }, { "epoch": 3.38, "learning_rate": 3.315025859307062e-05, "loss": 1.8083, "step": 74130 }, { "epoch": 3.39, "learning_rate": 3.3147970158817336e-05, "loss": 1.7605, "step": 74140 }, { "epoch": 3.39, "learning_rate": 3.3145681724564057e-05, "loss": 1.6206, "step": 74150 }, { "epoch": 3.39, "learning_rate": 3.314339329031077e-05, "loss": 1.5702, "step": 74160 }, { "epoch": 3.39, "learning_rate": 3.3141104856057485e-05, "loss": 1.7303, "step": 74170 }, { "epoch": 3.39, "learning_rate": 3.3138816421804206e-05, "loss": 1.8119, "step": 74180 }, { "epoch": 3.39, "learning_rate": 3.313652798755092e-05, "loss": 1.8445, "step": 74190 }, { "epoch": 3.39, "learning_rate": 3.3134239553297634e-05, "loss": 1.7131, "step": 74200 }, { "epoch": 3.39, "learning_rate": 3.3131951119044355e-05, "loss": 1.9023, "step": 74210 }, { "epoch": 3.39, "learning_rate": 3.312966268479107e-05, "loss": 1.8105, "step": 74220 }, { "epoch": 3.39, "learning_rate": 3.312737425053778e-05, "loss": 1.9158, "step": 74230 }, { "epoch": 3.39, "learning_rate": 3.3125085816284504e-05, "loss": 1.7561, "step": 74240 }, { "epoch": 3.39, "learning_rate": 3.312279738203122e-05, "loss": 1.7764, "step": 74250 }, { "epoch": 3.39, "learning_rate": 3.312050894777793e-05, "loss": 1.6754, "step": 74260 }, { "epoch": 3.39, "learning_rate": 3.311822051352465e-05, "loss": 1.8142, "step": 74270 }, { "epoch": 3.39, "learning_rate": 3.311593207927137e-05, "loss": 1.7554, "step": 74280 }, { "epoch": 3.39, "learning_rate": 3.3113643645018075e-05, "loss": 1.7253, "step": 74290 }, { "epoch": 3.39, "learning_rate": 3.3111355210764796e-05, "loss": 1.6342, "step": 74300 }, { "epoch": 3.39, "learning_rate": 3.310906677651151e-05, "loss": 1.7761, "step": 74310 }, { "epoch": 3.39, "learning_rate": 3.3106778342258224e-05, "loss": 1.597, "step": 74320 }, { "epoch": 3.39, "learning_rate": 3.3104489908004945e-05, "loss": 1.7251, "step": 74330 }, { "epoch": 3.39, "learning_rate": 3.310220147375166e-05, "loss": 1.8255, "step": 74340 }, { "epoch": 3.4, "learning_rate": 3.309991303949837e-05, "loss": 1.8118, "step": 74350 }, { "epoch": 3.4, "learning_rate": 3.3097624605245094e-05, "loss": 1.797, "step": 74360 }, { "epoch": 3.4, "learning_rate": 3.309533617099181e-05, "loss": 1.7555, "step": 74370 }, { "epoch": 3.4, "learning_rate": 3.309304773673852e-05, "loss": 1.6982, "step": 74380 }, { "epoch": 3.4, "learning_rate": 3.309075930248524e-05, "loss": 1.5969, "step": 74390 }, { "epoch": 3.4, "learning_rate": 3.308847086823196e-05, "loss": 1.833, "step": 74400 }, { "epoch": 3.4, "learning_rate": 3.308618243397867e-05, "loss": 1.8595, "step": 74410 }, { "epoch": 3.4, "learning_rate": 3.308389399972539e-05, "loss": 1.7524, "step": 74420 }, { "epoch": 3.4, "learning_rate": 3.3081605565472106e-05, "loss": 1.7756, "step": 74430 }, { "epoch": 3.4, "learning_rate": 3.307931713121882e-05, "loss": 1.793, "step": 74440 }, { "epoch": 3.4, "learning_rate": 3.307702869696554e-05, "loss": 1.9296, "step": 74450 }, { "epoch": 3.4, "learning_rate": 3.3074740262712256e-05, "loss": 1.9971, "step": 74460 }, { "epoch": 3.4, "learning_rate": 3.307245182845897e-05, "loss": 1.8007, "step": 74470 }, { "epoch": 3.4, "learning_rate": 3.307016339420569e-05, "loss": 1.7977, "step": 74480 }, { "epoch": 3.4, "learning_rate": 3.30678749599524e-05, "loss": 1.9233, "step": 74490 }, { "epoch": 3.4, "learning_rate": 3.306558652569912e-05, "loss": 2.0, "step": 74500 }, { "epoch": 3.4, "learning_rate": 3.306329809144583e-05, "loss": 1.8579, "step": 74510 }, { "epoch": 3.4, "learning_rate": 3.306100965719255e-05, "loss": 1.6896, "step": 74520 }, { "epoch": 3.4, "learning_rate": 3.305872122293927e-05, "loss": 1.6586, "step": 74530 }, { "epoch": 3.4, "learning_rate": 3.305643278868598e-05, "loss": 1.7534, "step": 74540 }, { "epoch": 3.4, "learning_rate": 3.3054144354432696e-05, "loss": 1.6914, "step": 74550 }, { "epoch": 3.4, "learning_rate": 3.305185592017942e-05, "loss": 1.7121, "step": 74560 }, { "epoch": 3.41, "learning_rate": 3.304956748592613e-05, "loss": 1.7093, "step": 74570 }, { "epoch": 3.41, "learning_rate": 3.3047279051672846e-05, "loss": 1.7754, "step": 74580 }, { "epoch": 3.41, "learning_rate": 3.3044990617419566e-05, "loss": 1.882, "step": 74590 }, { "epoch": 3.41, "learning_rate": 3.304270218316628e-05, "loss": 1.8295, "step": 74600 }, { "epoch": 3.41, "learning_rate": 3.3040413748912995e-05, "loss": 1.9749, "step": 74610 }, { "epoch": 3.41, "learning_rate": 3.3038125314659716e-05, "loss": 1.7266, "step": 74620 }, { "epoch": 3.41, "learning_rate": 3.303583688040643e-05, "loss": 1.7706, "step": 74630 }, { "epoch": 3.41, "learning_rate": 3.3033548446153144e-05, "loss": 1.9826, "step": 74640 }, { "epoch": 3.41, "learning_rate": 3.3031260011899865e-05, "loss": 1.8236, "step": 74650 }, { "epoch": 3.41, "learning_rate": 3.302897157764658e-05, "loss": 1.6893, "step": 74660 }, { "epoch": 3.41, "learning_rate": 3.302668314339329e-05, "loss": 1.8669, "step": 74670 }, { "epoch": 3.41, "learning_rate": 3.302439470914001e-05, "loss": 1.7512, "step": 74680 }, { "epoch": 3.41, "learning_rate": 3.302210627488672e-05, "loss": 1.6434, "step": 74690 }, { "epoch": 3.41, "learning_rate": 3.3019817840633436e-05, "loss": 1.8518, "step": 74700 }, { "epoch": 3.41, "learning_rate": 3.3017529406380156e-05, "loss": 1.6815, "step": 74710 }, { "epoch": 3.41, "learning_rate": 3.301524097212687e-05, "loss": 1.8755, "step": 74720 }, { "epoch": 3.41, "learning_rate": 3.3012952537873585e-05, "loss": 1.7839, "step": 74730 }, { "epoch": 3.41, "learning_rate": 3.3010664103620306e-05, "loss": 1.6593, "step": 74740 }, { "epoch": 3.41, "learning_rate": 3.300837566936702e-05, "loss": 2.0482, "step": 74750 }, { "epoch": 3.41, "learning_rate": 3.3006087235113734e-05, "loss": 1.7659, "step": 74760 }, { "epoch": 3.41, "learning_rate": 3.3003798800860455e-05, "loss": 1.7614, "step": 74770 }, { "epoch": 3.41, "learning_rate": 3.300151036660717e-05, "loss": 1.702, "step": 74780 }, { "epoch": 3.42, "learning_rate": 3.299922193235388e-05, "loss": 1.8253, "step": 74790 }, { "epoch": 3.42, "learning_rate": 3.2996933498100604e-05, "loss": 1.7548, "step": 74800 }, { "epoch": 3.42, "learning_rate": 3.299464506384732e-05, "loss": 1.8089, "step": 74810 }, { "epoch": 3.42, "learning_rate": 3.299235662959403e-05, "loss": 1.7936, "step": 74820 }, { "epoch": 3.42, "learning_rate": 3.299006819534075e-05, "loss": 1.9123, "step": 74830 }, { "epoch": 3.42, "learning_rate": 3.298777976108747e-05, "loss": 1.8804, "step": 74840 }, { "epoch": 3.42, "learning_rate": 3.298549132683418e-05, "loss": 1.7333, "step": 74850 }, { "epoch": 3.42, "learning_rate": 3.29832028925809e-05, "loss": 1.9017, "step": 74860 }, { "epoch": 3.42, "learning_rate": 3.2980914458327616e-05, "loss": 1.6957, "step": 74870 }, { "epoch": 3.42, "learning_rate": 3.297862602407433e-05, "loss": 1.7755, "step": 74880 }, { "epoch": 3.42, "learning_rate": 3.2976337589821045e-05, "loss": 1.7601, "step": 74890 }, { "epoch": 3.42, "learning_rate": 3.297404915556776e-05, "loss": 1.6943, "step": 74900 }, { "epoch": 3.42, "learning_rate": 3.297176072131448e-05, "loss": 1.6494, "step": 74910 }, { "epoch": 3.42, "learning_rate": 3.2969472287061194e-05, "loss": 1.7215, "step": 74920 }, { "epoch": 3.42, "learning_rate": 3.296718385280791e-05, "loss": 1.8562, "step": 74930 }, { "epoch": 3.42, "learning_rate": 3.296489541855462e-05, "loss": 1.7252, "step": 74940 }, { "epoch": 3.42, "learning_rate": 3.296260698430134e-05, "loss": 1.9119, "step": 74950 }, { "epoch": 3.42, "learning_rate": 3.296031855004806e-05, "loss": 1.7563, "step": 74960 }, { "epoch": 3.42, "learning_rate": 3.295803011579477e-05, "loss": 1.7349, "step": 74970 }, { "epoch": 3.42, "learning_rate": 3.295574168154149e-05, "loss": 1.7541, "step": 74980 }, { "epoch": 3.42, "learning_rate": 3.2953453247288206e-05, "loss": 1.7475, "step": 74990 }, { "epoch": 3.42, "learning_rate": 3.295116481303492e-05, "loss": 1.8453, "step": 75000 }, { "epoch": 3.43, "learning_rate": 3.294887637878164e-05, "loss": 1.7, "step": 75010 }, { "epoch": 3.43, "learning_rate": 3.2946587944528356e-05, "loss": 1.7233, "step": 75020 }, { "epoch": 3.43, "learning_rate": 3.294429951027507e-05, "loss": 1.6268, "step": 75030 }, { "epoch": 3.43, "learning_rate": 3.294201107602179e-05, "loss": 1.7382, "step": 75040 }, { "epoch": 3.43, "learning_rate": 3.2939722641768505e-05, "loss": 1.6689, "step": 75050 }, { "epoch": 3.43, "learning_rate": 3.293743420751522e-05, "loss": 1.8153, "step": 75060 }, { "epoch": 3.43, "learning_rate": 3.293514577326194e-05, "loss": 1.8645, "step": 75070 }, { "epoch": 3.43, "learning_rate": 3.293285733900865e-05, "loss": 1.8147, "step": 75080 }, { "epoch": 3.43, "learning_rate": 3.293056890475537e-05, "loss": 1.8718, "step": 75090 }, { "epoch": 3.43, "learning_rate": 3.292828047050208e-05, "loss": 1.8383, "step": 75100 }, { "epoch": 3.43, "learning_rate": 3.2925992036248796e-05, "loss": 1.6887, "step": 75110 }, { "epoch": 3.43, "learning_rate": 3.292370360199552e-05, "loss": 1.9021, "step": 75120 }, { "epoch": 3.43, "learning_rate": 3.292141516774223e-05, "loss": 1.6956, "step": 75130 }, { "epoch": 3.43, "learning_rate": 3.2919126733488945e-05, "loss": 1.7315, "step": 75140 }, { "epoch": 3.43, "learning_rate": 3.2916838299235666e-05, "loss": 1.7723, "step": 75150 }, { "epoch": 3.43, "learning_rate": 3.291454986498238e-05, "loss": 1.6393, "step": 75160 }, { "epoch": 3.43, "learning_rate": 3.2912261430729095e-05, "loss": 1.7967, "step": 75170 }, { "epoch": 3.43, "learning_rate": 3.2909972996475816e-05, "loss": 1.6051, "step": 75180 }, { "epoch": 3.43, "learning_rate": 3.290768456222253e-05, "loss": 1.6954, "step": 75190 }, { "epoch": 3.43, "learning_rate": 3.2905396127969244e-05, "loss": 1.76, "step": 75200 }, { "epoch": 3.43, "learning_rate": 3.2903107693715965e-05, "loss": 1.7601, "step": 75210 }, { "epoch": 3.43, "learning_rate": 3.290081925946268e-05, "loss": 1.754, "step": 75220 }, { "epoch": 3.44, "learning_rate": 3.289853082520939e-05, "loss": 1.7727, "step": 75230 }, { "epoch": 3.44, "learning_rate": 3.2896242390956114e-05, "loss": 1.7696, "step": 75240 }, { "epoch": 3.44, "learning_rate": 3.289395395670283e-05, "loss": 1.7025, "step": 75250 }, { "epoch": 3.44, "learning_rate": 3.289166552244954e-05, "loss": 1.8805, "step": 75260 }, { "epoch": 3.44, "learning_rate": 3.288937708819626e-05, "loss": 1.7795, "step": 75270 }, { "epoch": 3.44, "learning_rate": 3.288708865394297e-05, "loss": 1.6501, "step": 75280 }, { "epoch": 3.44, "learning_rate": 3.2884800219689685e-05, "loss": 1.6846, "step": 75290 }, { "epoch": 3.44, "learning_rate": 3.2882511785436405e-05, "loss": 1.7122, "step": 75300 }, { "epoch": 3.44, "learning_rate": 3.288022335118312e-05, "loss": 1.8082, "step": 75310 }, { "epoch": 3.44, "learning_rate": 3.2877934916929834e-05, "loss": 1.8748, "step": 75320 }, { "epoch": 3.44, "learning_rate": 3.2875646482676555e-05, "loss": 1.6926, "step": 75330 }, { "epoch": 3.44, "learning_rate": 3.287335804842327e-05, "loss": 1.7191, "step": 75340 }, { "epoch": 3.44, "learning_rate": 3.287106961416998e-05, "loss": 1.7848, "step": 75350 }, { "epoch": 3.44, "learning_rate": 3.2868781179916704e-05, "loss": 1.7806, "step": 75360 }, { "epoch": 3.44, "learning_rate": 3.286649274566342e-05, "loss": 1.8949, "step": 75370 }, { "epoch": 3.44, "learning_rate": 3.286420431141013e-05, "loss": 1.9637, "step": 75380 }, { "epoch": 3.44, "learning_rate": 3.286191587715685e-05, "loss": 1.651, "step": 75390 }, { "epoch": 3.44, "learning_rate": 3.285962744290357e-05, "loss": 1.6998, "step": 75400 }, { "epoch": 3.44, "learning_rate": 3.285733900865028e-05, "loss": 1.8323, "step": 75410 }, { "epoch": 3.44, "learning_rate": 3.2855050574397e-05, "loss": 1.7083, "step": 75420 }, { "epoch": 3.44, "learning_rate": 3.2852762140143716e-05, "loss": 1.882, "step": 75430 }, { "epoch": 3.44, "learning_rate": 3.285047370589043e-05, "loss": 1.9762, "step": 75440 }, { "epoch": 3.45, "learning_rate": 3.284818527163715e-05, "loss": 1.7536, "step": 75450 }, { "epoch": 3.45, "learning_rate": 3.2845896837383866e-05, "loss": 1.682, "step": 75460 }, { "epoch": 3.45, "learning_rate": 3.284360840313058e-05, "loss": 1.7123, "step": 75470 }, { "epoch": 3.45, "learning_rate": 3.2841319968877294e-05, "loss": 1.7412, "step": 75480 }, { "epoch": 3.45, "learning_rate": 3.283903153462401e-05, "loss": 1.76, "step": 75490 }, { "epoch": 3.45, "learning_rate": 3.283674310037073e-05, "loss": 1.7109, "step": 75500 }, { "epoch": 3.45, "learning_rate": 3.283445466611744e-05, "loss": 1.8009, "step": 75510 }, { "epoch": 3.45, "learning_rate": 3.283216623186416e-05, "loss": 1.6606, "step": 75520 }, { "epoch": 3.45, "learning_rate": 3.282987779761088e-05, "loss": 1.7775, "step": 75530 }, { "epoch": 3.45, "learning_rate": 3.282758936335759e-05, "loss": 1.8852, "step": 75540 }, { "epoch": 3.45, "learning_rate": 3.2825300929104306e-05, "loss": 1.6575, "step": 75550 }, { "epoch": 3.45, "learning_rate": 3.282301249485103e-05, "loss": 2.0521, "step": 75560 }, { "epoch": 3.45, "learning_rate": 3.282072406059774e-05, "loss": 1.8282, "step": 75570 }, { "epoch": 3.45, "learning_rate": 3.2818435626344455e-05, "loss": 1.648, "step": 75580 }, { "epoch": 3.45, "learning_rate": 3.2816147192091176e-05, "loss": 1.9741, "step": 75590 }, { "epoch": 3.45, "learning_rate": 3.281385875783789e-05, "loss": 1.8245, "step": 75600 }, { "epoch": 3.45, "learning_rate": 3.2811570323584605e-05, "loss": 1.7779, "step": 75610 }, { "epoch": 3.45, "learning_rate": 3.2809281889331326e-05, "loss": 1.8382, "step": 75620 }, { "epoch": 3.45, "learning_rate": 3.280699345507804e-05, "loss": 1.8312, "step": 75630 }, { "epoch": 3.45, "learning_rate": 3.2804705020824754e-05, "loss": 1.7372, "step": 75640 }, { "epoch": 3.45, "learning_rate": 3.2802416586571475e-05, "loss": 1.6683, "step": 75650 }, { "epoch": 3.45, "learning_rate": 3.280012815231819e-05, "loss": 1.6787, "step": 75660 }, { "epoch": 3.46, "learning_rate": 3.2797839718064896e-05, "loss": 1.7024, "step": 75670 }, { "epoch": 3.46, "learning_rate": 3.279555128381162e-05, "loss": 1.745, "step": 75680 }, { "epoch": 3.46, "learning_rate": 3.279326284955833e-05, "loss": 1.6802, "step": 75690 }, { "epoch": 3.46, "learning_rate": 3.2790974415305045e-05, "loss": 1.8329, "step": 75700 }, { "epoch": 3.46, "learning_rate": 3.2788685981051766e-05, "loss": 1.9505, "step": 75710 }, { "epoch": 3.46, "learning_rate": 3.278639754679848e-05, "loss": 1.6634, "step": 75720 }, { "epoch": 3.46, "learning_rate": 3.2784109112545195e-05, "loss": 1.8014, "step": 75730 }, { "epoch": 3.46, "learning_rate": 3.2781820678291915e-05, "loss": 1.7625, "step": 75740 }, { "epoch": 3.46, "learning_rate": 3.277953224403863e-05, "loss": 1.5131, "step": 75750 }, { "epoch": 3.46, "learning_rate": 3.2777243809785344e-05, "loss": 1.7438, "step": 75760 }, { "epoch": 3.46, "learning_rate": 3.2774955375532065e-05, "loss": 1.7172, "step": 75770 }, { "epoch": 3.46, "learning_rate": 3.277266694127878e-05, "loss": 1.7153, "step": 75780 }, { "epoch": 3.46, "learning_rate": 3.277037850702549e-05, "loss": 1.7505, "step": 75790 }, { "epoch": 3.46, "learning_rate": 3.2768090072772214e-05, "loss": 1.8913, "step": 75800 }, { "epoch": 3.46, "learning_rate": 3.276580163851893e-05, "loss": 1.654, "step": 75810 }, { "epoch": 3.46, "learning_rate": 3.276351320426564e-05, "loss": 1.8473, "step": 75820 }, { "epoch": 3.46, "learning_rate": 3.276122477001236e-05, "loss": 1.9086, "step": 75830 }, { "epoch": 3.46, "learning_rate": 3.275893633575908e-05, "loss": 1.8968, "step": 75840 }, { "epoch": 3.46, "learning_rate": 3.275664790150579e-05, "loss": 1.7537, "step": 75850 }, { "epoch": 3.46, "learning_rate": 3.275435946725251e-05, "loss": 1.7669, "step": 75860 }, { "epoch": 3.46, "learning_rate": 3.275207103299922e-05, "loss": 1.9437, "step": 75870 }, { "epoch": 3.46, "learning_rate": 3.274978259874594e-05, "loss": 1.7133, "step": 75880 }, { "epoch": 3.47, "learning_rate": 3.2747494164492655e-05, "loss": 1.5788, "step": 75890 }, { "epoch": 3.47, "learning_rate": 3.274520573023937e-05, "loss": 1.9164, "step": 75900 }, { "epoch": 3.47, "learning_rate": 3.274291729598609e-05, "loss": 1.7448, "step": 75910 }, { "epoch": 3.47, "learning_rate": 3.2740628861732804e-05, "loss": 1.6212, "step": 75920 }, { "epoch": 3.47, "learning_rate": 3.273834042747952e-05, "loss": 1.6544, "step": 75930 }, { "epoch": 3.47, "learning_rate": 3.273605199322624e-05, "loss": 1.7282, "step": 75940 }, { "epoch": 3.47, "learning_rate": 3.273376355897295e-05, "loss": 1.7265, "step": 75950 }, { "epoch": 3.47, "learning_rate": 3.273147512471967e-05, "loss": 1.8603, "step": 75960 }, { "epoch": 3.47, "learning_rate": 3.272918669046639e-05, "loss": 1.6299, "step": 75970 }, { "epoch": 3.47, "learning_rate": 3.27268982562131e-05, "loss": 1.8732, "step": 75980 }, { "epoch": 3.47, "learning_rate": 3.2724609821959816e-05, "loss": 1.8644, "step": 75990 }, { "epoch": 3.47, "learning_rate": 3.272232138770654e-05, "loss": 1.79, "step": 76000 }, { "epoch": 3.47, "learning_rate": 3.272003295345325e-05, "loss": 1.7432, "step": 76010 }, { "epoch": 3.47, "learning_rate": 3.2717744519199965e-05, "loss": 1.7662, "step": 76020 }, { "epoch": 3.47, "learning_rate": 3.271545608494668e-05, "loss": 1.7532, "step": 76030 }, { "epoch": 3.47, "learning_rate": 3.27131676506934e-05, "loss": 1.8159, "step": 76040 }, { "epoch": 3.47, "learning_rate": 3.2710879216440115e-05, "loss": 1.911, "step": 76050 }, { "epoch": 3.47, "learning_rate": 3.270859078218683e-05, "loss": 1.5609, "step": 76060 }, { "epoch": 3.47, "learning_rate": 3.270630234793354e-05, "loss": 1.7206, "step": 76070 }, { "epoch": 3.47, "learning_rate": 3.270401391368026e-05, "loss": 1.6932, "step": 76080 }, { "epoch": 3.47, "learning_rate": 3.270172547942698e-05, "loss": 1.7767, "step": 76090 }, { "epoch": 3.47, "learning_rate": 3.269943704517369e-05, "loss": 1.5143, "step": 76100 }, { "epoch": 3.48, "learning_rate": 3.2697148610920406e-05, "loss": 1.7434, "step": 76110 }, { "epoch": 3.48, "learning_rate": 3.269486017666713e-05, "loss": 1.843, "step": 76120 }, { "epoch": 3.48, "learning_rate": 3.269257174241384e-05, "loss": 1.6253, "step": 76130 }, { "epoch": 3.48, "learning_rate": 3.2690283308160555e-05, "loss": 1.8244, "step": 76140 }, { "epoch": 3.48, "learning_rate": 3.2687994873907276e-05, "loss": 1.8345, "step": 76150 }, { "epoch": 3.48, "learning_rate": 3.268570643965399e-05, "loss": 1.8111, "step": 76160 }, { "epoch": 3.48, "learning_rate": 3.2683418005400705e-05, "loss": 1.7335, "step": 76170 }, { "epoch": 3.48, "learning_rate": 3.2681129571147425e-05, "loss": 1.8277, "step": 76180 }, { "epoch": 3.48, "learning_rate": 3.267884113689414e-05, "loss": 1.7763, "step": 76190 }, { "epoch": 3.48, "learning_rate": 3.2676552702640854e-05, "loss": 2.0016, "step": 76200 }, { "epoch": 3.48, "learning_rate": 3.2674264268387575e-05, "loss": 1.7081, "step": 76210 }, { "epoch": 3.48, "learning_rate": 3.267197583413429e-05, "loss": 1.7123, "step": 76220 }, { "epoch": 3.48, "learning_rate": 3.2669687399881e-05, "loss": 1.825, "step": 76230 }, { "epoch": 3.48, "learning_rate": 3.2667398965627724e-05, "loss": 1.8576, "step": 76240 }, { "epoch": 3.48, "learning_rate": 3.266511053137444e-05, "loss": 1.7793, "step": 76250 }, { "epoch": 3.48, "learning_rate": 3.266282209712115e-05, "loss": 1.7435, "step": 76260 }, { "epoch": 3.48, "learning_rate": 3.2660533662867866e-05, "loss": 1.7726, "step": 76270 }, { "epoch": 3.48, "learning_rate": 3.265824522861458e-05, "loss": 1.616, "step": 76280 }, { "epoch": 3.48, "learning_rate": 3.2655956794361294e-05, "loss": 1.7666, "step": 76290 }, { "epoch": 3.48, "learning_rate": 3.2653668360108015e-05, "loss": 1.8576, "step": 76300 }, { "epoch": 3.48, "learning_rate": 3.265137992585473e-05, "loss": 1.7706, "step": 76310 }, { "epoch": 3.48, "learning_rate": 3.2649091491601444e-05, "loss": 1.7715, "step": 76320 }, { "epoch": 3.49, "learning_rate": 3.2646803057348165e-05, "loss": 1.9134, "step": 76330 }, { "epoch": 3.49, "learning_rate": 3.264451462309488e-05, "loss": 1.7891, "step": 76340 }, { "epoch": 3.49, "learning_rate": 3.264222618884159e-05, "loss": 1.6711, "step": 76350 }, { "epoch": 3.49, "learning_rate": 3.2639937754588314e-05, "loss": 1.6976, "step": 76360 }, { "epoch": 3.49, "learning_rate": 3.263764932033503e-05, "loss": 1.7609, "step": 76370 }, { "epoch": 3.49, "learning_rate": 3.263536088608174e-05, "loss": 1.758, "step": 76380 }, { "epoch": 3.49, "learning_rate": 3.263307245182846e-05, "loss": 1.7659, "step": 76390 }, { "epoch": 3.49, "learning_rate": 3.263078401757518e-05, "loss": 1.779, "step": 76400 }, { "epoch": 3.49, "learning_rate": 3.262849558332189e-05, "loss": 1.8321, "step": 76410 }, { "epoch": 3.49, "learning_rate": 3.262620714906861e-05, "loss": 1.7393, "step": 76420 }, { "epoch": 3.49, "learning_rate": 3.2623918714815326e-05, "loss": 1.7319, "step": 76430 }, { "epoch": 3.49, "learning_rate": 3.262163028056204e-05, "loss": 1.6596, "step": 76440 }, { "epoch": 3.49, "learning_rate": 3.261934184630876e-05, "loss": 1.8666, "step": 76450 }, { "epoch": 3.49, "learning_rate": 3.261705341205547e-05, "loss": 1.5931, "step": 76460 }, { "epoch": 3.49, "learning_rate": 3.261476497780219e-05, "loss": 1.7222, "step": 76470 }, { "epoch": 3.49, "learning_rate": 3.2612476543548904e-05, "loss": 1.8241, "step": 76480 }, { "epoch": 3.49, "learning_rate": 3.261018810929562e-05, "loss": 1.8036, "step": 76490 }, { "epoch": 3.49, "learning_rate": 3.260789967504234e-05, "loss": 1.7586, "step": 76500 }, { "epoch": 3.49, "learning_rate": 3.260561124078905e-05, "loss": 1.9477, "step": 76510 }, { "epoch": 3.49, "learning_rate": 3.260332280653577e-05, "loss": 1.7806, "step": 76520 }, { "epoch": 3.49, "learning_rate": 3.260103437228249e-05, "loss": 1.8531, "step": 76530 }, { "epoch": 3.5, "learning_rate": 3.25987459380292e-05, "loss": 1.6668, "step": 76540 }, { "epoch": 3.5, "learning_rate": 3.2596457503775916e-05, "loss": 1.8145, "step": 76550 }, { "epoch": 3.5, "learning_rate": 3.259416906952264e-05, "loss": 1.7745, "step": 76560 }, { "epoch": 3.5, "learning_rate": 3.259188063526935e-05, "loss": 1.796, "step": 76570 }, { "epoch": 3.5, "learning_rate": 3.2589592201016065e-05, "loss": 1.7639, "step": 76580 }, { "epoch": 3.5, "learning_rate": 3.2587303766762786e-05, "loss": 1.5962, "step": 76590 }, { "epoch": 3.5, "learning_rate": 3.25850153325095e-05, "loss": 1.8663, "step": 76600 }, { "epoch": 3.5, "learning_rate": 3.2582726898256214e-05, "loss": 1.8822, "step": 76610 }, { "epoch": 3.5, "learning_rate": 3.2580438464002935e-05, "loss": 1.4923, "step": 76620 }, { "epoch": 3.5, "learning_rate": 3.257815002974965e-05, "loss": 1.6902, "step": 76630 }, { "epoch": 3.5, "learning_rate": 3.2575861595496364e-05, "loss": 1.7933, "step": 76640 }, { "epoch": 3.5, "learning_rate": 3.2573573161243085e-05, "loss": 1.6855, "step": 76650 }, { "epoch": 3.5, "learning_rate": 3.257128472698979e-05, "loss": 1.8518, "step": 76660 }, { "epoch": 3.5, "learning_rate": 3.2568996292736506e-05, "loss": 1.9508, "step": 76670 }, { "epoch": 3.5, "learning_rate": 3.256670785848323e-05, "loss": 1.7538, "step": 76680 }, { "epoch": 3.5, "learning_rate": 3.256441942422994e-05, "loss": 1.8624, "step": 76690 }, { "epoch": 3.5, "learning_rate": 3.2562130989976655e-05, "loss": 1.8103, "step": 76700 }, { "epoch": 3.5, "learning_rate": 3.2559842555723376e-05, "loss": 1.7879, "step": 76710 }, { "epoch": 3.5, "learning_rate": 3.255755412147009e-05, "loss": 1.7708, "step": 76720 }, { "epoch": 3.5, "learning_rate": 3.2555265687216804e-05, "loss": 1.957, "step": 76730 }, { "epoch": 3.5, "learning_rate": 3.2552977252963525e-05, "loss": 1.7147, "step": 76740 }, { "epoch": 3.5, "learning_rate": 3.255068881871024e-05, "loss": 1.7146, "step": 76750 }, { "epoch": 3.51, "learning_rate": 3.2548400384456954e-05, "loss": 1.9686, "step": 76760 }, { "epoch": 3.51, "learning_rate": 3.2546111950203674e-05, "loss": 1.5557, "step": 76770 }, { "epoch": 3.51, "learning_rate": 3.254382351595039e-05, "loss": 1.8055, "step": 76780 }, { "epoch": 3.51, "learning_rate": 3.25415350816971e-05, "loss": 1.7686, "step": 76790 }, { "epoch": 3.51, "learning_rate": 3.2539246647443824e-05, "loss": 1.8131, "step": 76800 }, { "epoch": 3.51, "learning_rate": 3.253695821319054e-05, "loss": 1.6657, "step": 76810 }, { "epoch": 3.51, "learning_rate": 3.253466977893725e-05, "loss": 1.7648, "step": 76820 }, { "epoch": 3.51, "learning_rate": 3.253238134468397e-05, "loss": 1.5138, "step": 76830 }, { "epoch": 3.51, "learning_rate": 3.253009291043069e-05, "loss": 1.8022, "step": 76840 }, { "epoch": 3.51, "learning_rate": 3.25278044761774e-05, "loss": 1.7707, "step": 76850 }, { "epoch": 3.51, "learning_rate": 3.2525516041924115e-05, "loss": 1.7185, "step": 76860 }, { "epoch": 3.51, "learning_rate": 3.252322760767083e-05, "loss": 1.8288, "step": 76870 }, { "epoch": 3.51, "learning_rate": 3.252093917341755e-05, "loss": 1.7572, "step": 76880 }, { "epoch": 3.51, "learning_rate": 3.2518650739164264e-05, "loss": 1.8345, "step": 76890 }, { "epoch": 3.51, "learning_rate": 3.251636230491098e-05, "loss": 1.7499, "step": 76900 }, { "epoch": 3.51, "learning_rate": 3.25140738706577e-05, "loss": 1.7922, "step": 76910 }, { "epoch": 3.51, "learning_rate": 3.2511785436404414e-05, "loss": 1.6189, "step": 76920 }, { "epoch": 3.51, "learning_rate": 3.250949700215113e-05, "loss": 1.9086, "step": 76930 }, { "epoch": 3.51, "learning_rate": 3.250720856789785e-05, "loss": 1.8672, "step": 76940 }, { "epoch": 3.51, "learning_rate": 3.250492013364456e-05, "loss": 1.7307, "step": 76950 }, { "epoch": 3.51, "learning_rate": 3.250263169939128e-05, "loss": 1.7678, "step": 76960 }, { "epoch": 3.51, "learning_rate": 3.2500343265138e-05, "loss": 1.7911, "step": 76970 }, { "epoch": 3.52, "learning_rate": 3.249805483088471e-05, "loss": 1.59, "step": 76980 }, { "epoch": 3.52, "learning_rate": 3.2495766396631426e-05, "loss": 1.7871, "step": 76990 }, { "epoch": 3.52, "learning_rate": 3.249347796237815e-05, "loss": 1.7261, "step": 77000 }, { "epoch": 3.52, "learning_rate": 3.249118952812486e-05, "loss": 1.702, "step": 77010 }, { "epoch": 3.52, "learning_rate": 3.2488901093871575e-05, "loss": 1.7972, "step": 77020 }, { "epoch": 3.52, "learning_rate": 3.2486612659618296e-05, "loss": 1.6798, "step": 77030 }, { "epoch": 3.52, "learning_rate": 3.248432422536501e-05, "loss": 1.7334, "step": 77040 }, { "epoch": 3.52, "learning_rate": 3.2482035791111724e-05, "loss": 1.7425, "step": 77050 }, { "epoch": 3.52, "learning_rate": 3.247974735685844e-05, "loss": 1.5738, "step": 77060 }, { "epoch": 3.52, "learning_rate": 3.247745892260515e-05, "loss": 1.658, "step": 77070 }, { "epoch": 3.52, "learning_rate": 3.247517048835187e-05, "loss": 1.6446, "step": 77080 }, { "epoch": 3.52, "learning_rate": 3.247288205409859e-05, "loss": 1.5671, "step": 77090 }, { "epoch": 3.52, "learning_rate": 3.24705936198453e-05, "loss": 1.757, "step": 77100 }, { "epoch": 3.52, "learning_rate": 3.2468305185592016e-05, "loss": 1.8074, "step": 77110 }, { "epoch": 3.52, "learning_rate": 3.246601675133874e-05, "loss": 1.7324, "step": 77120 }, { "epoch": 3.52, "learning_rate": 3.246372831708545e-05, "loss": 1.8432, "step": 77130 }, { "epoch": 3.52, "learning_rate": 3.2461439882832165e-05, "loss": 1.6876, "step": 77140 }, { "epoch": 3.52, "learning_rate": 3.2459151448578886e-05, "loss": 1.7188, "step": 77150 }, { "epoch": 3.52, "learning_rate": 3.24568630143256e-05, "loss": 1.6421, "step": 77160 }, { "epoch": 3.52, "learning_rate": 3.2454574580072314e-05, "loss": 1.8241, "step": 77170 }, { "epoch": 3.52, "learning_rate": 3.2452286145819035e-05, "loss": 1.843, "step": 77180 }, { "epoch": 3.52, "learning_rate": 3.244999771156575e-05, "loss": 1.8107, "step": 77190 }, { "epoch": 3.53, "learning_rate": 3.2447709277312464e-05, "loss": 1.732, "step": 77200 }, { "epoch": 3.53, "learning_rate": 3.2445420843059184e-05, "loss": 1.7345, "step": 77210 }, { "epoch": 3.53, "learning_rate": 3.24431324088059e-05, "loss": 1.7934, "step": 77220 }, { "epoch": 3.53, "learning_rate": 3.244084397455261e-05, "loss": 1.8238, "step": 77230 }, { "epoch": 3.53, "learning_rate": 3.2438555540299334e-05, "loss": 1.7588, "step": 77240 }, { "epoch": 3.53, "learning_rate": 3.243626710604604e-05, "loss": 1.6722, "step": 77250 }, { "epoch": 3.53, "learning_rate": 3.2433978671792755e-05, "loss": 1.7261, "step": 77260 }, { "epoch": 3.53, "learning_rate": 3.2431690237539476e-05, "loss": 1.7184, "step": 77270 }, { "epoch": 3.53, "learning_rate": 3.242940180328619e-05, "loss": 1.6538, "step": 77280 }, { "epoch": 3.53, "learning_rate": 3.2427113369032904e-05, "loss": 1.8011, "step": 77290 }, { "epoch": 3.53, "learning_rate": 3.2424824934779625e-05, "loss": 1.5671, "step": 77300 }, { "epoch": 3.53, "learning_rate": 3.242253650052634e-05, "loss": 1.5201, "step": 77310 }, { "epoch": 3.53, "learning_rate": 3.2420248066273053e-05, "loss": 1.7936, "step": 77320 }, { "epoch": 3.53, "learning_rate": 3.2417959632019774e-05, "loss": 1.709, "step": 77330 }, { "epoch": 3.53, "learning_rate": 3.241567119776649e-05, "loss": 1.7948, "step": 77340 }, { "epoch": 3.53, "learning_rate": 3.24133827635132e-05, "loss": 1.6617, "step": 77350 }, { "epoch": 3.53, "learning_rate": 3.2411094329259924e-05, "loss": 1.6131, "step": 77360 }, { "epoch": 3.53, "learning_rate": 3.240880589500664e-05, "loss": 1.8576, "step": 77370 }, { "epoch": 3.53, "learning_rate": 3.240651746075335e-05, "loss": 1.7037, "step": 77380 }, { "epoch": 3.53, "learning_rate": 3.240422902650007e-05, "loss": 1.8288, "step": 77390 }, { "epoch": 3.53, "learning_rate": 3.240194059224679e-05, "loss": 1.8814, "step": 77400 }, { "epoch": 3.53, "learning_rate": 3.23996521579935e-05, "loss": 1.739, "step": 77410 }, { "epoch": 3.54, "learning_rate": 3.239736372374022e-05, "loss": 1.7684, "step": 77420 }, { "epoch": 3.54, "learning_rate": 3.2395075289486936e-05, "loss": 1.6587, "step": 77430 }, { "epoch": 3.54, "learning_rate": 3.239278685523365e-05, "loss": 1.9037, "step": 77440 }, { "epoch": 3.54, "learning_rate": 3.2390498420980364e-05, "loss": 1.7277, "step": 77450 }, { "epoch": 3.54, "learning_rate": 3.238820998672708e-05, "loss": 1.7255, "step": 77460 }, { "epoch": 3.54, "learning_rate": 3.23859215524738e-05, "loss": 1.6411, "step": 77470 }, { "epoch": 3.54, "learning_rate": 3.2383633118220514e-05, "loss": 1.7935, "step": 77480 }, { "epoch": 3.54, "learning_rate": 3.238134468396723e-05, "loss": 1.7578, "step": 77490 }, { "epoch": 3.54, "learning_rate": 3.237905624971395e-05, "loss": 1.7716, "step": 77500 }, { "epoch": 3.54, "learning_rate": 3.237676781546066e-05, "loss": 1.9057, "step": 77510 }, { "epoch": 3.54, "learning_rate": 3.237447938120738e-05, "loss": 1.6152, "step": 77520 }, { "epoch": 3.54, "learning_rate": 3.23721909469541e-05, "loss": 1.9188, "step": 77530 }, { "epoch": 3.54, "learning_rate": 3.236990251270081e-05, "loss": 1.729, "step": 77540 }, { "epoch": 3.54, "learning_rate": 3.2367614078447526e-05, "loss": 1.8311, "step": 77550 }, { "epoch": 3.54, "learning_rate": 3.236532564419425e-05, "loss": 1.8123, "step": 77560 }, { "epoch": 3.54, "learning_rate": 3.236303720994096e-05, "loss": 1.7497, "step": 77570 }, { "epoch": 3.54, "learning_rate": 3.2360748775687675e-05, "loss": 1.8604, "step": 77580 }, { "epoch": 3.54, "learning_rate": 3.2358460341434396e-05, "loss": 1.6046, "step": 77590 }, { "epoch": 3.54, "learning_rate": 3.235617190718111e-05, "loss": 1.8238, "step": 77600 }, { "epoch": 3.54, "learning_rate": 3.2353883472927824e-05, "loss": 1.752, "step": 77610 }, { "epoch": 3.54, "learning_rate": 3.2351595038674545e-05, "loss": 1.7453, "step": 77620 }, { "epoch": 3.54, "learning_rate": 3.234930660442126e-05, "loss": 1.8195, "step": 77630 }, { "epoch": 3.55, "learning_rate": 3.2347018170167974e-05, "loss": 1.7868, "step": 77640 }, { "epoch": 3.55, "learning_rate": 3.234472973591469e-05, "loss": 1.7418, "step": 77650 }, { "epoch": 3.55, "learning_rate": 3.23424413016614e-05, "loss": 1.8155, "step": 77660 }, { "epoch": 3.55, "learning_rate": 3.2340152867408116e-05, "loss": 1.6428, "step": 77670 }, { "epoch": 3.55, "learning_rate": 3.233786443315484e-05, "loss": 1.8531, "step": 77680 }, { "epoch": 3.55, "learning_rate": 3.233557599890155e-05, "loss": 1.7081, "step": 77690 }, { "epoch": 3.55, "learning_rate": 3.2333287564648265e-05, "loss": 1.7723, "step": 77700 }, { "epoch": 3.55, "learning_rate": 3.2330999130394986e-05, "loss": 1.7083, "step": 77710 }, { "epoch": 3.55, "learning_rate": 3.23287106961417e-05, "loss": 1.6219, "step": 77720 }, { "epoch": 3.55, "learning_rate": 3.2326422261888414e-05, "loss": 1.7529, "step": 77730 }, { "epoch": 3.55, "learning_rate": 3.2324133827635135e-05, "loss": 1.8934, "step": 77740 }, { "epoch": 3.55, "learning_rate": 3.232184539338185e-05, "loss": 1.7735, "step": 77750 }, { "epoch": 3.55, "learning_rate": 3.2319556959128563e-05, "loss": 1.7195, "step": 77760 }, { "epoch": 3.55, "learning_rate": 3.2317268524875284e-05, "loss": 1.6855, "step": 77770 }, { "epoch": 3.55, "learning_rate": 3.2314980090622e-05, "loss": 1.7075, "step": 77780 }, { "epoch": 3.55, "learning_rate": 3.231269165636871e-05, "loss": 1.6665, "step": 77790 }, { "epoch": 3.55, "learning_rate": 3.2310403222115434e-05, "loss": 1.6274, "step": 77800 }, { "epoch": 3.55, "learning_rate": 3.230811478786215e-05, "loss": 1.6796, "step": 77810 }, { "epoch": 3.55, "learning_rate": 3.230582635360886e-05, "loss": 1.5903, "step": 77820 }, { "epoch": 3.55, "learning_rate": 3.230353791935558e-05, "loss": 1.689, "step": 77830 }, { "epoch": 3.55, "learning_rate": 3.23012494851023e-05, "loss": 1.6271, "step": 77840 }, { "epoch": 3.55, "learning_rate": 3.229896105084901e-05, "loss": 1.7796, "step": 77850 }, { "epoch": 3.56, "learning_rate": 3.2296672616595725e-05, "loss": 1.8404, "step": 77860 }, { "epoch": 3.56, "learning_rate": 3.229438418234244e-05, "loss": 1.6973, "step": 77870 }, { "epoch": 3.56, "learning_rate": 3.229209574808916e-05, "loss": 1.6053, "step": 77880 }, { "epoch": 3.56, "learning_rate": 3.2289807313835874e-05, "loss": 1.767, "step": 77890 }, { "epoch": 3.56, "learning_rate": 3.228751887958259e-05, "loss": 1.6887, "step": 77900 }, { "epoch": 3.56, "learning_rate": 3.228523044532931e-05, "loss": 1.6262, "step": 77910 }, { "epoch": 3.56, "learning_rate": 3.2282942011076023e-05, "loss": 1.7462, "step": 77920 }, { "epoch": 3.56, "learning_rate": 3.228065357682274e-05, "loss": 1.6561, "step": 77930 }, { "epoch": 3.56, "learning_rate": 3.227836514256946e-05, "loss": 1.8333, "step": 77940 }, { "epoch": 3.56, "learning_rate": 3.227607670831617e-05, "loss": 1.7893, "step": 77950 }, { "epoch": 3.56, "learning_rate": 3.227378827406289e-05, "loss": 1.779, "step": 77960 }, { "epoch": 3.56, "learning_rate": 3.227149983980961e-05, "loss": 1.8252, "step": 77970 }, { "epoch": 3.56, "learning_rate": 3.226921140555632e-05, "loss": 1.5719, "step": 77980 }, { "epoch": 3.56, "learning_rate": 3.2266922971303036e-05, "loss": 1.7823, "step": 77990 }, { "epoch": 3.56, "learning_rate": 3.226463453704976e-05, "loss": 1.7025, "step": 78000 }, { "epoch": 3.56, "learning_rate": 3.226234610279647e-05, "loss": 1.5685, "step": 78010 }, { "epoch": 3.56, "learning_rate": 3.2260057668543185e-05, "loss": 1.6354, "step": 78020 }, { "epoch": 3.56, "learning_rate": 3.2257769234289906e-05, "loss": 1.584, "step": 78030 }, { "epoch": 3.56, "learning_rate": 3.2255480800036613e-05, "loss": 1.6656, "step": 78040 }, { "epoch": 3.56, "learning_rate": 3.225319236578333e-05, "loss": 1.8396, "step": 78050 }, { "epoch": 3.56, "learning_rate": 3.225090393153005e-05, "loss": 1.7219, "step": 78060 }, { "epoch": 3.56, "learning_rate": 3.224861549727676e-05, "loss": 1.8283, "step": 78070 }, { "epoch": 3.57, "learning_rate": 3.224632706302348e-05, "loss": 1.7832, "step": 78080 }, { "epoch": 3.57, "learning_rate": 3.22440386287702e-05, "loss": 1.9087, "step": 78090 }, { "epoch": 3.57, "learning_rate": 3.224175019451691e-05, "loss": 1.9172, "step": 78100 }, { "epoch": 3.57, "learning_rate": 3.2239461760263626e-05, "loss": 1.7751, "step": 78110 }, { "epoch": 3.57, "learning_rate": 3.223717332601035e-05, "loss": 1.6547, "step": 78120 }, { "epoch": 3.57, "learning_rate": 3.223488489175706e-05, "loss": 1.7815, "step": 78130 }, { "epoch": 3.57, "learning_rate": 3.2232596457503775e-05, "loss": 1.61, "step": 78140 }, { "epoch": 3.57, "learning_rate": 3.2230308023250496e-05, "loss": 1.8252, "step": 78150 }, { "epoch": 3.57, "learning_rate": 3.222801958899721e-05, "loss": 1.9309, "step": 78160 }, { "epoch": 3.57, "learning_rate": 3.2225731154743924e-05, "loss": 1.8505, "step": 78170 }, { "epoch": 3.57, "learning_rate": 3.2223442720490645e-05, "loss": 1.7651, "step": 78180 }, { "epoch": 3.57, "learning_rate": 3.222115428623736e-05, "loss": 1.8943, "step": 78190 }, { "epoch": 3.57, "learning_rate": 3.2218865851984073e-05, "loss": 1.7037, "step": 78200 }, { "epoch": 3.57, "learning_rate": 3.2216577417730794e-05, "loss": 1.7112, "step": 78210 }, { "epoch": 3.57, "learning_rate": 3.221428898347751e-05, "loss": 1.8045, "step": 78220 }, { "epoch": 3.57, "learning_rate": 3.221200054922422e-05, "loss": 1.8397, "step": 78230 }, { "epoch": 3.57, "learning_rate": 3.220971211497094e-05, "loss": 1.6736, "step": 78240 }, { "epoch": 3.57, "learning_rate": 3.220742368071765e-05, "loss": 1.6885, "step": 78250 }, { "epoch": 3.57, "learning_rate": 3.220513524646437e-05, "loss": 1.7607, "step": 78260 }, { "epoch": 3.57, "learning_rate": 3.2202846812211086e-05, "loss": 1.7439, "step": 78270 }, { "epoch": 3.57, "learning_rate": 3.22005583779578e-05, "loss": 1.8236, "step": 78280 }, { "epoch": 3.57, "learning_rate": 3.219826994370452e-05, "loss": 1.6193, "step": 78290 }, { "epoch": 3.58, "learning_rate": 3.2195981509451235e-05, "loss": 1.653, "step": 78300 }, { "epoch": 3.58, "learning_rate": 3.219369307519795e-05, "loss": 1.7265, "step": 78310 }, { "epoch": 3.58, "learning_rate": 3.219140464094467e-05, "loss": 1.641, "step": 78320 }, { "epoch": 3.58, "learning_rate": 3.2189116206691384e-05, "loss": 1.7367, "step": 78330 }, { "epoch": 3.58, "learning_rate": 3.21868277724381e-05, "loss": 1.7823, "step": 78340 }, { "epoch": 3.58, "learning_rate": 3.218453933818482e-05, "loss": 1.6857, "step": 78350 }, { "epoch": 3.58, "learning_rate": 3.2182250903931533e-05, "loss": 1.744, "step": 78360 }, { "epoch": 3.58, "learning_rate": 3.217996246967825e-05, "loss": 1.6425, "step": 78370 }, { "epoch": 3.58, "learning_rate": 3.217767403542496e-05, "loss": 1.6687, "step": 78380 }, { "epoch": 3.58, "learning_rate": 3.217538560117168e-05, "loss": 1.673, "step": 78390 }, { "epoch": 3.58, "learning_rate": 3.21730971669184e-05, "loss": 1.9946, "step": 78400 }, { "epoch": 3.58, "learning_rate": 3.217080873266511e-05, "loss": 1.6621, "step": 78410 }, { "epoch": 3.58, "learning_rate": 3.216852029841183e-05, "loss": 1.8268, "step": 78420 }, { "epoch": 3.58, "learning_rate": 3.2166231864158546e-05, "loss": 1.9566, "step": 78430 }, { "epoch": 3.58, "learning_rate": 3.216394342990526e-05, "loss": 1.7232, "step": 78440 }, { "epoch": 3.58, "learning_rate": 3.2161654995651974e-05, "loss": 1.8616, "step": 78450 }, { "epoch": 3.58, "learning_rate": 3.215936656139869e-05, "loss": 1.7575, "step": 78460 }, { "epoch": 3.58, "learning_rate": 3.215707812714541e-05, "loss": 1.7867, "step": 78470 }, { "epoch": 3.58, "learning_rate": 3.215478969289212e-05, "loss": 1.9278, "step": 78480 }, { "epoch": 3.58, "learning_rate": 3.215250125863884e-05, "loss": 1.5214, "step": 78490 }, { "epoch": 3.58, "learning_rate": 3.215021282438556e-05, "loss": 1.6269, "step": 78500 }, { "epoch": 3.58, "learning_rate": 3.214792439013227e-05, "loss": 1.6659, "step": 78510 }, { "epoch": 3.59, "learning_rate": 3.214563595587899e-05, "loss": 1.7969, "step": 78520 }, { "epoch": 3.59, "learning_rate": 3.214334752162571e-05, "loss": 1.735, "step": 78530 }, { "epoch": 3.59, "learning_rate": 3.214105908737242e-05, "loss": 1.5842, "step": 78540 }, { "epoch": 3.59, "learning_rate": 3.2138770653119136e-05, "loss": 1.5722, "step": 78550 }, { "epoch": 3.59, "learning_rate": 3.213648221886586e-05, "loss": 1.8231, "step": 78560 }, { "epoch": 3.59, "learning_rate": 3.213419378461257e-05, "loss": 1.7593, "step": 78570 }, { "epoch": 3.59, "learning_rate": 3.2131905350359285e-05, "loss": 1.6312, "step": 78580 }, { "epoch": 3.59, "learning_rate": 3.2129616916106006e-05, "loss": 1.7949, "step": 78590 }, { "epoch": 3.59, "learning_rate": 3.212732848185272e-05, "loss": 1.7354, "step": 78600 }, { "epoch": 3.59, "learning_rate": 3.2125040047599434e-05, "loss": 1.7008, "step": 78610 }, { "epoch": 3.59, "learning_rate": 3.2122751613346155e-05, "loss": 1.7512, "step": 78620 }, { "epoch": 3.59, "learning_rate": 3.212046317909287e-05, "loss": 1.7157, "step": 78630 }, { "epoch": 3.59, "learning_rate": 3.211817474483958e-05, "loss": 1.7349, "step": 78640 }, { "epoch": 3.59, "learning_rate": 3.21158863105863e-05, "loss": 1.9493, "step": 78650 }, { "epoch": 3.59, "learning_rate": 3.211359787633301e-05, "loss": 1.872, "step": 78660 }, { "epoch": 3.59, "learning_rate": 3.2111309442079726e-05, "loss": 1.8284, "step": 78670 }, { "epoch": 3.59, "learning_rate": 3.210902100782645e-05, "loss": 1.7949, "step": 78680 }, { "epoch": 3.59, "learning_rate": 3.210673257357316e-05, "loss": 1.7201, "step": 78690 }, { "epoch": 3.59, "learning_rate": 3.2104444139319875e-05, "loss": 1.6512, "step": 78700 }, { "epoch": 3.59, "learning_rate": 3.2102155705066596e-05, "loss": 1.6697, "step": 78710 }, { "epoch": 3.59, "learning_rate": 3.209986727081331e-05, "loss": 1.7376, "step": 78720 }, { "epoch": 3.6, "learning_rate": 3.2097578836560024e-05, "loss": 1.5233, "step": 78730 }, { "epoch": 3.6, "learning_rate": 3.2095290402306745e-05, "loss": 1.6973, "step": 78740 }, { "epoch": 3.6, "learning_rate": 3.209300196805346e-05, "loss": 1.6937, "step": 78750 }, { "epoch": 3.6, "learning_rate": 3.209071353380017e-05, "loss": 1.5654, "step": 78760 }, { "epoch": 3.6, "learning_rate": 3.2088425099546894e-05, "loss": 1.9693, "step": 78770 }, { "epoch": 3.6, "learning_rate": 3.208613666529361e-05, "loss": 1.7691, "step": 78780 }, { "epoch": 3.6, "learning_rate": 3.208384823104032e-05, "loss": 1.738, "step": 78790 }, { "epoch": 3.6, "learning_rate": 3.2081559796787043e-05, "loss": 1.8671, "step": 78800 }, { "epoch": 3.6, "learning_rate": 3.207927136253376e-05, "loss": 1.7736, "step": 78810 }, { "epoch": 3.6, "learning_rate": 3.207698292828047e-05, "loss": 1.854, "step": 78820 }, { "epoch": 3.6, "learning_rate": 3.2074694494027186e-05, "loss": 1.7431, "step": 78830 }, { "epoch": 3.6, "learning_rate": 3.20724060597739e-05, "loss": 1.6381, "step": 78840 }, { "epoch": 3.6, "learning_rate": 3.207011762552062e-05, "loss": 1.5662, "step": 78850 }, { "epoch": 3.6, "learning_rate": 3.2067829191267335e-05, "loss": 1.7383, "step": 78860 }, { "epoch": 3.6, "learning_rate": 3.206554075701405e-05, "loss": 1.7753, "step": 78870 }, { "epoch": 3.6, "learning_rate": 3.206325232276077e-05, "loss": 1.743, "step": 78880 }, { "epoch": 3.6, "learning_rate": 3.2060963888507484e-05, "loss": 1.6062, "step": 78890 }, { "epoch": 3.6, "learning_rate": 3.20586754542542e-05, "loss": 1.8122, "step": 78900 }, { "epoch": 3.6, "learning_rate": 3.205638702000092e-05, "loss": 1.7238, "step": 78910 }, { "epoch": 3.6, "learning_rate": 3.205409858574763e-05, "loss": 1.5774, "step": 78920 }, { "epoch": 3.6, "learning_rate": 3.205181015149435e-05, "loss": 1.7048, "step": 78930 }, { "epoch": 3.6, "learning_rate": 3.204952171724107e-05, "loss": 1.6456, "step": 78940 }, { "epoch": 3.61, "learning_rate": 3.204723328298778e-05, "loss": 1.7713, "step": 78950 }, { "epoch": 3.61, "learning_rate": 3.20449448487345e-05, "loss": 1.8646, "step": 78960 }, { "epoch": 3.61, "learning_rate": 3.204265641448122e-05, "loss": 1.7436, "step": 78970 }, { "epoch": 3.61, "learning_rate": 3.204036798022793e-05, "loss": 1.8646, "step": 78980 }, { "epoch": 3.61, "learning_rate": 3.2038079545974646e-05, "loss": 1.5381, "step": 78990 }, { "epoch": 3.61, "learning_rate": 3.203579111172137e-05, "loss": 1.6851, "step": 79000 }, { "epoch": 3.61, "learning_rate": 3.203350267746808e-05, "loss": 1.6775, "step": 79010 }, { "epoch": 3.61, "learning_rate": 3.2031214243214795e-05, "loss": 1.587, "step": 79020 }, { "epoch": 3.61, "learning_rate": 3.202892580896151e-05, "loss": 1.7472, "step": 79030 }, { "epoch": 3.61, "learning_rate": 3.202663737470822e-05, "loss": 1.7698, "step": 79040 }, { "epoch": 3.61, "learning_rate": 3.202434894045494e-05, "loss": 1.7628, "step": 79050 }, { "epoch": 3.61, "learning_rate": 3.202206050620166e-05, "loss": 1.6506, "step": 79060 }, { "epoch": 3.61, "learning_rate": 3.201977207194837e-05, "loss": 1.6721, "step": 79070 }, { "epoch": 3.61, "learning_rate": 3.2017483637695087e-05, "loss": 1.7748, "step": 79080 }, { "epoch": 3.61, "learning_rate": 3.201519520344181e-05, "loss": 1.6905, "step": 79090 }, { "epoch": 3.61, "learning_rate": 3.201290676918852e-05, "loss": 1.7329, "step": 79100 }, { "epoch": 3.61, "learning_rate": 3.2010618334935236e-05, "loss": 1.7448, "step": 79110 }, { "epoch": 3.61, "learning_rate": 3.200832990068196e-05, "loss": 1.7547, "step": 79120 }, { "epoch": 3.61, "learning_rate": 3.200604146642867e-05, "loss": 1.8054, "step": 79130 }, { "epoch": 3.61, "learning_rate": 3.2003753032175385e-05, "loss": 1.9224, "step": 79140 }, { "epoch": 3.61, "learning_rate": 3.2001464597922106e-05, "loss": 1.7426, "step": 79150 }, { "epoch": 3.61, "learning_rate": 3.199917616366882e-05, "loss": 1.7944, "step": 79160 }, { "epoch": 3.62, "learning_rate": 3.1996887729415534e-05, "loss": 1.5406, "step": 79170 }, { "epoch": 3.62, "learning_rate": 3.1994599295162255e-05, "loss": 1.641, "step": 79180 }, { "epoch": 3.62, "learning_rate": 3.199231086090897e-05, "loss": 1.6709, "step": 79190 }, { "epoch": 3.62, "learning_rate": 3.199002242665568e-05, "loss": 1.6355, "step": 79200 }, { "epoch": 3.62, "learning_rate": 3.1987733992402404e-05, "loss": 1.6413, "step": 79210 }, { "epoch": 3.62, "learning_rate": 3.198544555814912e-05, "loss": 1.6298, "step": 79220 }, { "epoch": 3.62, "learning_rate": 3.198315712389583e-05, "loss": 1.6599, "step": 79230 }, { "epoch": 3.62, "learning_rate": 3.1980868689642547e-05, "loss": 1.6889, "step": 79240 }, { "epoch": 3.62, "learning_rate": 3.197858025538926e-05, "loss": 1.7202, "step": 79250 }, { "epoch": 3.62, "learning_rate": 3.197629182113598e-05, "loss": 1.5972, "step": 79260 }, { "epoch": 3.62, "learning_rate": 3.1974003386882696e-05, "loss": 1.7392, "step": 79270 }, { "epoch": 3.62, "learning_rate": 3.197171495262941e-05, "loss": 1.771, "step": 79280 }, { "epoch": 3.62, "learning_rate": 3.196942651837613e-05, "loss": 1.6859, "step": 79290 }, { "epoch": 3.62, "learning_rate": 3.1967138084122845e-05, "loss": 1.7934, "step": 79300 }, { "epoch": 3.62, "learning_rate": 3.196484964986956e-05, "loss": 1.7623, "step": 79310 }, { "epoch": 3.62, "learning_rate": 3.196256121561628e-05, "loss": 1.7568, "step": 79320 }, { "epoch": 3.62, "learning_rate": 3.1960272781362994e-05, "loss": 1.6847, "step": 79330 }, { "epoch": 3.62, "learning_rate": 3.195798434710971e-05, "loss": 1.7786, "step": 79340 }, { "epoch": 3.62, "learning_rate": 3.195569591285643e-05, "loss": 1.7516, "step": 79350 }, { "epoch": 3.62, "learning_rate": 3.195340747860314e-05, "loss": 1.834, "step": 79360 }, { "epoch": 3.62, "learning_rate": 3.195111904434986e-05, "loss": 1.7044, "step": 79370 }, { "epoch": 3.62, "learning_rate": 3.194883061009658e-05, "loss": 1.8721, "step": 79380 }, { "epoch": 3.63, "learning_rate": 3.194654217584329e-05, "loss": 1.6453, "step": 79390 }, { "epoch": 3.63, "learning_rate": 3.194425374159001e-05, "loss": 1.8208, "step": 79400 }, { "epoch": 3.63, "learning_rate": 3.194196530733673e-05, "loss": 1.7198, "step": 79410 }, { "epoch": 3.63, "learning_rate": 3.193967687308344e-05, "loss": 1.8161, "step": 79420 }, { "epoch": 3.63, "learning_rate": 3.193738843883015e-05, "loss": 1.7298, "step": 79430 }, { "epoch": 3.63, "learning_rate": 3.193510000457687e-05, "loss": 1.6157, "step": 79440 }, { "epoch": 3.63, "learning_rate": 3.1932811570323584e-05, "loss": 1.7968, "step": 79450 }, { "epoch": 3.63, "learning_rate": 3.19305231360703e-05, "loss": 1.6746, "step": 79460 }, { "epoch": 3.63, "learning_rate": 3.192823470181702e-05, "loss": 1.6454, "step": 79470 }, { "epoch": 3.63, "learning_rate": 3.192594626756373e-05, "loss": 1.7643, "step": 79480 }, { "epoch": 3.63, "learning_rate": 3.192365783331045e-05, "loss": 1.5588, "step": 79490 }, { "epoch": 3.63, "learning_rate": 3.192136939905717e-05, "loss": 1.6567, "step": 79500 }, { "epoch": 3.63, "learning_rate": 3.191908096480388e-05, "loss": 1.7637, "step": 79510 }, { "epoch": 3.63, "learning_rate": 3.1916792530550597e-05, "loss": 1.7612, "step": 79520 }, { "epoch": 3.63, "learning_rate": 3.191450409629732e-05, "loss": 1.6749, "step": 79530 }, { "epoch": 3.63, "learning_rate": 3.191221566204403e-05, "loss": 1.9646, "step": 79540 }, { "epoch": 3.63, "learning_rate": 3.1909927227790746e-05, "loss": 1.6654, "step": 79550 }, { "epoch": 3.63, "learning_rate": 3.190763879353747e-05, "loss": 1.6767, "step": 79560 }, { "epoch": 3.63, "learning_rate": 3.190535035928418e-05, "loss": 1.6095, "step": 79570 }, { "epoch": 3.63, "learning_rate": 3.1903061925030895e-05, "loss": 1.8197, "step": 79580 }, { "epoch": 3.63, "learning_rate": 3.1900773490777616e-05, "loss": 1.837, "step": 79590 }, { "epoch": 3.63, "learning_rate": 3.189848505652433e-05, "loss": 1.464, "step": 79600 }, { "epoch": 3.64, "learning_rate": 3.1896196622271044e-05, "loss": 1.5766, "step": 79610 }, { "epoch": 3.64, "learning_rate": 3.189390818801776e-05, "loss": 2.035, "step": 79620 }, { "epoch": 3.64, "learning_rate": 3.189161975376447e-05, "loss": 1.704, "step": 79630 }, { "epoch": 3.64, "learning_rate": 3.1889331319511186e-05, "loss": 1.6698, "step": 79640 }, { "epoch": 3.64, "learning_rate": 3.188704288525791e-05, "loss": 1.6361, "step": 79650 }, { "epoch": 3.64, "learning_rate": 3.188475445100462e-05, "loss": 1.6555, "step": 79660 }, { "epoch": 3.64, "learning_rate": 3.1882466016751336e-05, "loss": 1.4881, "step": 79670 }, { "epoch": 3.64, "learning_rate": 3.1880177582498057e-05, "loss": 1.7319, "step": 79680 }, { "epoch": 3.64, "learning_rate": 3.187788914824477e-05, "loss": 1.5828, "step": 79690 }, { "epoch": 3.64, "learning_rate": 3.1875600713991485e-05, "loss": 1.7637, "step": 79700 }, { "epoch": 3.64, "learning_rate": 3.1873312279738206e-05, "loss": 1.716, "step": 79710 }, { "epoch": 3.64, "learning_rate": 3.187102384548492e-05, "loss": 1.7771, "step": 79720 }, { "epoch": 3.64, "learning_rate": 3.1868735411231634e-05, "loss": 1.6514, "step": 79730 }, { "epoch": 3.64, "learning_rate": 3.1866446976978355e-05, "loss": 1.9115, "step": 79740 }, { "epoch": 3.64, "learning_rate": 3.186415854272507e-05, "loss": 1.6769, "step": 79750 }, { "epoch": 3.64, "learning_rate": 3.186187010847178e-05, "loss": 1.6208, "step": 79760 }, { "epoch": 3.64, "learning_rate": 3.1859581674218504e-05, "loss": 1.6505, "step": 79770 }, { "epoch": 3.64, "learning_rate": 3.185729323996522e-05, "loss": 1.7562, "step": 79780 }, { "epoch": 3.64, "learning_rate": 3.185500480571193e-05, "loss": 1.504, "step": 79790 }, { "epoch": 3.64, "learning_rate": 3.185271637145865e-05, "loss": 1.8633, "step": 79800 }, { "epoch": 3.64, "learning_rate": 3.185042793720537e-05, "loss": 1.7034, "step": 79810 }, { "epoch": 3.64, "learning_rate": 3.184813950295208e-05, "loss": 1.763, "step": 79820 }, { "epoch": 3.65, "learning_rate": 3.1845851068698796e-05, "loss": 1.7712, "step": 79830 }, { "epoch": 3.65, "learning_rate": 3.184356263444551e-05, "loss": 1.6462, "step": 79840 }, { "epoch": 3.65, "learning_rate": 3.184127420019223e-05, "loss": 1.6125, "step": 79850 }, { "epoch": 3.65, "learning_rate": 3.1838985765938945e-05, "loss": 1.659, "step": 79860 }, { "epoch": 3.65, "learning_rate": 3.183669733168566e-05, "loss": 1.868, "step": 79870 }, { "epoch": 3.65, "learning_rate": 3.183440889743238e-05, "loss": 1.6532, "step": 79880 }, { "epoch": 3.65, "learning_rate": 3.1832120463179094e-05, "loss": 1.63, "step": 79890 }, { "epoch": 3.65, "learning_rate": 3.182983202892581e-05, "loss": 1.8101, "step": 79900 }, { "epoch": 3.65, "learning_rate": 3.182754359467253e-05, "loss": 1.6435, "step": 79910 }, { "epoch": 3.65, "learning_rate": 3.182525516041924e-05, "loss": 1.7417, "step": 79920 }, { "epoch": 3.65, "learning_rate": 3.182296672616596e-05, "loss": 1.7992, "step": 79930 }, { "epoch": 3.65, "learning_rate": 3.182067829191268e-05, "loss": 1.6278, "step": 79940 }, { "epoch": 3.65, "learning_rate": 3.181838985765939e-05, "loss": 1.8091, "step": 79950 }, { "epoch": 3.65, "learning_rate": 3.1816101423406107e-05, "loss": 1.5232, "step": 79960 }, { "epoch": 3.65, "learning_rate": 3.181381298915283e-05, "loss": 1.849, "step": 79970 }, { "epoch": 3.65, "learning_rate": 3.181152455489954e-05, "loss": 1.8045, "step": 79980 }, { "epoch": 3.65, "learning_rate": 3.1809236120646256e-05, "loss": 1.9213, "step": 79990 }, { "epoch": 3.65, "learning_rate": 3.1806947686392977e-05, "loss": 1.7361, "step": 80000 }, { "epoch": 3.65, "learning_rate": 3.180465925213969e-05, "loss": 1.692, "step": 80010 }, { "epoch": 3.65, "learning_rate": 3.18023708178864e-05, "loss": 1.7046, "step": 80020 }, { "epoch": 3.65, "learning_rate": 3.180008238363312e-05, "loss": 1.687, "step": 80030 }, { "epoch": 3.65, "learning_rate": 3.179779394937983e-05, "loss": 1.7535, "step": 80040 }, { "epoch": 3.66, "learning_rate": 3.179550551512655e-05, "loss": 1.7246, "step": 80050 }, { "epoch": 3.66, "learning_rate": 3.179321708087327e-05, "loss": 1.6543, "step": 80060 }, { "epoch": 3.66, "learning_rate": 3.179092864661998e-05, "loss": 1.7095, "step": 80070 }, { "epoch": 3.66, "learning_rate": 3.1788640212366696e-05, "loss": 1.6456, "step": 80080 }, { "epoch": 3.66, "learning_rate": 3.178635177811342e-05, "loss": 1.7373, "step": 80090 }, { "epoch": 3.66, "learning_rate": 3.178406334386013e-05, "loss": 1.6079, "step": 80100 }, { "epoch": 3.66, "learning_rate": 3.1781774909606846e-05, "loss": 1.7424, "step": 80110 }, { "epoch": 3.66, "learning_rate": 3.1779486475353567e-05, "loss": 1.733, "step": 80120 }, { "epoch": 3.66, "learning_rate": 3.177719804110028e-05, "loss": 1.6096, "step": 80130 }, { "epoch": 3.66, "learning_rate": 3.1774909606846995e-05, "loss": 1.8909, "step": 80140 }, { "epoch": 3.66, "learning_rate": 3.1772621172593716e-05, "loss": 1.8812, "step": 80150 }, { "epoch": 3.66, "learning_rate": 3.177033273834043e-05, "loss": 1.7528, "step": 80160 }, { "epoch": 3.66, "learning_rate": 3.1768044304087144e-05, "loss": 1.673, "step": 80170 }, { "epoch": 3.66, "learning_rate": 3.1765755869833865e-05, "loss": 1.5345, "step": 80180 }, { "epoch": 3.66, "learning_rate": 3.176346743558058e-05, "loss": 1.6474, "step": 80190 }, { "epoch": 3.66, "learning_rate": 3.176117900132729e-05, "loss": 1.6362, "step": 80200 }, { "epoch": 3.66, "learning_rate": 3.1758890567074014e-05, "loss": 1.8387, "step": 80210 }, { "epoch": 3.66, "learning_rate": 3.175660213282072e-05, "loss": 1.6236, "step": 80220 }, { "epoch": 3.66, "learning_rate": 3.175431369856744e-05, "loss": 1.6346, "step": 80230 }, { "epoch": 3.66, "learning_rate": 3.1752025264314156e-05, "loss": 1.6658, "step": 80240 }, { "epoch": 3.66, "learning_rate": 3.174973683006087e-05, "loss": 1.7653, "step": 80250 }, { "epoch": 3.66, "learning_rate": 3.174744839580759e-05, "loss": 1.8896, "step": 80260 }, { "epoch": 3.67, "learning_rate": 3.1745159961554306e-05, "loss": 1.9045, "step": 80270 }, { "epoch": 3.67, "learning_rate": 3.174287152730102e-05, "loss": 1.7985, "step": 80280 }, { "epoch": 3.67, "learning_rate": 3.174058309304774e-05, "loss": 1.5882, "step": 80290 }, { "epoch": 3.67, "learning_rate": 3.1738294658794455e-05, "loss": 1.7835, "step": 80300 }, { "epoch": 3.67, "learning_rate": 3.173600622454117e-05, "loss": 1.9012, "step": 80310 }, { "epoch": 3.67, "learning_rate": 3.173371779028789e-05, "loss": 1.8476, "step": 80320 }, { "epoch": 3.67, "learning_rate": 3.1731429356034604e-05, "loss": 1.6826, "step": 80330 }, { "epoch": 3.67, "learning_rate": 3.172914092178132e-05, "loss": 1.6088, "step": 80340 }, { "epoch": 3.67, "learning_rate": 3.172685248752804e-05, "loss": 1.6458, "step": 80350 }, { "epoch": 3.67, "learning_rate": 3.172456405327475e-05, "loss": 1.6772, "step": 80360 }, { "epoch": 3.67, "learning_rate": 3.172227561902147e-05, "loss": 1.705, "step": 80370 }, { "epoch": 3.67, "learning_rate": 3.171998718476819e-05, "loss": 1.6897, "step": 80380 }, { "epoch": 3.67, "learning_rate": 3.17176987505149e-05, "loss": 1.527, "step": 80390 }, { "epoch": 3.67, "learning_rate": 3.1715410316261616e-05, "loss": 1.6177, "step": 80400 }, { "epoch": 3.67, "learning_rate": 3.171312188200833e-05, "loss": 1.6222, "step": 80410 }, { "epoch": 3.67, "learning_rate": 3.1710833447755045e-05, "loss": 1.7905, "step": 80420 }, { "epoch": 3.67, "learning_rate": 3.170854501350176e-05, "loss": 1.7303, "step": 80430 }, { "epoch": 3.67, "learning_rate": 3.170625657924848e-05, "loss": 1.8402, "step": 80440 }, { "epoch": 3.67, "learning_rate": 3.1703968144995194e-05, "loss": 1.9099, "step": 80450 }, { "epoch": 3.67, "learning_rate": 3.170167971074191e-05, "loss": 1.6586, "step": 80460 }, { "epoch": 3.67, "learning_rate": 3.169939127648863e-05, "loss": 1.8165, "step": 80470 }, { "epoch": 3.67, "learning_rate": 3.169710284223534e-05, "loss": 1.5715, "step": 80480 }, { "epoch": 3.68, "learning_rate": 3.169481440798206e-05, "loss": 1.7649, "step": 80490 }, { "epoch": 3.68, "learning_rate": 3.169252597372878e-05, "loss": 1.7044, "step": 80500 }, { "epoch": 3.68, "learning_rate": 3.169023753947549e-05, "loss": 1.6534, "step": 80510 }, { "epoch": 3.68, "learning_rate": 3.1687949105222206e-05, "loss": 1.6829, "step": 80520 }, { "epoch": 3.68, "learning_rate": 3.168566067096893e-05, "loss": 1.6171, "step": 80530 }, { "epoch": 3.68, "learning_rate": 3.168337223671564e-05, "loss": 1.6133, "step": 80540 }, { "epoch": 3.68, "learning_rate": 3.1681083802462356e-05, "loss": 1.7857, "step": 80550 }, { "epoch": 3.68, "learning_rate": 3.1678795368209077e-05, "loss": 1.7433, "step": 80560 }, { "epoch": 3.68, "learning_rate": 3.167650693395579e-05, "loss": 1.7628, "step": 80570 }, { "epoch": 3.68, "learning_rate": 3.1674218499702505e-05, "loss": 1.6609, "step": 80580 }, { "epoch": 3.68, "learning_rate": 3.1671930065449226e-05, "loss": 1.9172, "step": 80590 }, { "epoch": 3.68, "learning_rate": 3.166964163119594e-05, "loss": 1.6444, "step": 80600 }, { "epoch": 3.68, "learning_rate": 3.1667353196942654e-05, "loss": 1.8342, "step": 80610 }, { "epoch": 3.68, "learning_rate": 3.166506476268937e-05, "loss": 1.6791, "step": 80620 }, { "epoch": 3.68, "learning_rate": 3.166277632843608e-05, "loss": 1.6316, "step": 80630 }, { "epoch": 3.68, "learning_rate": 3.16604878941828e-05, "loss": 1.6737, "step": 80640 }, { "epoch": 3.68, "learning_rate": 3.165819945992952e-05, "loss": 1.6722, "step": 80650 }, { "epoch": 3.68, "learning_rate": 3.165591102567623e-05, "loss": 1.6593, "step": 80660 }, { "epoch": 3.68, "learning_rate": 3.165362259142295e-05, "loss": 1.7018, "step": 80670 }, { "epoch": 3.68, "learning_rate": 3.1651334157169666e-05, "loss": 1.7033, "step": 80680 }, { "epoch": 3.68, "learning_rate": 3.164904572291638e-05, "loss": 1.7136, "step": 80690 }, { "epoch": 3.68, "learning_rate": 3.1646757288663095e-05, "loss": 1.7929, "step": 80700 }, { "epoch": 3.69, "learning_rate": 3.1644468854409816e-05, "loss": 1.7608, "step": 80710 }, { "epoch": 3.69, "learning_rate": 3.164218042015653e-05, "loss": 1.7606, "step": 80720 }, { "epoch": 3.69, "learning_rate": 3.1639891985903244e-05, "loss": 1.7242, "step": 80730 }, { "epoch": 3.69, "learning_rate": 3.1637603551649965e-05, "loss": 1.4551, "step": 80740 }, { "epoch": 3.69, "learning_rate": 3.163531511739668e-05, "loss": 1.8642, "step": 80750 }, { "epoch": 3.69, "learning_rate": 3.163302668314339e-05, "loss": 1.7408, "step": 80760 }, { "epoch": 3.69, "learning_rate": 3.1630738248890114e-05, "loss": 1.5439, "step": 80770 }, { "epoch": 3.69, "learning_rate": 3.162844981463683e-05, "loss": 1.6531, "step": 80780 }, { "epoch": 3.69, "learning_rate": 3.162616138038354e-05, "loss": 1.6492, "step": 80790 }, { "epoch": 3.69, "learning_rate": 3.162387294613026e-05, "loss": 1.5163, "step": 80800 }, { "epoch": 3.69, "learning_rate": 3.162158451187697e-05, "loss": 1.7277, "step": 80810 }, { "epoch": 3.69, "learning_rate": 3.161929607762369e-05, "loss": 1.6464, "step": 80820 }, { "epoch": 3.69, "learning_rate": 3.1617007643370406e-05, "loss": 1.9339, "step": 80830 }, { "epoch": 3.69, "learning_rate": 3.161471920911712e-05, "loss": 1.6251, "step": 80840 }, { "epoch": 3.69, "learning_rate": 3.161243077486384e-05, "loss": 1.6677, "step": 80850 }, { "epoch": 3.69, "learning_rate": 3.1610142340610555e-05, "loss": 1.6393, "step": 80860 }, { "epoch": 3.69, "learning_rate": 3.160785390635727e-05, "loss": 1.5224, "step": 80870 }, { "epoch": 3.69, "learning_rate": 3.160556547210399e-05, "loss": 1.6824, "step": 80880 }, { "epoch": 3.69, "learning_rate": 3.1603277037850704e-05, "loss": 1.7353, "step": 80890 }, { "epoch": 3.69, "learning_rate": 3.160098860359742e-05, "loss": 1.5496, "step": 80900 }, { "epoch": 3.69, "learning_rate": 3.159870016934414e-05, "loss": 1.7467, "step": 80910 }, { "epoch": 3.7, "learning_rate": 3.159641173509085e-05, "loss": 1.618, "step": 80920 }, { "epoch": 3.7, "learning_rate": 3.159412330083757e-05, "loss": 1.5323, "step": 80930 }, { "epoch": 3.7, "learning_rate": 3.159183486658429e-05, "loss": 1.7675, "step": 80940 }, { "epoch": 3.7, "learning_rate": 3.1589546432331e-05, "loss": 1.7782, "step": 80950 }, { "epoch": 3.7, "learning_rate": 3.1587257998077716e-05, "loss": 1.7824, "step": 80960 }, { "epoch": 3.7, "learning_rate": 3.158496956382444e-05, "loss": 1.6069, "step": 80970 }, { "epoch": 3.7, "learning_rate": 3.158268112957115e-05, "loss": 1.9729, "step": 80980 }, { "epoch": 3.7, "learning_rate": 3.1580392695317866e-05, "loss": 1.5812, "step": 80990 }, { "epoch": 3.7, "learning_rate": 3.1578104261064586e-05, "loss": 1.8193, "step": 81000 }, { "epoch": 3.7, "learning_rate": 3.1575815826811294e-05, "loss": 1.7834, "step": 81010 }, { "epoch": 3.7, "learning_rate": 3.157352739255801e-05, "loss": 1.728, "step": 81020 }, { "epoch": 3.7, "learning_rate": 3.157123895830473e-05, "loss": 1.5743, "step": 81030 }, { "epoch": 3.7, "learning_rate": 3.156895052405144e-05, "loss": 1.7501, "step": 81040 }, { "epoch": 3.7, "learning_rate": 3.156666208979816e-05, "loss": 1.8322, "step": 81050 }, { "epoch": 3.7, "learning_rate": 3.156437365554488e-05, "loss": 1.5063, "step": 81060 }, { "epoch": 3.7, "learning_rate": 3.156208522129159e-05, "loss": 1.7336, "step": 81070 }, { "epoch": 3.7, "learning_rate": 3.1559796787038306e-05, "loss": 1.6318, "step": 81080 }, { "epoch": 3.7, "learning_rate": 3.155750835278503e-05, "loss": 1.7185, "step": 81090 }, { "epoch": 3.7, "learning_rate": 3.155521991853174e-05, "loss": 1.6347, "step": 81100 }, { "epoch": 3.7, "learning_rate": 3.1552931484278455e-05, "loss": 1.7858, "step": 81110 }, { "epoch": 3.7, "learning_rate": 3.1550643050025176e-05, "loss": 1.5991, "step": 81120 }, { "epoch": 3.7, "learning_rate": 3.154835461577189e-05, "loss": 1.7611, "step": 81130 }, { "epoch": 3.71, "learning_rate": 3.1546066181518605e-05, "loss": 1.7884, "step": 81140 }, { "epoch": 3.71, "learning_rate": 3.1543777747265326e-05, "loss": 1.8521, "step": 81150 }, { "epoch": 3.71, "learning_rate": 3.154148931301204e-05, "loss": 1.7016, "step": 81160 }, { "epoch": 3.71, "learning_rate": 3.1539200878758754e-05, "loss": 1.7399, "step": 81170 }, { "epoch": 3.71, "learning_rate": 3.1536912444505475e-05, "loss": 1.504, "step": 81180 }, { "epoch": 3.71, "learning_rate": 3.153462401025219e-05, "loss": 1.8487, "step": 81190 }, { "epoch": 3.71, "learning_rate": 3.15323355759989e-05, "loss": 1.6729, "step": 81200 }, { "epoch": 3.71, "learning_rate": 3.153004714174562e-05, "loss": 1.6674, "step": 81210 }, { "epoch": 3.71, "learning_rate": 3.152775870749233e-05, "loss": 1.7107, "step": 81220 }, { "epoch": 3.71, "learning_rate": 3.152547027323905e-05, "loss": 1.8736, "step": 81230 }, { "epoch": 3.71, "learning_rate": 3.1523181838985766e-05, "loss": 1.5285, "step": 81240 }, { "epoch": 3.71, "learning_rate": 3.152089340473248e-05, "loss": 1.7531, "step": 81250 }, { "epoch": 3.71, "learning_rate": 3.15186049704792e-05, "loss": 1.7182, "step": 81260 }, { "epoch": 3.71, "learning_rate": 3.1516316536225916e-05, "loss": 1.5656, "step": 81270 }, { "epoch": 3.71, "learning_rate": 3.151402810197263e-05, "loss": 1.6767, "step": 81280 }, { "epoch": 3.71, "learning_rate": 3.151173966771935e-05, "loss": 1.674, "step": 81290 }, { "epoch": 3.71, "learning_rate": 3.1509451233466065e-05, "loss": 1.7731, "step": 81300 }, { "epoch": 3.71, "learning_rate": 3.150716279921278e-05, "loss": 1.7528, "step": 81310 }, { "epoch": 3.71, "learning_rate": 3.15048743649595e-05, "loss": 1.8258, "step": 81320 }, { "epoch": 3.71, "learning_rate": 3.1502585930706214e-05, "loss": 1.4634, "step": 81330 }, { "epoch": 3.71, "learning_rate": 3.150029749645293e-05, "loss": 1.6209, "step": 81340 }, { "epoch": 3.71, "learning_rate": 3.149800906219965e-05, "loss": 1.7241, "step": 81350 }, { "epoch": 3.72, "learning_rate": 3.149572062794636e-05, "loss": 1.6066, "step": 81360 }, { "epoch": 3.72, "learning_rate": 3.149343219369308e-05, "loss": 1.6767, "step": 81370 }, { "epoch": 3.72, "learning_rate": 3.14911437594398e-05, "loss": 1.7907, "step": 81380 }, { "epoch": 3.72, "learning_rate": 3.148885532518651e-05, "loss": 1.623, "step": 81390 }, { "epoch": 3.72, "learning_rate": 3.148656689093322e-05, "loss": 1.6507, "step": 81400 }, { "epoch": 3.72, "learning_rate": 3.148427845667994e-05, "loss": 1.7206, "step": 81410 }, { "epoch": 3.72, "learning_rate": 3.1481990022426655e-05, "loss": 1.5754, "step": 81420 }, { "epoch": 3.72, "learning_rate": 3.147970158817337e-05, "loss": 1.7178, "step": 81430 }, { "epoch": 3.72, "learning_rate": 3.147741315392009e-05, "loss": 1.6308, "step": 81440 }, { "epoch": 3.72, "learning_rate": 3.1475124719666804e-05, "loss": 1.6237, "step": 81450 }, { "epoch": 3.72, "learning_rate": 3.147283628541352e-05, "loss": 1.767, "step": 81460 }, { "epoch": 3.72, "learning_rate": 3.147054785116024e-05, "loss": 1.7687, "step": 81470 }, { "epoch": 3.72, "learning_rate": 3.146825941690695e-05, "loss": 1.5526, "step": 81480 }, { "epoch": 3.72, "learning_rate": 3.146597098265367e-05, "loss": 1.6798, "step": 81490 }, { "epoch": 3.72, "learning_rate": 3.146368254840039e-05, "loss": 1.6001, "step": 81500 }, { "epoch": 3.72, "learning_rate": 3.14613941141471e-05, "loss": 1.8116, "step": 81510 }, { "epoch": 3.72, "learning_rate": 3.1459105679893816e-05, "loss": 1.7927, "step": 81520 }, { "epoch": 3.72, "learning_rate": 3.145681724564054e-05, "loss": 1.6901, "step": 81530 }, { "epoch": 3.72, "learning_rate": 3.145452881138725e-05, "loss": 1.7644, "step": 81540 }, { "epoch": 3.72, "learning_rate": 3.1452240377133965e-05, "loss": 1.7658, "step": 81550 }, { "epoch": 3.72, "learning_rate": 3.1449951942880686e-05, "loss": 1.6743, "step": 81560 }, { "epoch": 3.72, "learning_rate": 3.14476635086274e-05, "loss": 1.5788, "step": 81570 }, { "epoch": 3.73, "learning_rate": 3.1445375074374115e-05, "loss": 1.8203, "step": 81580 }, { "epoch": 3.73, "learning_rate": 3.1443086640120836e-05, "loss": 1.7711, "step": 81590 }, { "epoch": 3.73, "learning_rate": 3.144079820586754e-05, "loss": 1.734, "step": 81600 }, { "epoch": 3.73, "learning_rate": 3.1438509771614264e-05, "loss": 1.6819, "step": 81610 }, { "epoch": 3.73, "learning_rate": 3.143622133736098e-05, "loss": 1.6474, "step": 81620 }, { "epoch": 3.73, "learning_rate": 3.143393290310769e-05, "loss": 1.5806, "step": 81630 }, { "epoch": 3.73, "learning_rate": 3.143164446885441e-05, "loss": 1.6243, "step": 81640 }, { "epoch": 3.73, "learning_rate": 3.142935603460113e-05, "loss": 1.8209, "step": 81650 }, { "epoch": 3.73, "learning_rate": 3.142706760034784e-05, "loss": 1.6222, "step": 81660 }, { "epoch": 3.73, "learning_rate": 3.142477916609456e-05, "loss": 1.7433, "step": 81670 }, { "epoch": 3.73, "learning_rate": 3.1422490731841276e-05, "loss": 1.8153, "step": 81680 }, { "epoch": 3.73, "learning_rate": 3.142020229758799e-05, "loss": 1.6632, "step": 81690 }, { "epoch": 3.73, "learning_rate": 3.141791386333471e-05, "loss": 1.6636, "step": 81700 }, { "epoch": 3.73, "learning_rate": 3.1415625429081425e-05, "loss": 1.9988, "step": 81710 }, { "epoch": 3.73, "learning_rate": 3.141333699482814e-05, "loss": 1.6577, "step": 81720 }, { "epoch": 3.73, "learning_rate": 3.141104856057486e-05, "loss": 1.7773, "step": 81730 }, { "epoch": 3.73, "learning_rate": 3.1408760126321575e-05, "loss": 1.6758, "step": 81740 }, { "epoch": 3.73, "learning_rate": 3.140647169206829e-05, "loss": 1.6917, "step": 81750 }, { "epoch": 3.73, "learning_rate": 3.140418325781501e-05, "loss": 1.6375, "step": 81760 }, { "epoch": 3.73, "learning_rate": 3.1401894823561724e-05, "loss": 1.7704, "step": 81770 }, { "epoch": 3.73, "learning_rate": 3.139960638930844e-05, "loss": 1.7023, "step": 81780 }, { "epoch": 3.73, "learning_rate": 3.139731795505516e-05, "loss": 1.6054, "step": 81790 }, { "epoch": 3.74, "learning_rate": 3.1395029520801866e-05, "loss": 1.7034, "step": 81800 }, { "epoch": 3.74, "learning_rate": 3.139274108654858e-05, "loss": 1.7605, "step": 81810 }, { "epoch": 3.74, "learning_rate": 3.13904526522953e-05, "loss": 1.8454, "step": 81820 }, { "epoch": 3.74, "learning_rate": 3.1388164218042015e-05, "loss": 1.761, "step": 81830 }, { "epoch": 3.74, "learning_rate": 3.138587578378873e-05, "loss": 1.5993, "step": 81840 }, { "epoch": 3.74, "learning_rate": 3.138358734953545e-05, "loss": 1.8506, "step": 81850 }, { "epoch": 3.74, "learning_rate": 3.1381298915282165e-05, "loss": 1.5939, "step": 81860 }, { "epoch": 3.74, "learning_rate": 3.137901048102888e-05, "loss": 1.6816, "step": 81870 }, { "epoch": 3.74, "learning_rate": 3.13767220467756e-05, "loss": 1.8583, "step": 81880 }, { "epoch": 3.74, "learning_rate": 3.1374433612522314e-05, "loss": 1.7179, "step": 81890 }, { "epoch": 3.74, "learning_rate": 3.137214517826903e-05, "loss": 1.7715, "step": 81900 }, { "epoch": 3.74, "learning_rate": 3.136985674401575e-05, "loss": 1.4989, "step": 81910 }, { "epoch": 3.74, "learning_rate": 3.136756830976246e-05, "loss": 1.6919, "step": 81920 }, { "epoch": 3.74, "learning_rate": 3.136527987550918e-05, "loss": 1.8008, "step": 81930 }, { "epoch": 3.74, "learning_rate": 3.13629914412559e-05, "loss": 1.7039, "step": 81940 }, { "epoch": 3.74, "learning_rate": 3.136070300700261e-05, "loss": 1.8036, "step": 81950 }, { "epoch": 3.74, "learning_rate": 3.1358414572749326e-05, "loss": 1.6583, "step": 81960 }, { "epoch": 3.74, "learning_rate": 3.135612613849605e-05, "loss": 1.6724, "step": 81970 }, { "epoch": 3.74, "learning_rate": 3.135383770424276e-05, "loss": 1.815, "step": 81980 }, { "epoch": 3.74, "learning_rate": 3.135154926998947e-05, "loss": 1.6934, "step": 81990 }, { "epoch": 3.74, "learning_rate": 3.134926083573619e-05, "loss": 1.701, "step": 82000 }, { "epoch": 3.74, "learning_rate": 3.1346972401482904e-05, "loss": 1.5927, "step": 82010 }, { "epoch": 3.75, "learning_rate": 3.134468396722962e-05, "loss": 1.5452, "step": 82020 }, { "epoch": 3.75, "learning_rate": 3.134239553297634e-05, "loss": 1.4902, "step": 82030 }, { "epoch": 3.75, "learning_rate": 3.134010709872305e-05, "loss": 1.5772, "step": 82040 }, { "epoch": 3.75, "learning_rate": 3.133781866446977e-05, "loss": 1.6387, "step": 82050 }, { "epoch": 3.75, "learning_rate": 3.133553023021649e-05, "loss": 1.7656, "step": 82060 }, { "epoch": 3.75, "learning_rate": 3.13332417959632e-05, "loss": 1.653, "step": 82070 }, { "epoch": 3.75, "learning_rate": 3.1330953361709916e-05, "loss": 1.7472, "step": 82080 }, { "epoch": 3.75, "learning_rate": 3.132866492745664e-05, "loss": 1.6757, "step": 82090 }, { "epoch": 3.75, "learning_rate": 3.132637649320335e-05, "loss": 1.635, "step": 82100 }, { "epoch": 3.75, "learning_rate": 3.1324088058950065e-05, "loss": 1.6178, "step": 82110 }, { "epoch": 3.75, "learning_rate": 3.1321799624696786e-05, "loss": 1.5855, "step": 82120 }, { "epoch": 3.75, "learning_rate": 3.13195111904435e-05, "loss": 1.8114, "step": 82130 }, { "epoch": 3.75, "learning_rate": 3.1317222756190215e-05, "loss": 1.758, "step": 82140 }, { "epoch": 3.75, "learning_rate": 3.1314934321936935e-05, "loss": 1.6535, "step": 82150 }, { "epoch": 3.75, "learning_rate": 3.131264588768365e-05, "loss": 1.7444, "step": 82160 }, { "epoch": 3.75, "learning_rate": 3.1310357453430364e-05, "loss": 1.5587, "step": 82170 }, { "epoch": 3.75, "learning_rate": 3.1308069019177085e-05, "loss": 1.7497, "step": 82180 }, { "epoch": 3.75, "learning_rate": 3.130578058492379e-05, "loss": 1.5873, "step": 82190 }, { "epoch": 3.75, "learning_rate": 3.130349215067051e-05, "loss": 1.6189, "step": 82200 }, { "epoch": 3.75, "learning_rate": 3.130120371641723e-05, "loss": 1.6407, "step": 82210 }, { "epoch": 3.75, "learning_rate": 3.129891528216394e-05, "loss": 1.4916, "step": 82220 }, { "epoch": 3.75, "learning_rate": 3.129662684791066e-05, "loss": 1.6883, "step": 82230 }, { "epoch": 3.76, "learning_rate": 3.1294338413657376e-05, "loss": 1.788, "step": 82240 }, { "epoch": 3.76, "learning_rate": 3.129204997940409e-05, "loss": 1.633, "step": 82250 }, { "epoch": 3.76, "learning_rate": 3.128976154515081e-05, "loss": 1.9198, "step": 82260 }, { "epoch": 3.76, "learning_rate": 3.1287473110897525e-05, "loss": 1.6389, "step": 82270 }, { "epoch": 3.76, "learning_rate": 3.128518467664424e-05, "loss": 1.7042, "step": 82280 }, { "epoch": 3.76, "learning_rate": 3.128289624239096e-05, "loss": 1.8004, "step": 82290 }, { "epoch": 3.76, "learning_rate": 3.1280607808137675e-05, "loss": 1.67, "step": 82300 }, { "epoch": 3.76, "learning_rate": 3.127831937388439e-05, "loss": 1.657, "step": 82310 }, { "epoch": 3.76, "learning_rate": 3.127603093963111e-05, "loss": 1.5439, "step": 82320 }, { "epoch": 3.76, "learning_rate": 3.1273742505377824e-05, "loss": 1.6747, "step": 82330 }, { "epoch": 3.76, "learning_rate": 3.127145407112454e-05, "loss": 1.6395, "step": 82340 }, { "epoch": 3.76, "learning_rate": 3.126916563687126e-05, "loss": 1.7968, "step": 82350 }, { "epoch": 3.76, "learning_rate": 3.126687720261797e-05, "loss": 1.6562, "step": 82360 }, { "epoch": 3.76, "learning_rate": 3.126458876836469e-05, "loss": 1.6422, "step": 82370 }, { "epoch": 3.76, "learning_rate": 3.126230033411141e-05, "loss": 1.6019, "step": 82380 }, { "epoch": 3.76, "learning_rate": 3.1260011899858115e-05, "loss": 1.5954, "step": 82390 }, { "epoch": 3.76, "learning_rate": 3.125772346560483e-05, "loss": 1.573, "step": 82400 }, { "epoch": 3.76, "learning_rate": 3.125543503135155e-05, "loss": 1.6026, "step": 82410 }, { "epoch": 3.76, "learning_rate": 3.1253146597098264e-05, "loss": 1.7679, "step": 82420 }, { "epoch": 3.76, "learning_rate": 3.125085816284498e-05, "loss": 1.8359, "step": 82430 }, { "epoch": 3.76, "learning_rate": 3.12485697285917e-05, "loss": 1.6267, "step": 82440 }, { "epoch": 3.76, "learning_rate": 3.1246281294338414e-05, "loss": 1.4626, "step": 82450 }, { "epoch": 3.77, "learning_rate": 3.124399286008513e-05, "loss": 1.4909, "step": 82460 }, { "epoch": 3.77, "learning_rate": 3.124170442583185e-05, "loss": 1.6778, "step": 82470 }, { "epoch": 3.77, "learning_rate": 3.123941599157856e-05, "loss": 1.5586, "step": 82480 }, { "epoch": 3.77, "learning_rate": 3.123712755732528e-05, "loss": 1.7231, "step": 82490 }, { "epoch": 3.77, "learning_rate": 3.1234839123072e-05, "loss": 1.6853, "step": 82500 }, { "epoch": 3.77, "learning_rate": 3.123255068881871e-05, "loss": 1.7471, "step": 82510 }, { "epoch": 3.77, "learning_rate": 3.1230262254565426e-05, "loss": 1.7184, "step": 82520 }, { "epoch": 3.77, "learning_rate": 3.122797382031215e-05, "loss": 1.7324, "step": 82530 }, { "epoch": 3.77, "learning_rate": 3.122568538605886e-05, "loss": 1.5496, "step": 82540 }, { "epoch": 3.77, "learning_rate": 3.1223396951805575e-05, "loss": 1.6805, "step": 82550 }, { "epoch": 3.77, "learning_rate": 3.1221108517552296e-05, "loss": 1.8135, "step": 82560 }, { "epoch": 3.77, "learning_rate": 3.121882008329901e-05, "loss": 1.6365, "step": 82570 }, { "epoch": 3.77, "learning_rate": 3.1216531649045724e-05, "loss": 1.5874, "step": 82580 }, { "epoch": 3.77, "learning_rate": 3.121424321479244e-05, "loss": 1.5716, "step": 82590 }, { "epoch": 3.77, "learning_rate": 3.121195478053915e-05, "loss": 1.7651, "step": 82600 }, { "epoch": 3.77, "learning_rate": 3.1209666346285874e-05, "loss": 1.6822, "step": 82610 }, { "epoch": 3.77, "learning_rate": 3.120737791203259e-05, "loss": 1.5694, "step": 82620 }, { "epoch": 3.77, "learning_rate": 3.12050894777793e-05, "loss": 1.6999, "step": 82630 }, { "epoch": 3.77, "learning_rate": 3.120280104352602e-05, "loss": 1.6819, "step": 82640 }, { "epoch": 3.77, "learning_rate": 3.120051260927274e-05, "loss": 1.7882, "step": 82650 }, { "epoch": 3.77, "learning_rate": 3.119822417501945e-05, "loss": 1.5692, "step": 82660 }, { "epoch": 3.77, "learning_rate": 3.119593574076617e-05, "loss": 1.5775, "step": 82670 }, { "epoch": 3.78, "learning_rate": 3.1193647306512886e-05, "loss": 1.6365, "step": 82680 }, { "epoch": 3.78, "learning_rate": 3.11913588722596e-05, "loss": 1.624, "step": 82690 }, { "epoch": 3.78, "learning_rate": 3.118907043800632e-05, "loss": 1.7007, "step": 82700 }, { "epoch": 3.78, "learning_rate": 3.1186782003753035e-05, "loss": 1.6901, "step": 82710 }, { "epoch": 3.78, "learning_rate": 3.118449356949975e-05, "loss": 1.5316, "step": 82720 }, { "epoch": 3.78, "learning_rate": 3.118220513524647e-05, "loss": 1.5009, "step": 82730 }, { "epoch": 3.78, "learning_rate": 3.1179916700993185e-05, "loss": 1.6807, "step": 82740 }, { "epoch": 3.78, "learning_rate": 3.11776282667399e-05, "loss": 1.5962, "step": 82750 }, { "epoch": 3.78, "learning_rate": 3.117533983248662e-05, "loss": 1.5634, "step": 82760 }, { "epoch": 3.78, "learning_rate": 3.1173051398233334e-05, "loss": 1.8579, "step": 82770 }, { "epoch": 3.78, "learning_rate": 3.117076296398004e-05, "loss": 1.5299, "step": 82780 }, { "epoch": 3.78, "learning_rate": 3.116847452972676e-05, "loss": 1.685, "step": 82790 }, { "epoch": 3.78, "learning_rate": 3.1166186095473476e-05, "loss": 1.5467, "step": 82800 }, { "epoch": 3.78, "learning_rate": 3.116389766122019e-05, "loss": 1.6196, "step": 82810 }, { "epoch": 3.78, "learning_rate": 3.116160922696691e-05, "loss": 1.665, "step": 82820 }, { "epoch": 3.78, "learning_rate": 3.1159320792713625e-05, "loss": 1.752, "step": 82830 }, { "epoch": 3.78, "learning_rate": 3.115703235846034e-05, "loss": 1.5974, "step": 82840 }, { "epoch": 3.78, "learning_rate": 3.115474392420706e-05, "loss": 1.5332, "step": 82850 }, { "epoch": 3.78, "learning_rate": 3.1152455489953774e-05, "loss": 1.8443, "step": 82860 }, { "epoch": 3.78, "learning_rate": 3.115016705570049e-05, "loss": 1.4796, "step": 82870 }, { "epoch": 3.78, "learning_rate": 3.114787862144721e-05, "loss": 1.8343, "step": 82880 }, { "epoch": 3.78, "learning_rate": 3.1145590187193924e-05, "loss": 1.5863, "step": 82890 }, { "epoch": 3.79, "learning_rate": 3.114330175294064e-05, "loss": 1.4795, "step": 82900 }, { "epoch": 3.79, "learning_rate": 3.114101331868736e-05, "loss": 1.5357, "step": 82910 }, { "epoch": 3.79, "learning_rate": 3.113872488443407e-05, "loss": 1.7837, "step": 82920 }, { "epoch": 3.79, "learning_rate": 3.113643645018079e-05, "loss": 1.5387, "step": 82930 }, { "epoch": 3.79, "learning_rate": 3.113414801592751e-05, "loss": 1.7838, "step": 82940 }, { "epoch": 3.79, "learning_rate": 3.113185958167422e-05, "loss": 1.6952, "step": 82950 }, { "epoch": 3.79, "learning_rate": 3.1129571147420936e-05, "loss": 1.7823, "step": 82960 }, { "epoch": 3.79, "learning_rate": 3.112728271316766e-05, "loss": 1.5319, "step": 82970 }, { "epoch": 3.79, "learning_rate": 3.1124994278914364e-05, "loss": 1.4989, "step": 82980 }, { "epoch": 3.79, "learning_rate": 3.1122705844661085e-05, "loss": 1.7782, "step": 82990 }, { "epoch": 3.79, "learning_rate": 3.11204174104078e-05, "loss": 1.5685, "step": 83000 }, { "epoch": 3.79, "learning_rate": 3.1118128976154514e-05, "loss": 1.8211, "step": 83010 }, { "epoch": 3.79, "learning_rate": 3.1115840541901234e-05, "loss": 1.6047, "step": 83020 }, { "epoch": 3.79, "learning_rate": 3.111355210764795e-05, "loss": 1.7466, "step": 83030 }, { "epoch": 3.79, "learning_rate": 3.111126367339466e-05, "loss": 1.6289, "step": 83040 }, { "epoch": 3.79, "learning_rate": 3.110897523914138e-05, "loss": 1.5305, "step": 83050 }, { "epoch": 3.79, "learning_rate": 3.11066868048881e-05, "loss": 1.8272, "step": 83060 }, { "epoch": 3.79, "learning_rate": 3.110439837063481e-05, "loss": 1.5748, "step": 83070 }, { "epoch": 3.79, "learning_rate": 3.1102109936381526e-05, "loss": 1.7217, "step": 83080 }, { "epoch": 3.79, "learning_rate": 3.109982150212825e-05, "loss": 1.7479, "step": 83090 }, { "epoch": 3.79, "learning_rate": 3.109753306787496e-05, "loss": 1.808, "step": 83100 }, { "epoch": 3.8, "learning_rate": 3.1095244633621675e-05, "loss": 1.7464, "step": 83110 }, { "epoch": 3.8, "learning_rate": 3.1092956199368396e-05, "loss": 1.6409, "step": 83120 }, { "epoch": 3.8, "learning_rate": 3.109066776511511e-05, "loss": 1.526, "step": 83130 }, { "epoch": 3.8, "learning_rate": 3.1088379330861824e-05, "loss": 1.6274, "step": 83140 }, { "epoch": 3.8, "learning_rate": 3.1086090896608545e-05, "loss": 1.8098, "step": 83150 }, { "epoch": 3.8, "learning_rate": 3.108380246235526e-05, "loss": 1.5936, "step": 83160 }, { "epoch": 3.8, "learning_rate": 3.1081514028101974e-05, "loss": 1.7671, "step": 83170 }, { "epoch": 3.8, "learning_rate": 3.107922559384869e-05, "loss": 1.5984, "step": 83180 }, { "epoch": 3.8, "learning_rate": 3.10769371595954e-05, "loss": 1.7925, "step": 83190 }, { "epoch": 3.8, "learning_rate": 3.107464872534212e-05, "loss": 1.7026, "step": 83200 }, { "epoch": 3.8, "learning_rate": 3.107236029108884e-05, "loss": 1.6677, "step": 83210 }, { "epoch": 3.8, "learning_rate": 3.107007185683555e-05, "loss": 1.6125, "step": 83220 }, { "epoch": 3.8, "learning_rate": 3.106778342258227e-05, "loss": 1.7059, "step": 83230 }, { "epoch": 3.8, "learning_rate": 3.1065494988328986e-05, "loss": 1.56, "step": 83240 }, { "epoch": 3.8, "learning_rate": 3.10632065540757e-05, "loss": 1.4819, "step": 83250 }, { "epoch": 3.8, "learning_rate": 3.106091811982242e-05, "loss": 1.6025, "step": 83260 }, { "epoch": 3.8, "learning_rate": 3.1058629685569135e-05, "loss": 1.7928, "step": 83270 }, { "epoch": 3.8, "learning_rate": 3.105634125131585e-05, "loss": 1.642, "step": 83280 }, { "epoch": 3.8, "learning_rate": 3.105405281706257e-05, "loss": 1.7437, "step": 83290 }, { "epoch": 3.8, "learning_rate": 3.1051764382809284e-05, "loss": 1.6747, "step": 83300 }, { "epoch": 3.8, "learning_rate": 3.1049475948556e-05, "loss": 1.6445, "step": 83310 }, { "epoch": 3.8, "learning_rate": 3.104718751430272e-05, "loss": 1.6972, "step": 83320 }, { "epoch": 3.81, "learning_rate": 3.1044899080049434e-05, "loss": 1.6716, "step": 83330 }, { "epoch": 3.81, "learning_rate": 3.104261064579615e-05, "loss": 1.6963, "step": 83340 }, { "epoch": 3.81, "learning_rate": 3.104032221154287e-05, "loss": 1.6014, "step": 83350 }, { "epoch": 3.81, "learning_rate": 3.103803377728958e-05, "loss": 1.8577, "step": 83360 }, { "epoch": 3.81, "learning_rate": 3.10357453430363e-05, "loss": 1.6381, "step": 83370 }, { "epoch": 3.81, "learning_rate": 3.103345690878301e-05, "loss": 1.6186, "step": 83380 }, { "epoch": 3.81, "learning_rate": 3.1031168474529725e-05, "loss": 1.5379, "step": 83390 }, { "epoch": 3.81, "learning_rate": 3.102888004027644e-05, "loss": 1.833, "step": 83400 }, { "epoch": 3.81, "learning_rate": 3.102659160602316e-05, "loss": 1.7277, "step": 83410 }, { "epoch": 3.81, "learning_rate": 3.1024303171769874e-05, "loss": 1.654, "step": 83420 }, { "epoch": 3.81, "learning_rate": 3.102201473751659e-05, "loss": 1.6187, "step": 83430 }, { "epoch": 3.81, "learning_rate": 3.101972630326331e-05, "loss": 1.783, "step": 83440 }, { "epoch": 3.81, "learning_rate": 3.1017437869010024e-05, "loss": 1.5378, "step": 83450 }, { "epoch": 3.81, "learning_rate": 3.101514943475674e-05, "loss": 1.7288, "step": 83460 }, { "epoch": 3.81, "learning_rate": 3.101286100050346e-05, "loss": 1.567, "step": 83470 }, { "epoch": 3.81, "learning_rate": 3.101057256625017e-05, "loss": 1.6611, "step": 83480 }, { "epoch": 3.81, "learning_rate": 3.100828413199689e-05, "loss": 1.7133, "step": 83490 }, { "epoch": 3.81, "learning_rate": 3.100599569774361e-05, "loss": 1.7521, "step": 83500 }, { "epoch": 3.81, "learning_rate": 3.100370726349032e-05, "loss": 1.7895, "step": 83510 }, { "epoch": 3.81, "learning_rate": 3.1001418829237036e-05, "loss": 1.6213, "step": 83520 }, { "epoch": 3.81, "learning_rate": 3.099913039498376e-05, "loss": 1.6388, "step": 83530 }, { "epoch": 3.81, "learning_rate": 3.099684196073047e-05, "loss": 1.7177, "step": 83540 }, { "epoch": 3.82, "learning_rate": 3.0994553526477185e-05, "loss": 1.7598, "step": 83550 }, { "epoch": 3.82, "learning_rate": 3.0992265092223906e-05, "loss": 1.6788, "step": 83560 }, { "epoch": 3.82, "learning_rate": 3.0989976657970613e-05, "loss": 1.6986, "step": 83570 }, { "epoch": 3.82, "learning_rate": 3.0987688223717334e-05, "loss": 1.7637, "step": 83580 }, { "epoch": 3.82, "learning_rate": 3.098539978946405e-05, "loss": 1.7258, "step": 83590 }, { "epoch": 3.82, "learning_rate": 3.098311135521076e-05, "loss": 1.7008, "step": 83600 }, { "epoch": 3.82, "learning_rate": 3.0980822920957484e-05, "loss": 1.7022, "step": 83610 }, { "epoch": 3.82, "learning_rate": 3.09785344867042e-05, "loss": 1.7281, "step": 83620 }, { "epoch": 3.82, "learning_rate": 3.097624605245091e-05, "loss": 1.6605, "step": 83630 }, { "epoch": 3.82, "learning_rate": 3.097395761819763e-05, "loss": 1.67, "step": 83640 }, { "epoch": 3.82, "learning_rate": 3.097166918394435e-05, "loss": 1.5762, "step": 83650 }, { "epoch": 3.82, "learning_rate": 3.096938074969106e-05, "loss": 1.6062, "step": 83660 }, { "epoch": 3.82, "learning_rate": 3.096709231543778e-05, "loss": 1.4295, "step": 83670 }, { "epoch": 3.82, "learning_rate": 3.0964803881184496e-05, "loss": 1.8842, "step": 83680 }, { "epoch": 3.82, "learning_rate": 3.096251544693121e-05, "loss": 1.6784, "step": 83690 }, { "epoch": 3.82, "learning_rate": 3.096022701267793e-05, "loss": 1.5671, "step": 83700 }, { "epoch": 3.82, "learning_rate": 3.0957938578424645e-05, "loss": 1.7208, "step": 83710 }, { "epoch": 3.82, "learning_rate": 3.095565014417136e-05, "loss": 1.7363, "step": 83720 }, { "epoch": 3.82, "learning_rate": 3.095336170991808e-05, "loss": 1.7608, "step": 83730 }, { "epoch": 3.82, "learning_rate": 3.0951073275664794e-05, "loss": 1.5971, "step": 83740 }, { "epoch": 3.82, "learning_rate": 3.094878484141151e-05, "loss": 1.7157, "step": 83750 }, { "epoch": 3.82, "learning_rate": 3.094649640715823e-05, "loss": 1.6602, "step": 83760 }, { "epoch": 3.83, "learning_rate": 3.094420797290494e-05, "loss": 1.6828, "step": 83770 }, { "epoch": 3.83, "learning_rate": 3.094191953865165e-05, "loss": 1.6501, "step": 83780 }, { "epoch": 3.83, "learning_rate": 3.093963110439837e-05, "loss": 1.5389, "step": 83790 }, { "epoch": 3.83, "learning_rate": 3.0937342670145086e-05, "loss": 1.7561, "step": 83800 }, { "epoch": 3.83, "learning_rate": 3.09350542358918e-05, "loss": 1.6503, "step": 83810 }, { "epoch": 3.83, "learning_rate": 3.093276580163852e-05, "loss": 1.5609, "step": 83820 }, { "epoch": 3.83, "learning_rate": 3.0930477367385235e-05, "loss": 1.5995, "step": 83830 }, { "epoch": 3.83, "learning_rate": 3.092818893313195e-05, "loss": 1.6863, "step": 83840 }, { "epoch": 3.83, "learning_rate": 3.092590049887867e-05, "loss": 1.7795, "step": 83850 }, { "epoch": 3.83, "learning_rate": 3.0923612064625384e-05, "loss": 1.7387, "step": 83860 }, { "epoch": 3.83, "learning_rate": 3.09213236303721e-05, "loss": 1.7818, "step": 83870 }, { "epoch": 3.83, "learning_rate": 3.091903519611882e-05, "loss": 1.6156, "step": 83880 }, { "epoch": 3.83, "learning_rate": 3.0916746761865533e-05, "loss": 1.7276, "step": 83890 }, { "epoch": 3.83, "learning_rate": 3.091445832761225e-05, "loss": 1.836, "step": 83900 }, { "epoch": 3.83, "learning_rate": 3.091216989335897e-05, "loss": 1.6942, "step": 83910 }, { "epoch": 3.83, "learning_rate": 3.090988145910568e-05, "loss": 1.8134, "step": 83920 }, { "epoch": 3.83, "learning_rate": 3.09075930248524e-05, "loss": 1.7517, "step": 83930 }, { "epoch": 3.83, "learning_rate": 3.090530459059912e-05, "loss": 1.6189, "step": 83940 }, { "epoch": 3.83, "learning_rate": 3.090301615634583e-05, "loss": 1.6599, "step": 83950 }, { "epoch": 3.83, "learning_rate": 3.0900727722092546e-05, "loss": 1.6955, "step": 83960 }, { "epoch": 3.83, "learning_rate": 3.089843928783926e-05, "loss": 1.6144, "step": 83970 }, { "epoch": 3.83, "learning_rate": 3.0896150853585974e-05, "loss": 1.6538, "step": 83980 }, { "epoch": 3.84, "learning_rate": 3.0893862419332695e-05, "loss": 1.4867, "step": 83990 }, { "epoch": 3.84, "learning_rate": 3.089157398507941e-05, "loss": 1.6723, "step": 84000 }, { "epoch": 3.84, "learning_rate": 3.0889285550826123e-05, "loss": 1.6753, "step": 84010 }, { "epoch": 3.84, "learning_rate": 3.0886997116572844e-05, "loss": 1.7034, "step": 84020 }, { "epoch": 3.84, "learning_rate": 3.088470868231956e-05, "loss": 1.7737, "step": 84030 }, { "epoch": 3.84, "learning_rate": 3.088242024806627e-05, "loss": 1.7956, "step": 84040 }, { "epoch": 3.84, "learning_rate": 3.0880131813812994e-05, "loss": 1.7034, "step": 84050 }, { "epoch": 3.84, "learning_rate": 3.087784337955971e-05, "loss": 1.7944, "step": 84060 }, { "epoch": 3.84, "learning_rate": 3.087555494530642e-05, "loss": 1.8023, "step": 84070 }, { "epoch": 3.84, "learning_rate": 3.087326651105314e-05, "loss": 1.6165, "step": 84080 }, { "epoch": 3.84, "learning_rate": 3.087097807679986e-05, "loss": 1.6844, "step": 84090 }, { "epoch": 3.84, "learning_rate": 3.086868964254657e-05, "loss": 1.612, "step": 84100 }, { "epoch": 3.84, "learning_rate": 3.086640120829329e-05, "loss": 1.6914, "step": 84110 }, { "epoch": 3.84, "learning_rate": 3.0864112774040006e-05, "loss": 1.6658, "step": 84120 }, { "epoch": 3.84, "learning_rate": 3.086182433978672e-05, "loss": 1.457, "step": 84130 }, { "epoch": 3.84, "learning_rate": 3.0859535905533434e-05, "loss": 1.6458, "step": 84140 }, { "epoch": 3.84, "learning_rate": 3.0857247471280155e-05, "loss": 1.8724, "step": 84150 }, { "epoch": 3.84, "learning_rate": 3.085495903702687e-05, "loss": 1.7061, "step": 84160 }, { "epoch": 3.84, "learning_rate": 3.0852670602773583e-05, "loss": 1.4821, "step": 84170 }, { "epoch": 3.84, "learning_rate": 3.08503821685203e-05, "loss": 1.5547, "step": 84180 }, { "epoch": 3.84, "learning_rate": 3.084809373426701e-05, "loss": 1.7345, "step": 84190 }, { "epoch": 3.84, "learning_rate": 3.084580530001373e-05, "loss": 1.5684, "step": 84200 }, { "epoch": 3.85, "learning_rate": 3.084351686576045e-05, "loss": 2.0524, "step": 84210 }, { "epoch": 3.85, "learning_rate": 3.084122843150716e-05, "loss": 1.5196, "step": 84220 }, { "epoch": 3.85, "learning_rate": 3.083893999725388e-05, "loss": 1.6196, "step": 84230 }, { "epoch": 3.85, "learning_rate": 3.0836651563000596e-05, "loss": 1.7514, "step": 84240 }, { "epoch": 3.85, "learning_rate": 3.083436312874731e-05, "loss": 1.7514, "step": 84250 }, { "epoch": 3.85, "learning_rate": 3.083207469449403e-05, "loss": 1.4242, "step": 84260 }, { "epoch": 3.85, "learning_rate": 3.0829786260240745e-05, "loss": 1.6304, "step": 84270 }, { "epoch": 3.85, "learning_rate": 3.082749782598746e-05, "loss": 1.727, "step": 84280 }, { "epoch": 3.85, "learning_rate": 3.082520939173418e-05, "loss": 1.5617, "step": 84290 }, { "epoch": 3.85, "learning_rate": 3.0822920957480894e-05, "loss": 1.8134, "step": 84300 }, { "epoch": 3.85, "learning_rate": 3.082063252322761e-05, "loss": 1.6223, "step": 84310 }, { "epoch": 3.85, "learning_rate": 3.081834408897433e-05, "loss": 1.6478, "step": 84320 }, { "epoch": 3.85, "learning_rate": 3.0816055654721043e-05, "loss": 1.6332, "step": 84330 }, { "epoch": 3.85, "learning_rate": 3.081376722046776e-05, "loss": 1.5568, "step": 84340 }, { "epoch": 3.85, "learning_rate": 3.081147878621448e-05, "loss": 1.5463, "step": 84350 }, { "epoch": 3.85, "learning_rate": 3.0809190351961186e-05, "loss": 1.799, "step": 84360 }, { "epoch": 3.85, "learning_rate": 3.08069019177079e-05, "loss": 1.7324, "step": 84370 }, { "epoch": 3.85, "learning_rate": 3.080461348345462e-05, "loss": 1.7395, "step": 84380 }, { "epoch": 3.85, "learning_rate": 3.0802325049201335e-05, "loss": 1.7066, "step": 84390 }, { "epoch": 3.85, "learning_rate": 3.080003661494805e-05, "loss": 1.5459, "step": 84400 }, { "epoch": 3.85, "learning_rate": 3.079774818069477e-05, "loss": 1.7121, "step": 84410 }, { "epoch": 3.85, "learning_rate": 3.0795459746441484e-05, "loss": 1.5977, "step": 84420 }, { "epoch": 3.86, "learning_rate": 3.07931713121882e-05, "loss": 1.7527, "step": 84430 }, { "epoch": 3.86, "learning_rate": 3.079088287793492e-05, "loss": 1.7203, "step": 84440 }, { "epoch": 3.86, "learning_rate": 3.0788594443681633e-05, "loss": 1.4848, "step": 84450 }, { "epoch": 3.86, "learning_rate": 3.078630600942835e-05, "loss": 1.6379, "step": 84460 }, { "epoch": 3.86, "learning_rate": 3.078401757517507e-05, "loss": 1.6245, "step": 84470 }, { "epoch": 3.86, "learning_rate": 3.078172914092178e-05, "loss": 1.6054, "step": 84480 }, { "epoch": 3.86, "learning_rate": 3.07794407066685e-05, "loss": 1.6581, "step": 84490 }, { "epoch": 3.86, "learning_rate": 3.077715227241522e-05, "loss": 1.545, "step": 84500 }, { "epoch": 3.86, "learning_rate": 3.077486383816193e-05, "loss": 1.7289, "step": 84510 }, { "epoch": 3.86, "learning_rate": 3.0772575403908646e-05, "loss": 1.6425, "step": 84520 }, { "epoch": 3.86, "learning_rate": 3.077028696965537e-05, "loss": 1.5853, "step": 84530 }, { "epoch": 3.86, "learning_rate": 3.076799853540208e-05, "loss": 1.7328, "step": 84540 }, { "epoch": 3.86, "learning_rate": 3.0765710101148795e-05, "loss": 1.6162, "step": 84550 }, { "epoch": 3.86, "learning_rate": 3.076342166689551e-05, "loss": 1.7609, "step": 84560 }, { "epoch": 3.86, "learning_rate": 3.076113323264222e-05, "loss": 1.6785, "step": 84570 }, { "epoch": 3.86, "learning_rate": 3.0758844798388944e-05, "loss": 1.9292, "step": 84580 }, { "epoch": 3.86, "learning_rate": 3.075655636413566e-05, "loss": 1.7244, "step": 84590 }, { "epoch": 3.86, "learning_rate": 3.075426792988237e-05, "loss": 1.6507, "step": 84600 }, { "epoch": 3.86, "learning_rate": 3.0751979495629093e-05, "loss": 1.6977, "step": 84610 }, { "epoch": 3.86, "learning_rate": 3.074969106137581e-05, "loss": 1.715, "step": 84620 }, { "epoch": 3.86, "learning_rate": 3.074740262712252e-05, "loss": 1.7903, "step": 84630 }, { "epoch": 3.86, "learning_rate": 3.074511419286924e-05, "loss": 1.735, "step": 84640 }, { "epoch": 3.87, "learning_rate": 3.074282575861596e-05, "loss": 1.6841, "step": 84650 }, { "epoch": 3.87, "learning_rate": 3.074053732436267e-05, "loss": 1.8799, "step": 84660 }, { "epoch": 3.87, "learning_rate": 3.073824889010939e-05, "loss": 1.7009, "step": 84670 }, { "epoch": 3.87, "learning_rate": 3.0735960455856106e-05, "loss": 1.6473, "step": 84680 }, { "epoch": 3.87, "learning_rate": 3.073367202160282e-05, "loss": 1.6595, "step": 84690 }, { "epoch": 3.87, "learning_rate": 3.073138358734954e-05, "loss": 1.7458, "step": 84700 }, { "epoch": 3.87, "learning_rate": 3.0729095153096255e-05, "loss": 1.7321, "step": 84710 }, { "epoch": 3.87, "learning_rate": 3.072680671884297e-05, "loss": 1.6414, "step": 84720 }, { "epoch": 3.87, "learning_rate": 3.072451828458969e-05, "loss": 1.7265, "step": 84730 }, { "epoch": 3.87, "learning_rate": 3.0722229850336404e-05, "loss": 1.729, "step": 84740 }, { "epoch": 3.87, "learning_rate": 3.071994141608312e-05, "loss": 1.5802, "step": 84750 }, { "epoch": 3.87, "learning_rate": 3.071765298182983e-05, "loss": 1.7094, "step": 84760 }, { "epoch": 3.87, "learning_rate": 3.071536454757655e-05, "loss": 1.6529, "step": 84770 }, { "epoch": 3.87, "learning_rate": 3.071307611332326e-05, "loss": 1.5976, "step": 84780 }, { "epoch": 3.87, "learning_rate": 3.071078767906998e-05, "loss": 1.8033, "step": 84790 }, { "epoch": 3.87, "learning_rate": 3.0708499244816696e-05, "loss": 1.7758, "step": 84800 }, { "epoch": 3.87, "learning_rate": 3.070621081056341e-05, "loss": 1.6049, "step": 84810 }, { "epoch": 3.87, "learning_rate": 3.070392237631013e-05, "loss": 1.594, "step": 84820 }, { "epoch": 3.87, "learning_rate": 3.0701633942056845e-05, "loss": 1.7516, "step": 84830 }, { "epoch": 3.87, "learning_rate": 3.069934550780356e-05, "loss": 1.5464, "step": 84840 }, { "epoch": 3.87, "learning_rate": 3.069705707355028e-05, "loss": 1.7108, "step": 84850 }, { "epoch": 3.87, "learning_rate": 3.0694768639296994e-05, "loss": 1.8525, "step": 84860 }, { "epoch": 3.88, "learning_rate": 3.069248020504371e-05, "loss": 1.6978, "step": 84870 }, { "epoch": 3.88, "learning_rate": 3.069019177079043e-05, "loss": 1.7438, "step": 84880 }, { "epoch": 3.88, "learning_rate": 3.068790333653714e-05, "loss": 1.7815, "step": 84890 }, { "epoch": 3.88, "learning_rate": 3.068561490228386e-05, "loss": 1.771, "step": 84900 }, { "epoch": 3.88, "learning_rate": 3.068332646803058e-05, "loss": 1.7252, "step": 84910 }, { "epoch": 3.88, "learning_rate": 3.068103803377729e-05, "loss": 1.5607, "step": 84920 }, { "epoch": 3.88, "learning_rate": 3.067874959952401e-05, "loss": 1.5345, "step": 84930 }, { "epoch": 3.88, "learning_rate": 3.067646116527073e-05, "loss": 1.4927, "step": 84940 }, { "epoch": 3.88, "learning_rate": 3.067417273101744e-05, "loss": 1.5892, "step": 84950 }, { "epoch": 3.88, "learning_rate": 3.0671884296764156e-05, "loss": 1.8137, "step": 84960 }, { "epoch": 3.88, "learning_rate": 3.066959586251087e-05, "loss": 1.9078, "step": 84970 }, { "epoch": 3.88, "learning_rate": 3.0667307428257584e-05, "loss": 1.6342, "step": 84980 }, { "epoch": 3.88, "learning_rate": 3.0665018994004305e-05, "loss": 1.4997, "step": 84990 }, { "epoch": 3.88, "learning_rate": 3.066273055975102e-05, "loss": 1.5599, "step": 85000 }, { "epoch": 3.88, "learning_rate": 3.066044212549773e-05, "loss": 1.6207, "step": 85010 }, { "epoch": 3.88, "learning_rate": 3.0658153691244454e-05, "loss": 1.8746, "step": 85020 }, { "epoch": 3.88, "learning_rate": 3.065586525699117e-05, "loss": 1.5076, "step": 85030 }, { "epoch": 3.88, "learning_rate": 3.065357682273788e-05, "loss": 1.6283, "step": 85040 }, { "epoch": 3.88, "learning_rate": 3.06512883884846e-05, "loss": 1.647, "step": 85050 }, { "epoch": 3.88, "learning_rate": 3.064899995423132e-05, "loss": 1.7239, "step": 85060 }, { "epoch": 3.88, "learning_rate": 3.064671151997803e-05, "loss": 1.7827, "step": 85070 }, { "epoch": 3.88, "learning_rate": 3.064442308572475e-05, "loss": 1.5455, "step": 85080 }, { "epoch": 3.89, "learning_rate": 3.064213465147147e-05, "loss": 1.705, "step": 85090 }, { "epoch": 3.89, "learning_rate": 3.063984621721818e-05, "loss": 1.6369, "step": 85100 }, { "epoch": 3.89, "learning_rate": 3.06375577829649e-05, "loss": 1.7445, "step": 85110 }, { "epoch": 3.89, "learning_rate": 3.0635269348711616e-05, "loss": 1.6161, "step": 85120 }, { "epoch": 3.89, "learning_rate": 3.063298091445833e-05, "loss": 1.8026, "step": 85130 }, { "epoch": 3.89, "learning_rate": 3.063069248020505e-05, "loss": 1.5884, "step": 85140 }, { "epoch": 3.89, "learning_rate": 3.0628404045951765e-05, "loss": 1.6671, "step": 85150 }, { "epoch": 3.89, "learning_rate": 3.062611561169847e-05, "loss": 1.82, "step": 85160 }, { "epoch": 3.89, "learning_rate": 3.062382717744519e-05, "loss": 1.6002, "step": 85170 }, { "epoch": 3.89, "learning_rate": 3.062153874319191e-05, "loss": 1.6135, "step": 85180 }, { "epoch": 3.89, "learning_rate": 3.061925030893862e-05, "loss": 1.7099, "step": 85190 }, { "epoch": 3.89, "learning_rate": 3.061696187468534e-05, "loss": 1.6932, "step": 85200 }, { "epoch": 3.89, "learning_rate": 3.061467344043206e-05, "loss": 1.6769, "step": 85210 }, { "epoch": 3.89, "learning_rate": 3.061238500617877e-05, "loss": 1.5359, "step": 85220 }, { "epoch": 3.89, "learning_rate": 3.061009657192549e-05, "loss": 1.8247, "step": 85230 }, { "epoch": 3.89, "learning_rate": 3.0607808137672206e-05, "loss": 1.7253, "step": 85240 }, { "epoch": 3.89, "learning_rate": 3.060551970341892e-05, "loss": 1.7753, "step": 85250 }, { "epoch": 3.89, "learning_rate": 3.060323126916564e-05, "loss": 1.6411, "step": 85260 }, { "epoch": 3.89, "learning_rate": 3.0600942834912355e-05, "loss": 1.6344, "step": 85270 }, { "epoch": 3.89, "learning_rate": 3.059865440065907e-05, "loss": 1.6532, "step": 85280 }, { "epoch": 3.89, "learning_rate": 3.059636596640579e-05, "loss": 1.7205, "step": 85290 }, { "epoch": 3.9, "learning_rate": 3.0594077532152504e-05, "loss": 1.6934, "step": 85300 }, { "epoch": 3.9, "learning_rate": 3.059178909789922e-05, "loss": 1.4881, "step": 85310 }, { "epoch": 3.9, "learning_rate": 3.058950066364594e-05, "loss": 1.6813, "step": 85320 }, { "epoch": 3.9, "learning_rate": 3.058721222939265e-05, "loss": 1.869, "step": 85330 }, { "epoch": 3.9, "learning_rate": 3.058492379513937e-05, "loss": 1.5039, "step": 85340 }, { "epoch": 3.9, "learning_rate": 3.058263536088608e-05, "loss": 1.6176, "step": 85350 }, { "epoch": 3.9, "learning_rate": 3.0580346926632796e-05, "loss": 1.6565, "step": 85360 }, { "epoch": 3.9, "learning_rate": 3.057805849237952e-05, "loss": 1.5082, "step": 85370 }, { "epoch": 3.9, "learning_rate": 3.057577005812623e-05, "loss": 1.5932, "step": 85380 }, { "epoch": 3.9, "learning_rate": 3.0573481623872945e-05, "loss": 1.6525, "step": 85390 }, { "epoch": 3.9, "learning_rate": 3.057119318961966e-05, "loss": 1.606, "step": 85400 }, { "epoch": 3.9, "learning_rate": 3.056890475536638e-05, "loss": 1.8973, "step": 85410 }, { "epoch": 3.9, "learning_rate": 3.0566616321113094e-05, "loss": 1.5971, "step": 85420 }, { "epoch": 3.9, "learning_rate": 3.056432788685981e-05, "loss": 1.7686, "step": 85430 }, { "epoch": 3.9, "learning_rate": 3.056203945260653e-05, "loss": 1.7654, "step": 85440 }, { "epoch": 3.9, "learning_rate": 3.055975101835324e-05, "loss": 1.7091, "step": 85450 }, { "epoch": 3.9, "learning_rate": 3.055746258409996e-05, "loss": 1.6587, "step": 85460 }, { "epoch": 3.9, "learning_rate": 3.055517414984668e-05, "loss": 1.6269, "step": 85470 }, { "epoch": 3.9, "learning_rate": 3.055288571559339e-05, "loss": 1.645, "step": 85480 }, { "epoch": 3.9, "learning_rate": 3.0550597281340107e-05, "loss": 1.5314, "step": 85490 }, { "epoch": 3.9, "learning_rate": 3.054830884708683e-05, "loss": 1.6332, "step": 85500 }, { "epoch": 3.9, "learning_rate": 3.054602041283354e-05, "loss": 1.787, "step": 85510 }, { "epoch": 3.91, "learning_rate": 3.0543731978580256e-05, "loss": 1.4258, "step": 85520 }, { "epoch": 3.91, "learning_rate": 3.054144354432698e-05, "loss": 1.7134, "step": 85530 }, { "epoch": 3.91, "learning_rate": 3.053915511007369e-05, "loss": 1.8056, "step": 85540 }, { "epoch": 3.91, "learning_rate": 3.0536866675820405e-05, "loss": 1.7791, "step": 85550 }, { "epoch": 3.91, "learning_rate": 3.053457824156712e-05, "loss": 1.6683, "step": 85560 }, { "epoch": 3.91, "learning_rate": 3.053228980731383e-05, "loss": 1.6855, "step": 85570 }, { "epoch": 3.91, "learning_rate": 3.0530001373060554e-05, "loss": 1.9009, "step": 85580 }, { "epoch": 3.91, "learning_rate": 3.052771293880727e-05, "loss": 1.5061, "step": 85590 }, { "epoch": 3.91, "learning_rate": 3.052542450455398e-05, "loss": 1.7372, "step": 85600 }, { "epoch": 3.91, "learning_rate": 3.05231360703007e-05, "loss": 1.6006, "step": 85610 }, { "epoch": 3.91, "learning_rate": 3.052084763604742e-05, "loss": 1.6201, "step": 85620 }, { "epoch": 3.91, "learning_rate": 3.051855920179413e-05, "loss": 1.639, "step": 85630 }, { "epoch": 3.91, "learning_rate": 3.051627076754085e-05, "loss": 1.7628, "step": 85640 }, { "epoch": 3.91, "learning_rate": 3.0513982333287567e-05, "loss": 1.7927, "step": 85650 }, { "epoch": 3.91, "learning_rate": 3.0511693899034284e-05, "loss": 1.754, "step": 85660 }, { "epoch": 3.91, "learning_rate": 3.0509405464780998e-05, "loss": 1.7953, "step": 85670 }, { "epoch": 3.91, "learning_rate": 3.0507117030527716e-05, "loss": 1.6444, "step": 85680 }, { "epoch": 3.91, "learning_rate": 3.0504828596274433e-05, "loss": 1.7683, "step": 85690 }, { "epoch": 3.91, "learning_rate": 3.0502540162021147e-05, "loss": 1.5434, "step": 85700 }, { "epoch": 3.91, "learning_rate": 3.0500251727767865e-05, "loss": 1.732, "step": 85710 }, { "epoch": 3.91, "learning_rate": 3.0497963293514582e-05, "loss": 2.0536, "step": 85720 }, { "epoch": 3.91, "learning_rate": 3.0495674859261297e-05, "loss": 1.6742, "step": 85730 }, { "epoch": 3.92, "learning_rate": 3.0493386425008014e-05, "loss": 1.5784, "step": 85740 }, { "epoch": 3.92, "learning_rate": 3.0491097990754725e-05, "loss": 1.5983, "step": 85750 }, { "epoch": 3.92, "learning_rate": 3.0488809556501442e-05, "loss": 1.612, "step": 85760 }, { "epoch": 3.92, "learning_rate": 3.0486521122248157e-05, "loss": 1.6926, "step": 85770 }, { "epoch": 3.92, "learning_rate": 3.0484232687994874e-05, "loss": 1.6457, "step": 85780 }, { "epoch": 3.92, "learning_rate": 3.048194425374159e-05, "loss": 1.4754, "step": 85790 }, { "epoch": 3.92, "learning_rate": 3.0479655819488306e-05, "loss": 1.6927, "step": 85800 }, { "epoch": 3.92, "learning_rate": 3.0477367385235023e-05, "loss": 1.5451, "step": 85810 }, { "epoch": 3.92, "learning_rate": 3.047507895098174e-05, "loss": 1.6906, "step": 85820 }, { "epoch": 3.92, "learning_rate": 3.0472790516728455e-05, "loss": 1.73, "step": 85830 }, { "epoch": 3.92, "learning_rate": 3.0470502082475172e-05, "loss": 1.7984, "step": 85840 }, { "epoch": 3.92, "learning_rate": 3.046821364822189e-05, "loss": 1.6582, "step": 85850 }, { "epoch": 3.92, "learning_rate": 3.0465925213968604e-05, "loss": 1.6584, "step": 85860 }, { "epoch": 3.92, "learning_rate": 3.046363677971532e-05, "loss": 1.4944, "step": 85870 }, { "epoch": 3.92, "learning_rate": 3.046134834546204e-05, "loss": 1.6028, "step": 85880 }, { "epoch": 3.92, "learning_rate": 3.0459059911208753e-05, "loss": 1.7607, "step": 85890 }, { "epoch": 3.92, "learning_rate": 3.045677147695547e-05, "loss": 1.4594, "step": 85900 }, { "epoch": 3.92, "learning_rate": 3.0454483042702185e-05, "loss": 1.7084, "step": 85910 }, { "epoch": 3.92, "learning_rate": 3.0452194608448902e-05, "loss": 1.6487, "step": 85920 }, { "epoch": 3.92, "learning_rate": 3.044990617419562e-05, "loss": 1.7535, "step": 85930 }, { "epoch": 3.92, "learning_rate": 3.0447617739942334e-05, "loss": 1.5383, "step": 85940 }, { "epoch": 3.92, "learning_rate": 3.0445329305689048e-05, "loss": 1.5852, "step": 85950 }, { "epoch": 3.93, "learning_rate": 3.0443040871435762e-05, "loss": 1.7568, "step": 85960 }, { "epoch": 3.93, "learning_rate": 3.044075243718248e-05, "loss": 1.6269, "step": 85970 }, { "epoch": 3.93, "learning_rate": 3.0438464002929194e-05, "loss": 1.7477, "step": 85980 }, { "epoch": 3.93, "learning_rate": 3.043617556867591e-05, "loss": 1.6276, "step": 85990 }, { "epoch": 3.93, "learning_rate": 3.043388713442263e-05, "loss": 1.5458, "step": 86000 }, { "epoch": 3.93, "learning_rate": 3.0431598700169343e-05, "loss": 1.7662, "step": 86010 }, { "epoch": 3.93, "learning_rate": 3.042931026591606e-05, "loss": 1.6834, "step": 86020 }, { "epoch": 3.93, "learning_rate": 3.0427021831662778e-05, "loss": 1.7393, "step": 86030 }, { "epoch": 3.93, "learning_rate": 3.0424733397409492e-05, "loss": 1.4856, "step": 86040 }, { "epoch": 3.93, "learning_rate": 3.042244496315621e-05, "loss": 1.6618, "step": 86050 }, { "epoch": 3.93, "learning_rate": 3.0420156528902927e-05, "loss": 1.5722, "step": 86060 }, { "epoch": 3.93, "learning_rate": 3.041786809464964e-05, "loss": 1.6831, "step": 86070 }, { "epoch": 3.93, "learning_rate": 3.041557966039636e-05, "loss": 1.4846, "step": 86080 }, { "epoch": 3.93, "learning_rate": 3.0413291226143077e-05, "loss": 1.6754, "step": 86090 }, { "epoch": 3.93, "learning_rate": 3.041100279188979e-05, "loss": 1.7427, "step": 86100 }, { "epoch": 3.93, "learning_rate": 3.0408714357636508e-05, "loss": 1.6301, "step": 86110 }, { "epoch": 3.93, "learning_rate": 3.0406425923383226e-05, "loss": 1.7869, "step": 86120 }, { "epoch": 3.93, "learning_rate": 3.040413748912994e-05, "loss": 1.4823, "step": 86130 }, { "epoch": 3.93, "learning_rate": 3.040184905487665e-05, "loss": 1.5412, "step": 86140 }, { "epoch": 3.93, "learning_rate": 3.0399560620623368e-05, "loss": 1.6279, "step": 86150 }, { "epoch": 3.93, "learning_rate": 3.0397272186370086e-05, "loss": 1.7077, "step": 86160 }, { "epoch": 3.93, "learning_rate": 3.03949837521168e-05, "loss": 1.7416, "step": 86170 }, { "epoch": 3.94, "learning_rate": 3.0392695317863517e-05, "loss": 1.738, "step": 86180 }, { "epoch": 3.94, "learning_rate": 3.0390406883610235e-05, "loss": 1.6977, "step": 86190 }, { "epoch": 3.94, "learning_rate": 3.038811844935695e-05, "loss": 1.7493, "step": 86200 }, { "epoch": 3.94, "learning_rate": 3.0385830015103666e-05, "loss": 1.6296, "step": 86210 }, { "epoch": 3.94, "learning_rate": 3.0383541580850384e-05, "loss": 1.7824, "step": 86220 }, { "epoch": 3.94, "learning_rate": 3.0381253146597098e-05, "loss": 1.6857, "step": 86230 }, { "epoch": 3.94, "learning_rate": 3.0378964712343816e-05, "loss": 1.5389, "step": 86240 }, { "epoch": 3.94, "learning_rate": 3.0376676278090533e-05, "loss": 1.6326, "step": 86250 }, { "epoch": 3.94, "learning_rate": 3.0374387843837247e-05, "loss": 1.719, "step": 86260 }, { "epoch": 3.94, "learning_rate": 3.0372099409583965e-05, "loss": 1.623, "step": 86270 }, { "epoch": 3.94, "learning_rate": 3.0369810975330682e-05, "loss": 1.6652, "step": 86280 }, { "epoch": 3.94, "learning_rate": 3.0367522541077396e-05, "loss": 1.6218, "step": 86290 }, { "epoch": 3.94, "learning_rate": 3.0365234106824114e-05, "loss": 1.4784, "step": 86300 }, { "epoch": 3.94, "learning_rate": 3.036294567257083e-05, "loss": 1.4372, "step": 86310 }, { "epoch": 3.94, "learning_rate": 3.0360657238317546e-05, "loss": 1.5309, "step": 86320 }, { "epoch": 3.94, "learning_rate": 3.0358368804064263e-05, "loss": 1.5779, "step": 86330 }, { "epoch": 3.94, "learning_rate": 3.0356080369810974e-05, "loss": 1.5673, "step": 86340 }, { "epoch": 3.94, "learning_rate": 3.035379193555769e-05, "loss": 1.6856, "step": 86350 }, { "epoch": 3.94, "learning_rate": 3.0351503501304406e-05, "loss": 1.5261, "step": 86360 }, { "epoch": 3.94, "learning_rate": 3.0349215067051123e-05, "loss": 1.6596, "step": 86370 }, { "epoch": 3.94, "learning_rate": 3.034692663279784e-05, "loss": 1.7655, "step": 86380 }, { "epoch": 3.94, "learning_rate": 3.0344638198544555e-05, "loss": 1.5822, "step": 86390 }, { "epoch": 3.95, "learning_rate": 3.0342349764291272e-05, "loss": 1.6392, "step": 86400 }, { "epoch": 3.95, "learning_rate": 3.034006133003799e-05, "loss": 1.6509, "step": 86410 }, { "epoch": 3.95, "learning_rate": 3.0337772895784704e-05, "loss": 1.7889, "step": 86420 }, { "epoch": 3.95, "learning_rate": 3.033548446153142e-05, "loss": 1.5483, "step": 86430 }, { "epoch": 3.95, "learning_rate": 3.033319602727814e-05, "loss": 1.9879, "step": 86440 }, { "epoch": 3.95, "learning_rate": 3.0330907593024853e-05, "loss": 1.6795, "step": 86450 }, { "epoch": 3.95, "learning_rate": 3.032861915877157e-05, "loss": 1.7147, "step": 86460 }, { "epoch": 3.95, "learning_rate": 3.0326330724518288e-05, "loss": 1.6873, "step": 86470 }, { "epoch": 3.95, "learning_rate": 3.0324042290265002e-05, "loss": 1.6122, "step": 86480 }, { "epoch": 3.95, "learning_rate": 3.032175385601172e-05, "loss": 1.4737, "step": 86490 }, { "epoch": 3.95, "learning_rate": 3.0319465421758437e-05, "loss": 1.5454, "step": 86500 }, { "epoch": 3.95, "learning_rate": 3.031717698750515e-05, "loss": 1.8359, "step": 86510 }, { "epoch": 3.95, "learning_rate": 3.031488855325187e-05, "loss": 1.6495, "step": 86520 }, { "epoch": 3.95, "learning_rate": 3.0312600118998587e-05, "loss": 1.6701, "step": 86530 }, { "epoch": 3.95, "learning_rate": 3.0310311684745297e-05, "loss": 1.7506, "step": 86540 }, { "epoch": 3.95, "learning_rate": 3.030802325049201e-05, "loss": 1.7204, "step": 86550 }, { "epoch": 3.95, "learning_rate": 3.030573481623873e-05, "loss": 1.6223, "step": 86560 }, { "epoch": 3.95, "learning_rate": 3.0303446381985446e-05, "loss": 1.5498, "step": 86570 }, { "epoch": 3.95, "learning_rate": 3.030115794773216e-05, "loss": 1.7998, "step": 86580 }, { "epoch": 3.95, "learning_rate": 3.0298869513478878e-05, "loss": 1.8369, "step": 86590 }, { "epoch": 3.95, "learning_rate": 3.0296581079225596e-05, "loss": 1.6164, "step": 86600 }, { "epoch": 3.95, "learning_rate": 3.029429264497231e-05, "loss": 1.6292, "step": 86610 }, { "epoch": 3.96, "learning_rate": 3.0292004210719027e-05, "loss": 1.7606, "step": 86620 }, { "epoch": 3.96, "learning_rate": 3.0289715776465745e-05, "loss": 1.7445, "step": 86630 }, { "epoch": 3.96, "learning_rate": 3.028742734221246e-05, "loss": 1.7815, "step": 86640 }, { "epoch": 3.96, "learning_rate": 3.0285138907959176e-05, "loss": 1.4404, "step": 86650 }, { "epoch": 3.96, "learning_rate": 3.0282850473705894e-05, "loss": 1.5786, "step": 86660 }, { "epoch": 3.96, "learning_rate": 3.0280562039452608e-05, "loss": 1.5546, "step": 86670 }, { "epoch": 3.96, "learning_rate": 3.0278273605199326e-05, "loss": 1.7007, "step": 86680 }, { "epoch": 3.96, "learning_rate": 3.0275985170946043e-05, "loss": 1.7828, "step": 86690 }, { "epoch": 3.96, "learning_rate": 3.0273696736692757e-05, "loss": 1.6237, "step": 86700 }, { "epoch": 3.96, "learning_rate": 3.0271408302439475e-05, "loss": 1.6331, "step": 86710 }, { "epoch": 3.96, "learning_rate": 3.0269119868186192e-05, "loss": 1.6722, "step": 86720 }, { "epoch": 3.96, "learning_rate": 3.0266831433932906e-05, "loss": 1.5939, "step": 86730 }, { "epoch": 3.96, "learning_rate": 3.0264542999679617e-05, "loss": 1.6585, "step": 86740 }, { "epoch": 3.96, "learning_rate": 3.0262254565426335e-05, "loss": 1.8003, "step": 86750 }, { "epoch": 3.96, "learning_rate": 3.0259966131173052e-05, "loss": 1.6639, "step": 86760 }, { "epoch": 3.96, "learning_rate": 3.0257677696919766e-05, "loss": 1.7246, "step": 86770 }, { "epoch": 3.96, "learning_rate": 3.0255389262666484e-05, "loss": 1.6186, "step": 86780 }, { "epoch": 3.96, "learning_rate": 3.02531008284132e-05, "loss": 1.6269, "step": 86790 }, { "epoch": 3.96, "learning_rate": 3.0250812394159916e-05, "loss": 1.5362, "step": 86800 }, { "epoch": 3.96, "learning_rate": 3.0248523959906633e-05, "loss": 1.62, "step": 86810 }, { "epoch": 3.96, "learning_rate": 3.024623552565335e-05, "loss": 1.5075, "step": 86820 }, { "epoch": 3.96, "learning_rate": 3.0243947091400065e-05, "loss": 1.8345, "step": 86830 }, { "epoch": 3.97, "learning_rate": 3.0241658657146782e-05, "loss": 1.6664, "step": 86840 }, { "epoch": 3.97, "learning_rate": 3.02393702228935e-05, "loss": 1.6202, "step": 86850 }, { "epoch": 3.97, "learning_rate": 3.0237081788640214e-05, "loss": 1.7463, "step": 86860 }, { "epoch": 3.97, "learning_rate": 3.023479335438693e-05, "loss": 1.6416, "step": 86870 }, { "epoch": 3.97, "learning_rate": 3.023250492013365e-05, "loss": 1.5439, "step": 86880 }, { "epoch": 3.97, "learning_rate": 3.0230216485880363e-05, "loss": 1.6678, "step": 86890 }, { "epoch": 3.97, "learning_rate": 3.022792805162708e-05, "loss": 1.6058, "step": 86900 }, { "epoch": 3.97, "learning_rate": 3.0225639617373798e-05, "loss": 1.5225, "step": 86910 }, { "epoch": 3.97, "learning_rate": 3.0223351183120512e-05, "loss": 1.8399, "step": 86920 }, { "epoch": 3.97, "learning_rate": 3.0221062748867223e-05, "loss": 1.6821, "step": 86930 }, { "epoch": 3.97, "learning_rate": 3.021877431461394e-05, "loss": 1.7655, "step": 86940 }, { "epoch": 3.97, "learning_rate": 3.0216485880360658e-05, "loss": 1.7842, "step": 86950 }, { "epoch": 3.97, "learning_rate": 3.0214197446107372e-05, "loss": 1.5502, "step": 86960 }, { "epoch": 3.97, "learning_rate": 3.021190901185409e-05, "loss": 1.7538, "step": 86970 }, { "epoch": 3.97, "learning_rate": 3.0209620577600807e-05, "loss": 1.5863, "step": 86980 }, { "epoch": 3.97, "learning_rate": 3.020733214334752e-05, "loss": 1.6071, "step": 86990 }, { "epoch": 3.97, "learning_rate": 3.020504370909424e-05, "loss": 1.6945, "step": 87000 }, { "epoch": 3.97, "learning_rate": 3.0202755274840956e-05, "loss": 1.6589, "step": 87010 }, { "epoch": 3.97, "learning_rate": 3.020046684058767e-05, "loss": 1.8295, "step": 87020 }, { "epoch": 3.97, "learning_rate": 3.0198178406334388e-05, "loss": 1.5165, "step": 87030 }, { "epoch": 3.97, "learning_rate": 3.0195889972081106e-05, "loss": 1.7414, "step": 87040 }, { "epoch": 3.97, "learning_rate": 3.019360153782782e-05, "loss": 1.6973, "step": 87050 }, { "epoch": 3.98, "learning_rate": 3.0191313103574537e-05, "loss": 1.7066, "step": 87060 }, { "epoch": 3.98, "learning_rate": 3.018902466932125e-05, "loss": 1.6807, "step": 87070 }, { "epoch": 3.98, "learning_rate": 3.018673623506797e-05, "loss": 1.5679, "step": 87080 }, { "epoch": 3.98, "learning_rate": 3.0184447800814686e-05, "loss": 1.6745, "step": 87090 }, { "epoch": 3.98, "learning_rate": 3.01821593665614e-05, "loss": 1.6467, "step": 87100 }, { "epoch": 3.98, "learning_rate": 3.0179870932308118e-05, "loss": 1.9827, "step": 87110 }, { "epoch": 3.98, "learning_rate": 3.0177582498054836e-05, "loss": 1.6508, "step": 87120 }, { "epoch": 3.98, "learning_rate": 3.0175294063801546e-05, "loss": 1.7516, "step": 87130 }, { "epoch": 3.98, "learning_rate": 3.017300562954826e-05, "loss": 1.5849, "step": 87140 }, { "epoch": 3.98, "learning_rate": 3.0170717195294978e-05, "loss": 1.5829, "step": 87150 }, { "epoch": 3.98, "learning_rate": 3.0168428761041696e-05, "loss": 1.6378, "step": 87160 }, { "epoch": 3.98, "learning_rate": 3.016614032678841e-05, "loss": 1.7165, "step": 87170 }, { "epoch": 3.98, "learning_rate": 3.0163851892535127e-05, "loss": 1.5673, "step": 87180 }, { "epoch": 3.98, "learning_rate": 3.0161563458281845e-05, "loss": 1.7552, "step": 87190 }, { "epoch": 3.98, "learning_rate": 3.015927502402856e-05, "loss": 1.6957, "step": 87200 }, { "epoch": 3.98, "learning_rate": 3.0156986589775276e-05, "loss": 1.5469, "step": 87210 }, { "epoch": 3.98, "learning_rate": 3.0154698155521994e-05, "loss": 1.5555, "step": 87220 }, { "epoch": 3.98, "learning_rate": 3.0152409721268708e-05, "loss": 1.62, "step": 87230 }, { "epoch": 3.98, "learning_rate": 3.0150121287015426e-05, "loss": 1.5949, "step": 87240 }, { "epoch": 3.98, "learning_rate": 3.0147832852762143e-05, "loss": 1.6115, "step": 87250 }, { "epoch": 3.98, "learning_rate": 3.0145544418508857e-05, "loss": 1.7131, "step": 87260 }, { "epoch": 3.98, "learning_rate": 3.0143255984255575e-05, "loss": 1.6909, "step": 87270 }, { "epoch": 3.99, "learning_rate": 3.0140967550002292e-05, "loss": 1.6418, "step": 87280 }, { "epoch": 3.99, "learning_rate": 3.0138679115749006e-05, "loss": 1.8445, "step": 87290 }, { "epoch": 3.99, "learning_rate": 3.0136390681495724e-05, "loss": 1.6638, "step": 87300 }, { "epoch": 3.99, "learning_rate": 3.013410224724244e-05, "loss": 1.6223, "step": 87310 }, { "epoch": 3.99, "learning_rate": 3.0131813812989156e-05, "loss": 1.7055, "step": 87320 }, { "epoch": 3.99, "learning_rate": 3.0129525378735866e-05, "loss": 1.6185, "step": 87330 }, { "epoch": 3.99, "learning_rate": 3.0127236944482584e-05, "loss": 1.7815, "step": 87340 }, { "epoch": 3.99, "learning_rate": 3.01249485102293e-05, "loss": 1.6207, "step": 87350 }, { "epoch": 3.99, "learning_rate": 3.0122660075976015e-05, "loss": 1.6427, "step": 87360 }, { "epoch": 3.99, "learning_rate": 3.0120371641722733e-05, "loss": 1.8063, "step": 87370 }, { "epoch": 3.99, "learning_rate": 3.011808320746945e-05, "loss": 1.5952, "step": 87380 }, { "epoch": 3.99, "learning_rate": 3.0115794773216165e-05, "loss": 1.8766, "step": 87390 }, { "epoch": 3.99, "learning_rate": 3.0113506338962882e-05, "loss": 1.9096, "step": 87400 }, { "epoch": 3.99, "learning_rate": 3.01112179047096e-05, "loss": 1.7028, "step": 87410 }, { "epoch": 3.99, "learning_rate": 3.0108929470456314e-05, "loss": 1.7737, "step": 87420 }, { "epoch": 3.99, "learning_rate": 3.010664103620303e-05, "loss": 1.5473, "step": 87430 }, { "epoch": 3.99, "learning_rate": 3.010435260194975e-05, "loss": 1.5391, "step": 87440 }, { "epoch": 3.99, "learning_rate": 3.0102064167696463e-05, "loss": 1.5665, "step": 87450 }, { "epoch": 3.99, "learning_rate": 3.009977573344318e-05, "loss": 1.6052, "step": 87460 }, { "epoch": 3.99, "learning_rate": 3.0097487299189898e-05, "loss": 1.6588, "step": 87470 }, { "epoch": 3.99, "learning_rate": 3.0095198864936612e-05, "loss": 1.5633, "step": 87480 }, { "epoch": 4.0, "learning_rate": 3.009291043068333e-05, "loss": 1.5106, "step": 87490 }, { "epoch": 4.0, "learning_rate": 3.0090621996430047e-05, "loss": 1.4474, "step": 87500 }, { "epoch": 4.0, "learning_rate": 3.008833356217676e-05, "loss": 1.5856, "step": 87510 }, { "epoch": 4.0, "learning_rate": 3.008604512792348e-05, "loss": 1.635, "step": 87520 }, { "epoch": 4.0, "learning_rate": 3.008375669367019e-05, "loss": 1.4933, "step": 87530 }, { "epoch": 4.0, "learning_rate": 3.0081468259416907e-05, "loss": 1.5705, "step": 87540 }, { "epoch": 4.0, "learning_rate": 3.007917982516362e-05, "loss": 1.6868, "step": 87550 }, { "epoch": 4.0, "learning_rate": 3.007689139091034e-05, "loss": 1.6183, "step": 87560 }, { "epoch": 4.0, "learning_rate": 3.0074602956657056e-05, "loss": 1.5172, "step": 87570 }, { "epoch": 4.0, "learning_rate": 3.007231452240377e-05, "loss": 1.5305, "step": 87580 }, { "epoch": 4.0, "learning_rate": 3.0070026088150488e-05, "loss": 1.7223, "step": 87590 }, { "epoch": 4.0, "eval_cer": 0.6818398992213074, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.5164973735809326, "eval_runtime": 2527.8935, "eval_samples_per_second": 4.181, "eval_steps_per_second": 2.091, "eval_wer": 0.9927152317880795, "step": 87599 }, { "epoch": 4.0, "learning_rate": 3.0067737653897205e-05, "loss": 1.6058, "step": 87600 }, { "epoch": 4.0, "learning_rate": 3.006544921964392e-05, "loss": 1.6642, "step": 87610 }, { "epoch": 4.0, "learning_rate": 3.0063160785390637e-05, "loss": 1.515, "step": 87620 }, { "epoch": 4.0, "learning_rate": 3.0060872351137355e-05, "loss": 1.4913, "step": 87630 }, { "epoch": 4.0, "learning_rate": 3.005858391688407e-05, "loss": 1.6774, "step": 87640 }, { "epoch": 4.0, "learning_rate": 3.0056295482630786e-05, "loss": 1.5583, "step": 87650 }, { "epoch": 4.0, "learning_rate": 3.0054007048377504e-05, "loss": 1.6414, "step": 87660 }, { "epoch": 4.0, "learning_rate": 3.0051718614124218e-05, "loss": 1.6417, "step": 87670 }, { "epoch": 4.0, "learning_rate": 3.0049430179870935e-05, "loss": 1.5689, "step": 87680 }, { "epoch": 4.0, "learning_rate": 3.0047141745617653e-05, "loss": 1.5025, "step": 87690 }, { "epoch": 4.0, "learning_rate": 3.0044853311364367e-05, "loss": 1.4467, "step": 87700 }, { "epoch": 4.01, "learning_rate": 3.0042564877111085e-05, "loss": 1.5978, "step": 87710 }, { "epoch": 4.01, "learning_rate": 3.0040276442857795e-05, "loss": 1.6279, "step": 87720 }, { "epoch": 4.01, "learning_rate": 3.0037988008604513e-05, "loss": 1.747, "step": 87730 }, { "epoch": 4.01, "learning_rate": 3.0035699574351227e-05, "loss": 1.4957, "step": 87740 }, { "epoch": 4.01, "learning_rate": 3.0033411140097945e-05, "loss": 1.546, "step": 87750 }, { "epoch": 4.01, "learning_rate": 3.0031122705844662e-05, "loss": 1.6395, "step": 87760 }, { "epoch": 4.01, "learning_rate": 3.0028834271591376e-05, "loss": 1.555, "step": 87770 }, { "epoch": 4.01, "learning_rate": 3.0026545837338094e-05, "loss": 1.7399, "step": 87780 }, { "epoch": 4.01, "learning_rate": 3.002425740308481e-05, "loss": 1.5047, "step": 87790 }, { "epoch": 4.01, "learning_rate": 3.0021968968831525e-05, "loss": 1.6892, "step": 87800 }, { "epoch": 4.01, "learning_rate": 3.0019680534578243e-05, "loss": 1.6212, "step": 87810 }, { "epoch": 4.01, "learning_rate": 3.001739210032496e-05, "loss": 1.6651, "step": 87820 }, { "epoch": 4.01, "learning_rate": 3.0015103666071675e-05, "loss": 1.9467, "step": 87830 }, { "epoch": 4.01, "learning_rate": 3.0012815231818392e-05, "loss": 1.5543, "step": 87840 }, { "epoch": 4.01, "learning_rate": 3.001052679756511e-05, "loss": 1.8632, "step": 87850 }, { "epoch": 4.01, "learning_rate": 3.0008238363311824e-05, "loss": 1.4843, "step": 87860 }, { "epoch": 4.01, "learning_rate": 3.000594992905854e-05, "loss": 1.6204, "step": 87870 }, { "epoch": 4.01, "learning_rate": 3.000366149480526e-05, "loss": 1.404, "step": 87880 }, { "epoch": 4.01, "learning_rate": 3.0001373060551973e-05, "loss": 1.8729, "step": 87890 }, { "epoch": 4.01, "learning_rate": 2.999908462629869e-05, "loss": 1.6813, "step": 87900 }, { "epoch": 4.01, "learning_rate": 2.9996796192045408e-05, "loss": 1.6233, "step": 87910 }, { "epoch": 4.01, "learning_rate": 2.999450775779212e-05, "loss": 1.55, "step": 87920 }, { "epoch": 4.02, "learning_rate": 2.9992219323538833e-05, "loss": 1.7316, "step": 87930 }, { "epoch": 4.02, "learning_rate": 2.998993088928555e-05, "loss": 1.6137, "step": 87940 }, { "epoch": 4.02, "learning_rate": 2.9987642455032268e-05, "loss": 1.4431, "step": 87950 }, { "epoch": 4.02, "learning_rate": 2.9985354020778982e-05, "loss": 1.7071, "step": 87960 }, { "epoch": 4.02, "learning_rate": 2.99830655865257e-05, "loss": 1.813, "step": 87970 }, { "epoch": 4.02, "learning_rate": 2.9980777152272417e-05, "loss": 1.652, "step": 87980 }, { "epoch": 4.02, "learning_rate": 2.997848871801913e-05, "loss": 1.588, "step": 87990 }, { "epoch": 4.02, "learning_rate": 2.997620028376585e-05, "loss": 1.536, "step": 88000 }, { "epoch": 4.02, "learning_rate": 2.9973911849512566e-05, "loss": 1.71, "step": 88010 }, { "epoch": 4.02, "learning_rate": 2.997162341525928e-05, "loss": 1.5447, "step": 88020 }, { "epoch": 4.02, "learning_rate": 2.9969334981005998e-05, "loss": 1.4593, "step": 88030 }, { "epoch": 4.02, "learning_rate": 2.9967046546752715e-05, "loss": 1.6249, "step": 88040 }, { "epoch": 4.02, "learning_rate": 2.996475811249943e-05, "loss": 1.6408, "step": 88050 }, { "epoch": 4.02, "learning_rate": 2.9962469678246147e-05, "loss": 1.544, "step": 88060 }, { "epoch": 4.02, "learning_rate": 2.9960181243992865e-05, "loss": 1.5337, "step": 88070 }, { "epoch": 4.02, "learning_rate": 2.995789280973958e-05, "loss": 1.6815, "step": 88080 }, { "epoch": 4.02, "learning_rate": 2.9955604375486296e-05, "loss": 1.5452, "step": 88090 }, { "epoch": 4.02, "learning_rate": 2.9953315941233014e-05, "loss": 1.5156, "step": 88100 }, { "epoch": 4.02, "learning_rate": 2.9951027506979728e-05, "loss": 1.7065, "step": 88110 }, { "epoch": 4.02, "learning_rate": 2.994873907272644e-05, "loss": 1.4924, "step": 88120 }, { "epoch": 4.02, "learning_rate": 2.9946450638473156e-05, "loss": 1.7052, "step": 88130 }, { "epoch": 4.02, "learning_rate": 2.9944162204219874e-05, "loss": 1.6648, "step": 88140 }, { "epoch": 4.03, "learning_rate": 2.9941873769966588e-05, "loss": 1.7195, "step": 88150 }, { "epoch": 4.03, "learning_rate": 2.9939585335713305e-05, "loss": 1.7202, "step": 88160 }, { "epoch": 4.03, "learning_rate": 2.9937296901460023e-05, "loss": 1.4563, "step": 88170 }, { "epoch": 4.03, "learning_rate": 2.9935008467206737e-05, "loss": 1.6296, "step": 88180 }, { "epoch": 4.03, "learning_rate": 2.9932720032953455e-05, "loss": 1.6049, "step": 88190 }, { "epoch": 4.03, "learning_rate": 2.9930431598700172e-05, "loss": 1.6117, "step": 88200 }, { "epoch": 4.03, "learning_rate": 2.9928143164446886e-05, "loss": 1.737, "step": 88210 }, { "epoch": 4.03, "learning_rate": 2.9925854730193604e-05, "loss": 1.5077, "step": 88220 }, { "epoch": 4.03, "learning_rate": 2.992356629594032e-05, "loss": 1.7476, "step": 88230 }, { "epoch": 4.03, "learning_rate": 2.9921277861687035e-05, "loss": 1.5621, "step": 88240 }, { "epoch": 4.03, "learning_rate": 2.9918989427433753e-05, "loss": 1.4774, "step": 88250 }, { "epoch": 4.03, "learning_rate": 2.9916700993180467e-05, "loss": 1.7552, "step": 88260 }, { "epoch": 4.03, "learning_rate": 2.9914412558927185e-05, "loss": 1.6273, "step": 88270 }, { "epoch": 4.03, "learning_rate": 2.9912124124673902e-05, "loss": 1.5232, "step": 88280 }, { "epoch": 4.03, "learning_rate": 2.9909835690420616e-05, "loss": 1.7534, "step": 88290 }, { "epoch": 4.03, "learning_rate": 2.9907547256167334e-05, "loss": 1.5198, "step": 88300 }, { "epoch": 4.03, "learning_rate": 2.990525882191405e-05, "loss": 1.5461, "step": 88310 }, { "epoch": 4.03, "learning_rate": 2.9902970387660762e-05, "loss": 1.5766, "step": 88320 }, { "epoch": 4.03, "learning_rate": 2.9900681953407476e-05, "loss": 1.7234, "step": 88330 }, { "epoch": 4.03, "learning_rate": 2.9898393519154194e-05, "loss": 1.6806, "step": 88340 }, { "epoch": 4.03, "learning_rate": 2.989610508490091e-05, "loss": 1.5484, "step": 88350 }, { "epoch": 4.03, "learning_rate": 2.9893816650647625e-05, "loss": 1.8353, "step": 88360 }, { "epoch": 4.04, "learning_rate": 2.9891528216394343e-05, "loss": 1.692, "step": 88370 }, { "epoch": 4.04, "learning_rate": 2.988923978214106e-05, "loss": 1.7332, "step": 88380 }, { "epoch": 4.04, "learning_rate": 2.9886951347887775e-05, "loss": 1.4911, "step": 88390 }, { "epoch": 4.04, "learning_rate": 2.9884662913634492e-05, "loss": 1.4824, "step": 88400 }, { "epoch": 4.04, "learning_rate": 2.988237447938121e-05, "loss": 1.5983, "step": 88410 }, { "epoch": 4.04, "learning_rate": 2.9880086045127924e-05, "loss": 1.5579, "step": 88420 }, { "epoch": 4.04, "learning_rate": 2.987779761087464e-05, "loss": 1.6151, "step": 88430 }, { "epoch": 4.04, "learning_rate": 2.987550917662136e-05, "loss": 1.6898, "step": 88440 }, { "epoch": 4.04, "learning_rate": 2.9873220742368073e-05, "loss": 1.583, "step": 88450 }, { "epoch": 4.04, "learning_rate": 2.987093230811479e-05, "loss": 1.7244, "step": 88460 }, { "epoch": 4.04, "learning_rate": 2.9868643873861508e-05, "loss": 1.6819, "step": 88470 }, { "epoch": 4.04, "learning_rate": 2.9866355439608222e-05, "loss": 1.4808, "step": 88480 }, { "epoch": 4.04, "learning_rate": 2.986406700535494e-05, "loss": 1.577, "step": 88490 }, { "epoch": 4.04, "learning_rate": 2.9861778571101657e-05, "loss": 1.6059, "step": 88500 }, { "epoch": 4.04, "learning_rate": 2.9859490136848368e-05, "loss": 1.6733, "step": 88510 }, { "epoch": 4.04, "learning_rate": 2.9857201702595082e-05, "loss": 1.8003, "step": 88520 }, { "epoch": 4.04, "learning_rate": 2.98549132683418e-05, "loss": 1.773, "step": 88530 }, { "epoch": 4.04, "learning_rate": 2.9852624834088517e-05, "loss": 1.5667, "step": 88540 }, { "epoch": 4.04, "learning_rate": 2.985033639983523e-05, "loss": 1.5426, "step": 88550 }, { "epoch": 4.04, "learning_rate": 2.984804796558195e-05, "loss": 1.7076, "step": 88560 }, { "epoch": 4.04, "learning_rate": 2.9845759531328666e-05, "loss": 1.6893, "step": 88570 }, { "epoch": 4.04, "learning_rate": 2.984347109707538e-05, "loss": 1.5587, "step": 88580 }, { "epoch": 4.05, "learning_rate": 2.9841182662822098e-05, "loss": 1.6677, "step": 88590 }, { "epoch": 4.05, "learning_rate": 2.9838894228568815e-05, "loss": 1.627, "step": 88600 }, { "epoch": 4.05, "learning_rate": 2.983660579431553e-05, "loss": 1.5727, "step": 88610 }, { "epoch": 4.05, "learning_rate": 2.9834317360062247e-05, "loss": 1.5799, "step": 88620 }, { "epoch": 4.05, "learning_rate": 2.9832028925808965e-05, "loss": 1.673, "step": 88630 }, { "epoch": 4.05, "learning_rate": 2.982974049155568e-05, "loss": 1.498, "step": 88640 }, { "epoch": 4.05, "learning_rate": 2.9827452057302396e-05, "loss": 1.7921, "step": 88650 }, { "epoch": 4.05, "learning_rate": 2.9825163623049114e-05, "loss": 1.8337, "step": 88660 }, { "epoch": 4.05, "learning_rate": 2.9822875188795828e-05, "loss": 1.6338, "step": 88670 }, { "epoch": 4.05, "learning_rate": 2.9820586754542545e-05, "loss": 1.655, "step": 88680 }, { "epoch": 4.05, "learning_rate": 2.9818298320289263e-05, "loss": 1.7376, "step": 88690 }, { "epoch": 4.05, "learning_rate": 2.9816009886035977e-05, "loss": 1.6119, "step": 88700 }, { "epoch": 4.05, "learning_rate": 2.9813721451782688e-05, "loss": 1.8504, "step": 88710 }, { "epoch": 4.05, "learning_rate": 2.9811433017529405e-05, "loss": 1.5384, "step": 88720 }, { "epoch": 4.05, "learning_rate": 2.9809144583276123e-05, "loss": 1.3296, "step": 88730 }, { "epoch": 4.05, "learning_rate": 2.9806856149022837e-05, "loss": 1.6457, "step": 88740 }, { "epoch": 4.05, "learning_rate": 2.9804567714769554e-05, "loss": 1.4302, "step": 88750 }, { "epoch": 4.05, "learning_rate": 2.9802279280516272e-05, "loss": 1.5333, "step": 88760 }, { "epoch": 4.05, "learning_rate": 2.9799990846262986e-05, "loss": 1.7054, "step": 88770 }, { "epoch": 4.05, "learning_rate": 2.9797702412009704e-05, "loss": 1.561, "step": 88780 }, { "epoch": 4.05, "learning_rate": 2.979541397775642e-05, "loss": 1.6178, "step": 88790 }, { "epoch": 4.05, "learning_rate": 2.9793125543503135e-05, "loss": 1.5567, "step": 88800 }, { "epoch": 4.06, "learning_rate": 2.9790837109249853e-05, "loss": 1.5516, "step": 88810 }, { "epoch": 4.06, "learning_rate": 2.978854867499657e-05, "loss": 1.5478, "step": 88820 }, { "epoch": 4.06, "learning_rate": 2.9786260240743284e-05, "loss": 1.7108, "step": 88830 }, { "epoch": 4.06, "learning_rate": 2.9783971806490002e-05, "loss": 1.7485, "step": 88840 }, { "epoch": 4.06, "learning_rate": 2.978168337223672e-05, "loss": 1.7342, "step": 88850 }, { "epoch": 4.06, "learning_rate": 2.9779394937983434e-05, "loss": 1.5276, "step": 88860 }, { "epoch": 4.06, "learning_rate": 2.977710650373015e-05, "loss": 1.6658, "step": 88870 }, { "epoch": 4.06, "learning_rate": 2.977481806947687e-05, "loss": 1.5712, "step": 88880 }, { "epoch": 4.06, "learning_rate": 2.9772529635223583e-05, "loss": 1.5617, "step": 88890 }, { "epoch": 4.06, "learning_rate": 2.97702412009703e-05, "loss": 1.614, "step": 88900 }, { "epoch": 4.06, "learning_rate": 2.976795276671701e-05, "loss": 1.4935, "step": 88910 }, { "epoch": 4.06, "learning_rate": 2.976566433246373e-05, "loss": 1.5888, "step": 88920 }, { "epoch": 4.06, "learning_rate": 2.9763375898210443e-05, "loss": 1.5992, "step": 88930 }, { "epoch": 4.06, "learning_rate": 2.976108746395716e-05, "loss": 1.5533, "step": 88940 }, { "epoch": 4.06, "learning_rate": 2.9758799029703878e-05, "loss": 1.6539, "step": 88950 }, { "epoch": 4.06, "learning_rate": 2.9756510595450592e-05, "loss": 1.7197, "step": 88960 }, { "epoch": 4.06, "learning_rate": 2.975422216119731e-05, "loss": 1.7354, "step": 88970 }, { "epoch": 4.06, "learning_rate": 2.9751933726944027e-05, "loss": 1.6111, "step": 88980 }, { "epoch": 4.06, "learning_rate": 2.974964529269074e-05, "loss": 1.4696, "step": 88990 }, { "epoch": 4.06, "learning_rate": 2.974735685843746e-05, "loss": 1.5134, "step": 89000 }, { "epoch": 4.06, "learning_rate": 2.9745068424184176e-05, "loss": 1.6195, "step": 89010 }, { "epoch": 4.06, "learning_rate": 2.974277998993089e-05, "loss": 1.4644, "step": 89020 }, { "epoch": 4.07, "learning_rate": 2.9740491555677608e-05, "loss": 1.5829, "step": 89030 }, { "epoch": 4.07, "learning_rate": 2.9738203121424325e-05, "loss": 1.644, "step": 89040 }, { "epoch": 4.07, "learning_rate": 2.973591468717104e-05, "loss": 1.7075, "step": 89050 }, { "epoch": 4.07, "learning_rate": 2.9733626252917757e-05, "loss": 1.5127, "step": 89060 }, { "epoch": 4.07, "learning_rate": 2.9731337818664474e-05, "loss": 1.7181, "step": 89070 }, { "epoch": 4.07, "learning_rate": 2.972904938441119e-05, "loss": 1.6624, "step": 89080 }, { "epoch": 4.07, "learning_rate": 2.9726760950157906e-05, "loss": 1.5107, "step": 89090 }, { "epoch": 4.07, "learning_rate": 2.9724472515904624e-05, "loss": 1.7092, "step": 89100 }, { "epoch": 4.07, "learning_rate": 2.9722184081651334e-05, "loss": 1.5535, "step": 89110 }, { "epoch": 4.07, "learning_rate": 2.971989564739805e-05, "loss": 1.5471, "step": 89120 }, { "epoch": 4.07, "learning_rate": 2.9717607213144766e-05, "loss": 1.6098, "step": 89130 }, { "epoch": 4.07, "learning_rate": 2.9715318778891484e-05, "loss": 1.5977, "step": 89140 }, { "epoch": 4.07, "learning_rate": 2.9713030344638198e-05, "loss": 1.6538, "step": 89150 }, { "epoch": 4.07, "learning_rate": 2.9710741910384915e-05, "loss": 1.3991, "step": 89160 }, { "epoch": 4.07, "learning_rate": 2.9708453476131633e-05, "loss": 1.5042, "step": 89170 }, { "epoch": 4.07, "learning_rate": 2.9706165041878347e-05, "loss": 1.5046, "step": 89180 }, { "epoch": 4.07, "learning_rate": 2.9703876607625064e-05, "loss": 1.5288, "step": 89190 }, { "epoch": 4.07, "learning_rate": 2.9701588173371782e-05, "loss": 1.6307, "step": 89200 }, { "epoch": 4.07, "learning_rate": 2.9699299739118496e-05, "loss": 1.6575, "step": 89210 }, { "epoch": 4.07, "learning_rate": 2.9697011304865214e-05, "loss": 1.5651, "step": 89220 }, { "epoch": 4.07, "learning_rate": 2.969472287061193e-05, "loss": 1.556, "step": 89230 }, { "epoch": 4.07, "learning_rate": 2.9692434436358645e-05, "loss": 1.4788, "step": 89240 }, { "epoch": 4.08, "learning_rate": 2.9690146002105363e-05, "loss": 1.6269, "step": 89250 }, { "epoch": 4.08, "learning_rate": 2.968785756785208e-05, "loss": 1.6832, "step": 89260 }, { "epoch": 4.08, "learning_rate": 2.9685569133598794e-05, "loss": 1.7149, "step": 89270 }, { "epoch": 4.08, "learning_rate": 2.9683280699345512e-05, "loss": 1.7446, "step": 89280 }, { "epoch": 4.08, "learning_rate": 2.968099226509223e-05, "loss": 1.6888, "step": 89290 }, { "epoch": 4.08, "learning_rate": 2.967870383083894e-05, "loss": 1.5062, "step": 89300 }, { "epoch": 4.08, "learning_rate": 2.9676415396585654e-05, "loss": 1.4473, "step": 89310 }, { "epoch": 4.08, "learning_rate": 2.9674126962332372e-05, "loss": 1.5455, "step": 89320 }, { "epoch": 4.08, "learning_rate": 2.967183852807909e-05, "loss": 1.6269, "step": 89330 }, { "epoch": 4.08, "learning_rate": 2.9669550093825804e-05, "loss": 1.6664, "step": 89340 }, { "epoch": 4.08, "learning_rate": 2.966726165957252e-05, "loss": 1.6416, "step": 89350 }, { "epoch": 4.08, "learning_rate": 2.966497322531924e-05, "loss": 1.7098, "step": 89360 }, { "epoch": 4.08, "learning_rate": 2.9662684791065953e-05, "loss": 1.5563, "step": 89370 }, { "epoch": 4.08, "learning_rate": 2.966039635681267e-05, "loss": 1.5773, "step": 89380 }, { "epoch": 4.08, "learning_rate": 2.9658107922559388e-05, "loss": 1.6699, "step": 89390 }, { "epoch": 4.08, "learning_rate": 2.9655819488306102e-05, "loss": 1.7407, "step": 89400 }, { "epoch": 4.08, "learning_rate": 2.965353105405282e-05, "loss": 1.5262, "step": 89410 }, { "epoch": 4.08, "learning_rate": 2.9651242619799534e-05, "loss": 1.6582, "step": 89420 }, { "epoch": 4.08, "learning_rate": 2.964895418554625e-05, "loss": 1.5006, "step": 89430 }, { "epoch": 4.08, "learning_rate": 2.964666575129297e-05, "loss": 1.776, "step": 89440 }, { "epoch": 4.08, "learning_rate": 2.9644377317039683e-05, "loss": 1.6808, "step": 89450 }, { "epoch": 4.08, "learning_rate": 2.96420888827864e-05, "loss": 1.8453, "step": 89460 }, { "epoch": 4.09, "learning_rate": 2.9639800448533118e-05, "loss": 1.5945, "step": 89470 }, { "epoch": 4.09, "learning_rate": 2.9637512014279832e-05, "loss": 1.4575, "step": 89480 }, { "epoch": 4.09, "learning_rate": 2.963522358002655e-05, "loss": 1.5191, "step": 89490 }, { "epoch": 4.09, "learning_rate": 2.963293514577326e-05, "loss": 1.5919, "step": 89500 }, { "epoch": 4.09, "learning_rate": 2.9630646711519978e-05, "loss": 1.6006, "step": 89510 }, { "epoch": 4.09, "learning_rate": 2.9628358277266692e-05, "loss": 1.5169, "step": 89520 }, { "epoch": 4.09, "learning_rate": 2.962606984301341e-05, "loss": 1.7331, "step": 89530 }, { "epoch": 4.09, "learning_rate": 2.9623781408760127e-05, "loss": 1.7273, "step": 89540 }, { "epoch": 4.09, "learning_rate": 2.962149297450684e-05, "loss": 1.4912, "step": 89550 }, { "epoch": 4.09, "learning_rate": 2.961920454025356e-05, "loss": 1.7244, "step": 89560 }, { "epoch": 4.09, "learning_rate": 2.9616916106000276e-05, "loss": 1.6485, "step": 89570 }, { "epoch": 4.09, "learning_rate": 2.961462767174699e-05, "loss": 1.6798, "step": 89580 }, { "epoch": 4.09, "learning_rate": 2.9612339237493708e-05, "loss": 1.8036, "step": 89590 }, { "epoch": 4.09, "learning_rate": 2.9610050803240425e-05, "loss": 1.6745, "step": 89600 }, { "epoch": 4.09, "learning_rate": 2.960776236898714e-05, "loss": 1.5506, "step": 89610 }, { "epoch": 4.09, "learning_rate": 2.9605473934733857e-05, "loss": 1.7151, "step": 89620 }, { "epoch": 4.09, "learning_rate": 2.9603185500480574e-05, "loss": 1.4857, "step": 89630 }, { "epoch": 4.09, "learning_rate": 2.960089706622729e-05, "loss": 1.6192, "step": 89640 }, { "epoch": 4.09, "learning_rate": 2.9598608631974006e-05, "loss": 1.8109, "step": 89650 }, { "epoch": 4.09, "learning_rate": 2.9596320197720724e-05, "loss": 1.5617, "step": 89660 }, { "epoch": 4.09, "learning_rate": 2.9594031763467438e-05, "loss": 1.8367, "step": 89670 }, { "epoch": 4.1, "learning_rate": 2.9591743329214155e-05, "loss": 1.5013, "step": 89680 }, { "epoch": 4.1, "learning_rate": 2.9589454894960873e-05, "loss": 1.5209, "step": 89690 }, { "epoch": 4.1, "learning_rate": 2.9587166460707583e-05, "loss": 1.5, "step": 89700 }, { "epoch": 4.1, "learning_rate": 2.9584878026454298e-05, "loss": 1.5249, "step": 89710 }, { "epoch": 4.1, "learning_rate": 2.9582589592201015e-05, "loss": 1.7686, "step": 89720 }, { "epoch": 4.1, "learning_rate": 2.9580301157947733e-05, "loss": 1.5118, "step": 89730 }, { "epoch": 4.1, "learning_rate": 2.9578012723694447e-05, "loss": 1.8181, "step": 89740 }, { "epoch": 4.1, "learning_rate": 2.9575724289441164e-05, "loss": 1.6721, "step": 89750 }, { "epoch": 4.1, "learning_rate": 2.9573435855187882e-05, "loss": 1.6422, "step": 89760 }, { "epoch": 4.1, "learning_rate": 2.9571147420934596e-05, "loss": 1.726, "step": 89770 }, { "epoch": 4.1, "learning_rate": 2.9568858986681314e-05, "loss": 1.5659, "step": 89780 }, { "epoch": 4.1, "learning_rate": 2.956657055242803e-05, "loss": 1.6924, "step": 89790 }, { "epoch": 4.1, "learning_rate": 2.9564282118174745e-05, "loss": 1.6014, "step": 89800 }, { "epoch": 4.1, "learning_rate": 2.9561993683921463e-05, "loss": 1.5429, "step": 89810 }, { "epoch": 4.1, "learning_rate": 2.955970524966818e-05, "loss": 1.6576, "step": 89820 }, { "epoch": 4.1, "learning_rate": 2.9557416815414894e-05, "loss": 1.6656, "step": 89830 }, { "epoch": 4.1, "learning_rate": 2.9555128381161612e-05, "loss": 1.6844, "step": 89840 }, { "epoch": 4.1, "learning_rate": 2.955283994690833e-05, "loss": 1.6505, "step": 89850 }, { "epoch": 4.1, "learning_rate": 2.9550551512655044e-05, "loss": 1.5167, "step": 89860 }, { "epoch": 4.1, "learning_rate": 2.954826307840176e-05, "loss": 1.736, "step": 89870 }, { "epoch": 4.1, "learning_rate": 2.954597464414848e-05, "loss": 1.65, "step": 89880 }, { "epoch": 4.1, "learning_rate": 2.9543686209895193e-05, "loss": 1.4882, "step": 89890 }, { "epoch": 4.11, "learning_rate": 2.9541397775641903e-05, "loss": 1.5897, "step": 89900 }, { "epoch": 4.11, "learning_rate": 2.953910934138862e-05, "loss": 1.5653, "step": 89910 }, { "epoch": 4.11, "learning_rate": 2.953682090713534e-05, "loss": 1.5358, "step": 89920 }, { "epoch": 4.11, "learning_rate": 2.9534532472882053e-05, "loss": 1.5458, "step": 89930 }, { "epoch": 4.11, "learning_rate": 2.953224403862877e-05, "loss": 1.5037, "step": 89940 }, { "epoch": 4.11, "learning_rate": 2.9529955604375488e-05, "loss": 1.7023, "step": 89950 }, { "epoch": 4.11, "learning_rate": 2.9527667170122202e-05, "loss": 1.5806, "step": 89960 }, { "epoch": 4.11, "learning_rate": 2.952537873586892e-05, "loss": 1.6666, "step": 89970 }, { "epoch": 4.11, "learning_rate": 2.9523090301615637e-05, "loss": 1.5803, "step": 89980 }, { "epoch": 4.11, "learning_rate": 2.952080186736235e-05, "loss": 1.638, "step": 89990 }, { "epoch": 4.11, "learning_rate": 2.951851343310907e-05, "loss": 1.7259, "step": 90000 }, { "epoch": 4.11, "learning_rate": 2.9516224998855786e-05, "loss": 1.7302, "step": 90010 }, { "epoch": 4.11, "learning_rate": 2.95139365646025e-05, "loss": 1.8281, "step": 90020 }, { "epoch": 4.11, "learning_rate": 2.9511648130349218e-05, "loss": 1.5418, "step": 90030 }, { "epoch": 4.11, "learning_rate": 2.9509359696095935e-05, "loss": 1.594, "step": 90040 }, { "epoch": 4.11, "learning_rate": 2.950707126184265e-05, "loss": 1.5045, "step": 90050 }, { "epoch": 4.11, "learning_rate": 2.9504782827589367e-05, "loss": 1.6001, "step": 90060 }, { "epoch": 4.11, "learning_rate": 2.9502494393336084e-05, "loss": 1.5128, "step": 90070 }, { "epoch": 4.11, "learning_rate": 2.95002059590828e-05, "loss": 1.8503, "step": 90080 }, { "epoch": 4.11, "learning_rate": 2.949791752482951e-05, "loss": 1.4494, "step": 90090 }, { "epoch": 4.11, "learning_rate": 2.9495629090576227e-05, "loss": 1.4855, "step": 90100 }, { "epoch": 4.11, "learning_rate": 2.9493340656322944e-05, "loss": 1.6261, "step": 90110 }, { "epoch": 4.12, "learning_rate": 2.949105222206966e-05, "loss": 1.5007, "step": 90120 }, { "epoch": 4.12, "learning_rate": 2.9488763787816376e-05, "loss": 1.6707, "step": 90130 }, { "epoch": 4.12, "learning_rate": 2.9486475353563093e-05, "loss": 1.5906, "step": 90140 }, { "epoch": 4.12, "learning_rate": 2.9484186919309808e-05, "loss": 1.5587, "step": 90150 }, { "epoch": 4.12, "learning_rate": 2.9481898485056525e-05, "loss": 1.6343, "step": 90160 }, { "epoch": 4.12, "learning_rate": 2.9479610050803243e-05, "loss": 1.6528, "step": 90170 }, { "epoch": 4.12, "learning_rate": 2.9477321616549957e-05, "loss": 1.5567, "step": 90180 }, { "epoch": 4.12, "learning_rate": 2.9475033182296674e-05, "loss": 1.7595, "step": 90190 }, { "epoch": 4.12, "learning_rate": 2.9472744748043392e-05, "loss": 1.5947, "step": 90200 }, { "epoch": 4.12, "learning_rate": 2.9470456313790106e-05, "loss": 1.6933, "step": 90210 }, { "epoch": 4.12, "learning_rate": 2.9468167879536823e-05, "loss": 1.4655, "step": 90220 }, { "epoch": 4.12, "learning_rate": 2.946587944528354e-05, "loss": 1.7048, "step": 90230 }, { "epoch": 4.12, "learning_rate": 2.9463591011030255e-05, "loss": 1.5934, "step": 90240 }, { "epoch": 4.12, "learning_rate": 2.9461302576776973e-05, "loss": 1.7105, "step": 90250 }, { "epoch": 4.12, "learning_rate": 2.945901414252369e-05, "loss": 1.496, "step": 90260 }, { "epoch": 4.12, "learning_rate": 2.9456725708270404e-05, "loss": 1.6259, "step": 90270 }, { "epoch": 4.12, "learning_rate": 2.9454437274017122e-05, "loss": 1.6077, "step": 90280 }, { "epoch": 4.12, "learning_rate": 2.9452148839763833e-05, "loss": 1.6257, "step": 90290 }, { "epoch": 4.12, "learning_rate": 2.944986040551055e-05, "loss": 1.5729, "step": 90300 }, { "epoch": 4.12, "learning_rate": 2.9447571971257264e-05, "loss": 1.6937, "step": 90310 }, { "epoch": 4.12, "learning_rate": 2.9445283537003982e-05, "loss": 1.7651, "step": 90320 }, { "epoch": 4.12, "learning_rate": 2.94429951027507e-05, "loss": 1.6173, "step": 90330 }, { "epoch": 4.13, "learning_rate": 2.9440706668497413e-05, "loss": 1.5981, "step": 90340 }, { "epoch": 4.13, "learning_rate": 2.943841823424413e-05, "loss": 1.5611, "step": 90350 }, { "epoch": 4.13, "learning_rate": 2.943612979999085e-05, "loss": 1.748, "step": 90360 }, { "epoch": 4.13, "learning_rate": 2.9433841365737563e-05, "loss": 1.5399, "step": 90370 }, { "epoch": 4.13, "learning_rate": 2.943155293148428e-05, "loss": 1.6477, "step": 90380 }, { "epoch": 4.13, "learning_rate": 2.9429264497230998e-05, "loss": 1.5997, "step": 90390 }, { "epoch": 4.13, "learning_rate": 2.9426976062977712e-05, "loss": 1.6201, "step": 90400 }, { "epoch": 4.13, "learning_rate": 2.942468762872443e-05, "loss": 1.6057, "step": 90410 }, { "epoch": 4.13, "learning_rate": 2.9422399194471147e-05, "loss": 1.5379, "step": 90420 }, { "epoch": 4.13, "learning_rate": 2.942011076021786e-05, "loss": 1.5635, "step": 90430 }, { "epoch": 4.13, "learning_rate": 2.941782232596458e-05, "loss": 1.571, "step": 90440 }, { "epoch": 4.13, "learning_rate": 2.9415533891711296e-05, "loss": 1.7956, "step": 90450 }, { "epoch": 4.13, "learning_rate": 2.941324545745801e-05, "loss": 1.4528, "step": 90460 }, { "epoch": 4.13, "learning_rate": 2.9410957023204728e-05, "loss": 1.6396, "step": 90470 }, { "epoch": 4.13, "learning_rate": 2.9408668588951445e-05, "loss": 1.7243, "step": 90480 }, { "epoch": 4.13, "learning_rate": 2.9406380154698156e-05, "loss": 1.5693, "step": 90490 }, { "epoch": 4.13, "learning_rate": 2.940409172044487e-05, "loss": 1.6276, "step": 90500 }, { "epoch": 4.13, "learning_rate": 2.9401803286191588e-05, "loss": 1.5687, "step": 90510 }, { "epoch": 4.13, "learning_rate": 2.9399514851938305e-05, "loss": 1.7281, "step": 90520 }, { "epoch": 4.13, "learning_rate": 2.939722641768502e-05, "loss": 1.3782, "step": 90530 }, { "epoch": 4.13, "learning_rate": 2.9394937983431737e-05, "loss": 1.5117, "step": 90540 }, { "epoch": 4.13, "learning_rate": 2.9392649549178454e-05, "loss": 1.6134, "step": 90550 }, { "epoch": 4.14, "learning_rate": 2.939036111492517e-05, "loss": 1.5856, "step": 90560 }, { "epoch": 4.14, "learning_rate": 2.9388072680671886e-05, "loss": 1.5675, "step": 90570 }, { "epoch": 4.14, "learning_rate": 2.93857842464186e-05, "loss": 1.5726, "step": 90580 }, { "epoch": 4.14, "learning_rate": 2.9383495812165318e-05, "loss": 1.6238, "step": 90590 }, { "epoch": 4.14, "learning_rate": 2.9381207377912035e-05, "loss": 1.5165, "step": 90600 }, { "epoch": 4.14, "learning_rate": 2.937891894365875e-05, "loss": 1.568, "step": 90610 }, { "epoch": 4.14, "learning_rate": 2.9376630509405467e-05, "loss": 1.6953, "step": 90620 }, { "epoch": 4.14, "learning_rate": 2.9374342075152184e-05, "loss": 1.6043, "step": 90630 }, { "epoch": 4.14, "learning_rate": 2.93720536408989e-05, "loss": 1.685, "step": 90640 }, { "epoch": 4.14, "learning_rate": 2.9369765206645616e-05, "loss": 1.5287, "step": 90650 }, { "epoch": 4.14, "learning_rate": 2.9367476772392333e-05, "loss": 1.4323, "step": 90660 }, { "epoch": 4.14, "learning_rate": 2.9365188338139048e-05, "loss": 1.5111, "step": 90670 }, { "epoch": 4.14, "learning_rate": 2.9362899903885765e-05, "loss": 1.5382, "step": 90680 }, { "epoch": 4.14, "learning_rate": 2.9360611469632476e-05, "loss": 1.6518, "step": 90690 }, { "epoch": 4.14, "learning_rate": 2.9358323035379193e-05, "loss": 1.5429, "step": 90700 }, { "epoch": 4.14, "learning_rate": 2.9356034601125907e-05, "loss": 1.5269, "step": 90710 }, { "epoch": 4.14, "learning_rate": 2.9353746166872625e-05, "loss": 1.5022, "step": 90720 }, { "epoch": 4.14, "learning_rate": 2.9351457732619343e-05, "loss": 1.6171, "step": 90730 }, { "epoch": 4.14, "learning_rate": 2.9349169298366057e-05, "loss": 1.6097, "step": 90740 }, { "epoch": 4.14, "learning_rate": 2.9346880864112774e-05, "loss": 1.6537, "step": 90750 }, { "epoch": 4.14, "learning_rate": 2.9344592429859492e-05, "loss": 1.8302, "step": 90760 }, { "epoch": 4.14, "learning_rate": 2.9342303995606206e-05, "loss": 1.5933, "step": 90770 }, { "epoch": 4.15, "learning_rate": 2.9340015561352923e-05, "loss": 1.5059, "step": 90780 }, { "epoch": 4.15, "learning_rate": 2.933772712709964e-05, "loss": 1.5552, "step": 90790 }, { "epoch": 4.15, "learning_rate": 2.9335438692846355e-05, "loss": 1.5171, "step": 90800 }, { "epoch": 4.15, "learning_rate": 2.9333150258593073e-05, "loss": 1.809, "step": 90810 }, { "epoch": 4.15, "learning_rate": 2.933086182433979e-05, "loss": 1.5575, "step": 90820 }, { "epoch": 4.15, "learning_rate": 2.9328573390086504e-05, "loss": 1.6339, "step": 90830 }, { "epoch": 4.15, "learning_rate": 2.9326284955833222e-05, "loss": 1.5416, "step": 90840 }, { "epoch": 4.15, "learning_rate": 2.932399652157994e-05, "loss": 1.4808, "step": 90850 }, { "epoch": 4.15, "learning_rate": 2.9321708087326653e-05, "loss": 1.5939, "step": 90860 }, { "epoch": 4.15, "learning_rate": 2.931941965307337e-05, "loss": 1.6779, "step": 90870 }, { "epoch": 4.15, "learning_rate": 2.931713121882008e-05, "loss": 1.7831, "step": 90880 }, { "epoch": 4.15, "learning_rate": 2.93148427845668e-05, "loss": 1.6184, "step": 90890 }, { "epoch": 4.15, "learning_rate": 2.9312554350313513e-05, "loss": 1.5788, "step": 90900 }, { "epoch": 4.15, "learning_rate": 2.931026591606023e-05, "loss": 1.7051, "step": 90910 }, { "epoch": 4.15, "learning_rate": 2.930797748180695e-05, "loss": 1.5066, "step": 90920 }, { "epoch": 4.15, "learning_rate": 2.9305689047553662e-05, "loss": 1.5428, "step": 90930 }, { "epoch": 4.15, "learning_rate": 2.930340061330038e-05, "loss": 1.633, "step": 90940 }, { "epoch": 4.15, "learning_rate": 2.9301112179047098e-05, "loss": 1.5276, "step": 90950 }, { "epoch": 4.15, "learning_rate": 2.929882374479381e-05, "loss": 1.6924, "step": 90960 }, { "epoch": 4.15, "learning_rate": 2.929653531054053e-05, "loss": 1.6032, "step": 90970 }, { "epoch": 4.15, "learning_rate": 2.9294246876287247e-05, "loss": 1.7186, "step": 90980 }, { "epoch": 4.15, "learning_rate": 2.929195844203396e-05, "loss": 1.6856, "step": 90990 }, { "epoch": 4.16, "learning_rate": 2.928967000778068e-05, "loss": 1.6446, "step": 91000 }, { "epoch": 4.16, "learning_rate": 2.9287381573527396e-05, "loss": 1.5387, "step": 91010 }, { "epoch": 4.16, "learning_rate": 2.928509313927411e-05, "loss": 1.588, "step": 91020 }, { "epoch": 4.16, "learning_rate": 2.9282804705020828e-05, "loss": 1.7174, "step": 91030 }, { "epoch": 4.16, "learning_rate": 2.9280516270767545e-05, "loss": 1.5483, "step": 91040 }, { "epoch": 4.16, "learning_rate": 2.927822783651426e-05, "loss": 1.7592, "step": 91050 }, { "epoch": 4.16, "learning_rate": 2.9275939402260977e-05, "loss": 1.6054, "step": 91060 }, { "epoch": 4.16, "learning_rate": 2.9273650968007694e-05, "loss": 1.4672, "step": 91070 }, { "epoch": 4.16, "learning_rate": 2.9271362533754405e-05, "loss": 1.6935, "step": 91080 }, { "epoch": 4.16, "learning_rate": 2.926907409950112e-05, "loss": 1.6718, "step": 91090 }, { "epoch": 4.16, "learning_rate": 2.9266785665247837e-05, "loss": 1.6261, "step": 91100 }, { "epoch": 4.16, "learning_rate": 2.9264497230994554e-05, "loss": 1.4914, "step": 91110 }, { "epoch": 4.16, "learning_rate": 2.9262208796741268e-05, "loss": 1.5984, "step": 91120 }, { "epoch": 4.16, "learning_rate": 2.9259920362487986e-05, "loss": 1.6487, "step": 91130 }, { "epoch": 4.16, "learning_rate": 2.9257631928234703e-05, "loss": 1.5235, "step": 91140 }, { "epoch": 4.16, "learning_rate": 2.9255343493981417e-05, "loss": 1.5168, "step": 91150 }, { "epoch": 4.16, "learning_rate": 2.9253055059728135e-05, "loss": 1.5863, "step": 91160 }, { "epoch": 4.16, "learning_rate": 2.9250766625474853e-05, "loss": 1.5598, "step": 91170 }, { "epoch": 4.16, "learning_rate": 2.9248478191221567e-05, "loss": 1.5499, "step": 91180 }, { "epoch": 4.16, "learning_rate": 2.9246189756968284e-05, "loss": 1.6048, "step": 91190 }, { "epoch": 4.16, "learning_rate": 2.9243901322715e-05, "loss": 1.7318, "step": 91200 }, { "epoch": 4.16, "learning_rate": 2.9241612888461716e-05, "loss": 1.6455, "step": 91210 }, { "epoch": 4.17, "learning_rate": 2.9239324454208433e-05, "loss": 1.5231, "step": 91220 }, { "epoch": 4.17, "learning_rate": 2.923703601995515e-05, "loss": 1.4737, "step": 91230 }, { "epoch": 4.17, "learning_rate": 2.9234747585701865e-05, "loss": 1.5916, "step": 91240 }, { "epoch": 4.17, "learning_rate": 2.9232459151448583e-05, "loss": 1.7536, "step": 91250 }, { "epoch": 4.17, "learning_rate": 2.92301707171953e-05, "loss": 1.5858, "step": 91260 }, { "epoch": 4.17, "learning_rate": 2.9227882282942014e-05, "loss": 1.4919, "step": 91270 }, { "epoch": 4.17, "learning_rate": 2.9225593848688725e-05, "loss": 1.4859, "step": 91280 }, { "epoch": 4.17, "learning_rate": 2.9223305414435442e-05, "loss": 1.5554, "step": 91290 }, { "epoch": 4.17, "learning_rate": 2.922101698018216e-05, "loss": 1.5909, "step": 91300 }, { "epoch": 4.17, "learning_rate": 2.9218728545928874e-05, "loss": 1.5487, "step": 91310 }, { "epoch": 4.17, "learning_rate": 2.921644011167559e-05, "loss": 1.4409, "step": 91320 }, { "epoch": 4.17, "learning_rate": 2.921415167742231e-05, "loss": 1.3442, "step": 91330 }, { "epoch": 4.17, "learning_rate": 2.9211863243169023e-05, "loss": 1.491, "step": 91340 }, { "epoch": 4.17, "learning_rate": 2.920957480891574e-05, "loss": 1.7525, "step": 91350 }, { "epoch": 4.17, "learning_rate": 2.920728637466246e-05, "loss": 1.5401, "step": 91360 }, { "epoch": 4.17, "learning_rate": 2.9204997940409172e-05, "loss": 1.5939, "step": 91370 }, { "epoch": 4.17, "learning_rate": 2.920270950615589e-05, "loss": 1.65, "step": 91380 }, { "epoch": 4.17, "learning_rate": 2.9200421071902607e-05, "loss": 1.7085, "step": 91390 }, { "epoch": 4.17, "learning_rate": 2.919813263764932e-05, "loss": 1.4487, "step": 91400 }, { "epoch": 4.17, "learning_rate": 2.919584420339604e-05, "loss": 1.536, "step": 91410 }, { "epoch": 4.17, "learning_rate": 2.9193555769142757e-05, "loss": 1.6803, "step": 91420 }, { "epoch": 4.17, "learning_rate": 2.919126733488947e-05, "loss": 1.7204, "step": 91430 }, { "epoch": 4.18, "learning_rate": 2.918897890063619e-05, "loss": 1.6994, "step": 91440 }, { "epoch": 4.18, "learning_rate": 2.9186690466382906e-05, "loss": 1.6041, "step": 91450 }, { "epoch": 4.18, "learning_rate": 2.918440203212962e-05, "loss": 1.5457, "step": 91460 }, { "epoch": 4.18, "learning_rate": 2.9182113597876337e-05, "loss": 1.4872, "step": 91470 }, { "epoch": 4.18, "learning_rate": 2.9179825163623048e-05, "loss": 1.6432, "step": 91480 }, { "epoch": 4.18, "learning_rate": 2.9177536729369766e-05, "loss": 1.685, "step": 91490 }, { "epoch": 4.18, "learning_rate": 2.917524829511648e-05, "loss": 1.6521, "step": 91500 }, { "epoch": 4.18, "learning_rate": 2.9172959860863197e-05, "loss": 1.7333, "step": 91510 }, { "epoch": 4.18, "learning_rate": 2.9170671426609915e-05, "loss": 1.4676, "step": 91520 }, { "epoch": 4.18, "learning_rate": 2.916838299235663e-05, "loss": 1.5049, "step": 91530 }, { "epoch": 4.18, "learning_rate": 2.9166094558103347e-05, "loss": 1.4735, "step": 91540 }, { "epoch": 4.18, "learning_rate": 2.9163806123850064e-05, "loss": 1.5628, "step": 91550 }, { "epoch": 4.18, "learning_rate": 2.9161517689596778e-05, "loss": 1.7407, "step": 91560 }, { "epoch": 4.18, "learning_rate": 2.9159229255343496e-05, "loss": 1.4657, "step": 91570 }, { "epoch": 4.18, "learning_rate": 2.9156940821090213e-05, "loss": 1.5608, "step": 91580 }, { "epoch": 4.18, "learning_rate": 2.9154652386836927e-05, "loss": 1.4979, "step": 91590 }, { "epoch": 4.18, "learning_rate": 2.9152363952583645e-05, "loss": 1.6501, "step": 91600 }, { "epoch": 4.18, "learning_rate": 2.9150075518330362e-05, "loss": 1.6023, "step": 91610 }, { "epoch": 4.18, "learning_rate": 2.9147787084077077e-05, "loss": 1.5795, "step": 91620 }, { "epoch": 4.18, "learning_rate": 2.9145498649823794e-05, "loss": 1.5694, "step": 91630 }, { "epoch": 4.18, "learning_rate": 2.914321021557051e-05, "loss": 1.7195, "step": 91640 }, { "epoch": 4.18, "learning_rate": 2.9140921781317226e-05, "loss": 1.4673, "step": 91650 }, { "epoch": 4.19, "learning_rate": 2.9138633347063943e-05, "loss": 1.5195, "step": 91660 }, { "epoch": 4.19, "learning_rate": 2.9136344912810654e-05, "loss": 1.6496, "step": 91670 }, { "epoch": 4.19, "learning_rate": 2.913405647855737e-05, "loss": 1.521, "step": 91680 }, { "epoch": 4.19, "learning_rate": 2.9131768044304086e-05, "loss": 1.6361, "step": 91690 }, { "epoch": 4.19, "learning_rate": 2.9129479610050803e-05, "loss": 1.6307, "step": 91700 }, { "epoch": 4.19, "learning_rate": 2.912719117579752e-05, "loss": 1.6197, "step": 91710 }, { "epoch": 4.19, "learning_rate": 2.9124902741544235e-05, "loss": 1.6757, "step": 91720 }, { "epoch": 4.19, "learning_rate": 2.9122614307290952e-05, "loss": 1.6593, "step": 91730 }, { "epoch": 4.19, "learning_rate": 2.912032587303767e-05, "loss": 1.6751, "step": 91740 }, { "epoch": 4.19, "learning_rate": 2.9118037438784384e-05, "loss": 1.7771, "step": 91750 }, { "epoch": 4.19, "learning_rate": 2.91157490045311e-05, "loss": 1.5176, "step": 91760 }, { "epoch": 4.19, "learning_rate": 2.9113460570277816e-05, "loss": 1.5936, "step": 91770 }, { "epoch": 4.19, "learning_rate": 2.9111172136024533e-05, "loss": 1.6011, "step": 91780 }, { "epoch": 4.19, "learning_rate": 2.910888370177125e-05, "loss": 1.5463, "step": 91790 }, { "epoch": 4.19, "learning_rate": 2.9106595267517965e-05, "loss": 1.5859, "step": 91800 }, { "epoch": 4.19, "learning_rate": 2.9104306833264682e-05, "loss": 1.6218, "step": 91810 }, { "epoch": 4.19, "learning_rate": 2.91020183990114e-05, "loss": 1.5274, "step": 91820 }, { "epoch": 4.19, "learning_rate": 2.9099729964758114e-05, "loss": 1.6186, "step": 91830 }, { "epoch": 4.19, "learning_rate": 2.909744153050483e-05, "loss": 1.6235, "step": 91840 }, { "epoch": 4.19, "learning_rate": 2.909515309625155e-05, "loss": 1.7536, "step": 91850 }, { "epoch": 4.19, "learning_rate": 2.9092864661998263e-05, "loss": 1.6818, "step": 91860 }, { "epoch": 4.2, "learning_rate": 2.9090576227744974e-05, "loss": 1.4829, "step": 91870 }, { "epoch": 4.2, "learning_rate": 2.908828779349169e-05, "loss": 1.7431, "step": 91880 }, { "epoch": 4.2, "learning_rate": 2.908599935923841e-05, "loss": 1.569, "step": 91890 }, { "epoch": 4.2, "learning_rate": 2.9083710924985123e-05, "loss": 1.6192, "step": 91900 }, { "epoch": 4.2, "learning_rate": 2.908142249073184e-05, "loss": 1.5215, "step": 91910 }, { "epoch": 4.2, "learning_rate": 2.9079134056478558e-05, "loss": 1.4491, "step": 91920 }, { "epoch": 4.2, "learning_rate": 2.9076845622225272e-05, "loss": 1.61, "step": 91930 }, { "epoch": 4.2, "learning_rate": 2.907455718797199e-05, "loss": 1.5826, "step": 91940 }, { "epoch": 4.2, "learning_rate": 2.9072268753718707e-05, "loss": 1.7981, "step": 91950 }, { "epoch": 4.2, "learning_rate": 2.906998031946542e-05, "loss": 1.6054, "step": 91960 }, { "epoch": 4.2, "learning_rate": 2.906769188521214e-05, "loss": 1.5575, "step": 91970 }, { "epoch": 4.2, "learning_rate": 2.9065403450958857e-05, "loss": 1.5783, "step": 91980 }, { "epoch": 4.2, "learning_rate": 2.906311501670557e-05, "loss": 1.5599, "step": 91990 }, { "epoch": 4.2, "learning_rate": 2.9060826582452288e-05, "loss": 1.7265, "step": 92000 }, { "epoch": 4.2, "learning_rate": 2.9058538148199006e-05, "loss": 1.6897, "step": 92010 }, { "epoch": 4.2, "learning_rate": 2.905624971394572e-05, "loss": 1.6003, "step": 92020 }, { "epoch": 4.2, "learning_rate": 2.9053961279692437e-05, "loss": 1.6613, "step": 92030 }, { "epoch": 4.2, "learning_rate": 2.9051672845439155e-05, "loss": 1.5312, "step": 92040 }, { "epoch": 4.2, "learning_rate": 2.904938441118587e-05, "loss": 1.4321, "step": 92050 }, { "epoch": 4.2, "learning_rate": 2.9047095976932587e-05, "loss": 1.6959, "step": 92060 }, { "epoch": 4.2, "learning_rate": 2.9044807542679297e-05, "loss": 1.5279, "step": 92070 }, { "epoch": 4.2, "learning_rate": 2.9042519108426015e-05, "loss": 1.7328, "step": 92080 }, { "epoch": 4.21, "learning_rate": 2.904023067417273e-05, "loss": 1.6823, "step": 92090 }, { "epoch": 4.21, "learning_rate": 2.9037942239919446e-05, "loss": 1.7484, "step": 92100 }, { "epoch": 4.21, "learning_rate": 2.9035653805666164e-05, "loss": 1.536, "step": 92110 }, { "epoch": 4.21, "learning_rate": 2.9033365371412878e-05, "loss": 1.4076, "step": 92120 }, { "epoch": 4.21, "learning_rate": 2.9031076937159596e-05, "loss": 1.5253, "step": 92130 }, { "epoch": 4.21, "learning_rate": 2.9028788502906313e-05, "loss": 1.5684, "step": 92140 }, { "epoch": 4.21, "learning_rate": 2.9026500068653027e-05, "loss": 1.6751, "step": 92150 }, { "epoch": 4.21, "learning_rate": 2.9024211634399745e-05, "loss": 1.7024, "step": 92160 }, { "epoch": 4.21, "learning_rate": 2.9021923200146462e-05, "loss": 1.7262, "step": 92170 }, { "epoch": 4.21, "learning_rate": 2.9019634765893177e-05, "loss": 1.5998, "step": 92180 }, { "epoch": 4.21, "learning_rate": 2.9017346331639894e-05, "loss": 1.4891, "step": 92190 }, { "epoch": 4.21, "learning_rate": 2.901505789738661e-05, "loss": 1.6681, "step": 92200 }, { "epoch": 4.21, "learning_rate": 2.9012769463133326e-05, "loss": 1.6329, "step": 92210 }, { "epoch": 4.21, "learning_rate": 2.9010481028880043e-05, "loss": 1.6304, "step": 92220 }, { "epoch": 4.21, "learning_rate": 2.900819259462676e-05, "loss": 1.5681, "step": 92230 }, { "epoch": 4.21, "learning_rate": 2.9005904160373475e-05, "loss": 1.6756, "step": 92240 }, { "epoch": 4.21, "learning_rate": 2.9003615726120192e-05, "loss": 1.5755, "step": 92250 }, { "epoch": 4.21, "learning_rate": 2.900132729186691e-05, "loss": 1.4815, "step": 92260 }, { "epoch": 4.21, "learning_rate": 2.899903885761362e-05, "loss": 1.5951, "step": 92270 }, { "epoch": 4.21, "learning_rate": 2.8996750423360335e-05, "loss": 1.5871, "step": 92280 }, { "epoch": 4.21, "learning_rate": 2.8994461989107052e-05, "loss": 1.8066, "step": 92290 }, { "epoch": 4.21, "learning_rate": 2.899217355485377e-05, "loss": 1.5338, "step": 92300 }, { "epoch": 4.22, "learning_rate": 2.8989885120600484e-05, "loss": 1.5256, "step": 92310 }, { "epoch": 4.22, "learning_rate": 2.89875966863472e-05, "loss": 1.6975, "step": 92320 }, { "epoch": 4.22, "learning_rate": 2.898530825209392e-05, "loss": 1.581, "step": 92330 }, { "epoch": 4.22, "learning_rate": 2.8983019817840633e-05, "loss": 1.715, "step": 92340 }, { "epoch": 4.22, "learning_rate": 2.898073138358735e-05, "loss": 1.4222, "step": 92350 }, { "epoch": 4.22, "learning_rate": 2.8978442949334068e-05, "loss": 1.4724, "step": 92360 }, { "epoch": 4.22, "learning_rate": 2.8976154515080782e-05, "loss": 1.6145, "step": 92370 }, { "epoch": 4.22, "learning_rate": 2.89738660808275e-05, "loss": 1.5625, "step": 92380 }, { "epoch": 4.22, "learning_rate": 2.8971577646574217e-05, "loss": 1.537, "step": 92390 }, { "epoch": 4.22, "learning_rate": 2.896928921232093e-05, "loss": 1.6296, "step": 92400 }, { "epoch": 4.22, "learning_rate": 2.896700077806765e-05, "loss": 1.405, "step": 92410 }, { "epoch": 4.22, "learning_rate": 2.8964712343814367e-05, "loss": 1.7476, "step": 92420 }, { "epoch": 4.22, "learning_rate": 2.896242390956108e-05, "loss": 1.6458, "step": 92430 }, { "epoch": 4.22, "learning_rate": 2.8960135475307798e-05, "loss": 1.5787, "step": 92440 }, { "epoch": 4.22, "learning_rate": 2.8957847041054516e-05, "loss": 1.6204, "step": 92450 }, { "epoch": 4.22, "learning_rate": 2.8955558606801226e-05, "loss": 1.5688, "step": 92460 }, { "epoch": 4.22, "learning_rate": 2.895327017254794e-05, "loss": 1.6146, "step": 92470 }, { "epoch": 4.22, "learning_rate": 2.8950981738294658e-05, "loss": 1.5119, "step": 92480 }, { "epoch": 4.22, "learning_rate": 2.8948693304041376e-05, "loss": 1.5546, "step": 92490 }, { "epoch": 4.22, "learning_rate": 2.894640486978809e-05, "loss": 1.376, "step": 92500 }, { "epoch": 4.22, "learning_rate": 2.8944116435534807e-05, "loss": 1.6373, "step": 92510 }, { "epoch": 4.22, "learning_rate": 2.8941828001281525e-05, "loss": 1.5237, "step": 92520 }, { "epoch": 4.23, "learning_rate": 2.893953956702824e-05, "loss": 1.4984, "step": 92530 }, { "epoch": 4.23, "learning_rate": 2.8937251132774956e-05, "loss": 1.5299, "step": 92540 }, { "epoch": 4.23, "learning_rate": 2.8934962698521674e-05, "loss": 1.6119, "step": 92550 }, { "epoch": 4.23, "learning_rate": 2.8932674264268388e-05, "loss": 1.558, "step": 92560 }, { "epoch": 4.23, "learning_rate": 2.8930385830015106e-05, "loss": 1.5578, "step": 92570 }, { "epoch": 4.23, "learning_rate": 2.8928097395761823e-05, "loss": 1.6626, "step": 92580 }, { "epoch": 4.23, "learning_rate": 2.8925808961508537e-05, "loss": 1.489, "step": 92590 }, { "epoch": 4.23, "learning_rate": 2.8923520527255255e-05, "loss": 1.5748, "step": 92600 }, { "epoch": 4.23, "learning_rate": 2.8921232093001972e-05, "loss": 1.649, "step": 92610 }, { "epoch": 4.23, "learning_rate": 2.8918943658748686e-05, "loss": 1.5964, "step": 92620 }, { "epoch": 4.23, "learning_rate": 2.8916655224495404e-05, "loss": 1.7323, "step": 92630 }, { "epoch": 4.23, "learning_rate": 2.891436679024212e-05, "loss": 1.6409, "step": 92640 }, { "epoch": 4.23, "learning_rate": 2.8912078355988836e-05, "loss": 1.5171, "step": 92650 }, { "epoch": 4.23, "learning_rate": 2.8909789921735546e-05, "loss": 1.5537, "step": 92660 }, { "epoch": 4.23, "learning_rate": 2.8907501487482264e-05, "loss": 1.6555, "step": 92670 }, { "epoch": 4.23, "learning_rate": 2.890521305322898e-05, "loss": 1.7415, "step": 92680 }, { "epoch": 4.23, "learning_rate": 2.8902924618975696e-05, "loss": 1.6747, "step": 92690 }, { "epoch": 4.23, "learning_rate": 2.8900636184722413e-05, "loss": 1.562, "step": 92700 }, { "epoch": 4.23, "learning_rate": 2.889834775046913e-05, "loss": 1.3894, "step": 92710 }, { "epoch": 4.23, "learning_rate": 2.8896059316215845e-05, "loss": 1.6527, "step": 92720 }, { "epoch": 4.23, "learning_rate": 2.8893770881962562e-05, "loss": 1.5374, "step": 92730 }, { "epoch": 4.23, "learning_rate": 2.889148244770928e-05, "loss": 1.4879, "step": 92740 }, { "epoch": 4.24, "learning_rate": 2.8889194013455994e-05, "loss": 1.685, "step": 92750 }, { "epoch": 4.24, "learning_rate": 2.888690557920271e-05, "loss": 1.6516, "step": 92760 }, { "epoch": 4.24, "learning_rate": 2.888461714494943e-05, "loss": 1.497, "step": 92770 }, { "epoch": 4.24, "learning_rate": 2.8882328710696143e-05, "loss": 1.7841, "step": 92780 }, { "epoch": 4.24, "learning_rate": 2.888004027644286e-05, "loss": 1.4937, "step": 92790 }, { "epoch": 4.24, "learning_rate": 2.8877751842189578e-05, "loss": 1.6134, "step": 92800 }, { "epoch": 4.24, "learning_rate": 2.8875463407936292e-05, "loss": 1.869, "step": 92810 }, { "epoch": 4.24, "learning_rate": 2.887317497368301e-05, "loss": 1.5855, "step": 92820 }, { "epoch": 4.24, "learning_rate": 2.8870886539429727e-05, "loss": 1.6203, "step": 92830 }, { "epoch": 4.24, "learning_rate": 2.886859810517644e-05, "loss": 1.5623, "step": 92840 }, { "epoch": 4.24, "learning_rate": 2.886630967092316e-05, "loss": 1.3881, "step": 92850 }, { "epoch": 4.24, "learning_rate": 2.886402123666987e-05, "loss": 1.649, "step": 92860 }, { "epoch": 4.24, "learning_rate": 2.8861732802416587e-05, "loss": 1.5526, "step": 92870 }, { "epoch": 4.24, "learning_rate": 2.88594443681633e-05, "loss": 1.6245, "step": 92880 }, { "epoch": 4.24, "learning_rate": 2.885715593391002e-05, "loss": 1.4123, "step": 92890 }, { "epoch": 4.24, "learning_rate": 2.8854867499656736e-05, "loss": 1.5951, "step": 92900 }, { "epoch": 4.24, "learning_rate": 2.885257906540345e-05, "loss": 1.602, "step": 92910 }, { "epoch": 4.24, "learning_rate": 2.8850290631150168e-05, "loss": 1.5148, "step": 92920 }, { "epoch": 4.24, "learning_rate": 2.8848002196896882e-05, "loss": 1.4864, "step": 92930 }, { "epoch": 4.24, "learning_rate": 2.88457137626436e-05, "loss": 1.5516, "step": 92940 }, { "epoch": 4.24, "learning_rate": 2.8843425328390317e-05, "loss": 1.5276, "step": 92950 }, { "epoch": 4.24, "learning_rate": 2.884113689413703e-05, "loss": 1.7643, "step": 92960 }, { "epoch": 4.25, "learning_rate": 2.883884845988375e-05, "loss": 1.618, "step": 92970 }, { "epoch": 4.25, "learning_rate": 2.8836560025630466e-05, "loss": 1.5466, "step": 92980 }, { "epoch": 4.25, "learning_rate": 2.883427159137718e-05, "loss": 1.4758, "step": 92990 }, { "epoch": 4.25, "learning_rate": 2.8831983157123898e-05, "loss": 1.5344, "step": 93000 }, { "epoch": 4.25, "learning_rate": 2.8829694722870616e-05, "loss": 1.6085, "step": 93010 }, { "epoch": 4.25, "learning_rate": 2.882740628861733e-05, "loss": 1.6247, "step": 93020 }, { "epoch": 4.25, "learning_rate": 2.8825117854364047e-05, "loss": 1.4372, "step": 93030 }, { "epoch": 4.25, "learning_rate": 2.8822829420110765e-05, "loss": 1.4935, "step": 93040 }, { "epoch": 4.25, "learning_rate": 2.882054098585748e-05, "loss": 1.5741, "step": 93050 }, { "epoch": 4.25, "learning_rate": 2.881825255160419e-05, "loss": 1.6832, "step": 93060 }, { "epoch": 4.25, "learning_rate": 2.8815964117350907e-05, "loss": 1.5146, "step": 93070 }, { "epoch": 4.25, "learning_rate": 2.8813675683097625e-05, "loss": 1.7264, "step": 93080 }, { "epoch": 4.25, "learning_rate": 2.881138724884434e-05, "loss": 1.8022, "step": 93090 }, { "epoch": 4.25, "learning_rate": 2.8809098814591056e-05, "loss": 1.6575, "step": 93100 }, { "epoch": 4.25, "learning_rate": 2.8806810380337774e-05, "loss": 1.4808, "step": 93110 }, { "epoch": 4.25, "learning_rate": 2.8804521946084488e-05, "loss": 1.6364, "step": 93120 }, { "epoch": 4.25, "learning_rate": 2.8802233511831206e-05, "loss": 1.7048, "step": 93130 }, { "epoch": 4.25, "learning_rate": 2.8799945077577923e-05, "loss": 1.6153, "step": 93140 }, { "epoch": 4.25, "learning_rate": 2.8797656643324637e-05, "loss": 1.5452, "step": 93150 }, { "epoch": 4.25, "learning_rate": 2.8795368209071355e-05, "loss": 1.5942, "step": 93160 }, { "epoch": 4.25, "learning_rate": 2.8793079774818072e-05, "loss": 1.5302, "step": 93170 }, { "epoch": 4.25, "learning_rate": 2.8790791340564786e-05, "loss": 1.5936, "step": 93180 }, { "epoch": 4.26, "learning_rate": 2.8788502906311504e-05, "loss": 1.5697, "step": 93190 }, { "epoch": 4.26, "learning_rate": 2.878621447205822e-05, "loss": 1.7073, "step": 93200 }, { "epoch": 4.26, "learning_rate": 2.8783926037804936e-05, "loss": 1.7218, "step": 93210 }, { "epoch": 4.26, "learning_rate": 2.8781637603551653e-05, "loss": 1.5592, "step": 93220 }, { "epoch": 4.26, "learning_rate": 2.877934916929837e-05, "loss": 1.5789, "step": 93230 }, { "epoch": 4.26, "learning_rate": 2.8777060735045085e-05, "loss": 1.6968, "step": 93240 }, { "epoch": 4.26, "learning_rate": 2.8774772300791795e-05, "loss": 1.6385, "step": 93250 }, { "epoch": 4.26, "learning_rate": 2.8772483866538513e-05, "loss": 1.6751, "step": 93260 }, { "epoch": 4.26, "learning_rate": 2.877019543228523e-05, "loss": 1.6792, "step": 93270 }, { "epoch": 4.26, "learning_rate": 2.8767906998031945e-05, "loss": 1.5973, "step": 93280 }, { "epoch": 4.26, "learning_rate": 2.8765618563778662e-05, "loss": 1.6979, "step": 93290 }, { "epoch": 4.26, "learning_rate": 2.876333012952538e-05, "loss": 1.623, "step": 93300 }, { "epoch": 4.26, "learning_rate": 2.8761041695272094e-05, "loss": 1.6017, "step": 93310 }, { "epoch": 4.26, "learning_rate": 2.875875326101881e-05, "loss": 1.5869, "step": 93320 }, { "epoch": 4.26, "learning_rate": 2.875646482676553e-05, "loss": 1.5572, "step": 93330 }, { "epoch": 4.26, "learning_rate": 2.8754176392512243e-05, "loss": 1.6686, "step": 93340 }, { "epoch": 4.26, "learning_rate": 2.875188795825896e-05, "loss": 1.5705, "step": 93350 }, { "epoch": 4.26, "learning_rate": 2.8749599524005678e-05, "loss": 1.7196, "step": 93360 }, { "epoch": 4.26, "learning_rate": 2.8747311089752392e-05, "loss": 1.7715, "step": 93370 }, { "epoch": 4.26, "learning_rate": 2.874502265549911e-05, "loss": 1.5993, "step": 93380 }, { "epoch": 4.26, "learning_rate": 2.8742734221245827e-05, "loss": 1.6701, "step": 93390 }, { "epoch": 4.26, "learning_rate": 2.874044578699254e-05, "loss": 1.5659, "step": 93400 }, { "epoch": 4.27, "learning_rate": 2.873815735273926e-05, "loss": 1.542, "step": 93410 }, { "epoch": 4.27, "learning_rate": 2.8735868918485976e-05, "loss": 1.6304, "step": 93420 }, { "epoch": 4.27, "learning_rate": 2.873358048423269e-05, "loss": 1.5484, "step": 93430 }, { "epoch": 4.27, "learning_rate": 2.8731292049979408e-05, "loss": 1.5588, "step": 93440 }, { "epoch": 4.27, "learning_rate": 2.872900361572612e-05, "loss": 1.5428, "step": 93450 }, { "epoch": 4.27, "learning_rate": 2.8726715181472836e-05, "loss": 1.4524, "step": 93460 }, { "epoch": 4.27, "learning_rate": 2.872442674721955e-05, "loss": 1.8989, "step": 93470 }, { "epoch": 4.27, "learning_rate": 2.8722138312966268e-05, "loss": 1.4705, "step": 93480 }, { "epoch": 4.27, "learning_rate": 2.8719849878712985e-05, "loss": 1.6139, "step": 93490 }, { "epoch": 4.27, "learning_rate": 2.87175614444597e-05, "loss": 1.7733, "step": 93500 }, { "epoch": 4.27, "learning_rate": 2.8715273010206417e-05, "loss": 1.5137, "step": 93510 }, { "epoch": 4.27, "learning_rate": 2.8712984575953135e-05, "loss": 1.6177, "step": 93520 }, { "epoch": 4.27, "learning_rate": 2.871069614169985e-05, "loss": 1.538, "step": 93530 }, { "epoch": 4.27, "learning_rate": 2.8708407707446566e-05, "loss": 1.6666, "step": 93540 }, { "epoch": 4.27, "learning_rate": 2.8706119273193284e-05, "loss": 1.409, "step": 93550 }, { "epoch": 4.27, "learning_rate": 2.8703830838939998e-05, "loss": 1.5738, "step": 93560 }, { "epoch": 4.27, "learning_rate": 2.8701542404686716e-05, "loss": 1.4876, "step": 93570 }, { "epoch": 4.27, "learning_rate": 2.8699253970433433e-05, "loss": 1.6819, "step": 93580 }, { "epoch": 4.27, "learning_rate": 2.8696965536180147e-05, "loss": 1.4811, "step": 93590 }, { "epoch": 4.27, "learning_rate": 2.8694677101926865e-05, "loss": 1.5243, "step": 93600 }, { "epoch": 4.27, "learning_rate": 2.8692388667673582e-05, "loss": 1.47, "step": 93610 }, { "epoch": 4.27, "learning_rate": 2.8690100233420296e-05, "loss": 1.521, "step": 93620 }, { "epoch": 4.28, "learning_rate": 2.8687811799167014e-05, "loss": 1.5753, "step": 93630 }, { "epoch": 4.28, "learning_rate": 2.868552336491373e-05, "loss": 1.7497, "step": 93640 }, { "epoch": 4.28, "learning_rate": 2.8683234930660442e-05, "loss": 1.7432, "step": 93650 }, { "epoch": 4.28, "learning_rate": 2.8680946496407156e-05, "loss": 1.5488, "step": 93660 }, { "epoch": 4.28, "learning_rate": 2.8678658062153874e-05, "loss": 1.6635, "step": 93670 }, { "epoch": 4.28, "learning_rate": 2.867636962790059e-05, "loss": 1.5345, "step": 93680 }, { "epoch": 4.28, "learning_rate": 2.8674081193647305e-05, "loss": 1.5679, "step": 93690 }, { "epoch": 4.28, "learning_rate": 2.8671792759394023e-05, "loss": 1.6147, "step": 93700 }, { "epoch": 4.28, "learning_rate": 2.866950432514074e-05, "loss": 1.7185, "step": 93710 }, { "epoch": 4.28, "learning_rate": 2.8667215890887455e-05, "loss": 1.6531, "step": 93720 }, { "epoch": 4.28, "learning_rate": 2.8664927456634172e-05, "loss": 1.4922, "step": 93730 }, { "epoch": 4.28, "learning_rate": 2.866263902238089e-05, "loss": 1.7557, "step": 93740 }, { "epoch": 4.28, "learning_rate": 2.8660350588127604e-05, "loss": 1.7133, "step": 93750 }, { "epoch": 4.28, "learning_rate": 2.865806215387432e-05, "loss": 1.7233, "step": 93760 }, { "epoch": 4.28, "learning_rate": 2.865577371962104e-05, "loss": 1.6676, "step": 93770 }, { "epoch": 4.28, "learning_rate": 2.8653485285367753e-05, "loss": 1.5751, "step": 93780 }, { "epoch": 4.28, "learning_rate": 2.865119685111447e-05, "loss": 1.396, "step": 93790 }, { "epoch": 4.28, "learning_rate": 2.8648908416861188e-05, "loss": 1.5057, "step": 93800 }, { "epoch": 4.28, "learning_rate": 2.8646619982607902e-05, "loss": 1.624, "step": 93810 }, { "epoch": 4.28, "learning_rate": 2.864433154835462e-05, "loss": 1.6208, "step": 93820 }, { "epoch": 4.28, "learning_rate": 2.8642043114101337e-05, "loss": 1.5631, "step": 93830 }, { "epoch": 4.28, "learning_rate": 2.863975467984805e-05, "loss": 1.487, "step": 93840 }, { "epoch": 4.29, "learning_rate": 2.8637466245594762e-05, "loss": 1.5489, "step": 93850 }, { "epoch": 4.29, "learning_rate": 2.863517781134148e-05, "loss": 1.4873, "step": 93860 }, { "epoch": 4.29, "learning_rate": 2.8632889377088197e-05, "loss": 1.5807, "step": 93870 }, { "epoch": 4.29, "learning_rate": 2.863060094283491e-05, "loss": 1.5377, "step": 93880 }, { "epoch": 4.29, "learning_rate": 2.862831250858163e-05, "loss": 1.8395, "step": 93890 }, { "epoch": 4.29, "learning_rate": 2.8626024074328346e-05, "loss": 1.5678, "step": 93900 }, { "epoch": 4.29, "learning_rate": 2.862373564007506e-05, "loss": 1.5849, "step": 93910 }, { "epoch": 4.29, "learning_rate": 2.8621447205821778e-05, "loss": 1.6278, "step": 93920 }, { "epoch": 4.29, "learning_rate": 2.8619158771568495e-05, "loss": 1.5897, "step": 93930 }, { "epoch": 4.29, "learning_rate": 2.861687033731521e-05, "loss": 1.5112, "step": 93940 }, { "epoch": 4.29, "learning_rate": 2.8614581903061927e-05, "loss": 1.3755, "step": 93950 }, { "epoch": 4.29, "learning_rate": 2.8612293468808645e-05, "loss": 1.6921, "step": 93960 }, { "epoch": 4.29, "learning_rate": 2.861000503455536e-05, "loss": 1.5418, "step": 93970 }, { "epoch": 4.29, "learning_rate": 2.8607716600302076e-05, "loss": 1.7697, "step": 93980 }, { "epoch": 4.29, "learning_rate": 2.8605428166048794e-05, "loss": 1.6608, "step": 93990 }, { "epoch": 4.29, "learning_rate": 2.8603139731795508e-05, "loss": 1.4632, "step": 94000 }, { "epoch": 4.29, "learning_rate": 2.8600851297542225e-05, "loss": 1.5886, "step": 94010 }, { "epoch": 4.29, "learning_rate": 2.859856286328894e-05, "loss": 1.5571, "step": 94020 }, { "epoch": 4.29, "learning_rate": 2.8596274429035657e-05, "loss": 1.6113, "step": 94030 }, { "epoch": 4.29, "learning_rate": 2.8593985994782368e-05, "loss": 1.4028, "step": 94040 }, { "epoch": 4.29, "learning_rate": 2.8591697560529085e-05, "loss": 1.6315, "step": 94050 }, { "epoch": 4.3, "learning_rate": 2.8589409126275803e-05, "loss": 1.8873, "step": 94060 }, { "epoch": 4.3, "learning_rate": 2.8587120692022517e-05, "loss": 1.6187, "step": 94070 }, { "epoch": 4.3, "learning_rate": 2.8584832257769235e-05, "loss": 1.43, "step": 94080 }, { "epoch": 4.3, "learning_rate": 2.858254382351595e-05, "loss": 1.5783, "step": 94090 }, { "epoch": 4.3, "learning_rate": 2.8580255389262666e-05, "loss": 1.508, "step": 94100 }, { "epoch": 4.3, "learning_rate": 2.8577966955009384e-05, "loss": 1.4007, "step": 94110 }, { "epoch": 4.3, "learning_rate": 2.8575678520756098e-05, "loss": 1.7516, "step": 94120 }, { "epoch": 4.3, "learning_rate": 2.8573390086502815e-05, "loss": 1.5303, "step": 94130 }, { "epoch": 4.3, "learning_rate": 2.8571101652249533e-05, "loss": 1.7208, "step": 94140 }, { "epoch": 4.3, "learning_rate": 2.8568813217996247e-05, "loss": 1.8545, "step": 94150 }, { "epoch": 4.3, "learning_rate": 2.8566524783742965e-05, "loss": 1.5532, "step": 94160 }, { "epoch": 4.3, "learning_rate": 2.8564236349489682e-05, "loss": 1.5655, "step": 94170 }, { "epoch": 4.3, "learning_rate": 2.8561947915236396e-05, "loss": 1.5013, "step": 94180 }, { "epoch": 4.3, "learning_rate": 2.8559659480983114e-05, "loss": 1.6523, "step": 94190 }, { "epoch": 4.3, "learning_rate": 2.855737104672983e-05, "loss": 1.7, "step": 94200 }, { "epoch": 4.3, "learning_rate": 2.8555082612476545e-05, "loss": 1.6284, "step": 94210 }, { "epoch": 4.3, "learning_rate": 2.8552794178223263e-05, "loss": 1.476, "step": 94220 }, { "epoch": 4.3, "learning_rate": 2.855050574396998e-05, "loss": 1.7135, "step": 94230 }, { "epoch": 4.3, "learning_rate": 2.854821730971669e-05, "loss": 1.5951, "step": 94240 }, { "epoch": 4.3, "learning_rate": 2.8545928875463405e-05, "loss": 1.5749, "step": 94250 }, { "epoch": 4.3, "learning_rate": 2.8543640441210123e-05, "loss": 1.5212, "step": 94260 }, { "epoch": 4.3, "learning_rate": 2.854135200695684e-05, "loss": 1.4402, "step": 94270 }, { "epoch": 4.31, "learning_rate": 2.8539063572703555e-05, "loss": 1.5977, "step": 94280 }, { "epoch": 4.31, "learning_rate": 2.8536775138450272e-05, "loss": 1.3796, "step": 94290 }, { "epoch": 4.31, "learning_rate": 2.853448670419699e-05, "loss": 1.5111, "step": 94300 }, { "epoch": 4.31, "learning_rate": 2.8532198269943704e-05, "loss": 1.7495, "step": 94310 }, { "epoch": 4.31, "learning_rate": 2.852990983569042e-05, "loss": 1.5274, "step": 94320 }, { "epoch": 4.31, "learning_rate": 2.852762140143714e-05, "loss": 1.5564, "step": 94330 }, { "epoch": 4.31, "learning_rate": 2.8525332967183853e-05, "loss": 1.6283, "step": 94340 }, { "epoch": 4.31, "learning_rate": 2.852304453293057e-05, "loss": 1.6488, "step": 94350 }, { "epoch": 4.31, "learning_rate": 2.8520756098677288e-05, "loss": 1.569, "step": 94360 }, { "epoch": 4.31, "learning_rate": 2.8518467664424002e-05, "loss": 1.4728, "step": 94370 }, { "epoch": 4.31, "learning_rate": 2.851617923017072e-05, "loss": 1.5265, "step": 94380 }, { "epoch": 4.31, "learning_rate": 2.8513890795917437e-05, "loss": 1.4015, "step": 94390 }, { "epoch": 4.31, "learning_rate": 2.851160236166415e-05, "loss": 1.6546, "step": 94400 }, { "epoch": 4.31, "learning_rate": 2.850931392741087e-05, "loss": 1.527, "step": 94410 }, { "epoch": 4.31, "learning_rate": 2.8507025493157586e-05, "loss": 1.5745, "step": 94420 }, { "epoch": 4.31, "learning_rate": 2.85047370589043e-05, "loss": 1.5188, "step": 94430 }, { "epoch": 4.31, "learning_rate": 2.850244862465101e-05, "loss": 1.5596, "step": 94440 }, { "epoch": 4.31, "learning_rate": 2.850016019039773e-05, "loss": 1.6598, "step": 94450 }, { "epoch": 4.31, "learning_rate": 2.8497871756144446e-05, "loss": 1.6575, "step": 94460 }, { "epoch": 4.31, "learning_rate": 2.849558332189116e-05, "loss": 1.7232, "step": 94470 }, { "epoch": 4.31, "learning_rate": 2.8493294887637878e-05, "loss": 1.498, "step": 94480 }, { "epoch": 4.31, "learning_rate": 2.8491006453384595e-05, "loss": 1.6649, "step": 94490 }, { "epoch": 4.32, "learning_rate": 2.848871801913131e-05, "loss": 1.5307, "step": 94500 }, { "epoch": 4.32, "learning_rate": 2.8486429584878027e-05, "loss": 1.6508, "step": 94510 }, { "epoch": 4.32, "learning_rate": 2.8484141150624745e-05, "loss": 1.5367, "step": 94520 }, { "epoch": 4.32, "learning_rate": 2.848185271637146e-05, "loss": 1.8078, "step": 94530 }, { "epoch": 4.32, "learning_rate": 2.8479564282118176e-05, "loss": 1.6453, "step": 94540 }, { "epoch": 4.32, "learning_rate": 2.8477275847864894e-05, "loss": 1.5253, "step": 94550 }, { "epoch": 4.32, "learning_rate": 2.8474987413611608e-05, "loss": 1.6002, "step": 94560 }, { "epoch": 4.32, "learning_rate": 2.8472698979358325e-05, "loss": 1.518, "step": 94570 }, { "epoch": 4.32, "learning_rate": 2.8470410545105043e-05, "loss": 1.5804, "step": 94580 }, { "epoch": 4.32, "learning_rate": 2.8468122110851757e-05, "loss": 1.6021, "step": 94590 }, { "epoch": 4.32, "learning_rate": 2.8465833676598475e-05, "loss": 1.6522, "step": 94600 }, { "epoch": 4.32, "learning_rate": 2.8463545242345192e-05, "loss": 1.5857, "step": 94610 }, { "epoch": 4.32, "learning_rate": 2.8461256808091906e-05, "loss": 1.5828, "step": 94620 }, { "epoch": 4.32, "learning_rate": 2.8458968373838624e-05, "loss": 1.5351, "step": 94630 }, { "epoch": 4.32, "learning_rate": 2.8456679939585334e-05, "loss": 1.7194, "step": 94640 }, { "epoch": 4.32, "learning_rate": 2.8454391505332052e-05, "loss": 1.6789, "step": 94650 }, { "epoch": 4.32, "learning_rate": 2.8452103071078766e-05, "loss": 1.5506, "step": 94660 }, { "epoch": 4.32, "learning_rate": 2.8449814636825484e-05, "loss": 1.5739, "step": 94670 }, { "epoch": 4.32, "learning_rate": 2.84475262025722e-05, "loss": 1.5863, "step": 94680 }, { "epoch": 4.32, "learning_rate": 2.8445237768318915e-05, "loss": 1.62, "step": 94690 }, { "epoch": 4.32, "learning_rate": 2.8442949334065633e-05, "loss": 1.4767, "step": 94700 }, { "epoch": 4.32, "learning_rate": 2.844066089981235e-05, "loss": 1.6061, "step": 94710 }, { "epoch": 4.33, "learning_rate": 2.8438372465559064e-05, "loss": 1.7127, "step": 94720 }, { "epoch": 4.33, "learning_rate": 2.8436084031305782e-05, "loss": 1.5044, "step": 94730 }, { "epoch": 4.33, "learning_rate": 2.84337955970525e-05, "loss": 1.5933, "step": 94740 }, { "epoch": 4.33, "learning_rate": 2.8431507162799214e-05, "loss": 1.5512, "step": 94750 }, { "epoch": 4.33, "learning_rate": 2.842921872854593e-05, "loss": 1.7515, "step": 94760 }, { "epoch": 4.33, "learning_rate": 2.842693029429265e-05, "loss": 1.5552, "step": 94770 }, { "epoch": 4.33, "learning_rate": 2.8424641860039363e-05, "loss": 1.4095, "step": 94780 }, { "epoch": 4.33, "learning_rate": 2.842235342578608e-05, "loss": 1.6033, "step": 94790 }, { "epoch": 4.33, "learning_rate": 2.8420064991532798e-05, "loss": 1.4346, "step": 94800 }, { "epoch": 4.33, "learning_rate": 2.8417776557279512e-05, "loss": 1.3918, "step": 94810 }, { "epoch": 4.33, "learning_rate": 2.841548812302623e-05, "loss": 1.6118, "step": 94820 }, { "epoch": 4.33, "learning_rate": 2.841319968877294e-05, "loss": 1.4568, "step": 94830 }, { "epoch": 4.33, "learning_rate": 2.8410911254519658e-05, "loss": 1.5209, "step": 94840 }, { "epoch": 4.33, "learning_rate": 2.8408622820266372e-05, "loss": 1.6198, "step": 94850 }, { "epoch": 4.33, "learning_rate": 2.840633438601309e-05, "loss": 1.5872, "step": 94860 }, { "epoch": 4.33, "learning_rate": 2.8404045951759807e-05, "loss": 1.4655, "step": 94870 }, { "epoch": 4.33, "learning_rate": 2.840175751750652e-05, "loss": 1.7815, "step": 94880 }, { "epoch": 4.33, "learning_rate": 2.839946908325324e-05, "loss": 1.5349, "step": 94890 }, { "epoch": 4.33, "learning_rate": 2.8397180648999956e-05, "loss": 1.3957, "step": 94900 }, { "epoch": 4.33, "learning_rate": 2.839489221474667e-05, "loss": 1.4619, "step": 94910 }, { "epoch": 4.33, "learning_rate": 2.8392603780493388e-05, "loss": 1.5749, "step": 94920 }, { "epoch": 4.33, "learning_rate": 2.8390315346240105e-05, "loss": 1.6687, "step": 94930 }, { "epoch": 4.34, "learning_rate": 2.838802691198682e-05, "loss": 1.6372, "step": 94940 }, { "epoch": 4.34, "learning_rate": 2.8385738477733537e-05, "loss": 1.5963, "step": 94950 }, { "epoch": 4.34, "learning_rate": 2.8383450043480255e-05, "loss": 1.5538, "step": 94960 }, { "epoch": 4.34, "learning_rate": 2.838116160922697e-05, "loss": 1.7473, "step": 94970 }, { "epoch": 4.34, "learning_rate": 2.8378873174973686e-05, "loss": 1.411, "step": 94980 }, { "epoch": 4.34, "learning_rate": 2.8376584740720404e-05, "loss": 1.6901, "step": 94990 }, { "epoch": 4.34, "learning_rate": 2.8374296306467118e-05, "loss": 1.6294, "step": 95000 }, { "epoch": 4.34, "learning_rate": 2.8372007872213835e-05, "loss": 1.3812, "step": 95010 }, { "epoch": 4.34, "learning_rate": 2.8369719437960553e-05, "loss": 1.6668, "step": 95020 }, { "epoch": 4.34, "learning_rate": 2.8367431003707264e-05, "loss": 1.7028, "step": 95030 }, { "epoch": 4.34, "learning_rate": 2.8365142569453978e-05, "loss": 1.6206, "step": 95040 }, { "epoch": 4.34, "learning_rate": 2.8362854135200695e-05, "loss": 1.5756, "step": 95050 }, { "epoch": 4.34, "learning_rate": 2.8360565700947413e-05, "loss": 1.4283, "step": 95060 }, { "epoch": 4.34, "learning_rate": 2.8358277266694127e-05, "loss": 1.5838, "step": 95070 }, { "epoch": 4.34, "learning_rate": 2.8355988832440844e-05, "loss": 1.5112, "step": 95080 }, { "epoch": 4.34, "learning_rate": 2.8353700398187562e-05, "loss": 1.6342, "step": 95090 }, { "epoch": 4.34, "learning_rate": 2.8351411963934276e-05, "loss": 1.5621, "step": 95100 }, { "epoch": 4.34, "learning_rate": 2.8349123529680994e-05, "loss": 1.7107, "step": 95110 }, { "epoch": 4.34, "learning_rate": 2.834683509542771e-05, "loss": 1.525, "step": 95120 }, { "epoch": 4.34, "learning_rate": 2.8344546661174425e-05, "loss": 1.5208, "step": 95130 }, { "epoch": 4.34, "learning_rate": 2.8342258226921143e-05, "loss": 1.5962, "step": 95140 }, { "epoch": 4.34, "learning_rate": 2.833996979266786e-05, "loss": 1.6195, "step": 95150 }, { "epoch": 4.35, "learning_rate": 2.8337681358414574e-05, "loss": 1.599, "step": 95160 }, { "epoch": 4.35, "learning_rate": 2.8335392924161292e-05, "loss": 1.5752, "step": 95170 }, { "epoch": 4.35, "learning_rate": 2.833310448990801e-05, "loss": 1.6319, "step": 95180 }, { "epoch": 4.35, "learning_rate": 2.8330816055654724e-05, "loss": 1.3696, "step": 95190 }, { "epoch": 4.35, "learning_rate": 2.832852762140144e-05, "loss": 1.4997, "step": 95200 }, { "epoch": 4.35, "learning_rate": 2.8326239187148155e-05, "loss": 1.4201, "step": 95210 }, { "epoch": 4.35, "learning_rate": 2.8323950752894873e-05, "loss": 1.6264, "step": 95220 }, { "epoch": 4.35, "learning_rate": 2.8321662318641584e-05, "loss": 1.6816, "step": 95230 }, { "epoch": 4.35, "learning_rate": 2.83193738843883e-05, "loss": 1.6848, "step": 95240 }, { "epoch": 4.35, "learning_rate": 2.831708545013502e-05, "loss": 1.4962, "step": 95250 }, { "epoch": 4.35, "learning_rate": 2.8314797015881733e-05, "loss": 1.4193, "step": 95260 }, { "epoch": 4.35, "learning_rate": 2.831250858162845e-05, "loss": 1.5754, "step": 95270 }, { "epoch": 4.35, "learning_rate": 2.8310220147375164e-05, "loss": 1.499, "step": 95280 }, { "epoch": 4.35, "learning_rate": 2.8307931713121882e-05, "loss": 1.5946, "step": 95290 }, { "epoch": 4.35, "learning_rate": 2.83056432788686e-05, "loss": 1.5291, "step": 95300 }, { "epoch": 4.35, "learning_rate": 2.8303354844615314e-05, "loss": 1.4852, "step": 95310 }, { "epoch": 4.35, "learning_rate": 2.830106641036203e-05, "loss": 1.3706, "step": 95320 }, { "epoch": 4.35, "learning_rate": 2.829877797610875e-05, "loss": 1.5861, "step": 95330 }, { "epoch": 4.35, "learning_rate": 2.8296489541855463e-05, "loss": 1.4995, "step": 95340 }, { "epoch": 4.35, "learning_rate": 2.829420110760218e-05, "loss": 1.7233, "step": 95350 }, { "epoch": 4.35, "learning_rate": 2.8291912673348898e-05, "loss": 1.7543, "step": 95360 }, { "epoch": 4.35, "learning_rate": 2.8289624239095612e-05, "loss": 1.6208, "step": 95370 }, { "epoch": 4.36, "learning_rate": 2.828733580484233e-05, "loss": 1.6882, "step": 95380 }, { "epoch": 4.36, "learning_rate": 2.8285047370589047e-05, "loss": 1.6286, "step": 95390 }, { "epoch": 4.36, "learning_rate": 2.828275893633576e-05, "loss": 1.6995, "step": 95400 }, { "epoch": 4.36, "learning_rate": 2.828047050208248e-05, "loss": 1.5699, "step": 95410 }, { "epoch": 4.36, "learning_rate": 2.8278182067829196e-05, "loss": 1.4829, "step": 95420 }, { "epoch": 4.36, "learning_rate": 2.8275893633575907e-05, "loss": 1.4404, "step": 95430 }, { "epoch": 4.36, "learning_rate": 2.827360519932262e-05, "loss": 1.6119, "step": 95440 }, { "epoch": 4.36, "learning_rate": 2.827131676506934e-05, "loss": 1.4752, "step": 95450 }, { "epoch": 4.36, "learning_rate": 2.8269028330816056e-05, "loss": 1.7213, "step": 95460 }, { "epoch": 4.36, "learning_rate": 2.826673989656277e-05, "loss": 1.5258, "step": 95470 }, { "epoch": 4.36, "learning_rate": 2.8264451462309488e-05, "loss": 1.6215, "step": 95480 }, { "epoch": 4.36, "learning_rate": 2.8262163028056205e-05, "loss": 1.5869, "step": 95490 }, { "epoch": 4.36, "learning_rate": 2.825987459380292e-05, "loss": 1.611, "step": 95500 }, { "epoch": 4.36, "learning_rate": 2.8257586159549637e-05, "loss": 1.5146, "step": 95510 }, { "epoch": 4.36, "learning_rate": 2.8255297725296354e-05, "loss": 1.6381, "step": 95520 }, { "epoch": 4.36, "learning_rate": 2.825300929104307e-05, "loss": 1.5255, "step": 95530 }, { "epoch": 4.36, "learning_rate": 2.8250720856789786e-05, "loss": 1.7115, "step": 95540 }, { "epoch": 4.36, "learning_rate": 2.8248432422536504e-05, "loss": 1.5848, "step": 95550 }, { "epoch": 4.36, "learning_rate": 2.8246143988283218e-05, "loss": 1.4172, "step": 95560 }, { "epoch": 4.36, "learning_rate": 2.8243855554029935e-05, "loss": 1.55, "step": 95570 }, { "epoch": 4.36, "learning_rate": 2.8241567119776653e-05, "loss": 1.6788, "step": 95580 }, { "epoch": 4.36, "learning_rate": 2.8239278685523367e-05, "loss": 1.5237, "step": 95590 }, { "epoch": 4.37, "learning_rate": 2.8236990251270084e-05, "loss": 1.5557, "step": 95600 }, { "epoch": 4.37, "learning_rate": 2.8234701817016802e-05, "loss": 1.4845, "step": 95610 }, { "epoch": 4.37, "learning_rate": 2.8232413382763516e-05, "loss": 1.5927, "step": 95620 }, { "epoch": 4.37, "learning_rate": 2.8230124948510227e-05, "loss": 1.4992, "step": 95630 }, { "epoch": 4.37, "learning_rate": 2.8227836514256944e-05, "loss": 1.7411, "step": 95640 }, { "epoch": 4.37, "learning_rate": 2.8225548080003662e-05, "loss": 1.4609, "step": 95650 }, { "epoch": 4.37, "learning_rate": 2.8223259645750376e-05, "loss": 1.6356, "step": 95660 }, { "epoch": 4.37, "learning_rate": 2.8220971211497094e-05, "loss": 1.4348, "step": 95670 }, { "epoch": 4.37, "learning_rate": 2.821868277724381e-05, "loss": 1.4354, "step": 95680 }, { "epoch": 4.37, "learning_rate": 2.8216394342990525e-05, "loss": 1.7513, "step": 95690 }, { "epoch": 4.37, "learning_rate": 2.8214105908737243e-05, "loss": 1.6038, "step": 95700 }, { "epoch": 4.37, "learning_rate": 2.821181747448396e-05, "loss": 1.5702, "step": 95710 }, { "epoch": 4.37, "learning_rate": 2.8209529040230674e-05, "loss": 1.4709, "step": 95720 }, { "epoch": 4.37, "learning_rate": 2.8207240605977392e-05, "loss": 1.4222, "step": 95730 }, { "epoch": 4.37, "learning_rate": 2.820495217172411e-05, "loss": 1.6328, "step": 95740 }, { "epoch": 4.37, "learning_rate": 2.8202663737470824e-05, "loss": 1.615, "step": 95750 }, { "epoch": 4.37, "learning_rate": 2.820037530321754e-05, "loss": 1.5524, "step": 95760 }, { "epoch": 4.37, "learning_rate": 2.819808686896426e-05, "loss": 1.4905, "step": 95770 }, { "epoch": 4.37, "learning_rate": 2.8195798434710973e-05, "loss": 1.5026, "step": 95780 }, { "epoch": 4.37, "learning_rate": 2.819351000045769e-05, "loss": 1.5642, "step": 95790 }, { "epoch": 4.37, "learning_rate": 2.8191221566204408e-05, "loss": 1.669, "step": 95800 }, { "epoch": 4.37, "learning_rate": 2.8188933131951122e-05, "loss": 1.5789, "step": 95810 }, { "epoch": 4.38, "learning_rate": 2.8186644697697833e-05, "loss": 1.6004, "step": 95820 }, { "epoch": 4.38, "learning_rate": 2.818435626344455e-05, "loss": 1.523, "step": 95830 }, { "epoch": 4.38, "learning_rate": 2.8182067829191268e-05, "loss": 1.7044, "step": 95840 }, { "epoch": 4.38, "learning_rate": 2.8179779394937982e-05, "loss": 1.4972, "step": 95850 }, { "epoch": 4.38, "learning_rate": 2.81774909606847e-05, "loss": 1.5732, "step": 95860 }, { "epoch": 4.38, "learning_rate": 2.8175202526431417e-05, "loss": 1.5559, "step": 95870 }, { "epoch": 4.38, "learning_rate": 2.817291409217813e-05, "loss": 1.6521, "step": 95880 }, { "epoch": 4.38, "learning_rate": 2.817062565792485e-05, "loss": 1.5515, "step": 95890 }, { "epoch": 4.38, "learning_rate": 2.8168337223671566e-05, "loss": 1.4731, "step": 95900 }, { "epoch": 4.38, "learning_rate": 2.816604878941828e-05, "loss": 1.5156, "step": 95910 }, { "epoch": 4.38, "learning_rate": 2.8163760355164998e-05, "loss": 1.5945, "step": 95920 }, { "epoch": 4.38, "learning_rate": 2.8161471920911715e-05, "loss": 1.7776, "step": 95930 }, { "epoch": 4.38, "learning_rate": 2.815918348665843e-05, "loss": 1.5658, "step": 95940 }, { "epoch": 4.38, "learning_rate": 2.8156895052405147e-05, "loss": 1.4157, "step": 95950 }, { "epoch": 4.38, "learning_rate": 2.8154606618151864e-05, "loss": 1.6018, "step": 95960 }, { "epoch": 4.38, "learning_rate": 2.815231818389858e-05, "loss": 1.7072, "step": 95970 }, { "epoch": 4.38, "learning_rate": 2.8150029749645296e-05, "loss": 1.5245, "step": 95980 }, { "epoch": 4.38, "learning_rate": 2.8147741315392014e-05, "loss": 1.6608, "step": 95990 }, { "epoch": 4.38, "learning_rate": 2.8145452881138728e-05, "loss": 1.613, "step": 96000 }, { "epoch": 4.38, "learning_rate": 2.8143164446885445e-05, "loss": 1.5497, "step": 96010 }, { "epoch": 4.38, "learning_rate": 2.8140876012632156e-05, "loss": 1.6748, "step": 96020 }, { "epoch": 4.38, "learning_rate": 2.8138587578378873e-05, "loss": 1.4295, "step": 96030 }, { "epoch": 4.39, "learning_rate": 2.8136299144125588e-05, "loss": 1.44, "step": 96040 }, { "epoch": 4.39, "learning_rate": 2.8134010709872305e-05, "loss": 1.5147, "step": 96050 }, { "epoch": 4.39, "learning_rate": 2.8131722275619023e-05, "loss": 1.5193, "step": 96060 }, { "epoch": 4.39, "learning_rate": 2.8129433841365737e-05, "loss": 1.6001, "step": 96070 }, { "epoch": 4.39, "learning_rate": 2.8127145407112454e-05, "loss": 1.4546, "step": 96080 }, { "epoch": 4.39, "learning_rate": 2.8124856972859172e-05, "loss": 1.6333, "step": 96090 }, { "epoch": 4.39, "learning_rate": 2.8122568538605886e-05, "loss": 1.7549, "step": 96100 }, { "epoch": 4.39, "learning_rate": 2.8120280104352603e-05, "loss": 1.6464, "step": 96110 }, { "epoch": 4.39, "learning_rate": 2.811799167009932e-05, "loss": 1.5501, "step": 96120 }, { "epoch": 4.39, "learning_rate": 2.8115703235846035e-05, "loss": 1.5551, "step": 96130 }, { "epoch": 4.39, "learning_rate": 2.8113414801592753e-05, "loss": 1.5585, "step": 96140 }, { "epoch": 4.39, "learning_rate": 2.811112636733947e-05, "loss": 1.625, "step": 96150 }, { "epoch": 4.39, "learning_rate": 2.8108837933086184e-05, "loss": 1.7787, "step": 96160 }, { "epoch": 4.39, "learning_rate": 2.8106549498832902e-05, "loss": 1.6618, "step": 96170 }, { "epoch": 4.39, "learning_rate": 2.810426106457962e-05, "loss": 1.7594, "step": 96180 }, { "epoch": 4.39, "learning_rate": 2.8101972630326333e-05, "loss": 1.5709, "step": 96190 }, { "epoch": 4.39, "learning_rate": 2.809968419607305e-05, "loss": 1.6423, "step": 96200 }, { "epoch": 4.39, "learning_rate": 2.809739576181977e-05, "loss": 1.6413, "step": 96210 }, { "epoch": 4.39, "learning_rate": 2.809510732756648e-05, "loss": 1.7287, "step": 96220 }, { "epoch": 4.39, "learning_rate": 2.8092818893313193e-05, "loss": 1.5587, "step": 96230 }, { "epoch": 4.39, "learning_rate": 2.809053045905991e-05, "loss": 1.5586, "step": 96240 }, { "epoch": 4.4, "learning_rate": 2.808824202480663e-05, "loss": 1.6249, "step": 96250 }, { "epoch": 4.4, "learning_rate": 2.8085953590553343e-05, "loss": 1.5064, "step": 96260 }, { "epoch": 4.4, "learning_rate": 2.808366515630006e-05, "loss": 1.7009, "step": 96270 }, { "epoch": 4.4, "learning_rate": 2.8081376722046778e-05, "loss": 1.3153, "step": 96280 }, { "epoch": 4.4, "learning_rate": 2.8079088287793492e-05, "loss": 1.5091, "step": 96290 }, { "epoch": 4.4, "learning_rate": 2.807679985354021e-05, "loss": 1.4938, "step": 96300 }, { "epoch": 4.4, "learning_rate": 2.8074511419286927e-05, "loss": 1.721, "step": 96310 }, { "epoch": 4.4, "learning_rate": 2.807222298503364e-05, "loss": 1.5061, "step": 96320 }, { "epoch": 4.4, "learning_rate": 2.806993455078036e-05, "loss": 1.519, "step": 96330 }, { "epoch": 4.4, "learning_rate": 2.8067646116527076e-05, "loss": 1.5234, "step": 96340 }, { "epoch": 4.4, "learning_rate": 2.806535768227379e-05, "loss": 1.6894, "step": 96350 }, { "epoch": 4.4, "learning_rate": 2.8063069248020508e-05, "loss": 1.6511, "step": 96360 }, { "epoch": 4.4, "learning_rate": 2.8060780813767222e-05, "loss": 1.5283, "step": 96370 }, { "epoch": 4.4, "learning_rate": 2.805849237951394e-05, "loss": 1.5911, "step": 96380 }, { "epoch": 4.4, "learning_rate": 2.8056203945260657e-05, "loss": 1.5289, "step": 96390 }, { "epoch": 4.4, "learning_rate": 2.805391551100737e-05, "loss": 1.5933, "step": 96400 }, { "epoch": 4.4, "learning_rate": 2.805162707675409e-05, "loss": 1.5525, "step": 96410 }, { "epoch": 4.4, "learning_rate": 2.80493386425008e-05, "loss": 1.4597, "step": 96420 }, { "epoch": 4.4, "learning_rate": 2.8047050208247517e-05, "loss": 1.6715, "step": 96430 }, { "epoch": 4.4, "learning_rate": 2.804476177399423e-05, "loss": 1.5104, "step": 96440 }, { "epoch": 4.4, "learning_rate": 2.804247333974095e-05, "loss": 1.5651, "step": 96450 }, { "epoch": 4.4, "learning_rate": 2.8040184905487666e-05, "loss": 1.4232, "step": 96460 }, { "epoch": 4.41, "learning_rate": 2.803789647123438e-05, "loss": 1.5471, "step": 96470 }, { "epoch": 4.41, "learning_rate": 2.8035608036981098e-05, "loss": 1.6344, "step": 96480 }, { "epoch": 4.41, "learning_rate": 2.8033319602727815e-05, "loss": 1.771, "step": 96490 }, { "epoch": 4.41, "learning_rate": 2.803103116847453e-05, "loss": 1.452, "step": 96500 }, { "epoch": 4.41, "learning_rate": 2.8028742734221247e-05, "loss": 1.6297, "step": 96510 }, { "epoch": 4.41, "learning_rate": 2.8026454299967964e-05, "loss": 1.5749, "step": 96520 }, { "epoch": 4.41, "learning_rate": 2.802416586571468e-05, "loss": 1.5071, "step": 96530 }, { "epoch": 4.41, "learning_rate": 2.8021877431461396e-05, "loss": 1.6675, "step": 96540 }, { "epoch": 4.41, "learning_rate": 2.8019588997208113e-05, "loss": 1.5765, "step": 96550 }, { "epoch": 4.41, "learning_rate": 2.8017300562954828e-05, "loss": 1.5623, "step": 96560 }, { "epoch": 4.41, "learning_rate": 2.8015012128701545e-05, "loss": 1.7844, "step": 96570 }, { "epoch": 4.41, "learning_rate": 2.8012723694448263e-05, "loss": 1.59, "step": 96580 }, { "epoch": 4.41, "learning_rate": 2.8010435260194977e-05, "loss": 1.5676, "step": 96590 }, { "epoch": 4.41, "learning_rate": 2.8008146825941694e-05, "loss": 1.632, "step": 96600 }, { "epoch": 4.41, "learning_rate": 2.8005858391688405e-05, "loss": 1.473, "step": 96610 }, { "epoch": 4.41, "learning_rate": 2.8003569957435123e-05, "loss": 1.7458, "step": 96620 }, { "epoch": 4.41, "learning_rate": 2.8001281523181837e-05, "loss": 1.5124, "step": 96630 }, { "epoch": 4.41, "learning_rate": 2.7998993088928554e-05, "loss": 1.412, "step": 96640 }, { "epoch": 4.41, "learning_rate": 2.7996704654675272e-05, "loss": 1.7491, "step": 96650 }, { "epoch": 4.41, "learning_rate": 2.7994416220421986e-05, "loss": 1.5189, "step": 96660 }, { "epoch": 4.41, "learning_rate": 2.7992127786168703e-05, "loss": 1.7505, "step": 96670 }, { "epoch": 4.41, "learning_rate": 2.798983935191542e-05, "loss": 1.673, "step": 96680 }, { "epoch": 4.42, "learning_rate": 2.7987550917662135e-05, "loss": 1.5564, "step": 96690 }, { "epoch": 4.42, "learning_rate": 2.7985262483408853e-05, "loss": 1.4667, "step": 96700 }, { "epoch": 4.42, "learning_rate": 2.798297404915557e-05, "loss": 1.5595, "step": 96710 }, { "epoch": 4.42, "learning_rate": 2.7980685614902284e-05, "loss": 1.5956, "step": 96720 }, { "epoch": 4.42, "learning_rate": 2.7978397180649002e-05, "loss": 1.5199, "step": 96730 }, { "epoch": 4.42, "learning_rate": 2.797610874639572e-05, "loss": 1.5761, "step": 96740 }, { "epoch": 4.42, "learning_rate": 2.7973820312142433e-05, "loss": 1.5323, "step": 96750 }, { "epoch": 4.42, "learning_rate": 2.797153187788915e-05, "loss": 1.5741, "step": 96760 }, { "epoch": 4.42, "learning_rate": 2.796924344363587e-05, "loss": 1.5984, "step": 96770 }, { "epoch": 4.42, "learning_rate": 2.7966955009382583e-05, "loss": 1.4609, "step": 96780 }, { "epoch": 4.42, "learning_rate": 2.79646665751293e-05, "loss": 1.694, "step": 96790 }, { "epoch": 4.42, "learning_rate": 2.7962378140876018e-05, "loss": 1.5704, "step": 96800 }, { "epoch": 4.42, "learning_rate": 2.796008970662273e-05, "loss": 1.577, "step": 96810 }, { "epoch": 4.42, "learning_rate": 2.7957801272369442e-05, "loss": 1.566, "step": 96820 }, { "epoch": 4.42, "learning_rate": 2.795551283811616e-05, "loss": 1.6872, "step": 96830 }, { "epoch": 4.42, "learning_rate": 2.7953224403862878e-05, "loss": 1.6185, "step": 96840 }, { "epoch": 4.42, "learning_rate": 2.795093596960959e-05, "loss": 1.5805, "step": 96850 }, { "epoch": 4.42, "learning_rate": 2.794864753535631e-05, "loss": 1.6038, "step": 96860 }, { "epoch": 4.42, "learning_rate": 2.7946359101103027e-05, "loss": 1.6416, "step": 96870 }, { "epoch": 4.42, "learning_rate": 2.794407066684974e-05, "loss": 1.511, "step": 96880 }, { "epoch": 4.42, "learning_rate": 2.794178223259646e-05, "loss": 1.615, "step": 96890 }, { "epoch": 4.42, "learning_rate": 2.7939493798343176e-05, "loss": 1.6076, "step": 96900 }, { "epoch": 4.43, "learning_rate": 2.793720536408989e-05, "loss": 1.4516, "step": 96910 }, { "epoch": 4.43, "learning_rate": 2.7934916929836608e-05, "loss": 1.6866, "step": 96920 }, { "epoch": 4.43, "learning_rate": 2.7932628495583325e-05, "loss": 1.5783, "step": 96930 }, { "epoch": 4.43, "learning_rate": 2.793034006133004e-05, "loss": 1.5749, "step": 96940 }, { "epoch": 4.43, "learning_rate": 2.7928051627076757e-05, "loss": 1.6006, "step": 96950 }, { "epoch": 4.43, "learning_rate": 2.7925763192823474e-05, "loss": 1.5065, "step": 96960 }, { "epoch": 4.43, "learning_rate": 2.792347475857019e-05, "loss": 1.5887, "step": 96970 }, { "epoch": 4.43, "learning_rate": 2.7921186324316906e-05, "loss": 1.4901, "step": 96980 }, { "epoch": 4.43, "learning_rate": 2.7918897890063623e-05, "loss": 1.5305, "step": 96990 }, { "epoch": 4.43, "learning_rate": 2.7916609455810338e-05, "loss": 1.7178, "step": 97000 }, { "epoch": 4.43, "learning_rate": 2.7914321021557048e-05, "loss": 1.8007, "step": 97010 }, { "epoch": 4.43, "learning_rate": 2.7912032587303766e-05, "loss": 1.5734, "step": 97020 }, { "epoch": 4.43, "learning_rate": 2.7909744153050483e-05, "loss": 1.4515, "step": 97030 }, { "epoch": 4.43, "learning_rate": 2.7907455718797197e-05, "loss": 1.4794, "step": 97040 }, { "epoch": 4.43, "learning_rate": 2.7905167284543915e-05, "loss": 1.6228, "step": 97050 }, { "epoch": 4.43, "learning_rate": 2.7902878850290633e-05, "loss": 1.4445, "step": 97060 }, { "epoch": 4.43, "learning_rate": 2.7900590416037347e-05, "loss": 1.5794, "step": 97070 }, { "epoch": 4.43, "learning_rate": 2.7898301981784064e-05, "loss": 1.9091, "step": 97080 }, { "epoch": 4.43, "learning_rate": 2.7896013547530782e-05, "loss": 1.423, "step": 97090 }, { "epoch": 4.43, "learning_rate": 2.7893725113277496e-05, "loss": 1.5315, "step": 97100 }, { "epoch": 4.43, "learning_rate": 2.7891436679024213e-05, "loss": 1.6955, "step": 97110 }, { "epoch": 4.43, "learning_rate": 2.788914824477093e-05, "loss": 1.5418, "step": 97120 }, { "epoch": 4.44, "learning_rate": 2.7886859810517645e-05, "loss": 1.3235, "step": 97130 }, { "epoch": 4.44, "learning_rate": 2.7884571376264363e-05, "loss": 1.5853, "step": 97140 }, { "epoch": 4.44, "learning_rate": 2.788228294201108e-05, "loss": 1.4698, "step": 97150 }, { "epoch": 4.44, "learning_rate": 2.7879994507757794e-05, "loss": 1.57, "step": 97160 }, { "epoch": 4.44, "learning_rate": 2.7877706073504512e-05, "loss": 1.5702, "step": 97170 }, { "epoch": 4.44, "learning_rate": 2.787541763925123e-05, "loss": 1.6703, "step": 97180 }, { "epoch": 4.44, "learning_rate": 2.7873129204997943e-05, "loss": 1.6846, "step": 97190 }, { "epoch": 4.44, "learning_rate": 2.787084077074466e-05, "loss": 1.659, "step": 97200 }, { "epoch": 4.44, "learning_rate": 2.786855233649137e-05, "loss": 1.5916, "step": 97210 }, { "epoch": 4.44, "learning_rate": 2.786626390223809e-05, "loss": 1.4771, "step": 97220 }, { "epoch": 4.44, "learning_rate": 2.7863975467984803e-05, "loss": 1.6073, "step": 97230 }, { "epoch": 4.44, "learning_rate": 2.786168703373152e-05, "loss": 1.5795, "step": 97240 }, { "epoch": 4.44, "learning_rate": 2.785939859947824e-05, "loss": 1.5458, "step": 97250 }, { "epoch": 4.44, "learning_rate": 2.7857110165224952e-05, "loss": 1.4558, "step": 97260 }, { "epoch": 4.44, "learning_rate": 2.785482173097167e-05, "loss": 1.4736, "step": 97270 }, { "epoch": 4.44, "learning_rate": 2.7852533296718388e-05, "loss": 1.5805, "step": 97280 }, { "epoch": 4.44, "learning_rate": 2.78502448624651e-05, "loss": 1.6307, "step": 97290 }, { "epoch": 4.44, "learning_rate": 2.784795642821182e-05, "loss": 1.6772, "step": 97300 }, { "epoch": 4.44, "learning_rate": 2.7845667993958537e-05, "loss": 1.6099, "step": 97310 }, { "epoch": 4.44, "learning_rate": 2.784337955970525e-05, "loss": 1.7164, "step": 97320 }, { "epoch": 4.44, "learning_rate": 2.784109112545197e-05, "loss": 1.6, "step": 97330 }, { "epoch": 4.44, "learning_rate": 2.7838802691198686e-05, "loss": 1.6326, "step": 97340 }, { "epoch": 4.45, "learning_rate": 2.78365142569454e-05, "loss": 1.4801, "step": 97350 }, { "epoch": 4.45, "learning_rate": 2.7834225822692118e-05, "loss": 1.5835, "step": 97360 }, { "epoch": 4.45, "learning_rate": 2.7831937388438835e-05, "loss": 1.6678, "step": 97370 }, { "epoch": 4.45, "learning_rate": 2.782964895418555e-05, "loss": 1.535, "step": 97380 }, { "epoch": 4.45, "learning_rate": 2.7827360519932267e-05, "loss": 1.5712, "step": 97390 }, { "epoch": 4.45, "learning_rate": 2.7825072085678977e-05, "loss": 1.546, "step": 97400 }, { "epoch": 4.45, "learning_rate": 2.7822783651425695e-05, "loss": 1.7017, "step": 97410 }, { "epoch": 4.45, "learning_rate": 2.782049521717241e-05, "loss": 1.6522, "step": 97420 }, { "epoch": 4.45, "learning_rate": 2.7818206782919127e-05, "loss": 1.7599, "step": 97430 }, { "epoch": 4.45, "learning_rate": 2.7815918348665844e-05, "loss": 1.5703, "step": 97440 }, { "epoch": 4.45, "learning_rate": 2.7813629914412558e-05, "loss": 1.6206, "step": 97450 }, { "epoch": 4.45, "learning_rate": 2.7811341480159276e-05, "loss": 1.5192, "step": 97460 }, { "epoch": 4.45, "learning_rate": 2.7809053045905993e-05, "loss": 1.5635, "step": 97470 }, { "epoch": 4.45, "learning_rate": 2.7806764611652707e-05, "loss": 1.5137, "step": 97480 }, { "epoch": 4.45, "learning_rate": 2.7804476177399425e-05, "loss": 1.6707, "step": 97490 }, { "epoch": 4.45, "learning_rate": 2.7802187743146142e-05, "loss": 1.4405, "step": 97500 }, { "epoch": 4.45, "learning_rate": 2.7799899308892857e-05, "loss": 1.4843, "step": 97510 }, { "epoch": 4.45, "learning_rate": 2.7797610874639574e-05, "loss": 1.4817, "step": 97520 }, { "epoch": 4.45, "learning_rate": 2.7795322440386288e-05, "loss": 1.5709, "step": 97530 }, { "epoch": 4.45, "learning_rate": 2.7793034006133006e-05, "loss": 1.5094, "step": 97540 }, { "epoch": 4.45, "learning_rate": 2.7790745571879723e-05, "loss": 1.5666, "step": 97550 }, { "epoch": 4.45, "learning_rate": 2.7788457137626437e-05, "loss": 1.5169, "step": 97560 }, { "epoch": 4.46, "learning_rate": 2.7786168703373155e-05, "loss": 1.5543, "step": 97570 }, { "epoch": 4.46, "learning_rate": 2.7783880269119872e-05, "loss": 1.6266, "step": 97580 }, { "epoch": 4.46, "learning_rate": 2.7781591834866587e-05, "loss": 1.559, "step": 97590 }, { "epoch": 4.46, "learning_rate": 2.7779303400613297e-05, "loss": 1.4677, "step": 97600 }, { "epoch": 4.46, "learning_rate": 2.7777014966360015e-05, "loss": 1.5232, "step": 97610 }, { "epoch": 4.46, "learning_rate": 2.7774726532106732e-05, "loss": 1.4767, "step": 97620 }, { "epoch": 4.46, "learning_rate": 2.7772438097853447e-05, "loss": 1.6231, "step": 97630 }, { "epoch": 4.46, "learning_rate": 2.7770149663600164e-05, "loss": 1.5141, "step": 97640 }, { "epoch": 4.46, "learning_rate": 2.776786122934688e-05, "loss": 1.6184, "step": 97650 }, { "epoch": 4.46, "learning_rate": 2.7765572795093596e-05, "loss": 1.5761, "step": 97660 }, { "epoch": 4.46, "learning_rate": 2.7763284360840313e-05, "loss": 1.486, "step": 97670 }, { "epoch": 4.46, "learning_rate": 2.776099592658703e-05, "loss": 1.6538, "step": 97680 }, { "epoch": 4.46, "learning_rate": 2.7758707492333745e-05, "loss": 1.6269, "step": 97690 }, { "epoch": 4.46, "learning_rate": 2.7756419058080462e-05, "loss": 1.6207, "step": 97700 }, { "epoch": 4.46, "learning_rate": 2.775413062382718e-05, "loss": 1.5565, "step": 97710 }, { "epoch": 4.46, "learning_rate": 2.7751842189573894e-05, "loss": 1.6127, "step": 97720 }, { "epoch": 4.46, "learning_rate": 2.774955375532061e-05, "loss": 1.5373, "step": 97730 }, { "epoch": 4.46, "learning_rate": 2.774726532106733e-05, "loss": 1.6607, "step": 97740 }, { "epoch": 4.46, "learning_rate": 2.7744976886814043e-05, "loss": 1.6444, "step": 97750 }, { "epoch": 4.46, "learning_rate": 2.774268845256076e-05, "loss": 1.4687, "step": 97760 }, { "epoch": 4.46, "learning_rate": 2.7740400018307478e-05, "loss": 1.5742, "step": 97770 }, { "epoch": 4.46, "learning_rate": 2.7738111584054192e-05, "loss": 1.5478, "step": 97780 }, { "epoch": 4.47, "learning_rate": 2.773582314980091e-05, "loss": 1.6938, "step": 97790 }, { "epoch": 4.47, "learning_rate": 2.773353471554762e-05, "loss": 1.868, "step": 97800 }, { "epoch": 4.47, "learning_rate": 2.7731246281294338e-05, "loss": 1.599, "step": 97810 }, { "epoch": 4.47, "learning_rate": 2.7728957847041052e-05, "loss": 1.6681, "step": 97820 }, { "epoch": 4.47, "learning_rate": 2.772666941278777e-05, "loss": 1.6912, "step": 97830 }, { "epoch": 4.47, "learning_rate": 2.7724380978534487e-05, "loss": 1.6532, "step": 97840 }, { "epoch": 4.47, "learning_rate": 2.77220925442812e-05, "loss": 1.668, "step": 97850 }, { "epoch": 4.47, "learning_rate": 2.771980411002792e-05, "loss": 1.5583, "step": 97860 }, { "epoch": 4.47, "learning_rate": 2.7717515675774637e-05, "loss": 1.4227, "step": 97870 }, { "epoch": 4.47, "learning_rate": 2.771522724152135e-05, "loss": 1.624, "step": 97880 }, { "epoch": 4.47, "learning_rate": 2.7712938807268068e-05, "loss": 1.5938, "step": 97890 }, { "epoch": 4.47, "learning_rate": 2.7710650373014786e-05, "loss": 1.4456, "step": 97900 }, { "epoch": 4.47, "learning_rate": 2.77083619387615e-05, "loss": 1.6791, "step": 97910 }, { "epoch": 4.47, "learning_rate": 2.7706073504508217e-05, "loss": 1.5583, "step": 97920 }, { "epoch": 4.47, "learning_rate": 2.7703785070254935e-05, "loss": 1.4028, "step": 97930 }, { "epoch": 4.47, "learning_rate": 2.770149663600165e-05, "loss": 1.5435, "step": 97940 }, { "epoch": 4.47, "learning_rate": 2.7699208201748367e-05, "loss": 1.6259, "step": 97950 }, { "epoch": 4.47, "learning_rate": 2.7696919767495084e-05, "loss": 1.6525, "step": 97960 }, { "epoch": 4.47, "learning_rate": 2.7694631333241798e-05, "loss": 1.6757, "step": 97970 }, { "epoch": 4.47, "learning_rate": 2.7692342898988516e-05, "loss": 1.482, "step": 97980 }, { "epoch": 4.47, "learning_rate": 2.7690054464735233e-05, "loss": 1.5343, "step": 97990 }, { "epoch": 4.47, "learning_rate": 2.7687766030481944e-05, "loss": 1.6951, "step": 98000 }, { "epoch": 4.48, "learning_rate": 2.7685477596228658e-05, "loss": 1.4459, "step": 98010 }, { "epoch": 4.48, "learning_rate": 2.7683189161975376e-05, "loss": 1.5145, "step": 98020 }, { "epoch": 4.48, "learning_rate": 2.7680900727722093e-05, "loss": 1.5794, "step": 98030 }, { "epoch": 4.48, "learning_rate": 2.7678612293468807e-05, "loss": 1.6457, "step": 98040 }, { "epoch": 4.48, "learning_rate": 2.7676323859215525e-05, "loss": 1.5793, "step": 98050 }, { "epoch": 4.48, "learning_rate": 2.7674035424962242e-05, "loss": 1.7, "step": 98060 }, { "epoch": 4.48, "learning_rate": 2.7671746990708957e-05, "loss": 1.4619, "step": 98070 }, { "epoch": 4.48, "learning_rate": 2.7669458556455674e-05, "loss": 1.5389, "step": 98080 }, { "epoch": 4.48, "learning_rate": 2.766717012220239e-05, "loss": 1.5695, "step": 98090 }, { "epoch": 4.48, "learning_rate": 2.7664881687949106e-05, "loss": 1.6771, "step": 98100 }, { "epoch": 4.48, "learning_rate": 2.7662593253695823e-05, "loss": 1.4273, "step": 98110 }, { "epoch": 4.48, "learning_rate": 2.766030481944254e-05, "loss": 1.6386, "step": 98120 }, { "epoch": 4.48, "learning_rate": 2.7658016385189255e-05, "loss": 1.4252, "step": 98130 }, { "epoch": 4.48, "learning_rate": 2.7655727950935972e-05, "loss": 1.4983, "step": 98140 }, { "epoch": 4.48, "learning_rate": 2.765343951668269e-05, "loss": 1.6172, "step": 98150 }, { "epoch": 4.48, "learning_rate": 2.7651151082429404e-05, "loss": 1.4949, "step": 98160 }, { "epoch": 4.48, "learning_rate": 2.764886264817612e-05, "loss": 1.7528, "step": 98170 }, { "epoch": 4.48, "learning_rate": 2.764657421392284e-05, "loss": 1.735, "step": 98180 }, { "epoch": 4.48, "learning_rate": 2.764428577966955e-05, "loss": 1.5409, "step": 98190 }, { "epoch": 4.48, "learning_rate": 2.7641997345416264e-05, "loss": 1.5413, "step": 98200 }, { "epoch": 4.48, "learning_rate": 2.763970891116298e-05, "loss": 1.5097, "step": 98210 }, { "epoch": 4.48, "learning_rate": 2.76374204769097e-05, "loss": 1.6228, "step": 98220 }, { "epoch": 4.49, "learning_rate": 2.7635132042656413e-05, "loss": 1.5222, "step": 98230 }, { "epoch": 4.49, "learning_rate": 2.763284360840313e-05, "loss": 1.4704, "step": 98240 }, { "epoch": 4.49, "learning_rate": 2.7630555174149848e-05, "loss": 1.5849, "step": 98250 }, { "epoch": 4.49, "learning_rate": 2.7628266739896562e-05, "loss": 1.5105, "step": 98260 }, { "epoch": 4.49, "learning_rate": 2.762597830564328e-05, "loss": 1.5567, "step": 98270 }, { "epoch": 4.49, "learning_rate": 2.7623689871389997e-05, "loss": 1.5924, "step": 98280 }, { "epoch": 4.49, "learning_rate": 2.762140143713671e-05, "loss": 1.8572, "step": 98290 }, { "epoch": 4.49, "learning_rate": 2.761911300288343e-05, "loss": 1.7846, "step": 98300 }, { "epoch": 4.49, "learning_rate": 2.7616824568630147e-05, "loss": 1.6299, "step": 98310 }, { "epoch": 4.49, "learning_rate": 2.761453613437686e-05, "loss": 1.261, "step": 98320 }, { "epoch": 4.49, "learning_rate": 2.7612247700123578e-05, "loss": 1.5152, "step": 98330 }, { "epoch": 4.49, "learning_rate": 2.7609959265870296e-05, "loss": 1.3742, "step": 98340 }, { "epoch": 4.49, "learning_rate": 2.760767083161701e-05, "loss": 1.5892, "step": 98350 }, { "epoch": 4.49, "learning_rate": 2.7605382397363727e-05, "loss": 1.5178, "step": 98360 }, { "epoch": 4.49, "learning_rate": 2.7603093963110445e-05, "loss": 1.4857, "step": 98370 }, { "epoch": 4.49, "learning_rate": 2.760080552885716e-05, "loss": 1.6324, "step": 98380 }, { "epoch": 4.49, "learning_rate": 2.759851709460387e-05, "loss": 1.5242, "step": 98390 }, { "epoch": 4.49, "learning_rate": 2.7596228660350587e-05, "loss": 1.4446, "step": 98400 }, { "epoch": 4.49, "learning_rate": 2.7593940226097305e-05, "loss": 1.3499, "step": 98410 }, { "epoch": 4.49, "learning_rate": 2.759165179184402e-05, "loss": 1.4597, "step": 98420 }, { "epoch": 4.49, "learning_rate": 2.7589363357590736e-05, "loss": 1.7157, "step": 98430 }, { "epoch": 4.5, "learning_rate": 2.7587074923337454e-05, "loss": 1.4529, "step": 98440 }, { "epoch": 4.5, "learning_rate": 2.7584786489084168e-05, "loss": 1.5455, "step": 98450 }, { "epoch": 4.5, "learning_rate": 2.7582498054830886e-05, "loss": 1.5992, "step": 98460 }, { "epoch": 4.5, "learning_rate": 2.7580209620577603e-05, "loss": 1.371, "step": 98470 }, { "epoch": 4.5, "learning_rate": 2.7577921186324317e-05, "loss": 1.5443, "step": 98480 }, { "epoch": 4.5, "learning_rate": 2.7575632752071035e-05, "loss": 1.5281, "step": 98490 }, { "epoch": 4.5, "learning_rate": 2.7573344317817752e-05, "loss": 1.6922, "step": 98500 }, { "epoch": 4.5, "learning_rate": 2.7571055883564466e-05, "loss": 1.5842, "step": 98510 }, { "epoch": 4.5, "learning_rate": 2.7568767449311184e-05, "loss": 1.6987, "step": 98520 }, { "epoch": 4.5, "learning_rate": 2.75664790150579e-05, "loss": 1.6183, "step": 98530 }, { "epoch": 4.5, "learning_rate": 2.7564190580804616e-05, "loss": 1.5456, "step": 98540 }, { "epoch": 4.5, "learning_rate": 2.7561902146551333e-05, "loss": 1.6606, "step": 98550 }, { "epoch": 4.5, "learning_rate": 2.755961371229805e-05, "loss": 1.5227, "step": 98560 }, { "epoch": 4.5, "learning_rate": 2.7557325278044765e-05, "loss": 1.4974, "step": 98570 }, { "epoch": 4.5, "learning_rate": 2.7555036843791482e-05, "loss": 1.6415, "step": 98580 }, { "epoch": 4.5, "learning_rate": 2.7552748409538193e-05, "loss": 1.7331, "step": 98590 }, { "epoch": 4.5, "learning_rate": 2.755045997528491e-05, "loss": 1.5698, "step": 98600 }, { "epoch": 4.5, "learning_rate": 2.7548171541031625e-05, "loss": 1.394, "step": 98610 }, { "epoch": 4.5, "learning_rate": 2.7545883106778342e-05, "loss": 1.6963, "step": 98620 }, { "epoch": 4.5, "learning_rate": 2.754359467252506e-05, "loss": 1.3602, "step": 98630 }, { "epoch": 4.5, "learning_rate": 2.7541306238271774e-05, "loss": 1.4566, "step": 98640 }, { "epoch": 4.5, "learning_rate": 2.753901780401849e-05, "loss": 1.5635, "step": 98650 }, { "epoch": 4.51, "learning_rate": 2.753672936976521e-05, "loss": 1.569, "step": 98660 }, { "epoch": 4.51, "learning_rate": 2.7534440935511923e-05, "loss": 1.5171, "step": 98670 }, { "epoch": 4.51, "learning_rate": 2.753215250125864e-05, "loss": 1.5572, "step": 98680 }, { "epoch": 4.51, "learning_rate": 2.7529864067005358e-05, "loss": 1.7172, "step": 98690 }, { "epoch": 4.51, "learning_rate": 2.7527575632752072e-05, "loss": 1.5144, "step": 98700 }, { "epoch": 4.51, "learning_rate": 2.752528719849879e-05, "loss": 1.4408, "step": 98710 }, { "epoch": 4.51, "learning_rate": 2.7522998764245504e-05, "loss": 1.5128, "step": 98720 }, { "epoch": 4.51, "learning_rate": 2.752071032999222e-05, "loss": 1.46, "step": 98730 }, { "epoch": 4.51, "learning_rate": 2.751842189573894e-05, "loss": 1.4466, "step": 98740 }, { "epoch": 4.51, "learning_rate": 2.7516133461485653e-05, "loss": 1.4644, "step": 98750 }, { "epoch": 4.51, "learning_rate": 2.751384502723237e-05, "loss": 1.5539, "step": 98760 }, { "epoch": 4.51, "learning_rate": 2.7511556592979088e-05, "loss": 1.7992, "step": 98770 }, { "epoch": 4.51, "learning_rate": 2.7509268158725802e-05, "loss": 1.7688, "step": 98780 }, { "epoch": 4.51, "learning_rate": 2.7506979724472513e-05, "loss": 1.4534, "step": 98790 }, { "epoch": 4.51, "learning_rate": 2.750469129021923e-05, "loss": 1.5133, "step": 98800 }, { "epoch": 4.51, "learning_rate": 2.7502402855965948e-05, "loss": 1.3966, "step": 98810 }, { "epoch": 4.51, "learning_rate": 2.7500114421712662e-05, "loss": 1.528, "step": 98820 }, { "epoch": 4.51, "learning_rate": 2.749782598745938e-05, "loss": 1.6822, "step": 98830 }, { "epoch": 4.51, "learning_rate": 2.7495537553206097e-05, "loss": 1.5849, "step": 98840 }, { "epoch": 4.51, "learning_rate": 2.749324911895281e-05, "loss": 1.6098, "step": 98850 }, { "epoch": 4.51, "learning_rate": 2.749096068469953e-05, "loss": 1.524, "step": 98860 }, { "epoch": 4.51, "learning_rate": 2.7488672250446246e-05, "loss": 1.6169, "step": 98870 }, { "epoch": 4.52, "learning_rate": 2.748638381619296e-05, "loss": 1.4575, "step": 98880 }, { "epoch": 4.52, "learning_rate": 2.7484095381939678e-05, "loss": 1.4941, "step": 98890 }, { "epoch": 4.52, "learning_rate": 2.7481806947686396e-05, "loss": 1.513, "step": 98900 }, { "epoch": 4.52, "learning_rate": 2.747951851343311e-05, "loss": 1.5771, "step": 98910 }, { "epoch": 4.52, "learning_rate": 2.7477230079179827e-05, "loss": 1.4729, "step": 98920 }, { "epoch": 4.52, "learning_rate": 2.7474941644926545e-05, "loss": 1.4323, "step": 98930 }, { "epoch": 4.52, "learning_rate": 2.747265321067326e-05, "loss": 1.52, "step": 98940 }, { "epoch": 4.52, "learning_rate": 2.7470364776419976e-05, "loss": 1.5208, "step": 98950 }, { "epoch": 4.52, "learning_rate": 2.7468076342166694e-05, "loss": 1.6148, "step": 98960 }, { "epoch": 4.52, "learning_rate": 2.7465787907913408e-05, "loss": 1.557, "step": 98970 }, { "epoch": 4.52, "learning_rate": 2.746349947366012e-05, "loss": 1.4077, "step": 98980 }, { "epoch": 4.52, "learning_rate": 2.7461211039406836e-05, "loss": 1.4568, "step": 98990 }, { "epoch": 4.52, "learning_rate": 2.7458922605153554e-05, "loss": 1.6836, "step": 99000 }, { "epoch": 4.52, "learning_rate": 2.7456634170900268e-05, "loss": 1.5298, "step": 99010 }, { "epoch": 4.52, "learning_rate": 2.7454345736646986e-05, "loss": 1.4418, "step": 99020 }, { "epoch": 4.52, "learning_rate": 2.7452057302393703e-05, "loss": 1.5247, "step": 99030 }, { "epoch": 4.52, "learning_rate": 2.7449768868140417e-05, "loss": 1.6304, "step": 99040 }, { "epoch": 4.52, "learning_rate": 2.7447480433887135e-05, "loss": 1.5887, "step": 99050 }, { "epoch": 4.52, "learning_rate": 2.7445191999633852e-05, "loss": 1.4232, "step": 99060 }, { "epoch": 4.52, "learning_rate": 2.7442903565380566e-05, "loss": 1.5823, "step": 99070 }, { "epoch": 4.52, "learning_rate": 2.7440615131127284e-05, "loss": 1.3358, "step": 99080 }, { "epoch": 4.52, "learning_rate": 2.7438326696874e-05, "loss": 1.4934, "step": 99090 }, { "epoch": 4.53, "learning_rate": 2.7436038262620716e-05, "loss": 1.5449, "step": 99100 }, { "epoch": 4.53, "learning_rate": 2.7433749828367433e-05, "loss": 1.5611, "step": 99110 }, { "epoch": 4.53, "learning_rate": 2.743146139411415e-05, "loss": 1.6452, "step": 99120 }, { "epoch": 4.53, "learning_rate": 2.7429172959860865e-05, "loss": 1.6611, "step": 99130 }, { "epoch": 4.53, "learning_rate": 2.7426884525607582e-05, "loss": 1.4902, "step": 99140 }, { "epoch": 4.53, "learning_rate": 2.74245960913543e-05, "loss": 1.6465, "step": 99150 }, { "epoch": 4.53, "learning_rate": 2.7422307657101014e-05, "loss": 1.5493, "step": 99160 }, { "epoch": 4.53, "learning_rate": 2.742001922284773e-05, "loss": 1.5375, "step": 99170 }, { "epoch": 4.53, "learning_rate": 2.7417730788594442e-05, "loss": 1.6386, "step": 99180 }, { "epoch": 4.53, "learning_rate": 2.741544235434116e-05, "loss": 1.5755, "step": 99190 }, { "epoch": 4.53, "learning_rate": 2.7413153920087874e-05, "loss": 1.4237, "step": 99200 }, { "epoch": 4.53, "learning_rate": 2.741086548583459e-05, "loss": 1.6045, "step": 99210 }, { "epoch": 4.53, "learning_rate": 2.740857705158131e-05, "loss": 1.3773, "step": 99220 }, { "epoch": 4.53, "learning_rate": 2.7406288617328023e-05, "loss": 1.6283, "step": 99230 }, { "epoch": 4.53, "learning_rate": 2.740400018307474e-05, "loss": 1.583, "step": 99240 }, { "epoch": 4.53, "learning_rate": 2.7401711748821458e-05, "loss": 1.4962, "step": 99250 }, { "epoch": 4.53, "learning_rate": 2.7399423314568172e-05, "loss": 1.4666, "step": 99260 }, { "epoch": 4.53, "learning_rate": 2.739713488031489e-05, "loss": 1.4484, "step": 99270 }, { "epoch": 4.53, "learning_rate": 2.7394846446061607e-05, "loss": 1.5875, "step": 99280 }, { "epoch": 4.53, "learning_rate": 2.739255801180832e-05, "loss": 1.5388, "step": 99290 }, { "epoch": 4.53, "learning_rate": 2.739026957755504e-05, "loss": 1.6905, "step": 99300 }, { "epoch": 4.53, "learning_rate": 2.7387981143301756e-05, "loss": 1.5976, "step": 99310 }, { "epoch": 4.54, "learning_rate": 2.738569270904847e-05, "loss": 1.5669, "step": 99320 }, { "epoch": 4.54, "learning_rate": 2.7383404274795188e-05, "loss": 1.5231, "step": 99330 }, { "epoch": 4.54, "learning_rate": 2.7381115840541906e-05, "loss": 1.6499, "step": 99340 }, { "epoch": 4.54, "learning_rate": 2.737882740628862e-05, "loss": 1.5778, "step": 99350 }, { "epoch": 4.54, "learning_rate": 2.7376538972035337e-05, "loss": 1.406, "step": 99360 }, { "epoch": 4.54, "learning_rate": 2.7374250537782055e-05, "loss": 1.4234, "step": 99370 }, { "epoch": 4.54, "learning_rate": 2.7371962103528766e-05, "loss": 1.5111, "step": 99380 }, { "epoch": 4.54, "learning_rate": 2.736967366927548e-05, "loss": 1.5433, "step": 99390 }, { "epoch": 4.54, "learning_rate": 2.7367385235022197e-05, "loss": 1.5254, "step": 99400 }, { "epoch": 4.54, "learning_rate": 2.7365096800768915e-05, "loss": 1.5679, "step": 99410 }, { "epoch": 4.54, "learning_rate": 2.736280836651563e-05, "loss": 1.4951, "step": 99420 }, { "epoch": 4.54, "learning_rate": 2.7360519932262346e-05, "loss": 1.7646, "step": 99430 }, { "epoch": 4.54, "learning_rate": 2.7358231498009064e-05, "loss": 1.7425, "step": 99440 }, { "epoch": 4.54, "learning_rate": 2.7355943063755778e-05, "loss": 1.4649, "step": 99450 }, { "epoch": 4.54, "learning_rate": 2.7353654629502496e-05, "loss": 1.4198, "step": 99460 }, { "epoch": 4.54, "learning_rate": 2.7351366195249213e-05, "loss": 1.5171, "step": 99470 }, { "epoch": 4.54, "learning_rate": 2.7349077760995927e-05, "loss": 1.6558, "step": 99480 }, { "epoch": 4.54, "learning_rate": 2.7346789326742645e-05, "loss": 1.6113, "step": 99490 }, { "epoch": 4.54, "learning_rate": 2.7344500892489362e-05, "loss": 1.7047, "step": 99500 }, { "epoch": 4.54, "learning_rate": 2.7342212458236076e-05, "loss": 1.5856, "step": 99510 }, { "epoch": 4.54, "learning_rate": 2.7339924023982794e-05, "loss": 1.3504, "step": 99520 }, { "epoch": 4.54, "learning_rate": 2.733763558972951e-05, "loss": 1.5998, "step": 99530 }, { "epoch": 4.55, "learning_rate": 2.7335347155476226e-05, "loss": 1.6006, "step": 99540 }, { "epoch": 4.55, "learning_rate": 2.7333058721222943e-05, "loss": 1.5305, "step": 99550 }, { "epoch": 4.55, "learning_rate": 2.733077028696966e-05, "loss": 1.604, "step": 99560 }, { "epoch": 4.55, "learning_rate": 2.7328481852716375e-05, "loss": 1.3544, "step": 99570 }, { "epoch": 4.55, "learning_rate": 2.7326193418463085e-05, "loss": 1.5185, "step": 99580 }, { "epoch": 4.55, "learning_rate": 2.7323904984209803e-05, "loss": 1.7163, "step": 99590 }, { "epoch": 4.55, "learning_rate": 2.732161654995652e-05, "loss": 1.8319, "step": 99600 }, { "epoch": 4.55, "learning_rate": 2.7319328115703235e-05, "loss": 1.5914, "step": 99610 }, { "epoch": 4.55, "learning_rate": 2.7317039681449952e-05, "loss": 1.4005, "step": 99620 }, { "epoch": 4.55, "learning_rate": 2.731475124719667e-05, "loss": 1.6006, "step": 99630 }, { "epoch": 4.55, "learning_rate": 2.7312462812943384e-05, "loss": 1.4893, "step": 99640 }, { "epoch": 4.55, "learning_rate": 2.73101743786901e-05, "loss": 1.7202, "step": 99650 }, { "epoch": 4.55, "learning_rate": 2.730788594443682e-05, "loss": 1.5884, "step": 99660 }, { "epoch": 4.55, "learning_rate": 2.7305597510183533e-05, "loss": 1.7614, "step": 99670 }, { "epoch": 4.55, "learning_rate": 2.730330907593025e-05, "loss": 1.4733, "step": 99680 }, { "epoch": 4.55, "learning_rate": 2.7301020641676968e-05, "loss": 1.5418, "step": 99690 }, { "epoch": 4.55, "learning_rate": 2.7298732207423682e-05, "loss": 1.7745, "step": 99700 }, { "epoch": 4.55, "learning_rate": 2.72964437731704e-05, "loss": 1.5416, "step": 99710 }, { "epoch": 4.55, "learning_rate": 2.7294155338917117e-05, "loss": 1.6483, "step": 99720 }, { "epoch": 4.55, "learning_rate": 2.729186690466383e-05, "loss": 1.5792, "step": 99730 }, { "epoch": 4.55, "learning_rate": 2.728957847041055e-05, "loss": 1.4844, "step": 99740 }, { "epoch": 4.55, "learning_rate": 2.7287290036157266e-05, "loss": 1.512, "step": 99750 }, { "epoch": 4.56, "learning_rate": 2.728500160190398e-05, "loss": 1.3539, "step": 99760 }, { "epoch": 4.56, "learning_rate": 2.728271316765069e-05, "loss": 1.5628, "step": 99770 }, { "epoch": 4.56, "learning_rate": 2.728042473339741e-05, "loss": 1.3408, "step": 99780 }, { "epoch": 4.56, "learning_rate": 2.7278136299144126e-05, "loss": 1.5093, "step": 99790 }, { "epoch": 4.56, "learning_rate": 2.727584786489084e-05, "loss": 1.4522, "step": 99800 }, { "epoch": 4.56, "learning_rate": 2.7273559430637558e-05, "loss": 1.4464, "step": 99810 }, { "epoch": 4.56, "learning_rate": 2.7271270996384275e-05, "loss": 1.6025, "step": 99820 }, { "epoch": 4.56, "learning_rate": 2.726898256213099e-05, "loss": 1.4323, "step": 99830 }, { "epoch": 4.56, "learning_rate": 2.7266694127877707e-05, "loss": 1.7878, "step": 99840 }, { "epoch": 4.56, "learning_rate": 2.7264405693624425e-05, "loss": 1.6778, "step": 99850 }, { "epoch": 4.56, "learning_rate": 2.726211725937114e-05, "loss": 1.5195, "step": 99860 }, { "epoch": 4.56, "learning_rate": 2.7259828825117856e-05, "loss": 1.6359, "step": 99870 }, { "epoch": 4.56, "learning_rate": 2.725754039086457e-05, "loss": 1.5855, "step": 99880 }, { "epoch": 4.56, "learning_rate": 2.7255251956611288e-05, "loss": 1.6301, "step": 99890 }, { "epoch": 4.56, "learning_rate": 2.7252963522358005e-05, "loss": 1.462, "step": 99900 }, { "epoch": 4.56, "learning_rate": 2.725067508810472e-05, "loss": 1.5702, "step": 99910 }, { "epoch": 4.56, "learning_rate": 2.7248386653851437e-05, "loss": 1.596, "step": 99920 }, { "epoch": 4.56, "learning_rate": 2.7246098219598155e-05, "loss": 1.6414, "step": 99930 }, { "epoch": 4.56, "learning_rate": 2.724380978534487e-05, "loss": 1.5222, "step": 99940 }, { "epoch": 4.56, "learning_rate": 2.7241521351091586e-05, "loss": 1.5379, "step": 99950 }, { "epoch": 4.56, "learning_rate": 2.7239232916838304e-05, "loss": 1.6192, "step": 99960 }, { "epoch": 4.56, "learning_rate": 2.7236944482585015e-05, "loss": 1.4883, "step": 99970 }, { "epoch": 4.57, "learning_rate": 2.723465604833173e-05, "loss": 1.5606, "step": 99980 }, { "epoch": 4.57, "learning_rate": 2.7232367614078446e-05, "loss": 1.5602, "step": 99990 }, { "epoch": 4.57, "learning_rate": 2.7230079179825164e-05, "loss": 1.6559, "step": 100000 }, { "epoch": 4.57, "learning_rate": 2.7227790745571878e-05, "loss": 1.5085, "step": 100010 }, { "epoch": 4.57, "learning_rate": 2.7225502311318595e-05, "loss": 1.6047, "step": 100020 }, { "epoch": 4.57, "learning_rate": 2.7223213877065313e-05, "loss": 1.5495, "step": 100030 }, { "epoch": 4.57, "learning_rate": 2.7220925442812027e-05, "loss": 1.7417, "step": 100040 }, { "epoch": 4.57, "learning_rate": 2.7218637008558745e-05, "loss": 1.3781, "step": 100050 }, { "epoch": 4.57, "learning_rate": 2.7216348574305462e-05, "loss": 1.6155, "step": 100060 }, { "epoch": 4.57, "learning_rate": 2.7214060140052176e-05, "loss": 1.5217, "step": 100070 }, { "epoch": 4.57, "learning_rate": 2.7211771705798894e-05, "loss": 1.5373, "step": 100080 }, { "epoch": 4.57, "learning_rate": 2.720948327154561e-05, "loss": 1.6564, "step": 100090 }, { "epoch": 4.57, "learning_rate": 2.7207194837292325e-05, "loss": 1.4705, "step": 100100 }, { "epoch": 4.57, "learning_rate": 2.7204906403039043e-05, "loss": 1.6093, "step": 100110 }, { "epoch": 4.57, "learning_rate": 2.720261796878576e-05, "loss": 1.6721, "step": 100120 }, { "epoch": 4.57, "learning_rate": 2.7200329534532475e-05, "loss": 1.5606, "step": 100130 }, { "epoch": 4.57, "learning_rate": 2.7198041100279192e-05, "loss": 1.5723, "step": 100140 }, { "epoch": 4.57, "learning_rate": 2.719575266602591e-05, "loss": 1.5728, "step": 100150 }, { "epoch": 4.57, "learning_rate": 2.7193464231772624e-05, "loss": 1.5108, "step": 100160 }, { "epoch": 4.57, "learning_rate": 2.7191175797519335e-05, "loss": 1.521, "step": 100170 }, { "epoch": 4.57, "learning_rate": 2.7188887363266052e-05, "loss": 1.7486, "step": 100180 }, { "epoch": 4.57, "learning_rate": 2.718659892901277e-05, "loss": 1.5186, "step": 100190 }, { "epoch": 4.58, "learning_rate": 2.7184310494759484e-05, "loss": 1.4998, "step": 100200 }, { "epoch": 4.58, "learning_rate": 2.71820220605062e-05, "loss": 1.5942, "step": 100210 }, { "epoch": 4.58, "learning_rate": 2.717973362625292e-05, "loss": 1.5761, "step": 100220 }, { "epoch": 4.58, "learning_rate": 2.7177445191999633e-05, "loss": 1.506, "step": 100230 }, { "epoch": 4.58, "learning_rate": 2.717515675774635e-05, "loss": 1.6252, "step": 100240 }, { "epoch": 4.58, "learning_rate": 2.7172868323493068e-05, "loss": 1.5649, "step": 100250 }, { "epoch": 4.58, "learning_rate": 2.7170579889239782e-05, "loss": 1.5905, "step": 100260 }, { "epoch": 4.58, "learning_rate": 2.71682914549865e-05, "loss": 1.6109, "step": 100270 }, { "epoch": 4.58, "learning_rate": 2.7166003020733217e-05, "loss": 1.5518, "step": 100280 }, { "epoch": 4.58, "learning_rate": 2.716371458647993e-05, "loss": 1.787, "step": 100290 }, { "epoch": 4.58, "learning_rate": 2.716142615222665e-05, "loss": 1.4835, "step": 100300 }, { "epoch": 4.58, "learning_rate": 2.7159137717973366e-05, "loss": 1.4675, "step": 100310 }, { "epoch": 4.58, "learning_rate": 2.715684928372008e-05, "loss": 1.6251, "step": 100320 }, { "epoch": 4.58, "learning_rate": 2.7154560849466798e-05, "loss": 1.4232, "step": 100330 }, { "epoch": 4.58, "learning_rate": 2.7152272415213515e-05, "loss": 1.6358, "step": 100340 }, { "epoch": 4.58, "learning_rate": 2.714998398096023e-05, "loss": 1.6331, "step": 100350 }, { "epoch": 4.58, "learning_rate": 2.7147695546706947e-05, "loss": 1.4498, "step": 100360 }, { "epoch": 4.58, "learning_rate": 2.7145407112453658e-05, "loss": 1.711, "step": 100370 }, { "epoch": 4.58, "learning_rate": 2.7143118678200375e-05, "loss": 1.717, "step": 100380 }, { "epoch": 4.58, "learning_rate": 2.714083024394709e-05, "loss": 1.5951, "step": 100390 }, { "epoch": 4.58, "learning_rate": 2.7138541809693807e-05, "loss": 1.6389, "step": 100400 }, { "epoch": 4.58, "learning_rate": 2.7136253375440525e-05, "loss": 1.5797, "step": 100410 }, { "epoch": 4.59, "learning_rate": 2.713396494118724e-05, "loss": 1.5069, "step": 100420 }, { "epoch": 4.59, "learning_rate": 2.7131676506933956e-05, "loss": 1.6452, "step": 100430 }, { "epoch": 4.59, "learning_rate": 2.7129388072680674e-05, "loss": 1.4693, "step": 100440 }, { "epoch": 4.59, "learning_rate": 2.7127099638427388e-05, "loss": 1.5009, "step": 100450 }, { "epoch": 4.59, "learning_rate": 2.7124811204174105e-05, "loss": 1.7355, "step": 100460 }, { "epoch": 4.59, "learning_rate": 2.7122522769920823e-05, "loss": 1.483, "step": 100470 }, { "epoch": 4.59, "learning_rate": 2.7120234335667537e-05, "loss": 1.4385, "step": 100480 }, { "epoch": 4.59, "learning_rate": 2.7117945901414255e-05, "loss": 1.5241, "step": 100490 }, { "epoch": 4.59, "learning_rate": 2.7115657467160972e-05, "loss": 1.5559, "step": 100500 }, { "epoch": 4.59, "learning_rate": 2.7113369032907686e-05, "loss": 1.625, "step": 100510 }, { "epoch": 4.59, "learning_rate": 2.7111080598654404e-05, "loss": 1.5715, "step": 100520 }, { "epoch": 4.59, "learning_rate": 2.710879216440112e-05, "loss": 1.4921, "step": 100530 }, { "epoch": 4.59, "learning_rate": 2.7106503730147835e-05, "loss": 1.4012, "step": 100540 }, { "epoch": 4.59, "learning_rate": 2.7104215295894553e-05, "loss": 1.4907, "step": 100550 }, { "epoch": 4.59, "learning_rate": 2.7101926861641264e-05, "loss": 1.6121, "step": 100560 }, { "epoch": 4.59, "learning_rate": 2.709963842738798e-05, "loss": 1.5917, "step": 100570 }, { "epoch": 4.59, "learning_rate": 2.7097349993134695e-05, "loss": 1.7038, "step": 100580 }, { "epoch": 4.59, "learning_rate": 2.7095061558881413e-05, "loss": 1.5744, "step": 100590 }, { "epoch": 4.59, "learning_rate": 2.709277312462813e-05, "loss": 1.5995, "step": 100600 }, { "epoch": 4.59, "learning_rate": 2.7090484690374844e-05, "loss": 1.5883, "step": 100610 }, { "epoch": 4.59, "learning_rate": 2.7088196256121562e-05, "loss": 1.6225, "step": 100620 }, { "epoch": 4.6, "learning_rate": 2.708590782186828e-05, "loss": 1.444, "step": 100630 }, { "epoch": 4.6, "learning_rate": 2.7083619387614994e-05, "loss": 1.7115, "step": 100640 }, { "epoch": 4.6, "learning_rate": 2.708133095336171e-05, "loss": 1.5906, "step": 100650 }, { "epoch": 4.6, "learning_rate": 2.707904251910843e-05, "loss": 1.6327, "step": 100660 }, { "epoch": 4.6, "learning_rate": 2.7076754084855143e-05, "loss": 1.6103, "step": 100670 }, { "epoch": 4.6, "learning_rate": 2.707446565060186e-05, "loss": 1.474, "step": 100680 }, { "epoch": 4.6, "learning_rate": 2.7072177216348578e-05, "loss": 1.6755, "step": 100690 }, { "epoch": 4.6, "learning_rate": 2.7069888782095292e-05, "loss": 1.4367, "step": 100700 }, { "epoch": 4.6, "learning_rate": 2.706760034784201e-05, "loss": 1.6434, "step": 100710 }, { "epoch": 4.6, "learning_rate": 2.7065311913588727e-05, "loss": 1.4852, "step": 100720 }, { "epoch": 4.6, "learning_rate": 2.706302347933544e-05, "loss": 1.6116, "step": 100730 }, { "epoch": 4.6, "learning_rate": 2.706073504508216e-05, "loss": 1.4649, "step": 100740 }, { "epoch": 4.6, "learning_rate": 2.7058446610828876e-05, "loss": 1.5194, "step": 100750 }, { "epoch": 4.6, "learning_rate": 2.7056158176575587e-05, "loss": 1.7031, "step": 100760 }, { "epoch": 4.6, "learning_rate": 2.70538697423223e-05, "loss": 1.5536, "step": 100770 }, { "epoch": 4.6, "learning_rate": 2.705158130806902e-05, "loss": 1.4044, "step": 100780 }, { "epoch": 4.6, "learning_rate": 2.7049292873815736e-05, "loss": 1.5883, "step": 100790 }, { "epoch": 4.6, "learning_rate": 2.704700443956245e-05, "loss": 1.635, "step": 100800 }, { "epoch": 4.6, "learning_rate": 2.7044716005309168e-05, "loss": 1.5954, "step": 100810 }, { "epoch": 4.6, "learning_rate": 2.7042427571055885e-05, "loss": 1.5165, "step": 100820 }, { "epoch": 4.6, "learning_rate": 2.70401391368026e-05, "loss": 1.4086, "step": 100830 }, { "epoch": 4.6, "learning_rate": 2.7037850702549317e-05, "loss": 1.6021, "step": 100840 }, { "epoch": 4.61, "learning_rate": 2.7035562268296035e-05, "loss": 1.582, "step": 100850 }, { "epoch": 4.61, "learning_rate": 2.703327383404275e-05, "loss": 1.5789, "step": 100860 }, { "epoch": 4.61, "learning_rate": 2.7030985399789466e-05, "loss": 1.5879, "step": 100870 }, { "epoch": 4.61, "learning_rate": 2.7028696965536184e-05, "loss": 1.4632, "step": 100880 }, { "epoch": 4.61, "learning_rate": 2.7026408531282898e-05, "loss": 1.5722, "step": 100890 }, { "epoch": 4.61, "learning_rate": 2.7024120097029615e-05, "loss": 1.6661, "step": 100900 }, { "epoch": 4.61, "learning_rate": 2.7021831662776333e-05, "loss": 1.7358, "step": 100910 }, { "epoch": 4.61, "learning_rate": 2.7019543228523047e-05, "loss": 1.5553, "step": 100920 }, { "epoch": 4.61, "learning_rate": 2.7017254794269765e-05, "loss": 1.5813, "step": 100930 }, { "epoch": 4.61, "learning_rate": 2.7014966360016482e-05, "loss": 1.5831, "step": 100940 }, { "epoch": 4.61, "learning_rate": 2.7012677925763196e-05, "loss": 1.4408, "step": 100950 }, { "epoch": 4.61, "learning_rate": 2.7010389491509907e-05, "loss": 1.4421, "step": 100960 }, { "epoch": 4.61, "learning_rate": 2.7008101057256624e-05, "loss": 1.5629, "step": 100970 }, { "epoch": 4.61, "learning_rate": 2.7005812623003342e-05, "loss": 1.6578, "step": 100980 }, { "epoch": 4.61, "learning_rate": 2.7003524188750056e-05, "loss": 1.5737, "step": 100990 }, { "epoch": 4.61, "learning_rate": 2.7001235754496774e-05, "loss": 1.6981, "step": 101000 }, { "epoch": 4.61, "learning_rate": 2.699894732024349e-05, "loss": 1.569, "step": 101010 }, { "epoch": 4.61, "learning_rate": 2.6996658885990205e-05, "loss": 1.4461, "step": 101020 }, { "epoch": 4.61, "learning_rate": 2.6994370451736923e-05, "loss": 1.5594, "step": 101030 }, { "epoch": 4.61, "learning_rate": 2.6992082017483637e-05, "loss": 1.6166, "step": 101040 }, { "epoch": 4.61, "learning_rate": 2.6989793583230354e-05, "loss": 1.4682, "step": 101050 }, { "epoch": 4.61, "learning_rate": 2.6987505148977072e-05, "loss": 1.3604, "step": 101060 }, { "epoch": 4.62, "learning_rate": 2.6985216714723786e-05, "loss": 1.6303, "step": 101070 }, { "epoch": 4.62, "learning_rate": 2.6982928280470504e-05, "loss": 1.5447, "step": 101080 }, { "epoch": 4.62, "learning_rate": 2.698063984621722e-05, "loss": 1.519, "step": 101090 }, { "epoch": 4.62, "learning_rate": 2.6978351411963935e-05, "loss": 1.5671, "step": 101100 }, { "epoch": 4.62, "learning_rate": 2.6976062977710653e-05, "loss": 1.6707, "step": 101110 }, { "epoch": 4.62, "learning_rate": 2.697377454345737e-05, "loss": 1.3315, "step": 101120 }, { "epoch": 4.62, "learning_rate": 2.6971486109204084e-05, "loss": 1.5561, "step": 101130 }, { "epoch": 4.62, "learning_rate": 2.6969197674950802e-05, "loss": 1.4519, "step": 101140 }, { "epoch": 4.62, "learning_rate": 2.696690924069752e-05, "loss": 1.6958, "step": 101150 }, { "epoch": 4.62, "learning_rate": 2.696462080644423e-05, "loss": 1.4566, "step": 101160 }, { "epoch": 4.62, "learning_rate": 2.6962332372190944e-05, "loss": 1.5033, "step": 101170 }, { "epoch": 4.62, "learning_rate": 2.6960043937937662e-05, "loss": 1.5897, "step": 101180 }, { "epoch": 4.62, "learning_rate": 2.695775550368438e-05, "loss": 1.6502, "step": 101190 }, { "epoch": 4.62, "learning_rate": 2.6955467069431094e-05, "loss": 1.5108, "step": 101200 }, { "epoch": 4.62, "learning_rate": 2.695317863517781e-05, "loss": 1.4918, "step": 101210 }, { "epoch": 4.62, "learning_rate": 2.695089020092453e-05, "loss": 1.4584, "step": 101220 }, { "epoch": 4.62, "learning_rate": 2.6948601766671243e-05, "loss": 1.4352, "step": 101230 }, { "epoch": 4.62, "learning_rate": 2.694631333241796e-05, "loss": 1.5938, "step": 101240 }, { "epoch": 4.62, "learning_rate": 2.6944024898164678e-05, "loss": 1.6714, "step": 101250 }, { "epoch": 4.62, "learning_rate": 2.6941736463911392e-05, "loss": 1.3984, "step": 101260 }, { "epoch": 4.62, "learning_rate": 2.693944802965811e-05, "loss": 1.5033, "step": 101270 }, { "epoch": 4.62, "learning_rate": 2.6937159595404827e-05, "loss": 1.5169, "step": 101280 }, { "epoch": 4.63, "learning_rate": 2.693487116115154e-05, "loss": 1.544, "step": 101290 }, { "epoch": 4.63, "learning_rate": 2.693258272689826e-05, "loss": 1.6214, "step": 101300 }, { "epoch": 4.63, "learning_rate": 2.6930294292644976e-05, "loss": 1.5709, "step": 101310 }, { "epoch": 4.63, "learning_rate": 2.692800585839169e-05, "loss": 1.6208, "step": 101320 }, { "epoch": 4.63, "learning_rate": 2.6925717424138408e-05, "loss": 1.6701, "step": 101330 }, { "epoch": 4.63, "learning_rate": 2.6923428989885125e-05, "loss": 1.3081, "step": 101340 }, { "epoch": 4.63, "learning_rate": 2.6921140555631836e-05, "loss": 1.498, "step": 101350 }, { "epoch": 4.63, "learning_rate": 2.691885212137855e-05, "loss": 1.6329, "step": 101360 }, { "epoch": 4.63, "learning_rate": 2.6916563687125268e-05, "loss": 1.4965, "step": 101370 }, { "epoch": 4.63, "learning_rate": 2.6914275252871985e-05, "loss": 1.5499, "step": 101380 }, { "epoch": 4.63, "learning_rate": 2.69119868186187e-05, "loss": 1.5563, "step": 101390 }, { "epoch": 4.63, "learning_rate": 2.6909698384365417e-05, "loss": 1.7121, "step": 101400 }, { "epoch": 4.63, "learning_rate": 2.6907409950112134e-05, "loss": 1.5957, "step": 101410 }, { "epoch": 4.63, "learning_rate": 2.690512151585885e-05, "loss": 1.5844, "step": 101420 }, { "epoch": 4.63, "learning_rate": 2.6902833081605566e-05, "loss": 1.6859, "step": 101430 }, { "epoch": 4.63, "learning_rate": 2.6900544647352284e-05, "loss": 1.5275, "step": 101440 }, { "epoch": 4.63, "learning_rate": 2.6898256213098998e-05, "loss": 1.4498, "step": 101450 }, { "epoch": 4.63, "learning_rate": 2.6895967778845715e-05, "loss": 1.5769, "step": 101460 }, { "epoch": 4.63, "learning_rate": 2.6893679344592433e-05, "loss": 1.4351, "step": 101470 }, { "epoch": 4.63, "learning_rate": 2.6891390910339147e-05, "loss": 1.4863, "step": 101480 }, { "epoch": 4.63, "learning_rate": 2.6889102476085864e-05, "loss": 1.6369, "step": 101490 }, { "epoch": 4.63, "learning_rate": 2.6886814041832582e-05, "loss": 1.6407, "step": 101500 }, { "epoch": 4.64, "learning_rate": 2.6884525607579296e-05, "loss": 1.44, "step": 101510 }, { "epoch": 4.64, "learning_rate": 2.6882237173326014e-05, "loss": 1.5152, "step": 101520 }, { "epoch": 4.64, "learning_rate": 2.687994873907273e-05, "loss": 1.6724, "step": 101530 }, { "epoch": 4.64, "learning_rate": 2.6877660304819445e-05, "loss": 1.5936, "step": 101540 }, { "epoch": 4.64, "learning_rate": 2.6875371870566156e-05, "loss": 1.6906, "step": 101550 }, { "epoch": 4.64, "learning_rate": 2.6873083436312874e-05, "loss": 1.6588, "step": 101560 }, { "epoch": 4.64, "learning_rate": 2.687079500205959e-05, "loss": 1.6386, "step": 101570 }, { "epoch": 4.64, "learning_rate": 2.6868506567806305e-05, "loss": 1.5034, "step": 101580 }, { "epoch": 4.64, "learning_rate": 2.6866218133553023e-05, "loss": 1.4928, "step": 101590 }, { "epoch": 4.64, "learning_rate": 2.686392969929974e-05, "loss": 1.6171, "step": 101600 }, { "epoch": 4.64, "learning_rate": 2.6861641265046454e-05, "loss": 1.5835, "step": 101610 }, { "epoch": 4.64, "learning_rate": 2.6859352830793172e-05, "loss": 1.3106, "step": 101620 }, { "epoch": 4.64, "learning_rate": 2.685706439653989e-05, "loss": 1.5613, "step": 101630 }, { "epoch": 4.64, "learning_rate": 2.6854775962286604e-05, "loss": 1.4869, "step": 101640 }, { "epoch": 4.64, "learning_rate": 2.685248752803332e-05, "loss": 1.5147, "step": 101650 }, { "epoch": 4.64, "learning_rate": 2.685019909378004e-05, "loss": 1.7096, "step": 101660 }, { "epoch": 4.64, "learning_rate": 2.6847910659526753e-05, "loss": 1.4862, "step": 101670 }, { "epoch": 4.64, "learning_rate": 2.684562222527347e-05, "loss": 1.4827, "step": 101680 }, { "epoch": 4.64, "learning_rate": 2.6843333791020188e-05, "loss": 1.5956, "step": 101690 }, { "epoch": 4.64, "learning_rate": 2.6841045356766902e-05, "loss": 1.375, "step": 101700 }, { "epoch": 4.64, "learning_rate": 2.683875692251362e-05, "loss": 1.6165, "step": 101710 }, { "epoch": 4.64, "learning_rate": 2.6836468488260337e-05, "loss": 1.5948, "step": 101720 }, { "epoch": 4.65, "learning_rate": 2.683418005400705e-05, "loss": 1.6016, "step": 101730 }, { "epoch": 4.65, "learning_rate": 2.683189161975377e-05, "loss": 1.5604, "step": 101740 }, { "epoch": 4.65, "learning_rate": 2.682960318550048e-05, "loss": 1.4749, "step": 101750 }, { "epoch": 4.65, "learning_rate": 2.6827314751247197e-05, "loss": 1.6459, "step": 101760 }, { "epoch": 4.65, "learning_rate": 2.682502631699391e-05, "loss": 1.4452, "step": 101770 }, { "epoch": 4.65, "learning_rate": 2.682273788274063e-05, "loss": 1.5926, "step": 101780 }, { "epoch": 4.65, "learning_rate": 2.6820449448487346e-05, "loss": 1.4612, "step": 101790 }, { "epoch": 4.65, "learning_rate": 2.681816101423406e-05, "loss": 1.5702, "step": 101800 }, { "epoch": 4.65, "learning_rate": 2.6815872579980778e-05, "loss": 1.4888, "step": 101810 }, { "epoch": 4.65, "learning_rate": 2.6813584145727495e-05, "loss": 1.5187, "step": 101820 }, { "epoch": 4.65, "learning_rate": 2.681129571147421e-05, "loss": 1.4877, "step": 101830 }, { "epoch": 4.65, "learning_rate": 2.6809007277220927e-05, "loss": 1.5032, "step": 101840 }, { "epoch": 4.65, "learning_rate": 2.6806718842967644e-05, "loss": 1.4175, "step": 101850 }, { "epoch": 4.65, "learning_rate": 2.680443040871436e-05, "loss": 1.4202, "step": 101860 }, { "epoch": 4.65, "learning_rate": 2.6802141974461076e-05, "loss": 1.7678, "step": 101870 }, { "epoch": 4.65, "learning_rate": 2.6799853540207794e-05, "loss": 1.4587, "step": 101880 }, { "epoch": 4.65, "learning_rate": 2.6797565105954508e-05, "loss": 1.5342, "step": 101890 }, { "epoch": 4.65, "learning_rate": 2.6795276671701225e-05, "loss": 1.5288, "step": 101900 }, { "epoch": 4.65, "learning_rate": 2.6792988237447943e-05, "loss": 1.7019, "step": 101910 }, { "epoch": 4.65, "learning_rate": 2.6790699803194657e-05, "loss": 1.444, "step": 101920 }, { "epoch": 4.65, "learning_rate": 2.6788411368941374e-05, "loss": 1.5813, "step": 101930 }, { "epoch": 4.65, "learning_rate": 2.6786122934688092e-05, "loss": 1.7203, "step": 101940 }, { "epoch": 4.66, "learning_rate": 2.6783834500434803e-05, "loss": 1.5956, "step": 101950 }, { "epoch": 4.66, "learning_rate": 2.6781546066181517e-05, "loss": 1.6404, "step": 101960 }, { "epoch": 4.66, "learning_rate": 2.6779257631928234e-05, "loss": 1.6982, "step": 101970 }, { "epoch": 4.66, "learning_rate": 2.6776969197674952e-05, "loss": 1.5648, "step": 101980 }, { "epoch": 4.66, "learning_rate": 2.6774680763421666e-05, "loss": 1.6687, "step": 101990 }, { "epoch": 4.66, "learning_rate": 2.6772392329168383e-05, "loss": 1.4844, "step": 102000 }, { "epoch": 4.66, "learning_rate": 2.67701038949151e-05, "loss": 1.5263, "step": 102010 }, { "epoch": 4.66, "learning_rate": 2.6767815460661815e-05, "loss": 1.612, "step": 102020 }, { "epoch": 4.66, "learning_rate": 2.6765527026408533e-05, "loss": 1.5616, "step": 102030 }, { "epoch": 4.66, "learning_rate": 2.676323859215525e-05, "loss": 1.5738, "step": 102040 }, { "epoch": 4.66, "learning_rate": 2.6760950157901964e-05, "loss": 1.4267, "step": 102050 }, { "epoch": 4.66, "learning_rate": 2.6758661723648682e-05, "loss": 1.6715, "step": 102060 }, { "epoch": 4.66, "learning_rate": 2.67563732893954e-05, "loss": 1.5946, "step": 102070 }, { "epoch": 4.66, "learning_rate": 2.6754084855142114e-05, "loss": 1.5564, "step": 102080 }, { "epoch": 4.66, "learning_rate": 2.675179642088883e-05, "loss": 1.4643, "step": 102090 }, { "epoch": 4.66, "learning_rate": 2.674950798663555e-05, "loss": 1.5755, "step": 102100 }, { "epoch": 4.66, "learning_rate": 2.6747219552382263e-05, "loss": 1.4138, "step": 102110 }, { "epoch": 4.66, "learning_rate": 2.674493111812898e-05, "loss": 1.6424, "step": 102120 }, { "epoch": 4.66, "learning_rate": 2.6742642683875698e-05, "loss": 1.3508, "step": 102130 }, { "epoch": 4.66, "learning_rate": 2.674035424962241e-05, "loss": 1.5464, "step": 102140 }, { "epoch": 4.66, "learning_rate": 2.6738065815369123e-05, "loss": 1.5373, "step": 102150 }, { "epoch": 4.66, "learning_rate": 2.673577738111584e-05, "loss": 1.5197, "step": 102160 }, { "epoch": 4.67, "learning_rate": 2.6733488946862558e-05, "loss": 1.526, "step": 102170 }, { "epoch": 4.67, "learning_rate": 2.6731200512609272e-05, "loss": 1.3547, "step": 102180 }, { "epoch": 4.67, "learning_rate": 2.672891207835599e-05, "loss": 1.3955, "step": 102190 }, { "epoch": 4.67, "learning_rate": 2.6726623644102707e-05, "loss": 1.5185, "step": 102200 }, { "epoch": 4.67, "learning_rate": 2.672433520984942e-05, "loss": 1.3976, "step": 102210 }, { "epoch": 4.67, "learning_rate": 2.672204677559614e-05, "loss": 1.4444, "step": 102220 }, { "epoch": 4.67, "learning_rate": 2.6719758341342853e-05, "loss": 1.3724, "step": 102230 }, { "epoch": 4.67, "learning_rate": 2.671746990708957e-05, "loss": 1.5245, "step": 102240 }, { "epoch": 4.67, "learning_rate": 2.6715181472836288e-05, "loss": 1.6216, "step": 102250 }, { "epoch": 4.67, "learning_rate": 2.6712893038583002e-05, "loss": 1.4016, "step": 102260 }, { "epoch": 4.67, "learning_rate": 2.671060460432972e-05, "loss": 1.2879, "step": 102270 }, { "epoch": 4.67, "learning_rate": 2.6708316170076437e-05, "loss": 1.5627, "step": 102280 }, { "epoch": 4.67, "learning_rate": 2.670602773582315e-05, "loss": 1.5718, "step": 102290 }, { "epoch": 4.67, "learning_rate": 2.670373930156987e-05, "loss": 1.532, "step": 102300 }, { "epoch": 4.67, "learning_rate": 2.6701450867316586e-05, "loss": 1.5751, "step": 102310 }, { "epoch": 4.67, "learning_rate": 2.66991624330633e-05, "loss": 1.5692, "step": 102320 }, { "epoch": 4.67, "learning_rate": 2.6696873998810018e-05, "loss": 1.5411, "step": 102330 }, { "epoch": 4.67, "learning_rate": 2.669458556455673e-05, "loss": 1.6005, "step": 102340 }, { "epoch": 4.67, "learning_rate": 2.6692297130303446e-05, "loss": 1.2736, "step": 102350 }, { "epoch": 4.67, "learning_rate": 2.669000869605016e-05, "loss": 1.554, "step": 102360 }, { "epoch": 4.67, "learning_rate": 2.6687720261796878e-05, "loss": 1.7468, "step": 102370 }, { "epoch": 4.67, "learning_rate": 2.6685431827543595e-05, "loss": 1.5555, "step": 102380 }, { "epoch": 4.68, "learning_rate": 2.668314339329031e-05, "loss": 1.6498, "step": 102390 }, { "epoch": 4.68, "learning_rate": 2.6680854959037027e-05, "loss": 1.5404, "step": 102400 }, { "epoch": 4.68, "learning_rate": 2.6678566524783744e-05, "loss": 1.4399, "step": 102410 }, { "epoch": 4.68, "learning_rate": 2.667627809053046e-05, "loss": 1.4337, "step": 102420 }, { "epoch": 4.68, "learning_rate": 2.6673989656277176e-05, "loss": 1.4498, "step": 102430 }, { "epoch": 4.68, "learning_rate": 2.6671701222023893e-05, "loss": 1.3763, "step": 102440 }, { "epoch": 4.68, "learning_rate": 2.6669412787770608e-05, "loss": 1.5421, "step": 102450 }, { "epoch": 4.68, "learning_rate": 2.6667124353517325e-05, "loss": 1.3908, "step": 102460 }, { "epoch": 4.68, "learning_rate": 2.6664835919264043e-05, "loss": 1.48, "step": 102470 }, { "epoch": 4.68, "learning_rate": 2.6662547485010757e-05, "loss": 1.5757, "step": 102480 }, { "epoch": 4.68, "learning_rate": 2.6660259050757474e-05, "loss": 1.393, "step": 102490 }, { "epoch": 4.68, "learning_rate": 2.6657970616504192e-05, "loss": 1.5229, "step": 102500 }, { "epoch": 4.68, "learning_rate": 2.6655682182250906e-05, "loss": 1.4192, "step": 102510 }, { "epoch": 4.68, "learning_rate": 2.6653393747997623e-05, "loss": 1.5455, "step": 102520 }, { "epoch": 4.68, "learning_rate": 2.665110531374434e-05, "loss": 1.8111, "step": 102530 }, { "epoch": 4.68, "learning_rate": 2.6648816879491052e-05, "loss": 1.4282, "step": 102540 }, { "epoch": 4.68, "learning_rate": 2.6646528445237766e-05, "loss": 1.4675, "step": 102550 }, { "epoch": 4.68, "learning_rate": 2.6644240010984483e-05, "loss": 1.3676, "step": 102560 }, { "epoch": 4.68, "learning_rate": 2.66419515767312e-05, "loss": 1.71, "step": 102570 }, { "epoch": 4.68, "learning_rate": 2.6639663142477915e-05, "loss": 1.5863, "step": 102580 }, { "epoch": 4.68, "learning_rate": 2.6637374708224633e-05, "loss": 1.4969, "step": 102590 }, { "epoch": 4.68, "learning_rate": 2.663508627397135e-05, "loss": 1.3063, "step": 102600 }, { "epoch": 4.69, "learning_rate": 2.6632797839718064e-05, "loss": 1.5971, "step": 102610 }, { "epoch": 4.69, "learning_rate": 2.6630509405464782e-05, "loss": 1.5082, "step": 102620 }, { "epoch": 4.69, "learning_rate": 2.66282209712115e-05, "loss": 1.4391, "step": 102630 }, { "epoch": 4.69, "learning_rate": 2.6625932536958213e-05, "loss": 1.6001, "step": 102640 }, { "epoch": 4.69, "learning_rate": 2.662364410270493e-05, "loss": 1.6463, "step": 102650 }, { "epoch": 4.69, "learning_rate": 2.662135566845165e-05, "loss": 1.4595, "step": 102660 }, { "epoch": 4.69, "learning_rate": 2.6619067234198363e-05, "loss": 1.4652, "step": 102670 }, { "epoch": 4.69, "learning_rate": 2.661677879994508e-05, "loss": 1.6251, "step": 102680 }, { "epoch": 4.69, "learning_rate": 2.6614490365691798e-05, "loss": 1.57, "step": 102690 }, { "epoch": 4.69, "learning_rate": 2.6612201931438512e-05, "loss": 1.517, "step": 102700 }, { "epoch": 4.69, "learning_rate": 2.660991349718523e-05, "loss": 1.7137, "step": 102710 }, { "epoch": 4.69, "learning_rate": 2.6607625062931947e-05, "loss": 1.7401, "step": 102720 }, { "epoch": 4.69, "learning_rate": 2.660533662867866e-05, "loss": 1.4229, "step": 102730 }, { "epoch": 4.69, "learning_rate": 2.660304819442537e-05, "loss": 1.4926, "step": 102740 }, { "epoch": 4.69, "learning_rate": 2.660075976017209e-05, "loss": 1.501, "step": 102750 }, { "epoch": 4.69, "learning_rate": 2.6598471325918807e-05, "loss": 1.4752, "step": 102760 }, { "epoch": 4.69, "learning_rate": 2.659618289166552e-05, "loss": 1.5304, "step": 102770 }, { "epoch": 4.69, "learning_rate": 2.659389445741224e-05, "loss": 1.5523, "step": 102780 }, { "epoch": 4.69, "learning_rate": 2.6591606023158956e-05, "loss": 1.5852, "step": 102790 }, { "epoch": 4.69, "learning_rate": 2.658931758890567e-05, "loss": 1.5625, "step": 102800 }, { "epoch": 4.69, "learning_rate": 2.6587029154652388e-05, "loss": 1.5835, "step": 102810 }, { "epoch": 4.7, "learning_rate": 2.6584740720399105e-05, "loss": 1.5418, "step": 102820 }, { "epoch": 4.7, "learning_rate": 2.658245228614582e-05, "loss": 1.7383, "step": 102830 }, { "epoch": 4.7, "learning_rate": 2.6580163851892537e-05, "loss": 1.5908, "step": 102840 }, { "epoch": 4.7, "learning_rate": 2.6577875417639254e-05, "loss": 1.634, "step": 102850 }, { "epoch": 4.7, "learning_rate": 2.657558698338597e-05, "loss": 1.6078, "step": 102860 }, { "epoch": 4.7, "learning_rate": 2.6573298549132686e-05, "loss": 1.6484, "step": 102870 }, { "epoch": 4.7, "learning_rate": 2.6571010114879403e-05, "loss": 1.5438, "step": 102880 }, { "epoch": 4.7, "learning_rate": 2.6568721680626118e-05, "loss": 1.5664, "step": 102890 }, { "epoch": 4.7, "learning_rate": 2.6566433246372835e-05, "loss": 1.4495, "step": 102900 }, { "epoch": 4.7, "learning_rate": 2.6564144812119553e-05, "loss": 1.4066, "step": 102910 }, { "epoch": 4.7, "learning_rate": 2.6561856377866267e-05, "loss": 1.5119, "step": 102920 }, { "epoch": 4.7, "learning_rate": 2.6559567943612977e-05, "loss": 1.2979, "step": 102930 }, { "epoch": 4.7, "learning_rate": 2.6557279509359695e-05, "loss": 1.4175, "step": 102940 }, { "epoch": 4.7, "learning_rate": 2.6554991075106413e-05, "loss": 1.4535, "step": 102950 }, { "epoch": 4.7, "learning_rate": 2.6552702640853127e-05, "loss": 1.5195, "step": 102960 }, { "epoch": 4.7, "learning_rate": 2.6550414206599844e-05, "loss": 1.5677, "step": 102970 }, { "epoch": 4.7, "learning_rate": 2.6548125772346562e-05, "loss": 1.4423, "step": 102980 }, { "epoch": 4.7, "learning_rate": 2.6545837338093276e-05, "loss": 1.5211, "step": 102990 }, { "epoch": 4.7, "learning_rate": 2.6543548903839993e-05, "loss": 1.5001, "step": 103000 }, { "epoch": 4.7, "learning_rate": 2.654126046958671e-05, "loss": 1.4468, "step": 103010 }, { "epoch": 4.7, "learning_rate": 2.6538972035333425e-05, "loss": 1.5473, "step": 103020 }, { "epoch": 4.7, "learning_rate": 2.6536683601080143e-05, "loss": 1.5507, "step": 103030 }, { "epoch": 4.71, "learning_rate": 2.653439516682686e-05, "loss": 1.6517, "step": 103040 }, { "epoch": 4.71, "learning_rate": 2.6532106732573574e-05, "loss": 1.7987, "step": 103050 }, { "epoch": 4.71, "learning_rate": 2.6529818298320292e-05, "loss": 1.4261, "step": 103060 }, { "epoch": 4.71, "learning_rate": 2.652752986406701e-05, "loss": 1.5551, "step": 103070 }, { "epoch": 4.71, "learning_rate": 2.6525241429813723e-05, "loss": 1.6591, "step": 103080 }, { "epoch": 4.71, "learning_rate": 2.652295299556044e-05, "loss": 1.4399, "step": 103090 }, { "epoch": 4.71, "learning_rate": 2.652066456130716e-05, "loss": 1.6471, "step": 103100 }, { "epoch": 4.71, "learning_rate": 2.6518376127053873e-05, "loss": 1.5473, "step": 103110 }, { "epoch": 4.71, "learning_rate": 2.651608769280059e-05, "loss": 1.5655, "step": 103120 }, { "epoch": 4.71, "learning_rate": 2.65137992585473e-05, "loss": 1.417, "step": 103130 }, { "epoch": 4.71, "learning_rate": 2.651151082429402e-05, "loss": 1.4733, "step": 103140 }, { "epoch": 4.71, "learning_rate": 2.6509222390040732e-05, "loss": 1.4189, "step": 103150 }, { "epoch": 4.71, "learning_rate": 2.650693395578745e-05, "loss": 1.4695, "step": 103160 }, { "epoch": 4.71, "learning_rate": 2.6504645521534168e-05, "loss": 1.5543, "step": 103170 }, { "epoch": 4.71, "learning_rate": 2.650235708728088e-05, "loss": 1.4166, "step": 103180 }, { "epoch": 4.71, "learning_rate": 2.65000686530276e-05, "loss": 1.5761, "step": 103190 }, { "epoch": 4.71, "learning_rate": 2.6497780218774317e-05, "loss": 1.7191, "step": 103200 }, { "epoch": 4.71, "learning_rate": 2.649549178452103e-05, "loss": 1.4534, "step": 103210 }, { "epoch": 4.71, "learning_rate": 2.649320335026775e-05, "loss": 1.419, "step": 103220 }, { "epoch": 4.71, "learning_rate": 2.6490914916014466e-05, "loss": 1.5036, "step": 103230 }, { "epoch": 4.71, "learning_rate": 2.648862648176118e-05, "loss": 1.4182, "step": 103240 }, { "epoch": 4.71, "learning_rate": 2.6486338047507898e-05, "loss": 1.6725, "step": 103250 }, { "epoch": 4.72, "learning_rate": 2.6484049613254615e-05, "loss": 1.4709, "step": 103260 }, { "epoch": 4.72, "learning_rate": 2.648176117900133e-05, "loss": 1.7615, "step": 103270 }, { "epoch": 4.72, "learning_rate": 2.6479472744748047e-05, "loss": 1.4454, "step": 103280 }, { "epoch": 4.72, "learning_rate": 2.6477184310494764e-05, "loss": 1.4931, "step": 103290 }, { "epoch": 4.72, "learning_rate": 2.647489587624148e-05, "loss": 1.466, "step": 103300 }, { "epoch": 4.72, "learning_rate": 2.6472607441988196e-05, "loss": 1.7314, "step": 103310 }, { "epoch": 4.72, "learning_rate": 2.647031900773491e-05, "loss": 1.5435, "step": 103320 }, { "epoch": 4.72, "learning_rate": 2.6468030573481624e-05, "loss": 1.6246, "step": 103330 }, { "epoch": 4.72, "learning_rate": 2.6465742139228338e-05, "loss": 1.4407, "step": 103340 }, { "epoch": 4.72, "learning_rate": 2.6463453704975056e-05, "loss": 1.5337, "step": 103350 }, { "epoch": 4.72, "learning_rate": 2.6461165270721773e-05, "loss": 1.4968, "step": 103360 }, { "epoch": 4.72, "learning_rate": 2.6458876836468487e-05, "loss": 1.6516, "step": 103370 }, { "epoch": 4.72, "learning_rate": 2.6456588402215205e-05, "loss": 1.6425, "step": 103380 }, { "epoch": 4.72, "learning_rate": 2.645429996796192e-05, "loss": 1.3959, "step": 103390 }, { "epoch": 4.72, "learning_rate": 2.6452011533708637e-05, "loss": 1.4075, "step": 103400 }, { "epoch": 4.72, "learning_rate": 2.6449723099455354e-05, "loss": 1.8693, "step": 103410 }, { "epoch": 4.72, "learning_rate": 2.6447434665202068e-05, "loss": 1.6429, "step": 103420 }, { "epoch": 4.72, "learning_rate": 2.6445146230948786e-05, "loss": 1.5024, "step": 103430 }, { "epoch": 4.72, "learning_rate": 2.6442857796695503e-05, "loss": 1.5183, "step": 103440 }, { "epoch": 4.72, "learning_rate": 2.6440569362442217e-05, "loss": 1.4939, "step": 103450 }, { "epoch": 4.72, "learning_rate": 2.6438280928188935e-05, "loss": 1.5171, "step": 103460 }, { "epoch": 4.72, "learning_rate": 2.6435992493935653e-05, "loss": 1.6432, "step": 103470 }, { "epoch": 4.73, "learning_rate": 2.6433704059682367e-05, "loss": 1.6425, "step": 103480 }, { "epoch": 4.73, "learning_rate": 2.6431415625429084e-05, "loss": 1.5867, "step": 103490 }, { "epoch": 4.73, "learning_rate": 2.64291271911758e-05, "loss": 1.5814, "step": 103500 }, { "epoch": 4.73, "learning_rate": 2.6426838756922516e-05, "loss": 1.6383, "step": 103510 }, { "epoch": 4.73, "learning_rate": 2.6424550322669233e-05, "loss": 1.4886, "step": 103520 }, { "epoch": 4.73, "learning_rate": 2.6422261888415944e-05, "loss": 1.432, "step": 103530 }, { "epoch": 4.73, "learning_rate": 2.641997345416266e-05, "loss": 1.6079, "step": 103540 }, { "epoch": 4.73, "learning_rate": 2.6417685019909376e-05, "loss": 1.568, "step": 103550 }, { "epoch": 4.73, "learning_rate": 2.6415396585656093e-05, "loss": 1.5165, "step": 103560 }, { "epoch": 4.73, "learning_rate": 2.641310815140281e-05, "loss": 1.3753, "step": 103570 }, { "epoch": 4.73, "learning_rate": 2.6410819717149525e-05, "loss": 1.5894, "step": 103580 }, { "epoch": 4.73, "learning_rate": 2.6408531282896242e-05, "loss": 1.5406, "step": 103590 }, { "epoch": 4.73, "learning_rate": 2.640624284864296e-05, "loss": 1.6315, "step": 103600 }, { "epoch": 4.73, "learning_rate": 2.6403954414389674e-05, "loss": 1.2801, "step": 103610 }, { "epoch": 4.73, "learning_rate": 2.640166598013639e-05, "loss": 1.6135, "step": 103620 }, { "epoch": 4.73, "learning_rate": 2.639937754588311e-05, "loss": 1.419, "step": 103630 }, { "epoch": 4.73, "learning_rate": 2.6397089111629823e-05, "loss": 1.5026, "step": 103640 }, { "epoch": 4.73, "learning_rate": 2.639480067737654e-05, "loss": 1.4678, "step": 103650 }, { "epoch": 4.73, "learning_rate": 2.639251224312326e-05, "loss": 1.444, "step": 103660 }, { "epoch": 4.73, "learning_rate": 2.6390223808869972e-05, "loss": 1.4296, "step": 103670 }, { "epoch": 4.73, "learning_rate": 2.638793537461669e-05, "loss": 1.5123, "step": 103680 }, { "epoch": 4.73, "learning_rate": 2.6385646940363407e-05, "loss": 1.5581, "step": 103690 }, { "epoch": 4.74, "learning_rate": 2.638335850611012e-05, "loss": 1.6326, "step": 103700 }, { "epoch": 4.74, "learning_rate": 2.638107007185684e-05, "loss": 1.5818, "step": 103710 }, { "epoch": 4.74, "learning_rate": 2.637878163760355e-05, "loss": 1.5565, "step": 103720 }, { "epoch": 4.74, "learning_rate": 2.6376493203350267e-05, "loss": 1.54, "step": 103730 }, { "epoch": 4.74, "learning_rate": 2.637420476909698e-05, "loss": 1.3896, "step": 103740 }, { "epoch": 4.74, "learning_rate": 2.63719163348437e-05, "loss": 1.7043, "step": 103750 }, { "epoch": 4.74, "learning_rate": 2.6369627900590417e-05, "loss": 1.6489, "step": 103760 }, { "epoch": 4.74, "learning_rate": 2.636733946633713e-05, "loss": 1.5886, "step": 103770 }, { "epoch": 4.74, "learning_rate": 2.6365051032083848e-05, "loss": 1.7347, "step": 103780 }, { "epoch": 4.74, "learning_rate": 2.6362762597830566e-05, "loss": 1.6067, "step": 103790 }, { "epoch": 4.74, "learning_rate": 2.636047416357728e-05, "loss": 1.4406, "step": 103800 }, { "epoch": 4.74, "learning_rate": 2.6358185729323997e-05, "loss": 1.6217, "step": 103810 }, { "epoch": 4.74, "learning_rate": 2.6355897295070715e-05, "loss": 1.4663, "step": 103820 }, { "epoch": 4.74, "learning_rate": 2.635360886081743e-05, "loss": 1.3746, "step": 103830 }, { "epoch": 4.74, "learning_rate": 2.6351320426564147e-05, "loss": 1.5343, "step": 103840 }, { "epoch": 4.74, "learning_rate": 2.6349031992310864e-05, "loss": 1.5606, "step": 103850 }, { "epoch": 4.74, "learning_rate": 2.6346743558057578e-05, "loss": 1.6941, "step": 103860 }, { "epoch": 4.74, "learning_rate": 2.6344455123804296e-05, "loss": 1.6211, "step": 103870 }, { "epoch": 4.74, "learning_rate": 2.6342166689551013e-05, "loss": 1.572, "step": 103880 }, { "epoch": 4.74, "learning_rate": 2.6339878255297727e-05, "loss": 1.6756, "step": 103890 }, { "epoch": 4.74, "learning_rate": 2.6337589821044445e-05, "loss": 1.5877, "step": 103900 }, { "epoch": 4.74, "learning_rate": 2.6335301386791162e-05, "loss": 1.4212, "step": 103910 }, { "epoch": 4.75, "learning_rate": 2.6333012952537873e-05, "loss": 1.5618, "step": 103920 }, { "epoch": 4.75, "learning_rate": 2.6330724518284587e-05, "loss": 1.3974, "step": 103930 }, { "epoch": 4.75, "learning_rate": 2.6328436084031305e-05, "loss": 1.4371, "step": 103940 }, { "epoch": 4.75, "learning_rate": 2.6326147649778022e-05, "loss": 1.5504, "step": 103950 }, { "epoch": 4.75, "learning_rate": 2.6323859215524737e-05, "loss": 1.4701, "step": 103960 }, { "epoch": 4.75, "learning_rate": 2.6321570781271454e-05, "loss": 1.4785, "step": 103970 }, { "epoch": 4.75, "learning_rate": 2.631928234701817e-05, "loss": 1.5177, "step": 103980 }, { "epoch": 4.75, "learning_rate": 2.6316993912764886e-05, "loss": 1.3784, "step": 103990 }, { "epoch": 4.75, "learning_rate": 2.6314705478511603e-05, "loss": 1.3017, "step": 104000 }, { "epoch": 4.75, "learning_rate": 2.631241704425832e-05, "loss": 1.7634, "step": 104010 }, { "epoch": 4.75, "learning_rate": 2.6310128610005035e-05, "loss": 1.5612, "step": 104020 }, { "epoch": 4.75, "learning_rate": 2.6307840175751752e-05, "loss": 1.5788, "step": 104030 }, { "epoch": 4.75, "learning_rate": 2.630555174149847e-05, "loss": 1.5792, "step": 104040 }, { "epoch": 4.75, "learning_rate": 2.6303263307245184e-05, "loss": 1.5272, "step": 104050 }, { "epoch": 4.75, "learning_rate": 2.63009748729919e-05, "loss": 1.4685, "step": 104060 }, { "epoch": 4.75, "learning_rate": 2.629868643873862e-05, "loss": 1.5551, "step": 104070 }, { "epoch": 4.75, "learning_rate": 2.6296398004485333e-05, "loss": 1.4271, "step": 104080 }, { "epoch": 4.75, "learning_rate": 2.629410957023205e-05, "loss": 1.4174, "step": 104090 }, { "epoch": 4.75, "learning_rate": 2.6291821135978768e-05, "loss": 1.4698, "step": 104100 }, { "epoch": 4.75, "learning_rate": 2.6289532701725482e-05, "loss": 1.6056, "step": 104110 }, { "epoch": 4.75, "learning_rate": 2.6287244267472193e-05, "loss": 1.5309, "step": 104120 }, { "epoch": 4.75, "learning_rate": 2.628495583321891e-05, "loss": 1.5808, "step": 104130 }, { "epoch": 4.76, "learning_rate": 2.6282667398965628e-05, "loss": 1.5532, "step": 104140 }, { "epoch": 4.76, "learning_rate": 2.6280378964712342e-05, "loss": 1.5833, "step": 104150 }, { "epoch": 4.76, "learning_rate": 2.627809053045906e-05, "loss": 1.6026, "step": 104160 }, { "epoch": 4.76, "learning_rate": 2.6275802096205777e-05, "loss": 1.6357, "step": 104170 }, { "epoch": 4.76, "learning_rate": 2.627351366195249e-05, "loss": 1.5565, "step": 104180 }, { "epoch": 4.76, "learning_rate": 2.627122522769921e-05, "loss": 1.4121, "step": 104190 }, { "epoch": 4.76, "learning_rate": 2.6268936793445927e-05, "loss": 1.5671, "step": 104200 }, { "epoch": 4.76, "learning_rate": 2.626664835919264e-05, "loss": 1.5611, "step": 104210 }, { "epoch": 4.76, "learning_rate": 2.6264359924939358e-05, "loss": 1.508, "step": 104220 }, { "epoch": 4.76, "learning_rate": 2.6262071490686076e-05, "loss": 1.5246, "step": 104230 }, { "epoch": 4.76, "learning_rate": 2.625978305643279e-05, "loss": 1.4829, "step": 104240 }, { "epoch": 4.76, "learning_rate": 2.6257494622179507e-05, "loss": 1.5658, "step": 104250 }, { "epoch": 4.76, "learning_rate": 2.6255206187926225e-05, "loss": 1.2802, "step": 104260 }, { "epoch": 4.76, "learning_rate": 2.625291775367294e-05, "loss": 1.5547, "step": 104270 }, { "epoch": 4.76, "learning_rate": 2.6250629319419657e-05, "loss": 1.4975, "step": 104280 }, { "epoch": 4.76, "learning_rate": 2.6248340885166374e-05, "loss": 1.6023, "step": 104290 }, { "epoch": 4.76, "learning_rate": 2.6246052450913088e-05, "loss": 1.5356, "step": 104300 }, { "epoch": 4.76, "learning_rate": 2.6243764016659806e-05, "loss": 1.5098, "step": 104310 }, { "epoch": 4.76, "learning_rate": 2.6241475582406516e-05, "loss": 1.5017, "step": 104320 }, { "epoch": 4.76, "learning_rate": 2.6239187148153234e-05, "loss": 1.3147, "step": 104330 }, { "epoch": 4.76, "learning_rate": 2.6236898713899948e-05, "loss": 1.6753, "step": 104340 }, { "epoch": 4.76, "learning_rate": 2.6234610279646666e-05, "loss": 1.4814, "step": 104350 }, { "epoch": 4.77, "learning_rate": 2.6232321845393383e-05, "loss": 1.4446, "step": 104360 }, { "epoch": 4.77, "learning_rate": 2.6230033411140097e-05, "loss": 1.6435, "step": 104370 }, { "epoch": 4.77, "learning_rate": 2.6227744976886815e-05, "loss": 1.4872, "step": 104380 }, { "epoch": 4.77, "learning_rate": 2.6225456542633532e-05, "loss": 1.4807, "step": 104390 }, { "epoch": 4.77, "learning_rate": 2.6223168108380246e-05, "loss": 1.593, "step": 104400 }, { "epoch": 4.77, "learning_rate": 2.6220879674126964e-05, "loss": 1.7458, "step": 104410 }, { "epoch": 4.77, "learning_rate": 2.621859123987368e-05, "loss": 1.4625, "step": 104420 }, { "epoch": 4.77, "learning_rate": 2.6216302805620396e-05, "loss": 1.5111, "step": 104430 }, { "epoch": 4.77, "learning_rate": 2.6214014371367113e-05, "loss": 1.4352, "step": 104440 }, { "epoch": 4.77, "learning_rate": 2.621172593711383e-05, "loss": 1.6047, "step": 104450 }, { "epoch": 4.77, "learning_rate": 2.6209437502860545e-05, "loss": 1.5014, "step": 104460 }, { "epoch": 4.77, "learning_rate": 2.6207149068607262e-05, "loss": 1.4959, "step": 104470 }, { "epoch": 4.77, "learning_rate": 2.620486063435398e-05, "loss": 1.5607, "step": 104480 }, { "epoch": 4.77, "learning_rate": 2.6202572200100694e-05, "loss": 1.3871, "step": 104490 }, { "epoch": 4.77, "learning_rate": 2.620028376584741e-05, "loss": 1.4609, "step": 104500 }, { "epoch": 4.77, "learning_rate": 2.6197995331594122e-05, "loss": 1.4795, "step": 104510 }, { "epoch": 4.77, "learning_rate": 2.619570689734084e-05, "loss": 1.3539, "step": 104520 }, { "epoch": 4.77, "learning_rate": 2.6193418463087554e-05, "loss": 1.4758, "step": 104530 }, { "epoch": 4.77, "learning_rate": 2.619113002883427e-05, "loss": 1.4239, "step": 104540 }, { "epoch": 4.77, "learning_rate": 2.6188841594580986e-05, "loss": 1.4373, "step": 104550 }, { "epoch": 4.77, "learning_rate": 2.6186553160327703e-05, "loss": 1.4976, "step": 104560 }, { "epoch": 4.77, "learning_rate": 2.618426472607442e-05, "loss": 1.4772, "step": 104570 }, { "epoch": 4.78, "learning_rate": 2.6181976291821135e-05, "loss": 1.454, "step": 104580 }, { "epoch": 4.78, "learning_rate": 2.6179687857567852e-05, "loss": 1.5943, "step": 104590 }, { "epoch": 4.78, "learning_rate": 2.617739942331457e-05, "loss": 1.5019, "step": 104600 }, { "epoch": 4.78, "learning_rate": 2.6175110989061284e-05, "loss": 1.3624, "step": 104610 }, { "epoch": 4.78, "learning_rate": 2.6172822554808e-05, "loss": 1.5067, "step": 104620 }, { "epoch": 4.78, "learning_rate": 2.617053412055472e-05, "loss": 1.4344, "step": 104630 }, { "epoch": 4.78, "learning_rate": 2.6168245686301433e-05, "loss": 1.6293, "step": 104640 }, { "epoch": 4.78, "learning_rate": 2.616595725204815e-05, "loss": 1.6582, "step": 104650 }, { "epoch": 4.78, "learning_rate": 2.6163668817794868e-05, "loss": 1.4618, "step": 104660 }, { "epoch": 4.78, "learning_rate": 2.6161380383541582e-05, "loss": 1.5762, "step": 104670 }, { "epoch": 4.78, "learning_rate": 2.61590919492883e-05, "loss": 1.5412, "step": 104680 }, { "epoch": 4.78, "learning_rate": 2.6156803515035017e-05, "loss": 1.6312, "step": 104690 }, { "epoch": 4.78, "learning_rate": 2.615451508078173e-05, "loss": 1.5734, "step": 104700 }, { "epoch": 4.78, "learning_rate": 2.6152226646528442e-05, "loss": 1.5209, "step": 104710 }, { "epoch": 4.78, "learning_rate": 2.614993821227516e-05, "loss": 1.4842, "step": 104720 }, { "epoch": 4.78, "learning_rate": 2.6147649778021877e-05, "loss": 1.4159, "step": 104730 }, { "epoch": 4.78, "learning_rate": 2.614536134376859e-05, "loss": 1.5362, "step": 104740 }, { "epoch": 4.78, "learning_rate": 2.614307290951531e-05, "loss": 1.5172, "step": 104750 }, { "epoch": 4.78, "learning_rate": 2.6140784475262026e-05, "loss": 1.5539, "step": 104760 }, { "epoch": 4.78, "learning_rate": 2.613849604100874e-05, "loss": 1.515, "step": 104770 }, { "epoch": 4.78, "learning_rate": 2.6136207606755458e-05, "loss": 1.4287, "step": 104780 }, { "epoch": 4.78, "learning_rate": 2.6133919172502176e-05, "loss": 1.7639, "step": 104790 }, { "epoch": 4.79, "learning_rate": 2.613163073824889e-05, "loss": 1.5387, "step": 104800 }, { "epoch": 4.79, "learning_rate": 2.6129342303995607e-05, "loss": 1.4977, "step": 104810 }, { "epoch": 4.79, "learning_rate": 2.6127053869742325e-05, "loss": 1.4101, "step": 104820 }, { "epoch": 4.79, "learning_rate": 2.612476543548904e-05, "loss": 1.6385, "step": 104830 }, { "epoch": 4.79, "learning_rate": 2.6122477001235756e-05, "loss": 1.4877, "step": 104840 }, { "epoch": 4.79, "learning_rate": 2.6120188566982474e-05, "loss": 1.5257, "step": 104850 }, { "epoch": 4.79, "learning_rate": 2.6117900132729188e-05, "loss": 1.5275, "step": 104860 }, { "epoch": 4.79, "learning_rate": 2.6115611698475906e-05, "loss": 1.6255, "step": 104870 }, { "epoch": 4.79, "learning_rate": 2.6113323264222623e-05, "loss": 1.5487, "step": 104880 }, { "epoch": 4.79, "learning_rate": 2.6111034829969337e-05, "loss": 1.7121, "step": 104890 }, { "epoch": 4.79, "learning_rate": 2.6108746395716055e-05, "loss": 1.5373, "step": 104900 }, { "epoch": 4.79, "learning_rate": 2.6106457961462766e-05, "loss": 1.5832, "step": 104910 }, { "epoch": 4.79, "learning_rate": 2.6104169527209483e-05, "loss": 1.5477, "step": 104920 }, { "epoch": 4.79, "learning_rate": 2.6101881092956197e-05, "loss": 1.5759, "step": 104930 }, { "epoch": 4.79, "learning_rate": 2.6099592658702915e-05, "loss": 1.4671, "step": 104940 }, { "epoch": 4.79, "learning_rate": 2.6097304224449632e-05, "loss": 1.5236, "step": 104950 }, { "epoch": 4.79, "learning_rate": 2.6095015790196346e-05, "loss": 1.6989, "step": 104960 }, { "epoch": 4.79, "learning_rate": 2.6092727355943064e-05, "loss": 1.498, "step": 104970 }, { "epoch": 4.79, "learning_rate": 2.609043892168978e-05, "loss": 1.5129, "step": 104980 }, { "epoch": 4.79, "learning_rate": 2.6088150487436496e-05, "loss": 1.6467, "step": 104990 }, { "epoch": 4.79, "learning_rate": 2.6085862053183213e-05, "loss": 1.6479, "step": 105000 }, { "epoch": 4.8, "learning_rate": 2.608357361892993e-05, "loss": 1.5445, "step": 105010 }, { "epoch": 4.8, "learning_rate": 2.6081285184676645e-05, "loss": 1.522, "step": 105020 }, { "epoch": 4.8, "learning_rate": 2.6078996750423362e-05, "loss": 1.5385, "step": 105030 }, { "epoch": 4.8, "learning_rate": 2.607670831617008e-05, "loss": 1.5274, "step": 105040 }, { "epoch": 4.8, "learning_rate": 2.6074419881916794e-05, "loss": 1.4921, "step": 105050 }, { "epoch": 4.8, "learning_rate": 2.607213144766351e-05, "loss": 1.5182, "step": 105060 }, { "epoch": 4.8, "learning_rate": 2.606984301341023e-05, "loss": 1.5029, "step": 105070 }, { "epoch": 4.8, "learning_rate": 2.6067554579156943e-05, "loss": 1.5002, "step": 105080 }, { "epoch": 4.8, "learning_rate": 2.606526614490366e-05, "loss": 1.5289, "step": 105090 }, { "epoch": 4.8, "learning_rate": 2.6062977710650378e-05, "loss": 1.4163, "step": 105100 }, { "epoch": 4.8, "learning_rate": 2.606068927639709e-05, "loss": 1.667, "step": 105110 }, { "epoch": 4.8, "learning_rate": 2.6058400842143803e-05, "loss": 1.5666, "step": 105120 }, { "epoch": 4.8, "learning_rate": 2.605611240789052e-05, "loss": 1.4968, "step": 105130 }, { "epoch": 4.8, "learning_rate": 2.6053823973637238e-05, "loss": 1.5311, "step": 105140 }, { "epoch": 4.8, "learning_rate": 2.6051535539383952e-05, "loss": 1.593, "step": 105150 }, { "epoch": 4.8, "learning_rate": 2.604924710513067e-05, "loss": 1.584, "step": 105160 }, { "epoch": 4.8, "learning_rate": 2.6046958670877387e-05, "loss": 1.5865, "step": 105170 }, { "epoch": 4.8, "learning_rate": 2.60446702366241e-05, "loss": 1.5573, "step": 105180 }, { "epoch": 4.8, "learning_rate": 2.604238180237082e-05, "loss": 1.4137, "step": 105190 }, { "epoch": 4.8, "learning_rate": 2.6040093368117536e-05, "loss": 1.586, "step": 105200 }, { "epoch": 4.8, "learning_rate": 2.603780493386425e-05, "loss": 1.4342, "step": 105210 }, { "epoch": 4.8, "learning_rate": 2.6035516499610968e-05, "loss": 1.3868, "step": 105220 }, { "epoch": 4.81, "learning_rate": 2.6033228065357686e-05, "loss": 1.488, "step": 105230 }, { "epoch": 4.81, "learning_rate": 2.60309396311044e-05, "loss": 1.4621, "step": 105240 }, { "epoch": 4.81, "learning_rate": 2.6028651196851117e-05, "loss": 1.5128, "step": 105250 }, { "epoch": 4.81, "learning_rate": 2.6026362762597835e-05, "loss": 1.4553, "step": 105260 }, { "epoch": 4.81, "learning_rate": 2.602407432834455e-05, "loss": 1.4534, "step": 105270 }, { "epoch": 4.81, "learning_rate": 2.6021785894091266e-05, "loss": 1.7529, "step": 105280 }, { "epoch": 4.81, "learning_rate": 2.6019497459837984e-05, "loss": 1.6036, "step": 105290 }, { "epoch": 4.81, "learning_rate": 2.6017209025584698e-05, "loss": 1.5948, "step": 105300 }, { "epoch": 4.81, "learning_rate": 2.601492059133141e-05, "loss": 1.6815, "step": 105310 }, { "epoch": 4.81, "learning_rate": 2.6012632157078126e-05, "loss": 1.5234, "step": 105320 }, { "epoch": 4.81, "learning_rate": 2.6010343722824844e-05, "loss": 1.5036, "step": 105330 }, { "epoch": 4.81, "learning_rate": 2.6008055288571558e-05, "loss": 1.4607, "step": 105340 }, { "epoch": 4.81, "learning_rate": 2.6005766854318276e-05, "loss": 1.829, "step": 105350 }, { "epoch": 4.81, "learning_rate": 2.6003478420064993e-05, "loss": 1.6285, "step": 105360 }, { "epoch": 4.81, "learning_rate": 2.6001189985811707e-05, "loss": 1.5995, "step": 105370 }, { "epoch": 4.81, "learning_rate": 2.5998901551558425e-05, "loss": 1.4633, "step": 105380 }, { "epoch": 4.81, "learning_rate": 2.5996613117305142e-05, "loss": 1.5971, "step": 105390 }, { "epoch": 4.81, "learning_rate": 2.5994324683051856e-05, "loss": 1.5655, "step": 105400 }, { "epoch": 4.81, "learning_rate": 2.5992036248798574e-05, "loss": 1.4581, "step": 105410 }, { "epoch": 4.81, "learning_rate": 2.598974781454529e-05, "loss": 1.562, "step": 105420 }, { "epoch": 4.81, "learning_rate": 2.5987459380292006e-05, "loss": 1.4676, "step": 105430 }, { "epoch": 4.81, "learning_rate": 2.5985170946038723e-05, "loss": 1.5183, "step": 105440 }, { "epoch": 4.82, "learning_rate": 2.598288251178544e-05, "loss": 1.4335, "step": 105450 }, { "epoch": 4.82, "learning_rate": 2.5980594077532155e-05, "loss": 1.4053, "step": 105460 }, { "epoch": 4.82, "learning_rate": 2.5978305643278872e-05, "loss": 1.3698, "step": 105470 }, { "epoch": 4.82, "learning_rate": 2.597601720902559e-05, "loss": 1.543, "step": 105480 }, { "epoch": 4.82, "learning_rate": 2.5973728774772304e-05, "loss": 1.4336, "step": 105490 }, { "epoch": 4.82, "learning_rate": 2.5971440340519015e-05, "loss": 1.5903, "step": 105500 }, { "epoch": 4.82, "learning_rate": 2.5969151906265732e-05, "loss": 1.5866, "step": 105510 }, { "epoch": 4.82, "learning_rate": 2.596686347201245e-05, "loss": 1.5365, "step": 105520 }, { "epoch": 4.82, "learning_rate": 2.5964575037759164e-05, "loss": 1.4715, "step": 105530 }, { "epoch": 4.82, "learning_rate": 2.596228660350588e-05, "loss": 1.4864, "step": 105540 }, { "epoch": 4.82, "learning_rate": 2.59599981692526e-05, "loss": 1.5045, "step": 105550 }, { "epoch": 4.82, "learning_rate": 2.5957709734999313e-05, "loss": 1.5002, "step": 105560 }, { "epoch": 4.82, "learning_rate": 2.595542130074603e-05, "loss": 1.4569, "step": 105570 }, { "epoch": 4.82, "learning_rate": 2.5953132866492748e-05, "loss": 1.5951, "step": 105580 }, { "epoch": 4.82, "learning_rate": 2.5950844432239462e-05, "loss": 1.4883, "step": 105590 }, { "epoch": 4.82, "learning_rate": 2.594855599798618e-05, "loss": 1.4635, "step": 105600 }, { "epoch": 4.82, "learning_rate": 2.5946267563732897e-05, "loss": 1.7311, "step": 105610 }, { "epoch": 4.82, "learning_rate": 2.594397912947961e-05, "loss": 1.7246, "step": 105620 }, { "epoch": 4.82, "learning_rate": 2.594169069522633e-05, "loss": 1.4639, "step": 105630 }, { "epoch": 4.82, "learning_rate": 2.5939402260973046e-05, "loss": 1.4817, "step": 105640 }, { "epoch": 4.82, "learning_rate": 2.593711382671976e-05, "loss": 1.5041, "step": 105650 }, { "epoch": 4.82, "learning_rate": 2.5934825392466478e-05, "loss": 1.5826, "step": 105660 }, { "epoch": 4.83, "learning_rate": 2.5932536958213192e-05, "loss": 1.5582, "step": 105670 }, { "epoch": 4.83, "learning_rate": 2.593024852395991e-05, "loss": 1.3769, "step": 105680 }, { "epoch": 4.83, "learning_rate": 2.5927960089706627e-05, "loss": 1.5441, "step": 105690 }, { "epoch": 4.83, "learning_rate": 2.5925671655453338e-05, "loss": 1.4368, "step": 105700 }, { "epoch": 4.83, "learning_rate": 2.5923383221200055e-05, "loss": 1.617, "step": 105710 }, { "epoch": 4.83, "learning_rate": 2.592109478694677e-05, "loss": 1.4579, "step": 105720 }, { "epoch": 4.83, "learning_rate": 2.5918806352693487e-05, "loss": 1.4473, "step": 105730 }, { "epoch": 4.83, "learning_rate": 2.59165179184402e-05, "loss": 1.4148, "step": 105740 }, { "epoch": 4.83, "learning_rate": 2.591422948418692e-05, "loss": 1.6243, "step": 105750 }, { "epoch": 4.83, "learning_rate": 2.5911941049933636e-05, "loss": 1.6833, "step": 105760 }, { "epoch": 4.83, "learning_rate": 2.590965261568035e-05, "loss": 1.5818, "step": 105770 }, { "epoch": 4.83, "learning_rate": 2.5907364181427068e-05, "loss": 1.4073, "step": 105780 }, { "epoch": 4.83, "learning_rate": 2.5905075747173785e-05, "loss": 1.4948, "step": 105790 }, { "epoch": 4.83, "learning_rate": 2.59027873129205e-05, "loss": 1.5471, "step": 105800 }, { "epoch": 4.83, "learning_rate": 2.5900498878667217e-05, "loss": 1.5277, "step": 105810 }, { "epoch": 4.83, "learning_rate": 2.5898210444413935e-05, "loss": 1.5263, "step": 105820 }, { "epoch": 4.83, "learning_rate": 2.589592201016065e-05, "loss": 1.4677, "step": 105830 }, { "epoch": 4.83, "learning_rate": 2.5893633575907366e-05, "loss": 1.5901, "step": 105840 }, { "epoch": 4.83, "learning_rate": 2.5891345141654084e-05, "loss": 1.4856, "step": 105850 }, { "epoch": 4.83, "learning_rate": 2.5889056707400798e-05, "loss": 1.5294, "step": 105860 }, { "epoch": 4.83, "learning_rate": 2.5886768273147516e-05, "loss": 1.5756, "step": 105870 }, { "epoch": 4.83, "learning_rate": 2.5884479838894233e-05, "loss": 1.5664, "step": 105880 }, { "epoch": 4.84, "learning_rate": 2.5882191404640947e-05, "loss": 1.4902, "step": 105890 }, { "epoch": 4.84, "learning_rate": 2.5879902970387658e-05, "loss": 1.4889, "step": 105900 }, { "epoch": 4.84, "learning_rate": 2.5877614536134375e-05, "loss": 1.6087, "step": 105910 }, { "epoch": 4.84, "learning_rate": 2.5875326101881093e-05, "loss": 1.6069, "step": 105920 }, { "epoch": 4.84, "learning_rate": 2.5873037667627807e-05, "loss": 1.4036, "step": 105930 }, { "epoch": 4.84, "learning_rate": 2.5870749233374525e-05, "loss": 1.7516, "step": 105940 }, { "epoch": 4.84, "learning_rate": 2.5868460799121242e-05, "loss": 1.5443, "step": 105950 }, { "epoch": 4.84, "learning_rate": 2.5866172364867956e-05, "loss": 1.3956, "step": 105960 }, { "epoch": 4.84, "learning_rate": 2.5863883930614674e-05, "loss": 1.6031, "step": 105970 }, { "epoch": 4.84, "learning_rate": 2.586159549636139e-05, "loss": 1.4141, "step": 105980 }, { "epoch": 4.84, "learning_rate": 2.5859307062108105e-05, "loss": 1.5739, "step": 105990 }, { "epoch": 4.84, "learning_rate": 2.5857018627854823e-05, "loss": 1.7276, "step": 106000 }, { "epoch": 4.84, "learning_rate": 2.585473019360154e-05, "loss": 1.7648, "step": 106010 }, { "epoch": 4.84, "learning_rate": 2.5852441759348255e-05, "loss": 1.5917, "step": 106020 }, { "epoch": 4.84, "learning_rate": 2.5850153325094972e-05, "loss": 1.6537, "step": 106030 }, { "epoch": 4.84, "learning_rate": 2.584786489084169e-05, "loss": 1.787, "step": 106040 }, { "epoch": 4.84, "learning_rate": 2.5845576456588404e-05, "loss": 1.5341, "step": 106050 }, { "epoch": 4.84, "learning_rate": 2.584328802233512e-05, "loss": 1.5343, "step": 106060 }, { "epoch": 4.84, "learning_rate": 2.584099958808184e-05, "loss": 1.5102, "step": 106070 }, { "epoch": 4.84, "learning_rate": 2.5838711153828553e-05, "loss": 1.5392, "step": 106080 }, { "epoch": 4.84, "learning_rate": 2.583642271957527e-05, "loss": 1.4981, "step": 106090 }, { "epoch": 4.84, "learning_rate": 2.583413428532198e-05, "loss": 1.6189, "step": 106100 }, { "epoch": 4.85, "learning_rate": 2.58318458510687e-05, "loss": 1.4618, "step": 106110 }, { "epoch": 4.85, "learning_rate": 2.5829557416815413e-05, "loss": 1.4979, "step": 106120 }, { "epoch": 4.85, "learning_rate": 2.582726898256213e-05, "loss": 1.5908, "step": 106130 }, { "epoch": 4.85, "learning_rate": 2.5824980548308848e-05, "loss": 1.6217, "step": 106140 }, { "epoch": 4.85, "learning_rate": 2.5822692114055562e-05, "loss": 1.8435, "step": 106150 }, { "epoch": 4.85, "learning_rate": 2.582040367980228e-05, "loss": 1.4372, "step": 106160 }, { "epoch": 4.85, "learning_rate": 2.5818115245548997e-05, "loss": 1.3966, "step": 106170 }, { "epoch": 4.85, "learning_rate": 2.581582681129571e-05, "loss": 1.6002, "step": 106180 }, { "epoch": 4.85, "learning_rate": 2.581353837704243e-05, "loss": 1.494, "step": 106190 }, { "epoch": 4.85, "learning_rate": 2.5811249942789146e-05, "loss": 1.7114, "step": 106200 }, { "epoch": 4.85, "learning_rate": 2.580896150853586e-05, "loss": 1.3856, "step": 106210 }, { "epoch": 4.85, "learning_rate": 2.5806673074282578e-05, "loss": 1.5189, "step": 106220 }, { "epoch": 4.85, "learning_rate": 2.5804384640029295e-05, "loss": 1.6204, "step": 106230 }, { "epoch": 4.85, "learning_rate": 2.580209620577601e-05, "loss": 1.4477, "step": 106240 }, { "epoch": 4.85, "learning_rate": 2.5799807771522727e-05, "loss": 1.3325, "step": 106250 }, { "epoch": 4.85, "learning_rate": 2.5797519337269445e-05, "loss": 1.6698, "step": 106260 }, { "epoch": 4.85, "learning_rate": 2.579523090301616e-05, "loss": 1.4894, "step": 106270 }, { "epoch": 4.85, "learning_rate": 2.5792942468762876e-05, "loss": 1.5743, "step": 106280 }, { "epoch": 4.85, "learning_rate": 2.5790654034509587e-05, "loss": 1.6082, "step": 106290 }, { "epoch": 4.85, "learning_rate": 2.5788365600256305e-05, "loss": 1.5869, "step": 106300 }, { "epoch": 4.85, "learning_rate": 2.578607716600302e-05, "loss": 1.4262, "step": 106310 }, { "epoch": 4.85, "learning_rate": 2.5783788731749736e-05, "loss": 1.5483, "step": 106320 }, { "epoch": 4.86, "learning_rate": 2.5781500297496454e-05, "loss": 1.6342, "step": 106330 }, { "epoch": 4.86, "learning_rate": 2.5779211863243168e-05, "loss": 1.4725, "step": 106340 }, { "epoch": 4.86, "learning_rate": 2.5776923428989885e-05, "loss": 1.4723, "step": 106350 }, { "epoch": 4.86, "learning_rate": 2.5774634994736603e-05, "loss": 1.5362, "step": 106360 }, { "epoch": 4.86, "learning_rate": 2.5772346560483317e-05, "loss": 1.5414, "step": 106370 }, { "epoch": 4.86, "learning_rate": 2.5770058126230035e-05, "loss": 1.7142, "step": 106380 }, { "epoch": 4.86, "learning_rate": 2.5767769691976752e-05, "loss": 1.5022, "step": 106390 }, { "epoch": 4.86, "learning_rate": 2.5765481257723466e-05, "loss": 1.5169, "step": 106400 }, { "epoch": 4.86, "learning_rate": 2.5763192823470184e-05, "loss": 1.5428, "step": 106410 }, { "epoch": 4.86, "learning_rate": 2.57609043892169e-05, "loss": 1.4968, "step": 106420 }, { "epoch": 4.86, "learning_rate": 2.5758615954963615e-05, "loss": 1.4946, "step": 106430 }, { "epoch": 4.86, "learning_rate": 2.5756327520710333e-05, "loss": 1.7227, "step": 106440 }, { "epoch": 4.86, "learning_rate": 2.575403908645705e-05, "loss": 1.635, "step": 106450 }, { "epoch": 4.86, "learning_rate": 2.5751750652203765e-05, "loss": 1.4124, "step": 106460 }, { "epoch": 4.86, "learning_rate": 2.5749462217950482e-05, "loss": 1.3833, "step": 106470 }, { "epoch": 4.86, "learning_rate": 2.57471737836972e-05, "loss": 1.5673, "step": 106480 }, { "epoch": 4.86, "learning_rate": 2.574488534944391e-05, "loss": 1.6632, "step": 106490 }, { "epoch": 4.86, "learning_rate": 2.5742596915190625e-05, "loss": 1.5879, "step": 106500 }, { "epoch": 4.86, "learning_rate": 2.5740308480937342e-05, "loss": 1.548, "step": 106510 }, { "epoch": 4.86, "learning_rate": 2.573802004668406e-05, "loss": 1.5329, "step": 106520 }, { "epoch": 4.86, "learning_rate": 2.5735731612430774e-05, "loss": 1.6668, "step": 106530 }, { "epoch": 4.86, "learning_rate": 2.573344317817749e-05, "loss": 1.4444, "step": 106540 }, { "epoch": 4.87, "learning_rate": 2.573115474392421e-05, "loss": 1.4359, "step": 106550 }, { "epoch": 4.87, "learning_rate": 2.5728866309670923e-05, "loss": 1.6081, "step": 106560 }, { "epoch": 4.87, "learning_rate": 2.572657787541764e-05, "loss": 1.4486, "step": 106570 }, { "epoch": 4.87, "learning_rate": 2.5724289441164358e-05, "loss": 1.5459, "step": 106580 }, { "epoch": 4.87, "learning_rate": 2.5722001006911072e-05, "loss": 1.5389, "step": 106590 }, { "epoch": 4.87, "learning_rate": 2.571971257265779e-05, "loss": 1.5685, "step": 106600 }, { "epoch": 4.87, "learning_rate": 2.5717424138404507e-05, "loss": 1.4867, "step": 106610 }, { "epoch": 4.87, "learning_rate": 2.571513570415122e-05, "loss": 1.4277, "step": 106620 }, { "epoch": 4.87, "learning_rate": 2.571284726989794e-05, "loss": 1.7129, "step": 106630 }, { "epoch": 4.87, "learning_rate": 2.5710558835644656e-05, "loss": 1.3322, "step": 106640 }, { "epoch": 4.87, "learning_rate": 2.570827040139137e-05, "loss": 1.5675, "step": 106650 }, { "epoch": 4.87, "learning_rate": 2.5705981967138088e-05, "loss": 1.6701, "step": 106660 }, { "epoch": 4.87, "learning_rate": 2.5703693532884805e-05, "loss": 1.5537, "step": 106670 }, { "epoch": 4.87, "learning_rate": 2.570140509863152e-05, "loss": 1.5394, "step": 106680 }, { "epoch": 4.87, "learning_rate": 2.569911666437823e-05, "loss": 1.5349, "step": 106690 }, { "epoch": 4.87, "learning_rate": 2.5696828230124948e-05, "loss": 1.5234, "step": 106700 }, { "epoch": 4.87, "learning_rate": 2.5694539795871665e-05, "loss": 1.6781, "step": 106710 }, { "epoch": 4.87, "learning_rate": 2.569225136161838e-05, "loss": 1.6249, "step": 106720 }, { "epoch": 4.87, "learning_rate": 2.5689962927365097e-05, "loss": 1.374, "step": 106730 }, { "epoch": 4.87, "learning_rate": 2.5687674493111815e-05, "loss": 1.4251, "step": 106740 }, { "epoch": 4.87, "learning_rate": 2.568538605885853e-05, "loss": 1.546, "step": 106750 }, { "epoch": 4.87, "learning_rate": 2.5683097624605246e-05, "loss": 1.4848, "step": 106760 }, { "epoch": 4.88, "learning_rate": 2.5680809190351964e-05, "loss": 1.5198, "step": 106770 }, { "epoch": 4.88, "learning_rate": 2.5678520756098678e-05, "loss": 1.5455, "step": 106780 }, { "epoch": 4.88, "learning_rate": 2.5676232321845395e-05, "loss": 1.4143, "step": 106790 }, { "epoch": 4.88, "learning_rate": 2.5673943887592113e-05, "loss": 1.4988, "step": 106800 }, { "epoch": 4.88, "learning_rate": 2.5671655453338827e-05, "loss": 1.5517, "step": 106810 }, { "epoch": 4.88, "learning_rate": 2.5669367019085545e-05, "loss": 1.4437, "step": 106820 }, { "epoch": 4.88, "learning_rate": 2.566707858483226e-05, "loss": 1.5751, "step": 106830 }, { "epoch": 4.88, "learning_rate": 2.5664790150578976e-05, "loss": 1.4791, "step": 106840 }, { "epoch": 4.88, "learning_rate": 2.5662501716325694e-05, "loss": 1.3534, "step": 106850 }, { "epoch": 4.88, "learning_rate": 2.5660213282072408e-05, "loss": 1.5134, "step": 106860 }, { "epoch": 4.88, "learning_rate": 2.5657924847819125e-05, "loss": 1.5733, "step": 106870 }, { "epoch": 4.88, "learning_rate": 2.5655636413565843e-05, "loss": 1.5139, "step": 106880 }, { "epoch": 4.88, "learning_rate": 2.5653347979312554e-05, "loss": 1.4005, "step": 106890 }, { "epoch": 4.88, "learning_rate": 2.5651059545059268e-05, "loss": 1.4037, "step": 106900 }, { "epoch": 4.88, "learning_rate": 2.5648771110805985e-05, "loss": 1.5144, "step": 106910 }, { "epoch": 4.88, "learning_rate": 2.5646482676552703e-05, "loss": 1.4401, "step": 106920 }, { "epoch": 4.88, "learning_rate": 2.5644194242299417e-05, "loss": 1.4664, "step": 106930 }, { "epoch": 4.88, "learning_rate": 2.5641905808046134e-05, "loss": 1.6024, "step": 106940 }, { "epoch": 4.88, "learning_rate": 2.5639617373792852e-05, "loss": 1.6311, "step": 106950 }, { "epoch": 4.88, "learning_rate": 2.5637328939539566e-05, "loss": 1.4966, "step": 106960 }, { "epoch": 4.88, "learning_rate": 2.5635040505286284e-05, "loss": 1.5988, "step": 106970 }, { "epoch": 4.88, "learning_rate": 2.5632752071033e-05, "loss": 1.5823, "step": 106980 }, { "epoch": 4.89, "learning_rate": 2.5630463636779715e-05, "loss": 1.5408, "step": 106990 }, { "epoch": 4.89, "learning_rate": 2.5628175202526433e-05, "loss": 1.4283, "step": 107000 }, { "epoch": 4.89, "learning_rate": 2.562588676827315e-05, "loss": 1.576, "step": 107010 }, { "epoch": 4.89, "learning_rate": 2.5623598334019864e-05, "loss": 1.4136, "step": 107020 }, { "epoch": 4.89, "learning_rate": 2.5621309899766582e-05, "loss": 1.5836, "step": 107030 }, { "epoch": 4.89, "learning_rate": 2.56190214655133e-05, "loss": 1.4994, "step": 107040 }, { "epoch": 4.89, "learning_rate": 2.5616733031260014e-05, "loss": 1.4753, "step": 107050 }, { "epoch": 4.89, "learning_rate": 2.561444459700673e-05, "loss": 1.6109, "step": 107060 }, { "epoch": 4.89, "learning_rate": 2.561215616275345e-05, "loss": 1.4729, "step": 107070 }, { "epoch": 4.89, "learning_rate": 2.560986772850016e-05, "loss": 1.669, "step": 107080 }, { "epoch": 4.89, "learning_rate": 2.5607579294246874e-05, "loss": 1.4544, "step": 107090 }, { "epoch": 4.89, "learning_rate": 2.560529085999359e-05, "loss": 1.6642, "step": 107100 }, { "epoch": 4.89, "learning_rate": 2.560300242574031e-05, "loss": 1.5232, "step": 107110 }, { "epoch": 4.89, "learning_rate": 2.5600713991487023e-05, "loss": 1.6651, "step": 107120 }, { "epoch": 4.89, "learning_rate": 2.559842555723374e-05, "loss": 1.7309, "step": 107130 }, { "epoch": 4.89, "learning_rate": 2.5596137122980458e-05, "loss": 1.6532, "step": 107140 }, { "epoch": 4.89, "learning_rate": 2.5593848688727172e-05, "loss": 1.5352, "step": 107150 }, { "epoch": 4.89, "learning_rate": 2.559156025447389e-05, "loss": 1.41, "step": 107160 }, { "epoch": 4.89, "learning_rate": 2.5589271820220607e-05, "loss": 1.6173, "step": 107170 }, { "epoch": 4.89, "learning_rate": 2.558698338596732e-05, "loss": 1.6944, "step": 107180 }, { "epoch": 4.89, "learning_rate": 2.558469495171404e-05, "loss": 1.5665, "step": 107190 }, { "epoch": 4.9, "learning_rate": 2.5582406517460756e-05, "loss": 1.6622, "step": 107200 }, { "epoch": 4.9, "learning_rate": 2.558011808320747e-05, "loss": 1.6834, "step": 107210 }, { "epoch": 4.9, "learning_rate": 2.5577829648954188e-05, "loss": 1.513, "step": 107220 }, { "epoch": 4.9, "learning_rate": 2.5575541214700905e-05, "loss": 1.4755, "step": 107230 }, { "epoch": 4.9, "learning_rate": 2.557325278044762e-05, "loss": 1.466, "step": 107240 }, { "epoch": 4.9, "learning_rate": 2.5570964346194337e-05, "loss": 1.5191, "step": 107250 }, { "epoch": 4.9, "learning_rate": 2.5568675911941055e-05, "loss": 1.576, "step": 107260 }, { "epoch": 4.9, "learning_rate": 2.556638747768777e-05, "loss": 1.5738, "step": 107270 }, { "epoch": 4.9, "learning_rate": 2.556409904343448e-05, "loss": 1.4432, "step": 107280 }, { "epoch": 4.9, "learning_rate": 2.5561810609181197e-05, "loss": 1.4125, "step": 107290 }, { "epoch": 4.9, "learning_rate": 2.5559522174927914e-05, "loss": 1.5605, "step": 107300 }, { "epoch": 4.9, "learning_rate": 2.555723374067463e-05, "loss": 1.351, "step": 107310 }, { "epoch": 4.9, "learning_rate": 2.5554945306421346e-05, "loss": 1.5865, "step": 107320 }, { "epoch": 4.9, "learning_rate": 2.5552656872168064e-05, "loss": 1.5236, "step": 107330 }, { "epoch": 4.9, "learning_rate": 2.5550368437914778e-05, "loss": 1.4331, "step": 107340 }, { "epoch": 4.9, "learning_rate": 2.5548080003661495e-05, "loss": 1.6506, "step": 107350 }, { "epoch": 4.9, "learning_rate": 2.5545791569408213e-05, "loss": 1.5903, "step": 107360 }, { "epoch": 4.9, "learning_rate": 2.5543503135154927e-05, "loss": 1.3705, "step": 107370 }, { "epoch": 4.9, "learning_rate": 2.5541214700901644e-05, "loss": 1.4963, "step": 107380 }, { "epoch": 4.9, "learning_rate": 2.5538926266648362e-05, "loss": 1.5175, "step": 107390 }, { "epoch": 4.9, "learning_rate": 2.5536637832395076e-05, "loss": 1.4095, "step": 107400 }, { "epoch": 4.9, "learning_rate": 2.5534349398141794e-05, "loss": 1.535, "step": 107410 }, { "epoch": 4.91, "learning_rate": 2.553206096388851e-05, "loss": 1.4626, "step": 107420 }, { "epoch": 4.91, "learning_rate": 2.5529772529635225e-05, "loss": 1.4218, "step": 107430 }, { "epoch": 4.91, "learning_rate": 2.5527484095381943e-05, "loss": 1.6276, "step": 107440 }, { "epoch": 4.91, "learning_rate": 2.552519566112866e-05, "loss": 1.4217, "step": 107450 }, { "epoch": 4.91, "learning_rate": 2.5522907226875374e-05, "loss": 1.4361, "step": 107460 }, { "epoch": 4.91, "learning_rate": 2.5520618792622092e-05, "loss": 1.6165, "step": 107470 }, { "epoch": 4.91, "learning_rate": 2.5518330358368803e-05, "loss": 1.4995, "step": 107480 }, { "epoch": 4.91, "learning_rate": 2.551604192411552e-05, "loss": 1.403, "step": 107490 }, { "epoch": 4.91, "learning_rate": 2.5513753489862234e-05, "loss": 1.6439, "step": 107500 }, { "epoch": 4.91, "learning_rate": 2.5511465055608952e-05, "loss": 1.4933, "step": 107510 }, { "epoch": 4.91, "learning_rate": 2.550917662135567e-05, "loss": 1.5579, "step": 107520 }, { "epoch": 4.91, "learning_rate": 2.5506888187102384e-05, "loss": 1.476, "step": 107530 }, { "epoch": 4.91, "learning_rate": 2.55045997528491e-05, "loss": 1.4362, "step": 107540 }, { "epoch": 4.91, "learning_rate": 2.550231131859582e-05, "loss": 1.6645, "step": 107550 }, { "epoch": 4.91, "learning_rate": 2.5500022884342533e-05, "loss": 1.6058, "step": 107560 }, { "epoch": 4.91, "learning_rate": 2.549773445008925e-05, "loss": 1.5845, "step": 107570 }, { "epoch": 4.91, "learning_rate": 2.5495446015835968e-05, "loss": 1.527, "step": 107580 }, { "epoch": 4.91, "learning_rate": 2.5493157581582682e-05, "loss": 1.608, "step": 107590 }, { "epoch": 4.91, "learning_rate": 2.54908691473294e-05, "loss": 1.3372, "step": 107600 }, { "epoch": 4.91, "learning_rate": 2.5488580713076117e-05, "loss": 1.5006, "step": 107610 }, { "epoch": 4.91, "learning_rate": 2.548629227882283e-05, "loss": 1.4575, "step": 107620 }, { "epoch": 4.91, "learning_rate": 2.548400384456955e-05, "loss": 1.5758, "step": 107630 }, { "epoch": 4.92, "learning_rate": 2.5481715410316266e-05, "loss": 1.4291, "step": 107640 }, { "epoch": 4.92, "learning_rate": 2.547942697606298e-05, "loss": 1.6117, "step": 107650 }, { "epoch": 4.92, "learning_rate": 2.5477138541809698e-05, "loss": 1.5172, "step": 107660 }, { "epoch": 4.92, "learning_rate": 2.5474850107556415e-05, "loss": 1.5056, "step": 107670 }, { "epoch": 4.92, "learning_rate": 2.5472561673303126e-05, "loss": 1.4086, "step": 107680 }, { "epoch": 4.92, "learning_rate": 2.547027323904984e-05, "loss": 1.7101, "step": 107690 }, { "epoch": 4.92, "learning_rate": 2.5467984804796558e-05, "loss": 1.7432, "step": 107700 }, { "epoch": 4.92, "learning_rate": 2.5465696370543275e-05, "loss": 1.4106, "step": 107710 }, { "epoch": 4.92, "learning_rate": 2.546340793628999e-05, "loss": 1.591, "step": 107720 }, { "epoch": 4.92, "learning_rate": 2.5461119502036707e-05, "loss": 1.5338, "step": 107730 }, { "epoch": 4.92, "learning_rate": 2.5458831067783424e-05, "loss": 1.441, "step": 107740 }, { "epoch": 4.92, "learning_rate": 2.545654263353014e-05, "loss": 1.4257, "step": 107750 }, { "epoch": 4.92, "learning_rate": 2.5454254199276856e-05, "loss": 1.6124, "step": 107760 }, { "epoch": 4.92, "learning_rate": 2.5451965765023574e-05, "loss": 1.6015, "step": 107770 }, { "epoch": 4.92, "learning_rate": 2.5449677330770288e-05, "loss": 1.4644, "step": 107780 }, { "epoch": 4.92, "learning_rate": 2.5447388896517005e-05, "loss": 1.7581, "step": 107790 }, { "epoch": 4.92, "learning_rate": 2.5445100462263723e-05, "loss": 1.5706, "step": 107800 }, { "epoch": 4.92, "learning_rate": 2.5442812028010437e-05, "loss": 1.5117, "step": 107810 }, { "epoch": 4.92, "learning_rate": 2.5440523593757154e-05, "loss": 1.5735, "step": 107820 }, { "epoch": 4.92, "learning_rate": 2.5438235159503872e-05, "loss": 1.5374, "step": 107830 }, { "epoch": 4.92, "learning_rate": 2.5435946725250586e-05, "loss": 1.5419, "step": 107840 }, { "epoch": 4.92, "learning_rate": 2.5433658290997304e-05, "loss": 1.6207, "step": 107850 }, { "epoch": 4.93, "learning_rate": 2.543136985674402e-05, "loss": 1.6688, "step": 107860 }, { "epoch": 4.93, "learning_rate": 2.5429081422490732e-05, "loss": 1.6623, "step": 107870 }, { "epoch": 4.93, "learning_rate": 2.5426792988237446e-05, "loss": 1.585, "step": 107880 }, { "epoch": 4.93, "learning_rate": 2.5424504553984164e-05, "loss": 1.6818, "step": 107890 }, { "epoch": 4.93, "learning_rate": 2.542221611973088e-05, "loss": 1.5475, "step": 107900 }, { "epoch": 4.93, "learning_rate": 2.5419927685477595e-05, "loss": 1.5184, "step": 107910 }, { "epoch": 4.93, "learning_rate": 2.5417639251224313e-05, "loss": 1.6419, "step": 107920 }, { "epoch": 4.93, "learning_rate": 2.541535081697103e-05, "loss": 1.5717, "step": 107930 }, { "epoch": 4.93, "learning_rate": 2.5413062382717744e-05, "loss": 1.6132, "step": 107940 }, { "epoch": 4.93, "learning_rate": 2.5410773948464462e-05, "loss": 1.5494, "step": 107950 }, { "epoch": 4.93, "learning_rate": 2.540848551421118e-05, "loss": 1.5874, "step": 107960 }, { "epoch": 4.93, "learning_rate": 2.5406197079957894e-05, "loss": 1.4867, "step": 107970 }, { "epoch": 4.93, "learning_rate": 2.540390864570461e-05, "loss": 1.6507, "step": 107980 }, { "epoch": 4.93, "learning_rate": 2.540162021145133e-05, "loss": 1.6366, "step": 107990 }, { "epoch": 4.93, "learning_rate": 2.5399331777198043e-05, "loss": 1.4983, "step": 108000 }, { "epoch": 4.93, "learning_rate": 2.539704334294476e-05, "loss": 1.3167, "step": 108010 }, { "epoch": 4.93, "learning_rate": 2.5394754908691474e-05, "loss": 1.4106, "step": 108020 }, { "epoch": 4.93, "learning_rate": 2.5392466474438192e-05, "loss": 1.5716, "step": 108030 }, { "epoch": 4.93, "learning_rate": 2.539017804018491e-05, "loss": 1.6007, "step": 108040 }, { "epoch": 4.93, "learning_rate": 2.5387889605931624e-05, "loss": 1.6321, "step": 108050 }, { "epoch": 4.93, "learning_rate": 2.538560117167834e-05, "loss": 1.6229, "step": 108060 }, { "epoch": 4.93, "learning_rate": 2.5383312737425052e-05, "loss": 1.5, "step": 108070 }, { "epoch": 4.94, "learning_rate": 2.538102430317177e-05, "loss": 1.6063, "step": 108080 }, { "epoch": 4.94, "learning_rate": 2.5378735868918483e-05, "loss": 1.4716, "step": 108090 }, { "epoch": 4.94, "learning_rate": 2.53764474346652e-05, "loss": 1.5783, "step": 108100 }, { "epoch": 4.94, "learning_rate": 2.537415900041192e-05, "loss": 1.4488, "step": 108110 }, { "epoch": 4.94, "learning_rate": 2.5371870566158633e-05, "loss": 1.5463, "step": 108120 }, { "epoch": 4.94, "learning_rate": 2.536958213190535e-05, "loss": 1.4896, "step": 108130 }, { "epoch": 4.94, "learning_rate": 2.5367293697652068e-05, "loss": 1.4522, "step": 108140 }, { "epoch": 4.94, "learning_rate": 2.5365005263398782e-05, "loss": 1.3267, "step": 108150 }, { "epoch": 4.94, "learning_rate": 2.53627168291455e-05, "loss": 1.5295, "step": 108160 }, { "epoch": 4.94, "learning_rate": 2.5360428394892217e-05, "loss": 1.485, "step": 108170 }, { "epoch": 4.94, "learning_rate": 2.535813996063893e-05, "loss": 1.554, "step": 108180 }, { "epoch": 4.94, "learning_rate": 2.535585152638565e-05, "loss": 1.4131, "step": 108190 }, { "epoch": 4.94, "learning_rate": 2.5353563092132366e-05, "loss": 1.4279, "step": 108200 }, { "epoch": 4.94, "learning_rate": 2.535127465787908e-05, "loss": 1.5359, "step": 108210 }, { "epoch": 4.94, "learning_rate": 2.5348986223625798e-05, "loss": 1.662, "step": 108220 }, { "epoch": 4.94, "learning_rate": 2.5346697789372515e-05, "loss": 1.4965, "step": 108230 }, { "epoch": 4.94, "learning_rate": 2.534440935511923e-05, "loss": 1.4868, "step": 108240 }, { "epoch": 4.94, "learning_rate": 2.5342120920865947e-05, "loss": 1.3761, "step": 108250 }, { "epoch": 4.94, "learning_rate": 2.5339832486612664e-05, "loss": 1.5888, "step": 108260 }, { "epoch": 4.94, "learning_rate": 2.5337544052359375e-05, "loss": 1.4773, "step": 108270 }, { "epoch": 4.94, "learning_rate": 2.533525561810609e-05, "loss": 1.6092, "step": 108280 }, { "epoch": 4.94, "learning_rate": 2.5332967183852807e-05, "loss": 1.4679, "step": 108290 }, { "epoch": 4.95, "learning_rate": 2.5330678749599524e-05, "loss": 1.4847, "step": 108300 }, { "epoch": 4.95, "learning_rate": 2.532839031534624e-05, "loss": 1.4723, "step": 108310 }, { "epoch": 4.95, "learning_rate": 2.5326101881092956e-05, "loss": 1.4556, "step": 108320 }, { "epoch": 4.95, "learning_rate": 2.5323813446839673e-05, "loss": 1.3869, "step": 108330 }, { "epoch": 4.95, "learning_rate": 2.5321525012586388e-05, "loss": 1.4823, "step": 108340 }, { "epoch": 4.95, "learning_rate": 2.5319236578333105e-05, "loss": 1.4901, "step": 108350 }, { "epoch": 4.95, "learning_rate": 2.5316948144079823e-05, "loss": 1.5509, "step": 108360 }, { "epoch": 4.95, "learning_rate": 2.5314659709826537e-05, "loss": 1.5971, "step": 108370 }, { "epoch": 4.95, "learning_rate": 2.5312371275573254e-05, "loss": 1.6789, "step": 108380 }, { "epoch": 4.95, "learning_rate": 2.5310082841319972e-05, "loss": 1.4097, "step": 108390 }, { "epoch": 4.95, "learning_rate": 2.5307794407066686e-05, "loss": 1.5526, "step": 108400 }, { "epoch": 4.95, "learning_rate": 2.5305505972813403e-05, "loss": 1.3687, "step": 108410 }, { "epoch": 4.95, "learning_rate": 2.530321753856012e-05, "loss": 1.4731, "step": 108420 }, { "epoch": 4.95, "learning_rate": 2.5300929104306835e-05, "loss": 1.5712, "step": 108430 }, { "epoch": 4.95, "learning_rate": 2.5298640670053553e-05, "loss": 1.4911, "step": 108440 }, { "epoch": 4.95, "learning_rate": 2.529635223580027e-05, "loss": 1.5083, "step": 108450 }, { "epoch": 4.95, "learning_rate": 2.5294063801546984e-05, "loss": 1.5722, "step": 108460 }, { "epoch": 4.95, "learning_rate": 2.5291775367293695e-05, "loss": 1.6438, "step": 108470 }, { "epoch": 4.95, "learning_rate": 2.5289486933040413e-05, "loss": 1.329, "step": 108480 }, { "epoch": 4.95, "learning_rate": 2.528719849878713e-05, "loss": 1.6507, "step": 108490 }, { "epoch": 4.95, "learning_rate": 2.5284910064533844e-05, "loss": 1.6021, "step": 108500 }, { "epoch": 4.95, "learning_rate": 2.5282621630280562e-05, "loss": 1.4603, "step": 108510 }, { "epoch": 4.96, "learning_rate": 2.528033319602728e-05, "loss": 1.741, "step": 108520 }, { "epoch": 4.96, "learning_rate": 2.5278044761773993e-05, "loss": 1.4615, "step": 108530 }, { "epoch": 4.96, "learning_rate": 2.527575632752071e-05, "loss": 1.5925, "step": 108540 }, { "epoch": 4.96, "learning_rate": 2.527346789326743e-05, "loss": 1.5513, "step": 108550 }, { "epoch": 4.96, "learning_rate": 2.5271179459014143e-05, "loss": 1.4127, "step": 108560 }, { "epoch": 4.96, "learning_rate": 2.526889102476086e-05, "loss": 1.5526, "step": 108570 }, { "epoch": 4.96, "learning_rate": 2.5266602590507578e-05, "loss": 1.5172, "step": 108580 }, { "epoch": 4.96, "learning_rate": 2.5264314156254292e-05, "loss": 1.5301, "step": 108590 }, { "epoch": 4.96, "learning_rate": 2.526202572200101e-05, "loss": 1.4824, "step": 108600 }, { "epoch": 4.96, "learning_rate": 2.5259737287747727e-05, "loss": 1.5139, "step": 108610 }, { "epoch": 4.96, "learning_rate": 2.525744885349444e-05, "loss": 1.4506, "step": 108620 }, { "epoch": 4.96, "learning_rate": 2.525516041924116e-05, "loss": 1.5711, "step": 108630 }, { "epoch": 4.96, "learning_rate": 2.5252871984987876e-05, "loss": 1.4925, "step": 108640 }, { "epoch": 4.96, "learning_rate": 2.525058355073459e-05, "loss": 1.6126, "step": 108650 }, { "epoch": 4.96, "learning_rate": 2.52482951164813e-05, "loss": 1.5686, "step": 108660 }, { "epoch": 4.96, "learning_rate": 2.524600668222802e-05, "loss": 1.5325, "step": 108670 }, { "epoch": 4.96, "learning_rate": 2.5243718247974736e-05, "loss": 1.4917, "step": 108680 }, { "epoch": 4.96, "learning_rate": 2.524142981372145e-05, "loss": 1.4362, "step": 108690 }, { "epoch": 4.96, "learning_rate": 2.5239141379468168e-05, "loss": 1.5033, "step": 108700 }, { "epoch": 4.96, "learning_rate": 2.5236852945214885e-05, "loss": 1.5129, "step": 108710 }, { "epoch": 4.96, "learning_rate": 2.52345645109616e-05, "loss": 1.4483, "step": 108720 }, { "epoch": 4.96, "learning_rate": 2.5232276076708317e-05, "loss": 1.6073, "step": 108730 }, { "epoch": 4.97, "learning_rate": 2.5229987642455034e-05, "loss": 1.6143, "step": 108740 }, { "epoch": 4.97, "learning_rate": 2.522769920820175e-05, "loss": 1.6883, "step": 108750 }, { "epoch": 4.97, "learning_rate": 2.5225410773948466e-05, "loss": 1.4113, "step": 108760 }, { "epoch": 4.97, "learning_rate": 2.5223122339695183e-05, "loss": 1.4249, "step": 108770 }, { "epoch": 4.97, "learning_rate": 2.5220833905441898e-05, "loss": 1.5366, "step": 108780 }, { "epoch": 4.97, "learning_rate": 2.5218545471188615e-05, "loss": 1.5589, "step": 108790 }, { "epoch": 4.97, "learning_rate": 2.5216257036935333e-05, "loss": 1.5322, "step": 108800 }, { "epoch": 4.97, "learning_rate": 2.5213968602682047e-05, "loss": 1.3708, "step": 108810 }, { "epoch": 4.97, "learning_rate": 2.5211680168428764e-05, "loss": 1.4764, "step": 108820 }, { "epoch": 4.97, "learning_rate": 2.5209391734175482e-05, "loss": 1.581, "step": 108830 }, { "epoch": 4.97, "learning_rate": 2.5207103299922196e-05, "loss": 1.4731, "step": 108840 }, { "epoch": 4.97, "learning_rate": 2.5204814865668913e-05, "loss": 1.5814, "step": 108850 }, { "epoch": 4.97, "learning_rate": 2.5202526431415624e-05, "loss": 1.7199, "step": 108860 }, { "epoch": 4.97, "learning_rate": 2.5200237997162342e-05, "loss": 1.6396, "step": 108870 }, { "epoch": 4.97, "learning_rate": 2.5197949562909056e-05, "loss": 1.6521, "step": 108880 }, { "epoch": 4.97, "learning_rate": 2.5195661128655773e-05, "loss": 1.2548, "step": 108890 }, { "epoch": 4.97, "learning_rate": 2.519337269440249e-05, "loss": 1.6304, "step": 108900 }, { "epoch": 4.97, "learning_rate": 2.5191084260149205e-05, "loss": 1.5372, "step": 108910 }, { "epoch": 4.97, "learning_rate": 2.5188795825895923e-05, "loss": 1.5667, "step": 108920 }, { "epoch": 4.97, "learning_rate": 2.518650739164264e-05, "loss": 1.3617, "step": 108930 }, { "epoch": 4.97, "learning_rate": 2.5184218957389354e-05, "loss": 1.5096, "step": 108940 }, { "epoch": 4.97, "learning_rate": 2.5181930523136072e-05, "loss": 1.5133, "step": 108950 }, { "epoch": 4.98, "learning_rate": 2.517964208888279e-05, "loss": 1.4425, "step": 108960 }, { "epoch": 4.98, "learning_rate": 2.5177353654629503e-05, "loss": 1.42, "step": 108970 }, { "epoch": 4.98, "learning_rate": 2.517506522037622e-05, "loss": 1.4457, "step": 108980 }, { "epoch": 4.98, "learning_rate": 2.517277678612294e-05, "loss": 1.6231, "step": 108990 }, { "epoch": 4.98, "learning_rate": 2.5170488351869653e-05, "loss": 1.5769, "step": 109000 }, { "epoch": 4.98, "learning_rate": 2.516819991761637e-05, "loss": 1.5367, "step": 109010 }, { "epoch": 4.98, "learning_rate": 2.5165911483363088e-05, "loss": 1.3937, "step": 109020 }, { "epoch": 4.98, "learning_rate": 2.5163623049109802e-05, "loss": 1.5253, "step": 109030 }, { "epoch": 4.98, "learning_rate": 2.516133461485652e-05, "loss": 1.564, "step": 109040 }, { "epoch": 4.98, "learning_rate": 2.5159046180603237e-05, "loss": 1.4731, "step": 109050 }, { "epoch": 4.98, "learning_rate": 2.5156757746349948e-05, "loss": 1.6443, "step": 109060 }, { "epoch": 4.98, "learning_rate": 2.515446931209666e-05, "loss": 1.4136, "step": 109070 }, { "epoch": 4.98, "learning_rate": 2.515218087784338e-05, "loss": 1.5123, "step": 109080 }, { "epoch": 4.98, "learning_rate": 2.5149892443590097e-05, "loss": 1.4892, "step": 109090 }, { "epoch": 4.98, "learning_rate": 2.514760400933681e-05, "loss": 1.5432, "step": 109100 }, { "epoch": 4.98, "learning_rate": 2.514531557508353e-05, "loss": 1.4791, "step": 109110 }, { "epoch": 4.98, "learning_rate": 2.5143027140830246e-05, "loss": 1.6498, "step": 109120 }, { "epoch": 4.98, "learning_rate": 2.514073870657696e-05, "loss": 1.6164, "step": 109130 }, { "epoch": 4.98, "learning_rate": 2.5138450272323678e-05, "loss": 1.654, "step": 109140 }, { "epoch": 4.98, "learning_rate": 2.5136161838070395e-05, "loss": 1.59, "step": 109150 }, { "epoch": 4.98, "learning_rate": 2.513387340381711e-05, "loss": 1.6223, "step": 109160 }, { "epoch": 4.98, "learning_rate": 2.5131584969563827e-05, "loss": 1.5563, "step": 109170 }, { "epoch": 4.99, "learning_rate": 2.512929653531054e-05, "loss": 1.41, "step": 109180 }, { "epoch": 4.99, "learning_rate": 2.512700810105726e-05, "loss": 1.5326, "step": 109190 }, { "epoch": 4.99, "learning_rate": 2.5124719666803976e-05, "loss": 1.5043, "step": 109200 }, { "epoch": 4.99, "learning_rate": 2.512243123255069e-05, "loss": 1.4955, "step": 109210 }, { "epoch": 4.99, "learning_rate": 2.5120142798297408e-05, "loss": 1.4982, "step": 109220 }, { "epoch": 4.99, "learning_rate": 2.5117854364044125e-05, "loss": 1.3888, "step": 109230 }, { "epoch": 4.99, "learning_rate": 2.511556592979084e-05, "loss": 1.4065, "step": 109240 }, { "epoch": 4.99, "learning_rate": 2.5113277495537557e-05, "loss": 1.4223, "step": 109250 }, { "epoch": 4.99, "learning_rate": 2.5110989061284267e-05, "loss": 1.497, "step": 109260 }, { "epoch": 4.99, "learning_rate": 2.5108700627030985e-05, "loss": 1.6835, "step": 109270 }, { "epoch": 4.99, "learning_rate": 2.51064121927777e-05, "loss": 1.5695, "step": 109280 }, { "epoch": 4.99, "learning_rate": 2.5104123758524417e-05, "loss": 1.5114, "step": 109290 }, { "epoch": 4.99, "learning_rate": 2.5101835324271134e-05, "loss": 1.6359, "step": 109300 }, { "epoch": 4.99, "learning_rate": 2.5099546890017848e-05, "loss": 1.4643, "step": 109310 }, { "epoch": 4.99, "learning_rate": 2.5097258455764566e-05, "loss": 1.4671, "step": 109320 }, { "epoch": 4.99, "learning_rate": 2.5094970021511283e-05, "loss": 1.874, "step": 109330 }, { "epoch": 4.99, "learning_rate": 2.5092681587257997e-05, "loss": 1.3817, "step": 109340 }, { "epoch": 4.99, "learning_rate": 2.5090393153004715e-05, "loss": 1.517, "step": 109350 }, { "epoch": 4.99, "learning_rate": 2.5088104718751433e-05, "loss": 1.3917, "step": 109360 }, { "epoch": 4.99, "learning_rate": 2.5085816284498147e-05, "loss": 1.5149, "step": 109370 }, { "epoch": 4.99, "learning_rate": 2.5083527850244864e-05, "loss": 1.4471, "step": 109380 }, { "epoch": 5.0, "learning_rate": 2.5081239415991582e-05, "loss": 1.4139, "step": 109390 }, { "epoch": 5.0, "learning_rate": 2.5078950981738296e-05, "loss": 1.5554, "step": 109400 }, { "epoch": 5.0, "learning_rate": 2.5076662547485013e-05, "loss": 1.6728, "step": 109410 }, { "epoch": 5.0, "learning_rate": 2.507437411323173e-05, "loss": 1.3988, "step": 109420 }, { "epoch": 5.0, "learning_rate": 2.5072085678978445e-05, "loss": 1.4962, "step": 109430 }, { "epoch": 5.0, "learning_rate": 2.5069797244725163e-05, "loss": 1.4851, "step": 109440 }, { "epoch": 5.0, "learning_rate": 2.5067508810471873e-05, "loss": 1.6258, "step": 109450 }, { "epoch": 5.0, "learning_rate": 2.506522037621859e-05, "loss": 1.4418, "step": 109460 }, { "epoch": 5.0, "learning_rate": 2.5062931941965305e-05, "loss": 1.4715, "step": 109470 }, { "epoch": 5.0, "learning_rate": 2.5060643507712022e-05, "loss": 1.5167, "step": 109480 }, { "epoch": 5.0, "learning_rate": 2.505835507345874e-05, "loss": 1.5022, "step": 109490 }, { "epoch": 5.0, "eval_cer": 0.67826871720654, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.4133152961730957, "eval_runtime": 2564.0286, "eval_samples_per_second": 4.122, "eval_steps_per_second": 2.061, "eval_wer": 0.9927152317880795, "step": 109498 }, { "epoch": 5.0, "learning_rate": 2.5056066639205454e-05, "loss": 1.5497, "step": 109500 }, { "epoch": 5.0, "learning_rate": 2.505377820495217e-05, "loss": 1.6613, "step": 109510 }, { "epoch": 5.0, "learning_rate": 2.505148977069889e-05, "loss": 1.5617, "step": 109520 }, { "epoch": 5.0, "learning_rate": 2.5049201336445603e-05, "loss": 1.4069, "step": 109530 }, { "epoch": 5.0, "learning_rate": 2.504691290219232e-05, "loss": 1.4432, "step": 109540 }, { "epoch": 5.0, "learning_rate": 2.504462446793904e-05, "loss": 1.4498, "step": 109550 }, { "epoch": 5.0, "learning_rate": 2.5042336033685752e-05, "loss": 1.5555, "step": 109560 }, { "epoch": 5.0, "learning_rate": 2.504004759943247e-05, "loss": 1.3881, "step": 109570 }, { "epoch": 5.0, "learning_rate": 2.5037759165179188e-05, "loss": 1.5646, "step": 109580 }, { "epoch": 5.0, "learning_rate": 2.50354707309259e-05, "loss": 1.4809, "step": 109590 }, { "epoch": 5.0, "learning_rate": 2.503318229667262e-05, "loss": 1.4362, "step": 109600 }, { "epoch": 5.01, "learning_rate": 2.5030893862419337e-05, "loss": 1.3508, "step": 109610 }, { "epoch": 5.01, "learning_rate": 2.502860542816605e-05, "loss": 1.369, "step": 109620 }, { "epoch": 5.01, "learning_rate": 2.502631699391277e-05, "loss": 1.4339, "step": 109630 }, { "epoch": 5.01, "learning_rate": 2.5024028559659486e-05, "loss": 1.4109, "step": 109640 }, { "epoch": 5.01, "learning_rate": 2.5021740125406197e-05, "loss": 1.4362, "step": 109650 }, { "epoch": 5.01, "learning_rate": 2.501945169115291e-05, "loss": 1.5939, "step": 109660 }, { "epoch": 5.01, "learning_rate": 2.5017163256899628e-05, "loss": 1.4799, "step": 109670 }, { "epoch": 5.01, "learning_rate": 2.5014874822646346e-05, "loss": 1.5436, "step": 109680 }, { "epoch": 5.01, "learning_rate": 2.501258638839306e-05, "loss": 1.3521, "step": 109690 }, { "epoch": 5.01, "learning_rate": 2.5010297954139777e-05, "loss": 1.583, "step": 109700 }, { "epoch": 5.01, "learning_rate": 2.5008009519886495e-05, "loss": 1.5811, "step": 109710 }, { "epoch": 5.01, "learning_rate": 2.500572108563321e-05, "loss": 1.3693, "step": 109720 }, { "epoch": 5.01, "learning_rate": 2.5003432651379927e-05, "loss": 1.5059, "step": 109730 }, { "epoch": 5.01, "learning_rate": 2.5001144217126644e-05, "loss": 1.4751, "step": 109740 }, { "epoch": 5.01, "learning_rate": 2.4998855782873358e-05, "loss": 1.4308, "step": 109750 }, { "epoch": 5.01, "learning_rate": 2.4996567348620076e-05, "loss": 1.4824, "step": 109760 }, { "epoch": 5.01, "learning_rate": 2.4994278914366793e-05, "loss": 1.5279, "step": 109770 }, { "epoch": 5.01, "learning_rate": 2.4991990480113507e-05, "loss": 1.3582, "step": 109780 }, { "epoch": 5.01, "learning_rate": 2.4989702045860225e-05, "loss": 1.4537, "step": 109790 }, { "epoch": 5.01, "learning_rate": 2.498741361160694e-05, "loss": 1.5085, "step": 109800 }, { "epoch": 5.01, "learning_rate": 2.4985125177353653e-05, "loss": 1.4838, "step": 109810 }, { "epoch": 5.01, "learning_rate": 2.498283674310037e-05, "loss": 1.4108, "step": 109820 }, { "epoch": 5.02, "learning_rate": 2.4980548308847088e-05, "loss": 1.5432, "step": 109830 }, { "epoch": 5.02, "learning_rate": 2.4978259874593802e-05, "loss": 1.5567, "step": 109840 }, { "epoch": 5.02, "learning_rate": 2.497597144034052e-05, "loss": 1.3791, "step": 109850 }, { "epoch": 5.02, "learning_rate": 2.4973683006087237e-05, "loss": 1.6362, "step": 109860 }, { "epoch": 5.02, "learning_rate": 2.497139457183395e-05, "loss": 1.2896, "step": 109870 }, { "epoch": 5.02, "learning_rate": 2.496910613758067e-05, "loss": 1.4394, "step": 109880 }, { "epoch": 5.02, "learning_rate": 2.4966817703327387e-05, "loss": 1.6013, "step": 109890 }, { "epoch": 5.02, "learning_rate": 2.49645292690741e-05, "loss": 1.6136, "step": 109900 }, { "epoch": 5.02, "learning_rate": 2.4962240834820815e-05, "loss": 1.311, "step": 109910 }, { "epoch": 5.02, "learning_rate": 2.4959952400567532e-05, "loss": 1.4758, "step": 109920 }, { "epoch": 5.02, "learning_rate": 2.495766396631425e-05, "loss": 1.5709, "step": 109930 }, { "epoch": 5.02, "learning_rate": 2.4955375532060964e-05, "loss": 1.3206, "step": 109940 }, { "epoch": 5.02, "learning_rate": 2.495308709780768e-05, "loss": 1.3407, "step": 109950 }, { "epoch": 5.02, "learning_rate": 2.49507986635544e-05, "loss": 1.3491, "step": 109960 }, { "epoch": 5.02, "learning_rate": 2.4948510229301113e-05, "loss": 1.577, "step": 109970 }, { "epoch": 5.02, "learning_rate": 2.494622179504783e-05, "loss": 1.663, "step": 109980 }, { "epoch": 5.02, "learning_rate": 2.4943933360794548e-05, "loss": 1.4405, "step": 109990 }, { "epoch": 5.02, "learning_rate": 2.494164492654126e-05, "loss": 1.4799, "step": 110000 }, { "epoch": 5.02, "learning_rate": 2.4939356492287977e-05, "loss": 1.5853, "step": 110010 }, { "epoch": 5.02, "learning_rate": 2.4937068058034694e-05, "loss": 1.3425, "step": 110020 }, { "epoch": 5.02, "learning_rate": 2.4934779623781408e-05, "loss": 1.7278, "step": 110030 }, { "epoch": 5.02, "learning_rate": 2.4932491189528126e-05, "loss": 1.5616, "step": 110040 }, { "epoch": 5.03, "learning_rate": 2.4930202755274843e-05, "loss": 1.5864, "step": 110050 }, { "epoch": 5.03, "learning_rate": 2.4927914321021557e-05, "loss": 1.4786, "step": 110060 }, { "epoch": 5.03, "learning_rate": 2.4925625886768275e-05, "loss": 1.5022, "step": 110070 }, { "epoch": 5.03, "learning_rate": 2.4923337452514992e-05, "loss": 1.468, "step": 110080 }, { "epoch": 5.03, "learning_rate": 2.4921049018261707e-05, "loss": 1.4954, "step": 110090 }, { "epoch": 5.03, "learning_rate": 2.491876058400842e-05, "loss": 1.4406, "step": 110100 }, { "epoch": 5.03, "learning_rate": 2.4916472149755138e-05, "loss": 1.4282, "step": 110110 }, { "epoch": 5.03, "learning_rate": 2.4914183715501856e-05, "loss": 1.5342, "step": 110120 }, { "epoch": 5.03, "learning_rate": 2.491189528124857e-05, "loss": 1.5862, "step": 110130 }, { "epoch": 5.03, "learning_rate": 2.4909606846995287e-05, "loss": 1.3514, "step": 110140 }, { "epoch": 5.03, "learning_rate": 2.4907318412742005e-05, "loss": 1.4607, "step": 110150 }, { "epoch": 5.03, "learning_rate": 2.490502997848872e-05, "loss": 1.5723, "step": 110160 }, { "epoch": 5.03, "learning_rate": 2.4902741544235437e-05, "loss": 1.5166, "step": 110170 }, { "epoch": 5.03, "learning_rate": 2.4900453109982154e-05, "loss": 1.5839, "step": 110180 }, { "epoch": 5.03, "learning_rate": 2.4898164675728865e-05, "loss": 1.6468, "step": 110190 }, { "epoch": 5.03, "learning_rate": 2.4895876241475582e-05, "loss": 1.4472, "step": 110200 }, { "epoch": 5.03, "learning_rate": 2.48935878072223e-05, "loss": 1.4674, "step": 110210 }, { "epoch": 5.03, "learning_rate": 2.4891299372969014e-05, "loss": 1.4485, "step": 110220 }, { "epoch": 5.03, "learning_rate": 2.488901093871573e-05, "loss": 1.4616, "step": 110230 }, { "epoch": 5.03, "learning_rate": 2.488672250446245e-05, "loss": 1.4851, "step": 110240 }, { "epoch": 5.03, "learning_rate": 2.4884434070209163e-05, "loss": 1.4133, "step": 110250 }, { "epoch": 5.03, "learning_rate": 2.488214563595588e-05, "loss": 1.3828, "step": 110260 }, { "epoch": 5.04, "learning_rate": 2.4879857201702598e-05, "loss": 1.4833, "step": 110270 }, { "epoch": 5.04, "learning_rate": 2.4877568767449312e-05, "loss": 1.6048, "step": 110280 }, { "epoch": 5.04, "learning_rate": 2.4875280333196027e-05, "loss": 1.3491, "step": 110290 }, { "epoch": 5.04, "learning_rate": 2.4872991898942744e-05, "loss": 1.4619, "step": 110300 }, { "epoch": 5.04, "learning_rate": 2.487070346468946e-05, "loss": 1.4317, "step": 110310 }, { "epoch": 5.04, "learning_rate": 2.4868415030436176e-05, "loss": 1.4942, "step": 110320 }, { "epoch": 5.04, "learning_rate": 2.4866126596182893e-05, "loss": 1.6207, "step": 110330 }, { "epoch": 5.04, "learning_rate": 2.4863838161929607e-05, "loss": 1.3958, "step": 110340 }, { "epoch": 5.04, "learning_rate": 2.4861549727676325e-05, "loss": 1.4166, "step": 110350 }, { "epoch": 5.04, "learning_rate": 2.4859261293423042e-05, "loss": 1.4915, "step": 110360 }, { "epoch": 5.04, "learning_rate": 2.4856972859169757e-05, "loss": 1.3572, "step": 110370 }, { "epoch": 5.04, "learning_rate": 2.4854684424916474e-05, "loss": 1.5795, "step": 110380 }, { "epoch": 5.04, "learning_rate": 2.4852395990663188e-05, "loss": 1.551, "step": 110390 }, { "epoch": 5.04, "learning_rate": 2.4850107556409906e-05, "loss": 1.5128, "step": 110400 }, { "epoch": 5.04, "learning_rate": 2.484781912215662e-05, "loss": 1.6439, "step": 110410 }, { "epoch": 5.04, "learning_rate": 2.4845530687903337e-05, "loss": 1.427, "step": 110420 }, { "epoch": 5.04, "learning_rate": 2.4843242253650055e-05, "loss": 1.4419, "step": 110430 }, { "epoch": 5.04, "learning_rate": 2.484095381939677e-05, "loss": 1.4378, "step": 110440 }, { "epoch": 5.04, "learning_rate": 2.4838665385143487e-05, "loss": 1.5375, "step": 110450 }, { "epoch": 5.04, "learning_rate": 2.4836376950890204e-05, "loss": 1.4635, "step": 110460 }, { "epoch": 5.04, "learning_rate": 2.4834088516636918e-05, "loss": 1.5618, "step": 110470 }, { "epoch": 5.04, "learning_rate": 2.4831800082383636e-05, "loss": 1.6458, "step": 110480 }, { "epoch": 5.05, "learning_rate": 2.482951164813035e-05, "loss": 1.4922, "step": 110490 }, { "epoch": 5.05, "learning_rate": 2.4827223213877064e-05, "loss": 1.4818, "step": 110500 }, { "epoch": 5.05, "learning_rate": 2.482493477962378e-05, "loss": 1.4625, "step": 110510 }, { "epoch": 5.05, "learning_rate": 2.48226463453705e-05, "loss": 1.5454, "step": 110520 }, { "epoch": 5.05, "learning_rate": 2.4820357911117213e-05, "loss": 1.5086, "step": 110530 }, { "epoch": 5.05, "learning_rate": 2.481806947686393e-05, "loss": 1.5392, "step": 110540 }, { "epoch": 5.05, "learning_rate": 2.4815781042610648e-05, "loss": 1.4611, "step": 110550 }, { "epoch": 5.05, "learning_rate": 2.4813492608357362e-05, "loss": 1.5268, "step": 110560 }, { "epoch": 5.05, "learning_rate": 2.481120417410408e-05, "loss": 1.5264, "step": 110570 }, { "epoch": 5.05, "learning_rate": 2.4808915739850797e-05, "loss": 1.4239, "step": 110580 }, { "epoch": 5.05, "learning_rate": 2.480662730559751e-05, "loss": 1.4067, "step": 110590 }, { "epoch": 5.05, "learning_rate": 2.4804338871344226e-05, "loss": 1.6033, "step": 110600 }, { "epoch": 5.05, "learning_rate": 2.4802050437090943e-05, "loss": 1.4087, "step": 110610 }, { "epoch": 5.05, "learning_rate": 2.479976200283766e-05, "loss": 1.6082, "step": 110620 }, { "epoch": 5.05, "learning_rate": 2.4797473568584375e-05, "loss": 1.3891, "step": 110630 }, { "epoch": 5.05, "learning_rate": 2.4795185134331092e-05, "loss": 1.5467, "step": 110640 }, { "epoch": 5.05, "learning_rate": 2.479289670007781e-05, "loss": 1.7135, "step": 110650 }, { "epoch": 5.05, "learning_rate": 2.4790608265824524e-05, "loss": 1.5446, "step": 110660 }, { "epoch": 5.05, "learning_rate": 2.478831983157124e-05, "loss": 1.4647, "step": 110670 }, { "epoch": 5.05, "learning_rate": 2.478603139731796e-05, "loss": 1.6574, "step": 110680 }, { "epoch": 5.05, "learning_rate": 2.478374296306467e-05, "loss": 1.6637, "step": 110690 }, { "epoch": 5.05, "learning_rate": 2.4781454528811387e-05, "loss": 1.6135, "step": 110700 }, { "epoch": 5.06, "learning_rate": 2.4779166094558105e-05, "loss": 1.6004, "step": 110710 }, { "epoch": 5.06, "learning_rate": 2.477687766030482e-05, "loss": 1.5176, "step": 110720 }, { "epoch": 5.06, "learning_rate": 2.4774589226051536e-05, "loss": 1.3315, "step": 110730 }, { "epoch": 5.06, "learning_rate": 2.4772300791798254e-05, "loss": 1.5864, "step": 110740 }, { "epoch": 5.06, "learning_rate": 2.4770012357544968e-05, "loss": 1.3959, "step": 110750 }, { "epoch": 5.06, "learning_rate": 2.4767723923291686e-05, "loss": 1.5944, "step": 110760 }, { "epoch": 5.06, "learning_rate": 2.4765435489038403e-05, "loss": 1.4745, "step": 110770 }, { "epoch": 5.06, "learning_rate": 2.4763147054785117e-05, "loss": 1.4535, "step": 110780 }, { "epoch": 5.06, "learning_rate": 2.476085862053183e-05, "loss": 1.4523, "step": 110790 }, { "epoch": 5.06, "learning_rate": 2.475857018627855e-05, "loss": 1.5125, "step": 110800 }, { "epoch": 5.06, "learning_rate": 2.4756281752025266e-05, "loss": 1.5465, "step": 110810 }, { "epoch": 5.06, "learning_rate": 2.475399331777198e-05, "loss": 1.6502, "step": 110820 }, { "epoch": 5.06, "learning_rate": 2.4751704883518698e-05, "loss": 1.5186, "step": 110830 }, { "epoch": 5.06, "learning_rate": 2.4749416449265416e-05, "loss": 1.4218, "step": 110840 }, { "epoch": 5.06, "learning_rate": 2.474712801501213e-05, "loss": 1.4988, "step": 110850 }, { "epoch": 5.06, "learning_rate": 2.4744839580758847e-05, "loss": 1.3298, "step": 110860 }, { "epoch": 5.06, "learning_rate": 2.4742551146505565e-05, "loss": 1.4871, "step": 110870 }, { "epoch": 5.06, "learning_rate": 2.474026271225228e-05, "loss": 1.4819, "step": 110880 }, { "epoch": 5.06, "learning_rate": 2.4737974277998993e-05, "loss": 1.4799, "step": 110890 }, { "epoch": 5.06, "learning_rate": 2.473568584374571e-05, "loss": 1.5397, "step": 110900 }, { "epoch": 5.06, "learning_rate": 2.4733397409492425e-05, "loss": 1.4644, "step": 110910 }, { "epoch": 5.06, "learning_rate": 2.4731108975239142e-05, "loss": 1.6425, "step": 110920 }, { "epoch": 5.07, "learning_rate": 2.472882054098586e-05, "loss": 1.4619, "step": 110930 }, { "epoch": 5.07, "learning_rate": 2.4726532106732574e-05, "loss": 1.4701, "step": 110940 }, { "epoch": 5.07, "learning_rate": 2.472424367247929e-05, "loss": 1.3438, "step": 110950 }, { "epoch": 5.07, "learning_rate": 2.472195523822601e-05, "loss": 1.5145, "step": 110960 }, { "epoch": 5.07, "learning_rate": 2.4719666803972723e-05, "loss": 1.433, "step": 110970 }, { "epoch": 5.07, "learning_rate": 2.4717378369719437e-05, "loss": 1.4083, "step": 110980 }, { "epoch": 5.07, "learning_rate": 2.4715089935466155e-05, "loss": 1.5308, "step": 110990 }, { "epoch": 5.07, "learning_rate": 2.471280150121287e-05, "loss": 1.7228, "step": 111000 }, { "epoch": 5.07, "learning_rate": 2.4710513066959586e-05, "loss": 1.5771, "step": 111010 }, { "epoch": 5.07, "learning_rate": 2.4708224632706304e-05, "loss": 1.4485, "step": 111020 }, { "epoch": 5.07, "learning_rate": 2.4705936198453018e-05, "loss": 1.4257, "step": 111030 }, { "epoch": 5.07, "learning_rate": 2.4703647764199736e-05, "loss": 1.4415, "step": 111040 }, { "epoch": 5.07, "learning_rate": 2.4701359329946453e-05, "loss": 1.4202, "step": 111050 }, { "epoch": 5.07, "learning_rate": 2.4699070895693167e-05, "loss": 1.4034, "step": 111060 }, { "epoch": 5.07, "learning_rate": 2.4696782461439885e-05, "loss": 1.4676, "step": 111070 }, { "epoch": 5.07, "learning_rate": 2.46944940271866e-05, "loss": 1.4799, "step": 111080 }, { "epoch": 5.07, "learning_rate": 2.4692205592933316e-05, "loss": 1.3597, "step": 111090 }, { "epoch": 5.07, "learning_rate": 2.468991715868003e-05, "loss": 1.456, "step": 111100 }, { "epoch": 5.07, "learning_rate": 2.4687628724426748e-05, "loss": 1.4144, "step": 111110 }, { "epoch": 5.07, "learning_rate": 2.4685340290173466e-05, "loss": 1.5141, "step": 111120 }, { "epoch": 5.07, "learning_rate": 2.468305185592018e-05, "loss": 1.6461, "step": 111130 }, { "epoch": 5.07, "learning_rate": 2.4680763421666897e-05, "loss": 1.5221, "step": 111140 }, { "epoch": 5.08, "learning_rate": 2.4678474987413615e-05, "loss": 1.5091, "step": 111150 }, { "epoch": 5.08, "learning_rate": 2.467618655316033e-05, "loss": 1.4475, "step": 111160 }, { "epoch": 5.08, "learning_rate": 2.4673898118907046e-05, "loss": 1.4287, "step": 111170 }, { "epoch": 5.08, "learning_rate": 2.467160968465376e-05, "loss": 1.5374, "step": 111180 }, { "epoch": 5.08, "learning_rate": 2.4669321250400475e-05, "loss": 1.6117, "step": 111190 }, { "epoch": 5.08, "learning_rate": 2.4667032816147192e-05, "loss": 1.5205, "step": 111200 }, { "epoch": 5.08, "learning_rate": 2.466474438189391e-05, "loss": 1.5237, "step": 111210 }, { "epoch": 5.08, "learning_rate": 2.4662455947640624e-05, "loss": 1.4423, "step": 111220 }, { "epoch": 5.08, "learning_rate": 2.466016751338734e-05, "loss": 1.5513, "step": 111230 }, { "epoch": 5.08, "learning_rate": 2.465787907913406e-05, "loss": 1.4622, "step": 111240 }, { "epoch": 5.08, "learning_rate": 2.4655590644880773e-05, "loss": 1.5339, "step": 111250 }, { "epoch": 5.08, "learning_rate": 2.465330221062749e-05, "loss": 1.4088, "step": 111260 }, { "epoch": 5.08, "learning_rate": 2.4651013776374208e-05, "loss": 1.4395, "step": 111270 }, { "epoch": 5.08, "learning_rate": 2.4648725342120922e-05, "loss": 1.5, "step": 111280 }, { "epoch": 5.08, "learning_rate": 2.4646436907867636e-05, "loss": 1.3872, "step": 111290 }, { "epoch": 5.08, "learning_rate": 2.4644148473614354e-05, "loss": 1.4381, "step": 111300 }, { "epoch": 5.08, "learning_rate": 2.464186003936107e-05, "loss": 1.5064, "step": 111310 }, { "epoch": 5.08, "learning_rate": 2.4639571605107786e-05, "loss": 1.4352, "step": 111320 }, { "epoch": 5.08, "learning_rate": 2.4637283170854503e-05, "loss": 1.4385, "step": 111330 }, { "epoch": 5.08, "learning_rate": 2.463499473660122e-05, "loss": 1.4949, "step": 111340 }, { "epoch": 5.08, "learning_rate": 2.4632706302347935e-05, "loss": 1.4065, "step": 111350 }, { "epoch": 5.08, "learning_rate": 2.4630417868094652e-05, "loss": 1.4719, "step": 111360 }, { "epoch": 5.09, "learning_rate": 2.462812943384137e-05, "loss": 1.4535, "step": 111370 }, { "epoch": 5.09, "learning_rate": 2.462584099958808e-05, "loss": 1.5182, "step": 111380 }, { "epoch": 5.09, "learning_rate": 2.4623552565334798e-05, "loss": 1.3281, "step": 111390 }, { "epoch": 5.09, "learning_rate": 2.4621264131081516e-05, "loss": 1.5437, "step": 111400 }, { "epoch": 5.09, "learning_rate": 2.461897569682823e-05, "loss": 1.3007, "step": 111410 }, { "epoch": 5.09, "learning_rate": 2.4616687262574947e-05, "loss": 1.6156, "step": 111420 }, { "epoch": 5.09, "learning_rate": 2.4614398828321665e-05, "loss": 1.6193, "step": 111430 }, { "epoch": 5.09, "learning_rate": 2.461211039406838e-05, "loss": 1.5336, "step": 111440 }, { "epoch": 5.09, "learning_rate": 2.4609821959815096e-05, "loss": 1.497, "step": 111450 }, { "epoch": 5.09, "learning_rate": 2.4607533525561814e-05, "loss": 1.5545, "step": 111460 }, { "epoch": 5.09, "learning_rate": 2.4605245091308528e-05, "loss": 1.5911, "step": 111470 }, { "epoch": 5.09, "learning_rate": 2.4602956657055242e-05, "loss": 1.4997, "step": 111480 }, { "epoch": 5.09, "learning_rate": 2.460066822280196e-05, "loss": 1.5257, "step": 111490 }, { "epoch": 5.09, "learning_rate": 2.4598379788548674e-05, "loss": 1.5072, "step": 111500 }, { "epoch": 5.09, "learning_rate": 2.459609135429539e-05, "loss": 1.4036, "step": 111510 }, { "epoch": 5.09, "learning_rate": 2.459380292004211e-05, "loss": 1.5006, "step": 111520 }, { "epoch": 5.09, "learning_rate": 2.4591514485788823e-05, "loss": 1.4097, "step": 111530 }, { "epoch": 5.09, "learning_rate": 2.458922605153554e-05, "loss": 1.4767, "step": 111540 }, { "epoch": 5.09, "learning_rate": 2.4586937617282258e-05, "loss": 1.2808, "step": 111550 }, { "epoch": 5.09, "learning_rate": 2.4584649183028972e-05, "loss": 1.2884, "step": 111560 }, { "epoch": 5.09, "learning_rate": 2.458236074877569e-05, "loss": 1.4208, "step": 111570 }, { "epoch": 5.1, "learning_rate": 2.4580072314522404e-05, "loss": 1.5577, "step": 111580 }, { "epoch": 5.1, "learning_rate": 2.457778388026912e-05, "loss": 1.5081, "step": 111590 }, { "epoch": 5.1, "learning_rate": 2.4575495446015836e-05, "loss": 1.3984, "step": 111600 }, { "epoch": 5.1, "learning_rate": 2.4573207011762553e-05, "loss": 1.5313, "step": 111610 }, { "epoch": 5.1, "learning_rate": 2.457091857750927e-05, "loss": 1.5528, "step": 111620 }, { "epoch": 5.1, "learning_rate": 2.4568630143255985e-05, "loss": 1.5549, "step": 111630 }, { "epoch": 5.1, "learning_rate": 2.4566341709002702e-05, "loss": 1.5741, "step": 111640 }, { "epoch": 5.1, "learning_rate": 2.456405327474942e-05, "loss": 1.459, "step": 111650 }, { "epoch": 5.1, "learning_rate": 2.4561764840496134e-05, "loss": 1.4384, "step": 111660 }, { "epoch": 5.1, "learning_rate": 2.455947640624285e-05, "loss": 1.4973, "step": 111670 }, { "epoch": 5.1, "learning_rate": 2.4557187971989566e-05, "loss": 1.3479, "step": 111680 }, { "epoch": 5.1, "learning_rate": 2.455489953773628e-05, "loss": 1.5122, "step": 111690 }, { "epoch": 5.1, "learning_rate": 2.4552611103482997e-05, "loss": 1.5226, "step": 111700 }, { "epoch": 5.1, "learning_rate": 2.4550322669229715e-05, "loss": 1.3679, "step": 111710 }, { "epoch": 5.1, "learning_rate": 2.454803423497643e-05, "loss": 1.423, "step": 111720 }, { "epoch": 5.1, "learning_rate": 2.4545745800723146e-05, "loss": 1.5208, "step": 111730 }, { "epoch": 5.1, "learning_rate": 2.4543457366469864e-05, "loss": 1.7191, "step": 111740 }, { "epoch": 5.1, "learning_rate": 2.4541168932216578e-05, "loss": 1.3427, "step": 111750 }, { "epoch": 5.1, "learning_rate": 2.4538880497963296e-05, "loss": 1.4211, "step": 111760 }, { "epoch": 5.1, "learning_rate": 2.453659206371001e-05, "loss": 1.4033, "step": 111770 }, { "epoch": 5.1, "learning_rate": 2.4534303629456727e-05, "loss": 1.4407, "step": 111780 }, { "epoch": 5.1, "learning_rate": 2.453201519520344e-05, "loss": 1.5329, "step": 111790 }, { "epoch": 5.11, "learning_rate": 2.452972676095016e-05, "loss": 1.3835, "step": 111800 }, { "epoch": 5.11, "learning_rate": 2.4527438326696876e-05, "loss": 1.6089, "step": 111810 }, { "epoch": 5.11, "learning_rate": 2.452514989244359e-05, "loss": 1.4096, "step": 111820 }, { "epoch": 5.11, "learning_rate": 2.4522861458190308e-05, "loss": 1.3852, "step": 111830 }, { "epoch": 5.11, "learning_rate": 2.4520573023937026e-05, "loss": 1.5213, "step": 111840 }, { "epoch": 5.11, "learning_rate": 2.451828458968374e-05, "loss": 1.5027, "step": 111850 }, { "epoch": 5.11, "learning_rate": 2.4515996155430457e-05, "loss": 1.4275, "step": 111860 }, { "epoch": 5.11, "learning_rate": 2.451370772117717e-05, "loss": 1.5338, "step": 111870 }, { "epoch": 5.11, "learning_rate": 2.4511419286923885e-05, "loss": 1.3948, "step": 111880 }, { "epoch": 5.11, "learning_rate": 2.4509130852670603e-05, "loss": 1.5398, "step": 111890 }, { "epoch": 5.11, "learning_rate": 2.450684241841732e-05, "loss": 1.5002, "step": 111900 }, { "epoch": 5.11, "learning_rate": 2.4504553984164035e-05, "loss": 1.4625, "step": 111910 }, { "epoch": 5.11, "learning_rate": 2.4502265549910752e-05, "loss": 1.4781, "step": 111920 }, { "epoch": 5.11, "learning_rate": 2.449997711565747e-05, "loss": 1.6054, "step": 111930 }, { "epoch": 5.11, "learning_rate": 2.4497688681404184e-05, "loss": 1.5766, "step": 111940 }, { "epoch": 5.11, "learning_rate": 2.44954002471509e-05, "loss": 1.4466, "step": 111950 }, { "epoch": 5.11, "learning_rate": 2.449311181289762e-05, "loss": 1.5472, "step": 111960 }, { "epoch": 5.11, "learning_rate": 2.4490823378644333e-05, "loss": 1.604, "step": 111970 }, { "epoch": 5.11, "learning_rate": 2.4488534944391047e-05, "loss": 1.3504, "step": 111980 }, { "epoch": 5.11, "learning_rate": 2.4486246510137765e-05, "loss": 1.5523, "step": 111990 }, { "epoch": 5.11, "learning_rate": 2.4483958075884482e-05, "loss": 1.4036, "step": 112000 }, { "epoch": 5.11, "learning_rate": 2.4481669641631196e-05, "loss": 1.4238, "step": 112010 }, { "epoch": 5.12, "learning_rate": 2.4479381207377914e-05, "loss": 1.464, "step": 112020 }, { "epoch": 5.12, "learning_rate": 2.447709277312463e-05, "loss": 1.5786, "step": 112030 }, { "epoch": 5.12, "learning_rate": 2.4474804338871345e-05, "loss": 1.5599, "step": 112040 }, { "epoch": 5.12, "learning_rate": 2.4472515904618063e-05, "loss": 1.5353, "step": 112050 }, { "epoch": 5.12, "learning_rate": 2.4470227470364777e-05, "loss": 1.5367, "step": 112060 }, { "epoch": 5.12, "learning_rate": 2.446793903611149e-05, "loss": 1.4694, "step": 112070 }, { "epoch": 5.12, "learning_rate": 2.446565060185821e-05, "loss": 1.3287, "step": 112080 }, { "epoch": 5.12, "learning_rate": 2.4463362167604926e-05, "loss": 1.5299, "step": 112090 }, { "epoch": 5.12, "learning_rate": 2.446107373335164e-05, "loss": 1.3374, "step": 112100 }, { "epoch": 5.12, "learning_rate": 2.4458785299098358e-05, "loss": 1.6302, "step": 112110 }, { "epoch": 5.12, "learning_rate": 2.4456496864845075e-05, "loss": 1.4212, "step": 112120 }, { "epoch": 5.12, "learning_rate": 2.445420843059179e-05, "loss": 1.4296, "step": 112130 }, { "epoch": 5.12, "learning_rate": 2.4451919996338507e-05, "loss": 1.5521, "step": 112140 }, { "epoch": 5.12, "learning_rate": 2.4449631562085225e-05, "loss": 1.5285, "step": 112150 }, { "epoch": 5.12, "learning_rate": 2.444734312783194e-05, "loss": 1.5723, "step": 112160 }, { "epoch": 5.12, "learning_rate": 2.4445054693578653e-05, "loss": 1.5131, "step": 112170 }, { "epoch": 5.12, "learning_rate": 2.444276625932537e-05, "loss": 1.3552, "step": 112180 }, { "epoch": 5.12, "learning_rate": 2.4440477825072085e-05, "loss": 1.3758, "step": 112190 }, { "epoch": 5.12, "learning_rate": 2.4438189390818802e-05, "loss": 1.6027, "step": 112200 }, { "epoch": 5.12, "learning_rate": 2.443590095656552e-05, "loss": 1.458, "step": 112210 }, { "epoch": 5.12, "learning_rate": 2.4433612522312234e-05, "loss": 1.4679, "step": 112220 }, { "epoch": 5.12, "learning_rate": 2.443132408805895e-05, "loss": 1.4349, "step": 112230 }, { "epoch": 5.13, "learning_rate": 2.442903565380567e-05, "loss": 1.5098, "step": 112240 }, { "epoch": 5.13, "learning_rate": 2.4426747219552383e-05, "loss": 1.5546, "step": 112250 }, { "epoch": 5.13, "learning_rate": 2.44244587852991e-05, "loss": 1.5505, "step": 112260 }, { "epoch": 5.13, "learning_rate": 2.4422170351045815e-05, "loss": 1.5985, "step": 112270 }, { "epoch": 5.13, "learning_rate": 2.4419881916792532e-05, "loss": 1.5133, "step": 112280 }, { "epoch": 5.13, "learning_rate": 2.4417593482539246e-05, "loss": 1.3746, "step": 112290 }, { "epoch": 5.13, "learning_rate": 2.4415305048285964e-05, "loss": 1.4264, "step": 112300 }, { "epoch": 5.13, "learning_rate": 2.441301661403268e-05, "loss": 1.5522, "step": 112310 }, { "epoch": 5.13, "learning_rate": 2.4410728179779395e-05, "loss": 1.4059, "step": 112320 }, { "epoch": 5.13, "learning_rate": 2.4408439745526113e-05, "loss": 1.5292, "step": 112330 }, { "epoch": 5.13, "learning_rate": 2.440615131127283e-05, "loss": 1.4022, "step": 112340 }, { "epoch": 5.13, "learning_rate": 2.4403862877019545e-05, "loss": 1.357, "step": 112350 }, { "epoch": 5.13, "learning_rate": 2.4401574442766262e-05, "loss": 1.5431, "step": 112360 }, { "epoch": 5.13, "learning_rate": 2.4399286008512976e-05, "loss": 1.3785, "step": 112370 }, { "epoch": 5.13, "learning_rate": 2.439699757425969e-05, "loss": 1.287, "step": 112380 }, { "epoch": 5.13, "learning_rate": 2.4394709140006408e-05, "loss": 1.4565, "step": 112390 }, { "epoch": 5.13, "learning_rate": 2.4392420705753125e-05, "loss": 1.5969, "step": 112400 }, { "epoch": 5.13, "learning_rate": 2.439013227149984e-05, "loss": 1.6799, "step": 112410 }, { "epoch": 5.13, "learning_rate": 2.4387843837246557e-05, "loss": 1.6118, "step": 112420 }, { "epoch": 5.13, "learning_rate": 2.4385555402993275e-05, "loss": 1.6189, "step": 112430 }, { "epoch": 5.13, "learning_rate": 2.438326696873999e-05, "loss": 1.4743, "step": 112440 }, { "epoch": 5.13, "learning_rate": 2.4380978534486706e-05, "loss": 1.4406, "step": 112450 }, { "epoch": 5.14, "learning_rate": 2.4378690100233424e-05, "loss": 1.4905, "step": 112460 }, { "epoch": 5.14, "learning_rate": 2.4376401665980138e-05, "loss": 1.301, "step": 112470 }, { "epoch": 5.14, "learning_rate": 2.4374113231726852e-05, "loss": 1.4605, "step": 112480 }, { "epoch": 5.14, "learning_rate": 2.437182479747357e-05, "loss": 1.4439, "step": 112490 }, { "epoch": 5.14, "learning_rate": 2.4369536363220287e-05, "loss": 1.4674, "step": 112500 }, { "epoch": 5.14, "learning_rate": 2.4367247928967e-05, "loss": 1.3556, "step": 112510 }, { "epoch": 5.14, "learning_rate": 2.436495949471372e-05, "loss": 1.3447, "step": 112520 }, { "epoch": 5.14, "learning_rate": 2.4362671060460436e-05, "loss": 1.5295, "step": 112530 }, { "epoch": 5.14, "learning_rate": 2.436038262620715e-05, "loss": 1.3981, "step": 112540 }, { "epoch": 5.14, "learning_rate": 2.4358094191953868e-05, "loss": 1.3915, "step": 112550 }, { "epoch": 5.14, "learning_rate": 2.4355805757700585e-05, "loss": 1.4319, "step": 112560 }, { "epoch": 5.14, "learning_rate": 2.4353517323447296e-05, "loss": 1.6295, "step": 112570 }, { "epoch": 5.14, "learning_rate": 2.4351228889194014e-05, "loss": 1.5296, "step": 112580 }, { "epoch": 5.14, "learning_rate": 2.434894045494073e-05, "loss": 1.561, "step": 112590 }, { "epoch": 5.14, "learning_rate": 2.4346652020687445e-05, "loss": 1.5482, "step": 112600 }, { "epoch": 5.14, "learning_rate": 2.4344363586434163e-05, "loss": 1.4028, "step": 112610 }, { "epoch": 5.14, "learning_rate": 2.434207515218088e-05, "loss": 1.4398, "step": 112620 }, { "epoch": 5.14, "learning_rate": 2.4339786717927595e-05, "loss": 1.5012, "step": 112630 }, { "epoch": 5.14, "learning_rate": 2.4337498283674312e-05, "loss": 1.5229, "step": 112640 }, { "epoch": 5.14, "learning_rate": 2.433520984942103e-05, "loss": 1.4941, "step": 112650 }, { "epoch": 5.14, "learning_rate": 2.4332921415167744e-05, "loss": 1.5261, "step": 112660 }, { "epoch": 5.14, "learning_rate": 2.4330632980914458e-05, "loss": 1.5108, "step": 112670 }, { "epoch": 5.15, "learning_rate": 2.4328344546661175e-05, "loss": 1.5056, "step": 112680 }, { "epoch": 5.15, "learning_rate": 2.432605611240789e-05, "loss": 1.6062, "step": 112690 }, { "epoch": 5.15, "learning_rate": 2.4323767678154607e-05, "loss": 1.5238, "step": 112700 }, { "epoch": 5.15, "learning_rate": 2.4321479243901325e-05, "loss": 1.536, "step": 112710 }, { "epoch": 5.15, "learning_rate": 2.431919080964804e-05, "loss": 1.4062, "step": 112720 }, { "epoch": 5.15, "learning_rate": 2.4316902375394756e-05, "loss": 1.5783, "step": 112730 }, { "epoch": 5.15, "learning_rate": 2.4314613941141474e-05, "loss": 1.4541, "step": 112740 }, { "epoch": 5.15, "learning_rate": 2.4312325506888188e-05, "loss": 1.3945, "step": 112750 }, { "epoch": 5.15, "learning_rate": 2.4310037072634902e-05, "loss": 1.5346, "step": 112760 }, { "epoch": 5.15, "learning_rate": 2.430774863838162e-05, "loss": 1.3921, "step": 112770 }, { "epoch": 5.15, "learning_rate": 2.4305460204128337e-05, "loss": 1.4678, "step": 112780 }, { "epoch": 5.15, "learning_rate": 2.430317176987505e-05, "loss": 1.4612, "step": 112790 }, { "epoch": 5.15, "learning_rate": 2.430088333562177e-05, "loss": 1.2546, "step": 112800 }, { "epoch": 5.15, "learning_rate": 2.4298594901368486e-05, "loss": 1.6438, "step": 112810 }, { "epoch": 5.15, "learning_rate": 2.42963064671152e-05, "loss": 1.5352, "step": 112820 }, { "epoch": 5.15, "learning_rate": 2.4294018032861918e-05, "loss": 1.4716, "step": 112830 }, { "epoch": 5.15, "learning_rate": 2.4291729598608635e-05, "loss": 1.5882, "step": 112840 }, { "epoch": 5.15, "learning_rate": 2.428944116435535e-05, "loss": 1.4944, "step": 112850 }, { "epoch": 5.15, "learning_rate": 2.4287152730102064e-05, "loss": 1.4671, "step": 112860 }, { "epoch": 5.15, "learning_rate": 2.428486429584878e-05, "loss": 1.5324, "step": 112870 }, { "epoch": 5.15, "learning_rate": 2.4282575861595495e-05, "loss": 1.4651, "step": 112880 }, { "epoch": 5.15, "learning_rate": 2.4280287427342213e-05, "loss": 1.5818, "step": 112890 }, { "epoch": 5.16, "learning_rate": 2.427799899308893e-05, "loss": 1.5272, "step": 112900 }, { "epoch": 5.16, "learning_rate": 2.4275710558835644e-05, "loss": 1.6291, "step": 112910 }, { "epoch": 5.16, "learning_rate": 2.4273422124582362e-05, "loss": 1.2759, "step": 112920 }, { "epoch": 5.16, "learning_rate": 2.427113369032908e-05, "loss": 1.4521, "step": 112930 }, { "epoch": 5.16, "learning_rate": 2.4268845256075794e-05, "loss": 1.5546, "step": 112940 }, { "epoch": 5.16, "learning_rate": 2.426655682182251e-05, "loss": 1.577, "step": 112950 }, { "epoch": 5.16, "learning_rate": 2.4264268387569225e-05, "loss": 1.6498, "step": 112960 }, { "epoch": 5.16, "learning_rate": 2.4261979953315943e-05, "loss": 1.4715, "step": 112970 }, { "epoch": 5.16, "learning_rate": 2.4259691519062657e-05, "loss": 1.4624, "step": 112980 }, { "epoch": 5.16, "learning_rate": 2.4257403084809375e-05, "loss": 1.5625, "step": 112990 }, { "epoch": 5.16, "learning_rate": 2.4255114650556092e-05, "loss": 1.4973, "step": 113000 }, { "epoch": 5.16, "learning_rate": 2.4252826216302806e-05, "loss": 1.4293, "step": 113010 }, { "epoch": 5.16, "learning_rate": 2.4250537782049524e-05, "loss": 1.6567, "step": 113020 }, { "epoch": 5.16, "learning_rate": 2.424824934779624e-05, "loss": 1.4892, "step": 113030 }, { "epoch": 5.16, "learning_rate": 2.4245960913542955e-05, "loss": 1.459, "step": 113040 }, { "epoch": 5.16, "learning_rate": 2.4243672479289673e-05, "loss": 1.4412, "step": 113050 }, { "epoch": 5.16, "learning_rate": 2.4241384045036387e-05, "loss": 1.5349, "step": 113060 }, { "epoch": 5.16, "learning_rate": 2.42390956107831e-05, "loss": 1.4682, "step": 113070 }, { "epoch": 5.16, "learning_rate": 2.423680717652982e-05, "loss": 1.4332, "step": 113080 }, { "epoch": 5.16, "learning_rate": 2.4234518742276536e-05, "loss": 1.5854, "step": 113090 }, { "epoch": 5.16, "learning_rate": 2.423223030802325e-05, "loss": 1.3923, "step": 113100 }, { "epoch": 5.16, "learning_rate": 2.4229941873769968e-05, "loss": 1.42, "step": 113110 }, { "epoch": 5.17, "learning_rate": 2.4227653439516685e-05, "loss": 1.4258, "step": 113120 }, { "epoch": 5.17, "learning_rate": 2.42253650052634e-05, "loss": 1.5959, "step": 113130 }, { "epoch": 5.17, "learning_rate": 2.4223076571010117e-05, "loss": 1.5156, "step": 113140 }, { "epoch": 5.17, "learning_rate": 2.4220788136756835e-05, "loss": 1.4219, "step": 113150 }, { "epoch": 5.17, "learning_rate": 2.421849970250355e-05, "loss": 1.6208, "step": 113160 }, { "epoch": 5.17, "learning_rate": 2.4216211268250263e-05, "loss": 1.6248, "step": 113170 }, { "epoch": 5.17, "learning_rate": 2.421392283399698e-05, "loss": 1.4018, "step": 113180 }, { "epoch": 5.17, "learning_rate": 2.4211634399743698e-05, "loss": 1.4813, "step": 113190 }, { "epoch": 5.17, "learning_rate": 2.4209345965490412e-05, "loss": 1.5845, "step": 113200 }, { "epoch": 5.17, "learning_rate": 2.420705753123713e-05, "loss": 1.4017, "step": 113210 }, { "epoch": 5.17, "learning_rate": 2.4204769096983847e-05, "loss": 1.6457, "step": 113220 }, { "epoch": 5.17, "learning_rate": 2.420248066273056e-05, "loss": 1.4729, "step": 113230 }, { "epoch": 5.17, "learning_rate": 2.420019222847728e-05, "loss": 1.4606, "step": 113240 }, { "epoch": 5.17, "learning_rate": 2.4197903794223993e-05, "loss": 1.4717, "step": 113250 }, { "epoch": 5.17, "learning_rate": 2.4195615359970707e-05, "loss": 1.6127, "step": 113260 }, { "epoch": 5.17, "learning_rate": 2.4193326925717424e-05, "loss": 1.3712, "step": 113270 }, { "epoch": 5.17, "learning_rate": 2.4191038491464142e-05, "loss": 1.3056, "step": 113280 }, { "epoch": 5.17, "learning_rate": 2.4188750057210856e-05, "loss": 1.3157, "step": 113290 }, { "epoch": 5.17, "learning_rate": 2.4186461622957574e-05, "loss": 1.4758, "step": 113300 }, { "epoch": 5.17, "learning_rate": 2.418417318870429e-05, "loss": 1.6747, "step": 113310 }, { "epoch": 5.17, "learning_rate": 2.4181884754451005e-05, "loss": 1.3872, "step": 113320 }, { "epoch": 5.17, "learning_rate": 2.4179596320197723e-05, "loss": 1.4339, "step": 113330 }, { "epoch": 5.18, "learning_rate": 2.417730788594444e-05, "loss": 1.6416, "step": 113340 }, { "epoch": 5.18, "learning_rate": 2.4175019451691154e-05, "loss": 1.3926, "step": 113350 }, { "epoch": 5.18, "learning_rate": 2.417273101743787e-05, "loss": 1.5363, "step": 113360 }, { "epoch": 5.18, "learning_rate": 2.4170442583184586e-05, "loss": 1.4965, "step": 113370 }, { "epoch": 5.18, "learning_rate": 2.41681541489313e-05, "loss": 1.6151, "step": 113380 }, { "epoch": 5.18, "learning_rate": 2.4165865714678018e-05, "loss": 1.5411, "step": 113390 }, { "epoch": 5.18, "learning_rate": 2.4163577280424735e-05, "loss": 1.5931, "step": 113400 }, { "epoch": 5.18, "learning_rate": 2.416128884617145e-05, "loss": 1.4198, "step": 113410 }, { "epoch": 5.18, "learning_rate": 2.4159000411918167e-05, "loss": 1.3962, "step": 113420 }, { "epoch": 5.18, "learning_rate": 2.4156711977664884e-05, "loss": 1.6093, "step": 113430 }, { "epoch": 5.18, "learning_rate": 2.41544235434116e-05, "loss": 1.3245, "step": 113440 }, { "epoch": 5.18, "learning_rate": 2.4152135109158313e-05, "loss": 1.5249, "step": 113450 }, { "epoch": 5.18, "learning_rate": 2.414984667490503e-05, "loss": 1.3404, "step": 113460 }, { "epoch": 5.18, "learning_rate": 2.4147558240651748e-05, "loss": 1.7122, "step": 113470 }, { "epoch": 5.18, "learning_rate": 2.4145269806398462e-05, "loss": 1.3511, "step": 113480 }, { "epoch": 5.18, "learning_rate": 2.414298137214518e-05, "loss": 1.4875, "step": 113490 }, { "epoch": 5.18, "learning_rate": 2.4140692937891897e-05, "loss": 1.4157, "step": 113500 }, { "epoch": 5.18, "learning_rate": 2.413840450363861e-05, "loss": 1.541, "step": 113510 }, { "epoch": 5.18, "learning_rate": 2.413611606938533e-05, "loss": 1.4767, "step": 113520 }, { "epoch": 5.18, "learning_rate": 2.4133827635132046e-05, "loss": 1.4331, "step": 113530 }, { "epoch": 5.18, "learning_rate": 2.413153920087876e-05, "loss": 1.3994, "step": 113540 }, { "epoch": 5.18, "learning_rate": 2.4129250766625474e-05, "loss": 1.551, "step": 113550 }, { "epoch": 5.19, "learning_rate": 2.4126962332372192e-05, "loss": 1.4933, "step": 113560 }, { "epoch": 5.19, "learning_rate": 2.4124673898118906e-05, "loss": 1.5885, "step": 113570 }, { "epoch": 5.19, "learning_rate": 2.4122385463865624e-05, "loss": 1.3848, "step": 113580 }, { "epoch": 5.19, "learning_rate": 2.412009702961234e-05, "loss": 1.4404, "step": 113590 }, { "epoch": 5.19, "learning_rate": 2.4117808595359055e-05, "loss": 1.4348, "step": 113600 }, { "epoch": 5.19, "learning_rate": 2.4115520161105773e-05, "loss": 1.5058, "step": 113610 }, { "epoch": 5.19, "learning_rate": 2.411323172685249e-05, "loss": 1.3578, "step": 113620 }, { "epoch": 5.19, "learning_rate": 2.4110943292599204e-05, "loss": 1.4857, "step": 113630 }, { "epoch": 5.19, "learning_rate": 2.4108654858345922e-05, "loss": 1.4818, "step": 113640 }, { "epoch": 5.19, "learning_rate": 2.4106366424092636e-05, "loss": 1.5286, "step": 113650 }, { "epoch": 5.19, "learning_rate": 2.4104077989839354e-05, "loss": 1.3169, "step": 113660 }, { "epoch": 5.19, "learning_rate": 2.4101789555586068e-05, "loss": 1.2657, "step": 113670 }, { "epoch": 5.19, "learning_rate": 2.4099501121332785e-05, "loss": 1.3986, "step": 113680 }, { "epoch": 5.19, "learning_rate": 2.4097212687079503e-05, "loss": 1.3896, "step": 113690 }, { "epoch": 5.19, "learning_rate": 2.4094924252826217e-05, "loss": 1.3918, "step": 113700 }, { "epoch": 5.19, "learning_rate": 2.4092635818572934e-05, "loss": 1.7191, "step": 113710 }, { "epoch": 5.19, "learning_rate": 2.4090347384319652e-05, "loss": 1.4338, "step": 113720 }, { "epoch": 5.19, "learning_rate": 2.4088058950066366e-05, "loss": 1.4711, "step": 113730 }, { "epoch": 5.19, "learning_rate": 2.4085770515813084e-05, "loss": 1.4147, "step": 113740 }, { "epoch": 5.19, "learning_rate": 2.4083482081559798e-05, "loss": 1.4921, "step": 113750 }, { "epoch": 5.19, "learning_rate": 2.4081193647306512e-05, "loss": 1.4349, "step": 113760 }, { "epoch": 5.2, "learning_rate": 2.407890521305323e-05, "loss": 1.6005, "step": 113770 }, { "epoch": 5.2, "learning_rate": 2.4076616778799947e-05, "loss": 1.414, "step": 113780 }, { "epoch": 5.2, "learning_rate": 2.407432834454666e-05, "loss": 1.5356, "step": 113790 }, { "epoch": 5.2, "learning_rate": 2.407203991029338e-05, "loss": 1.3416, "step": 113800 }, { "epoch": 5.2, "learning_rate": 2.4069751476040096e-05, "loss": 1.4898, "step": 113810 }, { "epoch": 5.2, "learning_rate": 2.406746304178681e-05, "loss": 1.4606, "step": 113820 }, { "epoch": 5.2, "learning_rate": 2.4065174607533528e-05, "loss": 1.4471, "step": 113830 }, { "epoch": 5.2, "learning_rate": 2.4062886173280245e-05, "loss": 1.4487, "step": 113840 }, { "epoch": 5.2, "learning_rate": 2.4060597739026956e-05, "loss": 1.4968, "step": 113850 }, { "epoch": 5.2, "learning_rate": 2.4058309304773674e-05, "loss": 1.4572, "step": 113860 }, { "epoch": 5.2, "learning_rate": 2.405602087052039e-05, "loss": 1.3302, "step": 113870 }, { "epoch": 5.2, "learning_rate": 2.4053732436267105e-05, "loss": 1.5574, "step": 113880 }, { "epoch": 5.2, "learning_rate": 2.4051444002013823e-05, "loss": 1.5721, "step": 113890 }, { "epoch": 5.2, "learning_rate": 2.404915556776054e-05, "loss": 1.4564, "step": 113900 }, { "epoch": 5.2, "learning_rate": 2.4046867133507254e-05, "loss": 1.4352, "step": 113910 }, { "epoch": 5.2, "learning_rate": 2.4044578699253972e-05, "loss": 1.543, "step": 113920 }, { "epoch": 5.2, "learning_rate": 2.404229026500069e-05, "loss": 1.6953, "step": 113930 }, { "epoch": 5.2, "learning_rate": 2.4040001830747404e-05, "loss": 1.4933, "step": 113940 }, { "epoch": 5.2, "learning_rate": 2.4037713396494118e-05, "loss": 1.4309, "step": 113950 }, { "epoch": 5.2, "learning_rate": 2.4035424962240835e-05, "loss": 1.4761, "step": 113960 }, { "epoch": 5.2, "learning_rate": 2.4033136527987553e-05, "loss": 1.4451, "step": 113970 }, { "epoch": 5.2, "learning_rate": 2.4030848093734267e-05, "loss": 1.541, "step": 113980 }, { "epoch": 5.21, "learning_rate": 2.4028559659480984e-05, "loss": 1.5242, "step": 113990 }, { "epoch": 5.21, "learning_rate": 2.4026271225227702e-05, "loss": 1.5608, "step": 114000 }, { "epoch": 5.21, "learning_rate": 2.4023982790974416e-05, "loss": 1.4818, "step": 114010 }, { "epoch": 5.21, "learning_rate": 2.4021694356721134e-05, "loss": 1.5824, "step": 114020 }, { "epoch": 5.21, "learning_rate": 2.401940592246785e-05, "loss": 1.4734, "step": 114030 }, { "epoch": 5.21, "learning_rate": 2.4017117488214565e-05, "loss": 1.4928, "step": 114040 }, { "epoch": 5.21, "learning_rate": 2.401482905396128e-05, "loss": 1.4668, "step": 114050 }, { "epoch": 5.21, "learning_rate": 2.4012540619707997e-05, "loss": 1.485, "step": 114060 }, { "epoch": 5.21, "learning_rate": 2.401025218545471e-05, "loss": 1.5943, "step": 114070 }, { "epoch": 5.21, "learning_rate": 2.400796375120143e-05, "loss": 1.7541, "step": 114080 }, { "epoch": 5.21, "learning_rate": 2.4005675316948146e-05, "loss": 1.4223, "step": 114090 }, { "epoch": 5.21, "learning_rate": 2.400338688269486e-05, "loss": 1.39, "step": 114100 }, { "epoch": 5.21, "learning_rate": 2.4001098448441578e-05, "loss": 1.4754, "step": 114110 }, { "epoch": 5.21, "learning_rate": 2.3998810014188295e-05, "loss": 1.664, "step": 114120 }, { "epoch": 5.21, "learning_rate": 2.399652157993501e-05, "loss": 1.4494, "step": 114130 }, { "epoch": 5.21, "learning_rate": 2.3994233145681727e-05, "loss": 1.495, "step": 114140 }, { "epoch": 5.21, "learning_rate": 2.399194471142844e-05, "loss": 1.3994, "step": 114150 }, { "epoch": 5.21, "learning_rate": 2.398965627717516e-05, "loss": 1.5564, "step": 114160 }, { "epoch": 5.21, "learning_rate": 2.3987367842921873e-05, "loss": 1.4614, "step": 114170 }, { "epoch": 5.21, "learning_rate": 2.398507940866859e-05, "loss": 1.3576, "step": 114180 }, { "epoch": 5.21, "learning_rate": 2.3982790974415308e-05, "loss": 1.426, "step": 114190 }, { "epoch": 5.21, "learning_rate": 2.3980502540162022e-05, "loss": 1.5645, "step": 114200 }, { "epoch": 5.22, "learning_rate": 2.397821410590874e-05, "loss": 1.4657, "step": 114210 }, { "epoch": 5.22, "learning_rate": 2.3975925671655457e-05, "loss": 1.6876, "step": 114220 }, { "epoch": 5.22, "learning_rate": 2.397363723740217e-05, "loss": 1.4308, "step": 114230 }, { "epoch": 5.22, "learning_rate": 2.3971348803148885e-05, "loss": 1.4607, "step": 114240 }, { "epoch": 5.22, "learning_rate": 2.3969060368895603e-05, "loss": 1.439, "step": 114250 }, { "epoch": 5.22, "learning_rate": 2.3966771934642317e-05, "loss": 1.267, "step": 114260 }, { "epoch": 5.22, "learning_rate": 2.3964483500389034e-05, "loss": 1.44, "step": 114270 }, { "epoch": 5.22, "learning_rate": 2.3962195066135752e-05, "loss": 1.4553, "step": 114280 }, { "epoch": 5.22, "learning_rate": 2.3959906631882466e-05, "loss": 1.5367, "step": 114290 }, { "epoch": 5.22, "learning_rate": 2.3957618197629183e-05, "loss": 1.6255, "step": 114300 }, { "epoch": 5.22, "learning_rate": 2.39553297633759e-05, "loss": 1.4626, "step": 114310 }, { "epoch": 5.22, "learning_rate": 2.3953041329122615e-05, "loss": 1.621, "step": 114320 }, { "epoch": 5.22, "learning_rate": 2.3950752894869333e-05, "loss": 1.4556, "step": 114330 }, { "epoch": 5.22, "learning_rate": 2.3948464460616047e-05, "loss": 1.4234, "step": 114340 }, { "epoch": 5.22, "learning_rate": 2.3946176026362764e-05, "loss": 1.4531, "step": 114350 }, { "epoch": 5.22, "learning_rate": 2.394388759210948e-05, "loss": 1.3869, "step": 114360 }, { "epoch": 5.22, "learning_rate": 2.3941599157856196e-05, "loss": 1.5371, "step": 114370 }, { "epoch": 5.22, "learning_rate": 2.3939310723602914e-05, "loss": 1.3443, "step": 114380 }, { "epoch": 5.22, "learning_rate": 2.3937022289349628e-05, "loss": 1.4613, "step": 114390 }, { "epoch": 5.22, "learning_rate": 2.3934733855096345e-05, "loss": 1.349, "step": 114400 }, { "epoch": 5.22, "learning_rate": 2.393244542084306e-05, "loss": 1.4115, "step": 114410 }, { "epoch": 5.22, "learning_rate": 2.3930156986589777e-05, "loss": 1.4558, "step": 114420 }, { "epoch": 5.23, "learning_rate": 2.3927868552336494e-05, "loss": 1.5999, "step": 114430 }, { "epoch": 5.23, "learning_rate": 2.392558011808321e-05, "loss": 1.5642, "step": 114440 }, { "epoch": 5.23, "learning_rate": 2.3923291683829923e-05, "loss": 1.5654, "step": 114450 }, { "epoch": 5.23, "learning_rate": 2.392100324957664e-05, "loss": 1.3449, "step": 114460 }, { "epoch": 5.23, "learning_rate": 2.3918714815323358e-05, "loss": 1.6179, "step": 114470 }, { "epoch": 5.23, "learning_rate": 2.3916426381070072e-05, "loss": 1.4555, "step": 114480 }, { "epoch": 5.23, "learning_rate": 2.391413794681679e-05, "loss": 1.4312, "step": 114490 }, { "epoch": 5.23, "learning_rate": 2.3911849512563507e-05, "loss": 1.4687, "step": 114500 }, { "epoch": 5.23, "learning_rate": 2.390956107831022e-05, "loss": 1.5192, "step": 114510 }, { "epoch": 5.23, "learning_rate": 2.390727264405694e-05, "loss": 1.5091, "step": 114520 }, { "epoch": 5.23, "learning_rate": 2.3904984209803656e-05, "loss": 1.5081, "step": 114530 }, { "epoch": 5.23, "learning_rate": 2.3902695775550367e-05, "loss": 1.6326, "step": 114540 }, { "epoch": 5.23, "learning_rate": 2.3900407341297084e-05, "loss": 1.5701, "step": 114550 }, { "epoch": 5.23, "learning_rate": 2.3898118907043802e-05, "loss": 1.3887, "step": 114560 }, { "epoch": 5.23, "learning_rate": 2.3895830472790516e-05, "loss": 1.6143, "step": 114570 }, { "epoch": 5.23, "learning_rate": 2.3893542038537233e-05, "loss": 1.4302, "step": 114580 }, { "epoch": 5.23, "learning_rate": 2.389125360428395e-05, "loss": 1.4173, "step": 114590 }, { "epoch": 5.23, "learning_rate": 2.3888965170030665e-05, "loss": 1.3617, "step": 114600 }, { "epoch": 5.23, "learning_rate": 2.3886676735777383e-05, "loss": 1.6552, "step": 114610 }, { "epoch": 5.23, "learning_rate": 2.38843883015241e-05, "loss": 1.6405, "step": 114620 }, { "epoch": 5.23, "learning_rate": 2.3882099867270814e-05, "loss": 1.6471, "step": 114630 }, { "epoch": 5.23, "learning_rate": 2.387981143301753e-05, "loss": 1.378, "step": 114640 }, { "epoch": 5.24, "learning_rate": 2.3877522998764246e-05, "loss": 1.4342, "step": 114650 }, { "epoch": 5.24, "learning_rate": 2.3875234564510963e-05, "loss": 1.3867, "step": 114660 }, { "epoch": 5.24, "learning_rate": 2.3872946130257678e-05, "loss": 1.4574, "step": 114670 }, { "epoch": 5.24, "learning_rate": 2.3870657696004395e-05, "loss": 1.4398, "step": 114680 }, { "epoch": 5.24, "learning_rate": 2.3868369261751113e-05, "loss": 1.5476, "step": 114690 }, { "epoch": 5.24, "learning_rate": 2.3866080827497827e-05, "loss": 1.6085, "step": 114700 }, { "epoch": 5.24, "learning_rate": 2.3863792393244544e-05, "loss": 1.4467, "step": 114710 }, { "epoch": 5.24, "learning_rate": 2.3861503958991262e-05, "loss": 1.6241, "step": 114720 }, { "epoch": 5.24, "learning_rate": 2.3859215524737976e-05, "loss": 1.4709, "step": 114730 }, { "epoch": 5.24, "learning_rate": 2.385692709048469e-05, "loss": 1.4678, "step": 114740 }, { "epoch": 5.24, "learning_rate": 2.3854638656231408e-05, "loss": 1.3794, "step": 114750 }, { "epoch": 5.24, "learning_rate": 2.3852350221978122e-05, "loss": 1.458, "step": 114760 }, { "epoch": 5.24, "learning_rate": 2.385006178772484e-05, "loss": 1.6026, "step": 114770 }, { "epoch": 5.24, "learning_rate": 2.3847773353471557e-05, "loss": 1.5204, "step": 114780 }, { "epoch": 5.24, "learning_rate": 2.384548491921827e-05, "loss": 1.6067, "step": 114790 }, { "epoch": 5.24, "learning_rate": 2.384319648496499e-05, "loss": 1.4724, "step": 114800 }, { "epoch": 5.24, "learning_rate": 2.3840908050711706e-05, "loss": 1.4924, "step": 114810 }, { "epoch": 5.24, "learning_rate": 2.383861961645842e-05, "loss": 1.3857, "step": 114820 }, { "epoch": 5.24, "learning_rate": 2.3836331182205138e-05, "loss": 1.4922, "step": 114830 }, { "epoch": 5.24, "learning_rate": 2.3834042747951852e-05, "loss": 1.6998, "step": 114840 }, { "epoch": 5.24, "learning_rate": 2.383175431369857e-05, "loss": 1.4881, "step": 114850 }, { "epoch": 5.24, "learning_rate": 2.3829465879445283e-05, "loss": 1.4882, "step": 114860 }, { "epoch": 5.25, "learning_rate": 2.3827177445192e-05, "loss": 1.5357, "step": 114870 }, { "epoch": 5.25, "learning_rate": 2.382488901093872e-05, "loss": 1.3531, "step": 114880 }, { "epoch": 5.25, "learning_rate": 2.3822600576685433e-05, "loss": 1.5573, "step": 114890 }, { "epoch": 5.25, "learning_rate": 2.382031214243215e-05, "loss": 1.4426, "step": 114900 }, { "epoch": 5.25, "learning_rate": 2.3818023708178868e-05, "loss": 1.6012, "step": 114910 }, { "epoch": 5.25, "learning_rate": 2.3815735273925582e-05, "loss": 1.3458, "step": 114920 }, { "epoch": 5.25, "learning_rate": 2.38134468396723e-05, "loss": 1.5481, "step": 114930 }, { "epoch": 5.25, "learning_rate": 2.3811158405419013e-05, "loss": 1.3243, "step": 114940 }, { "epoch": 5.25, "learning_rate": 2.3808869971165728e-05, "loss": 1.4512, "step": 114950 }, { "epoch": 5.25, "learning_rate": 2.3806581536912445e-05, "loss": 1.3812, "step": 114960 }, { "epoch": 5.25, "learning_rate": 2.3804293102659163e-05, "loss": 1.5369, "step": 114970 }, { "epoch": 5.25, "learning_rate": 2.3802004668405877e-05, "loss": 1.4085, "step": 114980 }, { "epoch": 5.25, "learning_rate": 2.3799716234152594e-05, "loss": 1.477, "step": 114990 }, { "epoch": 5.25, "learning_rate": 2.3797427799899312e-05, "loss": 1.384, "step": 115000 }, { "epoch": 5.25, "learning_rate": 2.3795139365646026e-05, "loss": 1.2997, "step": 115010 }, { "epoch": 5.25, "learning_rate": 2.3792850931392743e-05, "loss": 1.3936, "step": 115020 }, { "epoch": 5.25, "learning_rate": 2.3790562497139458e-05, "loss": 1.5642, "step": 115030 }, { "epoch": 5.25, "learning_rate": 2.378827406288617e-05, "loss": 1.3864, "step": 115040 }, { "epoch": 5.25, "learning_rate": 2.378598562863289e-05, "loss": 1.5972, "step": 115050 }, { "epoch": 5.25, "learning_rate": 2.3783697194379607e-05, "loss": 1.4763, "step": 115060 }, { "epoch": 5.25, "learning_rate": 2.378140876012632e-05, "loss": 1.5699, "step": 115070 }, { "epoch": 5.25, "learning_rate": 2.377912032587304e-05, "loss": 1.4201, "step": 115080 }, { "epoch": 5.26, "learning_rate": 2.3776831891619756e-05, "loss": 1.6351, "step": 115090 }, { "epoch": 5.26, "learning_rate": 2.377454345736647e-05, "loss": 1.4652, "step": 115100 }, { "epoch": 5.26, "learning_rate": 2.3772255023113188e-05, "loss": 1.4283, "step": 115110 }, { "epoch": 5.26, "learning_rate": 2.3769966588859905e-05, "loss": 1.3828, "step": 115120 }, { "epoch": 5.26, "learning_rate": 2.376767815460662e-05, "loss": 1.4516, "step": 115130 }, { "epoch": 5.26, "learning_rate": 2.3765389720353333e-05, "loss": 1.4466, "step": 115140 }, { "epoch": 5.26, "learning_rate": 2.376310128610005e-05, "loss": 1.4826, "step": 115150 }, { "epoch": 5.26, "learning_rate": 2.376081285184677e-05, "loss": 1.4135, "step": 115160 }, { "epoch": 5.26, "learning_rate": 2.3758524417593483e-05, "loss": 1.4072, "step": 115170 }, { "epoch": 5.26, "learning_rate": 2.37562359833402e-05, "loss": 1.4993, "step": 115180 }, { "epoch": 5.26, "learning_rate": 2.3753947549086918e-05, "loss": 1.425, "step": 115190 }, { "epoch": 5.26, "learning_rate": 2.3751659114833632e-05, "loss": 1.6145, "step": 115200 }, { "epoch": 5.26, "learning_rate": 2.374937068058035e-05, "loss": 1.5489, "step": 115210 }, { "epoch": 5.26, "learning_rate": 2.3747082246327067e-05, "loss": 1.3695, "step": 115220 }, { "epoch": 5.26, "learning_rate": 2.3744793812073777e-05, "loss": 1.475, "step": 115230 }, { "epoch": 5.26, "learning_rate": 2.3742505377820495e-05, "loss": 1.6734, "step": 115240 }, { "epoch": 5.26, "learning_rate": 2.3740216943567213e-05, "loss": 1.2277, "step": 115250 }, { "epoch": 5.26, "learning_rate": 2.3737928509313927e-05, "loss": 1.4191, "step": 115260 }, { "epoch": 5.26, "learning_rate": 2.3735640075060644e-05, "loss": 1.5745, "step": 115270 }, { "epoch": 5.26, "learning_rate": 2.3733351640807362e-05, "loss": 1.4892, "step": 115280 }, { "epoch": 5.26, "learning_rate": 2.3731063206554076e-05, "loss": 1.6685, "step": 115290 }, { "epoch": 5.26, "learning_rate": 2.3728774772300793e-05, "loss": 1.648, "step": 115300 }, { "epoch": 5.27, "learning_rate": 2.372648633804751e-05, "loss": 1.4895, "step": 115310 }, { "epoch": 5.27, "learning_rate": 2.3724197903794225e-05, "loss": 1.4974, "step": 115320 }, { "epoch": 5.27, "learning_rate": 2.372190946954094e-05, "loss": 1.4798, "step": 115330 }, { "epoch": 5.27, "learning_rate": 2.3719621035287657e-05, "loss": 1.5152, "step": 115340 }, { "epoch": 5.27, "learning_rate": 2.3717332601034374e-05, "loss": 1.4075, "step": 115350 }, { "epoch": 5.27, "learning_rate": 2.371504416678109e-05, "loss": 1.547, "step": 115360 }, { "epoch": 5.27, "learning_rate": 2.3712755732527806e-05, "loss": 1.3688, "step": 115370 }, { "epoch": 5.27, "learning_rate": 2.3710467298274523e-05, "loss": 1.3503, "step": 115380 }, { "epoch": 5.27, "learning_rate": 2.3708178864021238e-05, "loss": 1.3982, "step": 115390 }, { "epoch": 5.27, "learning_rate": 2.3705890429767955e-05, "loss": 1.4296, "step": 115400 }, { "epoch": 5.27, "learning_rate": 2.3703601995514673e-05, "loss": 1.5628, "step": 115410 }, { "epoch": 5.27, "learning_rate": 2.3701313561261387e-05, "loss": 1.3711, "step": 115420 }, { "epoch": 5.27, "learning_rate": 2.36990251270081e-05, "loss": 1.3552, "step": 115430 }, { "epoch": 5.27, "learning_rate": 2.369673669275482e-05, "loss": 1.4706, "step": 115440 }, { "epoch": 5.27, "learning_rate": 2.3694448258501532e-05, "loss": 1.3577, "step": 115450 }, { "epoch": 5.27, "learning_rate": 2.369215982424825e-05, "loss": 1.4963, "step": 115460 }, { "epoch": 5.27, "learning_rate": 2.3689871389994968e-05, "loss": 1.4715, "step": 115470 }, { "epoch": 5.27, "learning_rate": 2.368758295574168e-05, "loss": 1.559, "step": 115480 }, { "epoch": 5.27, "learning_rate": 2.36852945214884e-05, "loss": 1.4477, "step": 115490 }, { "epoch": 5.27, "learning_rate": 2.3683006087235117e-05, "loss": 1.5526, "step": 115500 }, { "epoch": 5.27, "learning_rate": 2.368071765298183e-05, "loss": 1.4962, "step": 115510 }, { "epoch": 5.27, "learning_rate": 2.367842921872855e-05, "loss": 1.4765, "step": 115520 }, { "epoch": 5.28, "learning_rate": 2.3676140784475262e-05, "loss": 1.3531, "step": 115530 }, { "epoch": 5.28, "learning_rate": 2.367385235022198e-05, "loss": 1.3849, "step": 115540 }, { "epoch": 5.28, "learning_rate": 2.3671563915968694e-05, "loss": 1.5012, "step": 115550 }, { "epoch": 5.28, "learning_rate": 2.366927548171541e-05, "loss": 1.4732, "step": 115560 }, { "epoch": 5.28, "learning_rate": 2.3666987047462126e-05, "loss": 1.478, "step": 115570 }, { "epoch": 5.28, "learning_rate": 2.3664698613208843e-05, "loss": 1.5728, "step": 115580 }, { "epoch": 5.28, "learning_rate": 2.366241017895556e-05, "loss": 1.5251, "step": 115590 }, { "epoch": 5.28, "learning_rate": 2.3660121744702275e-05, "loss": 1.5171, "step": 115600 }, { "epoch": 5.28, "learning_rate": 2.3657833310448992e-05, "loss": 1.1902, "step": 115610 }, { "epoch": 5.28, "learning_rate": 2.365554487619571e-05, "loss": 1.5712, "step": 115620 }, { "epoch": 5.28, "learning_rate": 2.3653256441942424e-05, "loss": 1.4494, "step": 115630 }, { "epoch": 5.28, "learning_rate": 2.3650968007689138e-05, "loss": 1.3513, "step": 115640 }, { "epoch": 5.28, "learning_rate": 2.3648679573435856e-05, "loss": 1.4444, "step": 115650 }, { "epoch": 5.28, "learning_rate": 2.3646391139182573e-05, "loss": 1.457, "step": 115660 }, { "epoch": 5.28, "learning_rate": 2.3644102704929287e-05, "loss": 1.4904, "step": 115670 }, { "epoch": 5.28, "learning_rate": 2.3641814270676005e-05, "loss": 1.6827, "step": 115680 }, { "epoch": 5.28, "learning_rate": 2.3639525836422722e-05, "loss": 1.5236, "step": 115690 }, { "epoch": 5.28, "learning_rate": 2.3637237402169437e-05, "loss": 1.4623, "step": 115700 }, { "epoch": 5.28, "learning_rate": 2.3634948967916154e-05, "loss": 1.4746, "step": 115710 }, { "epoch": 5.28, "learning_rate": 2.363266053366287e-05, "loss": 1.5315, "step": 115720 }, { "epoch": 5.28, "learning_rate": 2.3630372099409582e-05, "loss": 1.5318, "step": 115730 }, { "epoch": 5.28, "learning_rate": 2.36280836651563e-05, "loss": 1.4233, "step": 115740 }, { "epoch": 5.29, "learning_rate": 2.3625795230903017e-05, "loss": 1.6134, "step": 115750 }, { "epoch": 5.29, "learning_rate": 2.362350679664973e-05, "loss": 1.4248, "step": 115760 }, { "epoch": 5.29, "learning_rate": 2.362121836239645e-05, "loss": 1.4079, "step": 115770 }, { "epoch": 5.29, "learning_rate": 2.3618929928143167e-05, "loss": 1.4922, "step": 115780 }, { "epoch": 5.29, "learning_rate": 2.361664149388988e-05, "loss": 1.4637, "step": 115790 }, { "epoch": 5.29, "learning_rate": 2.3614353059636598e-05, "loss": 1.4544, "step": 115800 }, { "epoch": 5.29, "learning_rate": 2.3612064625383316e-05, "loss": 1.3747, "step": 115810 }, { "epoch": 5.29, "learning_rate": 2.360977619113003e-05, "loss": 1.4286, "step": 115820 }, { "epoch": 5.29, "learning_rate": 2.3607487756876744e-05, "loss": 1.4346, "step": 115830 }, { "epoch": 5.29, "learning_rate": 2.360519932262346e-05, "loss": 1.5318, "step": 115840 }, { "epoch": 5.29, "learning_rate": 2.360291088837018e-05, "loss": 1.721, "step": 115850 }, { "epoch": 5.29, "learning_rate": 2.3600622454116893e-05, "loss": 1.4799, "step": 115860 }, { "epoch": 5.29, "learning_rate": 2.359833401986361e-05, "loss": 1.5444, "step": 115870 }, { "epoch": 5.29, "learning_rate": 2.3596045585610328e-05, "loss": 1.577, "step": 115880 }, { "epoch": 5.29, "learning_rate": 2.3593757151357042e-05, "loss": 1.4963, "step": 115890 }, { "epoch": 5.29, "learning_rate": 2.359146871710376e-05, "loss": 1.4528, "step": 115900 }, { "epoch": 5.29, "learning_rate": 2.3589180282850477e-05, "loss": 1.4397, "step": 115910 }, { "epoch": 5.29, "learning_rate": 2.3586891848597188e-05, "loss": 1.3806, "step": 115920 }, { "epoch": 5.29, "learning_rate": 2.3584603414343906e-05, "loss": 1.5486, "step": 115930 }, { "epoch": 5.29, "learning_rate": 2.3582314980090623e-05, "loss": 1.5243, "step": 115940 }, { "epoch": 5.29, "learning_rate": 2.3580026545837337e-05, "loss": 1.3503, "step": 115950 }, { "epoch": 5.3, "learning_rate": 2.3577738111584055e-05, "loss": 1.4703, "step": 115960 }, { "epoch": 5.3, "learning_rate": 2.3575449677330772e-05, "loss": 1.4989, "step": 115970 }, { "epoch": 5.3, "learning_rate": 2.3573161243077487e-05, "loss": 1.6204, "step": 115980 }, { "epoch": 5.3, "learning_rate": 2.3570872808824204e-05, "loss": 1.5562, "step": 115990 }, { "epoch": 5.3, "learning_rate": 2.356858437457092e-05, "loss": 1.4927, "step": 116000 }, { "epoch": 5.3, "learning_rate": 2.3566295940317636e-05, "loss": 1.5888, "step": 116010 }, { "epoch": 5.3, "learning_rate": 2.356400750606435e-05, "loss": 1.5508, "step": 116020 }, { "epoch": 5.3, "learning_rate": 2.3561719071811067e-05, "loss": 1.2569, "step": 116030 }, { "epoch": 5.3, "learning_rate": 2.3559430637557785e-05, "loss": 1.4405, "step": 116040 }, { "epoch": 5.3, "learning_rate": 2.35571422033045e-05, "loss": 1.497, "step": 116050 }, { "epoch": 5.3, "learning_rate": 2.3554853769051217e-05, "loss": 1.5682, "step": 116060 }, { "epoch": 5.3, "learning_rate": 2.3552565334797934e-05, "loss": 1.42, "step": 116070 }, { "epoch": 5.3, "learning_rate": 2.3550276900544648e-05, "loss": 1.3382, "step": 116080 }, { "epoch": 5.3, "learning_rate": 2.3547988466291366e-05, "loss": 1.5161, "step": 116090 }, { "epoch": 5.3, "learning_rate": 2.3545700032038083e-05, "loss": 1.5982, "step": 116100 }, { "epoch": 5.3, "learning_rate": 2.3543411597784797e-05, "loss": 1.5908, "step": 116110 }, { "epoch": 5.3, "learning_rate": 2.354112316353151e-05, "loss": 1.583, "step": 116120 }, { "epoch": 5.3, "learning_rate": 2.353883472927823e-05, "loss": 1.4228, "step": 116130 }, { "epoch": 5.3, "learning_rate": 2.3536546295024943e-05, "loss": 1.4293, "step": 116140 }, { "epoch": 5.3, "learning_rate": 2.353425786077166e-05, "loss": 1.499, "step": 116150 }, { "epoch": 5.3, "learning_rate": 2.3531969426518378e-05, "loss": 1.4872, "step": 116160 }, { "epoch": 5.3, "learning_rate": 2.3529680992265092e-05, "loss": 1.4557, "step": 116170 }, { "epoch": 5.31, "learning_rate": 2.352739255801181e-05, "loss": 1.4804, "step": 116180 }, { "epoch": 5.31, "learning_rate": 2.3525104123758527e-05, "loss": 1.2762, "step": 116190 }, { "epoch": 5.31, "learning_rate": 2.352281568950524e-05, "loss": 1.5914, "step": 116200 }, { "epoch": 5.31, "learning_rate": 2.352052725525196e-05, "loss": 1.4605, "step": 116210 }, { "epoch": 5.31, "learning_rate": 2.3518238820998673e-05, "loss": 1.4871, "step": 116220 }, { "epoch": 5.31, "learning_rate": 2.3515950386745387e-05, "loss": 1.5025, "step": 116230 }, { "epoch": 5.31, "learning_rate": 2.3513661952492105e-05, "loss": 1.5156, "step": 116240 }, { "epoch": 5.31, "learning_rate": 2.3511373518238822e-05, "loss": 1.5599, "step": 116250 }, { "epoch": 5.31, "learning_rate": 2.3509085083985537e-05, "loss": 1.3769, "step": 116260 }, { "epoch": 5.31, "learning_rate": 2.3506796649732254e-05, "loss": 1.4924, "step": 116270 }, { "epoch": 5.31, "learning_rate": 2.350450821547897e-05, "loss": 1.4523, "step": 116280 }, { "epoch": 5.31, "learning_rate": 2.3502219781225686e-05, "loss": 1.5384, "step": 116290 }, { "epoch": 5.31, "learning_rate": 2.3499931346972403e-05, "loss": 1.4123, "step": 116300 }, { "epoch": 5.31, "learning_rate": 2.349764291271912e-05, "loss": 1.2717, "step": 116310 }, { "epoch": 5.31, "learning_rate": 2.3495354478465835e-05, "loss": 1.4653, "step": 116320 }, { "epoch": 5.31, "learning_rate": 2.349306604421255e-05, "loss": 1.6023, "step": 116330 }, { "epoch": 5.31, "learning_rate": 2.3490777609959267e-05, "loss": 1.2681, "step": 116340 }, { "epoch": 5.31, "learning_rate": 2.3488489175705984e-05, "loss": 1.5387, "step": 116350 }, { "epoch": 5.31, "learning_rate": 2.3486200741452698e-05, "loss": 1.5034, "step": 116360 }, { "epoch": 5.31, "learning_rate": 2.3483912307199416e-05, "loss": 1.5284, "step": 116370 }, { "epoch": 5.31, "learning_rate": 2.3481623872946133e-05, "loss": 1.45, "step": 116380 }, { "epoch": 5.31, "learning_rate": 2.3479335438692847e-05, "loss": 1.8296, "step": 116390 }, { "epoch": 5.32, "learning_rate": 2.3477047004439565e-05, "loss": 1.4393, "step": 116400 }, { "epoch": 5.32, "learning_rate": 2.3474758570186282e-05, "loss": 1.5665, "step": 116410 }, { "epoch": 5.32, "learning_rate": 2.3472470135932993e-05, "loss": 1.647, "step": 116420 }, { "epoch": 5.32, "learning_rate": 2.347018170167971e-05, "loss": 1.4447, "step": 116430 }, { "epoch": 5.32, "learning_rate": 2.3467893267426428e-05, "loss": 1.6053, "step": 116440 }, { "epoch": 5.32, "learning_rate": 2.3465604833173142e-05, "loss": 1.7403, "step": 116450 }, { "epoch": 5.32, "learning_rate": 2.346331639891986e-05, "loss": 1.5053, "step": 116460 }, { "epoch": 5.32, "learning_rate": 2.3461027964666577e-05, "loss": 1.4199, "step": 116470 }, { "epoch": 5.32, "learning_rate": 2.345873953041329e-05, "loss": 1.3874, "step": 116480 }, { "epoch": 5.32, "learning_rate": 2.345645109616001e-05, "loss": 1.6108, "step": 116490 }, { "epoch": 5.32, "learning_rate": 2.3454162661906727e-05, "loss": 1.3779, "step": 116500 }, { "epoch": 5.32, "learning_rate": 2.345187422765344e-05, "loss": 1.5385, "step": 116510 }, { "epoch": 5.32, "learning_rate": 2.3449585793400155e-05, "loss": 1.4883, "step": 116520 }, { "epoch": 5.32, "learning_rate": 2.3447297359146872e-05, "loss": 1.5374, "step": 116530 }, { "epoch": 5.32, "learning_rate": 2.344500892489359e-05, "loss": 1.3931, "step": 116540 }, { "epoch": 5.32, "learning_rate": 2.3442720490640304e-05, "loss": 1.325, "step": 116550 }, { "epoch": 5.32, "learning_rate": 2.344043205638702e-05, "loss": 1.4961, "step": 116560 }, { "epoch": 5.32, "learning_rate": 2.343814362213374e-05, "loss": 1.3902, "step": 116570 }, { "epoch": 5.32, "learning_rate": 2.3435855187880453e-05, "loss": 1.4279, "step": 116580 }, { "epoch": 5.32, "learning_rate": 2.343356675362717e-05, "loss": 1.4982, "step": 116590 }, { "epoch": 5.32, "learning_rate": 2.3431278319373888e-05, "loss": 1.5124, "step": 116600 }, { "epoch": 5.32, "learning_rate": 2.34289898851206e-05, "loss": 1.4875, "step": 116610 }, { "epoch": 5.33, "learning_rate": 2.3426701450867316e-05, "loss": 1.5326, "step": 116620 }, { "epoch": 5.33, "learning_rate": 2.3424413016614034e-05, "loss": 1.3896, "step": 116630 }, { "epoch": 5.33, "learning_rate": 2.3422124582360748e-05, "loss": 1.3302, "step": 116640 }, { "epoch": 5.33, "learning_rate": 2.3419836148107466e-05, "loss": 1.4301, "step": 116650 }, { "epoch": 5.33, "learning_rate": 2.3417547713854183e-05, "loss": 1.5189, "step": 116660 }, { "epoch": 5.33, "learning_rate": 2.3415259279600897e-05, "loss": 1.5085, "step": 116670 }, { "epoch": 5.33, "learning_rate": 2.3412970845347615e-05, "loss": 1.4181, "step": 116680 }, { "epoch": 5.33, "learning_rate": 2.3410682411094332e-05, "loss": 1.4606, "step": 116690 }, { "epoch": 5.33, "learning_rate": 2.3408393976841046e-05, "loss": 1.6568, "step": 116700 }, { "epoch": 5.33, "learning_rate": 2.340610554258776e-05, "loss": 1.6591, "step": 116710 }, { "epoch": 5.33, "learning_rate": 2.3403817108334478e-05, "loss": 1.3723, "step": 116720 }, { "epoch": 5.33, "learning_rate": 2.3401528674081196e-05, "loss": 1.4791, "step": 116730 }, { "epoch": 5.33, "learning_rate": 2.339924023982791e-05, "loss": 1.4736, "step": 116740 }, { "epoch": 5.33, "learning_rate": 2.3396951805574627e-05, "loss": 1.6591, "step": 116750 }, { "epoch": 5.33, "learning_rate": 2.339466337132134e-05, "loss": 1.3657, "step": 116760 }, { "epoch": 5.33, "learning_rate": 2.339237493706806e-05, "loss": 1.436, "step": 116770 }, { "epoch": 5.33, "learning_rate": 2.3390086502814777e-05, "loss": 1.5044, "step": 116780 }, { "epoch": 5.33, "learning_rate": 2.338779806856149e-05, "loss": 1.5034, "step": 116790 }, { "epoch": 5.33, "learning_rate": 2.3385509634308208e-05, "loss": 1.6976, "step": 116800 }, { "epoch": 5.33, "learning_rate": 2.3383221200054922e-05, "loss": 1.3453, "step": 116810 }, { "epoch": 5.33, "learning_rate": 2.338093276580164e-05, "loss": 1.5737, "step": 116820 }, { "epoch": 5.33, "learning_rate": 2.3378644331548354e-05, "loss": 1.4529, "step": 116830 }, { "epoch": 5.34, "learning_rate": 2.337635589729507e-05, "loss": 1.4513, "step": 116840 }, { "epoch": 5.34, "learning_rate": 2.337406746304179e-05, "loss": 1.4328, "step": 116850 }, { "epoch": 5.34, "learning_rate": 2.3371779028788503e-05, "loss": 1.5327, "step": 116860 }, { "epoch": 5.34, "learning_rate": 2.336949059453522e-05, "loss": 1.5077, "step": 116870 }, { "epoch": 5.34, "learning_rate": 2.3367202160281938e-05, "loss": 1.5149, "step": 116880 }, { "epoch": 5.34, "learning_rate": 2.3364913726028652e-05, "loss": 1.392, "step": 116890 }, { "epoch": 5.34, "learning_rate": 2.336262529177537e-05, "loss": 1.4994, "step": 116900 }, { "epoch": 5.34, "learning_rate": 2.3360336857522084e-05, "loss": 1.3861, "step": 116910 }, { "epoch": 5.34, "learning_rate": 2.3358048423268798e-05, "loss": 1.3132, "step": 116920 }, { "epoch": 5.34, "learning_rate": 2.3355759989015516e-05, "loss": 1.5519, "step": 116930 }, { "epoch": 5.34, "learning_rate": 2.3353471554762233e-05, "loss": 1.4862, "step": 116940 }, { "epoch": 5.34, "learning_rate": 2.3351183120508947e-05, "loss": 1.5344, "step": 116950 }, { "epoch": 5.34, "learning_rate": 2.3348894686255665e-05, "loss": 1.5349, "step": 116960 }, { "epoch": 5.34, "learning_rate": 2.3346606252002382e-05, "loss": 1.4337, "step": 116970 }, { "epoch": 5.34, "learning_rate": 2.3344317817749096e-05, "loss": 1.4142, "step": 116980 }, { "epoch": 5.34, "learning_rate": 2.3342029383495814e-05, "loss": 1.4147, "step": 116990 }, { "epoch": 5.34, "learning_rate": 2.333974094924253e-05, "loss": 1.4567, "step": 117000 }, { "epoch": 5.34, "learning_rate": 2.3337452514989246e-05, "loss": 1.5469, "step": 117010 }, { "epoch": 5.34, "learning_rate": 2.333516408073596e-05, "loss": 1.5498, "step": 117020 }, { "epoch": 5.34, "learning_rate": 2.3332875646482677e-05, "loss": 1.3682, "step": 117030 }, { "epoch": 5.34, "learning_rate": 2.3330587212229395e-05, "loss": 1.3576, "step": 117040 }, { "epoch": 5.34, "learning_rate": 2.332829877797611e-05, "loss": 1.5001, "step": 117050 }, { "epoch": 5.35, "learning_rate": 2.3326010343722826e-05, "loss": 1.5225, "step": 117060 }, { "epoch": 5.35, "learning_rate": 2.3323721909469544e-05, "loss": 1.5824, "step": 117070 }, { "epoch": 5.35, "learning_rate": 2.3321433475216258e-05, "loss": 1.5207, "step": 117080 }, { "epoch": 5.35, "learning_rate": 2.3319145040962976e-05, "loss": 1.6169, "step": 117090 }, { "epoch": 5.35, "learning_rate": 2.3316856606709693e-05, "loss": 1.4313, "step": 117100 }, { "epoch": 5.35, "learning_rate": 2.3314568172456404e-05, "loss": 1.5956, "step": 117110 }, { "epoch": 5.35, "learning_rate": 2.331227973820312e-05, "loss": 1.6329, "step": 117120 }, { "epoch": 5.35, "learning_rate": 2.330999130394984e-05, "loss": 1.4309, "step": 117130 }, { "epoch": 5.35, "learning_rate": 2.3307702869696553e-05, "loss": 1.5216, "step": 117140 }, { "epoch": 5.35, "learning_rate": 2.330541443544327e-05, "loss": 1.3962, "step": 117150 }, { "epoch": 5.35, "learning_rate": 2.3303126001189988e-05, "loss": 1.4353, "step": 117160 }, { "epoch": 5.35, "learning_rate": 2.3300837566936702e-05, "loss": 1.4297, "step": 117170 }, { "epoch": 5.35, "learning_rate": 2.329854913268342e-05, "loss": 1.5091, "step": 117180 }, { "epoch": 5.35, "learning_rate": 2.3296260698430137e-05, "loss": 1.4943, "step": 117190 }, { "epoch": 5.35, "learning_rate": 2.329397226417685e-05, "loss": 1.5063, "step": 117200 }, { "epoch": 5.35, "learning_rate": 2.3291683829923566e-05, "loss": 1.4393, "step": 117210 }, { "epoch": 5.35, "learning_rate": 2.3289395395670283e-05, "loss": 1.5493, "step": 117220 }, { "epoch": 5.35, "learning_rate": 2.3287106961417e-05, "loss": 1.4297, "step": 117230 }, { "epoch": 5.35, "learning_rate": 2.3284818527163715e-05, "loss": 1.466, "step": 117240 }, { "epoch": 5.35, "learning_rate": 2.3282530092910432e-05, "loss": 1.4855, "step": 117250 }, { "epoch": 5.35, "learning_rate": 2.328024165865715e-05, "loss": 1.4464, "step": 117260 }, { "epoch": 5.35, "learning_rate": 2.3277953224403864e-05, "loss": 1.3222, "step": 117270 }, { "epoch": 5.36, "learning_rate": 2.327566479015058e-05, "loss": 1.5563, "step": 117280 }, { "epoch": 5.36, "learning_rate": 2.3273376355897296e-05, "loss": 1.416, "step": 117290 }, { "epoch": 5.36, "learning_rate": 2.3271087921644013e-05, "loss": 1.6186, "step": 117300 }, { "epoch": 5.36, "learning_rate": 2.3268799487390727e-05, "loss": 1.5215, "step": 117310 }, { "epoch": 5.36, "learning_rate": 2.3266511053137445e-05, "loss": 1.4285, "step": 117320 }, { "epoch": 5.36, "learning_rate": 2.326422261888416e-05, "loss": 1.6082, "step": 117330 }, { "epoch": 5.36, "learning_rate": 2.3261934184630876e-05, "loss": 1.6405, "step": 117340 }, { "epoch": 5.36, "learning_rate": 2.3259645750377594e-05, "loss": 1.4042, "step": 117350 }, { "epoch": 5.36, "learning_rate": 2.3257357316124308e-05, "loss": 1.4592, "step": 117360 }, { "epoch": 5.36, "learning_rate": 2.3255068881871026e-05, "loss": 1.6557, "step": 117370 }, { "epoch": 5.36, "learning_rate": 2.3252780447617743e-05, "loss": 1.5601, "step": 117380 }, { "epoch": 5.36, "learning_rate": 2.3250492013364457e-05, "loss": 1.4239, "step": 117390 }, { "epoch": 5.36, "learning_rate": 2.3248203579111175e-05, "loss": 1.3326, "step": 117400 }, { "epoch": 5.36, "learning_rate": 2.324591514485789e-05, "loss": 1.4617, "step": 117410 }, { "epoch": 5.36, "learning_rate": 2.3243626710604603e-05, "loss": 1.4325, "step": 117420 }, { "epoch": 5.36, "learning_rate": 2.324133827635132e-05, "loss": 1.3773, "step": 117430 }, { "epoch": 5.36, "learning_rate": 2.3239049842098038e-05, "loss": 1.4329, "step": 117440 }, { "epoch": 5.36, "learning_rate": 2.3236761407844752e-05, "loss": 1.4653, "step": 117450 }, { "epoch": 5.36, "learning_rate": 2.323447297359147e-05, "loss": 1.4603, "step": 117460 }, { "epoch": 5.36, "learning_rate": 2.3232184539338187e-05, "loss": 1.5703, "step": 117470 }, { "epoch": 5.36, "learning_rate": 2.32298961050849e-05, "loss": 1.5387, "step": 117480 }, { "epoch": 5.36, "learning_rate": 2.322760767083162e-05, "loss": 1.3549, "step": 117490 }, { "epoch": 5.37, "learning_rate": 2.3225319236578333e-05, "loss": 1.4901, "step": 117500 }, { "epoch": 5.37, "learning_rate": 2.322303080232505e-05, "loss": 1.5689, "step": 117510 }, { "epoch": 5.37, "learning_rate": 2.3220742368071765e-05, "loss": 1.3507, "step": 117520 }, { "epoch": 5.37, "learning_rate": 2.3218453933818482e-05, "loss": 1.2393, "step": 117530 }, { "epoch": 5.37, "learning_rate": 2.32161654995652e-05, "loss": 1.3445, "step": 117540 }, { "epoch": 5.37, "learning_rate": 2.3213877065311914e-05, "loss": 1.5806, "step": 117550 }, { "epoch": 5.37, "learning_rate": 2.321158863105863e-05, "loss": 1.4351, "step": 117560 }, { "epoch": 5.37, "learning_rate": 2.320930019680535e-05, "loss": 1.4789, "step": 117570 }, { "epoch": 5.37, "learning_rate": 2.3207011762552063e-05, "loss": 1.4672, "step": 117580 }, { "epoch": 5.37, "learning_rate": 2.320472332829878e-05, "loss": 1.4078, "step": 117590 }, { "epoch": 5.37, "learning_rate": 2.3202434894045495e-05, "loss": 1.4983, "step": 117600 }, { "epoch": 5.37, "learning_rate": 2.320014645979221e-05, "loss": 1.5361, "step": 117610 }, { "epoch": 5.37, "learning_rate": 2.3197858025538926e-05, "loss": 1.421, "step": 117620 }, { "epoch": 5.37, "learning_rate": 2.3195569591285644e-05, "loss": 1.4951, "step": 117630 }, { "epoch": 5.37, "learning_rate": 2.3193281157032358e-05, "loss": 1.519, "step": 117640 }, { "epoch": 5.37, "learning_rate": 2.3190992722779076e-05, "loss": 1.4194, "step": 117650 }, { "epoch": 5.37, "learning_rate": 2.3188704288525793e-05, "loss": 1.532, "step": 117660 }, { "epoch": 5.37, "learning_rate": 2.3186415854272507e-05, "loss": 1.5792, "step": 117670 }, { "epoch": 5.37, "learning_rate": 2.3184127420019225e-05, "loss": 1.439, "step": 117680 }, { "epoch": 5.37, "learning_rate": 2.3181838985765942e-05, "loss": 1.5217, "step": 117690 }, { "epoch": 5.37, "learning_rate": 2.3179550551512656e-05, "loss": 1.6443, "step": 117700 }, { "epoch": 5.37, "learning_rate": 2.317726211725937e-05, "loss": 1.5877, "step": 117710 }, { "epoch": 5.38, "learning_rate": 2.3174973683006088e-05, "loss": 1.5263, "step": 117720 }, { "epoch": 5.38, "learning_rate": 2.3172685248752806e-05, "loss": 1.5089, "step": 117730 }, { "epoch": 5.38, "learning_rate": 2.317039681449952e-05, "loss": 1.6782, "step": 117740 }, { "epoch": 5.38, "learning_rate": 2.3168108380246237e-05, "loss": 1.3359, "step": 117750 }, { "epoch": 5.38, "learning_rate": 2.3165819945992955e-05, "loss": 1.4005, "step": 117760 }, { "epoch": 5.38, "learning_rate": 2.316353151173967e-05, "loss": 1.4813, "step": 117770 }, { "epoch": 5.38, "learning_rate": 2.3161243077486386e-05, "loss": 1.5169, "step": 117780 }, { "epoch": 5.38, "learning_rate": 2.3158954643233104e-05, "loss": 1.4464, "step": 117790 }, { "epoch": 5.38, "learning_rate": 2.3156666208979815e-05, "loss": 1.5545, "step": 117800 }, { "epoch": 5.38, "learning_rate": 2.3154377774726532e-05, "loss": 1.5287, "step": 117810 }, { "epoch": 5.38, "learning_rate": 2.315208934047325e-05, "loss": 1.4136, "step": 117820 }, { "epoch": 5.38, "learning_rate": 2.3149800906219964e-05, "loss": 1.7292, "step": 117830 }, { "epoch": 5.38, "learning_rate": 2.314751247196668e-05, "loss": 1.4714, "step": 117840 }, { "epoch": 5.38, "learning_rate": 2.31452240377134e-05, "loss": 1.4242, "step": 117850 }, { "epoch": 5.38, "learning_rate": 2.3142935603460113e-05, "loss": 1.4046, "step": 117860 }, { "epoch": 5.38, "learning_rate": 2.314064716920683e-05, "loss": 1.4174, "step": 117870 }, { "epoch": 5.38, "learning_rate": 2.3138358734953548e-05, "loss": 1.5483, "step": 117880 }, { "epoch": 5.38, "learning_rate": 2.3136070300700262e-05, "loss": 1.4438, "step": 117890 }, { "epoch": 5.38, "learning_rate": 2.3133781866446976e-05, "loss": 1.5505, "step": 117900 }, { "epoch": 5.38, "learning_rate": 2.3131493432193694e-05, "loss": 1.4146, "step": 117910 }, { "epoch": 5.38, "learning_rate": 2.3129204997940408e-05, "loss": 1.5372, "step": 117920 }, { "epoch": 5.38, "learning_rate": 2.3126916563687125e-05, "loss": 1.6325, "step": 117930 }, { "epoch": 5.39, "learning_rate": 2.3124628129433843e-05, "loss": 1.2907, "step": 117940 }, { "epoch": 5.39, "learning_rate": 2.3122339695180557e-05, "loss": 1.3705, "step": 117950 }, { "epoch": 5.39, "learning_rate": 2.3120051260927275e-05, "loss": 1.4722, "step": 117960 }, { "epoch": 5.39, "learning_rate": 2.3117762826673992e-05, "loss": 1.5363, "step": 117970 }, { "epoch": 5.39, "learning_rate": 2.3115474392420706e-05, "loss": 1.4426, "step": 117980 }, { "epoch": 5.39, "learning_rate": 2.3113185958167424e-05, "loss": 1.5637, "step": 117990 }, { "epoch": 5.39, "learning_rate": 2.3110897523914138e-05, "loss": 1.5393, "step": 118000 }, { "epoch": 5.39, "learning_rate": 2.3108609089660855e-05, "loss": 1.6618, "step": 118010 }, { "epoch": 5.39, "learning_rate": 2.310632065540757e-05, "loss": 1.6212, "step": 118020 }, { "epoch": 5.39, "learning_rate": 2.3104032221154287e-05, "loss": 1.6058, "step": 118030 }, { "epoch": 5.39, "learning_rate": 2.3101743786901005e-05, "loss": 1.3258, "step": 118040 }, { "epoch": 5.39, "learning_rate": 2.309945535264772e-05, "loss": 1.5824, "step": 118050 }, { "epoch": 5.39, "learning_rate": 2.3097166918394436e-05, "loss": 1.4123, "step": 118060 }, { "epoch": 5.39, "learning_rate": 2.3094878484141154e-05, "loss": 1.5632, "step": 118070 }, { "epoch": 5.39, "learning_rate": 2.3092590049887868e-05, "loss": 1.4498, "step": 118080 }, { "epoch": 5.39, "learning_rate": 2.3090301615634585e-05, "loss": 1.5434, "step": 118090 }, { "epoch": 5.39, "learning_rate": 2.30880131813813e-05, "loss": 1.4584, "step": 118100 }, { "epoch": 5.39, "learning_rate": 2.3085724747128014e-05, "loss": 1.4891, "step": 118110 }, { "epoch": 5.39, "learning_rate": 2.308343631287473e-05, "loss": 1.3217, "step": 118120 }, { "epoch": 5.39, "learning_rate": 2.308114787862145e-05, "loss": 1.4436, "step": 118130 }, { "epoch": 5.39, "learning_rate": 2.3078859444368163e-05, "loss": 1.6616, "step": 118140 }, { "epoch": 5.4, "learning_rate": 2.307657101011488e-05, "loss": 1.4623, "step": 118150 }, { "epoch": 5.4, "learning_rate": 2.3074282575861598e-05, "loss": 1.5052, "step": 118160 }, { "epoch": 5.4, "learning_rate": 2.3071994141608312e-05, "loss": 1.3752, "step": 118170 }, { "epoch": 5.4, "learning_rate": 2.306970570735503e-05, "loss": 1.5641, "step": 118180 }, { "epoch": 5.4, "learning_rate": 2.3067417273101747e-05, "loss": 1.5589, "step": 118190 }, { "epoch": 5.4, "learning_rate": 2.306512883884846e-05, "loss": 1.5504, "step": 118200 }, { "epoch": 5.4, "learning_rate": 2.3062840404595175e-05, "loss": 1.3789, "step": 118210 }, { "epoch": 5.4, "learning_rate": 2.3060551970341893e-05, "loss": 1.5784, "step": 118220 }, { "epoch": 5.4, "learning_rate": 2.305826353608861e-05, "loss": 1.3096, "step": 118230 }, { "epoch": 5.4, "learning_rate": 2.3055975101835325e-05, "loss": 1.4357, "step": 118240 }, { "epoch": 5.4, "learning_rate": 2.3053686667582042e-05, "loss": 1.3543, "step": 118250 }, { "epoch": 5.4, "learning_rate": 2.305139823332876e-05, "loss": 1.4673, "step": 118260 }, { "epoch": 5.4, "learning_rate": 2.3049109799075474e-05, "loss": 1.6114, "step": 118270 }, { "epoch": 5.4, "learning_rate": 2.304682136482219e-05, "loss": 1.5025, "step": 118280 }, { "epoch": 5.4, "learning_rate": 2.3044532930568905e-05, "loss": 1.4692, "step": 118290 }, { "epoch": 5.4, "learning_rate": 2.304224449631562e-05, "loss": 1.4345, "step": 118300 }, { "epoch": 5.4, "learning_rate": 2.3039956062062337e-05, "loss": 1.7259, "step": 118310 }, { "epoch": 5.4, "learning_rate": 2.3037667627809055e-05, "loss": 1.39, "step": 118320 }, { "epoch": 5.4, "learning_rate": 2.303537919355577e-05, "loss": 1.2062, "step": 118330 }, { "epoch": 5.4, "learning_rate": 2.3033090759302486e-05, "loss": 1.3356, "step": 118340 }, { "epoch": 5.4, "learning_rate": 2.3030802325049204e-05, "loss": 1.5196, "step": 118350 }, { "epoch": 5.4, "learning_rate": 2.3028513890795918e-05, "loss": 1.3266, "step": 118360 }, { "epoch": 5.41, "learning_rate": 2.3026225456542635e-05, "loss": 1.4809, "step": 118370 }, { "epoch": 5.41, "learning_rate": 2.3023937022289353e-05, "loss": 1.4937, "step": 118380 }, { "epoch": 5.41, "learning_rate": 2.3021648588036067e-05, "loss": 1.3151, "step": 118390 }, { "epoch": 5.41, "learning_rate": 2.301936015378278e-05, "loss": 1.5441, "step": 118400 }, { "epoch": 5.41, "learning_rate": 2.30170717195295e-05, "loss": 1.4308, "step": 118410 }, { "epoch": 5.41, "learning_rate": 2.3014783285276216e-05, "loss": 1.5542, "step": 118420 }, { "epoch": 5.41, "learning_rate": 2.301249485102293e-05, "loss": 1.4967, "step": 118430 }, { "epoch": 5.41, "learning_rate": 2.3010206416769648e-05, "loss": 1.429, "step": 118440 }, { "epoch": 5.41, "learning_rate": 2.3007917982516365e-05, "loss": 1.4228, "step": 118450 }, { "epoch": 5.41, "learning_rate": 2.300562954826308e-05, "loss": 1.5345, "step": 118460 }, { "epoch": 5.41, "learning_rate": 2.3003341114009797e-05, "loss": 1.3186, "step": 118470 }, { "epoch": 5.41, "learning_rate": 2.300105267975651e-05, "loss": 1.6598, "step": 118480 }, { "epoch": 5.41, "learning_rate": 2.2998764245503225e-05, "loss": 1.4798, "step": 118490 }, { "epoch": 5.41, "learning_rate": 2.2996475811249943e-05, "loss": 1.5452, "step": 118500 }, { "epoch": 5.41, "learning_rate": 2.299418737699666e-05, "loss": 1.3627, "step": 118510 }, { "epoch": 5.41, "learning_rate": 2.2991898942743375e-05, "loss": 1.4761, "step": 118520 }, { "epoch": 5.41, "learning_rate": 2.2989610508490092e-05, "loss": 1.4009, "step": 118530 }, { "epoch": 5.41, "learning_rate": 2.298732207423681e-05, "loss": 1.4422, "step": 118540 }, { "epoch": 5.41, "learning_rate": 2.2985033639983524e-05, "loss": 1.6731, "step": 118550 }, { "epoch": 5.41, "learning_rate": 2.298274520573024e-05, "loss": 1.5847, "step": 118560 }, { "epoch": 5.41, "learning_rate": 2.298045677147696e-05, "loss": 1.76, "step": 118570 }, { "epoch": 5.41, "learning_rate": 2.2978168337223673e-05, "loss": 1.5493, "step": 118580 }, { "epoch": 5.42, "learning_rate": 2.2975879902970387e-05, "loss": 1.6052, "step": 118590 }, { "epoch": 5.42, "learning_rate": 2.2973591468717105e-05, "loss": 1.4079, "step": 118600 }, { "epoch": 5.42, "learning_rate": 2.297130303446382e-05, "loss": 1.4073, "step": 118610 }, { "epoch": 5.42, "learning_rate": 2.2969014600210536e-05, "loss": 1.3522, "step": 118620 }, { "epoch": 5.42, "learning_rate": 2.2966726165957254e-05, "loss": 1.5691, "step": 118630 }, { "epoch": 5.42, "learning_rate": 2.2964437731703968e-05, "loss": 1.4443, "step": 118640 }, { "epoch": 5.42, "learning_rate": 2.2962149297450685e-05, "loss": 1.3349, "step": 118650 }, { "epoch": 5.42, "learning_rate": 2.2959860863197403e-05, "loss": 1.424, "step": 118660 }, { "epoch": 5.42, "learning_rate": 2.2957572428944117e-05, "loss": 1.4884, "step": 118670 }, { "epoch": 5.42, "learning_rate": 2.2955283994690835e-05, "loss": 1.465, "step": 118680 }, { "epoch": 5.42, "learning_rate": 2.295299556043755e-05, "loss": 1.5013, "step": 118690 }, { "epoch": 5.42, "learning_rate": 2.2950707126184266e-05, "loss": 1.3627, "step": 118700 }, { "epoch": 5.42, "learning_rate": 2.294841869193098e-05, "loss": 1.4574, "step": 118710 }, { "epoch": 5.42, "learning_rate": 2.2946130257677698e-05, "loss": 1.5091, "step": 118720 }, { "epoch": 5.42, "learning_rate": 2.2943841823424415e-05, "loss": 1.5216, "step": 118730 }, { "epoch": 5.42, "learning_rate": 2.294155338917113e-05, "loss": 1.6158, "step": 118740 }, { "epoch": 5.42, "learning_rate": 2.2939264954917847e-05, "loss": 1.5309, "step": 118750 }, { "epoch": 5.42, "learning_rate": 2.2936976520664565e-05, "loss": 1.4336, "step": 118760 }, { "epoch": 5.42, "learning_rate": 2.293468808641128e-05, "loss": 1.4661, "step": 118770 }, { "epoch": 5.42, "learning_rate": 2.2932399652157996e-05, "loss": 1.575, "step": 118780 }, { "epoch": 5.42, "learning_rate": 2.293011121790471e-05, "loss": 1.7029, "step": 118790 }, { "epoch": 5.42, "learning_rate": 2.2927822783651425e-05, "loss": 1.4568, "step": 118800 }, { "epoch": 5.43, "learning_rate": 2.2925534349398142e-05, "loss": 1.6091, "step": 118810 }, { "epoch": 5.43, "learning_rate": 2.292324591514486e-05, "loss": 1.4996, "step": 118820 }, { "epoch": 5.43, "learning_rate": 2.2920957480891574e-05, "loss": 1.4836, "step": 118830 }, { "epoch": 5.43, "learning_rate": 2.291866904663829e-05, "loss": 1.4768, "step": 118840 }, { "epoch": 5.43, "learning_rate": 2.291638061238501e-05, "loss": 1.5224, "step": 118850 }, { "epoch": 5.43, "learning_rate": 2.2914092178131723e-05, "loss": 1.5642, "step": 118860 }, { "epoch": 5.43, "learning_rate": 2.291180374387844e-05, "loss": 1.5313, "step": 118870 }, { "epoch": 5.43, "learning_rate": 2.2909515309625158e-05, "loss": 1.4944, "step": 118880 }, { "epoch": 5.43, "learning_rate": 2.2907226875371872e-05, "loss": 1.6047, "step": 118890 }, { "epoch": 5.43, "learning_rate": 2.2904938441118586e-05, "loss": 1.4708, "step": 118900 }, { "epoch": 5.43, "learning_rate": 2.2902650006865304e-05, "loss": 1.5074, "step": 118910 }, { "epoch": 5.43, "learning_rate": 2.290036157261202e-05, "loss": 1.499, "step": 118920 }, { "epoch": 5.43, "learning_rate": 2.2898073138358735e-05, "loss": 1.4928, "step": 118930 }, { "epoch": 5.43, "learning_rate": 2.2895784704105453e-05, "loss": 1.3898, "step": 118940 }, { "epoch": 5.43, "learning_rate": 2.289349626985217e-05, "loss": 1.309, "step": 118950 }, { "epoch": 5.43, "learning_rate": 2.2891207835598885e-05, "loss": 1.4383, "step": 118960 }, { "epoch": 5.43, "learning_rate": 2.2888919401345602e-05, "loss": 1.5922, "step": 118970 }, { "epoch": 5.43, "learning_rate": 2.288663096709232e-05, "loss": 1.5027, "step": 118980 }, { "epoch": 5.43, "learning_rate": 2.288434253283903e-05, "loss": 1.3717, "step": 118990 }, { "epoch": 5.43, "learning_rate": 2.2882054098585748e-05, "loss": 1.3904, "step": 119000 }, { "epoch": 5.43, "learning_rate": 2.2879765664332465e-05, "loss": 1.4555, "step": 119010 }, { "epoch": 5.43, "learning_rate": 2.287747723007918e-05, "loss": 1.4218, "step": 119020 }, { "epoch": 5.44, "learning_rate": 2.2875188795825897e-05, "loss": 1.4024, "step": 119030 }, { "epoch": 5.44, "learning_rate": 2.2872900361572615e-05, "loss": 1.5453, "step": 119040 }, { "epoch": 5.44, "learning_rate": 2.287061192731933e-05, "loss": 1.6574, "step": 119050 }, { "epoch": 5.44, "learning_rate": 2.2868323493066046e-05, "loss": 1.4406, "step": 119060 }, { "epoch": 5.44, "learning_rate": 2.2866035058812764e-05, "loss": 1.4841, "step": 119070 }, { "epoch": 5.44, "learning_rate": 2.2863746624559474e-05, "loss": 1.5521, "step": 119080 }, { "epoch": 5.44, "learning_rate": 2.2861458190306192e-05, "loss": 1.4696, "step": 119090 }, { "epoch": 5.44, "learning_rate": 2.285916975605291e-05, "loss": 1.4585, "step": 119100 }, { "epoch": 5.44, "learning_rate": 2.2856881321799624e-05, "loss": 1.4558, "step": 119110 }, { "epoch": 5.44, "learning_rate": 2.285459288754634e-05, "loss": 1.3582, "step": 119120 }, { "epoch": 5.44, "learning_rate": 2.285230445329306e-05, "loss": 1.697, "step": 119130 }, { "epoch": 5.44, "learning_rate": 2.2850016019039773e-05, "loss": 1.737, "step": 119140 }, { "epoch": 5.44, "learning_rate": 2.284772758478649e-05, "loss": 1.5594, "step": 119150 }, { "epoch": 5.44, "learning_rate": 2.2845439150533208e-05, "loss": 1.4515, "step": 119160 }, { "epoch": 5.44, "learning_rate": 2.2843150716279922e-05, "loss": 1.4749, "step": 119170 }, { "epoch": 5.44, "learning_rate": 2.2840862282026636e-05, "loss": 1.4496, "step": 119180 }, { "epoch": 5.44, "learning_rate": 2.2838573847773354e-05, "loss": 1.4562, "step": 119190 }, { "epoch": 5.44, "learning_rate": 2.283628541352007e-05, "loss": 1.6412, "step": 119200 }, { "epoch": 5.44, "learning_rate": 2.2833996979266785e-05, "loss": 1.5812, "step": 119210 }, { "epoch": 5.44, "learning_rate": 2.2831708545013503e-05, "loss": 1.4933, "step": 119220 }, { "epoch": 5.44, "learning_rate": 2.282942011076022e-05, "loss": 1.3499, "step": 119230 }, { "epoch": 5.44, "learning_rate": 2.2827131676506934e-05, "loss": 1.4741, "step": 119240 }, { "epoch": 5.45, "learning_rate": 2.2824843242253652e-05, "loss": 1.3129, "step": 119250 }, { "epoch": 5.45, "learning_rate": 2.282255480800037e-05, "loss": 1.6393, "step": 119260 }, { "epoch": 5.45, "learning_rate": 2.2820266373747084e-05, "loss": 1.4888, "step": 119270 }, { "epoch": 5.45, "learning_rate": 2.2817977939493798e-05, "loss": 1.3706, "step": 119280 }, { "epoch": 5.45, "learning_rate": 2.2815689505240515e-05, "loss": 1.4336, "step": 119290 }, { "epoch": 5.45, "learning_rate": 2.281340107098723e-05, "loss": 1.3833, "step": 119300 }, { "epoch": 5.45, "learning_rate": 2.2811112636733947e-05, "loss": 1.6261, "step": 119310 }, { "epoch": 5.45, "learning_rate": 2.2808824202480664e-05, "loss": 1.4968, "step": 119320 }, { "epoch": 5.45, "learning_rate": 2.280653576822738e-05, "loss": 1.5861, "step": 119330 }, { "epoch": 5.45, "learning_rate": 2.2804247333974096e-05, "loss": 1.506, "step": 119340 }, { "epoch": 5.45, "learning_rate": 2.2801958899720814e-05, "loss": 1.3977, "step": 119350 }, { "epoch": 5.45, "learning_rate": 2.2799670465467528e-05, "loss": 1.493, "step": 119360 }, { "epoch": 5.45, "learning_rate": 2.2797382031214245e-05, "loss": 1.5876, "step": 119370 }, { "epoch": 5.45, "learning_rate": 2.279509359696096e-05, "loss": 1.5766, "step": 119380 }, { "epoch": 5.45, "learning_rate": 2.2792805162707677e-05, "loss": 1.6038, "step": 119390 }, { "epoch": 5.45, "learning_rate": 2.279051672845439e-05, "loss": 1.5266, "step": 119400 }, { "epoch": 5.45, "learning_rate": 2.278822829420111e-05, "loss": 1.3188, "step": 119410 }, { "epoch": 5.45, "learning_rate": 2.2785939859947826e-05, "loss": 1.5002, "step": 119420 }, { "epoch": 5.45, "learning_rate": 2.278365142569454e-05, "loss": 1.3492, "step": 119430 }, { "epoch": 5.45, "learning_rate": 2.2781362991441258e-05, "loss": 1.6201, "step": 119440 }, { "epoch": 5.45, "learning_rate": 2.2779074557187975e-05, "loss": 1.6158, "step": 119450 }, { "epoch": 5.45, "learning_rate": 2.277678612293469e-05, "loss": 1.4617, "step": 119460 }, { "epoch": 5.46, "learning_rate": 2.2774497688681407e-05, "loss": 1.5253, "step": 119470 }, { "epoch": 5.46, "learning_rate": 2.277220925442812e-05, "loss": 1.4883, "step": 119480 }, { "epoch": 5.46, "learning_rate": 2.2769920820174835e-05, "loss": 1.5249, "step": 119490 }, { "epoch": 5.46, "learning_rate": 2.2767632385921553e-05, "loss": 1.4795, "step": 119500 }, { "epoch": 5.46, "learning_rate": 2.276534395166827e-05, "loss": 1.2883, "step": 119510 }, { "epoch": 5.46, "learning_rate": 2.2763055517414984e-05, "loss": 1.4194, "step": 119520 }, { "epoch": 5.46, "learning_rate": 2.2760767083161702e-05, "loss": 1.3899, "step": 119530 }, { "epoch": 5.46, "learning_rate": 2.275847864890842e-05, "loss": 1.564, "step": 119540 }, { "epoch": 5.46, "learning_rate": 2.2756190214655134e-05, "loss": 1.4741, "step": 119550 }, { "epoch": 5.46, "learning_rate": 2.275390178040185e-05, "loss": 1.5689, "step": 119560 }, { "epoch": 5.46, "learning_rate": 2.275161334614857e-05, "loss": 1.5861, "step": 119570 }, { "epoch": 5.46, "learning_rate": 2.2749324911895283e-05, "loss": 1.4327, "step": 119580 }, { "epoch": 5.46, "learning_rate": 2.2747036477641997e-05, "loss": 1.3921, "step": 119590 }, { "epoch": 5.46, "learning_rate": 2.2744748043388714e-05, "loss": 1.581, "step": 119600 }, { "epoch": 5.46, "learning_rate": 2.2742459609135432e-05, "loss": 1.414, "step": 119610 }, { "epoch": 5.46, "learning_rate": 2.2740171174882146e-05, "loss": 1.4033, "step": 119620 }, { "epoch": 5.46, "learning_rate": 2.2737882740628864e-05, "loss": 1.4546, "step": 119630 }, { "epoch": 5.46, "learning_rate": 2.2735594306375578e-05, "loss": 1.562, "step": 119640 }, { "epoch": 5.46, "learning_rate": 2.2733305872122295e-05, "loss": 1.3659, "step": 119650 }, { "epoch": 5.46, "learning_rate": 2.2731017437869013e-05, "loss": 1.5473, "step": 119660 }, { "epoch": 5.46, "learning_rate": 2.2728729003615727e-05, "loss": 1.659, "step": 119670 }, { "epoch": 5.46, "learning_rate": 2.272644056936244e-05, "loss": 1.5066, "step": 119680 }, { "epoch": 5.47, "learning_rate": 2.272415213510916e-05, "loss": 1.4304, "step": 119690 }, { "epoch": 5.47, "learning_rate": 2.2721863700855876e-05, "loss": 1.4307, "step": 119700 }, { "epoch": 5.47, "learning_rate": 2.271957526660259e-05, "loss": 1.4195, "step": 119710 }, { "epoch": 5.47, "learning_rate": 2.2717286832349308e-05, "loss": 1.4853, "step": 119720 }, { "epoch": 5.47, "learning_rate": 2.2714998398096025e-05, "loss": 1.4129, "step": 119730 }, { "epoch": 5.47, "learning_rate": 2.271270996384274e-05, "loss": 1.3478, "step": 119740 }, { "epoch": 5.47, "learning_rate": 2.2710421529589457e-05, "loss": 1.4659, "step": 119750 }, { "epoch": 5.47, "learning_rate": 2.2708133095336174e-05, "loss": 1.5319, "step": 119760 }, { "epoch": 5.47, "learning_rate": 2.270584466108289e-05, "loss": 1.4856, "step": 119770 }, { "epoch": 5.47, "learning_rate": 2.2703556226829603e-05, "loss": 1.349, "step": 119780 }, { "epoch": 5.47, "learning_rate": 2.270126779257632e-05, "loss": 1.4912, "step": 119790 }, { "epoch": 5.47, "learning_rate": 2.2698979358323034e-05, "loss": 1.3971, "step": 119800 }, { "epoch": 5.47, "learning_rate": 2.2696690924069752e-05, "loss": 1.563, "step": 119810 }, { "epoch": 5.47, "learning_rate": 2.269440248981647e-05, "loss": 1.3113, "step": 119820 }, { "epoch": 5.47, "learning_rate": 2.2692114055563184e-05, "loss": 1.4558, "step": 119830 }, { "epoch": 5.47, "learning_rate": 2.26898256213099e-05, "loss": 1.3929, "step": 119840 }, { "epoch": 5.47, "learning_rate": 2.268753718705662e-05, "loss": 1.5071, "step": 119850 }, { "epoch": 5.47, "learning_rate": 2.2685248752803333e-05, "loss": 1.5428, "step": 119860 }, { "epoch": 5.47, "learning_rate": 2.2682960318550047e-05, "loss": 1.4971, "step": 119870 }, { "epoch": 5.47, "learning_rate": 2.2680671884296764e-05, "loss": 1.5456, "step": 119880 }, { "epoch": 5.47, "learning_rate": 2.2678383450043482e-05, "loss": 1.4406, "step": 119890 }, { "epoch": 5.47, "learning_rate": 2.2676095015790196e-05, "loss": 1.3487, "step": 119900 }, { "epoch": 5.48, "learning_rate": 2.2673806581536914e-05, "loss": 1.5566, "step": 119910 }, { "epoch": 5.48, "learning_rate": 2.267151814728363e-05, "loss": 1.4137, "step": 119920 }, { "epoch": 5.48, "learning_rate": 2.2669229713030345e-05, "loss": 1.52, "step": 119930 }, { "epoch": 5.48, "learning_rate": 2.2666941278777063e-05, "loss": 1.4076, "step": 119940 }, { "epoch": 5.48, "learning_rate": 2.266465284452378e-05, "loss": 1.5416, "step": 119950 }, { "epoch": 5.48, "learning_rate": 2.2662364410270494e-05, "loss": 1.4946, "step": 119960 }, { "epoch": 5.48, "learning_rate": 2.266007597601721e-05, "loss": 1.55, "step": 119970 }, { "epoch": 5.48, "learning_rate": 2.2657787541763926e-05, "loss": 1.6071, "step": 119980 }, { "epoch": 5.48, "learning_rate": 2.265549910751064e-05, "loss": 1.5186, "step": 119990 }, { "epoch": 5.48, "learning_rate": 2.2653210673257358e-05, "loss": 1.3128, "step": 120000 }, { "epoch": 5.48, "learning_rate": 2.2650922239004075e-05, "loss": 1.4104, "step": 120010 }, { "epoch": 5.48, "learning_rate": 2.264863380475079e-05, "loss": 1.4639, "step": 120020 }, { "epoch": 5.48, "learning_rate": 2.2646345370497507e-05, "loss": 1.4909, "step": 120030 }, { "epoch": 5.48, "learning_rate": 2.2644056936244224e-05, "loss": 1.6183, "step": 120040 }, { "epoch": 5.48, "learning_rate": 2.264176850199094e-05, "loss": 1.5214, "step": 120050 }, { "epoch": 5.48, "learning_rate": 2.2639480067737656e-05, "loss": 1.3421, "step": 120060 }, { "epoch": 5.48, "learning_rate": 2.263719163348437e-05, "loss": 1.3469, "step": 120070 }, { "epoch": 5.48, "learning_rate": 2.2634903199231088e-05, "loss": 1.5583, "step": 120080 }, { "epoch": 5.48, "learning_rate": 2.2632614764977802e-05, "loss": 1.4267, "step": 120090 }, { "epoch": 5.48, "learning_rate": 2.263032633072452e-05, "loss": 1.5224, "step": 120100 }, { "epoch": 5.48, "learning_rate": 2.2628037896471237e-05, "loss": 1.5126, "step": 120110 }, { "epoch": 5.48, "learning_rate": 2.262574946221795e-05, "loss": 1.4748, "step": 120120 }, { "epoch": 5.49, "learning_rate": 2.262346102796467e-05, "loss": 1.6566, "step": 120130 }, { "epoch": 5.49, "learning_rate": 2.2621172593711386e-05, "loss": 1.5288, "step": 120140 }, { "epoch": 5.49, "learning_rate": 2.26188841594581e-05, "loss": 1.4687, "step": 120150 }, { "epoch": 5.49, "learning_rate": 2.2616595725204818e-05, "loss": 1.5331, "step": 120160 }, { "epoch": 5.49, "learning_rate": 2.2614307290951532e-05, "loss": 1.538, "step": 120170 }, { "epoch": 5.49, "learning_rate": 2.2612018856698246e-05, "loss": 1.5949, "step": 120180 }, { "epoch": 5.49, "learning_rate": 2.2609730422444964e-05, "loss": 1.5101, "step": 120190 }, { "epoch": 5.49, "learning_rate": 2.260744198819168e-05, "loss": 1.5389, "step": 120200 }, { "epoch": 5.49, "learning_rate": 2.2605153553938395e-05, "loss": 1.4774, "step": 120210 }, { "epoch": 5.49, "learning_rate": 2.2602865119685113e-05, "loss": 1.4253, "step": 120220 }, { "epoch": 5.49, "learning_rate": 2.260057668543183e-05, "loss": 1.4413, "step": 120230 }, { "epoch": 5.49, "learning_rate": 2.2598288251178544e-05, "loss": 1.4108, "step": 120240 }, { "epoch": 5.49, "learning_rate": 2.2595999816925262e-05, "loss": 1.5765, "step": 120250 }, { "epoch": 5.49, "learning_rate": 2.259371138267198e-05, "loss": 1.51, "step": 120260 }, { "epoch": 5.49, "learning_rate": 2.259142294841869e-05, "loss": 1.368, "step": 120270 }, { "epoch": 5.49, "learning_rate": 2.2589134514165408e-05, "loss": 1.5388, "step": 120280 }, { "epoch": 5.49, "learning_rate": 2.2586846079912125e-05, "loss": 1.5947, "step": 120290 }, { "epoch": 5.49, "learning_rate": 2.258455764565884e-05, "loss": 1.5947, "step": 120300 }, { "epoch": 5.49, "learning_rate": 2.2582269211405557e-05, "loss": 1.4354, "step": 120310 }, { "epoch": 5.49, "learning_rate": 2.2579980777152274e-05, "loss": 1.5276, "step": 120320 }, { "epoch": 5.49, "learning_rate": 2.257769234289899e-05, "loss": 1.5908, "step": 120330 }, { "epoch": 5.5, "learning_rate": 2.2575403908645706e-05, "loss": 1.4418, "step": 120340 }, { "epoch": 5.5, "learning_rate": 2.2573115474392424e-05, "loss": 1.5136, "step": 120350 }, { "epoch": 5.5, "learning_rate": 2.2570827040139138e-05, "loss": 1.383, "step": 120360 }, { "epoch": 5.5, "learning_rate": 2.2568538605885852e-05, "loss": 1.576, "step": 120370 }, { "epoch": 5.5, "learning_rate": 2.256625017163257e-05, "loss": 1.4395, "step": 120380 }, { "epoch": 5.5, "learning_rate": 2.2563961737379287e-05, "loss": 1.5786, "step": 120390 }, { "epoch": 5.5, "learning_rate": 2.2561673303126e-05, "loss": 1.3181, "step": 120400 }, { "epoch": 5.5, "learning_rate": 2.255938486887272e-05, "loss": 1.4081, "step": 120410 }, { "epoch": 5.5, "learning_rate": 2.2557096434619436e-05, "loss": 1.425, "step": 120420 }, { "epoch": 5.5, "learning_rate": 2.255480800036615e-05, "loss": 1.5186, "step": 120430 }, { "epoch": 5.5, "learning_rate": 2.2552519566112868e-05, "loss": 1.6672, "step": 120440 }, { "epoch": 5.5, "learning_rate": 2.2550231131859585e-05, "loss": 1.551, "step": 120450 }, { "epoch": 5.5, "learning_rate": 2.25479426976063e-05, "loss": 1.5034, "step": 120460 }, { "epoch": 5.5, "learning_rate": 2.2545654263353013e-05, "loss": 1.3438, "step": 120470 }, { "epoch": 5.5, "learning_rate": 2.254336582909973e-05, "loss": 1.7601, "step": 120480 }, { "epoch": 5.5, "learning_rate": 2.2541077394846445e-05, "loss": 1.4837, "step": 120490 }, { "epoch": 5.5, "learning_rate": 2.2538788960593163e-05, "loss": 1.3086, "step": 120500 }, { "epoch": 5.5, "learning_rate": 2.253650052633988e-05, "loss": 1.5349, "step": 120510 }, { "epoch": 5.5, "learning_rate": 2.2534212092086594e-05, "loss": 1.4295, "step": 120520 }, { "epoch": 5.5, "learning_rate": 2.2531923657833312e-05, "loss": 1.3595, "step": 120530 }, { "epoch": 5.5, "learning_rate": 2.252963522358003e-05, "loss": 1.425, "step": 120540 }, { "epoch": 5.5, "learning_rate": 2.2527346789326743e-05, "loss": 1.3482, "step": 120550 }, { "epoch": 5.51, "learning_rate": 2.252505835507346e-05, "loss": 1.489, "step": 120560 }, { "epoch": 5.51, "learning_rate": 2.2522769920820175e-05, "loss": 1.5753, "step": 120570 }, { "epoch": 5.51, "learning_rate": 2.2520481486566893e-05, "loss": 1.4334, "step": 120580 }, { "epoch": 5.51, "learning_rate": 2.2518193052313607e-05, "loss": 1.5495, "step": 120590 }, { "epoch": 5.51, "learning_rate": 2.2515904618060324e-05, "loss": 1.4529, "step": 120600 }, { "epoch": 5.51, "learning_rate": 2.2513616183807042e-05, "loss": 1.3034, "step": 120610 }, { "epoch": 5.51, "learning_rate": 2.2511327749553756e-05, "loss": 1.2959, "step": 120620 }, { "epoch": 5.51, "learning_rate": 2.2509039315300473e-05, "loss": 1.4868, "step": 120630 }, { "epoch": 5.51, "learning_rate": 2.250675088104719e-05, "loss": 1.3687, "step": 120640 }, { "epoch": 5.51, "learning_rate": 2.2504462446793905e-05, "loss": 1.3462, "step": 120650 }, { "epoch": 5.51, "learning_rate": 2.250217401254062e-05, "loss": 1.6593, "step": 120660 }, { "epoch": 5.51, "learning_rate": 2.2499885578287337e-05, "loss": 1.442, "step": 120670 }, { "epoch": 5.51, "learning_rate": 2.249759714403405e-05, "loss": 1.5256, "step": 120680 }, { "epoch": 5.51, "learning_rate": 2.249530870978077e-05, "loss": 1.3867, "step": 120690 }, { "epoch": 5.51, "learning_rate": 2.2493020275527486e-05, "loss": 1.44, "step": 120700 }, { "epoch": 5.51, "learning_rate": 2.24907318412742e-05, "loss": 1.5647, "step": 120710 }, { "epoch": 5.51, "learning_rate": 2.2488443407020918e-05, "loss": 1.4552, "step": 120720 }, { "epoch": 5.51, "learning_rate": 2.2486154972767635e-05, "loss": 1.4593, "step": 120730 }, { "epoch": 5.51, "learning_rate": 2.248386653851435e-05, "loss": 1.5602, "step": 120740 }, { "epoch": 5.51, "learning_rate": 2.2481578104261067e-05, "loss": 1.3437, "step": 120750 }, { "epoch": 5.51, "learning_rate": 2.247928967000778e-05, "loss": 1.4157, "step": 120760 }, { "epoch": 5.51, "learning_rate": 2.24770012357545e-05, "loss": 1.5449, "step": 120770 }, { "epoch": 5.52, "learning_rate": 2.2474712801501213e-05, "loss": 1.5381, "step": 120780 }, { "epoch": 5.52, "learning_rate": 2.247242436724793e-05, "loss": 1.4557, "step": 120790 }, { "epoch": 5.52, "learning_rate": 2.2470135932994644e-05, "loss": 1.4762, "step": 120800 }, { "epoch": 5.52, "learning_rate": 2.2467847498741362e-05, "loss": 1.404, "step": 120810 }, { "epoch": 5.52, "learning_rate": 2.246555906448808e-05, "loss": 1.3011, "step": 120820 }, { "epoch": 5.52, "learning_rate": 2.2463270630234793e-05, "loss": 1.4272, "step": 120830 }, { "epoch": 5.52, "learning_rate": 2.246098219598151e-05, "loss": 1.3883, "step": 120840 }, { "epoch": 5.52, "learning_rate": 2.245869376172823e-05, "loss": 1.4239, "step": 120850 }, { "epoch": 5.52, "learning_rate": 2.2456405327474943e-05, "loss": 1.5633, "step": 120860 }, { "epoch": 5.52, "learning_rate": 2.2454116893221657e-05, "loss": 1.4979, "step": 120870 }, { "epoch": 5.52, "learning_rate": 2.2451828458968374e-05, "loss": 1.5277, "step": 120880 }, { "epoch": 5.52, "learning_rate": 2.2449540024715092e-05, "loss": 1.436, "step": 120890 }, { "epoch": 5.52, "learning_rate": 2.2447251590461806e-05, "loss": 1.4616, "step": 120900 }, { "epoch": 5.52, "learning_rate": 2.2444963156208523e-05, "loss": 1.5522, "step": 120910 }, { "epoch": 5.52, "learning_rate": 2.244267472195524e-05, "loss": 1.7115, "step": 120920 }, { "epoch": 5.52, "learning_rate": 2.2440386287701955e-05, "loss": 1.4799, "step": 120930 }, { "epoch": 5.52, "learning_rate": 2.2438097853448673e-05, "loss": 1.5387, "step": 120940 }, { "epoch": 5.52, "learning_rate": 2.243580941919539e-05, "loss": 1.5218, "step": 120950 }, { "epoch": 5.52, "learning_rate": 2.24335209849421e-05, "loss": 1.5018, "step": 120960 }, { "epoch": 5.52, "learning_rate": 2.243123255068882e-05, "loss": 1.4532, "step": 120970 }, { "epoch": 5.52, "learning_rate": 2.2428944116435536e-05, "loss": 1.4914, "step": 120980 }, { "epoch": 5.52, "learning_rate": 2.242665568218225e-05, "loss": 1.4527, "step": 120990 }, { "epoch": 5.53, "learning_rate": 2.2424367247928968e-05, "loss": 1.361, "step": 121000 }, { "epoch": 5.53, "learning_rate": 2.2422078813675685e-05, "loss": 1.3557, "step": 121010 }, { "epoch": 5.53, "learning_rate": 2.24197903794224e-05, "loss": 1.4108, "step": 121020 }, { "epoch": 5.53, "learning_rate": 2.2417501945169117e-05, "loss": 1.4209, "step": 121030 }, { "epoch": 5.53, "learning_rate": 2.2415213510915834e-05, "loss": 1.518, "step": 121040 }, { "epoch": 5.53, "learning_rate": 2.241292507666255e-05, "loss": 1.5158, "step": 121050 }, { "epoch": 5.53, "learning_rate": 2.2410636642409263e-05, "loss": 1.4657, "step": 121060 }, { "epoch": 5.53, "learning_rate": 2.240834820815598e-05, "loss": 1.5254, "step": 121070 }, { "epoch": 5.53, "learning_rate": 2.2406059773902698e-05, "loss": 1.4978, "step": 121080 }, { "epoch": 5.53, "learning_rate": 2.2403771339649412e-05, "loss": 1.5405, "step": 121090 }, { "epoch": 5.53, "learning_rate": 2.240148290539613e-05, "loss": 1.5141, "step": 121100 }, { "epoch": 5.53, "learning_rate": 2.2399194471142847e-05, "loss": 1.3696, "step": 121110 }, { "epoch": 5.53, "learning_rate": 2.239690603688956e-05, "loss": 1.3829, "step": 121120 }, { "epoch": 5.53, "learning_rate": 2.239461760263628e-05, "loss": 1.5844, "step": 121130 }, { "epoch": 5.53, "learning_rate": 2.2392329168382996e-05, "loss": 1.5248, "step": 121140 }, { "epoch": 5.53, "learning_rate": 2.239004073412971e-05, "loss": 1.4107, "step": 121150 }, { "epoch": 5.53, "learning_rate": 2.2387752299876424e-05, "loss": 1.5588, "step": 121160 }, { "epoch": 5.53, "learning_rate": 2.2385463865623142e-05, "loss": 1.4949, "step": 121170 }, { "epoch": 5.53, "learning_rate": 2.2383175431369856e-05, "loss": 1.4733, "step": 121180 }, { "epoch": 5.53, "learning_rate": 2.2380886997116573e-05, "loss": 1.4344, "step": 121190 }, { "epoch": 5.53, "learning_rate": 2.237859856286329e-05, "loss": 1.6131, "step": 121200 }, { "epoch": 5.53, "learning_rate": 2.2376310128610005e-05, "loss": 1.3042, "step": 121210 }, { "epoch": 5.54, "learning_rate": 2.2374021694356723e-05, "loss": 1.4456, "step": 121220 }, { "epoch": 5.54, "learning_rate": 2.237173326010344e-05, "loss": 1.4308, "step": 121230 }, { "epoch": 5.54, "learning_rate": 2.2369444825850154e-05, "loss": 1.6048, "step": 121240 }, { "epoch": 5.54, "learning_rate": 2.2367156391596872e-05, "loss": 1.3867, "step": 121250 }, { "epoch": 5.54, "learning_rate": 2.2364867957343586e-05, "loss": 1.4848, "step": 121260 }, { "epoch": 5.54, "learning_rate": 2.2362579523090303e-05, "loss": 1.6321, "step": 121270 }, { "epoch": 5.54, "learning_rate": 2.2360291088837018e-05, "loss": 1.5569, "step": 121280 }, { "epoch": 5.54, "learning_rate": 2.2358002654583735e-05, "loss": 1.5226, "step": 121290 }, { "epoch": 5.54, "learning_rate": 2.2355714220330453e-05, "loss": 1.3954, "step": 121300 }, { "epoch": 5.54, "learning_rate": 2.2353425786077167e-05, "loss": 1.5201, "step": 121310 }, { "epoch": 5.54, "learning_rate": 2.2351137351823884e-05, "loss": 1.4104, "step": 121320 }, { "epoch": 5.54, "learning_rate": 2.2348848917570602e-05, "loss": 1.4794, "step": 121330 }, { "epoch": 5.54, "learning_rate": 2.2346560483317316e-05, "loss": 1.4235, "step": 121340 }, { "epoch": 5.54, "learning_rate": 2.2344272049064033e-05, "loss": 1.4223, "step": 121350 }, { "epoch": 5.54, "learning_rate": 2.2341983614810748e-05, "loss": 1.4252, "step": 121360 }, { "epoch": 5.54, "learning_rate": 2.233969518055746e-05, "loss": 1.5637, "step": 121370 }, { "epoch": 5.54, "learning_rate": 2.233740674630418e-05, "loss": 1.4889, "step": 121380 }, { "epoch": 5.54, "learning_rate": 2.2335118312050897e-05, "loss": 1.5914, "step": 121390 }, { "epoch": 5.54, "learning_rate": 2.233282987779761e-05, "loss": 1.4946, "step": 121400 }, { "epoch": 5.54, "learning_rate": 2.233054144354433e-05, "loss": 1.5717, "step": 121410 }, { "epoch": 5.54, "learning_rate": 2.2328253009291046e-05, "loss": 1.5603, "step": 121420 }, { "epoch": 5.54, "learning_rate": 2.232596457503776e-05, "loss": 1.535, "step": 121430 }, { "epoch": 5.55, "learning_rate": 2.2323676140784478e-05, "loss": 1.4017, "step": 121440 }, { "epoch": 5.55, "learning_rate": 2.232138770653119e-05, "loss": 1.5578, "step": 121450 }, { "epoch": 5.55, "learning_rate": 2.2319099272277906e-05, "loss": 1.4914, "step": 121460 }, { "epoch": 5.55, "learning_rate": 2.2316810838024623e-05, "loss": 1.4977, "step": 121470 }, { "epoch": 5.55, "learning_rate": 2.231452240377134e-05, "loss": 1.5051, "step": 121480 }, { "epoch": 5.55, "learning_rate": 2.2312233969518055e-05, "loss": 1.7876, "step": 121490 }, { "epoch": 5.55, "learning_rate": 2.2309945535264772e-05, "loss": 1.5814, "step": 121500 }, { "epoch": 5.55, "learning_rate": 2.230765710101149e-05, "loss": 1.3797, "step": 121510 }, { "epoch": 5.55, "learning_rate": 2.2305368666758204e-05, "loss": 1.4495, "step": 121520 }, { "epoch": 5.55, "learning_rate": 2.230308023250492e-05, "loss": 1.3949, "step": 121530 }, { "epoch": 5.55, "learning_rate": 2.230079179825164e-05, "loss": 1.5012, "step": 121540 }, { "epoch": 5.55, "learning_rate": 2.2298503363998353e-05, "loss": 1.401, "step": 121550 }, { "epoch": 5.55, "learning_rate": 2.2296214929745067e-05, "loss": 1.3561, "step": 121560 }, { "epoch": 5.55, "learning_rate": 2.2293926495491785e-05, "loss": 1.4357, "step": 121570 }, { "epoch": 5.55, "learning_rate": 2.2291638061238503e-05, "loss": 1.4409, "step": 121580 }, { "epoch": 5.55, "learning_rate": 2.2289349626985217e-05, "loss": 1.4964, "step": 121590 }, { "epoch": 5.55, "learning_rate": 2.2287061192731934e-05, "loss": 1.732, "step": 121600 }, { "epoch": 5.55, "learning_rate": 2.228477275847865e-05, "loss": 1.3443, "step": 121610 }, { "epoch": 5.55, "learning_rate": 2.2282484324225366e-05, "loss": 1.441, "step": 121620 }, { "epoch": 5.55, "learning_rate": 2.2280195889972083e-05, "loss": 1.5876, "step": 121630 }, { "epoch": 5.55, "learning_rate": 2.22779074557188e-05, "loss": 1.5129, "step": 121640 }, { "epoch": 5.55, "learning_rate": 2.227561902146551e-05, "loss": 1.5232, "step": 121650 }, { "epoch": 5.56, "learning_rate": 2.227333058721223e-05, "loss": 1.6508, "step": 121660 }, { "epoch": 5.56, "learning_rate": 2.2271042152958947e-05, "loss": 1.5395, "step": 121670 }, { "epoch": 5.56, "learning_rate": 2.226875371870566e-05, "loss": 1.4509, "step": 121680 }, { "epoch": 5.56, "learning_rate": 2.226646528445238e-05, "loss": 1.3653, "step": 121690 }, { "epoch": 5.56, "learning_rate": 2.2264176850199096e-05, "loss": 1.3241, "step": 121700 }, { "epoch": 5.56, "learning_rate": 2.226188841594581e-05, "loss": 1.4352, "step": 121710 }, { "epoch": 5.56, "learning_rate": 2.2259599981692527e-05, "loss": 1.5682, "step": 121720 }, { "epoch": 5.56, "learning_rate": 2.2257311547439245e-05, "loss": 1.3991, "step": 121730 }, { "epoch": 5.56, "learning_rate": 2.225502311318596e-05, "loss": 1.3127, "step": 121740 }, { "epoch": 5.56, "learning_rate": 2.2252734678932673e-05, "loss": 1.5043, "step": 121750 }, { "epoch": 5.56, "learning_rate": 2.225044624467939e-05, "loss": 1.4982, "step": 121760 }, { "epoch": 5.56, "learning_rate": 2.224815781042611e-05, "loss": 1.3047, "step": 121770 }, { "epoch": 5.56, "learning_rate": 2.2245869376172822e-05, "loss": 1.4343, "step": 121780 }, { "epoch": 5.56, "learning_rate": 2.224358094191954e-05, "loss": 1.6952, "step": 121790 }, { "epoch": 5.56, "learning_rate": 2.2241292507666257e-05, "loss": 1.3389, "step": 121800 }, { "epoch": 5.56, "learning_rate": 2.223900407341297e-05, "loss": 1.4322, "step": 121810 }, { "epoch": 5.56, "learning_rate": 2.223671563915969e-05, "loss": 1.5984, "step": 121820 }, { "epoch": 5.56, "learning_rate": 2.2234427204906407e-05, "loss": 1.5351, "step": 121830 }, { "epoch": 5.56, "learning_rate": 2.223213877065312e-05, "loss": 1.4486, "step": 121840 }, { "epoch": 5.56, "learning_rate": 2.2229850336399835e-05, "loss": 1.4932, "step": 121850 }, { "epoch": 5.56, "learning_rate": 2.2227561902146552e-05, "loss": 1.4385, "step": 121860 }, { "epoch": 5.56, "learning_rate": 2.2225273467893267e-05, "loss": 1.6211, "step": 121870 }, { "epoch": 5.57, "learning_rate": 2.2222985033639984e-05, "loss": 1.47, "step": 121880 }, { "epoch": 5.57, "learning_rate": 2.22206965993867e-05, "loss": 1.3981, "step": 121890 }, { "epoch": 5.57, "learning_rate": 2.2218408165133416e-05, "loss": 1.3898, "step": 121900 }, { "epoch": 5.57, "learning_rate": 2.2216119730880133e-05, "loss": 1.4405, "step": 121910 }, { "epoch": 5.57, "learning_rate": 2.221383129662685e-05, "loss": 1.3981, "step": 121920 }, { "epoch": 5.57, "learning_rate": 2.2211542862373565e-05, "loss": 1.4791, "step": 121930 }, { "epoch": 5.57, "learning_rate": 2.2209254428120282e-05, "loss": 1.3545, "step": 121940 }, { "epoch": 5.57, "learning_rate": 2.2206965993866997e-05, "loss": 1.5272, "step": 121950 }, { "epoch": 5.57, "learning_rate": 2.2204677559613714e-05, "loss": 1.5168, "step": 121960 }, { "epoch": 5.57, "learning_rate": 2.2202389125360428e-05, "loss": 1.4056, "step": 121970 }, { "epoch": 5.57, "learning_rate": 2.2200100691107146e-05, "loss": 1.5576, "step": 121980 }, { "epoch": 5.57, "learning_rate": 2.219781225685386e-05, "loss": 1.4942, "step": 121990 }, { "epoch": 5.57, "learning_rate": 2.2195523822600577e-05, "loss": 1.5588, "step": 122000 }, { "epoch": 5.57, "learning_rate": 2.2193235388347295e-05, "loss": 1.4717, "step": 122010 }, { "epoch": 5.57, "learning_rate": 2.219094695409401e-05, "loss": 1.3845, "step": 122020 }, { "epoch": 5.57, "learning_rate": 2.2188658519840727e-05, "loss": 1.5563, "step": 122030 }, { "epoch": 5.57, "learning_rate": 2.2186370085587444e-05, "loss": 1.6373, "step": 122040 }, { "epoch": 5.57, "learning_rate": 2.2184081651334158e-05, "loss": 1.397, "step": 122050 }, { "epoch": 5.57, "learning_rate": 2.2181793217080872e-05, "loss": 1.5315, "step": 122060 }, { "epoch": 5.57, "learning_rate": 2.217950478282759e-05, "loss": 1.5419, "step": 122070 }, { "epoch": 5.57, "learning_rate": 2.2177216348574307e-05, "loss": 1.4087, "step": 122080 }, { "epoch": 5.57, "learning_rate": 2.217492791432102e-05, "loss": 1.4026, "step": 122090 }, { "epoch": 5.58, "learning_rate": 2.217263948006774e-05, "loss": 1.4613, "step": 122100 }, { "epoch": 5.58, "learning_rate": 2.2170351045814457e-05, "loss": 1.5486, "step": 122110 }, { "epoch": 5.58, "learning_rate": 2.216806261156117e-05, "loss": 1.4111, "step": 122120 }, { "epoch": 5.58, "learning_rate": 2.2165774177307888e-05, "loss": 1.4196, "step": 122130 }, { "epoch": 5.58, "learning_rate": 2.2163485743054606e-05, "loss": 1.6851, "step": 122140 }, { "epoch": 5.58, "learning_rate": 2.2161197308801317e-05, "loss": 1.3861, "step": 122150 }, { "epoch": 5.58, "learning_rate": 2.2158908874548034e-05, "loss": 1.3176, "step": 122160 }, { "epoch": 5.58, "learning_rate": 2.215662044029475e-05, "loss": 1.417, "step": 122170 }, { "epoch": 5.58, "learning_rate": 2.2154332006041466e-05, "loss": 1.5077, "step": 122180 }, { "epoch": 5.58, "learning_rate": 2.2152043571788183e-05, "loss": 1.3287, "step": 122190 }, { "epoch": 5.58, "learning_rate": 2.21497551375349e-05, "loss": 1.4383, "step": 122200 }, { "epoch": 5.58, "learning_rate": 2.2147466703281615e-05, "loss": 1.4811, "step": 122210 }, { "epoch": 5.58, "learning_rate": 2.2145178269028332e-05, "loss": 1.5138, "step": 122220 }, { "epoch": 5.58, "learning_rate": 2.214288983477505e-05, "loss": 1.387, "step": 122230 }, { "epoch": 5.58, "learning_rate": 2.2140601400521764e-05, "loss": 1.2658, "step": 122240 }, { "epoch": 5.58, "learning_rate": 2.2138312966268478e-05, "loss": 1.4895, "step": 122250 }, { "epoch": 5.58, "learning_rate": 2.2136024532015196e-05, "loss": 1.5497, "step": 122260 }, { "epoch": 5.58, "learning_rate": 2.2133736097761913e-05, "loss": 1.5144, "step": 122270 }, { "epoch": 5.58, "learning_rate": 2.2131447663508627e-05, "loss": 1.4178, "step": 122280 }, { "epoch": 5.58, "learning_rate": 2.2129159229255345e-05, "loss": 1.3445, "step": 122290 }, { "epoch": 5.58, "learning_rate": 2.2126870795002062e-05, "loss": 1.4836, "step": 122300 }, { "epoch": 5.58, "learning_rate": 2.2124582360748777e-05, "loss": 1.3922, "step": 122310 }, { "epoch": 5.59, "learning_rate": 2.2122293926495494e-05, "loss": 1.4811, "step": 122320 }, { "epoch": 5.59, "learning_rate": 2.212000549224221e-05, "loss": 1.4028, "step": 122330 }, { "epoch": 5.59, "learning_rate": 2.2117717057988922e-05, "loss": 1.3681, "step": 122340 }, { "epoch": 5.59, "learning_rate": 2.211542862373564e-05, "loss": 1.4909, "step": 122350 }, { "epoch": 5.59, "learning_rate": 2.2113140189482357e-05, "loss": 1.5816, "step": 122360 }, { "epoch": 5.59, "learning_rate": 2.211085175522907e-05, "loss": 1.405, "step": 122370 }, { "epoch": 5.59, "learning_rate": 2.210856332097579e-05, "loss": 1.3721, "step": 122380 }, { "epoch": 5.59, "learning_rate": 2.2106274886722507e-05, "loss": 1.3689, "step": 122390 }, { "epoch": 5.59, "learning_rate": 2.210398645246922e-05, "loss": 1.4806, "step": 122400 }, { "epoch": 5.59, "learning_rate": 2.2101698018215938e-05, "loss": 1.3142, "step": 122410 }, { "epoch": 5.59, "learning_rate": 2.2099409583962656e-05, "loss": 1.5736, "step": 122420 }, { "epoch": 5.59, "learning_rate": 2.209712114970937e-05, "loss": 1.3897, "step": 122430 }, { "epoch": 5.59, "learning_rate": 2.2094832715456084e-05, "loss": 1.4641, "step": 122440 }, { "epoch": 5.59, "learning_rate": 2.20925442812028e-05, "loss": 1.4744, "step": 122450 }, { "epoch": 5.59, "learning_rate": 2.209025584694952e-05, "loss": 1.4834, "step": 122460 }, { "epoch": 5.59, "learning_rate": 2.2087967412696233e-05, "loss": 1.3684, "step": 122470 }, { "epoch": 5.59, "learning_rate": 2.208567897844295e-05, "loss": 1.4304, "step": 122480 }, { "epoch": 5.59, "learning_rate": 2.2083390544189668e-05, "loss": 1.4132, "step": 122490 }, { "epoch": 5.59, "learning_rate": 2.2081102109936382e-05, "loss": 1.3871, "step": 122500 }, { "epoch": 5.59, "learning_rate": 2.20788136756831e-05, "loss": 1.4542, "step": 122510 }, { "epoch": 5.59, "learning_rate": 2.2076525241429814e-05, "loss": 1.5946, "step": 122520 }, { "epoch": 5.6, "learning_rate": 2.207423680717653e-05, "loss": 1.5183, "step": 122530 }, { "epoch": 5.6, "learning_rate": 2.2071948372923246e-05, "loss": 1.4654, "step": 122540 }, { "epoch": 5.6, "learning_rate": 2.2069659938669963e-05, "loss": 1.6101, "step": 122550 }, { "epoch": 5.6, "learning_rate": 2.2067371504416677e-05, "loss": 1.6236, "step": 122560 }, { "epoch": 5.6, "learning_rate": 2.2065083070163395e-05, "loss": 1.4341, "step": 122570 }, { "epoch": 5.6, "learning_rate": 2.2062794635910112e-05, "loss": 1.4472, "step": 122580 }, { "epoch": 5.6, "learning_rate": 2.2060506201656827e-05, "loss": 1.4817, "step": 122590 }, { "epoch": 5.6, "learning_rate": 2.2058217767403544e-05, "loss": 1.624, "step": 122600 }, { "epoch": 5.6, "learning_rate": 2.205592933315026e-05, "loss": 1.5209, "step": 122610 }, { "epoch": 5.6, "learning_rate": 2.2053640898896976e-05, "loss": 1.4601, "step": 122620 }, { "epoch": 5.6, "learning_rate": 2.2051352464643693e-05, "loss": 1.5749, "step": 122630 }, { "epoch": 5.6, "learning_rate": 2.2049064030390407e-05, "loss": 1.5889, "step": 122640 }, { "epoch": 5.6, "learning_rate": 2.204677559613712e-05, "loss": 1.5507, "step": 122650 }, { "epoch": 5.6, "learning_rate": 2.204448716188384e-05, "loss": 1.3809, "step": 122660 }, { "epoch": 5.6, "learning_rate": 2.2042198727630557e-05, "loss": 1.3948, "step": 122670 }, { "epoch": 5.6, "learning_rate": 2.203991029337727e-05, "loss": 1.5727, "step": 122680 }, { "epoch": 5.6, "learning_rate": 2.2037621859123988e-05, "loss": 1.4645, "step": 122690 }, { "epoch": 5.6, "learning_rate": 2.2035333424870706e-05, "loss": 1.5322, "step": 122700 }, { "epoch": 5.6, "learning_rate": 2.203304499061742e-05, "loss": 1.46, "step": 122710 }, { "epoch": 5.6, "learning_rate": 2.2030756556364137e-05, "loss": 1.5841, "step": 122720 }, { "epoch": 5.6, "learning_rate": 2.2028468122110855e-05, "loss": 1.4391, "step": 122730 }, { "epoch": 5.6, "learning_rate": 2.202617968785757e-05, "loss": 1.6576, "step": 122740 }, { "epoch": 5.61, "learning_rate": 2.2023891253604283e-05, "loss": 1.4715, "step": 122750 }, { "epoch": 5.61, "learning_rate": 2.2021602819351e-05, "loss": 1.4629, "step": 122760 }, { "epoch": 5.61, "learning_rate": 2.2019314385097718e-05, "loss": 1.4032, "step": 122770 }, { "epoch": 5.61, "learning_rate": 2.2017025950844432e-05, "loss": 1.4951, "step": 122780 }, { "epoch": 5.61, "learning_rate": 2.201473751659115e-05, "loss": 1.2805, "step": 122790 }, { "epoch": 5.61, "learning_rate": 2.2012449082337867e-05, "loss": 1.3284, "step": 122800 }, { "epoch": 5.61, "learning_rate": 2.201016064808458e-05, "loss": 1.3434, "step": 122810 }, { "epoch": 5.61, "learning_rate": 2.20078722138313e-05, "loss": 1.5822, "step": 122820 }, { "epoch": 5.61, "learning_rate": 2.2005583779578017e-05, "loss": 1.5395, "step": 122830 }, { "epoch": 5.61, "learning_rate": 2.2003295345324727e-05, "loss": 1.4635, "step": 122840 }, { "epoch": 5.61, "learning_rate": 2.2001006911071445e-05, "loss": 1.4523, "step": 122850 }, { "epoch": 5.61, "learning_rate": 2.1998718476818162e-05, "loss": 1.505, "step": 122860 }, { "epoch": 5.61, "learning_rate": 2.1996430042564876e-05, "loss": 1.5329, "step": 122870 }, { "epoch": 5.61, "learning_rate": 2.1994141608311594e-05, "loss": 1.3964, "step": 122880 }, { "epoch": 5.61, "learning_rate": 2.199185317405831e-05, "loss": 1.478, "step": 122890 }, { "epoch": 5.61, "learning_rate": 2.1989564739805026e-05, "loss": 1.5104, "step": 122900 }, { "epoch": 5.61, "learning_rate": 2.1987276305551743e-05, "loss": 1.5006, "step": 122910 }, { "epoch": 5.61, "learning_rate": 2.198498787129846e-05, "loss": 1.5355, "step": 122920 }, { "epoch": 5.61, "learning_rate": 2.1982699437045175e-05, "loss": 1.5339, "step": 122930 }, { "epoch": 5.61, "learning_rate": 2.198041100279189e-05, "loss": 1.6966, "step": 122940 }, { "epoch": 5.61, "learning_rate": 2.1978122568538606e-05, "loss": 1.4374, "step": 122950 }, { "epoch": 5.61, "learning_rate": 2.1975834134285324e-05, "loss": 1.4227, "step": 122960 }, { "epoch": 5.62, "learning_rate": 2.1973545700032038e-05, "loss": 1.5281, "step": 122970 }, { "epoch": 5.62, "learning_rate": 2.1971257265778756e-05, "loss": 1.444, "step": 122980 }, { "epoch": 5.62, "learning_rate": 2.1968968831525473e-05, "loss": 1.5647, "step": 122990 }, { "epoch": 5.62, "learning_rate": 2.1966680397272187e-05, "loss": 1.6876, "step": 123000 }, { "epoch": 5.62, "learning_rate": 2.1964391963018905e-05, "loss": 1.4704, "step": 123010 }, { "epoch": 5.62, "learning_rate": 2.1962103528765622e-05, "loss": 1.4648, "step": 123020 }, { "epoch": 5.62, "learning_rate": 2.1959815094512336e-05, "loss": 1.3894, "step": 123030 }, { "epoch": 5.62, "learning_rate": 2.195752666025905e-05, "loss": 1.6229, "step": 123040 }, { "epoch": 5.62, "learning_rate": 2.1955238226005768e-05, "loss": 1.5325, "step": 123050 }, { "epoch": 5.62, "learning_rate": 2.1952949791752482e-05, "loss": 1.4993, "step": 123060 }, { "epoch": 5.62, "learning_rate": 2.19506613574992e-05, "loss": 1.5274, "step": 123070 }, { "epoch": 5.62, "learning_rate": 2.1948372923245917e-05, "loss": 1.4344, "step": 123080 }, { "epoch": 5.62, "learning_rate": 2.194608448899263e-05, "loss": 1.4144, "step": 123090 }, { "epoch": 5.62, "learning_rate": 2.194379605473935e-05, "loss": 1.4591, "step": 123100 }, { "epoch": 5.62, "learning_rate": 2.1941507620486066e-05, "loss": 1.4673, "step": 123110 }, { "epoch": 5.62, "learning_rate": 2.193921918623278e-05, "loss": 1.6137, "step": 123120 }, { "epoch": 5.62, "learning_rate": 2.1936930751979495e-05, "loss": 1.6554, "step": 123130 }, { "epoch": 5.62, "learning_rate": 2.1934642317726212e-05, "loss": 1.4157, "step": 123140 }, { "epoch": 5.62, "learning_rate": 2.1932353883472926e-05, "loss": 1.4981, "step": 123150 }, { "epoch": 5.62, "learning_rate": 2.1930065449219644e-05, "loss": 1.265, "step": 123160 }, { "epoch": 5.62, "learning_rate": 2.192777701496636e-05, "loss": 1.4089, "step": 123170 }, { "epoch": 5.62, "learning_rate": 2.1925488580713076e-05, "loss": 1.5855, "step": 123180 }, { "epoch": 5.63, "learning_rate": 2.1923200146459793e-05, "loss": 1.4261, "step": 123190 }, { "epoch": 5.63, "learning_rate": 2.192091171220651e-05, "loss": 1.5701, "step": 123200 }, { "epoch": 5.63, "learning_rate": 2.1918623277953225e-05, "loss": 1.4665, "step": 123210 }, { "epoch": 5.63, "learning_rate": 2.1916334843699942e-05, "loss": 1.4393, "step": 123220 }, { "epoch": 5.63, "learning_rate": 2.1914046409446656e-05, "loss": 1.3041, "step": 123230 }, { "epoch": 5.63, "learning_rate": 2.1911757975193374e-05, "loss": 1.5751, "step": 123240 }, { "epoch": 5.63, "learning_rate": 2.1909469540940088e-05, "loss": 1.3484, "step": 123250 }, { "epoch": 5.63, "learning_rate": 2.1907181106686806e-05, "loss": 1.6717, "step": 123260 }, { "epoch": 5.63, "learning_rate": 2.1904892672433523e-05, "loss": 1.3083, "step": 123270 }, { "epoch": 5.63, "learning_rate": 2.1902604238180237e-05, "loss": 1.6314, "step": 123280 }, { "epoch": 5.63, "learning_rate": 2.1900315803926955e-05, "loss": 1.3311, "step": 123290 }, { "epoch": 5.63, "learning_rate": 2.1898027369673672e-05, "loss": 1.507, "step": 123300 }, { "epoch": 5.63, "learning_rate": 2.1895738935420386e-05, "loss": 1.4354, "step": 123310 }, { "epoch": 5.63, "learning_rate": 2.1893450501167104e-05, "loss": 1.4279, "step": 123320 }, { "epoch": 5.63, "learning_rate": 2.1891162066913818e-05, "loss": 1.5933, "step": 123330 }, { "epoch": 5.63, "learning_rate": 2.1888873632660532e-05, "loss": 1.5028, "step": 123340 }, { "epoch": 5.63, "learning_rate": 2.188658519840725e-05, "loss": 1.5369, "step": 123350 }, { "epoch": 5.63, "learning_rate": 2.1884296764153967e-05, "loss": 1.4861, "step": 123360 }, { "epoch": 5.63, "learning_rate": 2.188200832990068e-05, "loss": 1.6656, "step": 123370 }, { "epoch": 5.63, "learning_rate": 2.18797198956474e-05, "loss": 1.485, "step": 123380 }, { "epoch": 5.63, "learning_rate": 2.1877431461394116e-05, "loss": 1.5384, "step": 123390 }, { "epoch": 5.63, "learning_rate": 2.187514302714083e-05, "loss": 1.3386, "step": 123400 }, { "epoch": 5.64, "learning_rate": 2.1872854592887548e-05, "loss": 1.7104, "step": 123410 }, { "epoch": 5.64, "learning_rate": 2.1870566158634266e-05, "loss": 1.4174, "step": 123420 }, { "epoch": 5.64, "learning_rate": 2.186827772438098e-05, "loss": 1.4855, "step": 123430 }, { "epoch": 5.64, "learning_rate": 2.1865989290127694e-05, "loss": 1.6316, "step": 123440 }, { "epoch": 5.64, "learning_rate": 2.186370085587441e-05, "loss": 1.5003, "step": 123450 }, { "epoch": 5.64, "learning_rate": 2.186141242162113e-05, "loss": 1.4246, "step": 123460 }, { "epoch": 5.64, "learning_rate": 2.1859123987367843e-05, "loss": 1.5218, "step": 123470 }, { "epoch": 5.64, "learning_rate": 2.185683555311456e-05, "loss": 1.3077, "step": 123480 }, { "epoch": 5.64, "learning_rate": 2.1854547118861278e-05, "loss": 1.466, "step": 123490 }, { "epoch": 5.64, "learning_rate": 2.1852258684607992e-05, "loss": 1.4128, "step": 123500 }, { "epoch": 5.64, "learning_rate": 2.184997025035471e-05, "loss": 1.4154, "step": 123510 }, { "epoch": 5.64, "learning_rate": 2.1847681816101427e-05, "loss": 1.5034, "step": 123520 }, { "epoch": 5.64, "learning_rate": 2.1845393381848138e-05, "loss": 1.3844, "step": 123530 }, { "epoch": 5.64, "learning_rate": 2.1843104947594856e-05, "loss": 1.3909, "step": 123540 }, { "epoch": 5.64, "learning_rate": 2.1840816513341573e-05, "loss": 1.5213, "step": 123550 }, { "epoch": 5.64, "learning_rate": 2.1838528079088287e-05, "loss": 1.4855, "step": 123560 }, { "epoch": 5.64, "learning_rate": 2.1836239644835005e-05, "loss": 1.3969, "step": 123570 }, { "epoch": 5.64, "learning_rate": 2.1833951210581722e-05, "loss": 1.3793, "step": 123580 }, { "epoch": 5.64, "learning_rate": 2.1831662776328436e-05, "loss": 1.4637, "step": 123590 }, { "epoch": 5.64, "learning_rate": 2.1829374342075154e-05, "loss": 1.3516, "step": 123600 }, { "epoch": 5.64, "learning_rate": 2.182708590782187e-05, "loss": 1.3426, "step": 123610 }, { "epoch": 5.64, "learning_rate": 2.1824797473568586e-05, "loss": 1.6048, "step": 123620 }, { "epoch": 5.65, "learning_rate": 2.18225090393153e-05, "loss": 1.4517, "step": 123630 }, { "epoch": 5.65, "learning_rate": 2.1820220605062017e-05, "loss": 1.4577, "step": 123640 }, { "epoch": 5.65, "learning_rate": 2.1817932170808735e-05, "loss": 1.4046, "step": 123650 }, { "epoch": 5.65, "learning_rate": 2.181564373655545e-05, "loss": 1.4224, "step": 123660 }, { "epoch": 5.65, "learning_rate": 2.1813355302302166e-05, "loss": 1.4075, "step": 123670 }, { "epoch": 5.65, "learning_rate": 2.1811066868048884e-05, "loss": 1.4714, "step": 123680 }, { "epoch": 5.65, "learning_rate": 2.1808778433795598e-05, "loss": 1.3554, "step": 123690 }, { "epoch": 5.65, "learning_rate": 2.1806489999542316e-05, "loss": 1.4079, "step": 123700 }, { "epoch": 5.65, "learning_rate": 2.180420156528903e-05, "loss": 1.4323, "step": 123710 }, { "epoch": 5.65, "learning_rate": 2.1801913131035747e-05, "loss": 1.6612, "step": 123720 }, { "epoch": 5.65, "learning_rate": 2.179962469678246e-05, "loss": 1.3352, "step": 123730 }, { "epoch": 5.65, "learning_rate": 2.179733626252918e-05, "loss": 1.3909, "step": 123740 }, { "epoch": 5.65, "learning_rate": 2.1795047828275893e-05, "loss": 1.7815, "step": 123750 }, { "epoch": 5.65, "learning_rate": 2.179275939402261e-05, "loss": 1.5188, "step": 123760 }, { "epoch": 5.65, "learning_rate": 2.1790470959769328e-05, "loss": 1.4108, "step": 123770 }, { "epoch": 5.65, "learning_rate": 2.1788182525516042e-05, "loss": 1.5282, "step": 123780 }, { "epoch": 5.65, "learning_rate": 2.178589409126276e-05, "loss": 1.4715, "step": 123790 }, { "epoch": 5.65, "learning_rate": 2.1783605657009477e-05, "loss": 1.4912, "step": 123800 }, { "epoch": 5.65, "learning_rate": 2.178131722275619e-05, "loss": 1.5328, "step": 123810 }, { "epoch": 5.65, "learning_rate": 2.177902878850291e-05, "loss": 1.5916, "step": 123820 }, { "epoch": 5.65, "learning_rate": 2.1776740354249623e-05, "loss": 1.5215, "step": 123830 }, { "epoch": 5.65, "learning_rate": 2.1774451919996337e-05, "loss": 1.4095, "step": 123840 }, { "epoch": 5.66, "learning_rate": 2.1772163485743055e-05, "loss": 1.3912, "step": 123850 }, { "epoch": 5.66, "learning_rate": 2.1769875051489772e-05, "loss": 1.3824, "step": 123860 }, { "epoch": 5.66, "learning_rate": 2.1767586617236486e-05, "loss": 1.5125, "step": 123870 }, { "epoch": 5.66, "learning_rate": 2.1765298182983204e-05, "loss": 1.4641, "step": 123880 }, { "epoch": 5.66, "learning_rate": 2.176300974872992e-05, "loss": 1.3561, "step": 123890 }, { "epoch": 5.66, "learning_rate": 2.1760721314476636e-05, "loss": 1.3972, "step": 123900 }, { "epoch": 5.66, "learning_rate": 2.1758432880223353e-05, "loss": 1.4741, "step": 123910 }, { "epoch": 5.66, "learning_rate": 2.1756144445970067e-05, "loss": 1.5062, "step": 123920 }, { "epoch": 5.66, "learning_rate": 2.1753856011716785e-05, "loss": 1.4197, "step": 123930 }, { "epoch": 5.66, "learning_rate": 2.17515675774635e-05, "loss": 1.4754, "step": 123940 }, { "epoch": 5.66, "learning_rate": 2.1749279143210216e-05, "loss": 1.3846, "step": 123950 }, { "epoch": 5.66, "learning_rate": 2.1746990708956934e-05, "loss": 1.5543, "step": 123960 }, { "epoch": 5.66, "learning_rate": 2.1744702274703648e-05, "loss": 1.4653, "step": 123970 }, { "epoch": 5.66, "learning_rate": 2.1742413840450366e-05, "loss": 1.5843, "step": 123980 }, { "epoch": 5.66, "learning_rate": 2.1740125406197083e-05, "loss": 1.2573, "step": 123990 }, { "epoch": 5.66, "learning_rate": 2.1737836971943797e-05, "loss": 1.5192, "step": 124000 }, { "epoch": 5.66, "learning_rate": 2.1735548537690515e-05, "loss": 1.3788, "step": 124010 }, { "epoch": 5.66, "learning_rate": 2.173326010343723e-05, "loss": 1.6475, "step": 124020 }, { "epoch": 5.66, "learning_rate": 2.1730971669183943e-05, "loss": 1.3877, "step": 124030 }, { "epoch": 5.66, "learning_rate": 2.172868323493066e-05, "loss": 1.5218, "step": 124040 }, { "epoch": 5.66, "learning_rate": 2.1726394800677378e-05, "loss": 1.4256, "step": 124050 }, { "epoch": 5.66, "learning_rate": 2.1724106366424092e-05, "loss": 1.4864, "step": 124060 }, { "epoch": 5.67, "learning_rate": 2.172181793217081e-05, "loss": 1.5423, "step": 124070 }, { "epoch": 5.67, "learning_rate": 2.1719529497917527e-05, "loss": 1.4254, "step": 124080 }, { "epoch": 5.67, "learning_rate": 2.171724106366424e-05, "loss": 1.4955, "step": 124090 }, { "epoch": 5.67, "learning_rate": 2.171495262941096e-05, "loss": 1.5295, "step": 124100 }, { "epoch": 5.67, "learning_rate": 2.1712664195157676e-05, "loss": 1.4334, "step": 124110 }, { "epoch": 5.67, "learning_rate": 2.171037576090439e-05, "loss": 1.6146, "step": 124120 }, { "epoch": 5.67, "learning_rate": 2.1708087326651105e-05, "loss": 1.5158, "step": 124130 }, { "epoch": 5.67, "learning_rate": 2.1705798892397822e-05, "loss": 1.3773, "step": 124140 }, { "epoch": 5.67, "learning_rate": 2.170351045814454e-05, "loss": 1.7238, "step": 124150 }, { "epoch": 5.67, "learning_rate": 2.1701222023891254e-05, "loss": 1.4368, "step": 124160 }, { "epoch": 5.67, "learning_rate": 2.169893358963797e-05, "loss": 1.5057, "step": 124170 }, { "epoch": 5.67, "learning_rate": 2.169664515538469e-05, "loss": 1.493, "step": 124180 }, { "epoch": 5.67, "learning_rate": 2.1694356721131403e-05, "loss": 1.4756, "step": 124190 }, { "epoch": 5.67, "learning_rate": 2.169206828687812e-05, "loss": 1.4652, "step": 124200 }, { "epoch": 5.67, "learning_rate": 2.1689779852624838e-05, "loss": 1.6134, "step": 124210 }, { "epoch": 5.67, "learning_rate": 2.168749141837155e-05, "loss": 1.5731, "step": 124220 }, { "epoch": 5.67, "learning_rate": 2.1685202984118266e-05, "loss": 1.3213, "step": 124230 }, { "epoch": 5.67, "learning_rate": 2.1682914549864984e-05, "loss": 1.4704, "step": 124240 }, { "epoch": 5.67, "learning_rate": 2.1680626115611698e-05, "loss": 1.4343, "step": 124250 }, { "epoch": 5.67, "learning_rate": 2.1678337681358415e-05, "loss": 1.4557, "step": 124260 }, { "epoch": 5.67, "learning_rate": 2.1676049247105133e-05, "loss": 1.4712, "step": 124270 }, { "epoch": 5.67, "learning_rate": 2.1673760812851847e-05, "loss": 1.5238, "step": 124280 }, { "epoch": 5.68, "learning_rate": 2.1671472378598565e-05, "loss": 1.363, "step": 124290 }, { "epoch": 5.68, "learning_rate": 2.1669183944345282e-05, "loss": 1.5089, "step": 124300 }, { "epoch": 5.68, "learning_rate": 2.1666895510091996e-05, "loss": 1.3683, "step": 124310 }, { "epoch": 5.68, "learning_rate": 2.166460707583871e-05, "loss": 1.393, "step": 124320 }, { "epoch": 5.68, "learning_rate": 2.1662318641585428e-05, "loss": 1.3398, "step": 124330 }, { "epoch": 5.68, "learning_rate": 2.1660030207332142e-05, "loss": 1.7234, "step": 124340 }, { "epoch": 5.68, "learning_rate": 2.165774177307886e-05, "loss": 1.4679, "step": 124350 }, { "epoch": 5.68, "learning_rate": 2.1655453338825577e-05, "loss": 1.4953, "step": 124360 }, { "epoch": 5.68, "learning_rate": 2.165316490457229e-05, "loss": 1.3821, "step": 124370 }, { "epoch": 5.68, "learning_rate": 2.165087647031901e-05, "loss": 1.5939, "step": 124380 }, { "epoch": 5.68, "learning_rate": 2.1648588036065726e-05, "loss": 1.4741, "step": 124390 }, { "epoch": 5.68, "learning_rate": 2.164629960181244e-05, "loss": 1.3958, "step": 124400 }, { "epoch": 5.68, "learning_rate": 2.1644011167559158e-05, "loss": 1.2723, "step": 124410 }, { "epoch": 5.68, "learning_rate": 2.1641722733305872e-05, "loss": 1.5553, "step": 124420 }, { "epoch": 5.68, "learning_rate": 2.163943429905259e-05, "loss": 1.3108, "step": 124430 }, { "epoch": 5.68, "learning_rate": 2.1637145864799304e-05, "loss": 1.3543, "step": 124440 }, { "epoch": 5.68, "learning_rate": 2.163485743054602e-05, "loss": 1.4067, "step": 124450 }, { "epoch": 5.68, "learning_rate": 2.163256899629274e-05, "loss": 1.5526, "step": 124460 }, { "epoch": 5.68, "learning_rate": 2.1630280562039453e-05, "loss": 1.372, "step": 124470 }, { "epoch": 5.68, "learning_rate": 2.162799212778617e-05, "loss": 1.5157, "step": 124480 }, { "epoch": 5.68, "learning_rate": 2.1625703693532888e-05, "loss": 1.4791, "step": 124490 }, { "epoch": 5.68, "learning_rate": 2.1623415259279602e-05, "loss": 1.6334, "step": 124500 }, { "epoch": 5.69, "learning_rate": 2.162112682502632e-05, "loss": 1.306, "step": 124510 }, { "epoch": 5.69, "learning_rate": 2.1618838390773034e-05, "loss": 1.6774, "step": 124520 }, { "epoch": 5.69, "learning_rate": 2.1616549956519748e-05, "loss": 1.4163, "step": 124530 }, { "epoch": 5.69, "learning_rate": 2.1614261522266465e-05, "loss": 1.4188, "step": 124540 }, { "epoch": 5.69, "learning_rate": 2.1611973088013183e-05, "loss": 1.4341, "step": 124550 }, { "epoch": 5.69, "learning_rate": 2.1609684653759897e-05, "loss": 1.5713, "step": 124560 }, { "epoch": 5.69, "learning_rate": 2.1607396219506615e-05, "loss": 1.4056, "step": 124570 }, { "epoch": 5.69, "learning_rate": 2.1605107785253332e-05, "loss": 1.4194, "step": 124580 }, { "epoch": 5.69, "learning_rate": 2.1602819351000046e-05, "loss": 1.5955, "step": 124590 }, { "epoch": 5.69, "learning_rate": 2.1600530916746764e-05, "loss": 1.5412, "step": 124600 }, { "epoch": 5.69, "learning_rate": 2.159824248249348e-05, "loss": 1.5164, "step": 124610 }, { "epoch": 5.69, "learning_rate": 2.1595954048240195e-05, "loss": 1.2909, "step": 124620 }, { "epoch": 5.69, "learning_rate": 2.159366561398691e-05, "loss": 1.5742, "step": 124630 }, { "epoch": 5.69, "learning_rate": 2.1591377179733627e-05, "loss": 1.473, "step": 124640 }, { "epoch": 5.69, "learning_rate": 2.1589088745480345e-05, "loss": 1.3855, "step": 124650 }, { "epoch": 5.69, "learning_rate": 2.158680031122706e-05, "loss": 1.4236, "step": 124660 }, { "epoch": 5.69, "learning_rate": 2.1584511876973776e-05, "loss": 1.6764, "step": 124670 }, { "epoch": 5.69, "learning_rate": 2.1582223442720494e-05, "loss": 1.4701, "step": 124680 }, { "epoch": 5.69, "learning_rate": 2.1579935008467208e-05, "loss": 1.3884, "step": 124690 }, { "epoch": 5.69, "learning_rate": 2.1577646574213925e-05, "loss": 1.4168, "step": 124700 }, { "epoch": 5.69, "learning_rate": 2.157535813996064e-05, "loss": 1.38, "step": 124710 }, { "epoch": 5.7, "learning_rate": 2.1573069705707354e-05, "loss": 1.496, "step": 124720 }, { "epoch": 5.7, "learning_rate": 2.157078127145407e-05, "loss": 1.3508, "step": 124730 }, { "epoch": 5.7, "learning_rate": 2.156849283720079e-05, "loss": 1.3678, "step": 124740 }, { "epoch": 5.7, "learning_rate": 2.1566204402947503e-05, "loss": 1.5033, "step": 124750 }, { "epoch": 5.7, "learning_rate": 2.156391596869422e-05, "loss": 1.4484, "step": 124760 }, { "epoch": 5.7, "learning_rate": 2.1561627534440938e-05, "loss": 1.5534, "step": 124770 }, { "epoch": 5.7, "learning_rate": 2.1559339100187652e-05, "loss": 1.5243, "step": 124780 }, { "epoch": 5.7, "learning_rate": 2.155705066593437e-05, "loss": 1.6691, "step": 124790 }, { "epoch": 5.7, "learning_rate": 2.1554762231681087e-05, "loss": 1.3221, "step": 124800 }, { "epoch": 5.7, "learning_rate": 2.15524737974278e-05, "loss": 1.5618, "step": 124810 }, { "epoch": 5.7, "learning_rate": 2.1550185363174515e-05, "loss": 1.5588, "step": 124820 }, { "epoch": 5.7, "learning_rate": 2.1547896928921233e-05, "loss": 1.4057, "step": 124830 }, { "epoch": 5.7, "learning_rate": 2.154560849466795e-05, "loss": 1.4441, "step": 124840 }, { "epoch": 5.7, "learning_rate": 2.1543320060414665e-05, "loss": 1.5647, "step": 124850 }, { "epoch": 5.7, "learning_rate": 2.1541031626161382e-05, "loss": 1.4153, "step": 124860 }, { "epoch": 5.7, "learning_rate": 2.1538743191908096e-05, "loss": 1.4894, "step": 124870 }, { "epoch": 5.7, "learning_rate": 2.1536454757654814e-05, "loss": 1.4266, "step": 124880 }, { "epoch": 5.7, "learning_rate": 2.153416632340153e-05, "loss": 1.4443, "step": 124890 }, { "epoch": 5.7, "learning_rate": 2.1531877889148245e-05, "loss": 1.4623, "step": 124900 }, { "epoch": 5.7, "learning_rate": 2.152958945489496e-05, "loss": 1.3874, "step": 124910 }, { "epoch": 5.7, "learning_rate": 2.1527301020641677e-05, "loss": 1.6063, "step": 124920 }, { "epoch": 5.7, "learning_rate": 2.1525012586388395e-05, "loss": 1.5016, "step": 124930 }, { "epoch": 5.71, "learning_rate": 2.152272415213511e-05, "loss": 1.3892, "step": 124940 }, { "epoch": 5.71, "learning_rate": 2.1520435717881826e-05, "loss": 1.4151, "step": 124950 }, { "epoch": 5.71, "learning_rate": 2.1518147283628544e-05, "loss": 1.4416, "step": 124960 }, { "epoch": 5.71, "learning_rate": 2.1515858849375258e-05, "loss": 1.5099, "step": 124970 }, { "epoch": 5.71, "learning_rate": 2.1513570415121975e-05, "loss": 1.5852, "step": 124980 }, { "epoch": 5.71, "learning_rate": 2.1511281980868693e-05, "loss": 1.3529, "step": 124990 }, { "epoch": 5.71, "learning_rate": 2.1508993546615407e-05, "loss": 1.5268, "step": 125000 }, { "epoch": 5.71, "learning_rate": 2.150670511236212e-05, "loss": 1.6069, "step": 125010 }, { "epoch": 5.71, "learning_rate": 2.150441667810884e-05, "loss": 1.5542, "step": 125020 }, { "epoch": 5.71, "learning_rate": 2.1502128243855553e-05, "loss": 1.6702, "step": 125030 }, { "epoch": 5.71, "learning_rate": 2.149983980960227e-05, "loss": 1.2447, "step": 125040 }, { "epoch": 5.71, "learning_rate": 2.1497551375348988e-05, "loss": 1.6077, "step": 125050 }, { "epoch": 5.71, "learning_rate": 2.1495262941095702e-05, "loss": 1.4173, "step": 125060 }, { "epoch": 5.71, "learning_rate": 2.149297450684242e-05, "loss": 1.3289, "step": 125070 }, { "epoch": 5.71, "learning_rate": 2.1490686072589137e-05, "loss": 1.4379, "step": 125080 }, { "epoch": 5.71, "learning_rate": 2.148839763833585e-05, "loss": 1.5012, "step": 125090 }, { "epoch": 5.71, "learning_rate": 2.148610920408257e-05, "loss": 1.6335, "step": 125100 }, { "epoch": 5.71, "learning_rate": 2.1483820769829283e-05, "loss": 1.3348, "step": 125110 }, { "epoch": 5.71, "learning_rate": 2.1481532335576e-05, "loss": 1.4142, "step": 125120 }, { "epoch": 5.71, "learning_rate": 2.1479243901322714e-05, "loss": 1.4783, "step": 125130 }, { "epoch": 5.71, "learning_rate": 2.1476955467069432e-05, "loss": 1.5703, "step": 125140 }, { "epoch": 5.71, "learning_rate": 2.147466703281615e-05, "loss": 1.5605, "step": 125150 }, { "epoch": 5.72, "learning_rate": 2.1472378598562864e-05, "loss": 1.3517, "step": 125160 }, { "epoch": 5.72, "learning_rate": 2.147009016430958e-05, "loss": 1.4219, "step": 125170 }, { "epoch": 5.72, "learning_rate": 2.14678017300563e-05, "loss": 1.4878, "step": 125180 }, { "epoch": 5.72, "learning_rate": 2.1465513295803013e-05, "loss": 1.4055, "step": 125190 }, { "epoch": 5.72, "learning_rate": 2.146322486154973e-05, "loss": 1.3932, "step": 125200 }, { "epoch": 5.72, "learning_rate": 2.1460936427296444e-05, "loss": 1.3768, "step": 125210 }, { "epoch": 5.72, "learning_rate": 2.145864799304316e-05, "loss": 1.5816, "step": 125220 }, { "epoch": 5.72, "learning_rate": 2.1456359558789876e-05, "loss": 1.3973, "step": 125230 }, { "epoch": 5.72, "learning_rate": 2.1454071124536594e-05, "loss": 1.3642, "step": 125240 }, { "epoch": 5.72, "learning_rate": 2.1451782690283308e-05, "loss": 1.4826, "step": 125250 }, { "epoch": 5.72, "learning_rate": 2.1449494256030025e-05, "loss": 1.5429, "step": 125260 }, { "epoch": 5.72, "learning_rate": 2.1447205821776743e-05, "loss": 1.4973, "step": 125270 }, { "epoch": 5.72, "learning_rate": 2.1444917387523457e-05, "loss": 1.4036, "step": 125280 }, { "epoch": 5.72, "learning_rate": 2.1442628953270175e-05, "loss": 1.5446, "step": 125290 }, { "epoch": 5.72, "learning_rate": 2.1440340519016892e-05, "loss": 1.3432, "step": 125300 }, { "epoch": 5.72, "learning_rate": 2.1438052084763606e-05, "loss": 1.2581, "step": 125310 }, { "epoch": 5.72, "learning_rate": 2.143576365051032e-05, "loss": 1.3696, "step": 125320 }, { "epoch": 5.72, "learning_rate": 2.1433475216257038e-05, "loss": 1.2636, "step": 125330 }, { "epoch": 5.72, "learning_rate": 2.1431186782003755e-05, "loss": 1.5469, "step": 125340 }, { "epoch": 5.72, "learning_rate": 2.142889834775047e-05, "loss": 1.5194, "step": 125350 }, { "epoch": 5.72, "learning_rate": 2.1426609913497187e-05, "loss": 1.3992, "step": 125360 }, { "epoch": 5.72, "learning_rate": 2.1424321479243905e-05, "loss": 1.3683, "step": 125370 }, { "epoch": 5.73, "learning_rate": 2.142203304499062e-05, "loss": 1.5474, "step": 125380 }, { "epoch": 5.73, "learning_rate": 2.1419744610737336e-05, "loss": 1.6269, "step": 125390 }, { "epoch": 5.73, "learning_rate": 2.1417456176484054e-05, "loss": 1.6384, "step": 125400 }, { "epoch": 5.73, "learning_rate": 2.1415167742230764e-05, "loss": 1.4502, "step": 125410 }, { "epoch": 5.73, "learning_rate": 2.1412879307977482e-05, "loss": 1.3051, "step": 125420 }, { "epoch": 5.73, "learning_rate": 2.14105908737242e-05, "loss": 1.5786, "step": 125430 }, { "epoch": 5.73, "learning_rate": 2.1408302439470914e-05, "loss": 1.4485, "step": 125440 }, { "epoch": 5.73, "learning_rate": 2.140601400521763e-05, "loss": 1.5122, "step": 125450 }, { "epoch": 5.73, "learning_rate": 2.140372557096435e-05, "loss": 1.5559, "step": 125460 }, { "epoch": 5.73, "learning_rate": 2.1401437136711063e-05, "loss": 1.4927, "step": 125470 }, { "epoch": 5.73, "learning_rate": 2.139914870245778e-05, "loss": 1.7332, "step": 125480 }, { "epoch": 5.73, "learning_rate": 2.1396860268204498e-05, "loss": 1.5117, "step": 125490 }, { "epoch": 5.73, "learning_rate": 2.139457183395121e-05, "loss": 1.4503, "step": 125500 }, { "epoch": 5.73, "learning_rate": 2.1392283399697926e-05, "loss": 1.3767, "step": 125510 }, { "epoch": 5.73, "learning_rate": 2.1389994965444644e-05, "loss": 1.5274, "step": 125520 }, { "epoch": 5.73, "learning_rate": 2.1387706531191358e-05, "loss": 1.3851, "step": 125530 }, { "epoch": 5.73, "learning_rate": 2.1385418096938075e-05, "loss": 1.3031, "step": 125540 }, { "epoch": 5.73, "learning_rate": 2.1383129662684793e-05, "loss": 1.5034, "step": 125550 }, { "epoch": 5.73, "learning_rate": 2.1380841228431507e-05, "loss": 1.5267, "step": 125560 }, { "epoch": 5.73, "learning_rate": 2.1378552794178224e-05, "loss": 1.3513, "step": 125570 }, { "epoch": 5.73, "learning_rate": 2.1376264359924942e-05, "loss": 1.4866, "step": 125580 }, { "epoch": 5.73, "learning_rate": 2.1373975925671656e-05, "loss": 1.5918, "step": 125590 }, { "epoch": 5.74, "learning_rate": 2.137168749141837e-05, "loss": 1.4455, "step": 125600 }, { "epoch": 5.74, "learning_rate": 2.1369399057165088e-05, "loss": 1.4744, "step": 125610 }, { "epoch": 5.74, "learning_rate": 2.1367110622911805e-05, "loss": 1.537, "step": 125620 }, { "epoch": 5.74, "learning_rate": 2.136482218865852e-05, "loss": 1.6273, "step": 125630 }, { "epoch": 5.74, "learning_rate": 2.1362533754405237e-05, "loss": 1.333, "step": 125640 }, { "epoch": 5.74, "learning_rate": 2.1360245320151954e-05, "loss": 1.5039, "step": 125650 }, { "epoch": 5.74, "learning_rate": 2.135795688589867e-05, "loss": 1.448, "step": 125660 }, { "epoch": 5.74, "learning_rate": 2.1355668451645386e-05, "loss": 1.3906, "step": 125670 }, { "epoch": 5.74, "learning_rate": 2.1353380017392104e-05, "loss": 1.5675, "step": 125680 }, { "epoch": 5.74, "learning_rate": 2.1351091583138818e-05, "loss": 1.4505, "step": 125690 }, { "epoch": 5.74, "learning_rate": 2.1348803148885532e-05, "loss": 1.4883, "step": 125700 }, { "epoch": 5.74, "learning_rate": 2.134651471463225e-05, "loss": 1.541, "step": 125710 }, { "epoch": 5.74, "learning_rate": 2.1344226280378964e-05, "loss": 1.3421, "step": 125720 }, { "epoch": 5.74, "learning_rate": 2.134193784612568e-05, "loss": 1.4393, "step": 125730 }, { "epoch": 5.74, "learning_rate": 2.13396494118724e-05, "loss": 1.5162, "step": 125740 }, { "epoch": 5.74, "learning_rate": 2.1337360977619113e-05, "loss": 1.3679, "step": 125750 }, { "epoch": 5.74, "learning_rate": 2.133507254336583e-05, "loss": 1.4148, "step": 125760 }, { "epoch": 5.74, "learning_rate": 2.1332784109112548e-05, "loss": 1.4758, "step": 125770 }, { "epoch": 5.74, "learning_rate": 2.1330495674859262e-05, "loss": 1.347, "step": 125780 }, { "epoch": 5.74, "learning_rate": 2.132820724060598e-05, "loss": 1.3943, "step": 125790 }, { "epoch": 5.74, "learning_rate": 2.1325918806352694e-05, "loss": 1.5543, "step": 125800 }, { "epoch": 5.74, "learning_rate": 2.132363037209941e-05, "loss": 1.5326, "step": 125810 }, { "epoch": 5.75, "learning_rate": 2.1321341937846125e-05, "loss": 1.3801, "step": 125820 }, { "epoch": 5.75, "learning_rate": 2.1319053503592843e-05, "loss": 1.3355, "step": 125830 }, { "epoch": 5.75, "learning_rate": 2.131676506933956e-05, "loss": 1.47, "step": 125840 }, { "epoch": 5.75, "learning_rate": 2.1314476635086274e-05, "loss": 1.4488, "step": 125850 }, { "epoch": 5.75, "learning_rate": 2.1312188200832992e-05, "loss": 1.4973, "step": 125860 }, { "epoch": 5.75, "learning_rate": 2.130989976657971e-05, "loss": 1.5232, "step": 125870 }, { "epoch": 5.75, "learning_rate": 2.1307611332326424e-05, "loss": 1.6154, "step": 125880 }, { "epoch": 5.75, "learning_rate": 2.130532289807314e-05, "loss": 1.4912, "step": 125890 }, { "epoch": 5.75, "learning_rate": 2.1303034463819855e-05, "loss": 1.364, "step": 125900 }, { "epoch": 5.75, "learning_rate": 2.130074602956657e-05, "loss": 1.5704, "step": 125910 }, { "epoch": 5.75, "learning_rate": 2.1298457595313287e-05, "loss": 1.3345, "step": 125920 }, { "epoch": 5.75, "learning_rate": 2.1296169161060004e-05, "loss": 1.5191, "step": 125930 }, { "epoch": 5.75, "learning_rate": 2.129388072680672e-05, "loss": 1.3644, "step": 125940 }, { "epoch": 5.75, "learning_rate": 2.1291592292553436e-05, "loss": 1.4769, "step": 125950 }, { "epoch": 5.75, "learning_rate": 2.1289303858300154e-05, "loss": 1.3499, "step": 125960 }, { "epoch": 5.75, "learning_rate": 2.1287015424046868e-05, "loss": 1.3825, "step": 125970 }, { "epoch": 5.75, "learning_rate": 2.1284726989793585e-05, "loss": 1.5305, "step": 125980 }, { "epoch": 5.75, "learning_rate": 2.1282438555540303e-05, "loss": 1.3901, "step": 125990 }, { "epoch": 5.75, "learning_rate": 2.1280150121287017e-05, "loss": 1.5847, "step": 126000 }, { "epoch": 5.75, "learning_rate": 2.127786168703373e-05, "loss": 1.4335, "step": 126010 }, { "epoch": 5.75, "learning_rate": 2.127557325278045e-05, "loss": 1.6272, "step": 126020 }, { "epoch": 5.75, "learning_rate": 2.1273284818527163e-05, "loss": 1.3916, "step": 126030 }, { "epoch": 5.76, "learning_rate": 2.127099638427388e-05, "loss": 1.4404, "step": 126040 }, { "epoch": 5.76, "learning_rate": 2.1268707950020598e-05, "loss": 1.4876, "step": 126050 }, { "epoch": 5.76, "learning_rate": 2.1266419515767312e-05, "loss": 1.4136, "step": 126060 }, { "epoch": 5.76, "learning_rate": 2.126413108151403e-05, "loss": 1.4471, "step": 126070 }, { "epoch": 5.76, "learning_rate": 2.1261842647260747e-05, "loss": 1.4127, "step": 126080 }, { "epoch": 5.76, "learning_rate": 2.125955421300746e-05, "loss": 1.5418, "step": 126090 }, { "epoch": 5.76, "learning_rate": 2.1257265778754175e-05, "loss": 1.4075, "step": 126100 }, { "epoch": 5.76, "learning_rate": 2.1254977344500893e-05, "loss": 1.4782, "step": 126110 }, { "epoch": 5.76, "learning_rate": 2.125268891024761e-05, "loss": 1.3972, "step": 126120 }, { "epoch": 5.76, "learning_rate": 2.1250400475994324e-05, "loss": 1.3887, "step": 126130 }, { "epoch": 5.76, "learning_rate": 2.1248112041741042e-05, "loss": 1.5283, "step": 126140 }, { "epoch": 5.76, "learning_rate": 2.124582360748776e-05, "loss": 1.4824, "step": 126150 }, { "epoch": 5.76, "learning_rate": 2.1243535173234474e-05, "loss": 1.4622, "step": 126160 }, { "epoch": 5.76, "learning_rate": 2.124124673898119e-05, "loss": 1.4866, "step": 126170 }, { "epoch": 5.76, "learning_rate": 2.123895830472791e-05, "loss": 1.3655, "step": 126180 }, { "epoch": 5.76, "learning_rate": 2.1236669870474623e-05, "loss": 1.6231, "step": 126190 }, { "epoch": 5.76, "learning_rate": 2.1234381436221337e-05, "loss": 1.482, "step": 126200 }, { "epoch": 5.76, "learning_rate": 2.1232093001968054e-05, "loss": 1.4683, "step": 126210 }, { "epoch": 5.76, "learning_rate": 2.122980456771477e-05, "loss": 1.5392, "step": 126220 }, { "epoch": 5.76, "learning_rate": 2.1227516133461486e-05, "loss": 1.5042, "step": 126230 }, { "epoch": 5.76, "learning_rate": 2.1225227699208204e-05, "loss": 1.3286, "step": 126240 }, { "epoch": 5.76, "learning_rate": 2.1222939264954918e-05, "loss": 1.4916, "step": 126250 }, { "epoch": 5.77, "learning_rate": 2.1220650830701635e-05, "loss": 1.4096, "step": 126260 }, { "epoch": 5.77, "learning_rate": 2.1218362396448353e-05, "loss": 1.6821, "step": 126270 }, { "epoch": 5.77, "learning_rate": 2.1216073962195067e-05, "loss": 1.447, "step": 126280 }, { "epoch": 5.77, "learning_rate": 2.121378552794178e-05, "loss": 1.3826, "step": 126290 }, { "epoch": 5.77, "learning_rate": 2.12114970936885e-05, "loss": 1.4377, "step": 126300 }, { "epoch": 5.77, "learning_rate": 2.1209208659435216e-05, "loss": 1.5309, "step": 126310 }, { "epoch": 5.77, "learning_rate": 2.120692022518193e-05, "loss": 1.5802, "step": 126320 }, { "epoch": 5.77, "learning_rate": 2.1204631790928648e-05, "loss": 1.5213, "step": 126330 }, { "epoch": 5.77, "learning_rate": 2.1202343356675365e-05, "loss": 1.5168, "step": 126340 }, { "epoch": 5.77, "learning_rate": 2.120005492242208e-05, "loss": 1.478, "step": 126350 }, { "epoch": 5.77, "learning_rate": 2.1197766488168797e-05, "loss": 1.4539, "step": 126360 }, { "epoch": 5.77, "learning_rate": 2.1195478053915514e-05, "loss": 1.4997, "step": 126370 }, { "epoch": 5.77, "learning_rate": 2.119318961966223e-05, "loss": 1.599, "step": 126380 }, { "epoch": 5.77, "learning_rate": 2.1190901185408943e-05, "loss": 1.39, "step": 126390 }, { "epoch": 5.77, "learning_rate": 2.118861275115566e-05, "loss": 1.4006, "step": 126400 }, { "epoch": 5.77, "learning_rate": 2.1186324316902374e-05, "loss": 1.526, "step": 126410 }, { "epoch": 5.77, "learning_rate": 2.1184035882649092e-05, "loss": 1.3508, "step": 126420 }, { "epoch": 5.77, "learning_rate": 2.118174744839581e-05, "loss": 1.4799, "step": 126430 }, { "epoch": 5.77, "learning_rate": 2.1179459014142523e-05, "loss": 1.4354, "step": 126440 }, { "epoch": 5.77, "learning_rate": 2.117717057988924e-05, "loss": 1.3977, "step": 126450 }, { "epoch": 5.77, "learning_rate": 2.117488214563596e-05, "loss": 1.4816, "step": 126460 }, { "epoch": 5.77, "learning_rate": 2.1172593711382673e-05, "loss": 1.368, "step": 126470 }, { "epoch": 5.78, "learning_rate": 2.117030527712939e-05, "loss": 1.5719, "step": 126480 }, { "epoch": 5.78, "learning_rate": 2.1168016842876104e-05, "loss": 1.4533, "step": 126490 }, { "epoch": 5.78, "learning_rate": 2.1165728408622822e-05, "loss": 1.4177, "step": 126500 }, { "epoch": 5.78, "learning_rate": 2.1163439974369536e-05, "loss": 1.6382, "step": 126510 }, { "epoch": 5.78, "learning_rate": 2.1161151540116253e-05, "loss": 1.4526, "step": 126520 }, { "epoch": 5.78, "learning_rate": 2.115886310586297e-05, "loss": 1.4017, "step": 126530 }, { "epoch": 5.78, "learning_rate": 2.1156574671609685e-05, "loss": 1.43, "step": 126540 }, { "epoch": 5.78, "learning_rate": 2.1154286237356403e-05, "loss": 1.3883, "step": 126550 }, { "epoch": 5.78, "learning_rate": 2.115199780310312e-05, "loss": 1.4711, "step": 126560 }, { "epoch": 5.78, "learning_rate": 2.1149709368849834e-05, "loss": 1.548, "step": 126570 }, { "epoch": 5.78, "learning_rate": 2.1147420934596552e-05, "loss": 1.5375, "step": 126580 }, { "epoch": 5.78, "learning_rate": 2.1145132500343266e-05, "loss": 1.445, "step": 126590 }, { "epoch": 5.78, "learning_rate": 2.114284406608998e-05, "loss": 1.396, "step": 126600 }, { "epoch": 5.78, "learning_rate": 2.1140555631836698e-05, "loss": 1.5893, "step": 126610 }, { "epoch": 5.78, "learning_rate": 2.1138267197583415e-05, "loss": 1.4628, "step": 126620 }, { "epoch": 5.78, "learning_rate": 2.113597876333013e-05, "loss": 1.4923, "step": 126630 }, { "epoch": 5.78, "learning_rate": 2.1133690329076847e-05, "loss": 1.4701, "step": 126640 }, { "epoch": 5.78, "learning_rate": 2.1131401894823564e-05, "loss": 1.4633, "step": 126650 }, { "epoch": 5.78, "learning_rate": 2.112911346057028e-05, "loss": 1.4507, "step": 126660 }, { "epoch": 5.78, "learning_rate": 2.1126825026316996e-05, "loss": 1.5913, "step": 126670 }, { "epoch": 5.78, "learning_rate": 2.1124536592063714e-05, "loss": 1.3909, "step": 126680 }, { "epoch": 5.78, "learning_rate": 2.1122248157810424e-05, "loss": 1.5326, "step": 126690 }, { "epoch": 5.79, "learning_rate": 2.1119959723557142e-05, "loss": 1.5909, "step": 126700 }, { "epoch": 5.79, "learning_rate": 2.111767128930386e-05, "loss": 1.6091, "step": 126710 }, { "epoch": 5.79, "learning_rate": 2.1115382855050573e-05, "loss": 1.3911, "step": 126720 }, { "epoch": 5.79, "learning_rate": 2.111309442079729e-05, "loss": 1.3569, "step": 126730 }, { "epoch": 5.79, "learning_rate": 2.111080598654401e-05, "loss": 1.4201, "step": 126740 }, { "epoch": 5.79, "learning_rate": 2.1108517552290723e-05, "loss": 1.5804, "step": 126750 }, { "epoch": 5.79, "learning_rate": 2.110622911803744e-05, "loss": 1.3126, "step": 126760 }, { "epoch": 5.79, "learning_rate": 2.1103940683784158e-05, "loss": 1.4762, "step": 126770 }, { "epoch": 5.79, "learning_rate": 2.1101652249530872e-05, "loss": 1.4715, "step": 126780 }, { "epoch": 5.79, "learning_rate": 2.1099363815277586e-05, "loss": 1.5267, "step": 126790 }, { "epoch": 5.79, "learning_rate": 2.1097075381024303e-05, "loss": 1.5473, "step": 126800 }, { "epoch": 5.79, "learning_rate": 2.109478694677102e-05, "loss": 1.5739, "step": 126810 }, { "epoch": 5.79, "learning_rate": 2.1092498512517735e-05, "loss": 1.5218, "step": 126820 }, { "epoch": 5.79, "learning_rate": 2.1090210078264453e-05, "loss": 1.3333, "step": 126830 }, { "epoch": 5.79, "learning_rate": 2.108792164401117e-05, "loss": 1.4813, "step": 126840 }, { "epoch": 5.79, "learning_rate": 2.1085633209757884e-05, "loss": 1.5998, "step": 126850 }, { "epoch": 5.79, "learning_rate": 2.1083344775504602e-05, "loss": 1.4114, "step": 126860 }, { "epoch": 5.79, "learning_rate": 2.108105634125132e-05, "loss": 1.4863, "step": 126870 }, { "epoch": 5.79, "learning_rate": 2.1078767906998033e-05, "loss": 1.4487, "step": 126880 }, { "epoch": 5.79, "learning_rate": 2.1076479472744748e-05, "loss": 1.433, "step": 126890 }, { "epoch": 5.79, "learning_rate": 2.1074191038491465e-05, "loss": 1.5099, "step": 126900 }, { "epoch": 5.8, "learning_rate": 2.107190260423818e-05, "loss": 1.3808, "step": 126910 }, { "epoch": 5.8, "learning_rate": 2.1069614169984897e-05, "loss": 1.5304, "step": 126920 }, { "epoch": 5.8, "learning_rate": 2.1067325735731614e-05, "loss": 1.6831, "step": 126930 }, { "epoch": 5.8, "learning_rate": 2.106503730147833e-05, "loss": 1.533, "step": 126940 }, { "epoch": 5.8, "learning_rate": 2.1062748867225046e-05, "loss": 1.3599, "step": 126950 }, { "epoch": 5.8, "learning_rate": 2.1060460432971763e-05, "loss": 1.5566, "step": 126960 }, { "epoch": 5.8, "learning_rate": 2.1058171998718478e-05, "loss": 1.505, "step": 126970 }, { "epoch": 5.8, "learning_rate": 2.1055883564465195e-05, "loss": 1.6952, "step": 126980 }, { "epoch": 5.8, "learning_rate": 2.105359513021191e-05, "loss": 1.4692, "step": 126990 }, { "epoch": 5.8, "learning_rate": 2.1051306695958627e-05, "loss": 1.5407, "step": 127000 }, { "epoch": 5.8, "learning_rate": 2.104901826170534e-05, "loss": 1.3977, "step": 127010 }, { "epoch": 5.8, "learning_rate": 2.104672982745206e-05, "loss": 1.5785, "step": 127020 }, { "epoch": 5.8, "learning_rate": 2.1044441393198776e-05, "loss": 1.4948, "step": 127030 }, { "epoch": 5.8, "learning_rate": 2.104215295894549e-05, "loss": 1.4617, "step": 127040 }, { "epoch": 5.8, "learning_rate": 2.1039864524692208e-05, "loss": 1.4065, "step": 127050 }, { "epoch": 5.8, "learning_rate": 2.1037576090438925e-05, "loss": 1.4578, "step": 127060 }, { "epoch": 5.8, "learning_rate": 2.103528765618564e-05, "loss": 1.507, "step": 127070 }, { "epoch": 5.8, "learning_rate": 2.1032999221932353e-05, "loss": 1.5583, "step": 127080 }, { "epoch": 5.8, "learning_rate": 2.103071078767907e-05, "loss": 1.4753, "step": 127090 }, { "epoch": 5.8, "learning_rate": 2.1028422353425785e-05, "loss": 1.4624, "step": 127100 }, { "epoch": 5.8, "learning_rate": 2.1026133919172503e-05, "loss": 1.3401, "step": 127110 }, { "epoch": 5.8, "learning_rate": 2.102384548491922e-05, "loss": 1.4261, "step": 127120 }, { "epoch": 5.81, "learning_rate": 2.1021557050665934e-05, "loss": 1.6203, "step": 127130 }, { "epoch": 5.81, "learning_rate": 2.1019268616412652e-05, "loss": 1.4256, "step": 127140 }, { "epoch": 5.81, "learning_rate": 2.101698018215937e-05, "loss": 1.3726, "step": 127150 }, { "epoch": 5.81, "learning_rate": 2.1014691747906083e-05, "loss": 1.4062, "step": 127160 }, { "epoch": 5.81, "learning_rate": 2.10124033136528e-05, "loss": 1.4652, "step": 127170 }, { "epoch": 5.81, "learning_rate": 2.1010114879399515e-05, "loss": 1.5057, "step": 127180 }, { "epoch": 5.81, "learning_rate": 2.1007826445146233e-05, "loss": 1.2664, "step": 127190 }, { "epoch": 5.81, "learning_rate": 2.1005538010892947e-05, "loss": 1.4109, "step": 127200 }, { "epoch": 5.81, "learning_rate": 2.1003249576639664e-05, "loss": 1.5374, "step": 127210 }, { "epoch": 5.81, "learning_rate": 2.100096114238638e-05, "loss": 1.4596, "step": 127220 }, { "epoch": 5.81, "learning_rate": 2.0998672708133096e-05, "loss": 1.2792, "step": 127230 }, { "epoch": 5.81, "learning_rate": 2.0996384273879813e-05, "loss": 1.4139, "step": 127240 }, { "epoch": 5.81, "learning_rate": 2.0994095839626528e-05, "loss": 1.3931, "step": 127250 }, { "epoch": 5.81, "learning_rate": 2.0991807405373245e-05, "loss": 1.3469, "step": 127260 }, { "epoch": 5.81, "learning_rate": 2.0989518971119963e-05, "loss": 1.4663, "step": 127270 }, { "epoch": 5.81, "learning_rate": 2.0987230536866677e-05, "loss": 1.4651, "step": 127280 }, { "epoch": 5.81, "learning_rate": 2.098494210261339e-05, "loss": 1.4874, "step": 127290 }, { "epoch": 5.81, "learning_rate": 2.098265366836011e-05, "loss": 1.4667, "step": 127300 }, { "epoch": 5.81, "learning_rate": 2.0980365234106826e-05, "loss": 1.4224, "step": 127310 }, { "epoch": 5.81, "learning_rate": 2.097807679985354e-05, "loss": 1.4465, "step": 127320 }, { "epoch": 5.81, "learning_rate": 2.0975788365600258e-05, "loss": 1.4504, "step": 127330 }, { "epoch": 5.81, "learning_rate": 2.0973499931346975e-05, "loss": 1.3966, "step": 127340 }, { "epoch": 5.82, "learning_rate": 2.097121149709369e-05, "loss": 1.514, "step": 127350 }, { "epoch": 5.82, "learning_rate": 2.0968923062840407e-05, "loss": 1.3885, "step": 127360 }, { "epoch": 5.82, "learning_rate": 2.0966634628587124e-05, "loss": 1.4443, "step": 127370 }, { "epoch": 5.82, "learning_rate": 2.0964346194333835e-05, "loss": 1.4893, "step": 127380 }, { "epoch": 5.82, "learning_rate": 2.0962057760080553e-05, "loss": 1.5232, "step": 127390 }, { "epoch": 5.82, "learning_rate": 2.095976932582727e-05, "loss": 1.4106, "step": 127400 }, { "epoch": 5.82, "learning_rate": 2.0957480891573984e-05, "loss": 1.4246, "step": 127410 }, { "epoch": 5.82, "learning_rate": 2.09551924573207e-05, "loss": 1.4854, "step": 127420 }, { "epoch": 5.82, "learning_rate": 2.095290402306742e-05, "loss": 1.4366, "step": 127430 }, { "epoch": 5.82, "learning_rate": 2.0950615588814133e-05, "loss": 1.4394, "step": 127440 }, { "epoch": 5.82, "learning_rate": 2.094832715456085e-05, "loss": 1.4053, "step": 127450 }, { "epoch": 5.82, "learning_rate": 2.094603872030757e-05, "loss": 1.4796, "step": 127460 }, { "epoch": 5.82, "learning_rate": 2.0943750286054283e-05, "loss": 1.4586, "step": 127470 }, { "epoch": 5.82, "learning_rate": 2.0941461851800997e-05, "loss": 1.4391, "step": 127480 }, { "epoch": 5.82, "learning_rate": 2.0939173417547714e-05, "loss": 1.4611, "step": 127490 }, { "epoch": 5.82, "learning_rate": 2.0936884983294432e-05, "loss": 1.3639, "step": 127500 }, { "epoch": 5.82, "learning_rate": 2.0934596549041146e-05, "loss": 1.4817, "step": 127510 }, { "epoch": 5.82, "learning_rate": 2.0932308114787863e-05, "loss": 1.5477, "step": 127520 }, { "epoch": 5.82, "learning_rate": 2.093001968053458e-05, "loss": 1.32, "step": 127530 }, { "epoch": 5.82, "learning_rate": 2.0927731246281295e-05, "loss": 1.5591, "step": 127540 }, { "epoch": 5.82, "learning_rate": 2.0925442812028013e-05, "loss": 1.5311, "step": 127550 }, { "epoch": 5.82, "learning_rate": 2.092315437777473e-05, "loss": 1.4952, "step": 127560 }, { "epoch": 5.83, "learning_rate": 2.0920865943521444e-05, "loss": 1.4286, "step": 127570 }, { "epoch": 5.83, "learning_rate": 2.091857750926816e-05, "loss": 1.5112, "step": 127580 }, { "epoch": 5.83, "learning_rate": 2.0916289075014876e-05, "loss": 1.3596, "step": 127590 }, { "epoch": 5.83, "learning_rate": 2.091400064076159e-05, "loss": 1.3784, "step": 127600 }, { "epoch": 5.83, "learning_rate": 2.0911712206508307e-05, "loss": 1.4689, "step": 127610 }, { "epoch": 5.83, "learning_rate": 2.0909423772255025e-05, "loss": 1.5211, "step": 127620 }, { "epoch": 5.83, "learning_rate": 2.090713533800174e-05, "loss": 1.4169, "step": 127630 }, { "epoch": 5.83, "learning_rate": 2.0904846903748457e-05, "loss": 1.4995, "step": 127640 }, { "epoch": 5.83, "learning_rate": 2.0902558469495174e-05, "loss": 1.4716, "step": 127650 }, { "epoch": 5.83, "learning_rate": 2.090027003524189e-05, "loss": 1.4792, "step": 127660 }, { "epoch": 5.83, "learning_rate": 2.0897981600988606e-05, "loss": 1.4724, "step": 127670 }, { "epoch": 5.83, "learning_rate": 2.089569316673532e-05, "loss": 1.421, "step": 127680 }, { "epoch": 5.83, "learning_rate": 2.0893404732482038e-05, "loss": 1.3826, "step": 127690 }, { "epoch": 5.83, "learning_rate": 2.089111629822875e-05, "loss": 1.4038, "step": 127700 }, { "epoch": 5.83, "learning_rate": 2.088882786397547e-05, "loss": 1.3161, "step": 127710 }, { "epoch": 5.83, "learning_rate": 2.0886539429722187e-05, "loss": 1.423, "step": 127720 }, { "epoch": 5.83, "learning_rate": 2.08842509954689e-05, "loss": 1.4813, "step": 127730 }, { "epoch": 5.83, "learning_rate": 2.088196256121562e-05, "loss": 1.5151, "step": 127740 }, { "epoch": 5.83, "learning_rate": 2.0879674126962332e-05, "loss": 1.4855, "step": 127750 }, { "epoch": 5.83, "learning_rate": 2.087738569270905e-05, "loss": 1.3833, "step": 127760 }, { "epoch": 5.83, "learning_rate": 2.0875097258455768e-05, "loss": 1.4756, "step": 127770 }, { "epoch": 5.83, "learning_rate": 2.087280882420248e-05, "loss": 1.3977, "step": 127780 }, { "epoch": 5.84, "learning_rate": 2.0870520389949196e-05, "loss": 1.4845, "step": 127790 }, { "epoch": 5.84, "learning_rate": 2.0868231955695913e-05, "loss": 1.523, "step": 127800 }, { "epoch": 5.84, "learning_rate": 2.086594352144263e-05, "loss": 1.4274, "step": 127810 }, { "epoch": 5.84, "learning_rate": 2.0863655087189345e-05, "loss": 1.4114, "step": 127820 }, { "epoch": 5.84, "learning_rate": 2.0861366652936062e-05, "loss": 1.5767, "step": 127830 }, { "epoch": 5.84, "learning_rate": 2.085907821868278e-05, "loss": 1.4509, "step": 127840 }, { "epoch": 5.84, "learning_rate": 2.0856789784429494e-05, "loss": 1.6155, "step": 127850 }, { "epoch": 5.84, "learning_rate": 2.085450135017621e-05, "loss": 1.4477, "step": 127860 }, { "epoch": 5.84, "learning_rate": 2.085221291592293e-05, "loss": 1.5177, "step": 127870 }, { "epoch": 5.84, "learning_rate": 2.084992448166964e-05, "loss": 1.3566, "step": 127880 }, { "epoch": 5.84, "learning_rate": 2.0847636047416357e-05, "loss": 1.3371, "step": 127890 }, { "epoch": 5.84, "learning_rate": 2.0845347613163075e-05, "loss": 1.4272, "step": 127900 }, { "epoch": 5.84, "learning_rate": 2.084305917890979e-05, "loss": 1.5197, "step": 127910 }, { "epoch": 5.84, "learning_rate": 2.0840770744656507e-05, "loss": 1.5311, "step": 127920 }, { "epoch": 5.84, "learning_rate": 2.0838482310403224e-05, "loss": 1.5956, "step": 127930 }, { "epoch": 5.84, "learning_rate": 2.0836193876149938e-05, "loss": 1.493, "step": 127940 }, { "epoch": 5.84, "learning_rate": 2.0833905441896656e-05, "loss": 1.4135, "step": 127950 }, { "epoch": 5.84, "learning_rate": 2.0831617007643373e-05, "loss": 1.6328, "step": 127960 }, { "epoch": 5.84, "learning_rate": 2.0829328573390087e-05, "loss": 1.3477, "step": 127970 }, { "epoch": 5.84, "learning_rate": 2.08270401391368e-05, "loss": 1.5753, "step": 127980 }, { "epoch": 5.84, "learning_rate": 2.082475170488352e-05, "loss": 1.4613, "step": 127990 }, { "epoch": 5.84, "learning_rate": 2.0822463270630237e-05, "loss": 1.5341, "step": 128000 }, { "epoch": 5.85, "learning_rate": 2.082017483637695e-05, "loss": 1.4766, "step": 128010 }, { "epoch": 5.85, "learning_rate": 2.0817886402123668e-05, "loss": 1.4071, "step": 128020 }, { "epoch": 5.85, "learning_rate": 2.0815597967870386e-05, "loss": 1.4786, "step": 128030 }, { "epoch": 5.85, "learning_rate": 2.08133095336171e-05, "loss": 1.4432, "step": 128040 }, { "epoch": 5.85, "learning_rate": 2.0811021099363817e-05, "loss": 1.5357, "step": 128050 }, { "epoch": 5.85, "learning_rate": 2.0808732665110535e-05, "loss": 1.2515, "step": 128060 }, { "epoch": 5.85, "learning_rate": 2.0806444230857246e-05, "loss": 1.4586, "step": 128070 }, { "epoch": 5.85, "learning_rate": 2.0804155796603963e-05, "loss": 1.5036, "step": 128080 }, { "epoch": 5.85, "learning_rate": 2.080186736235068e-05, "loss": 1.4251, "step": 128090 }, { "epoch": 5.85, "learning_rate": 2.0799578928097395e-05, "loss": 1.5054, "step": 128100 }, { "epoch": 5.85, "learning_rate": 2.0797290493844112e-05, "loss": 1.3071, "step": 128110 }, { "epoch": 5.85, "learning_rate": 2.079500205959083e-05, "loss": 1.4471, "step": 128120 }, { "epoch": 5.85, "learning_rate": 2.0792713625337544e-05, "loss": 1.5508, "step": 128130 }, { "epoch": 5.85, "learning_rate": 2.079042519108426e-05, "loss": 1.5793, "step": 128140 }, { "epoch": 5.85, "learning_rate": 2.078813675683098e-05, "loss": 1.3569, "step": 128150 }, { "epoch": 5.85, "learning_rate": 2.0785848322577693e-05, "loss": 1.4439, "step": 128160 }, { "epoch": 5.85, "learning_rate": 2.0783559888324407e-05, "loss": 1.5561, "step": 128170 }, { "epoch": 5.85, "learning_rate": 2.0781271454071125e-05, "loss": 1.4103, "step": 128180 }, { "epoch": 5.85, "learning_rate": 2.0778983019817842e-05, "loss": 1.364, "step": 128190 }, { "epoch": 5.85, "learning_rate": 2.0776694585564557e-05, "loss": 1.4469, "step": 128200 }, { "epoch": 5.85, "learning_rate": 2.0774406151311274e-05, "loss": 1.5619, "step": 128210 }, { "epoch": 5.85, "learning_rate": 2.077211771705799e-05, "loss": 1.3944, "step": 128220 }, { "epoch": 5.86, "learning_rate": 2.0769829282804706e-05, "loss": 1.5462, "step": 128230 }, { "epoch": 5.86, "learning_rate": 2.0767540848551423e-05, "loss": 1.3433, "step": 128240 }, { "epoch": 5.86, "learning_rate": 2.076525241429814e-05, "loss": 1.4502, "step": 128250 }, { "epoch": 5.86, "learning_rate": 2.0762963980044855e-05, "loss": 1.3596, "step": 128260 }, { "epoch": 5.86, "learning_rate": 2.076067554579157e-05, "loss": 1.6451, "step": 128270 }, { "epoch": 5.86, "learning_rate": 2.0758387111538287e-05, "loss": 1.5307, "step": 128280 }, { "epoch": 5.86, "learning_rate": 2.0756098677285e-05, "loss": 1.4516, "step": 128290 }, { "epoch": 5.86, "learning_rate": 2.0753810243031718e-05, "loss": 1.729, "step": 128300 }, { "epoch": 5.86, "learning_rate": 2.0751521808778436e-05, "loss": 1.4982, "step": 128310 }, { "epoch": 5.86, "learning_rate": 2.074923337452515e-05, "loss": 1.5779, "step": 128320 }, { "epoch": 5.86, "learning_rate": 2.0746944940271867e-05, "loss": 1.4343, "step": 128330 }, { "epoch": 5.86, "learning_rate": 2.0744656506018585e-05, "loss": 1.4048, "step": 128340 }, { "epoch": 5.86, "learning_rate": 2.07423680717653e-05, "loss": 1.4486, "step": 128350 }, { "epoch": 5.86, "learning_rate": 2.0740079637512017e-05, "loss": 1.3301, "step": 128360 }, { "epoch": 5.86, "learning_rate": 2.073779120325873e-05, "loss": 1.5416, "step": 128370 }, { "epoch": 5.86, "learning_rate": 2.0735502769005445e-05, "loss": 1.3577, "step": 128380 }, { "epoch": 5.86, "learning_rate": 2.0733214334752162e-05, "loss": 1.4023, "step": 128390 }, { "epoch": 5.86, "learning_rate": 2.073092590049888e-05, "loss": 1.5102, "step": 128400 }, { "epoch": 5.86, "learning_rate": 2.0728637466245594e-05, "loss": 1.3786, "step": 128410 }, { "epoch": 5.86, "learning_rate": 2.072634903199231e-05, "loss": 1.2209, "step": 128420 }, { "epoch": 5.86, "learning_rate": 2.072406059773903e-05, "loss": 1.4415, "step": 128430 }, { "epoch": 5.86, "learning_rate": 2.0721772163485743e-05, "loss": 1.481, "step": 128440 }, { "epoch": 5.87, "learning_rate": 2.071948372923246e-05, "loss": 1.5435, "step": 128450 }, { "epoch": 5.87, "learning_rate": 2.0717195294979178e-05, "loss": 1.5258, "step": 128460 }, { "epoch": 5.87, "learning_rate": 2.0714906860725892e-05, "loss": 1.4842, "step": 128470 }, { "epoch": 5.87, "learning_rate": 2.0712618426472607e-05, "loss": 1.3128, "step": 128480 }, { "epoch": 5.87, "learning_rate": 2.0710329992219324e-05, "loss": 1.3613, "step": 128490 }, { "epoch": 5.87, "learning_rate": 2.070804155796604e-05, "loss": 1.5773, "step": 128500 }, { "epoch": 5.87, "learning_rate": 2.0705753123712756e-05, "loss": 1.5051, "step": 128510 }, { "epoch": 5.87, "learning_rate": 2.0703464689459473e-05, "loss": 1.3695, "step": 128520 }, { "epoch": 5.87, "learning_rate": 2.070117625520619e-05, "loss": 1.4841, "step": 128530 }, { "epoch": 5.87, "learning_rate": 2.0698887820952905e-05, "loss": 1.6563, "step": 128540 }, { "epoch": 5.87, "learning_rate": 2.0696599386699622e-05, "loss": 1.3454, "step": 128550 }, { "epoch": 5.87, "learning_rate": 2.069431095244634e-05, "loss": 1.535, "step": 128560 }, { "epoch": 5.87, "learning_rate": 2.069202251819305e-05, "loss": 1.5687, "step": 128570 }, { "epoch": 5.87, "learning_rate": 2.0689734083939768e-05, "loss": 1.4866, "step": 128580 }, { "epoch": 5.87, "learning_rate": 2.0687445649686486e-05, "loss": 1.6993, "step": 128590 }, { "epoch": 5.87, "learning_rate": 2.06851572154332e-05, "loss": 1.4841, "step": 128600 }, { "epoch": 5.87, "learning_rate": 2.0682868781179917e-05, "loss": 1.41, "step": 128610 }, { "epoch": 5.87, "learning_rate": 2.0680580346926635e-05, "loss": 1.3241, "step": 128620 }, { "epoch": 5.87, "learning_rate": 2.067829191267335e-05, "loss": 1.3596, "step": 128630 }, { "epoch": 5.87, "learning_rate": 2.0676003478420067e-05, "loss": 1.3983, "step": 128640 }, { "epoch": 5.87, "learning_rate": 2.0673715044166784e-05, "loss": 1.4318, "step": 128650 }, { "epoch": 5.87, "learning_rate": 2.0671426609913498e-05, "loss": 1.5464, "step": 128660 }, { "epoch": 5.88, "learning_rate": 2.0669138175660212e-05, "loss": 1.354, "step": 128670 }, { "epoch": 5.88, "learning_rate": 2.066684974140693e-05, "loss": 1.6051, "step": 128680 }, { "epoch": 5.88, "learning_rate": 2.0664561307153647e-05, "loss": 1.5139, "step": 128690 }, { "epoch": 5.88, "learning_rate": 2.066227287290036e-05, "loss": 1.4376, "step": 128700 }, { "epoch": 5.88, "learning_rate": 2.065998443864708e-05, "loss": 1.433, "step": 128710 }, { "epoch": 5.88, "learning_rate": 2.0657696004393797e-05, "loss": 1.5559, "step": 128720 }, { "epoch": 5.88, "learning_rate": 2.065540757014051e-05, "loss": 1.6084, "step": 128730 }, { "epoch": 5.88, "learning_rate": 2.0653119135887228e-05, "loss": 1.3634, "step": 128740 }, { "epoch": 5.88, "learning_rate": 2.0650830701633946e-05, "loss": 1.4671, "step": 128750 }, { "epoch": 5.88, "learning_rate": 2.0648542267380656e-05, "loss": 1.3565, "step": 128760 }, { "epoch": 5.88, "learning_rate": 2.0646253833127374e-05, "loss": 1.3292, "step": 128770 }, { "epoch": 5.88, "learning_rate": 2.064396539887409e-05, "loss": 1.54, "step": 128780 }, { "epoch": 5.88, "learning_rate": 2.0641676964620806e-05, "loss": 1.288, "step": 128790 }, { "epoch": 5.88, "learning_rate": 2.0639388530367523e-05, "loss": 1.4556, "step": 128800 }, { "epoch": 5.88, "learning_rate": 2.063710009611424e-05, "loss": 1.5534, "step": 128810 }, { "epoch": 5.88, "learning_rate": 2.0634811661860955e-05, "loss": 1.4043, "step": 128820 }, { "epoch": 5.88, "learning_rate": 2.0632523227607672e-05, "loss": 1.2935, "step": 128830 }, { "epoch": 5.88, "learning_rate": 2.063023479335439e-05, "loss": 1.293, "step": 128840 }, { "epoch": 5.88, "learning_rate": 2.0627946359101104e-05, "loss": 1.6486, "step": 128850 }, { "epoch": 5.88, "learning_rate": 2.0625657924847818e-05, "loss": 1.3484, "step": 128860 }, { "epoch": 5.88, "learning_rate": 2.0623369490594536e-05, "loss": 1.3685, "step": 128870 }, { "epoch": 5.88, "learning_rate": 2.0621081056341253e-05, "loss": 1.422, "step": 128880 }, { "epoch": 5.89, "learning_rate": 2.0618792622087967e-05, "loss": 1.3527, "step": 128890 }, { "epoch": 5.89, "learning_rate": 2.0616504187834685e-05, "loss": 1.4461, "step": 128900 }, { "epoch": 5.89, "learning_rate": 2.0614215753581402e-05, "loss": 1.3249, "step": 128910 }, { "epoch": 5.89, "learning_rate": 2.0611927319328116e-05, "loss": 1.3589, "step": 128920 }, { "epoch": 5.89, "learning_rate": 2.0609638885074834e-05, "loss": 1.3439, "step": 128930 }, { "epoch": 5.89, "learning_rate": 2.0607350450821548e-05, "loss": 1.4626, "step": 128940 }, { "epoch": 5.89, "learning_rate": 2.0605062016568266e-05, "loss": 1.4129, "step": 128950 }, { "epoch": 5.89, "learning_rate": 2.060277358231498e-05, "loss": 1.4571, "step": 128960 }, { "epoch": 5.89, "learning_rate": 2.0600485148061697e-05, "loss": 1.4791, "step": 128970 }, { "epoch": 5.89, "learning_rate": 2.059819671380841e-05, "loss": 1.3136, "step": 128980 }, { "epoch": 5.89, "learning_rate": 2.059590827955513e-05, "loss": 1.4845, "step": 128990 }, { "epoch": 5.89, "learning_rate": 2.0593619845301846e-05, "loss": 1.5878, "step": 129000 }, { "epoch": 5.89, "learning_rate": 2.059133141104856e-05, "loss": 1.5694, "step": 129010 }, { "epoch": 5.89, "learning_rate": 2.0589042976795278e-05, "loss": 1.5787, "step": 129020 }, { "epoch": 5.89, "learning_rate": 2.0586754542541996e-05, "loss": 1.3409, "step": 129030 }, { "epoch": 5.89, "learning_rate": 2.058446610828871e-05, "loss": 1.3274, "step": 129040 }, { "epoch": 5.89, "learning_rate": 2.0582177674035427e-05, "loss": 1.3599, "step": 129050 }, { "epoch": 5.89, "learning_rate": 2.057988923978214e-05, "loss": 1.4218, "step": 129060 }, { "epoch": 5.89, "learning_rate": 2.0577600805528856e-05, "loss": 1.3856, "step": 129070 }, { "epoch": 5.89, "learning_rate": 2.0575312371275573e-05, "loss": 1.4765, "step": 129080 }, { "epoch": 5.89, "learning_rate": 2.057302393702229e-05, "loss": 1.3789, "step": 129090 }, { "epoch": 5.9, "learning_rate": 2.0570735502769005e-05, "loss": 1.4966, "step": 129100 }, { "epoch": 5.9, "learning_rate": 2.0568447068515722e-05, "loss": 1.482, "step": 129110 }, { "epoch": 5.9, "learning_rate": 2.056615863426244e-05, "loss": 1.2209, "step": 129120 }, { "epoch": 5.9, "learning_rate": 2.0563870200009154e-05, "loss": 1.3836, "step": 129130 }, { "epoch": 5.9, "learning_rate": 2.056158176575587e-05, "loss": 1.4764, "step": 129140 }, { "epoch": 5.9, "learning_rate": 2.055929333150259e-05, "loss": 1.4667, "step": 129150 }, { "epoch": 5.9, "learning_rate": 2.0557004897249303e-05, "loss": 1.4031, "step": 129160 }, { "epoch": 5.9, "learning_rate": 2.0554716462996017e-05, "loss": 1.4477, "step": 129170 }, { "epoch": 5.9, "learning_rate": 2.0552428028742735e-05, "loss": 1.4155, "step": 129180 }, { "epoch": 5.9, "learning_rate": 2.0550139594489452e-05, "loss": 1.6512, "step": 129190 }, { "epoch": 5.9, "learning_rate": 2.0547851160236166e-05, "loss": 1.5199, "step": 129200 }, { "epoch": 5.9, "learning_rate": 2.0545562725982884e-05, "loss": 1.595, "step": 129210 }, { "epoch": 5.9, "learning_rate": 2.05432742917296e-05, "loss": 1.4959, "step": 129220 }, { "epoch": 5.9, "learning_rate": 2.0540985857476316e-05, "loss": 1.4843, "step": 129230 }, { "epoch": 5.9, "learning_rate": 2.0538697423223033e-05, "loss": 1.4156, "step": 129240 }, { "epoch": 5.9, "learning_rate": 2.053640898896975e-05, "loss": 1.5207, "step": 129250 }, { "epoch": 5.9, "learning_rate": 2.053412055471646e-05, "loss": 1.4053, "step": 129260 }, { "epoch": 5.9, "learning_rate": 2.053183212046318e-05, "loss": 1.4576, "step": 129270 }, { "epoch": 5.9, "learning_rate": 2.0529543686209896e-05, "loss": 1.472, "step": 129280 }, { "epoch": 5.9, "learning_rate": 2.052725525195661e-05, "loss": 1.4169, "step": 129290 }, { "epoch": 5.9, "learning_rate": 2.0524966817703328e-05, "loss": 1.5355, "step": 129300 }, { "epoch": 5.9, "learning_rate": 2.0522678383450046e-05, "loss": 1.4312, "step": 129310 }, { "epoch": 5.91, "learning_rate": 2.052038994919676e-05, "loss": 1.5333, "step": 129320 }, { "epoch": 5.91, "learning_rate": 2.0518101514943477e-05, "loss": 1.4583, "step": 129330 }, { "epoch": 5.91, "learning_rate": 2.0515813080690195e-05, "loss": 1.4705, "step": 129340 }, { "epoch": 5.91, "learning_rate": 2.051352464643691e-05, "loss": 1.3895, "step": 129350 }, { "epoch": 5.91, "learning_rate": 2.0511236212183623e-05, "loss": 1.3954, "step": 129360 }, { "epoch": 5.91, "learning_rate": 2.050894777793034e-05, "loss": 1.4709, "step": 129370 }, { "epoch": 5.91, "learning_rate": 2.0506659343677058e-05, "loss": 1.3689, "step": 129380 }, { "epoch": 5.91, "learning_rate": 2.0504370909423772e-05, "loss": 1.6696, "step": 129390 }, { "epoch": 5.91, "learning_rate": 2.050208247517049e-05, "loss": 1.362, "step": 129400 }, { "epoch": 5.91, "learning_rate": 2.0499794040917207e-05, "loss": 1.5003, "step": 129410 }, { "epoch": 5.91, "learning_rate": 2.049750560666392e-05, "loss": 1.5198, "step": 129420 }, { "epoch": 5.91, "learning_rate": 2.049521717241064e-05, "loss": 1.3474, "step": 129430 }, { "epoch": 5.91, "learning_rate": 2.0492928738157356e-05, "loss": 1.5162, "step": 129440 }, { "epoch": 5.91, "learning_rate": 2.049064030390407e-05, "loss": 1.3306, "step": 129450 }, { "epoch": 5.91, "learning_rate": 2.0488351869650785e-05, "loss": 1.5814, "step": 129460 }, { "epoch": 5.91, "learning_rate": 2.0486063435397502e-05, "loss": 1.5968, "step": 129470 }, { "epoch": 5.91, "learning_rate": 2.0483775001144216e-05, "loss": 1.4228, "step": 129480 }, { "epoch": 5.91, "learning_rate": 2.0481486566890934e-05, "loss": 1.4883, "step": 129490 }, { "epoch": 5.91, "learning_rate": 2.047919813263765e-05, "loss": 1.3376, "step": 129500 }, { "epoch": 5.91, "learning_rate": 2.0476909698384366e-05, "loss": 1.4682, "step": 129510 }, { "epoch": 5.91, "learning_rate": 2.0474621264131083e-05, "loss": 1.3426, "step": 129520 }, { "epoch": 5.91, "learning_rate": 2.04723328298778e-05, "loss": 1.3216, "step": 129530 }, { "epoch": 5.92, "learning_rate": 2.0470044395624515e-05, "loss": 1.3783, "step": 129540 }, { "epoch": 5.92, "learning_rate": 2.046775596137123e-05, "loss": 1.4561, "step": 129550 }, { "epoch": 5.92, "learning_rate": 2.0465467527117946e-05, "loss": 1.5988, "step": 129560 }, { "epoch": 5.92, "learning_rate": 2.046317909286466e-05, "loss": 1.4629, "step": 129570 }, { "epoch": 5.92, "learning_rate": 2.0460890658611378e-05, "loss": 1.4292, "step": 129580 }, { "epoch": 5.92, "learning_rate": 2.0458602224358096e-05, "loss": 1.5663, "step": 129590 }, { "epoch": 5.92, "learning_rate": 2.045631379010481e-05, "loss": 1.3105, "step": 129600 }, { "epoch": 5.92, "learning_rate": 2.0454025355851527e-05, "loss": 1.4942, "step": 129610 }, { "epoch": 5.92, "learning_rate": 2.0451736921598245e-05, "loss": 1.4434, "step": 129620 }, { "epoch": 5.92, "learning_rate": 2.044944848734496e-05, "loss": 1.4515, "step": 129630 }, { "epoch": 5.92, "learning_rate": 2.0447160053091676e-05, "loss": 1.5135, "step": 129640 }, { "epoch": 5.92, "learning_rate": 2.044487161883839e-05, "loss": 1.4676, "step": 129650 }, { "epoch": 5.92, "learning_rate": 2.0442583184585108e-05, "loss": 1.3611, "step": 129660 }, { "epoch": 5.92, "learning_rate": 2.0440294750331822e-05, "loss": 1.5351, "step": 129670 }, { "epoch": 5.92, "learning_rate": 2.043800631607854e-05, "loss": 1.4043, "step": 129680 }, { "epoch": 5.92, "learning_rate": 2.0435717881825257e-05, "loss": 1.4816, "step": 129690 }, { "epoch": 5.92, "learning_rate": 2.043342944757197e-05, "loss": 1.4543, "step": 129700 }, { "epoch": 5.92, "learning_rate": 2.043114101331869e-05, "loss": 1.6009, "step": 129710 }, { "epoch": 5.92, "learning_rate": 2.0428852579065406e-05, "loss": 1.387, "step": 129720 }, { "epoch": 5.92, "learning_rate": 2.042656414481212e-05, "loss": 1.556, "step": 129730 }, { "epoch": 5.92, "learning_rate": 2.0424275710558838e-05, "loss": 1.539, "step": 129740 }, { "epoch": 5.92, "learning_rate": 2.0421987276305552e-05, "loss": 1.5317, "step": 129750 }, { "epoch": 5.93, "learning_rate": 2.0419698842052266e-05, "loss": 1.3993, "step": 129760 }, { "epoch": 5.93, "learning_rate": 2.0417410407798984e-05, "loss": 1.5169, "step": 129770 }, { "epoch": 5.93, "learning_rate": 2.04151219735457e-05, "loss": 1.5269, "step": 129780 }, { "epoch": 5.93, "learning_rate": 2.0412833539292416e-05, "loss": 1.4525, "step": 129790 }, { "epoch": 5.93, "learning_rate": 2.0410545105039133e-05, "loss": 1.4389, "step": 129800 }, { "epoch": 5.93, "learning_rate": 2.040825667078585e-05, "loss": 1.2842, "step": 129810 }, { "epoch": 5.93, "learning_rate": 2.0405968236532565e-05, "loss": 1.3178, "step": 129820 }, { "epoch": 5.93, "learning_rate": 2.0403679802279282e-05, "loss": 1.5768, "step": 129830 }, { "epoch": 5.93, "learning_rate": 2.0401391368026e-05, "loss": 1.3394, "step": 129840 }, { "epoch": 5.93, "learning_rate": 2.0399102933772714e-05, "loss": 1.3952, "step": 129850 }, { "epoch": 5.93, "learning_rate": 2.0396814499519428e-05, "loss": 1.5706, "step": 129860 }, { "epoch": 5.93, "learning_rate": 2.0394526065266146e-05, "loss": 1.4567, "step": 129870 }, { "epoch": 5.93, "learning_rate": 2.0392237631012863e-05, "loss": 1.3744, "step": 129880 }, { "epoch": 5.93, "learning_rate": 2.0389949196759577e-05, "loss": 1.4313, "step": 129890 }, { "epoch": 5.93, "learning_rate": 2.0387660762506295e-05, "loss": 1.3156, "step": 129900 }, { "epoch": 5.93, "learning_rate": 2.0385372328253012e-05, "loss": 1.4149, "step": 129910 }, { "epoch": 5.93, "learning_rate": 2.0383083893999726e-05, "loss": 1.3646, "step": 129920 }, { "epoch": 5.93, "learning_rate": 2.0380795459746444e-05, "loss": 1.4662, "step": 129930 }, { "epoch": 5.93, "learning_rate": 2.037850702549316e-05, "loss": 1.3509, "step": 129940 }, { "epoch": 5.93, "learning_rate": 2.0376218591239872e-05, "loss": 1.4388, "step": 129950 }, { "epoch": 5.93, "learning_rate": 2.037393015698659e-05, "loss": 1.4435, "step": 129960 }, { "epoch": 5.93, "learning_rate": 2.0371641722733307e-05, "loss": 1.4371, "step": 129970 }, { "epoch": 5.94, "learning_rate": 2.036935328848002e-05, "loss": 1.4265, "step": 129980 }, { "epoch": 5.94, "learning_rate": 2.036706485422674e-05, "loss": 1.6225, "step": 129990 }, { "epoch": 5.94, "learning_rate": 2.0364776419973456e-05, "loss": 1.5005, "step": 130000 }, { "epoch": 5.94, "learning_rate": 2.036248798572017e-05, "loss": 1.4848, "step": 130010 }, { "epoch": 5.94, "learning_rate": 2.0360199551466888e-05, "loss": 1.4941, "step": 130020 }, { "epoch": 5.94, "learning_rate": 2.0357911117213606e-05, "loss": 1.5896, "step": 130030 }, { "epoch": 5.94, "learning_rate": 2.035562268296032e-05, "loss": 1.399, "step": 130040 }, { "epoch": 5.94, "learning_rate": 2.0353334248707034e-05, "loss": 1.454, "step": 130050 }, { "epoch": 5.94, "learning_rate": 2.035104581445375e-05, "loss": 1.3358, "step": 130060 }, { "epoch": 5.94, "learning_rate": 2.034875738020047e-05, "loss": 1.4325, "step": 130070 }, { "epoch": 5.94, "learning_rate": 2.0346468945947183e-05, "loss": 1.4782, "step": 130080 }, { "epoch": 5.94, "learning_rate": 2.03441805116939e-05, "loss": 1.4001, "step": 130090 }, { "epoch": 5.94, "learning_rate": 2.0341892077440615e-05, "loss": 1.553, "step": 130100 }, { "epoch": 5.94, "learning_rate": 2.0339603643187332e-05, "loss": 1.3013, "step": 130110 }, { "epoch": 5.94, "learning_rate": 2.033731520893405e-05, "loss": 1.5281, "step": 130120 }, { "epoch": 5.94, "learning_rate": 2.0335026774680764e-05, "loss": 1.4878, "step": 130130 }, { "epoch": 5.94, "learning_rate": 2.033273834042748e-05, "loss": 1.5983, "step": 130140 }, { "epoch": 5.94, "learning_rate": 2.0330449906174195e-05, "loss": 1.499, "step": 130150 }, { "epoch": 5.94, "learning_rate": 2.0328161471920913e-05, "loss": 1.4345, "step": 130160 }, { "epoch": 5.94, "learning_rate": 2.0325873037667627e-05, "loss": 1.5539, "step": 130170 }, { "epoch": 5.94, "learning_rate": 2.0323584603414345e-05, "loss": 1.3071, "step": 130180 }, { "epoch": 5.94, "learning_rate": 2.0321296169161062e-05, "loss": 1.583, "step": 130190 }, { "epoch": 5.95, "learning_rate": 2.0319007734907776e-05, "loss": 1.5263, "step": 130200 }, { "epoch": 5.95, "learning_rate": 2.0316719300654494e-05, "loss": 1.5804, "step": 130210 }, { "epoch": 5.95, "learning_rate": 2.031443086640121e-05, "loss": 1.5625, "step": 130220 }, { "epoch": 5.95, "learning_rate": 2.0312142432147925e-05, "loss": 1.3865, "step": 130230 }, { "epoch": 5.95, "learning_rate": 2.0309853997894643e-05, "loss": 1.3966, "step": 130240 }, { "epoch": 5.95, "learning_rate": 2.0307565563641357e-05, "loss": 1.5162, "step": 130250 }, { "epoch": 5.95, "learning_rate": 2.030527712938807e-05, "loss": 1.6513, "step": 130260 }, { "epoch": 5.95, "learning_rate": 2.030298869513479e-05, "loss": 1.3721, "step": 130270 }, { "epoch": 5.95, "learning_rate": 2.0300700260881506e-05, "loss": 1.5666, "step": 130280 }, { "epoch": 5.95, "learning_rate": 2.029841182662822e-05, "loss": 1.5248, "step": 130290 }, { "epoch": 5.95, "learning_rate": 2.0296123392374938e-05, "loss": 1.4662, "step": 130300 }, { "epoch": 5.95, "learning_rate": 2.0293834958121655e-05, "loss": 1.2507, "step": 130310 }, { "epoch": 5.95, "learning_rate": 2.029154652386837e-05, "loss": 1.5378, "step": 130320 }, { "epoch": 5.95, "learning_rate": 2.0289258089615087e-05, "loss": 1.4369, "step": 130330 }, { "epoch": 5.95, "learning_rate": 2.02869696553618e-05, "loss": 1.3105, "step": 130340 }, { "epoch": 5.95, "learning_rate": 2.028468122110852e-05, "loss": 1.4233, "step": 130350 }, { "epoch": 5.95, "learning_rate": 2.0282392786855233e-05, "loss": 1.638, "step": 130360 }, { "epoch": 5.95, "learning_rate": 2.028010435260195e-05, "loss": 1.4494, "step": 130370 }, { "epoch": 5.95, "learning_rate": 2.0277815918348668e-05, "loss": 1.4067, "step": 130380 }, { "epoch": 5.95, "learning_rate": 2.0275527484095382e-05, "loss": 1.3171, "step": 130390 }, { "epoch": 5.95, "learning_rate": 2.02732390498421e-05, "loss": 1.4329, "step": 130400 }, { "epoch": 5.95, "learning_rate": 2.0270950615588817e-05, "loss": 1.5297, "step": 130410 }, { "epoch": 5.96, "learning_rate": 2.026866218133553e-05, "loss": 1.4946, "step": 130420 }, { "epoch": 5.96, "learning_rate": 2.026637374708225e-05, "loss": 1.4283, "step": 130430 }, { "epoch": 5.96, "learning_rate": 2.0264085312828963e-05, "loss": 1.3537, "step": 130440 }, { "epoch": 5.96, "learning_rate": 2.0261796878575677e-05, "loss": 1.5258, "step": 130450 }, { "epoch": 5.96, "learning_rate": 2.0259508444322395e-05, "loss": 1.3984, "step": 130460 }, { "epoch": 5.96, "learning_rate": 2.0257220010069112e-05, "loss": 1.5116, "step": 130470 }, { "epoch": 5.96, "learning_rate": 2.0254931575815826e-05, "loss": 1.4128, "step": 130480 }, { "epoch": 5.96, "learning_rate": 2.0252643141562544e-05, "loss": 1.367, "step": 130490 }, { "epoch": 5.96, "learning_rate": 2.025035470730926e-05, "loss": 1.3949, "step": 130500 }, { "epoch": 5.96, "learning_rate": 2.0248066273055975e-05, "loss": 1.4119, "step": 130510 }, { "epoch": 5.96, "learning_rate": 2.0245777838802693e-05, "loss": 1.5178, "step": 130520 }, { "epoch": 5.96, "learning_rate": 2.024348940454941e-05, "loss": 1.6448, "step": 130530 }, { "epoch": 5.96, "learning_rate": 2.0241200970296125e-05, "loss": 1.4913, "step": 130540 }, { "epoch": 5.96, "learning_rate": 2.023891253604284e-05, "loss": 1.4741, "step": 130550 }, { "epoch": 5.96, "learning_rate": 2.0236624101789556e-05, "loss": 1.5324, "step": 130560 }, { "epoch": 5.96, "learning_rate": 2.0234335667536274e-05, "loss": 1.52, "step": 130570 }, { "epoch": 5.96, "learning_rate": 2.0232047233282988e-05, "loss": 1.5034, "step": 130580 }, { "epoch": 5.96, "learning_rate": 2.0229758799029705e-05, "loss": 1.4617, "step": 130590 }, { "epoch": 5.96, "learning_rate": 2.0227470364776423e-05, "loss": 1.4463, "step": 130600 }, { "epoch": 5.96, "learning_rate": 2.0225181930523137e-05, "loss": 1.3164, "step": 130610 }, { "epoch": 5.96, "learning_rate": 2.0222893496269855e-05, "loss": 1.3581, "step": 130620 }, { "epoch": 5.96, "learning_rate": 2.0220605062016572e-05, "loss": 1.4972, "step": 130630 }, { "epoch": 5.97, "learning_rate": 2.0218316627763283e-05, "loss": 1.383, "step": 130640 }, { "epoch": 5.97, "learning_rate": 2.021602819351e-05, "loss": 1.4216, "step": 130650 }, { "epoch": 5.97, "learning_rate": 2.0213739759256718e-05, "loss": 1.5324, "step": 130660 }, { "epoch": 5.97, "learning_rate": 2.0211451325003432e-05, "loss": 1.4428, "step": 130670 }, { "epoch": 5.97, "learning_rate": 2.020916289075015e-05, "loss": 1.6496, "step": 130680 }, { "epoch": 5.97, "learning_rate": 2.0206874456496867e-05, "loss": 1.4953, "step": 130690 }, { "epoch": 5.97, "learning_rate": 2.020458602224358e-05, "loss": 1.4436, "step": 130700 }, { "epoch": 5.97, "learning_rate": 2.02022975879903e-05, "loss": 1.3305, "step": 130710 }, { "epoch": 5.97, "learning_rate": 2.0200009153737016e-05, "loss": 1.293, "step": 130720 }, { "epoch": 5.97, "learning_rate": 2.019772071948373e-05, "loss": 1.3721, "step": 130730 }, { "epoch": 5.97, "learning_rate": 2.0195432285230445e-05, "loss": 1.2665, "step": 130740 }, { "epoch": 5.97, "learning_rate": 2.0193143850977162e-05, "loss": 1.498, "step": 130750 }, { "epoch": 5.97, "learning_rate": 2.0190855416723876e-05, "loss": 1.3532, "step": 130760 }, { "epoch": 5.97, "learning_rate": 2.0188566982470594e-05, "loss": 1.295, "step": 130770 }, { "epoch": 5.97, "learning_rate": 2.018627854821731e-05, "loss": 1.4822, "step": 130780 }, { "epoch": 5.97, "learning_rate": 2.0183990113964025e-05, "loss": 1.54, "step": 130790 }, { "epoch": 5.97, "learning_rate": 2.0181701679710743e-05, "loss": 1.2578, "step": 130800 }, { "epoch": 5.97, "learning_rate": 2.017941324545746e-05, "loss": 1.5514, "step": 130810 }, { "epoch": 5.97, "learning_rate": 2.0177124811204175e-05, "loss": 1.5224, "step": 130820 }, { "epoch": 5.97, "learning_rate": 2.0174836376950892e-05, "loss": 1.4593, "step": 130830 }, { "epoch": 5.97, "learning_rate": 2.0172547942697606e-05, "loss": 1.4165, "step": 130840 }, { "epoch": 5.97, "learning_rate": 2.0170259508444324e-05, "loss": 1.5439, "step": 130850 }, { "epoch": 5.98, "learning_rate": 2.0167971074191038e-05, "loss": 1.4456, "step": 130860 }, { "epoch": 5.98, "learning_rate": 2.0165682639937755e-05, "loss": 1.4354, "step": 130870 }, { "epoch": 5.98, "learning_rate": 2.0163394205684473e-05, "loss": 1.8056, "step": 130880 }, { "epoch": 5.98, "learning_rate": 2.0161105771431187e-05, "loss": 1.315, "step": 130890 }, { "epoch": 5.98, "learning_rate": 2.0158817337177905e-05, "loss": 1.6119, "step": 130900 }, { "epoch": 5.98, "learning_rate": 2.0156528902924622e-05, "loss": 1.3516, "step": 130910 }, { "epoch": 5.98, "learning_rate": 2.0154240468671336e-05, "loss": 1.6047, "step": 130920 }, { "epoch": 5.98, "learning_rate": 2.0151952034418054e-05, "loss": 1.4995, "step": 130930 }, { "epoch": 5.98, "learning_rate": 2.0149663600164768e-05, "loss": 1.3145, "step": 130940 }, { "epoch": 5.98, "learning_rate": 2.0147375165911482e-05, "loss": 1.4779, "step": 130950 }, { "epoch": 5.98, "learning_rate": 2.01450867316582e-05, "loss": 1.4266, "step": 130960 }, { "epoch": 5.98, "learning_rate": 2.0142798297404917e-05, "loss": 1.451, "step": 130970 }, { "epoch": 5.98, "learning_rate": 2.014050986315163e-05, "loss": 1.4864, "step": 130980 }, { "epoch": 5.98, "learning_rate": 2.013822142889835e-05, "loss": 1.5054, "step": 130990 }, { "epoch": 5.98, "learning_rate": 2.0135932994645066e-05, "loss": 1.6562, "step": 131000 }, { "epoch": 5.98, "learning_rate": 2.013364456039178e-05, "loss": 1.4398, "step": 131010 }, { "epoch": 5.98, "learning_rate": 2.0131356126138498e-05, "loss": 1.4026, "step": 131020 }, { "epoch": 5.98, "learning_rate": 2.0129067691885215e-05, "loss": 1.5184, "step": 131030 }, { "epoch": 5.98, "learning_rate": 2.012677925763193e-05, "loss": 1.4201, "step": 131040 }, { "epoch": 5.98, "learning_rate": 2.0124490823378644e-05, "loss": 1.3799, "step": 131050 }, { "epoch": 5.98, "learning_rate": 2.012220238912536e-05, "loss": 1.4145, "step": 131060 }, { "epoch": 5.98, "learning_rate": 2.011991395487208e-05, "loss": 1.4862, "step": 131070 }, { "epoch": 5.99, "learning_rate": 2.0117625520618793e-05, "loss": 1.4934, "step": 131080 }, { "epoch": 5.99, "learning_rate": 2.011533708636551e-05, "loss": 1.527, "step": 131090 }, { "epoch": 5.99, "learning_rate": 2.0113048652112228e-05, "loss": 1.4734, "step": 131100 }, { "epoch": 5.99, "learning_rate": 2.0110760217858942e-05, "loss": 1.6312, "step": 131110 }, { "epoch": 5.99, "learning_rate": 2.010847178360566e-05, "loss": 1.3095, "step": 131120 }, { "epoch": 5.99, "learning_rate": 2.0106183349352374e-05, "loss": 1.3766, "step": 131130 }, { "epoch": 5.99, "learning_rate": 2.0103894915099088e-05, "loss": 1.4419, "step": 131140 }, { "epoch": 5.99, "learning_rate": 2.0101606480845805e-05, "loss": 1.3514, "step": 131150 }, { "epoch": 5.99, "learning_rate": 2.0099318046592523e-05, "loss": 1.5283, "step": 131160 }, { "epoch": 5.99, "learning_rate": 2.0097029612339237e-05, "loss": 1.3663, "step": 131170 }, { "epoch": 5.99, "learning_rate": 2.0094741178085955e-05, "loss": 1.4306, "step": 131180 }, { "epoch": 5.99, "learning_rate": 2.0092452743832672e-05, "loss": 1.5008, "step": 131190 }, { "epoch": 5.99, "learning_rate": 2.0090164309579386e-05, "loss": 1.4295, "step": 131200 }, { "epoch": 5.99, "learning_rate": 2.0087875875326104e-05, "loss": 1.381, "step": 131210 }, { "epoch": 5.99, "learning_rate": 2.008558744107282e-05, "loss": 1.36, "step": 131220 }, { "epoch": 5.99, "learning_rate": 2.0083299006819535e-05, "loss": 1.4728, "step": 131230 }, { "epoch": 5.99, "learning_rate": 2.008101057256625e-05, "loss": 1.4462, "step": 131240 }, { "epoch": 5.99, "learning_rate": 2.0078722138312967e-05, "loss": 1.4274, "step": 131250 }, { "epoch": 5.99, "learning_rate": 2.007643370405968e-05, "loss": 1.6125, "step": 131260 }, { "epoch": 5.99, "learning_rate": 2.00741452698064e-05, "loss": 1.4706, "step": 131270 }, { "epoch": 5.99, "learning_rate": 2.0071856835553116e-05, "loss": 1.5102, "step": 131280 }, { "epoch": 6.0, "learning_rate": 2.006956840129983e-05, "loss": 1.5209, "step": 131290 }, { "epoch": 6.0, "learning_rate": 2.0067279967046548e-05, "loss": 1.3337, "step": 131300 }, { "epoch": 6.0, "learning_rate": 2.0064991532793265e-05, "loss": 1.4761, "step": 131310 }, { "epoch": 6.0, "learning_rate": 2.006270309853998e-05, "loss": 1.434, "step": 131320 }, { "epoch": 6.0, "learning_rate": 2.0060414664286694e-05, "loss": 1.3998, "step": 131330 }, { "epoch": 6.0, "learning_rate": 2.005812623003341e-05, "loss": 1.3996, "step": 131340 }, { "epoch": 6.0, "learning_rate": 2.005583779578013e-05, "loss": 1.4676, "step": 131350 }, { "epoch": 6.0, "learning_rate": 2.0053549361526843e-05, "loss": 1.5241, "step": 131360 }, { "epoch": 6.0, "learning_rate": 2.005126092727356e-05, "loss": 1.603, "step": 131370 }, { "epoch": 6.0, "learning_rate": 2.0048972493020278e-05, "loss": 1.3712, "step": 131380 }, { "epoch": 6.0, "learning_rate": 2.0046684058766992e-05, "loss": 1.3348, "step": 131390 }, { "epoch": 6.0, "eval_cer": 0.6766227928174448, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.3648077249526978, "eval_runtime": 2693.4025, "eval_samples_per_second": 3.924, "eval_steps_per_second": 1.962, "eval_wer": 0.9927152317880795, "step": 131398 }, { "epoch": 6.0, "learning_rate": 2.004439562451371e-05, "loss": 1.5373, "step": 131400 }, { "epoch": 6.0, "learning_rate": 2.0042107190260427e-05, "loss": 1.427, "step": 131410 }, { "epoch": 6.0, "learning_rate": 2.003981875600714e-05, "loss": 1.4906, "step": 131420 }, { "epoch": 6.0, "learning_rate": 2.0037530321753855e-05, "loss": 1.4687, "step": 131430 }, { "epoch": 6.0, "learning_rate": 2.0035241887500573e-05, "loss": 1.5344, "step": 131440 }, { "epoch": 6.0, "learning_rate": 2.0032953453247287e-05, "loss": 1.2914, "step": 131450 }, { "epoch": 6.0, "learning_rate": 2.0030665018994004e-05, "loss": 1.4063, "step": 131460 }, { "epoch": 6.0, "learning_rate": 2.0028376584740722e-05, "loss": 1.3702, "step": 131470 }, { "epoch": 6.0, "learning_rate": 2.0026088150487436e-05, "loss": 1.4255, "step": 131480 }, { "epoch": 6.0, "learning_rate": 2.0023799716234154e-05, "loss": 1.4009, "step": 131490 }, { "epoch": 6.0, "learning_rate": 2.002151128198087e-05, "loss": 1.3904, "step": 131500 }, { "epoch": 6.01, "learning_rate": 2.0019222847727585e-05, "loss": 1.3625, "step": 131510 }, { "epoch": 6.01, "learning_rate": 2.0016934413474303e-05, "loss": 1.4827, "step": 131520 }, { "epoch": 6.01, "learning_rate": 2.0014645979221017e-05, "loss": 1.341, "step": 131530 }, { "epoch": 6.01, "learning_rate": 2.0012357544967734e-05, "loss": 1.289, "step": 131540 }, { "epoch": 6.01, "learning_rate": 2.001006911071445e-05, "loss": 1.423, "step": 131550 }, { "epoch": 6.01, "learning_rate": 2.0007780676461166e-05, "loss": 1.3026, "step": 131560 }, { "epoch": 6.01, "learning_rate": 2.0005492242207884e-05, "loss": 1.4156, "step": 131570 }, { "epoch": 6.01, "learning_rate": 2.0003203807954598e-05, "loss": 1.4345, "step": 131580 }, { "epoch": 6.01, "learning_rate": 2.0000915373701315e-05, "loss": 1.5037, "step": 131590 }, { "epoch": 6.01, "learning_rate": 1.9998626939448033e-05, "loss": 1.4336, "step": 131600 }, { "epoch": 6.01, "learning_rate": 1.9996338505194747e-05, "loss": 1.3492, "step": 131610 }, { "epoch": 6.01, "learning_rate": 1.9994050070941464e-05, "loss": 1.4316, "step": 131620 }, { "epoch": 6.01, "learning_rate": 1.999176163668818e-05, "loss": 1.6954, "step": 131630 }, { "epoch": 6.01, "learning_rate": 1.9989473202434893e-05, "loss": 1.4607, "step": 131640 }, { "epoch": 6.01, "learning_rate": 1.998718476818161e-05, "loss": 1.4158, "step": 131650 }, { "epoch": 6.01, "learning_rate": 1.9984896333928328e-05, "loss": 1.4256, "step": 131660 }, { "epoch": 6.01, "learning_rate": 1.9982607899675042e-05, "loss": 1.3773, "step": 131670 }, { "epoch": 6.01, "learning_rate": 1.998031946542176e-05, "loss": 1.4562, "step": 131680 }, { "epoch": 6.01, "learning_rate": 1.9978031031168477e-05, "loss": 1.3705, "step": 131690 }, { "epoch": 6.01, "learning_rate": 1.997574259691519e-05, "loss": 1.2692, "step": 131700 }, { "epoch": 6.01, "learning_rate": 1.997345416266191e-05, "loss": 1.4378, "step": 131710 }, { "epoch": 6.01, "learning_rate": 1.9971165728408626e-05, "loss": 1.4048, "step": 131720 }, { "epoch": 6.02, "learning_rate": 1.996887729415534e-05, "loss": 1.3839, "step": 131730 }, { "epoch": 6.02, "learning_rate": 1.9966588859902054e-05, "loss": 1.5403, "step": 131740 }, { "epoch": 6.02, "learning_rate": 1.9964300425648772e-05, "loss": 1.3772, "step": 131750 }, { "epoch": 6.02, "learning_rate": 1.996201199139549e-05, "loss": 1.2758, "step": 131760 }, { "epoch": 6.02, "learning_rate": 1.9959723557142204e-05, "loss": 1.3552, "step": 131770 }, { "epoch": 6.02, "learning_rate": 1.995743512288892e-05, "loss": 1.3816, "step": 131780 }, { "epoch": 6.02, "learning_rate": 1.995514668863564e-05, "loss": 1.2714, "step": 131790 }, { "epoch": 6.02, "learning_rate": 1.9952858254382353e-05, "loss": 1.3493, "step": 131800 }, { "epoch": 6.02, "learning_rate": 1.995056982012907e-05, "loss": 1.3441, "step": 131810 }, { "epoch": 6.02, "learning_rate": 1.9948281385875784e-05, "loss": 1.4997, "step": 131820 }, { "epoch": 6.02, "learning_rate": 1.99459929516225e-05, "loss": 1.3478, "step": 131830 }, { "epoch": 6.02, "learning_rate": 1.9943704517369216e-05, "loss": 1.4625, "step": 131840 }, { "epoch": 6.02, "learning_rate": 1.9941416083115934e-05, "loss": 1.5498, "step": 131850 }, { "epoch": 6.02, "learning_rate": 1.9939127648862648e-05, "loss": 1.2875, "step": 131860 }, { "epoch": 6.02, "learning_rate": 1.9936839214609365e-05, "loss": 1.296, "step": 131870 }, { "epoch": 6.02, "learning_rate": 1.9934550780356083e-05, "loss": 1.3584, "step": 131880 }, { "epoch": 6.02, "learning_rate": 1.9932262346102797e-05, "loss": 1.3746, "step": 131890 }, { "epoch": 6.02, "learning_rate": 1.9929973911849514e-05, "loss": 1.578, "step": 131900 }, { "epoch": 6.02, "learning_rate": 1.9927685477596232e-05, "loss": 1.3716, "step": 131910 }, { "epoch": 6.02, "learning_rate": 1.9925397043342943e-05, "loss": 1.2441, "step": 131920 }, { "epoch": 6.02, "learning_rate": 1.992310860908966e-05, "loss": 1.3168, "step": 131930 }, { "epoch": 6.02, "learning_rate": 1.9920820174836378e-05, "loss": 1.325, "step": 131940 }, { "epoch": 6.03, "learning_rate": 1.9918531740583092e-05, "loss": 1.3796, "step": 131950 }, { "epoch": 6.03, "learning_rate": 1.991624330632981e-05, "loss": 1.4505, "step": 131960 }, { "epoch": 6.03, "learning_rate": 1.9913954872076527e-05, "loss": 1.4922, "step": 131970 }, { "epoch": 6.03, "learning_rate": 1.991166643782324e-05, "loss": 1.4368, "step": 131980 }, { "epoch": 6.03, "learning_rate": 1.990937800356996e-05, "loss": 1.4546, "step": 131990 }, { "epoch": 6.03, "learning_rate": 1.9907089569316676e-05, "loss": 1.4042, "step": 132000 }, { "epoch": 6.03, "learning_rate": 1.990480113506339e-05, "loss": 1.507, "step": 132010 }, { "epoch": 6.03, "learning_rate": 1.9902512700810104e-05, "loss": 1.5271, "step": 132020 }, { "epoch": 6.03, "learning_rate": 1.9900224266556822e-05, "loss": 1.2656, "step": 132030 }, { "epoch": 6.03, "learning_rate": 1.989793583230354e-05, "loss": 1.4779, "step": 132040 }, { "epoch": 6.03, "learning_rate": 1.9895647398050254e-05, "loss": 1.3497, "step": 132050 }, { "epoch": 6.03, "learning_rate": 1.989335896379697e-05, "loss": 1.5162, "step": 132060 }, { "epoch": 6.03, "learning_rate": 1.989107052954369e-05, "loss": 1.3855, "step": 132070 }, { "epoch": 6.03, "learning_rate": 1.9888782095290403e-05, "loss": 1.5352, "step": 132080 }, { "epoch": 6.03, "learning_rate": 1.988649366103712e-05, "loss": 1.4029, "step": 132090 }, { "epoch": 6.03, "learning_rate": 1.9884205226783838e-05, "loss": 1.3638, "step": 132100 }, { "epoch": 6.03, "learning_rate": 1.9881916792530552e-05, "loss": 1.4364, "step": 132110 }, { "epoch": 6.03, "learning_rate": 1.9879628358277266e-05, "loss": 1.37, "step": 132120 }, { "epoch": 6.03, "learning_rate": 1.9877339924023984e-05, "loss": 1.4159, "step": 132130 }, { "epoch": 6.03, "learning_rate": 1.9875051489770698e-05, "loss": 1.4649, "step": 132140 }, { "epoch": 6.03, "learning_rate": 1.9872763055517415e-05, "loss": 1.4451, "step": 132150 }, { "epoch": 6.03, "learning_rate": 1.9870474621264133e-05, "loss": 1.3584, "step": 132160 }, { "epoch": 6.04, "learning_rate": 1.9868186187010847e-05, "loss": 1.4628, "step": 132170 }, { "epoch": 6.04, "learning_rate": 1.9865897752757564e-05, "loss": 1.5907, "step": 132180 }, { "epoch": 6.04, "learning_rate": 1.9863609318504282e-05, "loss": 1.3921, "step": 132190 }, { "epoch": 6.04, "learning_rate": 1.9861320884250996e-05, "loss": 1.3266, "step": 132200 }, { "epoch": 6.04, "learning_rate": 1.9859032449997714e-05, "loss": 1.4178, "step": 132210 }, { "epoch": 6.04, "learning_rate": 1.9856744015744428e-05, "loss": 1.4726, "step": 132220 }, { "epoch": 6.04, "learning_rate": 1.9854455581491145e-05, "loss": 1.337, "step": 132230 }, { "epoch": 6.04, "learning_rate": 1.985216714723786e-05, "loss": 1.5663, "step": 132240 }, { "epoch": 6.04, "learning_rate": 1.9849878712984577e-05, "loss": 1.3477, "step": 132250 }, { "epoch": 6.04, "learning_rate": 1.9847590278731294e-05, "loss": 1.386, "step": 132260 }, { "epoch": 6.04, "learning_rate": 1.984530184447801e-05, "loss": 1.6445, "step": 132270 }, { "epoch": 6.04, "learning_rate": 1.9843013410224726e-05, "loss": 1.4008, "step": 132280 }, { "epoch": 6.04, "learning_rate": 1.9840724975971444e-05, "loss": 1.4116, "step": 132290 }, { "epoch": 6.04, "learning_rate": 1.9838436541718158e-05, "loss": 1.4, "step": 132300 }, { "epoch": 6.04, "learning_rate": 1.9836148107464875e-05, "loss": 1.4341, "step": 132310 }, { "epoch": 6.04, "learning_rate": 1.983385967321159e-05, "loss": 1.5028, "step": 132320 }, { "epoch": 6.04, "learning_rate": 1.9831571238958303e-05, "loss": 1.502, "step": 132330 }, { "epoch": 6.04, "learning_rate": 1.982928280470502e-05, "loss": 1.3383, "step": 132340 }, { "epoch": 6.04, "learning_rate": 1.982699437045174e-05, "loss": 1.503, "step": 132350 }, { "epoch": 6.04, "learning_rate": 1.9824705936198453e-05, "loss": 1.5602, "step": 132360 }, { "epoch": 6.04, "learning_rate": 1.982241750194517e-05, "loss": 1.3265, "step": 132370 }, { "epoch": 6.04, "learning_rate": 1.9820129067691888e-05, "loss": 1.6121, "step": 132380 }, { "epoch": 6.05, "learning_rate": 1.9817840633438602e-05, "loss": 1.4843, "step": 132390 }, { "epoch": 6.05, "learning_rate": 1.981555219918532e-05, "loss": 1.3977, "step": 132400 }, { "epoch": 6.05, "learning_rate": 1.9813263764932037e-05, "loss": 1.3505, "step": 132410 }, { "epoch": 6.05, "learning_rate": 1.981097533067875e-05, "loss": 1.613, "step": 132420 }, { "epoch": 6.05, "learning_rate": 1.9808686896425465e-05, "loss": 1.3671, "step": 132430 }, { "epoch": 6.05, "learning_rate": 1.9806398462172183e-05, "loss": 1.5651, "step": 132440 }, { "epoch": 6.05, "learning_rate": 1.9804110027918897e-05, "loss": 1.4727, "step": 132450 }, { "epoch": 6.05, "learning_rate": 1.9801821593665614e-05, "loss": 1.4895, "step": 132460 }, { "epoch": 6.05, "learning_rate": 1.9799533159412332e-05, "loss": 1.4602, "step": 132470 }, { "epoch": 6.05, "learning_rate": 1.9797244725159046e-05, "loss": 1.4838, "step": 132480 }, { "epoch": 6.05, "learning_rate": 1.9794956290905764e-05, "loss": 1.5497, "step": 132490 }, { "epoch": 6.05, "learning_rate": 1.979266785665248e-05, "loss": 1.4958, "step": 132500 }, { "epoch": 6.05, "learning_rate": 1.9790379422399195e-05, "loss": 1.4259, "step": 132510 }, { "epoch": 6.05, "learning_rate": 1.978809098814591e-05, "loss": 1.3714, "step": 132520 }, { "epoch": 6.05, "learning_rate": 1.9785802553892627e-05, "loss": 1.4164, "step": 132530 }, { "epoch": 6.05, "learning_rate": 1.9783514119639344e-05, "loss": 1.4038, "step": 132540 }, { "epoch": 6.05, "learning_rate": 1.978122568538606e-05, "loss": 1.4454, "step": 132550 }, { "epoch": 6.05, "learning_rate": 1.9778937251132776e-05, "loss": 1.4168, "step": 132560 }, { "epoch": 6.05, "learning_rate": 1.9776648816879494e-05, "loss": 1.3806, "step": 132570 }, { "epoch": 6.05, "learning_rate": 1.9774360382626208e-05, "loss": 1.2953, "step": 132580 }, { "epoch": 6.05, "learning_rate": 1.9772071948372925e-05, "loss": 1.5062, "step": 132590 }, { "epoch": 6.05, "learning_rate": 1.9769783514119643e-05, "loss": 1.4631, "step": 132600 }, { "epoch": 6.06, "learning_rate": 1.9767495079866357e-05, "loss": 1.3931, "step": 132610 }, { "epoch": 6.06, "learning_rate": 1.976520664561307e-05, "loss": 1.3086, "step": 132620 }, { "epoch": 6.06, "learning_rate": 1.976291821135979e-05, "loss": 1.4748, "step": 132630 }, { "epoch": 6.06, "learning_rate": 1.9760629777106503e-05, "loss": 1.3526, "step": 132640 }, { "epoch": 6.06, "learning_rate": 1.975834134285322e-05, "loss": 1.4456, "step": 132650 }, { "epoch": 6.06, "learning_rate": 1.9756052908599938e-05, "loss": 1.3889, "step": 132660 }, { "epoch": 6.06, "learning_rate": 1.9753764474346652e-05, "loss": 1.349, "step": 132670 }, { "epoch": 6.06, "learning_rate": 1.975147604009337e-05, "loss": 1.4064, "step": 132680 }, { "epoch": 6.06, "learning_rate": 1.9749187605840087e-05, "loss": 1.3825, "step": 132690 }, { "epoch": 6.06, "learning_rate": 1.97468991715868e-05, "loss": 1.527, "step": 132700 }, { "epoch": 6.06, "learning_rate": 1.974461073733352e-05, "loss": 1.5826, "step": 132710 }, { "epoch": 6.06, "learning_rate": 1.9742322303080233e-05, "loss": 1.4585, "step": 132720 }, { "epoch": 6.06, "learning_rate": 1.974003386882695e-05, "loss": 1.4019, "step": 132730 }, { "epoch": 6.06, "learning_rate": 1.9737745434573664e-05, "loss": 1.4089, "step": 132740 }, { "epoch": 6.06, "learning_rate": 1.9735457000320382e-05, "loss": 1.5811, "step": 132750 }, { "epoch": 6.06, "learning_rate": 1.97331685660671e-05, "loss": 1.3416, "step": 132760 }, { "epoch": 6.06, "learning_rate": 1.9730880131813813e-05, "loss": 1.415, "step": 132770 }, { "epoch": 6.06, "learning_rate": 1.972859169756053e-05, "loss": 1.3988, "step": 132780 }, { "epoch": 6.06, "learning_rate": 1.972630326330725e-05, "loss": 1.2859, "step": 132790 }, { "epoch": 6.06, "learning_rate": 1.9724014829053963e-05, "loss": 1.2441, "step": 132800 }, { "epoch": 6.06, "learning_rate": 1.9721726394800677e-05, "loss": 1.4639, "step": 132810 }, { "epoch": 6.06, "learning_rate": 1.9719437960547394e-05, "loss": 1.426, "step": 132820 }, { "epoch": 6.07, "learning_rate": 1.971714952629411e-05, "loss": 1.3718, "step": 132830 }, { "epoch": 6.07, "learning_rate": 1.9714861092040826e-05, "loss": 1.4148, "step": 132840 }, { "epoch": 6.07, "learning_rate": 1.9712572657787543e-05, "loss": 1.4116, "step": 132850 }, { "epoch": 6.07, "learning_rate": 1.9710284223534258e-05, "loss": 1.4442, "step": 132860 }, { "epoch": 6.07, "learning_rate": 1.9707995789280975e-05, "loss": 1.4008, "step": 132870 }, { "epoch": 6.07, "learning_rate": 1.9705707355027693e-05, "loss": 1.3793, "step": 132880 }, { "epoch": 6.07, "learning_rate": 1.9703418920774407e-05, "loss": 1.5652, "step": 132890 }, { "epoch": 6.07, "learning_rate": 1.9701130486521124e-05, "loss": 1.4912, "step": 132900 }, { "epoch": 6.07, "learning_rate": 1.969884205226784e-05, "loss": 1.4, "step": 132910 }, { "epoch": 6.07, "learning_rate": 1.9696553618014556e-05, "loss": 1.2962, "step": 132920 }, { "epoch": 6.07, "learning_rate": 1.969426518376127e-05, "loss": 1.5773, "step": 132930 }, { "epoch": 6.07, "learning_rate": 1.9691976749507988e-05, "loss": 1.4391, "step": 132940 }, { "epoch": 6.07, "learning_rate": 1.9689688315254705e-05, "loss": 1.3415, "step": 132950 }, { "epoch": 6.07, "learning_rate": 1.968739988100142e-05, "loss": 1.3683, "step": 132960 }, { "epoch": 6.07, "learning_rate": 1.9685111446748137e-05, "loss": 1.2593, "step": 132970 }, { "epoch": 6.07, "learning_rate": 1.968282301249485e-05, "loss": 1.5425, "step": 132980 }, { "epoch": 6.07, "learning_rate": 1.968053457824157e-05, "loss": 1.4623, "step": 132990 }, { "epoch": 6.07, "learning_rate": 1.9678246143988286e-05, "loss": 1.4218, "step": 133000 }, { "epoch": 6.07, "learning_rate": 1.9675957709735e-05, "loss": 1.4387, "step": 133010 }, { "epoch": 6.07, "learning_rate": 1.9673669275481714e-05, "loss": 1.645, "step": 133020 }, { "epoch": 6.07, "learning_rate": 1.9671380841228432e-05, "loss": 1.3013, "step": 133030 }, { "epoch": 6.07, "learning_rate": 1.966909240697515e-05, "loss": 1.3728, "step": 133040 }, { "epoch": 6.08, "learning_rate": 1.9666803972721863e-05, "loss": 1.3126, "step": 133050 }, { "epoch": 6.08, "learning_rate": 1.966451553846858e-05, "loss": 1.6519, "step": 133060 }, { "epoch": 6.08, "learning_rate": 1.96622271042153e-05, "loss": 1.4822, "step": 133070 }, { "epoch": 6.08, "learning_rate": 1.9659938669962013e-05, "loss": 1.4863, "step": 133080 }, { "epoch": 6.08, "learning_rate": 1.965765023570873e-05, "loss": 1.4558, "step": 133090 }, { "epoch": 6.08, "learning_rate": 1.9655361801455448e-05, "loss": 1.349, "step": 133100 }, { "epoch": 6.08, "learning_rate": 1.965307336720216e-05, "loss": 1.2621, "step": 133110 }, { "epoch": 6.08, "learning_rate": 1.9650784932948876e-05, "loss": 1.3549, "step": 133120 }, { "epoch": 6.08, "learning_rate": 1.9648496498695593e-05, "loss": 1.397, "step": 133130 }, { "epoch": 6.08, "learning_rate": 1.9646208064442308e-05, "loss": 1.4739, "step": 133140 }, { "epoch": 6.08, "learning_rate": 1.9643919630189025e-05, "loss": 1.3885, "step": 133150 }, { "epoch": 6.08, "learning_rate": 1.9641631195935743e-05, "loss": 1.3266, "step": 133160 }, { "epoch": 6.08, "learning_rate": 1.9639342761682457e-05, "loss": 1.4136, "step": 133170 }, { "epoch": 6.08, "learning_rate": 1.9637054327429174e-05, "loss": 1.5782, "step": 133180 }, { "epoch": 6.08, "learning_rate": 1.9634765893175892e-05, "loss": 1.5381, "step": 133190 }, { "epoch": 6.08, "learning_rate": 1.9632477458922606e-05, "loss": 1.3838, "step": 133200 }, { "epoch": 6.08, "learning_rate": 1.963018902466932e-05, "loss": 1.4887, "step": 133210 }, { "epoch": 6.08, "learning_rate": 1.9627900590416038e-05, "loss": 1.4304, "step": 133220 }, { "epoch": 6.08, "learning_rate": 1.9625612156162755e-05, "loss": 1.5314, "step": 133230 }, { "epoch": 6.08, "learning_rate": 1.962332372190947e-05, "loss": 1.6523, "step": 133240 }, { "epoch": 6.08, "learning_rate": 1.9621035287656187e-05, "loss": 1.3667, "step": 133250 }, { "epoch": 6.09, "learning_rate": 1.9618746853402904e-05, "loss": 1.3416, "step": 133260 }, { "epoch": 6.09, "learning_rate": 1.961645841914962e-05, "loss": 1.4515, "step": 133270 }, { "epoch": 6.09, "learning_rate": 1.9614169984896336e-05, "loss": 1.5009, "step": 133280 }, { "epoch": 6.09, "learning_rate": 1.9611881550643053e-05, "loss": 1.3907, "step": 133290 }, { "epoch": 6.09, "learning_rate": 1.9609593116389768e-05, "loss": 1.3508, "step": 133300 }, { "epoch": 6.09, "learning_rate": 1.9607304682136482e-05, "loss": 1.517, "step": 133310 }, { "epoch": 6.09, "learning_rate": 1.96050162478832e-05, "loss": 1.1543, "step": 133320 }, { "epoch": 6.09, "learning_rate": 1.9602727813629913e-05, "loss": 1.321, "step": 133330 }, { "epoch": 6.09, "learning_rate": 1.960043937937663e-05, "loss": 1.3373, "step": 133340 }, { "epoch": 6.09, "learning_rate": 1.959815094512335e-05, "loss": 1.4655, "step": 133350 }, { "epoch": 6.09, "learning_rate": 1.9595862510870063e-05, "loss": 1.3901, "step": 133360 }, { "epoch": 6.09, "learning_rate": 1.959357407661678e-05, "loss": 1.3633, "step": 133370 }, { "epoch": 6.09, "learning_rate": 1.9591285642363498e-05, "loss": 1.3543, "step": 133380 }, { "epoch": 6.09, "learning_rate": 1.9588997208110212e-05, "loss": 1.3727, "step": 133390 }, { "epoch": 6.09, "learning_rate": 1.958670877385693e-05, "loss": 1.4446, "step": 133400 }, { "epoch": 6.09, "learning_rate": 1.9584420339603643e-05, "loss": 1.3405, "step": 133410 }, { "epoch": 6.09, "learning_rate": 1.958213190535036e-05, "loss": 1.2134, "step": 133420 }, { "epoch": 6.09, "learning_rate": 1.9579843471097075e-05, "loss": 1.2932, "step": 133430 }, { "epoch": 6.09, "learning_rate": 1.9577555036843793e-05, "loss": 1.4742, "step": 133440 }, { "epoch": 6.09, "learning_rate": 1.957526660259051e-05, "loss": 1.3499, "step": 133450 }, { "epoch": 6.09, "learning_rate": 1.9572978168337224e-05, "loss": 1.5425, "step": 133460 }, { "epoch": 6.09, "learning_rate": 1.9570689734083942e-05, "loss": 1.3735, "step": 133470 }, { "epoch": 6.1, "learning_rate": 1.956840129983066e-05, "loss": 1.4342, "step": 133480 }, { "epoch": 6.1, "learning_rate": 1.9566112865577373e-05, "loss": 1.4037, "step": 133490 }, { "epoch": 6.1, "learning_rate": 1.956382443132409e-05, "loss": 1.4383, "step": 133500 }, { "epoch": 6.1, "learning_rate": 1.9561535997070805e-05, "loss": 1.2608, "step": 133510 }, { "epoch": 6.1, "learning_rate": 1.955924756281752e-05, "loss": 1.3078, "step": 133520 }, { "epoch": 6.1, "learning_rate": 1.9556959128564237e-05, "loss": 1.4289, "step": 133530 }, { "epoch": 6.1, "learning_rate": 1.9554670694310954e-05, "loss": 1.4478, "step": 133540 }, { "epoch": 6.1, "learning_rate": 1.955238226005767e-05, "loss": 1.3589, "step": 133550 }, { "epoch": 6.1, "learning_rate": 1.9550093825804386e-05, "loss": 1.2788, "step": 133560 }, { "epoch": 6.1, "learning_rate": 1.9547805391551103e-05, "loss": 1.3458, "step": 133570 }, { "epoch": 6.1, "learning_rate": 1.9545516957297818e-05, "loss": 1.419, "step": 133580 }, { "epoch": 6.1, "learning_rate": 1.9543228523044535e-05, "loss": 1.4485, "step": 133590 }, { "epoch": 6.1, "learning_rate": 1.954094008879125e-05, "loss": 1.4988, "step": 133600 }, { "epoch": 6.1, "learning_rate": 1.9538651654537963e-05, "loss": 1.418, "step": 133610 }, { "epoch": 6.1, "learning_rate": 1.953636322028468e-05, "loss": 1.4922, "step": 133620 }, { "epoch": 6.1, "learning_rate": 1.95340747860314e-05, "loss": 1.5336, "step": 133630 }, { "epoch": 6.1, "learning_rate": 1.9531786351778112e-05, "loss": 1.2764, "step": 133640 }, { "epoch": 6.1, "learning_rate": 1.952949791752483e-05, "loss": 1.4267, "step": 133650 }, { "epoch": 6.1, "learning_rate": 1.9527209483271548e-05, "loss": 1.3843, "step": 133660 }, { "epoch": 6.1, "learning_rate": 1.952492104901826e-05, "loss": 1.4306, "step": 133670 }, { "epoch": 6.1, "learning_rate": 1.952263261476498e-05, "loss": 1.4501, "step": 133680 }, { "epoch": 6.1, "learning_rate": 1.9520344180511697e-05, "loss": 1.3518, "step": 133690 }, { "epoch": 6.11, "learning_rate": 1.951805574625841e-05, "loss": 1.3485, "step": 133700 }, { "epoch": 6.11, "learning_rate": 1.9515767312005125e-05, "loss": 1.4275, "step": 133710 }, { "epoch": 6.11, "learning_rate": 1.9513478877751842e-05, "loss": 1.4179, "step": 133720 }, { "epoch": 6.11, "learning_rate": 1.951119044349856e-05, "loss": 1.4334, "step": 133730 }, { "epoch": 6.11, "learning_rate": 1.9508902009245274e-05, "loss": 1.3624, "step": 133740 }, { "epoch": 6.11, "learning_rate": 1.950661357499199e-05, "loss": 1.409, "step": 133750 }, { "epoch": 6.11, "learning_rate": 1.950432514073871e-05, "loss": 1.4839, "step": 133760 }, { "epoch": 6.11, "learning_rate": 1.9502036706485423e-05, "loss": 1.4034, "step": 133770 }, { "epoch": 6.11, "learning_rate": 1.949974827223214e-05, "loss": 1.3249, "step": 133780 }, { "epoch": 6.11, "learning_rate": 1.949745983797886e-05, "loss": 1.3809, "step": 133790 }, { "epoch": 6.11, "learning_rate": 1.949517140372557e-05, "loss": 1.2819, "step": 133800 }, { "epoch": 6.11, "learning_rate": 1.9492882969472287e-05, "loss": 1.3207, "step": 133810 }, { "epoch": 6.11, "learning_rate": 1.9490594535219004e-05, "loss": 1.4607, "step": 133820 }, { "epoch": 6.11, "learning_rate": 1.9488306100965718e-05, "loss": 1.5926, "step": 133830 }, { "epoch": 6.11, "learning_rate": 1.9486017666712436e-05, "loss": 1.484, "step": 133840 }, { "epoch": 6.11, "learning_rate": 1.9483729232459153e-05, "loss": 1.3156, "step": 133850 }, { "epoch": 6.11, "learning_rate": 1.9481440798205867e-05, "loss": 1.5265, "step": 133860 }, { "epoch": 6.11, "learning_rate": 1.9479152363952585e-05, "loss": 1.3513, "step": 133870 }, { "epoch": 6.11, "learning_rate": 1.9476863929699303e-05, "loss": 1.3534, "step": 133880 }, { "epoch": 6.11, "learning_rate": 1.9474575495446017e-05, "loss": 1.4054, "step": 133890 }, { "epoch": 6.11, "learning_rate": 1.947228706119273e-05, "loss": 1.4086, "step": 133900 }, { "epoch": 6.11, "learning_rate": 1.9469998626939448e-05, "loss": 1.2775, "step": 133910 }, { "epoch": 6.12, "learning_rate": 1.9467710192686166e-05, "loss": 1.4249, "step": 133920 }, { "epoch": 6.12, "learning_rate": 1.946542175843288e-05, "loss": 1.3985, "step": 133930 }, { "epoch": 6.12, "learning_rate": 1.9463133324179597e-05, "loss": 1.5448, "step": 133940 }, { "epoch": 6.12, "learning_rate": 1.9460844889926315e-05, "loss": 1.466, "step": 133950 }, { "epoch": 6.12, "learning_rate": 1.945855645567303e-05, "loss": 1.3422, "step": 133960 }, { "epoch": 6.12, "learning_rate": 1.9456268021419747e-05, "loss": 1.5199, "step": 133970 }, { "epoch": 6.12, "learning_rate": 1.9453979587166464e-05, "loss": 1.273, "step": 133980 }, { "epoch": 6.12, "learning_rate": 1.945169115291318e-05, "loss": 1.405, "step": 133990 }, { "epoch": 6.12, "learning_rate": 1.9449402718659892e-05, "loss": 1.327, "step": 134000 }, { "epoch": 6.12, "learning_rate": 1.944711428440661e-05, "loss": 1.4102, "step": 134010 }, { "epoch": 6.12, "learning_rate": 1.9444825850153324e-05, "loss": 1.548, "step": 134020 }, { "epoch": 6.12, "learning_rate": 1.944253741590004e-05, "loss": 1.3992, "step": 134030 }, { "epoch": 6.12, "learning_rate": 1.944024898164676e-05, "loss": 1.3676, "step": 134040 }, { "epoch": 6.12, "learning_rate": 1.9437960547393473e-05, "loss": 1.4373, "step": 134050 }, { "epoch": 6.12, "learning_rate": 1.943567211314019e-05, "loss": 1.2313, "step": 134060 }, { "epoch": 6.12, "learning_rate": 1.943338367888691e-05, "loss": 1.2997, "step": 134070 }, { "epoch": 6.12, "learning_rate": 1.9431095244633622e-05, "loss": 1.3534, "step": 134080 }, { "epoch": 6.12, "learning_rate": 1.942880681038034e-05, "loss": 1.4296, "step": 134090 }, { "epoch": 6.12, "learning_rate": 1.9426518376127054e-05, "loss": 1.3399, "step": 134100 }, { "epoch": 6.12, "learning_rate": 1.942422994187377e-05, "loss": 1.3679, "step": 134110 }, { "epoch": 6.12, "learning_rate": 1.9421941507620486e-05, "loss": 1.3342, "step": 134120 }, { "epoch": 6.12, "learning_rate": 1.9419653073367203e-05, "loss": 1.3262, "step": 134130 }, { "epoch": 6.13, "learning_rate": 1.941736463911392e-05, "loss": 1.5439, "step": 134140 }, { "epoch": 6.13, "learning_rate": 1.9415076204860635e-05, "loss": 1.4011, "step": 134150 }, { "epoch": 6.13, "learning_rate": 1.9412787770607352e-05, "loss": 1.427, "step": 134160 }, { "epoch": 6.13, "learning_rate": 1.9410499336354067e-05, "loss": 1.3387, "step": 134170 }, { "epoch": 6.13, "learning_rate": 1.9408210902100784e-05, "loss": 1.5662, "step": 134180 }, { "epoch": 6.13, "learning_rate": 1.94059224678475e-05, "loss": 1.3566, "step": 134190 }, { "epoch": 6.13, "learning_rate": 1.9403634033594216e-05, "loss": 1.4245, "step": 134200 }, { "epoch": 6.13, "learning_rate": 1.940134559934093e-05, "loss": 1.4362, "step": 134210 }, { "epoch": 6.13, "learning_rate": 1.9399057165087647e-05, "loss": 1.3594, "step": 134220 }, { "epoch": 6.13, "learning_rate": 1.9396768730834365e-05, "loss": 1.4615, "step": 134230 }, { "epoch": 6.13, "learning_rate": 1.939448029658108e-05, "loss": 1.522, "step": 134240 }, { "epoch": 6.13, "learning_rate": 1.9392191862327797e-05, "loss": 1.553, "step": 134250 }, { "epoch": 6.13, "learning_rate": 1.9389903428074514e-05, "loss": 1.2945, "step": 134260 }, { "epoch": 6.13, "learning_rate": 1.9387614993821228e-05, "loss": 1.2815, "step": 134270 }, { "epoch": 6.13, "learning_rate": 1.9385326559567946e-05, "loss": 1.3548, "step": 134280 }, { "epoch": 6.13, "learning_rate": 1.9383038125314663e-05, "loss": 1.3636, "step": 134290 }, { "epoch": 6.13, "learning_rate": 1.9380749691061374e-05, "loss": 1.556, "step": 134300 }, { "epoch": 6.13, "learning_rate": 1.937846125680809e-05, "loss": 1.2788, "step": 134310 }, { "epoch": 6.13, "learning_rate": 1.937617282255481e-05, "loss": 1.4226, "step": 134320 }, { "epoch": 6.13, "learning_rate": 1.9373884388301523e-05, "loss": 1.5463, "step": 134330 }, { "epoch": 6.13, "learning_rate": 1.937159595404824e-05, "loss": 1.3894, "step": 134340 }, { "epoch": 6.13, "learning_rate": 1.9369307519794958e-05, "loss": 1.3125, "step": 134350 }, { "epoch": 6.14, "learning_rate": 1.9367019085541672e-05, "loss": 1.357, "step": 134360 }, { "epoch": 6.14, "learning_rate": 1.936473065128839e-05, "loss": 1.488, "step": 134370 }, { "epoch": 6.14, "learning_rate": 1.9362442217035107e-05, "loss": 1.3515, "step": 134380 }, { "epoch": 6.14, "learning_rate": 1.936015378278182e-05, "loss": 1.3178, "step": 134390 }, { "epoch": 6.14, "learning_rate": 1.9357865348528536e-05, "loss": 1.4689, "step": 134400 }, { "epoch": 6.14, "learning_rate": 1.9355576914275253e-05, "loss": 1.4542, "step": 134410 }, { "epoch": 6.14, "learning_rate": 1.935328848002197e-05, "loss": 1.3902, "step": 134420 }, { "epoch": 6.14, "learning_rate": 1.9351000045768685e-05, "loss": 1.2785, "step": 134430 }, { "epoch": 6.14, "learning_rate": 1.9348711611515402e-05, "loss": 1.6213, "step": 134440 }, { "epoch": 6.14, "learning_rate": 1.934642317726212e-05, "loss": 1.3847, "step": 134450 }, { "epoch": 6.14, "learning_rate": 1.9344134743008834e-05, "loss": 1.3769, "step": 134460 }, { "epoch": 6.14, "learning_rate": 1.934184630875555e-05, "loss": 1.3596, "step": 134470 }, { "epoch": 6.14, "learning_rate": 1.933955787450227e-05, "loss": 1.522, "step": 134480 }, { "epoch": 6.14, "learning_rate": 1.933726944024898e-05, "loss": 1.4533, "step": 134490 }, { "epoch": 6.14, "learning_rate": 1.9334981005995697e-05, "loss": 1.3971, "step": 134500 }, { "epoch": 6.14, "learning_rate": 1.9332692571742415e-05, "loss": 1.4022, "step": 134510 }, { "epoch": 6.14, "learning_rate": 1.933040413748913e-05, "loss": 1.3439, "step": 134520 }, { "epoch": 6.14, "learning_rate": 1.9328115703235847e-05, "loss": 1.4907, "step": 134530 }, { "epoch": 6.14, "learning_rate": 1.9325827268982564e-05, "loss": 1.3218, "step": 134540 }, { "epoch": 6.14, "learning_rate": 1.9323538834729278e-05, "loss": 1.515, "step": 134550 }, { "epoch": 6.14, "learning_rate": 1.9321250400475996e-05, "loss": 1.4944, "step": 134560 }, { "epoch": 6.14, "learning_rate": 1.9318961966222713e-05, "loss": 1.4226, "step": 134570 }, { "epoch": 6.15, "learning_rate": 1.9316673531969427e-05, "loss": 1.3417, "step": 134580 }, { "epoch": 6.15, "learning_rate": 1.931438509771614e-05, "loss": 1.4768, "step": 134590 }, { "epoch": 6.15, "learning_rate": 1.931209666346286e-05, "loss": 1.3794, "step": 134600 }, { "epoch": 6.15, "learning_rate": 1.9309808229209577e-05, "loss": 1.4068, "step": 134610 }, { "epoch": 6.15, "learning_rate": 1.930751979495629e-05, "loss": 1.4918, "step": 134620 }, { "epoch": 6.15, "learning_rate": 1.9305231360703008e-05, "loss": 1.3421, "step": 134630 }, { "epoch": 6.15, "learning_rate": 1.9302942926449726e-05, "loss": 1.507, "step": 134640 }, { "epoch": 6.15, "learning_rate": 1.930065449219644e-05, "loss": 1.4677, "step": 134650 }, { "epoch": 6.15, "learning_rate": 1.9298366057943157e-05, "loss": 1.4698, "step": 134660 }, { "epoch": 6.15, "learning_rate": 1.9296077623689875e-05, "loss": 1.4246, "step": 134670 }, { "epoch": 6.15, "learning_rate": 1.929378918943659e-05, "loss": 1.3612, "step": 134680 }, { "epoch": 6.15, "learning_rate": 1.9291500755183303e-05, "loss": 1.422, "step": 134690 }, { "epoch": 6.15, "learning_rate": 1.928921232093002e-05, "loss": 1.4823, "step": 134700 }, { "epoch": 6.15, "learning_rate": 1.9286923886676735e-05, "loss": 1.2782, "step": 134710 }, { "epoch": 6.15, "learning_rate": 1.9284635452423452e-05, "loss": 1.6998, "step": 134720 }, { "epoch": 6.15, "learning_rate": 1.928234701817017e-05, "loss": 1.4259, "step": 134730 }, { "epoch": 6.15, "learning_rate": 1.9280058583916884e-05, "loss": 1.4101, "step": 134740 }, { "epoch": 6.15, "learning_rate": 1.92777701496636e-05, "loss": 1.3327, "step": 134750 }, { "epoch": 6.15, "learning_rate": 1.927548171541032e-05, "loss": 1.5799, "step": 134760 }, { "epoch": 6.15, "learning_rate": 1.9273193281157033e-05, "loss": 1.3915, "step": 134770 }, { "epoch": 6.15, "learning_rate": 1.927090484690375e-05, "loss": 1.3426, "step": 134780 }, { "epoch": 6.15, "learning_rate": 1.9268616412650465e-05, "loss": 1.5435, "step": 134790 }, { "epoch": 6.16, "learning_rate": 1.926632797839718e-05, "loss": 1.4243, "step": 134800 }, { "epoch": 6.16, "learning_rate": 1.9264039544143896e-05, "loss": 1.3647, "step": 134810 }, { "epoch": 6.16, "learning_rate": 1.9261751109890614e-05, "loss": 1.5367, "step": 134820 }, { "epoch": 6.16, "learning_rate": 1.9259462675637328e-05, "loss": 1.6773, "step": 134830 }, { "epoch": 6.16, "learning_rate": 1.9257174241384046e-05, "loss": 1.3068, "step": 134840 }, { "epoch": 6.16, "learning_rate": 1.9254885807130763e-05, "loss": 1.358, "step": 134850 }, { "epoch": 6.16, "learning_rate": 1.9252597372877477e-05, "loss": 1.4695, "step": 134860 }, { "epoch": 6.16, "learning_rate": 1.9250308938624195e-05, "loss": 1.2965, "step": 134870 }, { "epoch": 6.16, "learning_rate": 1.9248020504370912e-05, "loss": 1.5737, "step": 134880 }, { "epoch": 6.16, "learning_rate": 1.9245732070117627e-05, "loss": 1.1986, "step": 134890 }, { "epoch": 6.16, "learning_rate": 1.924344363586434e-05, "loss": 1.3602, "step": 134900 }, { "epoch": 6.16, "learning_rate": 1.9241155201611058e-05, "loss": 1.417, "step": 134910 }, { "epoch": 6.16, "learning_rate": 1.9238866767357776e-05, "loss": 1.3878, "step": 134920 }, { "epoch": 6.16, "learning_rate": 1.923657833310449e-05, "loss": 1.4023, "step": 134930 }, { "epoch": 6.16, "learning_rate": 1.9234289898851207e-05, "loss": 1.432, "step": 134940 }, { "epoch": 6.16, "learning_rate": 1.9232001464597925e-05, "loss": 1.5204, "step": 134950 }, { "epoch": 6.16, "learning_rate": 1.922971303034464e-05, "loss": 1.3899, "step": 134960 }, { "epoch": 6.16, "learning_rate": 1.9227424596091357e-05, "loss": 1.3454, "step": 134970 }, { "epoch": 6.16, "learning_rate": 1.9225136161838074e-05, "loss": 1.4239, "step": 134980 }, { "epoch": 6.16, "learning_rate": 1.9222847727584785e-05, "loss": 1.2555, "step": 134990 }, { "epoch": 6.16, "learning_rate": 1.9220559293331502e-05, "loss": 1.4716, "step": 135000 }, { "epoch": 6.16, "learning_rate": 1.921827085907822e-05, "loss": 1.3397, "step": 135010 }, { "epoch": 6.17, "learning_rate": 1.9215982424824934e-05, "loss": 1.5028, "step": 135020 }, { "epoch": 6.17, "learning_rate": 1.921369399057165e-05, "loss": 1.4031, "step": 135030 }, { "epoch": 6.17, "learning_rate": 1.921140555631837e-05, "loss": 1.3372, "step": 135040 }, { "epoch": 6.17, "learning_rate": 1.9209117122065083e-05, "loss": 1.4645, "step": 135050 }, { "epoch": 6.17, "learning_rate": 1.92068286878118e-05, "loss": 1.343, "step": 135060 }, { "epoch": 6.17, "learning_rate": 1.9204540253558518e-05, "loss": 1.3042, "step": 135070 }, { "epoch": 6.17, "learning_rate": 1.9202251819305232e-05, "loss": 1.3582, "step": 135080 }, { "epoch": 6.17, "learning_rate": 1.9199963385051946e-05, "loss": 1.4224, "step": 135090 }, { "epoch": 6.17, "learning_rate": 1.9197674950798664e-05, "loss": 1.2683, "step": 135100 }, { "epoch": 6.17, "learning_rate": 1.919538651654538e-05, "loss": 1.4588, "step": 135110 }, { "epoch": 6.17, "learning_rate": 1.9193098082292096e-05, "loss": 1.425, "step": 135120 }, { "epoch": 6.17, "learning_rate": 1.9190809648038813e-05, "loss": 1.4668, "step": 135130 }, { "epoch": 6.17, "learning_rate": 1.918852121378553e-05, "loss": 1.3813, "step": 135140 }, { "epoch": 6.17, "learning_rate": 1.9186232779532245e-05, "loss": 1.4995, "step": 135150 }, { "epoch": 6.17, "learning_rate": 1.9183944345278962e-05, "loss": 1.29, "step": 135160 }, { "epoch": 6.17, "learning_rate": 1.918165591102568e-05, "loss": 1.4705, "step": 135170 }, { "epoch": 6.17, "learning_rate": 1.917936747677239e-05, "loss": 1.4603, "step": 135180 }, { "epoch": 6.17, "learning_rate": 1.9177079042519108e-05, "loss": 1.3567, "step": 135190 }, { "epoch": 6.17, "learning_rate": 1.9174790608265826e-05, "loss": 1.3945, "step": 135200 }, { "epoch": 6.17, "learning_rate": 1.917250217401254e-05, "loss": 1.6185, "step": 135210 }, { "epoch": 6.17, "learning_rate": 1.9170213739759257e-05, "loss": 1.4591, "step": 135220 }, { "epoch": 6.17, "learning_rate": 1.9167925305505975e-05, "loss": 1.3896, "step": 135230 }, { "epoch": 6.18, "learning_rate": 1.916563687125269e-05, "loss": 1.2654, "step": 135240 }, { "epoch": 6.18, "learning_rate": 1.9163348436999406e-05, "loss": 1.3509, "step": 135250 }, { "epoch": 6.18, "learning_rate": 1.9161060002746124e-05, "loss": 1.3419, "step": 135260 }, { "epoch": 6.18, "learning_rate": 1.9158771568492838e-05, "loss": 1.4762, "step": 135270 }, { "epoch": 6.18, "learning_rate": 1.9156483134239552e-05, "loss": 1.3424, "step": 135280 }, { "epoch": 6.18, "learning_rate": 1.915419469998627e-05, "loss": 1.5209, "step": 135290 }, { "epoch": 6.18, "learning_rate": 1.9151906265732987e-05, "loss": 1.6427, "step": 135300 }, { "epoch": 6.18, "learning_rate": 1.91496178314797e-05, "loss": 1.5064, "step": 135310 }, { "epoch": 6.18, "learning_rate": 1.914732939722642e-05, "loss": 1.4594, "step": 135320 }, { "epoch": 6.18, "learning_rate": 1.9145040962973133e-05, "loss": 1.5705, "step": 135330 }, { "epoch": 6.18, "learning_rate": 1.914275252871985e-05, "loss": 1.569, "step": 135340 }, { "epoch": 6.18, "learning_rate": 1.9140464094466568e-05, "loss": 1.3766, "step": 135350 }, { "epoch": 6.18, "learning_rate": 1.9138175660213282e-05, "loss": 1.453, "step": 135360 }, { "epoch": 6.18, "learning_rate": 1.913588722596e-05, "loss": 1.4011, "step": 135370 }, { "epoch": 6.18, "learning_rate": 1.9133598791706714e-05, "loss": 1.4789, "step": 135380 }, { "epoch": 6.18, "learning_rate": 1.913131035745343e-05, "loss": 1.3815, "step": 135390 }, { "epoch": 6.18, "learning_rate": 1.9129021923200146e-05, "loss": 1.4666, "step": 135400 }, { "epoch": 6.18, "learning_rate": 1.9126733488946863e-05, "loss": 1.4028, "step": 135410 }, { "epoch": 6.18, "learning_rate": 1.912444505469358e-05, "loss": 1.3751, "step": 135420 }, { "epoch": 6.18, "learning_rate": 1.9122156620440295e-05, "loss": 1.5139, "step": 135430 }, { "epoch": 6.18, "learning_rate": 1.9119868186187012e-05, "loss": 1.4486, "step": 135440 }, { "epoch": 6.19, "learning_rate": 1.911757975193373e-05, "loss": 1.4536, "step": 135450 }, { "epoch": 6.19, "learning_rate": 1.9115291317680444e-05, "loss": 1.4105, "step": 135460 }, { "epoch": 6.19, "learning_rate": 1.911300288342716e-05, "loss": 1.3529, "step": 135470 }, { "epoch": 6.19, "learning_rate": 1.9110714449173876e-05, "loss": 1.5018, "step": 135480 }, { "epoch": 6.19, "learning_rate": 1.910842601492059e-05, "loss": 1.4075, "step": 135490 }, { "epoch": 6.19, "learning_rate": 1.9106137580667307e-05, "loss": 1.4318, "step": 135500 }, { "epoch": 6.19, "learning_rate": 1.9103849146414025e-05, "loss": 1.4138, "step": 135510 }, { "epoch": 6.19, "learning_rate": 1.910156071216074e-05, "loss": 1.3441, "step": 135520 }, { "epoch": 6.19, "learning_rate": 1.9099272277907456e-05, "loss": 1.4783, "step": 135530 }, { "epoch": 6.19, "learning_rate": 1.9096983843654174e-05, "loss": 1.4613, "step": 135540 }, { "epoch": 6.19, "learning_rate": 1.9094695409400888e-05, "loss": 1.4083, "step": 135550 }, { "epoch": 6.19, "learning_rate": 1.9092406975147606e-05, "loss": 1.4229, "step": 135560 }, { "epoch": 6.19, "learning_rate": 1.9090118540894323e-05, "loss": 1.2802, "step": 135570 }, { "epoch": 6.19, "learning_rate": 1.9087830106641037e-05, "loss": 1.6913, "step": 135580 }, { "epoch": 6.19, "learning_rate": 1.908554167238775e-05, "loss": 1.4759, "step": 135590 }, { "epoch": 6.19, "learning_rate": 1.908325323813447e-05, "loss": 1.2972, "step": 135600 }, { "epoch": 6.19, "learning_rate": 1.9080964803881186e-05, "loss": 1.4334, "step": 135610 }, { "epoch": 6.19, "learning_rate": 1.90786763696279e-05, "loss": 1.4578, "step": 135620 }, { "epoch": 6.19, "learning_rate": 1.9076387935374618e-05, "loss": 1.3524, "step": 135630 }, { "epoch": 6.19, "learning_rate": 1.9074099501121336e-05, "loss": 1.4181, "step": 135640 }, { "epoch": 6.19, "learning_rate": 1.907181106686805e-05, "loss": 1.5284, "step": 135650 }, { "epoch": 6.19, "learning_rate": 1.9069522632614767e-05, "loss": 1.3841, "step": 135660 }, { "epoch": 6.2, "learning_rate": 1.9067234198361485e-05, "loss": 1.4052, "step": 135670 }, { "epoch": 6.2, "learning_rate": 1.9064945764108196e-05, "loss": 1.3482, "step": 135680 }, { "epoch": 6.2, "learning_rate": 1.9062657329854913e-05, "loss": 1.477, "step": 135690 }, { "epoch": 6.2, "learning_rate": 1.906036889560163e-05, "loss": 1.3201, "step": 135700 }, { "epoch": 6.2, "learning_rate": 1.9058080461348345e-05, "loss": 1.476, "step": 135710 }, { "epoch": 6.2, "learning_rate": 1.9055792027095062e-05, "loss": 1.4981, "step": 135720 }, { "epoch": 6.2, "learning_rate": 1.905350359284178e-05, "loss": 1.6228, "step": 135730 }, { "epoch": 6.2, "learning_rate": 1.9051215158588494e-05, "loss": 1.3112, "step": 135740 }, { "epoch": 6.2, "learning_rate": 1.904892672433521e-05, "loss": 1.4799, "step": 135750 }, { "epoch": 6.2, "learning_rate": 1.904663829008193e-05, "loss": 1.4752, "step": 135760 }, { "epoch": 6.2, "learning_rate": 1.9044349855828643e-05, "loss": 1.4633, "step": 135770 }, { "epoch": 6.2, "learning_rate": 1.9042061421575357e-05, "loss": 1.2668, "step": 135780 }, { "epoch": 6.2, "learning_rate": 1.9039772987322075e-05, "loss": 1.4087, "step": 135790 }, { "epoch": 6.2, "learning_rate": 1.9037484553068792e-05, "loss": 1.5356, "step": 135800 }, { "epoch": 6.2, "learning_rate": 1.9035196118815506e-05, "loss": 1.4425, "step": 135810 }, { "epoch": 6.2, "learning_rate": 1.9032907684562224e-05, "loss": 1.3687, "step": 135820 }, { "epoch": 6.2, "learning_rate": 1.903061925030894e-05, "loss": 1.4196, "step": 135830 }, { "epoch": 6.2, "learning_rate": 1.9028330816055656e-05, "loss": 1.2646, "step": 135840 }, { "epoch": 6.2, "learning_rate": 1.9026042381802373e-05, "loss": 1.3282, "step": 135850 }, { "epoch": 6.2, "learning_rate": 1.902375394754909e-05, "loss": 1.3176, "step": 135860 }, { "epoch": 6.2, "learning_rate": 1.9021465513295805e-05, "loss": 1.3597, "step": 135870 }, { "epoch": 6.2, "learning_rate": 1.901917707904252e-05, "loss": 1.4174, "step": 135880 }, { "epoch": 6.21, "learning_rate": 1.9016888644789236e-05, "loss": 1.3649, "step": 135890 }, { "epoch": 6.21, "learning_rate": 1.901460021053595e-05, "loss": 1.3153, "step": 135900 }, { "epoch": 6.21, "learning_rate": 1.9012311776282668e-05, "loss": 1.4355, "step": 135910 }, { "epoch": 6.21, "learning_rate": 1.9010023342029386e-05, "loss": 1.4116, "step": 135920 }, { "epoch": 6.21, "learning_rate": 1.90077349077761e-05, "loss": 1.3839, "step": 135930 }, { "epoch": 6.21, "learning_rate": 1.9005446473522817e-05, "loss": 1.423, "step": 135940 }, { "epoch": 6.21, "learning_rate": 1.9003158039269535e-05, "loss": 1.5028, "step": 135950 }, { "epoch": 6.21, "learning_rate": 1.900086960501625e-05, "loss": 1.5283, "step": 135960 }, { "epoch": 6.21, "learning_rate": 1.8998581170762963e-05, "loss": 1.335, "step": 135970 }, { "epoch": 6.21, "learning_rate": 1.899629273650968e-05, "loss": 1.3461, "step": 135980 }, { "epoch": 6.21, "learning_rate": 1.8994004302256395e-05, "loss": 1.5676, "step": 135990 }, { "epoch": 6.21, "learning_rate": 1.8991715868003112e-05, "loss": 1.4257, "step": 136000 }, { "epoch": 6.21, "learning_rate": 1.898942743374983e-05, "loss": 1.3743, "step": 136010 }, { "epoch": 6.21, "learning_rate": 1.8987138999496544e-05, "loss": 1.4409, "step": 136020 }, { "epoch": 6.21, "learning_rate": 1.898485056524326e-05, "loss": 1.3816, "step": 136030 }, { "epoch": 6.21, "learning_rate": 1.898256213098998e-05, "loss": 1.451, "step": 136040 }, { "epoch": 6.21, "learning_rate": 1.8980273696736693e-05, "loss": 1.2386, "step": 136050 }, { "epoch": 6.21, "learning_rate": 1.897798526248341e-05, "loss": 1.5081, "step": 136060 }, { "epoch": 6.21, "learning_rate": 1.8975696828230125e-05, "loss": 1.351, "step": 136070 }, { "epoch": 6.21, "learning_rate": 1.8973408393976842e-05, "loss": 1.2872, "step": 136080 }, { "epoch": 6.21, "learning_rate": 1.8971119959723556e-05, "loss": 1.3229, "step": 136090 }, { "epoch": 6.21, "learning_rate": 1.8968831525470274e-05, "loss": 1.4343, "step": 136100 }, { "epoch": 6.22, "learning_rate": 1.896654309121699e-05, "loss": 1.2717, "step": 136110 }, { "epoch": 6.22, "learning_rate": 1.8964254656963705e-05, "loss": 1.4717, "step": 136120 }, { "epoch": 6.22, "learning_rate": 1.8961966222710423e-05, "loss": 1.273, "step": 136130 }, { "epoch": 6.22, "learning_rate": 1.895967778845714e-05, "loss": 1.3957, "step": 136140 }, { "epoch": 6.22, "learning_rate": 1.8957389354203855e-05, "loss": 1.2778, "step": 136150 }, { "epoch": 6.22, "learning_rate": 1.8955100919950572e-05, "loss": 1.4823, "step": 136160 }, { "epoch": 6.22, "learning_rate": 1.8952812485697286e-05, "loss": 1.3682, "step": 136170 }, { "epoch": 6.22, "learning_rate": 1.8950524051444e-05, "loss": 1.5476, "step": 136180 }, { "epoch": 6.22, "learning_rate": 1.8948235617190718e-05, "loss": 1.4916, "step": 136190 }, { "epoch": 6.22, "learning_rate": 1.8945947182937436e-05, "loss": 1.4446, "step": 136200 }, { "epoch": 6.22, "learning_rate": 1.894365874868415e-05, "loss": 1.4797, "step": 136210 }, { "epoch": 6.22, "learning_rate": 1.8941370314430867e-05, "loss": 1.3611, "step": 136220 }, { "epoch": 6.22, "learning_rate": 1.8939081880177585e-05, "loss": 1.6011, "step": 136230 }, { "epoch": 6.22, "learning_rate": 1.89367934459243e-05, "loss": 1.3325, "step": 136240 }, { "epoch": 6.22, "learning_rate": 1.8934505011671016e-05, "loss": 1.5356, "step": 136250 }, { "epoch": 6.22, "learning_rate": 1.8932216577417734e-05, "loss": 1.3104, "step": 136260 }, { "epoch": 6.22, "learning_rate": 1.8929928143164448e-05, "loss": 1.3913, "step": 136270 }, { "epoch": 6.22, "learning_rate": 1.8927639708911162e-05, "loss": 1.3384, "step": 136280 }, { "epoch": 6.22, "learning_rate": 1.892535127465788e-05, "loss": 1.2528, "step": 136290 }, { "epoch": 6.22, "learning_rate": 1.8923062840404597e-05, "loss": 1.48, "step": 136300 }, { "epoch": 6.22, "learning_rate": 1.892077440615131e-05, "loss": 1.2878, "step": 136310 }, { "epoch": 6.22, "learning_rate": 1.891848597189803e-05, "loss": 1.4983, "step": 136320 }, { "epoch": 6.23, "learning_rate": 1.8916197537644746e-05, "loss": 1.4452, "step": 136330 }, { "epoch": 6.23, "learning_rate": 1.891390910339146e-05, "loss": 1.3663, "step": 136340 }, { "epoch": 6.23, "learning_rate": 1.8911620669138178e-05, "loss": 1.3517, "step": 136350 }, { "epoch": 6.23, "learning_rate": 1.8909332234884896e-05, "loss": 1.4148, "step": 136360 }, { "epoch": 6.23, "learning_rate": 1.8907043800631606e-05, "loss": 1.5073, "step": 136370 }, { "epoch": 6.23, "learning_rate": 1.8904755366378324e-05, "loss": 1.4943, "step": 136380 }, { "epoch": 6.23, "learning_rate": 1.890246693212504e-05, "loss": 1.502, "step": 136390 }, { "epoch": 6.23, "learning_rate": 1.8900178497871755e-05, "loss": 1.341, "step": 136400 }, { "epoch": 6.23, "learning_rate": 1.8897890063618473e-05, "loss": 1.3439, "step": 136410 }, { "epoch": 6.23, "learning_rate": 1.889560162936519e-05, "loss": 1.4125, "step": 136420 }, { "epoch": 6.23, "learning_rate": 1.8893313195111905e-05, "loss": 1.3325, "step": 136430 }, { "epoch": 6.23, "learning_rate": 1.8891024760858622e-05, "loss": 1.4045, "step": 136440 }, { "epoch": 6.23, "learning_rate": 1.888873632660534e-05, "loss": 1.4011, "step": 136450 }, { "epoch": 6.23, "learning_rate": 1.8886447892352054e-05, "loss": 1.3892, "step": 136460 }, { "epoch": 6.23, "learning_rate": 1.8884159458098768e-05, "loss": 1.4639, "step": 136470 }, { "epoch": 6.23, "learning_rate": 1.8881871023845485e-05, "loss": 1.3059, "step": 136480 }, { "epoch": 6.23, "learning_rate": 1.88795825895922e-05, "loss": 1.4035, "step": 136490 }, { "epoch": 6.23, "learning_rate": 1.8877294155338917e-05, "loss": 1.4143, "step": 136500 }, { "epoch": 6.23, "learning_rate": 1.8875005721085635e-05, "loss": 1.3675, "step": 136510 }, { "epoch": 6.23, "learning_rate": 1.887271728683235e-05, "loss": 1.4868, "step": 136520 }, { "epoch": 6.23, "learning_rate": 1.8870428852579066e-05, "loss": 1.2452, "step": 136530 }, { "epoch": 6.23, "learning_rate": 1.8868140418325784e-05, "loss": 1.5076, "step": 136540 }, { "epoch": 6.24, "learning_rate": 1.8865851984072498e-05, "loss": 1.369, "step": 136550 }, { "epoch": 6.24, "learning_rate": 1.8863563549819215e-05, "loss": 1.4752, "step": 136560 }, { "epoch": 6.24, "learning_rate": 1.886127511556593e-05, "loss": 1.3318, "step": 136570 }, { "epoch": 6.24, "learning_rate": 1.8858986681312647e-05, "loss": 1.4277, "step": 136580 }, { "epoch": 6.24, "learning_rate": 1.885669824705936e-05, "loss": 1.3046, "step": 136590 }, { "epoch": 6.24, "learning_rate": 1.885440981280608e-05, "loss": 1.5233, "step": 136600 }, { "epoch": 6.24, "learning_rate": 1.8852121378552796e-05, "loss": 1.3816, "step": 136610 }, { "epoch": 6.24, "learning_rate": 1.884983294429951e-05, "loss": 1.4024, "step": 136620 }, { "epoch": 6.24, "learning_rate": 1.8847544510046228e-05, "loss": 1.4897, "step": 136630 }, { "epoch": 6.24, "learning_rate": 1.8845256075792945e-05, "loss": 1.3498, "step": 136640 }, { "epoch": 6.24, "learning_rate": 1.884296764153966e-05, "loss": 1.422, "step": 136650 }, { "epoch": 6.24, "learning_rate": 1.8840679207286377e-05, "loss": 1.4864, "step": 136660 }, { "epoch": 6.24, "learning_rate": 1.883839077303309e-05, "loss": 1.5173, "step": 136670 }, { "epoch": 6.24, "learning_rate": 1.8836102338779805e-05, "loss": 1.3672, "step": 136680 }, { "epoch": 6.24, "learning_rate": 1.8833813904526523e-05, "loss": 1.3244, "step": 136690 }, { "epoch": 6.24, "learning_rate": 1.883152547027324e-05, "loss": 1.2405, "step": 136700 }, { "epoch": 6.24, "learning_rate": 1.8829237036019955e-05, "loss": 1.462, "step": 136710 }, { "epoch": 6.24, "learning_rate": 1.8826948601766672e-05, "loss": 1.4082, "step": 136720 }, { "epoch": 6.24, "learning_rate": 1.882466016751339e-05, "loss": 1.2917, "step": 136730 }, { "epoch": 6.24, "learning_rate": 1.8822371733260104e-05, "loss": 1.4978, "step": 136740 }, { "epoch": 6.24, "learning_rate": 1.882008329900682e-05, "loss": 1.4303, "step": 136750 }, { "epoch": 6.24, "learning_rate": 1.8817794864753535e-05, "loss": 1.4205, "step": 136760 }, { "epoch": 6.25, "learning_rate": 1.8815506430500253e-05, "loss": 1.5033, "step": 136770 }, { "epoch": 6.25, "learning_rate": 1.8813217996246967e-05, "loss": 1.3788, "step": 136780 }, { "epoch": 6.25, "learning_rate": 1.8810929561993685e-05, "loss": 1.2961, "step": 136790 }, { "epoch": 6.25, "learning_rate": 1.8808641127740402e-05, "loss": 1.3656, "step": 136800 }, { "epoch": 6.25, "learning_rate": 1.8806352693487116e-05, "loss": 1.5597, "step": 136810 }, { "epoch": 6.25, "learning_rate": 1.8804064259233834e-05, "loss": 1.5356, "step": 136820 }, { "epoch": 6.25, "learning_rate": 1.880177582498055e-05, "loss": 1.2631, "step": 136830 }, { "epoch": 6.25, "learning_rate": 1.8799487390727265e-05, "loss": 1.2779, "step": 136840 }, { "epoch": 6.25, "learning_rate": 1.8797198956473983e-05, "loss": 1.499, "step": 136850 }, { "epoch": 6.25, "learning_rate": 1.8794910522220697e-05, "loss": 1.5014, "step": 136860 }, { "epoch": 6.25, "learning_rate": 1.879262208796741e-05, "loss": 1.4124, "step": 136870 }, { "epoch": 6.25, "learning_rate": 1.879033365371413e-05, "loss": 1.2803, "step": 136880 }, { "epoch": 6.25, "learning_rate": 1.8788045219460846e-05, "loss": 1.425, "step": 136890 }, { "epoch": 6.25, "learning_rate": 1.878575678520756e-05, "loss": 1.2676, "step": 136900 }, { "epoch": 6.25, "learning_rate": 1.8783468350954278e-05, "loss": 1.4667, "step": 136910 }, { "epoch": 6.25, "learning_rate": 1.8781179916700995e-05, "loss": 1.5039, "step": 136920 }, { "epoch": 6.25, "learning_rate": 1.877889148244771e-05, "loss": 1.4025, "step": 136930 }, { "epoch": 6.25, "learning_rate": 1.8776603048194427e-05, "loss": 1.5629, "step": 136940 }, { "epoch": 6.25, "learning_rate": 1.8774314613941145e-05, "loss": 1.4211, "step": 136950 }, { "epoch": 6.25, "learning_rate": 1.877202617968786e-05, "loss": 1.5506, "step": 136960 }, { "epoch": 6.25, "learning_rate": 1.8769737745434573e-05, "loss": 1.4822, "step": 136970 }, { "epoch": 6.25, "learning_rate": 1.876744931118129e-05, "loss": 1.4366, "step": 136980 }, { "epoch": 6.26, "learning_rate": 1.8765160876928008e-05, "loss": 1.4724, "step": 136990 }, { "epoch": 6.26, "learning_rate": 1.8762872442674722e-05, "loss": 1.2659, "step": 137000 }, { "epoch": 6.26, "learning_rate": 1.876058400842144e-05, "loss": 1.4719, "step": 137010 }, { "epoch": 6.26, "learning_rate": 1.8758295574168157e-05, "loss": 1.4166, "step": 137020 }, { "epoch": 6.26, "learning_rate": 1.875600713991487e-05, "loss": 1.3412, "step": 137030 }, { "epoch": 6.26, "learning_rate": 1.875371870566159e-05, "loss": 1.4399, "step": 137040 }, { "epoch": 6.26, "learning_rate": 1.8751430271408303e-05, "loss": 1.3945, "step": 137050 }, { "epoch": 6.26, "learning_rate": 1.8749141837155017e-05, "loss": 1.4487, "step": 137060 }, { "epoch": 6.26, "learning_rate": 1.8746853402901735e-05, "loss": 1.4462, "step": 137070 }, { "epoch": 6.26, "learning_rate": 1.8744564968648452e-05, "loss": 1.5047, "step": 137080 }, { "epoch": 6.26, "learning_rate": 1.8742276534395166e-05, "loss": 1.397, "step": 137090 }, { "epoch": 6.26, "learning_rate": 1.8739988100141884e-05, "loss": 1.5927, "step": 137100 }, { "epoch": 6.26, "learning_rate": 1.87376996658886e-05, "loss": 1.4779, "step": 137110 }, { "epoch": 6.26, "learning_rate": 1.8735411231635315e-05, "loss": 1.5021, "step": 137120 }, { "epoch": 6.26, "learning_rate": 1.8733122797382033e-05, "loss": 1.5536, "step": 137130 }, { "epoch": 6.26, "learning_rate": 1.873083436312875e-05, "loss": 1.3326, "step": 137140 }, { "epoch": 6.26, "learning_rate": 1.8728545928875465e-05, "loss": 1.5197, "step": 137150 }, { "epoch": 6.26, "learning_rate": 1.872625749462218e-05, "loss": 1.3186, "step": 137160 }, { "epoch": 6.26, "learning_rate": 1.8723969060368896e-05, "loss": 1.5141, "step": 137170 }, { "epoch": 6.26, "learning_rate": 1.872168062611561e-05, "loss": 1.3668, "step": 137180 }, { "epoch": 6.26, "learning_rate": 1.8719392191862328e-05, "loss": 1.4095, "step": 137190 }, { "epoch": 6.26, "learning_rate": 1.8717103757609045e-05, "loss": 1.4597, "step": 137200 }, { "epoch": 6.27, "learning_rate": 1.871481532335576e-05, "loss": 1.3688, "step": 137210 }, { "epoch": 6.27, "learning_rate": 1.8712526889102477e-05, "loss": 1.4424, "step": 137220 }, { "epoch": 6.27, "learning_rate": 1.8710238454849195e-05, "loss": 1.5369, "step": 137230 }, { "epoch": 6.27, "learning_rate": 1.870795002059591e-05, "loss": 1.4426, "step": 137240 }, { "epoch": 6.27, "learning_rate": 1.8705661586342626e-05, "loss": 1.3374, "step": 137250 }, { "epoch": 6.27, "learning_rate": 1.870337315208934e-05, "loss": 1.3714, "step": 137260 }, { "epoch": 6.27, "learning_rate": 1.8701084717836058e-05, "loss": 1.3985, "step": 137270 }, { "epoch": 6.27, "learning_rate": 1.8698796283582772e-05, "loss": 1.5878, "step": 137280 }, { "epoch": 6.27, "learning_rate": 1.869650784932949e-05, "loss": 1.4722, "step": 137290 }, { "epoch": 6.27, "learning_rate": 1.8694219415076207e-05, "loss": 1.3741, "step": 137300 }, { "epoch": 6.27, "learning_rate": 1.869193098082292e-05, "loss": 1.2882, "step": 137310 }, { "epoch": 6.27, "learning_rate": 1.868964254656964e-05, "loss": 1.3511, "step": 137320 }, { "epoch": 6.27, "learning_rate": 1.8687354112316356e-05, "loss": 1.2598, "step": 137330 }, { "epoch": 6.27, "learning_rate": 1.868506567806307e-05, "loss": 1.3559, "step": 137340 }, { "epoch": 6.27, "learning_rate": 1.8682777243809788e-05, "loss": 1.5083, "step": 137350 }, { "epoch": 6.27, "learning_rate": 1.8680488809556502e-05, "loss": 1.5212, "step": 137360 }, { "epoch": 6.27, "learning_rate": 1.8678200375303216e-05, "loss": 1.4712, "step": 137370 }, { "epoch": 6.27, "learning_rate": 1.8675911941049934e-05, "loss": 1.2883, "step": 137380 }, { "epoch": 6.27, "learning_rate": 1.867362350679665e-05, "loss": 1.4207, "step": 137390 }, { "epoch": 6.27, "learning_rate": 1.8671335072543365e-05, "loss": 1.4496, "step": 137400 }, { "epoch": 6.27, "learning_rate": 1.8669046638290083e-05, "loss": 1.4609, "step": 137410 }, { "epoch": 6.27, "learning_rate": 1.86667582040368e-05, "loss": 1.3911, "step": 137420 }, { "epoch": 6.28, "learning_rate": 1.8664469769783514e-05, "loss": 1.3544, "step": 137430 }, { "epoch": 6.28, "learning_rate": 1.8662181335530232e-05, "loss": 1.4988, "step": 137440 }, { "epoch": 6.28, "learning_rate": 1.865989290127695e-05, "loss": 1.3295, "step": 137450 }, { "epoch": 6.28, "learning_rate": 1.8657604467023664e-05, "loss": 1.3717, "step": 137460 }, { "epoch": 6.28, "learning_rate": 1.8655316032770378e-05, "loss": 1.4167, "step": 137470 }, { "epoch": 6.28, "learning_rate": 1.8653027598517095e-05, "loss": 1.4205, "step": 137480 }, { "epoch": 6.28, "learning_rate": 1.8650739164263813e-05, "loss": 1.3008, "step": 137490 }, { "epoch": 6.28, "learning_rate": 1.8648450730010527e-05, "loss": 1.3777, "step": 137500 }, { "epoch": 6.28, "learning_rate": 1.8646162295757244e-05, "loss": 1.4551, "step": 137510 }, { "epoch": 6.28, "learning_rate": 1.8643873861503962e-05, "loss": 1.5795, "step": 137520 }, { "epoch": 6.28, "learning_rate": 1.8641585427250676e-05, "loss": 1.5166, "step": 137530 }, { "epoch": 6.28, "learning_rate": 1.8639296992997394e-05, "loss": 1.4855, "step": 137540 }, { "epoch": 6.28, "learning_rate": 1.863700855874411e-05, "loss": 1.4024, "step": 137550 }, { "epoch": 6.28, "learning_rate": 1.8634720124490822e-05, "loss": 1.4315, "step": 137560 }, { "epoch": 6.28, "learning_rate": 1.863243169023754e-05, "loss": 1.3669, "step": 137570 }, { "epoch": 6.28, "learning_rate": 1.8630143255984257e-05, "loss": 1.3492, "step": 137580 }, { "epoch": 6.28, "learning_rate": 1.862785482173097e-05, "loss": 1.54, "step": 137590 }, { "epoch": 6.28, "learning_rate": 1.862556638747769e-05, "loss": 1.4758, "step": 137600 }, { "epoch": 6.28, "learning_rate": 1.8623277953224406e-05, "loss": 1.5555, "step": 137610 }, { "epoch": 6.28, "learning_rate": 1.862098951897112e-05, "loss": 1.4299, "step": 137620 }, { "epoch": 6.28, "learning_rate": 1.8618701084717838e-05, "loss": 1.4916, "step": 137630 }, { "epoch": 6.29, "learning_rate": 1.8616412650464555e-05, "loss": 1.4761, "step": 137640 }, { "epoch": 6.29, "learning_rate": 1.861412421621127e-05, "loss": 1.4619, "step": 137650 }, { "epoch": 6.29, "learning_rate": 1.8611835781957984e-05, "loss": 1.4011, "step": 137660 }, { "epoch": 6.29, "learning_rate": 1.86095473477047e-05, "loss": 1.418, "step": 137670 }, { "epoch": 6.29, "learning_rate": 1.8607258913451415e-05, "loss": 1.3865, "step": 137680 }, { "epoch": 6.29, "learning_rate": 1.8604970479198133e-05, "loss": 1.3789, "step": 137690 }, { "epoch": 6.29, "learning_rate": 1.860268204494485e-05, "loss": 1.4386, "step": 137700 }, { "epoch": 6.29, "learning_rate": 1.8600393610691564e-05, "loss": 1.4682, "step": 137710 }, { "epoch": 6.29, "learning_rate": 1.8598105176438282e-05, "loss": 1.385, "step": 137720 }, { "epoch": 6.29, "learning_rate": 1.8595816742185e-05, "loss": 1.4, "step": 137730 }, { "epoch": 6.29, "learning_rate": 1.8593528307931714e-05, "loss": 1.4242, "step": 137740 }, { "epoch": 6.29, "learning_rate": 1.8591239873678428e-05, "loss": 1.4921, "step": 137750 }, { "epoch": 6.29, "learning_rate": 1.8588951439425145e-05, "loss": 1.3361, "step": 137760 }, { "epoch": 6.29, "learning_rate": 1.8586663005171863e-05, "loss": 1.3407, "step": 137770 }, { "epoch": 6.29, "learning_rate": 1.8584374570918577e-05, "loss": 1.4039, "step": 137780 }, { "epoch": 6.29, "learning_rate": 1.8582086136665294e-05, "loss": 1.3509, "step": 137790 }, { "epoch": 6.29, "learning_rate": 1.8579797702412012e-05, "loss": 1.3453, "step": 137800 }, { "epoch": 6.29, "learning_rate": 1.8577509268158726e-05, "loss": 1.5675, "step": 137810 }, { "epoch": 6.29, "learning_rate": 1.8575220833905444e-05, "loss": 1.4311, "step": 137820 }, { "epoch": 6.29, "learning_rate": 1.857293239965216e-05, "loss": 1.5109, "step": 137830 }, { "epoch": 6.29, "learning_rate": 1.8570643965398875e-05, "loss": 1.4845, "step": 137840 }, { "epoch": 6.29, "learning_rate": 1.856835553114559e-05, "loss": 1.3504, "step": 137850 }, { "epoch": 6.3, "learning_rate": 1.8566067096892307e-05, "loss": 1.3849, "step": 137860 }, { "epoch": 6.3, "learning_rate": 1.856377866263902e-05, "loss": 1.3763, "step": 137870 }, { "epoch": 6.3, "learning_rate": 1.856149022838574e-05, "loss": 1.3896, "step": 137880 }, { "epoch": 6.3, "learning_rate": 1.8559201794132456e-05, "loss": 1.4911, "step": 137890 }, { "epoch": 6.3, "learning_rate": 1.855691335987917e-05, "loss": 1.458, "step": 137900 }, { "epoch": 6.3, "learning_rate": 1.8554624925625888e-05, "loss": 1.4334, "step": 137910 }, { "epoch": 6.3, "learning_rate": 1.8552336491372605e-05, "loss": 1.5095, "step": 137920 }, { "epoch": 6.3, "learning_rate": 1.855004805711932e-05, "loss": 1.1492, "step": 137930 }, { "epoch": 6.3, "learning_rate": 1.8547759622866037e-05, "loss": 1.4808, "step": 137940 }, { "epoch": 6.3, "learning_rate": 1.854547118861275e-05, "loss": 1.5364, "step": 137950 }, { "epoch": 6.3, "learning_rate": 1.854318275435947e-05, "loss": 1.3772, "step": 137960 }, { "epoch": 6.3, "learning_rate": 1.8540894320106183e-05, "loss": 1.5221, "step": 137970 }, { "epoch": 6.3, "learning_rate": 1.85386058858529e-05, "loss": 1.4327, "step": 137980 }, { "epoch": 6.3, "learning_rate": 1.8536317451599618e-05, "loss": 1.5092, "step": 137990 }, { "epoch": 6.3, "learning_rate": 1.8534029017346332e-05, "loss": 1.4691, "step": 138000 }, { "epoch": 6.3, "learning_rate": 1.853174058309305e-05, "loss": 1.3101, "step": 138010 }, { "epoch": 6.3, "learning_rate": 1.8529452148839767e-05, "loss": 1.4287, "step": 138020 }, { "epoch": 6.3, "learning_rate": 1.852716371458648e-05, "loss": 1.4945, "step": 138030 }, { "epoch": 6.3, "learning_rate": 1.85248752803332e-05, "loss": 1.3881, "step": 138040 }, { "epoch": 6.3, "learning_rate": 1.8522586846079913e-05, "loss": 1.2791, "step": 138050 }, { "epoch": 6.3, "learning_rate": 1.8520298411826627e-05, "loss": 1.3539, "step": 138060 }, { "epoch": 6.3, "learning_rate": 1.8518009977573344e-05, "loss": 1.3071, "step": 138070 }, { "epoch": 6.31, "learning_rate": 1.8515721543320062e-05, "loss": 1.4746, "step": 138080 }, { "epoch": 6.31, "learning_rate": 1.8513433109066776e-05, "loss": 1.5149, "step": 138090 }, { "epoch": 6.31, "learning_rate": 1.8511144674813494e-05, "loss": 1.4257, "step": 138100 }, { "epoch": 6.31, "learning_rate": 1.850885624056021e-05, "loss": 1.5418, "step": 138110 }, { "epoch": 6.31, "learning_rate": 1.8506567806306925e-05, "loss": 1.21, "step": 138120 }, { "epoch": 6.31, "learning_rate": 1.8504279372053643e-05, "loss": 1.3825, "step": 138130 }, { "epoch": 6.31, "learning_rate": 1.850199093780036e-05, "loss": 1.4842, "step": 138140 }, { "epoch": 6.31, "learning_rate": 1.8499702503547074e-05, "loss": 1.5676, "step": 138150 }, { "epoch": 6.31, "learning_rate": 1.849741406929379e-05, "loss": 1.3646, "step": 138160 }, { "epoch": 6.31, "learning_rate": 1.8495125635040506e-05, "loss": 1.3479, "step": 138170 }, { "epoch": 6.31, "learning_rate": 1.8492837200787224e-05, "loss": 1.4507, "step": 138180 }, { "epoch": 6.31, "learning_rate": 1.8490548766533938e-05, "loss": 1.27, "step": 138190 }, { "epoch": 6.31, "learning_rate": 1.8488260332280655e-05, "loss": 1.2874, "step": 138200 }, { "epoch": 6.31, "learning_rate": 1.848597189802737e-05, "loss": 1.3588, "step": 138210 }, { "epoch": 6.31, "learning_rate": 1.8483683463774087e-05, "loss": 1.4532, "step": 138220 }, { "epoch": 6.31, "learning_rate": 1.8481395029520804e-05, "loss": 1.4258, "step": 138230 }, { "epoch": 6.31, "learning_rate": 1.847910659526752e-05, "loss": 1.2269, "step": 138240 }, { "epoch": 6.31, "learning_rate": 1.8476818161014233e-05, "loss": 1.3593, "step": 138250 }, { "epoch": 6.31, "learning_rate": 1.847452972676095e-05, "loss": 1.3608, "step": 138260 }, { "epoch": 6.31, "learning_rate": 1.8472241292507668e-05, "loss": 1.4816, "step": 138270 }, { "epoch": 6.31, "learning_rate": 1.8469952858254382e-05, "loss": 1.296, "step": 138280 }, { "epoch": 6.31, "learning_rate": 1.84676644240011e-05, "loss": 1.3969, "step": 138290 }, { "epoch": 6.32, "learning_rate": 1.8465375989747817e-05, "loss": 1.4863, "step": 138300 }, { "epoch": 6.32, "learning_rate": 1.846308755549453e-05, "loss": 1.4662, "step": 138310 }, { "epoch": 6.32, "learning_rate": 1.846079912124125e-05, "loss": 1.3904, "step": 138320 }, { "epoch": 6.32, "learning_rate": 1.8458510686987966e-05, "loss": 1.4545, "step": 138330 }, { "epoch": 6.32, "learning_rate": 1.845622225273468e-05, "loss": 1.3235, "step": 138340 }, { "epoch": 6.32, "learning_rate": 1.8453933818481394e-05, "loss": 1.5193, "step": 138350 }, { "epoch": 6.32, "learning_rate": 1.8451645384228112e-05, "loss": 1.4618, "step": 138360 }, { "epoch": 6.32, "learning_rate": 1.8449356949974826e-05, "loss": 1.3724, "step": 138370 }, { "epoch": 6.32, "learning_rate": 1.8447068515721544e-05, "loss": 1.3961, "step": 138380 }, { "epoch": 6.32, "learning_rate": 1.844478008146826e-05, "loss": 1.5373, "step": 138390 }, { "epoch": 6.32, "learning_rate": 1.8442491647214975e-05, "loss": 1.4674, "step": 138400 }, { "epoch": 6.32, "learning_rate": 1.8440203212961693e-05, "loss": 1.4806, "step": 138410 }, { "epoch": 6.32, "learning_rate": 1.843791477870841e-05, "loss": 1.3606, "step": 138420 }, { "epoch": 6.32, "learning_rate": 1.8435626344455124e-05, "loss": 1.3321, "step": 138430 }, { "epoch": 6.32, "learning_rate": 1.843333791020184e-05, "loss": 1.3644, "step": 138440 }, { "epoch": 6.32, "learning_rate": 1.8431049475948556e-05, "loss": 1.4051, "step": 138450 }, { "epoch": 6.32, "learning_rate": 1.8428761041695274e-05, "loss": 1.3146, "step": 138460 }, { "epoch": 6.32, "learning_rate": 1.8426472607441988e-05, "loss": 1.3789, "step": 138470 }, { "epoch": 6.32, "learning_rate": 1.8424184173188705e-05, "loss": 1.47, "step": 138480 }, { "epoch": 6.32, "learning_rate": 1.8421895738935423e-05, "loss": 1.5578, "step": 138490 }, { "epoch": 6.32, "learning_rate": 1.8419607304682137e-05, "loss": 1.6758, "step": 138500 }, { "epoch": 6.32, "learning_rate": 1.8417318870428854e-05, "loss": 1.2524, "step": 138510 }, { "epoch": 6.33, "learning_rate": 1.8415030436175572e-05, "loss": 1.326, "step": 138520 }, { "epoch": 6.33, "learning_rate": 1.8412742001922286e-05, "loss": 1.4717, "step": 138530 }, { "epoch": 6.33, "learning_rate": 1.8410453567669e-05, "loss": 1.4754, "step": 138540 }, { "epoch": 6.33, "learning_rate": 1.8408165133415718e-05, "loss": 1.2451, "step": 138550 }, { "epoch": 6.33, "learning_rate": 1.8405876699162432e-05, "loss": 1.4531, "step": 138560 }, { "epoch": 6.33, "learning_rate": 1.840358826490915e-05, "loss": 1.5524, "step": 138570 }, { "epoch": 6.33, "learning_rate": 1.8401299830655867e-05, "loss": 1.3931, "step": 138580 }, { "epoch": 6.33, "learning_rate": 1.839901139640258e-05, "loss": 1.526, "step": 138590 }, { "epoch": 6.33, "learning_rate": 1.83967229621493e-05, "loss": 1.4234, "step": 138600 }, { "epoch": 6.33, "learning_rate": 1.8394434527896016e-05, "loss": 1.3963, "step": 138610 }, { "epoch": 6.33, "learning_rate": 1.839214609364273e-05, "loss": 1.4005, "step": 138620 }, { "epoch": 6.33, "learning_rate": 1.8389857659389448e-05, "loss": 1.386, "step": 138630 }, { "epoch": 6.33, "learning_rate": 1.8387569225136162e-05, "loss": 1.3699, "step": 138640 }, { "epoch": 6.33, "learning_rate": 1.838528079088288e-05, "loss": 1.4356, "step": 138650 }, { "epoch": 6.33, "learning_rate": 1.8382992356629593e-05, "loss": 1.3393, "step": 138660 }, { "epoch": 6.33, "learning_rate": 1.838070392237631e-05, "loss": 1.4005, "step": 138670 }, { "epoch": 6.33, "learning_rate": 1.837841548812303e-05, "loss": 1.4588, "step": 138680 }, { "epoch": 6.33, "learning_rate": 1.8376127053869743e-05, "loss": 1.3618, "step": 138690 }, { "epoch": 6.33, "learning_rate": 1.837383861961646e-05, "loss": 1.3667, "step": 138700 }, { "epoch": 6.33, "learning_rate": 1.8371550185363178e-05, "loss": 1.5142, "step": 138710 }, { "epoch": 6.33, "learning_rate": 1.8369261751109892e-05, "loss": 1.4712, "step": 138720 }, { "epoch": 6.33, "learning_rate": 1.836697331685661e-05, "loss": 1.5933, "step": 138730 }, { "epoch": 6.34, "learning_rate": 1.8364684882603323e-05, "loss": 1.421, "step": 138740 }, { "epoch": 6.34, "learning_rate": 1.8362396448350038e-05, "loss": 1.4128, "step": 138750 }, { "epoch": 6.34, "learning_rate": 1.8360108014096755e-05, "loss": 1.291, "step": 138760 }, { "epoch": 6.34, "learning_rate": 1.8357819579843473e-05, "loss": 1.389, "step": 138770 }, { "epoch": 6.34, "learning_rate": 1.8355531145590187e-05, "loss": 1.6384, "step": 138780 }, { "epoch": 6.34, "learning_rate": 1.8353242711336904e-05, "loss": 1.3006, "step": 138790 }, { "epoch": 6.34, "learning_rate": 1.8350954277083622e-05, "loss": 1.4039, "step": 138800 }, { "epoch": 6.34, "learning_rate": 1.8348665842830336e-05, "loss": 1.4592, "step": 138810 }, { "epoch": 6.34, "learning_rate": 1.8346377408577053e-05, "loss": 1.4106, "step": 138820 }, { "epoch": 6.34, "learning_rate": 1.834408897432377e-05, "loss": 1.4319, "step": 138830 }, { "epoch": 6.34, "learning_rate": 1.8341800540070482e-05, "loss": 1.4004, "step": 138840 }, { "epoch": 6.34, "learning_rate": 1.83395121058172e-05, "loss": 1.4145, "step": 138850 }, { "epoch": 6.34, "learning_rate": 1.8337223671563917e-05, "loss": 1.3808, "step": 138860 }, { "epoch": 6.34, "learning_rate": 1.833493523731063e-05, "loss": 1.3646, "step": 138870 }, { "epoch": 6.34, "learning_rate": 1.833264680305735e-05, "loss": 1.4466, "step": 138880 }, { "epoch": 6.34, "learning_rate": 1.8330358368804066e-05, "loss": 1.3887, "step": 138890 }, { "epoch": 6.34, "learning_rate": 1.832806993455078e-05, "loss": 1.3236, "step": 138900 }, { "epoch": 6.34, "learning_rate": 1.8325781500297498e-05, "loss": 1.3209, "step": 138910 }, { "epoch": 6.34, "learning_rate": 1.8323493066044215e-05, "loss": 1.2915, "step": 138920 }, { "epoch": 6.34, "learning_rate": 1.832120463179093e-05, "loss": 1.3628, "step": 138930 }, { "epoch": 6.34, "learning_rate": 1.8318916197537643e-05, "loss": 1.4957, "step": 138940 }, { "epoch": 6.34, "learning_rate": 1.831662776328436e-05, "loss": 1.4959, "step": 138950 }, { "epoch": 6.35, "learning_rate": 1.831433932903108e-05, "loss": 1.3934, "step": 138960 }, { "epoch": 6.35, "learning_rate": 1.8312050894777793e-05, "loss": 1.3498, "step": 138970 }, { "epoch": 6.35, "learning_rate": 1.830976246052451e-05, "loss": 1.4009, "step": 138980 }, { "epoch": 6.35, "learning_rate": 1.8307474026271228e-05, "loss": 1.3779, "step": 138990 }, { "epoch": 6.35, "learning_rate": 1.8305185592017942e-05, "loss": 1.4626, "step": 139000 }, { "epoch": 6.35, "learning_rate": 1.830289715776466e-05, "loss": 1.3869, "step": 139010 }, { "epoch": 6.35, "learning_rate": 1.8300608723511377e-05, "loss": 1.3796, "step": 139020 }, { "epoch": 6.35, "learning_rate": 1.829832028925809e-05, "loss": 1.4995, "step": 139030 }, { "epoch": 6.35, "learning_rate": 1.8296031855004805e-05, "loss": 1.4016, "step": 139040 }, { "epoch": 6.35, "learning_rate": 1.8293743420751523e-05, "loss": 1.408, "step": 139050 }, { "epoch": 6.35, "learning_rate": 1.8291454986498237e-05, "loss": 1.6012, "step": 139060 }, { "epoch": 6.35, "learning_rate": 1.8289166552244954e-05, "loss": 1.3099, "step": 139070 }, { "epoch": 6.35, "learning_rate": 1.8286878117991672e-05, "loss": 1.3144, "step": 139080 }, { "epoch": 6.35, "learning_rate": 1.8284589683738386e-05, "loss": 1.445, "step": 139090 }, { "epoch": 6.35, "learning_rate": 1.8282301249485103e-05, "loss": 1.3762, "step": 139100 }, { "epoch": 6.35, "learning_rate": 1.828001281523182e-05, "loss": 1.4352, "step": 139110 }, { "epoch": 6.35, "learning_rate": 1.8277724380978535e-05, "loss": 1.3972, "step": 139120 }, { "epoch": 6.35, "learning_rate": 1.8275435946725253e-05, "loss": 1.3255, "step": 139130 }, { "epoch": 6.35, "learning_rate": 1.8273147512471967e-05, "loss": 1.4155, "step": 139140 }, { "epoch": 6.35, "learning_rate": 1.8270859078218684e-05, "loss": 1.3105, "step": 139150 }, { "epoch": 6.35, "learning_rate": 1.82685706439654e-05, "loss": 1.4292, "step": 139160 }, { "epoch": 6.35, "learning_rate": 1.8266282209712116e-05, "loss": 1.4775, "step": 139170 }, { "epoch": 6.36, "learning_rate": 1.8263993775458833e-05, "loss": 1.6877, "step": 139180 }, { "epoch": 6.36, "learning_rate": 1.8261705341205548e-05, "loss": 1.1684, "step": 139190 }, { "epoch": 6.36, "learning_rate": 1.8259416906952265e-05, "loss": 1.3138, "step": 139200 }, { "epoch": 6.36, "learning_rate": 1.8257128472698983e-05, "loss": 1.3872, "step": 139210 }, { "epoch": 6.36, "learning_rate": 1.8254840038445697e-05, "loss": 1.3251, "step": 139220 }, { "epoch": 6.36, "learning_rate": 1.825255160419241e-05, "loss": 1.3895, "step": 139230 }, { "epoch": 6.36, "learning_rate": 1.825026316993913e-05, "loss": 1.3938, "step": 139240 }, { "epoch": 6.36, "learning_rate": 1.8247974735685843e-05, "loss": 1.5709, "step": 139250 }, { "epoch": 6.36, "learning_rate": 1.824568630143256e-05, "loss": 1.4483, "step": 139260 }, { "epoch": 6.36, "learning_rate": 1.8243397867179278e-05, "loss": 1.3435, "step": 139270 }, { "epoch": 6.36, "learning_rate": 1.8241109432925992e-05, "loss": 1.4274, "step": 139280 }, { "epoch": 6.36, "learning_rate": 1.823882099867271e-05, "loss": 1.3136, "step": 139290 }, { "epoch": 6.36, "learning_rate": 1.8236532564419427e-05, "loss": 1.2742, "step": 139300 }, { "epoch": 6.36, "learning_rate": 1.823424413016614e-05, "loss": 1.5113, "step": 139310 }, { "epoch": 6.36, "learning_rate": 1.823195569591286e-05, "loss": 1.5238, "step": 139320 }, { "epoch": 6.36, "learning_rate": 1.8229667261659573e-05, "loss": 1.3021, "step": 139330 }, { "epoch": 6.36, "learning_rate": 1.822737882740629e-05, "loss": 1.4126, "step": 139340 }, { "epoch": 6.36, "learning_rate": 1.8225090393153004e-05, "loss": 1.3941, "step": 139350 }, { "epoch": 6.36, "learning_rate": 1.8222801958899722e-05, "loss": 1.4177, "step": 139360 }, { "epoch": 6.36, "learning_rate": 1.822051352464644e-05, "loss": 1.4156, "step": 139370 }, { "epoch": 6.36, "learning_rate": 1.8218225090393153e-05, "loss": 1.5449, "step": 139380 }, { "epoch": 6.36, "learning_rate": 1.821593665613987e-05, "loss": 1.5725, "step": 139390 }, { "epoch": 6.37, "learning_rate": 1.8213648221886585e-05, "loss": 1.4425, "step": 139400 }, { "epoch": 6.37, "learning_rate": 1.8211359787633303e-05, "loss": 1.419, "step": 139410 }, { "epoch": 6.37, "learning_rate": 1.820907135338002e-05, "loss": 1.2895, "step": 139420 }, { "epoch": 6.37, "learning_rate": 1.8206782919126734e-05, "loss": 1.4516, "step": 139430 }, { "epoch": 6.37, "learning_rate": 1.820449448487345e-05, "loss": 1.4892, "step": 139440 }, { "epoch": 6.37, "learning_rate": 1.8202206050620166e-05, "loss": 1.5416, "step": 139450 }, { "epoch": 6.37, "learning_rate": 1.8199917616366883e-05, "loss": 1.3449, "step": 139460 }, { "epoch": 6.37, "learning_rate": 1.8197629182113598e-05, "loss": 1.6595, "step": 139470 }, { "epoch": 6.37, "learning_rate": 1.8195340747860315e-05, "loss": 1.3623, "step": 139480 }, { "epoch": 6.37, "learning_rate": 1.8193052313607033e-05, "loss": 1.5028, "step": 139490 }, { "epoch": 6.37, "learning_rate": 1.8190763879353747e-05, "loss": 1.438, "step": 139500 }, { "epoch": 6.37, "learning_rate": 1.8188475445100464e-05, "loss": 1.2788, "step": 139510 }, { "epoch": 6.37, "learning_rate": 1.8186187010847182e-05, "loss": 1.3953, "step": 139520 }, { "epoch": 6.37, "learning_rate": 1.8183898576593892e-05, "loss": 1.3761, "step": 139530 }, { "epoch": 6.37, "learning_rate": 1.818161014234061e-05, "loss": 1.4559, "step": 139540 }, { "epoch": 6.37, "learning_rate": 1.8179321708087328e-05, "loss": 1.6463, "step": 139550 }, { "epoch": 6.37, "learning_rate": 1.817703327383404e-05, "loss": 1.4405, "step": 139560 }, { "epoch": 6.37, "learning_rate": 1.817474483958076e-05, "loss": 1.3896, "step": 139570 }, { "epoch": 6.37, "learning_rate": 1.8172456405327477e-05, "loss": 1.6051, "step": 139580 }, { "epoch": 6.37, "learning_rate": 1.817016797107419e-05, "loss": 1.61, "step": 139590 }, { "epoch": 6.37, "learning_rate": 1.816787953682091e-05, "loss": 1.3793, "step": 139600 }, { "epoch": 6.37, "learning_rate": 1.8165591102567626e-05, "loss": 1.3828, "step": 139610 }, { "epoch": 6.38, "learning_rate": 1.816330266831434e-05, "loss": 1.5521, "step": 139620 }, { "epoch": 6.38, "learning_rate": 1.8161014234061054e-05, "loss": 1.6119, "step": 139630 }, { "epoch": 6.38, "learning_rate": 1.815872579980777e-05, "loss": 1.3807, "step": 139640 }, { "epoch": 6.38, "learning_rate": 1.815643736555449e-05, "loss": 1.4368, "step": 139650 }, { "epoch": 6.38, "learning_rate": 1.8154148931301203e-05, "loss": 1.3975, "step": 139660 }, { "epoch": 6.38, "learning_rate": 1.815186049704792e-05, "loss": 1.379, "step": 139670 }, { "epoch": 6.38, "learning_rate": 1.814957206279464e-05, "loss": 1.4269, "step": 139680 }, { "epoch": 6.38, "learning_rate": 1.8147283628541353e-05, "loss": 1.4068, "step": 139690 }, { "epoch": 6.38, "learning_rate": 1.814499519428807e-05, "loss": 1.4126, "step": 139700 }, { "epoch": 6.38, "learning_rate": 1.8142706760034788e-05, "loss": 1.2573, "step": 139710 }, { "epoch": 6.38, "learning_rate": 1.81404183257815e-05, "loss": 1.3821, "step": 139720 }, { "epoch": 6.38, "learning_rate": 1.8138129891528216e-05, "loss": 1.5727, "step": 139730 }, { "epoch": 6.38, "learning_rate": 1.8135841457274933e-05, "loss": 1.5018, "step": 139740 }, { "epoch": 6.38, "learning_rate": 1.8133553023021647e-05, "loss": 1.4157, "step": 139750 }, { "epoch": 6.38, "learning_rate": 1.8131264588768365e-05, "loss": 1.4362, "step": 139760 }, { "epoch": 6.38, "learning_rate": 1.8128976154515083e-05, "loss": 1.3345, "step": 139770 }, { "epoch": 6.38, "learning_rate": 1.8126687720261797e-05, "loss": 1.4819, "step": 139780 }, { "epoch": 6.38, "learning_rate": 1.8124399286008514e-05, "loss": 1.4946, "step": 139790 }, { "epoch": 6.38, "learning_rate": 1.8122110851755232e-05, "loss": 1.4626, "step": 139800 }, { "epoch": 6.38, "learning_rate": 1.8119822417501946e-05, "loss": 1.3106, "step": 139810 }, { "epoch": 6.38, "learning_rate": 1.8117533983248663e-05, "loss": 1.454, "step": 139820 }, { "epoch": 6.39, "learning_rate": 1.8115245548995377e-05, "loss": 1.4616, "step": 139830 }, { "epoch": 6.39, "learning_rate": 1.8112957114742095e-05, "loss": 1.5411, "step": 139840 }, { "epoch": 6.39, "learning_rate": 1.811066868048881e-05, "loss": 1.3014, "step": 139850 }, { "epoch": 6.39, "learning_rate": 1.8108380246235527e-05, "loss": 1.3645, "step": 139860 }, { "epoch": 6.39, "learning_rate": 1.8106091811982244e-05, "loss": 1.459, "step": 139870 }, { "epoch": 6.39, "learning_rate": 1.810380337772896e-05, "loss": 1.4681, "step": 139880 }, { "epoch": 6.39, "learning_rate": 1.8101514943475676e-05, "loss": 1.2853, "step": 139890 }, { "epoch": 6.39, "learning_rate": 1.8099226509222393e-05, "loss": 1.3134, "step": 139900 }, { "epoch": 6.39, "learning_rate": 1.8096938074969107e-05, "loss": 1.48, "step": 139910 }, { "epoch": 6.39, "learning_rate": 1.8094649640715825e-05, "loss": 1.564, "step": 139920 }, { "epoch": 6.39, "learning_rate": 1.809236120646254e-05, "loss": 1.6094, "step": 139930 }, { "epoch": 6.39, "learning_rate": 1.8090072772209253e-05, "loss": 1.5478, "step": 139940 }, { "epoch": 6.39, "learning_rate": 1.808778433795597e-05, "loss": 1.4842, "step": 139950 }, { "epoch": 6.39, "learning_rate": 1.808549590370269e-05, "loss": 1.5555, "step": 139960 }, { "epoch": 6.39, "learning_rate": 1.8083207469449402e-05, "loss": 1.3952, "step": 139970 }, { "epoch": 6.39, "learning_rate": 1.808091903519612e-05, "loss": 1.4687, "step": 139980 }, { "epoch": 6.39, "learning_rate": 1.8078630600942838e-05, "loss": 1.496, "step": 139990 }, { "epoch": 6.39, "learning_rate": 1.807634216668955e-05, "loss": 1.6092, "step": 140000 }, { "epoch": 6.39, "learning_rate": 1.807405373243627e-05, "loss": 1.4408, "step": 140010 }, { "epoch": 6.39, "learning_rate": 1.8071765298182983e-05, "loss": 1.4569, "step": 140020 }, { "epoch": 6.39, "learning_rate": 1.8069476863929697e-05, "loss": 1.4292, "step": 140030 }, { "epoch": 6.39, "learning_rate": 1.8067188429676415e-05, "loss": 1.5359, "step": 140040 }, { "epoch": 6.4, "learning_rate": 1.8064899995423132e-05, "loss": 1.4312, "step": 140050 }, { "epoch": 6.4, "learning_rate": 1.8062611561169847e-05, "loss": 1.3898, "step": 140060 }, { "epoch": 6.4, "learning_rate": 1.8060323126916564e-05, "loss": 1.3928, "step": 140070 }, { "epoch": 6.4, "learning_rate": 1.805803469266328e-05, "loss": 1.4632, "step": 140080 }, { "epoch": 6.4, "learning_rate": 1.8055746258409996e-05, "loss": 1.3348, "step": 140090 }, { "epoch": 6.4, "learning_rate": 1.8053457824156713e-05, "loss": 1.4986, "step": 140100 }, { "epoch": 6.4, "learning_rate": 1.805116938990343e-05, "loss": 1.4198, "step": 140110 }, { "epoch": 6.4, "learning_rate": 1.8048880955650145e-05, "loss": 1.3085, "step": 140120 }, { "epoch": 6.4, "learning_rate": 1.804659252139686e-05, "loss": 1.4507, "step": 140130 }, { "epoch": 6.4, "learning_rate": 1.8044304087143577e-05, "loss": 1.7008, "step": 140140 }, { "epoch": 6.4, "learning_rate": 1.8042015652890294e-05, "loss": 1.3337, "step": 140150 }, { "epoch": 6.4, "learning_rate": 1.8039727218637008e-05, "loss": 1.5582, "step": 140160 }, { "epoch": 6.4, "learning_rate": 1.8037438784383726e-05, "loss": 1.4552, "step": 140170 }, { "epoch": 6.4, "learning_rate": 1.8035150350130443e-05, "loss": 1.4069, "step": 140180 }, { "epoch": 6.4, "learning_rate": 1.8032861915877157e-05, "loss": 1.398, "step": 140190 }, { "epoch": 6.4, "learning_rate": 1.8030573481623875e-05, "loss": 1.3974, "step": 140200 }, { "epoch": 6.4, "learning_rate": 1.8028285047370592e-05, "loss": 1.3867, "step": 140210 }, { "epoch": 6.4, "learning_rate": 1.8025996613117303e-05, "loss": 1.4576, "step": 140220 }, { "epoch": 6.4, "learning_rate": 1.802370817886402e-05, "loss": 1.4864, "step": 140230 }, { "epoch": 6.4, "learning_rate": 1.8021419744610738e-05, "loss": 1.4331, "step": 140240 }, { "epoch": 6.4, "learning_rate": 1.8019131310357452e-05, "loss": 1.2848, "step": 140250 }, { "epoch": 6.4, "learning_rate": 1.801684287610417e-05, "loss": 1.4029, "step": 140260 }, { "epoch": 6.41, "learning_rate": 1.8014554441850887e-05, "loss": 1.4602, "step": 140270 }, { "epoch": 6.41, "learning_rate": 1.80122660075976e-05, "loss": 1.4304, "step": 140280 }, { "epoch": 6.41, "learning_rate": 1.800997757334432e-05, "loss": 1.3476, "step": 140290 }, { "epoch": 6.41, "learning_rate": 1.8007689139091037e-05, "loss": 1.6111, "step": 140300 }, { "epoch": 6.41, "learning_rate": 1.800540070483775e-05, "loss": 1.5068, "step": 140310 }, { "epoch": 6.41, "learning_rate": 1.8003112270584465e-05, "loss": 1.2885, "step": 140320 }, { "epoch": 6.41, "learning_rate": 1.8000823836331182e-05, "loss": 1.4629, "step": 140330 }, { "epoch": 6.41, "learning_rate": 1.79985354020779e-05, "loss": 1.3767, "step": 140340 }, { "epoch": 6.41, "learning_rate": 1.7996246967824614e-05, "loss": 1.4082, "step": 140350 }, { "epoch": 6.41, "learning_rate": 1.799395853357133e-05, "loss": 1.4069, "step": 140360 }, { "epoch": 6.41, "learning_rate": 1.799167009931805e-05, "loss": 1.5965, "step": 140370 }, { "epoch": 6.41, "learning_rate": 1.7989381665064763e-05, "loss": 1.4076, "step": 140380 }, { "epoch": 6.41, "learning_rate": 1.798709323081148e-05, "loss": 1.6416, "step": 140390 }, { "epoch": 6.41, "learning_rate": 1.7984804796558198e-05, "loss": 1.3729, "step": 140400 }, { "epoch": 6.41, "learning_rate": 1.7982516362304912e-05, "loss": 1.4572, "step": 140410 }, { "epoch": 6.41, "learning_rate": 1.7980227928051627e-05, "loss": 1.4906, "step": 140420 }, { "epoch": 6.41, "learning_rate": 1.7977939493798344e-05, "loss": 1.4287, "step": 140430 }, { "epoch": 6.41, "learning_rate": 1.7975651059545058e-05, "loss": 1.3544, "step": 140440 }, { "epoch": 6.41, "learning_rate": 1.7973362625291776e-05, "loss": 1.3952, "step": 140450 }, { "epoch": 6.41, "learning_rate": 1.7971074191038493e-05, "loss": 1.3262, "step": 140460 }, { "epoch": 6.41, "learning_rate": 1.7968785756785207e-05, "loss": 1.551, "step": 140470 }, { "epoch": 6.41, "learning_rate": 1.7966497322531925e-05, "loss": 1.3928, "step": 140480 }, { "epoch": 6.42, "learning_rate": 1.7964208888278642e-05, "loss": 1.523, "step": 140490 }, { "epoch": 6.42, "learning_rate": 1.7961920454025357e-05, "loss": 1.5003, "step": 140500 }, { "epoch": 6.42, "learning_rate": 1.7959632019772074e-05, "loss": 1.5118, "step": 140510 }, { "epoch": 6.42, "learning_rate": 1.7957343585518788e-05, "loss": 1.5068, "step": 140520 }, { "epoch": 6.42, "learning_rate": 1.7955055151265506e-05, "loss": 1.3775, "step": 140530 }, { "epoch": 6.42, "learning_rate": 1.795276671701222e-05, "loss": 1.222, "step": 140540 }, { "epoch": 6.42, "learning_rate": 1.7950478282758937e-05, "loss": 1.6079, "step": 140550 }, { "epoch": 6.42, "learning_rate": 1.794818984850565e-05, "loss": 1.3293, "step": 140560 }, { "epoch": 6.42, "learning_rate": 1.794590141425237e-05, "loss": 1.3572, "step": 140570 }, { "epoch": 6.42, "learning_rate": 1.7943612979999087e-05, "loss": 1.4547, "step": 140580 }, { "epoch": 6.42, "learning_rate": 1.79413245457458e-05, "loss": 1.3428, "step": 140590 }, { "epoch": 6.42, "learning_rate": 1.7939036111492518e-05, "loss": 1.3803, "step": 140600 }, { "epoch": 6.42, "learning_rate": 1.7936747677239236e-05, "loss": 1.4693, "step": 140610 }, { "epoch": 6.42, "learning_rate": 1.793445924298595e-05, "loss": 1.5116, "step": 140620 }, { "epoch": 6.42, "learning_rate": 1.7932170808732664e-05, "loss": 1.2278, "step": 140630 }, { "epoch": 6.42, "learning_rate": 1.792988237447938e-05, "loss": 1.4275, "step": 140640 }, { "epoch": 6.42, "learning_rate": 1.79275939402261e-05, "loss": 1.3356, "step": 140650 }, { "epoch": 6.42, "learning_rate": 1.7925305505972813e-05, "loss": 1.348, "step": 140660 }, { "epoch": 6.42, "learning_rate": 1.792301707171953e-05, "loss": 1.3381, "step": 140670 }, { "epoch": 6.42, "learning_rate": 1.7920728637466248e-05, "loss": 1.4988, "step": 140680 }, { "epoch": 6.42, "learning_rate": 1.7918440203212962e-05, "loss": 1.3986, "step": 140690 }, { "epoch": 6.42, "learning_rate": 1.791615176895968e-05, "loss": 1.5483, "step": 140700 }, { "epoch": 6.43, "learning_rate": 1.7913863334706397e-05, "loss": 1.2423, "step": 140710 }, { "epoch": 6.43, "learning_rate": 1.7911574900453108e-05, "loss": 1.6107, "step": 140720 }, { "epoch": 6.43, "learning_rate": 1.7909286466199826e-05, "loss": 1.6222, "step": 140730 }, { "epoch": 6.43, "learning_rate": 1.7906998031946543e-05, "loss": 1.4161, "step": 140740 }, { "epoch": 6.43, "learning_rate": 1.7904709597693257e-05, "loss": 1.4784, "step": 140750 }, { "epoch": 6.43, "learning_rate": 1.7902421163439975e-05, "loss": 1.3946, "step": 140760 }, { "epoch": 6.43, "learning_rate": 1.7900132729186692e-05, "loss": 1.412, "step": 140770 }, { "epoch": 6.43, "learning_rate": 1.7897844294933407e-05, "loss": 1.4216, "step": 140780 }, { "epoch": 6.43, "learning_rate": 1.7895555860680124e-05, "loss": 1.4339, "step": 140790 }, { "epoch": 6.43, "learning_rate": 1.789326742642684e-05, "loss": 1.5078, "step": 140800 }, { "epoch": 6.43, "learning_rate": 1.7890978992173556e-05, "loss": 1.3682, "step": 140810 }, { "epoch": 6.43, "learning_rate": 1.788869055792027e-05, "loss": 1.2808, "step": 140820 }, { "epoch": 6.43, "learning_rate": 1.7886402123666987e-05, "loss": 1.4514, "step": 140830 }, { "epoch": 6.43, "learning_rate": 1.7884113689413705e-05, "loss": 1.3111, "step": 140840 }, { "epoch": 6.43, "learning_rate": 1.788182525516042e-05, "loss": 1.3543, "step": 140850 }, { "epoch": 6.43, "learning_rate": 1.7879536820907137e-05, "loss": 1.3551, "step": 140860 }, { "epoch": 6.43, "learning_rate": 1.7877248386653854e-05, "loss": 1.6051, "step": 140870 }, { "epoch": 6.43, "learning_rate": 1.7874959952400568e-05, "loss": 1.5066, "step": 140880 }, { "epoch": 6.43, "learning_rate": 1.7872671518147286e-05, "loss": 1.4421, "step": 140890 }, { "epoch": 6.43, "learning_rate": 1.7870383083894003e-05, "loss": 1.4585, "step": 140900 }, { "epoch": 6.43, "learning_rate": 1.7868094649640714e-05, "loss": 1.3416, "step": 140910 }, { "epoch": 6.43, "learning_rate": 1.786580621538743e-05, "loss": 1.3874, "step": 140920 }, { "epoch": 6.44, "learning_rate": 1.786351778113415e-05, "loss": 1.4152, "step": 140930 }, { "epoch": 6.44, "learning_rate": 1.7861229346880863e-05, "loss": 1.4335, "step": 140940 }, { "epoch": 6.44, "learning_rate": 1.785894091262758e-05, "loss": 1.2812, "step": 140950 }, { "epoch": 6.44, "learning_rate": 1.7856652478374298e-05, "loss": 1.3756, "step": 140960 }, { "epoch": 6.44, "learning_rate": 1.7854364044121012e-05, "loss": 1.5024, "step": 140970 }, { "epoch": 6.44, "learning_rate": 1.785207560986773e-05, "loss": 1.4315, "step": 140980 }, { "epoch": 6.44, "learning_rate": 1.7849787175614447e-05, "loss": 1.45, "step": 140990 }, { "epoch": 6.44, "learning_rate": 1.784749874136116e-05, "loss": 1.3898, "step": 141000 }, { "epoch": 6.44, "learning_rate": 1.7845210307107876e-05, "loss": 1.278, "step": 141010 }, { "epoch": 6.44, "learning_rate": 1.7842921872854593e-05, "loss": 1.3861, "step": 141020 }, { "epoch": 6.44, "learning_rate": 1.784063343860131e-05, "loss": 1.4178, "step": 141030 }, { "epoch": 6.44, "learning_rate": 1.7838345004348025e-05, "loss": 1.3987, "step": 141040 }, { "epoch": 6.44, "learning_rate": 1.7836056570094742e-05, "loss": 1.3989, "step": 141050 }, { "epoch": 6.44, "learning_rate": 1.783376813584146e-05, "loss": 1.4164, "step": 141060 }, { "epoch": 6.44, "learning_rate": 1.7831479701588174e-05, "loss": 1.4186, "step": 141070 }, { "epoch": 6.44, "learning_rate": 1.782919126733489e-05, "loss": 1.2132, "step": 141080 }, { "epoch": 6.44, "learning_rate": 1.782690283308161e-05, "loss": 1.5873, "step": 141090 }, { "epoch": 6.44, "learning_rate": 1.7824614398828323e-05, "loss": 1.4879, "step": 141100 }, { "epoch": 6.44, "learning_rate": 1.7822325964575037e-05, "loss": 1.2739, "step": 141110 }, { "epoch": 6.44, "learning_rate": 1.7820037530321755e-05, "loss": 1.574, "step": 141120 }, { "epoch": 6.44, "learning_rate": 1.781774909606847e-05, "loss": 1.323, "step": 141130 }, { "epoch": 6.44, "learning_rate": 1.7815460661815186e-05, "loss": 1.3233, "step": 141140 }, { "epoch": 6.45, "learning_rate": 1.7813172227561904e-05, "loss": 1.5005, "step": 141150 }, { "epoch": 6.45, "learning_rate": 1.7810883793308618e-05, "loss": 1.4804, "step": 141160 }, { "epoch": 6.45, "learning_rate": 1.7808595359055336e-05, "loss": 1.444, "step": 141170 }, { "epoch": 6.45, "learning_rate": 1.7806306924802053e-05, "loss": 1.355, "step": 141180 }, { "epoch": 6.45, "learning_rate": 1.7804018490548767e-05, "loss": 1.5344, "step": 141190 }, { "epoch": 6.45, "learning_rate": 1.7801730056295485e-05, "loss": 1.4315, "step": 141200 }, { "epoch": 6.45, "learning_rate": 1.77994416220422e-05, "loss": 1.4119, "step": 141210 }, { "epoch": 6.45, "learning_rate": 1.7797153187788913e-05, "loss": 1.4313, "step": 141220 }, { "epoch": 6.45, "learning_rate": 1.779486475353563e-05, "loss": 1.4094, "step": 141230 }, { "epoch": 6.45, "learning_rate": 1.7792576319282348e-05, "loss": 1.2952, "step": 141240 }, { "epoch": 6.45, "learning_rate": 1.7790287885029062e-05, "loss": 1.2963, "step": 141250 }, { "epoch": 6.45, "learning_rate": 1.778799945077578e-05, "loss": 1.3989, "step": 141260 }, { "epoch": 6.45, "learning_rate": 1.7785711016522497e-05, "loss": 1.4203, "step": 141270 }, { "epoch": 6.45, "learning_rate": 1.778342258226921e-05, "loss": 1.5093, "step": 141280 }, { "epoch": 6.45, "learning_rate": 1.778113414801593e-05, "loss": 1.3453, "step": 141290 }, { "epoch": 6.45, "learning_rate": 1.7778845713762646e-05, "loss": 1.4248, "step": 141300 }, { "epoch": 6.45, "learning_rate": 1.777655727950936e-05, "loss": 1.4933, "step": 141310 }, { "epoch": 6.45, "learning_rate": 1.7774268845256075e-05, "loss": 1.3866, "step": 141320 }, { "epoch": 6.45, "learning_rate": 1.7771980411002792e-05, "loss": 1.5241, "step": 141330 }, { "epoch": 6.45, "learning_rate": 1.776969197674951e-05, "loss": 1.5596, "step": 141340 }, { "epoch": 6.45, "learning_rate": 1.7767403542496224e-05, "loss": 1.4302, "step": 141350 }, { "epoch": 6.45, "learning_rate": 1.776511510824294e-05, "loss": 1.3489, "step": 141360 }, { "epoch": 6.46, "learning_rate": 1.776282667398966e-05, "loss": 1.3714, "step": 141370 }, { "epoch": 6.46, "learning_rate": 1.7760538239736373e-05, "loss": 1.5882, "step": 141380 }, { "epoch": 6.46, "learning_rate": 1.775824980548309e-05, "loss": 1.3061, "step": 141390 }, { "epoch": 6.46, "learning_rate": 1.7755961371229808e-05, "loss": 1.4801, "step": 141400 }, { "epoch": 6.46, "learning_rate": 1.775367293697652e-05, "loss": 1.2281, "step": 141410 }, { "epoch": 6.46, "learning_rate": 1.7751384502723236e-05, "loss": 1.3874, "step": 141420 }, { "epoch": 6.46, "learning_rate": 1.7749096068469954e-05, "loss": 1.4871, "step": 141430 }, { "epoch": 6.46, "learning_rate": 1.7746807634216668e-05, "loss": 1.4985, "step": 141440 }, { "epoch": 6.46, "learning_rate": 1.7744519199963386e-05, "loss": 1.4651, "step": 141450 }, { "epoch": 6.46, "learning_rate": 1.7742230765710103e-05, "loss": 1.4435, "step": 141460 }, { "epoch": 6.46, "learning_rate": 1.7739942331456817e-05, "loss": 1.5322, "step": 141470 }, { "epoch": 6.46, "learning_rate": 1.7737653897203535e-05, "loss": 1.2675, "step": 141480 }, { "epoch": 6.46, "learning_rate": 1.7735365462950252e-05, "loss": 1.4234, "step": 141490 }, { "epoch": 6.46, "learning_rate": 1.7733077028696966e-05, "loss": 1.2359, "step": 141500 }, { "epoch": 6.46, "learning_rate": 1.773078859444368e-05, "loss": 1.3633, "step": 141510 }, { "epoch": 6.46, "learning_rate": 1.7728500160190398e-05, "loss": 1.5035, "step": 141520 }, { "epoch": 6.46, "learning_rate": 1.7726211725937116e-05, "loss": 1.3141, "step": 141530 }, { "epoch": 6.46, "learning_rate": 1.772392329168383e-05, "loss": 1.4435, "step": 141540 }, { "epoch": 6.46, "learning_rate": 1.7721634857430547e-05, "loss": 1.613, "step": 141550 }, { "epoch": 6.46, "learning_rate": 1.7719346423177265e-05, "loss": 1.4137, "step": 141560 }, { "epoch": 6.46, "learning_rate": 1.771705798892398e-05, "loss": 1.4217, "step": 141570 }, { "epoch": 6.46, "learning_rate": 1.7714769554670696e-05, "loss": 1.4004, "step": 141580 }, { "epoch": 6.47, "learning_rate": 1.7712481120417414e-05, "loss": 1.4192, "step": 141590 }, { "epoch": 6.47, "learning_rate": 1.7710192686164125e-05, "loss": 1.5158, "step": 141600 }, { "epoch": 6.47, "learning_rate": 1.7707904251910842e-05, "loss": 1.3068, "step": 141610 }, { "epoch": 6.47, "learning_rate": 1.770561581765756e-05, "loss": 1.3605, "step": 141620 }, { "epoch": 6.47, "learning_rate": 1.7703327383404274e-05, "loss": 1.5468, "step": 141630 }, { "epoch": 6.47, "learning_rate": 1.770103894915099e-05, "loss": 1.3737, "step": 141640 }, { "epoch": 6.47, "learning_rate": 1.769875051489771e-05, "loss": 1.3349, "step": 141650 }, { "epoch": 6.47, "learning_rate": 1.7696462080644423e-05, "loss": 1.2701, "step": 141660 }, { "epoch": 6.47, "learning_rate": 1.769417364639114e-05, "loss": 1.3441, "step": 141670 }, { "epoch": 6.47, "learning_rate": 1.7691885212137858e-05, "loss": 1.4136, "step": 141680 }, { "epoch": 6.47, "learning_rate": 1.7689596777884572e-05, "loss": 1.364, "step": 141690 }, { "epoch": 6.47, "learning_rate": 1.7687308343631286e-05, "loss": 1.598, "step": 141700 }, { "epoch": 6.47, "learning_rate": 1.7685019909378004e-05, "loss": 1.4501, "step": 141710 }, { "epoch": 6.47, "learning_rate": 1.7682731475124718e-05, "loss": 1.513, "step": 141720 }, { "epoch": 6.47, "learning_rate": 1.7680443040871436e-05, "loss": 1.4245, "step": 141730 }, { "epoch": 6.47, "learning_rate": 1.7678154606618153e-05, "loss": 1.4767, "step": 141740 }, { "epoch": 6.47, "learning_rate": 1.7675866172364867e-05, "loss": 1.3139, "step": 141750 }, { "epoch": 6.47, "learning_rate": 1.7673577738111585e-05, "loss": 1.3426, "step": 141760 }, { "epoch": 6.47, "learning_rate": 1.7671289303858302e-05, "loss": 1.3967, "step": 141770 }, { "epoch": 6.47, "learning_rate": 1.7669000869605016e-05, "loss": 1.3306, "step": 141780 }, { "epoch": 6.47, "learning_rate": 1.7666712435351734e-05, "loss": 1.4205, "step": 141790 }, { "epoch": 6.47, "learning_rate": 1.7664424001098448e-05, "loss": 1.3094, "step": 141800 }, { "epoch": 6.48, "learning_rate": 1.7662135566845166e-05, "loss": 1.4172, "step": 141810 }, { "epoch": 6.48, "learning_rate": 1.765984713259188e-05, "loss": 1.394, "step": 141820 }, { "epoch": 6.48, "learning_rate": 1.7657558698338597e-05, "loss": 1.416, "step": 141830 }, { "epoch": 6.48, "learning_rate": 1.7655270264085315e-05, "loss": 1.4838, "step": 141840 }, { "epoch": 6.48, "learning_rate": 1.765298182983203e-05, "loss": 1.5023, "step": 141850 }, { "epoch": 6.48, "learning_rate": 1.7650693395578746e-05, "loss": 1.3972, "step": 141860 }, { "epoch": 6.48, "learning_rate": 1.7648404961325464e-05, "loss": 1.4481, "step": 141870 }, { "epoch": 6.48, "learning_rate": 1.7646116527072178e-05, "loss": 1.3617, "step": 141880 }, { "epoch": 6.48, "learning_rate": 1.7643828092818896e-05, "loss": 1.589, "step": 141890 }, { "epoch": 6.48, "learning_rate": 1.764153965856561e-05, "loss": 1.5376, "step": 141900 }, { "epoch": 6.48, "learning_rate": 1.7639251224312324e-05, "loss": 1.5453, "step": 141910 }, { "epoch": 6.48, "learning_rate": 1.763696279005904e-05, "loss": 1.4921, "step": 141920 }, { "epoch": 6.48, "learning_rate": 1.763467435580576e-05, "loss": 1.3438, "step": 141930 }, { "epoch": 6.48, "learning_rate": 1.7632385921552473e-05, "loss": 1.3717, "step": 141940 }, { "epoch": 6.48, "learning_rate": 1.763009748729919e-05, "loss": 1.3424, "step": 141950 }, { "epoch": 6.48, "learning_rate": 1.7627809053045908e-05, "loss": 1.3969, "step": 141960 }, { "epoch": 6.48, "learning_rate": 1.7625520618792622e-05, "loss": 1.5293, "step": 141970 }, { "epoch": 6.48, "learning_rate": 1.762323218453934e-05, "loss": 1.5596, "step": 141980 }, { "epoch": 6.48, "learning_rate": 1.7620943750286057e-05, "loss": 1.3655, "step": 141990 }, { "epoch": 6.48, "learning_rate": 1.761865531603277e-05, "loss": 1.4575, "step": 142000 }, { "epoch": 6.48, "learning_rate": 1.7616366881779486e-05, "loss": 1.3131, "step": 142010 }, { "epoch": 6.49, "learning_rate": 1.7614078447526203e-05, "loss": 1.5055, "step": 142020 }, { "epoch": 6.49, "learning_rate": 1.761179001327292e-05, "loss": 1.3517, "step": 142030 }, { "epoch": 6.49, "learning_rate": 1.7609501579019635e-05, "loss": 1.4432, "step": 142040 }, { "epoch": 6.49, "learning_rate": 1.7607213144766352e-05, "loss": 1.4772, "step": 142050 }, { "epoch": 6.49, "learning_rate": 1.760492471051307e-05, "loss": 1.4553, "step": 142060 }, { "epoch": 6.49, "learning_rate": 1.7602636276259784e-05, "loss": 1.5469, "step": 142070 }, { "epoch": 6.49, "learning_rate": 1.76003478420065e-05, "loss": 1.4693, "step": 142080 }, { "epoch": 6.49, "learning_rate": 1.759805940775322e-05, "loss": 1.3433, "step": 142090 }, { "epoch": 6.49, "learning_rate": 1.759577097349993e-05, "loss": 1.381, "step": 142100 }, { "epoch": 6.49, "learning_rate": 1.7593482539246647e-05, "loss": 1.2621, "step": 142110 }, { "epoch": 6.49, "learning_rate": 1.7591194104993365e-05, "loss": 1.4266, "step": 142120 }, { "epoch": 6.49, "learning_rate": 1.758890567074008e-05, "loss": 1.3438, "step": 142130 }, { "epoch": 6.49, "learning_rate": 1.7586617236486796e-05, "loss": 1.5002, "step": 142140 }, { "epoch": 6.49, "learning_rate": 1.7584328802233514e-05, "loss": 1.4239, "step": 142150 }, { "epoch": 6.49, "learning_rate": 1.7582040367980228e-05, "loss": 1.432, "step": 142160 }, { "epoch": 6.49, "learning_rate": 1.7579751933726946e-05, "loss": 1.3412, "step": 142170 }, { "epoch": 6.49, "learning_rate": 1.7577463499473663e-05, "loss": 1.4271, "step": 142180 }, { "epoch": 6.49, "learning_rate": 1.7575175065220377e-05, "loss": 1.3924, "step": 142190 }, { "epoch": 6.49, "learning_rate": 1.757288663096709e-05, "loss": 1.3638, "step": 142200 }, { "epoch": 6.49, "learning_rate": 1.757059819671381e-05, "loss": 1.4432, "step": 142210 }, { "epoch": 6.49, "learning_rate": 1.7568309762460526e-05, "loss": 1.3141, "step": 142220 }, { "epoch": 6.49, "learning_rate": 1.756602132820724e-05, "loss": 1.2286, "step": 142230 }, { "epoch": 6.5, "learning_rate": 1.7563732893953958e-05, "loss": 1.4773, "step": 142240 }, { "epoch": 6.5, "learning_rate": 1.7561444459700676e-05, "loss": 1.3236, "step": 142250 }, { "epoch": 6.5, "learning_rate": 1.755915602544739e-05, "loss": 1.4661, "step": 142260 }, { "epoch": 6.5, "learning_rate": 1.7556867591194107e-05, "loss": 1.383, "step": 142270 }, { "epoch": 6.5, "learning_rate": 1.755457915694082e-05, "loss": 1.5963, "step": 142280 }, { "epoch": 6.5, "learning_rate": 1.755229072268754e-05, "loss": 1.5062, "step": 142290 }, { "epoch": 6.5, "learning_rate": 1.7550002288434253e-05, "loss": 1.4879, "step": 142300 }, { "epoch": 6.5, "learning_rate": 1.754771385418097e-05, "loss": 1.5158, "step": 142310 }, { "epoch": 6.5, "learning_rate": 1.7545425419927685e-05, "loss": 1.263, "step": 142320 }, { "epoch": 6.5, "learning_rate": 1.7543136985674402e-05, "loss": 1.4296, "step": 142330 }, { "epoch": 6.5, "learning_rate": 1.754084855142112e-05, "loss": 1.5547, "step": 142340 }, { "epoch": 6.5, "learning_rate": 1.7538560117167834e-05, "loss": 1.4241, "step": 142350 }, { "epoch": 6.5, "learning_rate": 1.753627168291455e-05, "loss": 1.4725, "step": 142360 }, { "epoch": 6.5, "learning_rate": 1.753398324866127e-05, "loss": 1.4831, "step": 142370 }, { "epoch": 6.5, "learning_rate": 1.7531694814407983e-05, "loss": 1.56, "step": 142380 }, { "epoch": 6.5, "learning_rate": 1.75294063801547e-05, "loss": 1.3768, "step": 142390 }, { "epoch": 6.5, "learning_rate": 1.7527117945901415e-05, "loss": 1.5276, "step": 142400 }, { "epoch": 6.5, "learning_rate": 1.752482951164813e-05, "loss": 1.3578, "step": 142410 }, { "epoch": 6.5, "learning_rate": 1.7522541077394846e-05, "loss": 1.3202, "step": 142420 }, { "epoch": 6.5, "learning_rate": 1.7520252643141564e-05, "loss": 1.4421, "step": 142430 }, { "epoch": 6.5, "learning_rate": 1.7517964208888278e-05, "loss": 1.4129, "step": 142440 }, { "epoch": 6.5, "learning_rate": 1.7515675774634995e-05, "loss": 1.2705, "step": 142450 }, { "epoch": 6.51, "learning_rate": 1.7513387340381713e-05, "loss": 1.4848, "step": 142460 }, { "epoch": 6.51, "learning_rate": 1.7511098906128427e-05, "loss": 1.3942, "step": 142470 }, { "epoch": 6.51, "learning_rate": 1.7508810471875145e-05, "loss": 1.5503, "step": 142480 }, { "epoch": 6.51, "learning_rate": 1.750652203762186e-05, "loss": 1.4869, "step": 142490 }, { "epoch": 6.51, "learning_rate": 1.7504233603368576e-05, "loss": 1.5029, "step": 142500 }, { "epoch": 6.51, "learning_rate": 1.750194516911529e-05, "loss": 1.3336, "step": 142510 }, { "epoch": 6.51, "learning_rate": 1.7499656734862008e-05, "loss": 1.5234, "step": 142520 }, { "epoch": 6.51, "learning_rate": 1.7497368300608725e-05, "loss": 1.4608, "step": 142530 }, { "epoch": 6.51, "learning_rate": 1.749507986635544e-05, "loss": 1.3196, "step": 142540 }, { "epoch": 6.51, "learning_rate": 1.7492791432102157e-05, "loss": 1.406, "step": 142550 }, { "epoch": 6.51, "learning_rate": 1.7490502997848875e-05, "loss": 1.5507, "step": 142560 }, { "epoch": 6.51, "learning_rate": 1.748821456359559e-05, "loss": 1.3006, "step": 142570 }, { "epoch": 6.51, "learning_rate": 1.7485926129342306e-05, "loss": 1.3183, "step": 142580 }, { "epoch": 6.51, "learning_rate": 1.748363769508902e-05, "loss": 1.5066, "step": 142590 }, { "epoch": 6.51, "learning_rate": 1.7481349260835735e-05, "loss": 1.5034, "step": 142600 }, { "epoch": 6.51, "learning_rate": 1.7479060826582452e-05, "loss": 1.3869, "step": 142610 }, { "epoch": 6.51, "learning_rate": 1.747677239232917e-05, "loss": 1.3712, "step": 142620 }, { "epoch": 6.51, "learning_rate": 1.7474483958075884e-05, "loss": 1.2901, "step": 142630 }, { "epoch": 6.51, "learning_rate": 1.74721955238226e-05, "loss": 1.461, "step": 142640 }, { "epoch": 6.51, "learning_rate": 1.746990708956932e-05, "loss": 1.3345, "step": 142650 }, { "epoch": 6.51, "learning_rate": 1.7467618655316033e-05, "loss": 1.2425, "step": 142660 }, { "epoch": 6.51, "learning_rate": 1.746533022106275e-05, "loss": 1.4056, "step": 142670 }, { "epoch": 6.52, "learning_rate": 1.7463041786809468e-05, "loss": 1.5373, "step": 142680 }, { "epoch": 6.52, "learning_rate": 1.7460753352556182e-05, "loss": 1.4678, "step": 142690 }, { "epoch": 6.52, "learning_rate": 1.7458464918302896e-05, "loss": 1.404, "step": 142700 }, { "epoch": 6.52, "learning_rate": 1.7456176484049614e-05, "loss": 1.4271, "step": 142710 }, { "epoch": 6.52, "learning_rate": 1.745388804979633e-05, "loss": 1.528, "step": 142720 }, { "epoch": 6.52, "learning_rate": 1.7451599615543045e-05, "loss": 1.3354, "step": 142730 }, { "epoch": 6.52, "learning_rate": 1.7449311181289763e-05, "loss": 1.4344, "step": 142740 }, { "epoch": 6.52, "learning_rate": 1.744702274703648e-05, "loss": 1.237, "step": 142750 }, { "epoch": 6.52, "learning_rate": 1.7444734312783195e-05, "loss": 1.6027, "step": 142760 }, { "epoch": 6.52, "learning_rate": 1.7442445878529912e-05, "loss": 1.3828, "step": 142770 }, { "epoch": 6.52, "learning_rate": 1.744015744427663e-05, "loss": 1.2547, "step": 142780 }, { "epoch": 6.52, "learning_rate": 1.743786901002334e-05, "loss": 1.5023, "step": 142790 }, { "epoch": 6.52, "learning_rate": 1.7435580575770058e-05, "loss": 1.3502, "step": 142800 }, { "epoch": 6.52, "learning_rate": 1.7433292141516775e-05, "loss": 1.4029, "step": 142810 }, { "epoch": 6.52, "learning_rate": 1.743100370726349e-05, "loss": 1.453, "step": 142820 }, { "epoch": 6.52, "learning_rate": 1.7428715273010207e-05, "loss": 1.5619, "step": 142830 }, { "epoch": 6.52, "learning_rate": 1.7426426838756925e-05, "loss": 1.5925, "step": 142840 }, { "epoch": 6.52, "learning_rate": 1.742413840450364e-05, "loss": 1.4016, "step": 142850 }, { "epoch": 6.52, "learning_rate": 1.7421849970250356e-05, "loss": 1.4344, "step": 142860 }, { "epoch": 6.52, "learning_rate": 1.7419561535997074e-05, "loss": 1.4423, "step": 142870 }, { "epoch": 6.52, "learning_rate": 1.7417273101743788e-05, "loss": 1.3169, "step": 142880 }, { "epoch": 6.52, "learning_rate": 1.7414984667490502e-05, "loss": 1.4923, "step": 142890 }, { "epoch": 6.53, "learning_rate": 1.741269623323722e-05, "loss": 1.5335, "step": 142900 }, { "epoch": 6.53, "learning_rate": 1.7410407798983934e-05, "loss": 1.3222, "step": 142910 }, { "epoch": 6.53, "learning_rate": 1.740811936473065e-05, "loss": 1.613, "step": 142920 }, { "epoch": 6.53, "learning_rate": 1.740583093047737e-05, "loss": 1.4054, "step": 142930 }, { "epoch": 6.53, "learning_rate": 1.7403542496224083e-05, "loss": 1.4139, "step": 142940 }, { "epoch": 6.53, "learning_rate": 1.74012540619708e-05, "loss": 1.4966, "step": 142950 }, { "epoch": 6.53, "learning_rate": 1.7398965627717518e-05, "loss": 1.5307, "step": 142960 }, { "epoch": 6.53, "learning_rate": 1.7396677193464232e-05, "loss": 1.4554, "step": 142970 }, { "epoch": 6.53, "learning_rate": 1.739438875921095e-05, "loss": 1.3858, "step": 142980 }, { "epoch": 6.53, "learning_rate": 1.7392100324957664e-05, "loss": 1.4922, "step": 142990 }, { "epoch": 6.53, "learning_rate": 1.738981189070438e-05, "loss": 1.5674, "step": 143000 }, { "epoch": 6.53, "learning_rate": 1.7387523456451095e-05, "loss": 1.4415, "step": 143010 }, { "epoch": 6.53, "learning_rate": 1.7385235022197813e-05, "loss": 1.403, "step": 143020 }, { "epoch": 6.53, "learning_rate": 1.738294658794453e-05, "loss": 1.451, "step": 143030 }, { "epoch": 6.53, "learning_rate": 1.7380658153691245e-05, "loss": 1.3582, "step": 143040 }, { "epoch": 6.53, "learning_rate": 1.7378369719437962e-05, "loss": 1.556, "step": 143050 }, { "epoch": 6.53, "learning_rate": 1.737608128518468e-05, "loss": 1.3301, "step": 143060 }, { "epoch": 6.53, "learning_rate": 1.7373792850931394e-05, "loss": 1.4256, "step": 143070 }, { "epoch": 6.53, "learning_rate": 1.737150441667811e-05, "loss": 1.5132, "step": 143080 }, { "epoch": 6.53, "learning_rate": 1.7369215982424825e-05, "loss": 1.3984, "step": 143090 }, { "epoch": 6.53, "learning_rate": 1.736692754817154e-05, "loss": 1.4287, "step": 143100 }, { "epoch": 6.53, "learning_rate": 1.7364639113918257e-05, "loss": 1.41, "step": 143110 }, { "epoch": 6.54, "learning_rate": 1.7362350679664975e-05, "loss": 1.5464, "step": 143120 }, { "epoch": 6.54, "learning_rate": 1.736006224541169e-05, "loss": 1.336, "step": 143130 }, { "epoch": 6.54, "learning_rate": 1.7357773811158406e-05, "loss": 1.3219, "step": 143140 }, { "epoch": 6.54, "learning_rate": 1.7355485376905124e-05, "loss": 1.3194, "step": 143150 }, { "epoch": 6.54, "learning_rate": 1.7353196942651838e-05, "loss": 1.4383, "step": 143160 }, { "epoch": 6.54, "learning_rate": 1.7350908508398555e-05, "loss": 1.4538, "step": 143170 }, { "epoch": 6.54, "learning_rate": 1.7348620074145273e-05, "loss": 1.4121, "step": 143180 }, { "epoch": 6.54, "learning_rate": 1.7346331639891987e-05, "loss": 1.4584, "step": 143190 }, { "epoch": 6.54, "learning_rate": 1.73440432056387e-05, "loss": 1.3744, "step": 143200 }, { "epoch": 6.54, "learning_rate": 1.734175477138542e-05, "loss": 1.4946, "step": 143210 }, { "epoch": 6.54, "learning_rate": 1.7339466337132136e-05, "loss": 1.4642, "step": 143220 }, { "epoch": 6.54, "learning_rate": 1.733717790287885e-05, "loss": 1.5244, "step": 143230 }, { "epoch": 6.54, "learning_rate": 1.7334889468625568e-05, "loss": 1.5399, "step": 143240 }, { "epoch": 6.54, "learning_rate": 1.7332601034372285e-05, "loss": 1.3747, "step": 143250 }, { "epoch": 6.54, "learning_rate": 1.7330312600119e-05, "loss": 1.5434, "step": 143260 }, { "epoch": 6.54, "learning_rate": 1.7328024165865717e-05, "loss": 1.3775, "step": 143270 }, { "epoch": 6.54, "learning_rate": 1.732573573161243e-05, "loss": 1.4339, "step": 143280 }, { "epoch": 6.54, "learning_rate": 1.7323447297359145e-05, "loss": 1.3998, "step": 143290 }, { "epoch": 6.54, "learning_rate": 1.7321158863105863e-05, "loss": 1.6277, "step": 143300 }, { "epoch": 6.54, "learning_rate": 1.731887042885258e-05, "loss": 1.4877, "step": 143310 }, { "epoch": 6.54, "learning_rate": 1.7316581994599294e-05, "loss": 1.2671, "step": 143320 }, { "epoch": 6.54, "learning_rate": 1.7314293560346012e-05, "loss": 1.5259, "step": 143330 }, { "epoch": 6.55, "learning_rate": 1.731200512609273e-05, "loss": 1.3965, "step": 143340 }, { "epoch": 6.55, "learning_rate": 1.7309716691839444e-05, "loss": 1.3546, "step": 143350 }, { "epoch": 6.55, "learning_rate": 1.730742825758616e-05, "loss": 1.5453, "step": 143360 }, { "epoch": 6.55, "learning_rate": 1.730513982333288e-05, "loss": 1.474, "step": 143370 }, { "epoch": 6.55, "learning_rate": 1.7302851389079593e-05, "loss": 1.4588, "step": 143380 }, { "epoch": 6.55, "learning_rate": 1.7300562954826307e-05, "loss": 1.4386, "step": 143390 }, { "epoch": 6.55, "learning_rate": 1.7298274520573025e-05, "loss": 1.4154, "step": 143400 }, { "epoch": 6.55, "learning_rate": 1.7295986086319742e-05, "loss": 1.4664, "step": 143410 }, { "epoch": 6.55, "learning_rate": 1.7293697652066456e-05, "loss": 1.4277, "step": 143420 }, { "epoch": 6.55, "learning_rate": 1.7291409217813174e-05, "loss": 1.3751, "step": 143430 }, { "epoch": 6.55, "learning_rate": 1.728912078355989e-05, "loss": 1.404, "step": 143440 }, { "epoch": 6.55, "learning_rate": 1.7286832349306605e-05, "loss": 1.385, "step": 143450 }, { "epoch": 6.55, "learning_rate": 1.7284543915053323e-05, "loss": 1.3526, "step": 143460 }, { "epoch": 6.55, "learning_rate": 1.7282255480800037e-05, "loss": 1.2317, "step": 143470 }, { "epoch": 6.55, "learning_rate": 1.727996704654675e-05, "loss": 1.3546, "step": 143480 }, { "epoch": 6.55, "learning_rate": 1.727767861229347e-05, "loss": 1.3848, "step": 143490 }, { "epoch": 6.55, "learning_rate": 1.7275390178040186e-05, "loss": 1.4392, "step": 143500 }, { "epoch": 6.55, "learning_rate": 1.72731017437869e-05, "loss": 1.3916, "step": 143510 }, { "epoch": 6.55, "learning_rate": 1.7270813309533618e-05, "loss": 1.5843, "step": 143520 }, { "epoch": 6.55, "learning_rate": 1.7268524875280335e-05, "loss": 1.4564, "step": 143530 }, { "epoch": 6.55, "learning_rate": 1.726623644102705e-05, "loss": 1.3395, "step": 143540 }, { "epoch": 6.55, "learning_rate": 1.7263948006773767e-05, "loss": 1.3725, "step": 143550 }, { "epoch": 6.56, "learning_rate": 1.7261659572520485e-05, "loss": 1.4647, "step": 143560 }, { "epoch": 6.56, "learning_rate": 1.72593711382672e-05, "loss": 1.352, "step": 143570 }, { "epoch": 6.56, "learning_rate": 1.7257082704013913e-05, "loss": 1.5488, "step": 143580 }, { "epoch": 6.56, "learning_rate": 1.725479426976063e-05, "loss": 1.3227, "step": 143590 }, { "epoch": 6.56, "learning_rate": 1.7252505835507344e-05, "loss": 1.453, "step": 143600 }, { "epoch": 6.56, "learning_rate": 1.7250217401254062e-05, "loss": 1.5028, "step": 143610 }, { "epoch": 6.56, "learning_rate": 1.724792896700078e-05, "loss": 1.4629, "step": 143620 }, { "epoch": 6.56, "learning_rate": 1.7245640532747494e-05, "loss": 1.4012, "step": 143630 }, { "epoch": 6.56, "learning_rate": 1.724335209849421e-05, "loss": 1.4363, "step": 143640 }, { "epoch": 6.56, "learning_rate": 1.724106366424093e-05, "loss": 1.3949, "step": 143650 }, { "epoch": 6.56, "learning_rate": 1.7238775229987643e-05, "loss": 1.4824, "step": 143660 }, { "epoch": 6.56, "learning_rate": 1.723648679573436e-05, "loss": 1.3712, "step": 143670 }, { "epoch": 6.56, "learning_rate": 1.7234198361481074e-05, "loss": 1.3483, "step": 143680 }, { "epoch": 6.56, "learning_rate": 1.7231909927227792e-05, "loss": 1.5491, "step": 143690 }, { "epoch": 6.56, "learning_rate": 1.7229621492974506e-05, "loss": 1.3406, "step": 143700 }, { "epoch": 6.56, "learning_rate": 1.7227333058721224e-05, "loss": 1.42, "step": 143710 }, { "epoch": 6.56, "learning_rate": 1.722504462446794e-05, "loss": 1.3707, "step": 143720 }, { "epoch": 6.56, "learning_rate": 1.7222756190214655e-05, "loss": 1.4701, "step": 143730 }, { "epoch": 6.56, "learning_rate": 1.7220467755961373e-05, "loss": 1.2763, "step": 143740 }, { "epoch": 6.56, "learning_rate": 1.721817932170809e-05, "loss": 1.2821, "step": 143750 }, { "epoch": 6.56, "learning_rate": 1.7215890887454804e-05, "loss": 1.456, "step": 143760 }, { "epoch": 6.56, "learning_rate": 1.7213602453201522e-05, "loss": 1.3925, "step": 143770 }, { "epoch": 6.57, "learning_rate": 1.7211314018948236e-05, "loss": 1.4187, "step": 143780 }, { "epoch": 6.57, "learning_rate": 1.720902558469495e-05, "loss": 1.5034, "step": 143790 }, { "epoch": 6.57, "learning_rate": 1.7206737150441668e-05, "loss": 1.2746, "step": 143800 }, { "epoch": 6.57, "learning_rate": 1.7204448716188385e-05, "loss": 1.6002, "step": 143810 }, { "epoch": 6.57, "learning_rate": 1.72021602819351e-05, "loss": 1.3679, "step": 143820 }, { "epoch": 6.57, "learning_rate": 1.7199871847681817e-05, "loss": 1.3986, "step": 143830 }, { "epoch": 6.57, "learning_rate": 1.7197583413428534e-05, "loss": 1.4552, "step": 143840 }, { "epoch": 6.57, "learning_rate": 1.719529497917525e-05, "loss": 1.3592, "step": 143850 }, { "epoch": 6.57, "learning_rate": 1.7193006544921966e-05, "loss": 1.3981, "step": 143860 }, { "epoch": 6.57, "learning_rate": 1.7190718110668684e-05, "loss": 1.363, "step": 143870 }, { "epoch": 6.57, "learning_rate": 1.7188429676415398e-05, "loss": 1.4372, "step": 143880 }, { "epoch": 6.57, "learning_rate": 1.7186141242162112e-05, "loss": 1.3331, "step": 143890 }, { "epoch": 6.57, "learning_rate": 1.718385280790883e-05, "loss": 1.2466, "step": 143900 }, { "epoch": 6.57, "learning_rate": 1.7181564373655547e-05, "loss": 1.2871, "step": 143910 }, { "epoch": 6.57, "learning_rate": 1.717927593940226e-05, "loss": 1.3574, "step": 143920 }, { "epoch": 6.57, "learning_rate": 1.717698750514898e-05, "loss": 1.5565, "step": 143930 }, { "epoch": 6.57, "learning_rate": 1.7174699070895696e-05, "loss": 1.4645, "step": 143940 }, { "epoch": 6.57, "learning_rate": 1.717241063664241e-05, "loss": 1.4524, "step": 143950 }, { "epoch": 6.57, "learning_rate": 1.7170122202389128e-05, "loss": 1.4477, "step": 143960 }, { "epoch": 6.57, "learning_rate": 1.7167833768135845e-05, "loss": 1.4598, "step": 143970 }, { "epoch": 6.57, "learning_rate": 1.7165545333882556e-05, "loss": 1.2466, "step": 143980 }, { "epoch": 6.57, "learning_rate": 1.7163256899629274e-05, "loss": 1.3339, "step": 143990 }, { "epoch": 6.58, "learning_rate": 1.716096846537599e-05, "loss": 1.4424, "step": 144000 }, { "epoch": 6.58, "learning_rate": 1.7158680031122705e-05, "loss": 1.3411, "step": 144010 }, { "epoch": 6.58, "learning_rate": 1.7156391596869423e-05, "loss": 1.4042, "step": 144020 }, { "epoch": 6.58, "learning_rate": 1.715410316261614e-05, "loss": 1.4445, "step": 144030 }, { "epoch": 6.58, "learning_rate": 1.7151814728362854e-05, "loss": 1.4224, "step": 144040 }, { "epoch": 6.58, "learning_rate": 1.7149526294109572e-05, "loss": 1.4368, "step": 144050 }, { "epoch": 6.58, "learning_rate": 1.714723785985629e-05, "loss": 1.3581, "step": 144060 }, { "epoch": 6.58, "learning_rate": 1.7144949425603e-05, "loss": 1.375, "step": 144070 }, { "epoch": 6.58, "learning_rate": 1.7142660991349718e-05, "loss": 1.4178, "step": 144080 }, { "epoch": 6.58, "learning_rate": 1.7140372557096435e-05, "loss": 1.5185, "step": 144090 }, { "epoch": 6.58, "learning_rate": 1.713808412284315e-05, "loss": 1.3689, "step": 144100 }, { "epoch": 6.58, "learning_rate": 1.7135795688589867e-05, "loss": 1.4073, "step": 144110 }, { "epoch": 6.58, "learning_rate": 1.7133507254336584e-05, "loss": 1.6862, "step": 144120 }, { "epoch": 6.58, "learning_rate": 1.71312188200833e-05, "loss": 1.2959, "step": 144130 }, { "epoch": 6.58, "learning_rate": 1.7128930385830016e-05, "loss": 1.6581, "step": 144140 }, { "epoch": 6.58, "learning_rate": 1.7126641951576734e-05, "loss": 1.6301, "step": 144150 }, { "epoch": 6.58, "learning_rate": 1.7124353517323448e-05, "loss": 1.3203, "step": 144160 }, { "epoch": 6.58, "learning_rate": 1.7122065083070162e-05, "loss": 1.3415, "step": 144170 }, { "epoch": 6.58, "learning_rate": 1.711977664881688e-05, "loss": 1.4892, "step": 144180 }, { "epoch": 6.58, "learning_rate": 1.7117488214563597e-05, "loss": 1.2745, "step": 144190 }, { "epoch": 6.58, "learning_rate": 1.711519978031031e-05, "loss": 1.258, "step": 144200 }, { "epoch": 6.59, "learning_rate": 1.711291134605703e-05, "loss": 1.4575, "step": 144210 }, { "epoch": 6.59, "learning_rate": 1.7110622911803746e-05, "loss": 1.2503, "step": 144220 }, { "epoch": 6.59, "learning_rate": 1.710833447755046e-05, "loss": 1.4535, "step": 144230 }, { "epoch": 6.59, "learning_rate": 1.7106046043297178e-05, "loss": 1.5191, "step": 144240 }, { "epoch": 6.59, "learning_rate": 1.7103757609043895e-05, "loss": 1.3508, "step": 144250 }, { "epoch": 6.59, "learning_rate": 1.710146917479061e-05, "loss": 1.4897, "step": 144260 }, { "epoch": 6.59, "learning_rate": 1.7099180740537324e-05, "loss": 1.339, "step": 144270 }, { "epoch": 6.59, "learning_rate": 1.709689230628404e-05, "loss": 1.4592, "step": 144280 }, { "epoch": 6.59, "learning_rate": 1.7094603872030755e-05, "loss": 1.54, "step": 144290 }, { "epoch": 6.59, "learning_rate": 1.7092315437777473e-05, "loss": 1.3472, "step": 144300 }, { "epoch": 6.59, "learning_rate": 1.709002700352419e-05, "loss": 1.4214, "step": 144310 }, { "epoch": 6.59, "learning_rate": 1.7087738569270904e-05, "loss": 1.4209, "step": 144320 }, { "epoch": 6.59, "learning_rate": 1.7085450135017622e-05, "loss": 1.5025, "step": 144330 }, { "epoch": 6.59, "learning_rate": 1.708316170076434e-05, "loss": 1.287, "step": 144340 }, { "epoch": 6.59, "learning_rate": 1.7080873266511054e-05, "loss": 1.3452, "step": 144350 }, { "epoch": 6.59, "learning_rate": 1.707858483225777e-05, "loss": 1.2706, "step": 144360 }, { "epoch": 6.59, "learning_rate": 1.7076296398004485e-05, "loss": 1.5524, "step": 144370 }, { "epoch": 6.59, "learning_rate": 1.7074007963751203e-05, "loss": 1.4399, "step": 144380 }, { "epoch": 6.59, "learning_rate": 1.7071719529497917e-05, "loss": 1.5563, "step": 144390 }, { "epoch": 6.59, "learning_rate": 1.7069431095244634e-05, "loss": 1.4415, "step": 144400 }, { "epoch": 6.59, "learning_rate": 1.7067142660991352e-05, "loss": 1.4256, "step": 144410 }, { "epoch": 6.59, "learning_rate": 1.7064854226738066e-05, "loss": 1.4692, "step": 144420 }, { "epoch": 6.6, "learning_rate": 1.7062565792484784e-05, "loss": 1.3383, "step": 144430 }, { "epoch": 6.6, "learning_rate": 1.70602773582315e-05, "loss": 1.3527, "step": 144440 }, { "epoch": 6.6, "learning_rate": 1.7057988923978215e-05, "loss": 1.4832, "step": 144450 }, { "epoch": 6.6, "learning_rate": 1.7055700489724933e-05, "loss": 1.4289, "step": 144460 }, { "epoch": 6.6, "learning_rate": 1.7053412055471647e-05, "loss": 1.4676, "step": 144470 }, { "epoch": 6.6, "learning_rate": 1.705112362121836e-05, "loss": 1.4419, "step": 144480 }, { "epoch": 6.6, "learning_rate": 1.704883518696508e-05, "loss": 1.4178, "step": 144490 }, { "epoch": 6.6, "learning_rate": 1.7046546752711796e-05, "loss": 1.4991, "step": 144500 }, { "epoch": 6.6, "learning_rate": 1.704425831845851e-05, "loss": 1.5327, "step": 144510 }, { "epoch": 6.6, "learning_rate": 1.7041969884205228e-05, "loss": 1.2645, "step": 144520 }, { "epoch": 6.6, "learning_rate": 1.7039681449951945e-05, "loss": 1.7114, "step": 144530 }, { "epoch": 6.6, "learning_rate": 1.703739301569866e-05, "loss": 1.5252, "step": 144540 }, { "epoch": 6.6, "learning_rate": 1.7035104581445377e-05, "loss": 1.521, "step": 144550 }, { "epoch": 6.6, "learning_rate": 1.7032816147192094e-05, "loss": 1.4617, "step": 144560 }, { "epoch": 6.6, "learning_rate": 1.703052771293881e-05, "loss": 1.4376, "step": 144570 }, { "epoch": 6.6, "learning_rate": 1.7028239278685523e-05, "loss": 1.4185, "step": 144580 }, { "epoch": 6.6, "learning_rate": 1.702595084443224e-05, "loss": 1.3443, "step": 144590 }, { "epoch": 6.6, "learning_rate": 1.7023662410178958e-05, "loss": 1.3347, "step": 144600 }, { "epoch": 6.6, "learning_rate": 1.7021373975925672e-05, "loss": 1.5485, "step": 144610 }, { "epoch": 6.6, "learning_rate": 1.701908554167239e-05, "loss": 1.4054, "step": 144620 }, { "epoch": 6.6, "learning_rate": 1.7016797107419103e-05, "loss": 1.2981, "step": 144630 }, { "epoch": 6.6, "learning_rate": 1.701450867316582e-05, "loss": 1.3679, "step": 144640 }, { "epoch": 6.61, "learning_rate": 1.701222023891254e-05, "loss": 1.4071, "step": 144650 }, { "epoch": 6.61, "learning_rate": 1.7009931804659253e-05, "loss": 1.4995, "step": 144660 }, { "epoch": 6.61, "learning_rate": 1.7007643370405967e-05, "loss": 1.3221, "step": 144670 }, { "epoch": 6.61, "learning_rate": 1.7005354936152684e-05, "loss": 1.3098, "step": 144680 }, { "epoch": 6.61, "learning_rate": 1.7003066501899402e-05, "loss": 1.3644, "step": 144690 }, { "epoch": 6.61, "learning_rate": 1.7000778067646116e-05, "loss": 1.4156, "step": 144700 }, { "epoch": 6.61, "learning_rate": 1.6998489633392833e-05, "loss": 1.397, "step": 144710 }, { "epoch": 6.61, "learning_rate": 1.699620119913955e-05, "loss": 1.4582, "step": 144720 }, { "epoch": 6.61, "learning_rate": 1.6993912764886265e-05, "loss": 1.4892, "step": 144730 }, { "epoch": 6.61, "learning_rate": 1.6991624330632983e-05, "loss": 1.3862, "step": 144740 }, { "epoch": 6.61, "learning_rate": 1.69893358963797e-05, "loss": 1.3868, "step": 144750 }, { "epoch": 6.61, "learning_rate": 1.6987047462126414e-05, "loss": 1.3966, "step": 144760 }, { "epoch": 6.61, "learning_rate": 1.698475902787313e-05, "loss": 1.464, "step": 144770 }, { "epoch": 6.61, "learning_rate": 1.6982470593619846e-05, "loss": 1.3856, "step": 144780 }, { "epoch": 6.61, "learning_rate": 1.698018215936656e-05, "loss": 1.452, "step": 144790 }, { "epoch": 6.61, "learning_rate": 1.6977893725113278e-05, "loss": 1.3951, "step": 144800 }, { "epoch": 6.61, "learning_rate": 1.6975605290859995e-05, "loss": 1.3652, "step": 144810 }, { "epoch": 6.61, "learning_rate": 1.697331685660671e-05, "loss": 1.2933, "step": 144820 }, { "epoch": 6.61, "learning_rate": 1.6971028422353427e-05, "loss": 1.3994, "step": 144830 }, { "epoch": 6.61, "learning_rate": 1.6968739988100144e-05, "loss": 1.5406, "step": 144840 }, { "epoch": 6.61, "learning_rate": 1.696645155384686e-05, "loss": 1.4614, "step": 144850 }, { "epoch": 6.61, "learning_rate": 1.6964163119593573e-05, "loss": 1.483, "step": 144860 }, { "epoch": 6.62, "learning_rate": 1.696187468534029e-05, "loss": 1.3841, "step": 144870 }, { "epoch": 6.62, "learning_rate": 1.6959586251087008e-05, "loss": 1.426, "step": 144880 }, { "epoch": 6.62, "learning_rate": 1.6957297816833722e-05, "loss": 1.4918, "step": 144890 }, { "epoch": 6.62, "learning_rate": 1.695500938258044e-05, "loss": 1.4435, "step": 144900 }, { "epoch": 6.62, "learning_rate": 1.6952720948327157e-05, "loss": 1.2154, "step": 144910 }, { "epoch": 6.62, "learning_rate": 1.695043251407387e-05, "loss": 1.4035, "step": 144920 }, { "epoch": 6.62, "learning_rate": 1.694814407982059e-05, "loss": 1.3386, "step": 144930 }, { "epoch": 6.62, "learning_rate": 1.6945855645567306e-05, "loss": 1.5148, "step": 144940 }, { "epoch": 6.62, "learning_rate": 1.694356721131402e-05, "loss": 1.3791, "step": 144950 }, { "epoch": 6.62, "learning_rate": 1.6941278777060734e-05, "loss": 1.368, "step": 144960 }, { "epoch": 6.62, "learning_rate": 1.6938990342807452e-05, "loss": 1.3528, "step": 144970 }, { "epoch": 6.62, "learning_rate": 1.6936701908554166e-05, "loss": 1.3993, "step": 144980 }, { "epoch": 6.62, "learning_rate": 1.6934413474300883e-05, "loss": 1.3254, "step": 144990 }, { "epoch": 6.62, "learning_rate": 1.69321250400476e-05, "loss": 1.3549, "step": 145000 }, { "epoch": 6.62, "learning_rate": 1.6929836605794315e-05, "loss": 1.387, "step": 145010 }, { "epoch": 6.62, "learning_rate": 1.6927548171541033e-05, "loss": 1.4479, "step": 145020 }, { "epoch": 6.62, "learning_rate": 1.692525973728775e-05, "loss": 1.4401, "step": 145030 }, { "epoch": 6.62, "learning_rate": 1.6922971303034464e-05, "loss": 1.5096, "step": 145040 }, { "epoch": 6.62, "learning_rate": 1.6920682868781182e-05, "loss": 1.3774, "step": 145050 }, { "epoch": 6.62, "learning_rate": 1.6918394434527896e-05, "loss": 1.5091, "step": 145060 }, { "epoch": 6.62, "learning_rate": 1.6916106000274613e-05, "loss": 1.3847, "step": 145070 }, { "epoch": 6.62, "learning_rate": 1.6913817566021328e-05, "loss": 1.3786, "step": 145080 }, { "epoch": 6.63, "learning_rate": 1.6911529131768045e-05, "loss": 1.2866, "step": 145090 }, { "epoch": 6.63, "learning_rate": 1.6909240697514763e-05, "loss": 1.4738, "step": 145100 }, { "epoch": 6.63, "learning_rate": 1.6906952263261477e-05, "loss": 1.3966, "step": 145110 }, { "epoch": 6.63, "learning_rate": 1.6904663829008194e-05, "loss": 1.3659, "step": 145120 }, { "epoch": 6.63, "learning_rate": 1.6902375394754912e-05, "loss": 1.4662, "step": 145130 }, { "epoch": 6.63, "learning_rate": 1.6900086960501626e-05, "loss": 1.4124, "step": 145140 }, { "epoch": 6.63, "learning_rate": 1.6897798526248343e-05, "loss": 1.3127, "step": 145150 }, { "epoch": 6.63, "learning_rate": 1.6895510091995058e-05, "loss": 1.3124, "step": 145160 }, { "epoch": 6.63, "learning_rate": 1.6893221657741772e-05, "loss": 1.4056, "step": 145170 }, { "epoch": 6.63, "learning_rate": 1.689093322348849e-05, "loss": 1.4354, "step": 145180 }, { "epoch": 6.63, "learning_rate": 1.6888644789235207e-05, "loss": 1.471, "step": 145190 }, { "epoch": 6.63, "learning_rate": 1.688635635498192e-05, "loss": 1.6435, "step": 145200 }, { "epoch": 6.63, "learning_rate": 1.688406792072864e-05, "loss": 1.5198, "step": 145210 }, { "epoch": 6.63, "learning_rate": 1.6881779486475356e-05, "loss": 1.4807, "step": 145220 }, { "epoch": 6.63, "learning_rate": 1.687949105222207e-05, "loss": 1.2834, "step": 145230 }, { "epoch": 6.63, "learning_rate": 1.6877202617968788e-05, "loss": 1.3182, "step": 145240 }, { "epoch": 6.63, "learning_rate": 1.6874914183715505e-05, "loss": 1.4564, "step": 145250 }, { "epoch": 6.63, "learning_rate": 1.6872625749462216e-05, "loss": 1.5246, "step": 145260 }, { "epoch": 6.63, "learning_rate": 1.6870337315208933e-05, "loss": 1.4857, "step": 145270 }, { "epoch": 6.63, "learning_rate": 1.686804888095565e-05, "loss": 1.4065, "step": 145280 }, { "epoch": 6.63, "learning_rate": 1.6865760446702365e-05, "loss": 1.3543, "step": 145290 }, { "epoch": 6.63, "learning_rate": 1.6863472012449083e-05, "loss": 1.3536, "step": 145300 }, { "epoch": 6.64, "learning_rate": 1.68611835781958e-05, "loss": 1.3447, "step": 145310 }, { "epoch": 6.64, "learning_rate": 1.6858895143942514e-05, "loss": 1.5327, "step": 145320 }, { "epoch": 6.64, "learning_rate": 1.6856606709689232e-05, "loss": 1.3835, "step": 145330 }, { "epoch": 6.64, "learning_rate": 1.685431827543595e-05, "loss": 1.3664, "step": 145340 }, { "epoch": 6.64, "learning_rate": 1.6852029841182663e-05, "loss": 1.4368, "step": 145350 }, { "epoch": 6.64, "learning_rate": 1.6849741406929378e-05, "loss": 1.366, "step": 145360 }, { "epoch": 6.64, "learning_rate": 1.6847452972676095e-05, "loss": 1.3625, "step": 145370 }, { "epoch": 6.64, "learning_rate": 1.6845164538422813e-05, "loss": 1.3322, "step": 145380 }, { "epoch": 6.64, "learning_rate": 1.6842876104169527e-05, "loss": 1.3827, "step": 145390 }, { "epoch": 6.64, "learning_rate": 1.6840587669916244e-05, "loss": 1.4229, "step": 145400 }, { "epoch": 6.64, "learning_rate": 1.6838299235662962e-05, "loss": 1.4226, "step": 145410 }, { "epoch": 6.64, "learning_rate": 1.6836010801409676e-05, "loss": 1.3972, "step": 145420 }, { "epoch": 6.64, "learning_rate": 1.6833722367156393e-05, "loss": 1.4681, "step": 145430 }, { "epoch": 6.64, "learning_rate": 1.683143393290311e-05, "loss": 1.5199, "step": 145440 }, { "epoch": 6.64, "learning_rate": 1.6829145498649825e-05, "loss": 1.3548, "step": 145450 }, { "epoch": 6.64, "learning_rate": 1.682685706439654e-05, "loss": 1.2066, "step": 145460 }, { "epoch": 6.64, "learning_rate": 1.6824568630143257e-05, "loss": 1.3518, "step": 145470 }, { "epoch": 6.64, "learning_rate": 1.682228019588997e-05, "loss": 1.3794, "step": 145480 }, { "epoch": 6.64, "learning_rate": 1.681999176163669e-05, "loss": 1.4108, "step": 145490 }, { "epoch": 6.64, "learning_rate": 1.6817703327383406e-05, "loss": 1.42, "step": 145500 }, { "epoch": 6.64, "learning_rate": 1.681541489313012e-05, "loss": 1.5083, "step": 145510 }, { "epoch": 6.64, "learning_rate": 1.6813126458876838e-05, "loss": 1.3564, "step": 145520 }, { "epoch": 6.65, "learning_rate": 1.6810838024623555e-05, "loss": 1.2623, "step": 145530 }, { "epoch": 6.65, "learning_rate": 1.680854959037027e-05, "loss": 1.3727, "step": 145540 }, { "epoch": 6.65, "learning_rate": 1.6806261156116987e-05, "loss": 1.2693, "step": 145550 }, { "epoch": 6.65, "learning_rate": 1.68039727218637e-05, "loss": 1.5426, "step": 145560 }, { "epoch": 6.65, "learning_rate": 1.680168428761042e-05, "loss": 1.4551, "step": 145570 }, { "epoch": 6.65, "learning_rate": 1.6799395853357133e-05, "loss": 1.3745, "step": 145580 }, { "epoch": 6.65, "learning_rate": 1.679710741910385e-05, "loss": 1.4629, "step": 145590 }, { "epoch": 6.65, "learning_rate": 1.6794818984850568e-05, "loss": 1.2873, "step": 145600 }, { "epoch": 6.65, "learning_rate": 1.6792530550597282e-05, "loss": 1.2786, "step": 145610 }, { "epoch": 6.65, "learning_rate": 1.6790242116344e-05, "loss": 1.5677, "step": 145620 }, { "epoch": 6.65, "learning_rate": 1.6787953682090717e-05, "loss": 1.3152, "step": 145630 }, { "epoch": 6.65, "learning_rate": 1.678566524783743e-05, "loss": 1.3715, "step": 145640 }, { "epoch": 6.65, "learning_rate": 1.6783376813584145e-05, "loss": 1.4543, "step": 145650 }, { "epoch": 6.65, "learning_rate": 1.6781088379330863e-05, "loss": 1.4216, "step": 145660 }, { "epoch": 6.65, "learning_rate": 1.6778799945077577e-05, "loss": 1.4073, "step": 145670 }, { "epoch": 6.65, "learning_rate": 1.6776511510824294e-05, "loss": 1.3784, "step": 145680 }, { "epoch": 6.65, "learning_rate": 1.6774223076571012e-05, "loss": 1.4715, "step": 145690 }, { "epoch": 6.65, "learning_rate": 1.6771934642317726e-05, "loss": 1.528, "step": 145700 }, { "epoch": 6.65, "learning_rate": 1.6769646208064443e-05, "loss": 1.393, "step": 145710 }, { "epoch": 6.65, "learning_rate": 1.676735777381116e-05, "loss": 1.2031, "step": 145720 }, { "epoch": 6.65, "learning_rate": 1.6765069339557875e-05, "loss": 1.4497, "step": 145730 }, { "epoch": 6.65, "learning_rate": 1.6762780905304593e-05, "loss": 1.4152, "step": 145740 }, { "epoch": 6.66, "learning_rate": 1.6760492471051307e-05, "loss": 1.5314, "step": 145750 }, { "epoch": 6.66, "learning_rate": 1.6758204036798024e-05, "loss": 1.3004, "step": 145760 }, { "epoch": 6.66, "learning_rate": 1.675591560254474e-05, "loss": 1.4634, "step": 145770 }, { "epoch": 6.66, "learning_rate": 1.6753627168291456e-05, "loss": 1.4379, "step": 145780 }, { "epoch": 6.66, "learning_rate": 1.675133873403817e-05, "loss": 1.5662, "step": 145790 }, { "epoch": 6.66, "learning_rate": 1.6749050299784888e-05, "loss": 1.584, "step": 145800 }, { "epoch": 6.66, "learning_rate": 1.6746761865531605e-05, "loss": 1.386, "step": 145810 }, { "epoch": 6.66, "learning_rate": 1.674447343127832e-05, "loss": 1.3152, "step": 145820 }, { "epoch": 6.66, "learning_rate": 1.6742184997025037e-05, "loss": 1.3346, "step": 145830 }, { "epoch": 6.66, "learning_rate": 1.6739896562771754e-05, "loss": 1.4163, "step": 145840 }, { "epoch": 6.66, "learning_rate": 1.673760812851847e-05, "loss": 1.3611, "step": 145850 }, { "epoch": 6.66, "learning_rate": 1.6735319694265182e-05, "loss": 1.41, "step": 145860 }, { "epoch": 6.66, "learning_rate": 1.67330312600119e-05, "loss": 1.3727, "step": 145870 }, { "epoch": 6.66, "learning_rate": 1.6730742825758618e-05, "loss": 1.4867, "step": 145880 }, { "epoch": 6.66, "learning_rate": 1.672845439150533e-05, "loss": 1.5383, "step": 145890 }, { "epoch": 6.66, "learning_rate": 1.672616595725205e-05, "loss": 1.3821, "step": 145900 }, { "epoch": 6.66, "learning_rate": 1.6723877522998767e-05, "loss": 1.3893, "step": 145910 }, { "epoch": 6.66, "learning_rate": 1.672158908874548e-05, "loss": 1.443, "step": 145920 }, { "epoch": 6.66, "learning_rate": 1.67193006544922e-05, "loss": 1.467, "step": 145930 }, { "epoch": 6.66, "learning_rate": 1.6717012220238916e-05, "loss": 1.4266, "step": 145940 }, { "epoch": 6.66, "learning_rate": 1.6714723785985627e-05, "loss": 1.3582, "step": 145950 }, { "epoch": 6.66, "learning_rate": 1.6712435351732344e-05, "loss": 1.378, "step": 145960 }, { "epoch": 6.67, "learning_rate": 1.671014691747906e-05, "loss": 1.3371, "step": 145970 }, { "epoch": 6.67, "learning_rate": 1.6707858483225776e-05, "loss": 1.6465, "step": 145980 }, { "epoch": 6.67, "learning_rate": 1.6705570048972493e-05, "loss": 1.3916, "step": 145990 }, { "epoch": 6.67, "learning_rate": 1.670328161471921e-05, "loss": 1.3893, "step": 146000 }, { "epoch": 6.67, "learning_rate": 1.6700993180465925e-05, "loss": 1.569, "step": 146010 }, { "epoch": 6.67, "learning_rate": 1.6698704746212642e-05, "loss": 1.4218, "step": 146020 }, { "epoch": 6.67, "learning_rate": 1.669641631195936e-05, "loss": 1.449, "step": 146030 }, { "epoch": 6.67, "learning_rate": 1.6694127877706074e-05, "loss": 1.5266, "step": 146040 }, { "epoch": 6.67, "learning_rate": 1.6691839443452788e-05, "loss": 1.5073, "step": 146050 }, { "epoch": 6.67, "learning_rate": 1.6689551009199506e-05, "loss": 1.3537, "step": 146060 }, { "epoch": 6.67, "learning_rate": 1.6687262574946223e-05, "loss": 1.5457, "step": 146070 }, { "epoch": 6.67, "learning_rate": 1.6684974140692937e-05, "loss": 1.4156, "step": 146080 }, { "epoch": 6.67, "learning_rate": 1.6682685706439655e-05, "loss": 1.5182, "step": 146090 }, { "epoch": 6.67, "learning_rate": 1.6680397272186372e-05, "loss": 1.6088, "step": 146100 }, { "epoch": 6.67, "learning_rate": 1.6678108837933087e-05, "loss": 1.5117, "step": 146110 }, { "epoch": 6.67, "learning_rate": 1.6675820403679804e-05, "loss": 1.329, "step": 146120 }, { "epoch": 6.67, "learning_rate": 1.667353196942652e-05, "loss": 1.388, "step": 146130 }, { "epoch": 6.67, "learning_rate": 1.6671243535173236e-05, "loss": 1.4005, "step": 146140 }, { "epoch": 6.67, "learning_rate": 1.666895510091995e-05, "loss": 1.3853, "step": 146150 }, { "epoch": 6.67, "learning_rate": 1.6666666666666667e-05, "loss": 1.4728, "step": 146160 }, { "epoch": 6.67, "learning_rate": 1.666437823241338e-05, "loss": 1.6233, "step": 146170 }, { "epoch": 6.67, "learning_rate": 1.66620897981601e-05, "loss": 1.4801, "step": 146180 }, { "epoch": 6.68, "learning_rate": 1.6659801363906817e-05, "loss": 1.433, "step": 146190 }, { "epoch": 6.68, "learning_rate": 1.665751292965353e-05, "loss": 1.4173, "step": 146200 }, { "epoch": 6.68, "learning_rate": 1.6655224495400248e-05, "loss": 1.3433, "step": 146210 }, { "epoch": 6.68, "learning_rate": 1.6652936061146966e-05, "loss": 1.3387, "step": 146220 }, { "epoch": 6.68, "learning_rate": 1.665064762689368e-05, "loss": 1.282, "step": 146230 }, { "epoch": 6.68, "learning_rate": 1.6648359192640397e-05, "loss": 1.3995, "step": 146240 }, { "epoch": 6.68, "learning_rate": 1.664607075838711e-05, "loss": 1.4179, "step": 146250 }, { "epoch": 6.68, "learning_rate": 1.664378232413383e-05, "loss": 1.6015, "step": 146260 }, { "epoch": 6.68, "learning_rate": 1.6641493889880543e-05, "loss": 1.412, "step": 146270 }, { "epoch": 6.68, "learning_rate": 1.663920545562726e-05, "loss": 1.3605, "step": 146280 }, { "epoch": 6.68, "learning_rate": 1.663691702137398e-05, "loss": 1.4787, "step": 146290 }, { "epoch": 6.68, "learning_rate": 1.6634628587120692e-05, "loss": 1.4731, "step": 146300 }, { "epoch": 6.68, "learning_rate": 1.663234015286741e-05, "loss": 1.3672, "step": 146310 }, { "epoch": 6.68, "learning_rate": 1.6630051718614127e-05, "loss": 1.5667, "step": 146320 }, { "epoch": 6.68, "learning_rate": 1.662776328436084e-05, "loss": 1.3673, "step": 146330 }, { "epoch": 6.68, "learning_rate": 1.662547485010756e-05, "loss": 1.3532, "step": 146340 }, { "epoch": 6.68, "learning_rate": 1.6623186415854273e-05, "loss": 1.3035, "step": 146350 }, { "epoch": 6.68, "learning_rate": 1.6620897981600987e-05, "loss": 1.4569, "step": 146360 }, { "epoch": 6.68, "learning_rate": 1.6618609547347705e-05, "loss": 1.4216, "step": 146370 }, { "epoch": 6.68, "learning_rate": 1.6616321113094422e-05, "loss": 1.4569, "step": 146380 }, { "epoch": 6.68, "learning_rate": 1.6614032678841137e-05, "loss": 1.3101, "step": 146390 }, { "epoch": 6.69, "learning_rate": 1.6611744244587854e-05, "loss": 1.4901, "step": 146400 }, { "epoch": 6.69, "learning_rate": 1.660945581033457e-05, "loss": 1.3298, "step": 146410 }, { "epoch": 6.69, "learning_rate": 1.6607167376081286e-05, "loss": 1.1784, "step": 146420 }, { "epoch": 6.69, "learning_rate": 1.6604878941828003e-05, "loss": 1.4179, "step": 146430 }, { "epoch": 6.69, "learning_rate": 1.6602590507574717e-05, "loss": 1.4926, "step": 146440 }, { "epoch": 6.69, "learning_rate": 1.660030207332143e-05, "loss": 1.2945, "step": 146450 }, { "epoch": 6.69, "learning_rate": 1.659801363906815e-05, "loss": 1.2957, "step": 146460 }, { "epoch": 6.69, "learning_rate": 1.6595725204814867e-05, "loss": 1.2916, "step": 146470 }, { "epoch": 6.69, "learning_rate": 1.659343677056158e-05, "loss": 1.6609, "step": 146480 }, { "epoch": 6.69, "learning_rate": 1.6591148336308298e-05, "loss": 1.5131, "step": 146490 }, { "epoch": 6.69, "learning_rate": 1.6588859902055016e-05, "loss": 1.4825, "step": 146500 }, { "epoch": 6.69, "learning_rate": 1.658657146780173e-05, "loss": 1.4456, "step": 146510 }, { "epoch": 6.69, "learning_rate": 1.6584283033548447e-05, "loss": 1.3557, "step": 146520 }, { "epoch": 6.69, "learning_rate": 1.6581994599295165e-05, "loss": 1.5292, "step": 146530 }, { "epoch": 6.69, "learning_rate": 1.657970616504188e-05, "loss": 1.5727, "step": 146540 }, { "epoch": 6.69, "learning_rate": 1.6577417730788593e-05, "loss": 1.4312, "step": 146550 }, { "epoch": 6.69, "learning_rate": 1.657512929653531e-05, "loss": 1.4938, "step": 146560 }, { "epoch": 6.69, "learning_rate": 1.6572840862282028e-05, "loss": 1.4412, "step": 146570 }, { "epoch": 6.69, "learning_rate": 1.6570552428028742e-05, "loss": 1.3726, "step": 146580 }, { "epoch": 6.69, "learning_rate": 1.656826399377546e-05, "loss": 1.4474, "step": 146590 }, { "epoch": 6.69, "learning_rate": 1.6565975559522177e-05, "loss": 1.4974, "step": 146600 }, { "epoch": 6.69, "learning_rate": 1.656368712526889e-05, "loss": 1.396, "step": 146610 }, { "epoch": 6.7, "learning_rate": 1.656139869101561e-05, "loss": 1.3519, "step": 146620 }, { "epoch": 6.7, "learning_rate": 1.6559110256762327e-05, "loss": 1.3638, "step": 146630 }, { "epoch": 6.7, "learning_rate": 1.6556821822509037e-05, "loss": 1.3332, "step": 146640 }, { "epoch": 6.7, "learning_rate": 1.6554533388255755e-05, "loss": 1.4708, "step": 146650 }, { "epoch": 6.7, "learning_rate": 1.6552244954002472e-05, "loss": 1.5123, "step": 146660 }, { "epoch": 6.7, "learning_rate": 1.6549956519749187e-05, "loss": 1.4294, "step": 146670 }, { "epoch": 6.7, "learning_rate": 1.6547668085495904e-05, "loss": 1.3411, "step": 146680 }, { "epoch": 6.7, "learning_rate": 1.654537965124262e-05, "loss": 1.416, "step": 146690 }, { "epoch": 6.7, "learning_rate": 1.6543091216989336e-05, "loss": 1.2695, "step": 146700 }, { "epoch": 6.7, "learning_rate": 1.6540802782736053e-05, "loss": 1.3116, "step": 146710 }, { "epoch": 6.7, "learning_rate": 1.653851434848277e-05, "loss": 1.2949, "step": 146720 }, { "epoch": 6.7, "learning_rate": 1.6536225914229485e-05, "loss": 1.336, "step": 146730 }, { "epoch": 6.7, "learning_rate": 1.65339374799762e-05, "loss": 1.2626, "step": 146740 }, { "epoch": 6.7, "learning_rate": 1.6531649045722917e-05, "loss": 1.3497, "step": 146750 }, { "epoch": 6.7, "learning_rate": 1.6529360611469634e-05, "loss": 1.4662, "step": 146760 }, { "epoch": 6.7, "learning_rate": 1.6527072177216348e-05, "loss": 1.306, "step": 146770 }, { "epoch": 6.7, "learning_rate": 1.6524783742963066e-05, "loss": 1.453, "step": 146780 }, { "epoch": 6.7, "learning_rate": 1.6522495308709783e-05, "loss": 1.3499, "step": 146790 }, { "epoch": 6.7, "learning_rate": 1.6520206874456497e-05, "loss": 1.3319, "step": 146800 }, { "epoch": 6.7, "learning_rate": 1.6517918440203215e-05, "loss": 1.504, "step": 146810 }, { "epoch": 6.7, "learning_rate": 1.6515630005949932e-05, "loss": 1.476, "step": 146820 }, { "epoch": 6.7, "learning_rate": 1.6513341571696647e-05, "loss": 1.5672, "step": 146830 }, { "epoch": 6.71, "learning_rate": 1.651105313744336e-05, "loss": 1.5443, "step": 146840 }, { "epoch": 6.71, "learning_rate": 1.6508764703190078e-05, "loss": 1.3327, "step": 146850 }, { "epoch": 6.71, "learning_rate": 1.6506476268936792e-05, "loss": 1.4242, "step": 146860 }, { "epoch": 6.71, "learning_rate": 1.650418783468351e-05, "loss": 1.4094, "step": 146870 }, { "epoch": 6.71, "learning_rate": 1.6501899400430227e-05, "loss": 1.5145, "step": 146880 }, { "epoch": 6.71, "learning_rate": 1.649961096617694e-05, "loss": 1.5039, "step": 146890 }, { "epoch": 6.71, "learning_rate": 1.649732253192366e-05, "loss": 1.3523, "step": 146900 }, { "epoch": 6.71, "learning_rate": 1.6495034097670377e-05, "loss": 1.4915, "step": 146910 }, { "epoch": 6.71, "learning_rate": 1.649274566341709e-05, "loss": 1.5021, "step": 146920 }, { "epoch": 6.71, "learning_rate": 1.6490457229163808e-05, "loss": 1.3799, "step": 146930 }, { "epoch": 6.71, "learning_rate": 1.6488168794910522e-05, "loss": 1.479, "step": 146940 }, { "epoch": 6.71, "learning_rate": 1.648588036065724e-05, "loss": 1.4224, "step": 146950 }, { "epoch": 6.71, "learning_rate": 1.6483591926403954e-05, "loss": 1.3642, "step": 146960 }, { "epoch": 6.71, "learning_rate": 1.648130349215067e-05, "loss": 1.3972, "step": 146970 }, { "epoch": 6.71, "learning_rate": 1.6479015057897386e-05, "loss": 1.4838, "step": 146980 }, { "epoch": 6.71, "learning_rate": 1.6476726623644103e-05, "loss": 1.6008, "step": 146990 }, { "epoch": 6.71, "learning_rate": 1.647443818939082e-05, "loss": 1.5894, "step": 147000 }, { "epoch": 6.71, "learning_rate": 1.6472149755137535e-05, "loss": 1.3678, "step": 147010 }, { "epoch": 6.71, "learning_rate": 1.6469861320884252e-05, "loss": 1.3319, "step": 147020 }, { "epoch": 6.71, "learning_rate": 1.646757288663097e-05, "loss": 1.5858, "step": 147030 }, { "epoch": 6.71, "learning_rate": 1.6465284452377684e-05, "loss": 1.4399, "step": 147040 }, { "epoch": 6.71, "learning_rate": 1.6462996018124398e-05, "loss": 1.3706, "step": 147050 }, { "epoch": 6.72, "learning_rate": 1.6460707583871116e-05, "loss": 1.3599, "step": 147060 }, { "epoch": 6.72, "learning_rate": 1.6458419149617833e-05, "loss": 1.4642, "step": 147070 }, { "epoch": 6.72, "learning_rate": 1.6456130715364547e-05, "loss": 1.413, "step": 147080 }, { "epoch": 6.72, "learning_rate": 1.6453842281111265e-05, "loss": 1.5038, "step": 147090 }, { "epoch": 6.72, "learning_rate": 1.6451553846857982e-05, "loss": 1.5038, "step": 147100 }, { "epoch": 6.72, "learning_rate": 1.6449265412604696e-05, "loss": 1.2153, "step": 147110 }, { "epoch": 6.72, "learning_rate": 1.6446976978351414e-05, "loss": 1.4277, "step": 147120 }, { "epoch": 6.72, "learning_rate": 1.644468854409813e-05, "loss": 1.5183, "step": 147130 }, { "epoch": 6.72, "learning_rate": 1.6442400109844842e-05, "loss": 1.3124, "step": 147140 }, { "epoch": 6.72, "learning_rate": 1.644011167559156e-05, "loss": 1.5857, "step": 147150 }, { "epoch": 6.72, "learning_rate": 1.6437823241338277e-05, "loss": 1.4024, "step": 147160 }, { "epoch": 6.72, "learning_rate": 1.643553480708499e-05, "loss": 1.337, "step": 147170 }, { "epoch": 6.72, "learning_rate": 1.643324637283171e-05, "loss": 1.4318, "step": 147180 }, { "epoch": 6.72, "learning_rate": 1.6430957938578427e-05, "loss": 1.507, "step": 147190 }, { "epoch": 6.72, "learning_rate": 1.642866950432514e-05, "loss": 1.3635, "step": 147200 }, { "epoch": 6.72, "learning_rate": 1.6426381070071858e-05, "loss": 1.334, "step": 147210 }, { "epoch": 6.72, "learning_rate": 1.6424092635818576e-05, "loss": 1.3274, "step": 147220 }, { "epoch": 6.72, "learning_rate": 1.642180420156529e-05, "loss": 1.2929, "step": 147230 }, { "epoch": 6.72, "learning_rate": 1.6419515767312004e-05, "loss": 1.3924, "step": 147240 }, { "epoch": 6.72, "learning_rate": 1.641722733305872e-05, "loss": 1.406, "step": 147250 }, { "epoch": 6.72, "learning_rate": 1.641493889880544e-05, "loss": 1.4849, "step": 147260 }, { "epoch": 6.72, "learning_rate": 1.6412650464552153e-05, "loss": 1.5486, "step": 147270 }, { "epoch": 6.73, "learning_rate": 1.641036203029887e-05, "loss": 1.5014, "step": 147280 }, { "epoch": 6.73, "learning_rate": 1.6408073596045588e-05, "loss": 1.3944, "step": 147290 }, { "epoch": 6.73, "learning_rate": 1.6405785161792302e-05, "loss": 1.3204, "step": 147300 }, { "epoch": 6.73, "learning_rate": 1.640349672753902e-05, "loss": 1.4302, "step": 147310 }, { "epoch": 6.73, "learning_rate": 1.6401208293285737e-05, "loss": 1.5186, "step": 147320 }, { "epoch": 6.73, "learning_rate": 1.6398919859032448e-05, "loss": 1.3134, "step": 147330 }, { "epoch": 6.73, "learning_rate": 1.6396631424779166e-05, "loss": 1.3607, "step": 147340 }, { "epoch": 6.73, "learning_rate": 1.6394342990525883e-05, "loss": 1.5148, "step": 147350 }, { "epoch": 6.73, "learning_rate": 1.6392054556272597e-05, "loss": 1.4466, "step": 147360 }, { "epoch": 6.73, "learning_rate": 1.6389766122019315e-05, "loss": 1.2777, "step": 147370 }, { "epoch": 6.73, "learning_rate": 1.6387477687766032e-05, "loss": 1.3823, "step": 147380 }, { "epoch": 6.73, "learning_rate": 1.6385189253512746e-05, "loss": 1.2933, "step": 147390 }, { "epoch": 6.73, "learning_rate": 1.6382900819259464e-05, "loss": 1.4949, "step": 147400 }, { "epoch": 6.73, "learning_rate": 1.638061238500618e-05, "loss": 1.33, "step": 147410 }, { "epoch": 6.73, "learning_rate": 1.6378323950752896e-05, "loss": 1.2803, "step": 147420 }, { "epoch": 6.73, "learning_rate": 1.637603551649961e-05, "loss": 1.361, "step": 147430 }, { "epoch": 6.73, "learning_rate": 1.6373747082246327e-05, "loss": 1.3336, "step": 147440 }, { "epoch": 6.73, "learning_rate": 1.6371458647993045e-05, "loss": 1.325, "step": 147450 }, { "epoch": 6.73, "learning_rate": 1.636917021373976e-05, "loss": 1.3571, "step": 147460 }, { "epoch": 6.73, "learning_rate": 1.6366881779486476e-05, "loss": 1.2797, "step": 147470 }, { "epoch": 6.73, "learning_rate": 1.6364593345233194e-05, "loss": 1.5296, "step": 147480 }, { "epoch": 6.73, "learning_rate": 1.6362304910979908e-05, "loss": 1.3136, "step": 147490 }, { "epoch": 6.74, "learning_rate": 1.6360016476726626e-05, "loss": 1.4308, "step": 147500 }, { "epoch": 6.74, "learning_rate": 1.635772804247334e-05, "loss": 1.4886, "step": 147510 }, { "epoch": 6.74, "learning_rate": 1.6355439608220057e-05, "loss": 1.3062, "step": 147520 }, { "epoch": 6.74, "learning_rate": 1.635315117396677e-05, "loss": 1.7176, "step": 147530 }, { "epoch": 6.74, "learning_rate": 1.635086273971349e-05, "loss": 1.553, "step": 147540 }, { "epoch": 6.74, "learning_rate": 1.6348574305460203e-05, "loss": 1.4127, "step": 147550 }, { "epoch": 6.74, "learning_rate": 1.634628587120692e-05, "loss": 1.3898, "step": 147560 }, { "epoch": 6.74, "learning_rate": 1.6343997436953638e-05, "loss": 1.4884, "step": 147570 }, { "epoch": 6.74, "learning_rate": 1.6341709002700352e-05, "loss": 1.5427, "step": 147580 }, { "epoch": 6.74, "learning_rate": 1.633942056844707e-05, "loss": 1.4294, "step": 147590 }, { "epoch": 6.74, "learning_rate": 1.6337132134193787e-05, "loss": 1.4117, "step": 147600 }, { "epoch": 6.74, "learning_rate": 1.63348436999405e-05, "loss": 1.3418, "step": 147610 }, { "epoch": 6.74, "learning_rate": 1.633255526568722e-05, "loss": 1.4253, "step": 147620 }, { "epoch": 6.74, "learning_rate": 1.6330266831433933e-05, "loss": 1.5218, "step": 147630 }, { "epoch": 6.74, "learning_rate": 1.6327978397180647e-05, "loss": 1.4722, "step": 147640 }, { "epoch": 6.74, "learning_rate": 1.6325689962927365e-05, "loss": 1.5014, "step": 147650 }, { "epoch": 6.74, "learning_rate": 1.6323401528674082e-05, "loss": 1.5782, "step": 147660 }, { "epoch": 6.74, "learning_rate": 1.6321113094420796e-05, "loss": 1.3718, "step": 147670 }, { "epoch": 6.74, "learning_rate": 1.6318824660167514e-05, "loss": 1.4308, "step": 147680 }, { "epoch": 6.74, "learning_rate": 1.631653622591423e-05, "loss": 1.3461, "step": 147690 }, { "epoch": 6.74, "learning_rate": 1.6314247791660946e-05, "loss": 1.3566, "step": 147700 }, { "epoch": 6.74, "learning_rate": 1.6311959357407663e-05, "loss": 1.2796, "step": 147710 }, { "epoch": 6.75, "learning_rate": 1.630967092315438e-05, "loss": 1.4883, "step": 147720 }, { "epoch": 6.75, "learning_rate": 1.6307382488901095e-05, "loss": 1.4762, "step": 147730 }, { "epoch": 6.75, "learning_rate": 1.630509405464781e-05, "loss": 1.4024, "step": 147740 }, { "epoch": 6.75, "learning_rate": 1.6302805620394526e-05, "loss": 1.4227, "step": 147750 }, { "epoch": 6.75, "learning_rate": 1.6300517186141244e-05, "loss": 1.5369, "step": 147760 }, { "epoch": 6.75, "learning_rate": 1.6298228751887958e-05, "loss": 1.5205, "step": 147770 }, { "epoch": 6.75, "learning_rate": 1.6295940317634676e-05, "loss": 1.4346, "step": 147780 }, { "epoch": 6.75, "learning_rate": 1.6293651883381393e-05, "loss": 1.4395, "step": 147790 }, { "epoch": 6.75, "learning_rate": 1.6291363449128107e-05, "loss": 1.4624, "step": 147800 }, { "epoch": 6.75, "learning_rate": 1.6289075014874825e-05, "loss": 1.4331, "step": 147810 }, { "epoch": 6.75, "learning_rate": 1.6286786580621542e-05, "loss": 1.5687, "step": 147820 }, { "epoch": 6.75, "learning_rate": 1.6284498146368253e-05, "loss": 1.3598, "step": 147830 }, { "epoch": 6.75, "learning_rate": 1.628220971211497e-05, "loss": 1.4328, "step": 147840 }, { "epoch": 6.75, "learning_rate": 1.6279921277861688e-05, "loss": 1.4837, "step": 147850 }, { "epoch": 6.75, "learning_rate": 1.6277632843608402e-05, "loss": 1.2998, "step": 147860 }, { "epoch": 6.75, "learning_rate": 1.627534440935512e-05, "loss": 1.5298, "step": 147870 }, { "epoch": 6.75, "learning_rate": 1.6273055975101837e-05, "loss": 1.5067, "step": 147880 }, { "epoch": 6.75, "learning_rate": 1.627076754084855e-05, "loss": 1.5873, "step": 147890 }, { "epoch": 6.75, "learning_rate": 1.626847910659527e-05, "loss": 1.5488, "step": 147900 }, { "epoch": 6.75, "learning_rate": 1.6266190672341986e-05, "loss": 1.4633, "step": 147910 }, { "epoch": 6.75, "learning_rate": 1.62639022380887e-05, "loss": 1.4323, "step": 147920 }, { "epoch": 6.75, "learning_rate": 1.6261613803835415e-05, "loss": 1.4763, "step": 147930 }, { "epoch": 6.76, "learning_rate": 1.6259325369582132e-05, "loss": 1.42, "step": 147940 }, { "epoch": 6.76, "learning_rate": 1.625703693532885e-05, "loss": 1.3544, "step": 147950 }, { "epoch": 6.76, "learning_rate": 1.6254748501075564e-05, "loss": 1.3989, "step": 147960 }, { "epoch": 6.76, "learning_rate": 1.625246006682228e-05, "loss": 1.4188, "step": 147970 }, { "epoch": 6.76, "learning_rate": 1.6250171632569e-05, "loss": 1.4875, "step": 147980 }, { "epoch": 6.76, "learning_rate": 1.6247883198315713e-05, "loss": 1.4334, "step": 147990 }, { "epoch": 6.76, "learning_rate": 1.624559476406243e-05, "loss": 1.4252, "step": 148000 }, { "epoch": 6.76, "learning_rate": 1.6243306329809148e-05, "loss": 1.3583, "step": 148010 }, { "epoch": 6.76, "learning_rate": 1.6241017895555862e-05, "loss": 1.3295, "step": 148020 }, { "epoch": 6.76, "learning_rate": 1.6238729461302576e-05, "loss": 1.4988, "step": 148030 }, { "epoch": 6.76, "learning_rate": 1.6236441027049294e-05, "loss": 1.6036, "step": 148040 }, { "epoch": 6.76, "learning_rate": 1.6234152592796008e-05, "loss": 1.4135, "step": 148050 }, { "epoch": 6.76, "learning_rate": 1.6231864158542726e-05, "loss": 1.4312, "step": 148060 }, { "epoch": 6.76, "learning_rate": 1.6229575724289443e-05, "loss": 1.3563, "step": 148070 }, { "epoch": 6.76, "learning_rate": 1.6227287290036157e-05, "loss": 1.4836, "step": 148080 }, { "epoch": 6.76, "learning_rate": 1.6224998855782875e-05, "loss": 1.3992, "step": 148090 }, { "epoch": 6.76, "learning_rate": 1.6222710421529592e-05, "loss": 1.3813, "step": 148100 }, { "epoch": 6.76, "learning_rate": 1.6220421987276306e-05, "loss": 1.4542, "step": 148110 }, { "epoch": 6.76, "learning_rate": 1.621813355302302e-05, "loss": 1.4277, "step": 148120 }, { "epoch": 6.76, "learning_rate": 1.6215845118769738e-05, "loss": 1.4851, "step": 148130 }, { "epoch": 6.76, "learning_rate": 1.6213556684516452e-05, "loss": 1.475, "step": 148140 }, { "epoch": 6.76, "learning_rate": 1.621126825026317e-05, "loss": 1.3787, "step": 148150 }, { "epoch": 6.77, "learning_rate": 1.6208979816009887e-05, "loss": 1.4812, "step": 148160 }, { "epoch": 6.77, "learning_rate": 1.62066913817566e-05, "loss": 1.4972, "step": 148170 }, { "epoch": 6.77, "learning_rate": 1.620440294750332e-05, "loss": 1.3988, "step": 148180 }, { "epoch": 6.77, "learning_rate": 1.6202114513250036e-05, "loss": 1.492, "step": 148190 }, { "epoch": 6.77, "learning_rate": 1.619982607899675e-05, "loss": 1.3203, "step": 148200 }, { "epoch": 6.77, "learning_rate": 1.6197537644743468e-05, "loss": 1.4543, "step": 148210 }, { "epoch": 6.77, "learning_rate": 1.6195249210490182e-05, "loss": 1.6578, "step": 148220 }, { "epoch": 6.77, "learning_rate": 1.61929607762369e-05, "loss": 1.3904, "step": 148230 }, { "epoch": 6.77, "learning_rate": 1.6190672341983614e-05, "loss": 1.3773, "step": 148240 }, { "epoch": 6.77, "learning_rate": 1.618838390773033e-05, "loss": 1.6515, "step": 148250 }, { "epoch": 6.77, "learning_rate": 1.618609547347705e-05, "loss": 1.456, "step": 148260 }, { "epoch": 6.77, "learning_rate": 1.6183807039223763e-05, "loss": 1.2414, "step": 148270 }, { "epoch": 6.77, "learning_rate": 1.618151860497048e-05, "loss": 1.5923, "step": 148280 }, { "epoch": 6.77, "learning_rate": 1.6179230170717198e-05, "loss": 1.4088, "step": 148290 }, { "epoch": 6.77, "learning_rate": 1.6176941736463912e-05, "loss": 1.4009, "step": 148300 }, { "epoch": 6.77, "learning_rate": 1.617465330221063e-05, "loss": 1.332, "step": 148310 }, { "epoch": 6.77, "learning_rate": 1.6172364867957344e-05, "loss": 1.3291, "step": 148320 }, { "epoch": 6.77, "learning_rate": 1.6170076433704058e-05, "loss": 1.5099, "step": 148330 }, { "epoch": 6.77, "learning_rate": 1.6167787999450775e-05, "loss": 1.3941, "step": 148340 }, { "epoch": 6.77, "learning_rate": 1.6165499565197493e-05, "loss": 1.453, "step": 148350 }, { "epoch": 6.77, "learning_rate": 1.6163211130944207e-05, "loss": 1.409, "step": 148360 }, { "epoch": 6.77, "learning_rate": 1.6160922696690925e-05, "loss": 1.4872, "step": 148370 }, { "epoch": 6.78, "learning_rate": 1.6158634262437642e-05, "loss": 1.359, "step": 148380 }, { "epoch": 6.78, "learning_rate": 1.6156345828184356e-05, "loss": 1.3273, "step": 148390 }, { "epoch": 6.78, "learning_rate": 1.6154057393931074e-05, "loss": 1.3447, "step": 148400 }, { "epoch": 6.78, "learning_rate": 1.615176895967779e-05, "loss": 1.2983, "step": 148410 }, { "epoch": 6.78, "learning_rate": 1.6149480525424505e-05, "loss": 1.4523, "step": 148420 }, { "epoch": 6.78, "learning_rate": 1.614719209117122e-05, "loss": 1.3935, "step": 148430 }, { "epoch": 6.78, "learning_rate": 1.6144903656917937e-05, "loss": 1.4139, "step": 148440 }, { "epoch": 6.78, "learning_rate": 1.6142615222664655e-05, "loss": 1.3802, "step": 148450 }, { "epoch": 6.78, "learning_rate": 1.614032678841137e-05, "loss": 1.429, "step": 148460 }, { "epoch": 6.78, "learning_rate": 1.6138038354158086e-05, "loss": 1.365, "step": 148470 }, { "epoch": 6.78, "learning_rate": 1.6135749919904804e-05, "loss": 1.5064, "step": 148480 }, { "epoch": 6.78, "learning_rate": 1.6133461485651518e-05, "loss": 1.3488, "step": 148490 }, { "epoch": 6.78, "learning_rate": 1.6131173051398236e-05, "loss": 1.2627, "step": 148500 }, { "epoch": 6.78, "learning_rate": 1.6128884617144953e-05, "loss": 1.4749, "step": 148510 }, { "epoch": 6.78, "learning_rate": 1.6126596182891664e-05, "loss": 1.357, "step": 148520 }, { "epoch": 6.78, "learning_rate": 1.612430774863838e-05, "loss": 1.4263, "step": 148530 }, { "epoch": 6.78, "learning_rate": 1.61220193143851e-05, "loss": 1.296, "step": 148540 }, { "epoch": 6.78, "learning_rate": 1.6119730880131813e-05, "loss": 1.2197, "step": 148550 }, { "epoch": 6.78, "learning_rate": 1.611744244587853e-05, "loss": 1.3757, "step": 148560 }, { "epoch": 6.78, "learning_rate": 1.6115154011625248e-05, "loss": 1.4012, "step": 148570 }, { "epoch": 6.78, "learning_rate": 1.6112865577371962e-05, "loss": 1.3073, "step": 148580 }, { "epoch": 6.79, "learning_rate": 1.611057714311868e-05, "loss": 1.3612, "step": 148590 }, { "epoch": 6.79, "learning_rate": 1.6108288708865397e-05, "loss": 1.5033, "step": 148600 }, { "epoch": 6.79, "learning_rate": 1.610600027461211e-05, "loss": 1.364, "step": 148610 }, { "epoch": 6.79, "learning_rate": 1.6103711840358825e-05, "loss": 1.3724, "step": 148620 }, { "epoch": 6.79, "learning_rate": 1.6101423406105543e-05, "loss": 1.3751, "step": 148630 }, { "epoch": 6.79, "learning_rate": 1.609913497185226e-05, "loss": 1.2905, "step": 148640 }, { "epoch": 6.79, "learning_rate": 1.6096846537598975e-05, "loss": 1.4427, "step": 148650 }, { "epoch": 6.79, "learning_rate": 1.6094558103345692e-05, "loss": 1.562, "step": 148660 }, { "epoch": 6.79, "learning_rate": 1.609226966909241e-05, "loss": 1.3686, "step": 148670 }, { "epoch": 6.79, "learning_rate": 1.6089981234839124e-05, "loss": 1.436, "step": 148680 }, { "epoch": 6.79, "learning_rate": 1.608769280058584e-05, "loss": 1.3804, "step": 148690 }, { "epoch": 6.79, "learning_rate": 1.6085404366332555e-05, "loss": 1.3382, "step": 148700 }, { "epoch": 6.79, "learning_rate": 1.6083115932079273e-05, "loss": 1.4179, "step": 148710 }, { "epoch": 6.79, "learning_rate": 1.6080827497825987e-05, "loss": 1.4388, "step": 148720 }, { "epoch": 6.79, "learning_rate": 1.6078539063572705e-05, "loss": 1.4911, "step": 148730 }, { "epoch": 6.79, "learning_rate": 1.607625062931942e-05, "loss": 1.2621, "step": 148740 }, { "epoch": 6.79, "learning_rate": 1.6073962195066136e-05, "loss": 1.276, "step": 148750 }, { "epoch": 6.79, "learning_rate": 1.6071673760812854e-05, "loss": 1.4393, "step": 148760 }, { "epoch": 6.79, "learning_rate": 1.6069385326559568e-05, "loss": 1.4778, "step": 148770 }, { "epoch": 6.79, "learning_rate": 1.6067096892306285e-05, "loss": 1.4794, "step": 148780 }, { "epoch": 6.79, "learning_rate": 1.6064808458053003e-05, "loss": 1.4487, "step": 148790 }, { "epoch": 6.79, "learning_rate": 1.6062520023799717e-05, "loss": 1.4064, "step": 148800 }, { "epoch": 6.8, "learning_rate": 1.6060231589546435e-05, "loss": 1.5444, "step": 148810 }, { "epoch": 6.8, "learning_rate": 1.605794315529315e-05, "loss": 1.5078, "step": 148820 }, { "epoch": 6.8, "learning_rate": 1.6055654721039863e-05, "loss": 1.2394, "step": 148830 }, { "epoch": 6.8, "learning_rate": 1.605336628678658e-05, "loss": 1.6643, "step": 148840 }, { "epoch": 6.8, "learning_rate": 1.6051077852533298e-05, "loss": 1.4244, "step": 148850 }, { "epoch": 6.8, "learning_rate": 1.6048789418280012e-05, "loss": 1.2155, "step": 148860 }, { "epoch": 6.8, "learning_rate": 1.604650098402673e-05, "loss": 1.3799, "step": 148870 }, { "epoch": 6.8, "learning_rate": 1.6044212549773447e-05, "loss": 1.4629, "step": 148880 }, { "epoch": 6.8, "learning_rate": 1.604192411552016e-05, "loss": 1.2572, "step": 148890 }, { "epoch": 6.8, "learning_rate": 1.603963568126688e-05, "loss": 1.4143, "step": 148900 }, { "epoch": 6.8, "learning_rate": 1.6037347247013593e-05, "loss": 1.5106, "step": 148910 }, { "epoch": 6.8, "learning_rate": 1.603505881276031e-05, "loss": 1.3782, "step": 148920 }, { "epoch": 6.8, "learning_rate": 1.6032770378507025e-05, "loss": 1.4877, "step": 148930 }, { "epoch": 6.8, "learning_rate": 1.6030481944253742e-05, "loss": 1.602, "step": 148940 }, { "epoch": 6.8, "learning_rate": 1.602819351000046e-05, "loss": 1.4903, "step": 148950 }, { "epoch": 6.8, "learning_rate": 1.6025905075747174e-05, "loss": 1.5975, "step": 148960 }, { "epoch": 6.8, "learning_rate": 1.602361664149389e-05, "loss": 1.4214, "step": 148970 }, { "epoch": 6.8, "learning_rate": 1.602132820724061e-05, "loss": 1.3798, "step": 148980 }, { "epoch": 6.8, "learning_rate": 1.6019039772987323e-05, "loss": 1.4357, "step": 148990 }, { "epoch": 6.8, "learning_rate": 1.601675133873404e-05, "loss": 1.433, "step": 149000 }, { "epoch": 6.8, "learning_rate": 1.6014462904480755e-05, "loss": 1.315, "step": 149010 }, { "epoch": 6.8, "learning_rate": 1.601217447022747e-05, "loss": 1.4887, "step": 149020 }, { "epoch": 6.81, "learning_rate": 1.6009886035974186e-05, "loss": 1.4954, "step": 149030 }, { "epoch": 6.81, "learning_rate": 1.6007597601720904e-05, "loss": 1.3708, "step": 149040 }, { "epoch": 6.81, "learning_rate": 1.6005309167467618e-05, "loss": 1.5686, "step": 149050 }, { "epoch": 6.81, "learning_rate": 1.6003020733214335e-05, "loss": 1.4313, "step": 149060 }, { "epoch": 6.81, "learning_rate": 1.6000732298961053e-05, "loss": 1.3729, "step": 149070 }, { "epoch": 6.81, "learning_rate": 1.5998443864707767e-05, "loss": 1.3711, "step": 149080 }, { "epoch": 6.81, "learning_rate": 1.5996155430454485e-05, "loss": 1.3696, "step": 149090 }, { "epoch": 6.81, "learning_rate": 1.5993866996201202e-05, "loss": 1.3896, "step": 149100 }, { "epoch": 6.81, "learning_rate": 1.5991578561947916e-05, "loss": 1.527, "step": 149110 }, { "epoch": 6.81, "learning_rate": 1.598929012769463e-05, "loss": 1.2946, "step": 149120 }, { "epoch": 6.81, "learning_rate": 1.5987001693441348e-05, "loss": 1.2781, "step": 149130 }, { "epoch": 6.81, "learning_rate": 1.5984713259188065e-05, "loss": 1.3786, "step": 149140 }, { "epoch": 6.81, "learning_rate": 1.598242482493478e-05, "loss": 1.3908, "step": 149150 }, { "epoch": 6.81, "learning_rate": 1.5980136390681497e-05, "loss": 1.3782, "step": 149160 }, { "epoch": 6.81, "learning_rate": 1.5977847956428215e-05, "loss": 1.3391, "step": 149170 }, { "epoch": 6.81, "learning_rate": 1.597555952217493e-05, "loss": 1.5205, "step": 149180 }, { "epoch": 6.81, "learning_rate": 1.5973271087921646e-05, "loss": 1.4134, "step": 149190 }, { "epoch": 6.81, "learning_rate": 1.5970982653668364e-05, "loss": 1.419, "step": 149200 }, { "epoch": 6.81, "learning_rate": 1.5968694219415075e-05, "loss": 1.4138, "step": 149210 }, { "epoch": 6.81, "learning_rate": 1.5966405785161792e-05, "loss": 1.4908, "step": 149220 }, { "epoch": 6.81, "learning_rate": 1.596411735090851e-05, "loss": 1.3886, "step": 149230 }, { "epoch": 6.81, "learning_rate": 1.5961828916655224e-05, "loss": 1.5157, "step": 149240 }, { "epoch": 6.82, "learning_rate": 1.595954048240194e-05, "loss": 1.5616, "step": 149250 }, { "epoch": 6.82, "learning_rate": 1.595725204814866e-05, "loss": 1.3974, "step": 149260 }, { "epoch": 6.82, "learning_rate": 1.5954963613895373e-05, "loss": 1.4137, "step": 149270 }, { "epoch": 6.82, "learning_rate": 1.595267517964209e-05, "loss": 1.4237, "step": 149280 }, { "epoch": 6.82, "learning_rate": 1.5950386745388808e-05, "loss": 1.3199, "step": 149290 }, { "epoch": 6.82, "learning_rate": 1.5948098311135522e-05, "loss": 1.4508, "step": 149300 }, { "epoch": 6.82, "learning_rate": 1.5945809876882236e-05, "loss": 1.3961, "step": 149310 }, { "epoch": 6.82, "learning_rate": 1.5943521442628954e-05, "loss": 1.3714, "step": 149320 }, { "epoch": 6.82, "learning_rate": 1.5941233008375668e-05, "loss": 1.3745, "step": 149330 }, { "epoch": 6.82, "learning_rate": 1.5938944574122385e-05, "loss": 1.3396, "step": 149340 }, { "epoch": 6.82, "learning_rate": 1.5936656139869103e-05, "loss": 1.5065, "step": 149350 }, { "epoch": 6.82, "learning_rate": 1.5934367705615817e-05, "loss": 1.3612, "step": 149360 }, { "epoch": 6.82, "learning_rate": 1.5932079271362535e-05, "loss": 1.2985, "step": 149370 }, { "epoch": 6.82, "learning_rate": 1.5929790837109252e-05, "loss": 1.5536, "step": 149380 }, { "epoch": 6.82, "learning_rate": 1.5927502402855966e-05, "loss": 1.391, "step": 149390 }, { "epoch": 6.82, "learning_rate": 1.5925213968602684e-05, "loss": 1.6597, "step": 149400 }, { "epoch": 6.82, "learning_rate": 1.5922925534349398e-05, "loss": 1.3338, "step": 149410 }, { "epoch": 6.82, "learning_rate": 1.5920637100096115e-05, "loss": 1.4136, "step": 149420 }, { "epoch": 6.82, "learning_rate": 1.591834866584283e-05, "loss": 1.5334, "step": 149430 }, { "epoch": 6.82, "learning_rate": 1.5916060231589547e-05, "loss": 1.3612, "step": 149440 }, { "epoch": 6.82, "learning_rate": 1.5913771797336265e-05, "loss": 1.3445, "step": 149450 }, { "epoch": 6.82, "learning_rate": 1.591148336308298e-05, "loss": 1.3349, "step": 149460 }, { "epoch": 6.83, "learning_rate": 1.5909194928829696e-05, "loss": 1.588, "step": 149470 }, { "epoch": 6.83, "learning_rate": 1.5906906494576414e-05, "loss": 1.4276, "step": 149480 }, { "epoch": 6.83, "learning_rate": 1.5904618060323128e-05, "loss": 1.4464, "step": 149490 }, { "epoch": 6.83, "learning_rate": 1.5902329626069845e-05, "loss": 1.4446, "step": 149500 }, { "epoch": 6.83, "learning_rate": 1.590004119181656e-05, "loss": 1.4565, "step": 149510 }, { "epoch": 6.83, "learning_rate": 1.5897752757563274e-05, "loss": 1.2886, "step": 149520 }, { "epoch": 6.83, "learning_rate": 1.589546432330999e-05, "loss": 1.4906, "step": 149530 }, { "epoch": 6.83, "learning_rate": 1.589317588905671e-05, "loss": 1.4237, "step": 149540 }, { "epoch": 6.83, "learning_rate": 1.5890887454803423e-05, "loss": 1.3981, "step": 149550 }, { "epoch": 6.83, "learning_rate": 1.588859902055014e-05, "loss": 1.5453, "step": 149560 }, { "epoch": 6.83, "learning_rate": 1.5886310586296858e-05, "loss": 1.645, "step": 149570 }, { "epoch": 6.83, "learning_rate": 1.5884022152043572e-05, "loss": 1.4146, "step": 149580 }, { "epoch": 6.83, "learning_rate": 1.588173371779029e-05, "loss": 1.3427, "step": 149590 }, { "epoch": 6.83, "learning_rate": 1.5879445283537007e-05, "loss": 1.43, "step": 149600 }, { "epoch": 6.83, "learning_rate": 1.587715684928372e-05, "loss": 1.3926, "step": 149610 }, { "epoch": 6.83, "learning_rate": 1.5874868415030435e-05, "loss": 1.5122, "step": 149620 }, { "epoch": 6.83, "learning_rate": 1.5872579980777153e-05, "loss": 1.4298, "step": 149630 }, { "epoch": 6.83, "learning_rate": 1.587029154652387e-05, "loss": 1.3625, "step": 149640 }, { "epoch": 6.83, "learning_rate": 1.5868003112270584e-05, "loss": 1.4743, "step": 149650 }, { "epoch": 6.83, "learning_rate": 1.5865714678017302e-05, "loss": 1.425, "step": 149660 }, { "epoch": 6.83, "learning_rate": 1.586342624376402e-05, "loss": 1.5008, "step": 149670 }, { "epoch": 6.83, "learning_rate": 1.5861137809510734e-05, "loss": 1.6099, "step": 149680 }, { "epoch": 6.84, "learning_rate": 1.585884937525745e-05, "loss": 1.4887, "step": 149690 }, { "epoch": 6.84, "learning_rate": 1.5856560941004165e-05, "loss": 1.4508, "step": 149700 }, { "epoch": 6.84, "learning_rate": 1.585427250675088e-05, "loss": 1.3786, "step": 149710 }, { "epoch": 6.84, "learning_rate": 1.5851984072497597e-05, "loss": 1.4111, "step": 149720 }, { "epoch": 6.84, "learning_rate": 1.5849695638244314e-05, "loss": 1.3171, "step": 149730 }, { "epoch": 6.84, "learning_rate": 1.584740720399103e-05, "loss": 1.5596, "step": 149740 }, { "epoch": 6.84, "learning_rate": 1.5845118769737746e-05, "loss": 1.2169, "step": 149750 }, { "epoch": 6.84, "learning_rate": 1.5842830335484464e-05, "loss": 1.5051, "step": 149760 }, { "epoch": 6.84, "learning_rate": 1.5840541901231178e-05, "loss": 1.4186, "step": 149770 }, { "epoch": 6.84, "learning_rate": 1.5838253466977895e-05, "loss": 1.2955, "step": 149780 }, { "epoch": 6.84, "learning_rate": 1.5835965032724613e-05, "loss": 1.5846, "step": 149790 }, { "epoch": 6.84, "learning_rate": 1.5833676598471327e-05, "loss": 1.337, "step": 149800 }, { "epoch": 6.84, "learning_rate": 1.583138816421804e-05, "loss": 1.3422, "step": 149810 }, { "epoch": 6.84, "learning_rate": 1.582909972996476e-05, "loss": 1.451, "step": 149820 }, { "epoch": 6.84, "learning_rate": 1.5826811295711476e-05, "loss": 1.4304, "step": 149830 }, { "epoch": 6.84, "learning_rate": 1.582452286145819e-05, "loss": 1.294, "step": 149840 }, { "epoch": 6.84, "learning_rate": 1.5822234427204908e-05, "loss": 1.4189, "step": 149850 }, { "epoch": 6.84, "learning_rate": 1.5819945992951622e-05, "loss": 1.4216, "step": 149860 }, { "epoch": 6.84, "learning_rate": 1.581765755869834e-05, "loss": 1.2799, "step": 149870 }, { "epoch": 6.84, "learning_rate": 1.5815369124445057e-05, "loss": 1.259, "step": 149880 }, { "epoch": 6.84, "learning_rate": 1.581308069019177e-05, "loss": 1.4951, "step": 149890 }, { "epoch": 6.84, "learning_rate": 1.5810792255938485e-05, "loss": 1.3409, "step": 149900 }, { "epoch": 6.85, "learning_rate": 1.5808503821685203e-05, "loss": 1.4675, "step": 149910 }, { "epoch": 6.85, "learning_rate": 1.580621538743192e-05, "loss": 1.3189, "step": 149920 }, { "epoch": 6.85, "learning_rate": 1.5803926953178634e-05, "loss": 1.4667, "step": 149930 }, { "epoch": 6.85, "learning_rate": 1.5801638518925352e-05, "loss": 1.4331, "step": 149940 }, { "epoch": 6.85, "learning_rate": 1.579935008467207e-05, "loss": 1.4924, "step": 149950 }, { "epoch": 6.85, "learning_rate": 1.5797061650418784e-05, "loss": 1.4478, "step": 149960 }, { "epoch": 6.85, "learning_rate": 1.57947732161655e-05, "loss": 1.3862, "step": 149970 }, { "epoch": 6.85, "learning_rate": 1.579248478191222e-05, "loss": 1.521, "step": 149980 }, { "epoch": 6.85, "learning_rate": 1.5790196347658933e-05, "loss": 1.3964, "step": 149990 }, { "epoch": 6.85, "learning_rate": 1.5787907913405647e-05, "loss": 1.4171, "step": 150000 }, { "epoch": 6.85, "learning_rate": 1.5785619479152364e-05, "loss": 1.4318, "step": 150010 }, { "epoch": 6.85, "learning_rate": 1.578333104489908e-05, "loss": 1.4917, "step": 150020 }, { "epoch": 6.85, "learning_rate": 1.5781042610645796e-05, "loss": 1.4092, "step": 150030 }, { "epoch": 6.85, "learning_rate": 1.5778754176392514e-05, "loss": 1.4982, "step": 150040 }, { "epoch": 6.85, "learning_rate": 1.5776465742139228e-05, "loss": 1.3518, "step": 150050 }, { "epoch": 6.85, "learning_rate": 1.5774177307885945e-05, "loss": 1.4116, "step": 150060 }, { "epoch": 6.85, "learning_rate": 1.5771888873632663e-05, "loss": 1.4198, "step": 150070 }, { "epoch": 6.85, "learning_rate": 1.5769600439379377e-05, "loss": 1.3218, "step": 150080 }, { "epoch": 6.85, "learning_rate": 1.5767312005126094e-05, "loss": 1.4102, "step": 150090 }, { "epoch": 6.85, "learning_rate": 1.576502357087281e-05, "loss": 1.2825, "step": 150100 }, { "epoch": 6.85, "learning_rate": 1.5762735136619526e-05, "loss": 1.4032, "step": 150110 }, { "epoch": 6.85, "learning_rate": 1.576044670236624e-05, "loss": 1.4555, "step": 150120 }, { "epoch": 6.86, "learning_rate": 1.5758158268112958e-05, "loss": 1.2561, "step": 150130 }, { "epoch": 6.86, "learning_rate": 1.5755869833859675e-05, "loss": 1.6262, "step": 150140 }, { "epoch": 6.86, "learning_rate": 1.575358139960639e-05, "loss": 1.3387, "step": 150150 }, { "epoch": 6.86, "learning_rate": 1.5751292965353107e-05, "loss": 1.3732, "step": 150160 }, { "epoch": 6.86, "learning_rate": 1.5749004531099824e-05, "loss": 1.511, "step": 150170 }, { "epoch": 6.86, "learning_rate": 1.574671609684654e-05, "loss": 1.3923, "step": 150180 }, { "epoch": 6.86, "learning_rate": 1.5744427662593256e-05, "loss": 1.5063, "step": 150190 }, { "epoch": 6.86, "learning_rate": 1.574213922833997e-05, "loss": 1.3815, "step": 150200 }, { "epoch": 6.86, "learning_rate": 1.5739850794086684e-05, "loss": 1.3231, "step": 150210 }, { "epoch": 6.86, "learning_rate": 1.5737562359833402e-05, "loss": 1.5063, "step": 150220 }, { "epoch": 6.86, "learning_rate": 1.573527392558012e-05, "loss": 1.5256, "step": 150230 }, { "epoch": 6.86, "learning_rate": 1.5732985491326834e-05, "loss": 1.4269, "step": 150240 }, { "epoch": 6.86, "learning_rate": 1.573069705707355e-05, "loss": 1.4391, "step": 150250 }, { "epoch": 6.86, "learning_rate": 1.572840862282027e-05, "loss": 1.3518, "step": 150260 }, { "epoch": 6.86, "learning_rate": 1.5726120188566983e-05, "loss": 1.3239, "step": 150270 }, { "epoch": 6.86, "learning_rate": 1.57238317543137e-05, "loss": 1.5672, "step": 150280 }, { "epoch": 6.86, "learning_rate": 1.5721543320060418e-05, "loss": 1.3765, "step": 150290 }, { "epoch": 6.86, "learning_rate": 1.5719254885807132e-05, "loss": 1.4448, "step": 150300 }, { "epoch": 6.86, "learning_rate": 1.5716966451553846e-05, "loss": 1.4188, "step": 150310 }, { "epoch": 6.86, "learning_rate": 1.5714678017300564e-05, "loss": 1.4009, "step": 150320 }, { "epoch": 6.86, "learning_rate": 1.571238958304728e-05, "loss": 1.3711, "step": 150330 }, { "epoch": 6.86, "learning_rate": 1.5710101148793995e-05, "loss": 1.4207, "step": 150340 }, { "epoch": 6.87, "learning_rate": 1.5707812714540713e-05, "loss": 1.4951, "step": 150350 }, { "epoch": 6.87, "learning_rate": 1.570552428028743e-05, "loss": 1.4229, "step": 150360 }, { "epoch": 6.87, "learning_rate": 1.5703235846034144e-05, "loss": 1.2815, "step": 150370 }, { "epoch": 6.87, "learning_rate": 1.5700947411780862e-05, "loss": 1.5541, "step": 150380 }, { "epoch": 6.87, "learning_rate": 1.569865897752758e-05, "loss": 1.3461, "step": 150390 }, { "epoch": 6.87, "learning_rate": 1.569637054327429e-05, "loss": 1.3943, "step": 150400 }, { "epoch": 6.87, "learning_rate": 1.5694082109021008e-05, "loss": 1.4072, "step": 150410 }, { "epoch": 6.87, "learning_rate": 1.5691793674767725e-05, "loss": 1.588, "step": 150420 }, { "epoch": 6.87, "learning_rate": 1.568950524051444e-05, "loss": 1.4516, "step": 150430 }, { "epoch": 6.87, "learning_rate": 1.5687216806261157e-05, "loss": 1.3255, "step": 150440 }, { "epoch": 6.87, "learning_rate": 1.5684928372007874e-05, "loss": 1.4231, "step": 150450 }, { "epoch": 6.87, "learning_rate": 1.568263993775459e-05, "loss": 1.2475, "step": 150460 }, { "epoch": 6.87, "learning_rate": 1.5680351503501306e-05, "loss": 1.505, "step": 150470 }, { "epoch": 6.87, "learning_rate": 1.5678063069248024e-05, "loss": 1.5422, "step": 150480 }, { "epoch": 6.87, "learning_rate": 1.5675774634994734e-05, "loss": 1.4789, "step": 150490 }, { "epoch": 6.87, "learning_rate": 1.5673486200741452e-05, "loss": 1.5106, "step": 150500 }, { "epoch": 6.87, "learning_rate": 1.567119776648817e-05, "loss": 1.3804, "step": 150510 }, { "epoch": 6.87, "learning_rate": 1.5668909332234884e-05, "loss": 1.3733, "step": 150520 }, { "epoch": 6.87, "learning_rate": 1.56666208979816e-05, "loss": 1.2537, "step": 150530 }, { "epoch": 6.87, "learning_rate": 1.566433246372832e-05, "loss": 1.3318, "step": 150540 }, { "epoch": 6.87, "learning_rate": 1.5662044029475033e-05, "loss": 1.3066, "step": 150550 }, { "epoch": 6.87, "learning_rate": 1.565975559522175e-05, "loss": 1.4367, "step": 150560 }, { "epoch": 6.88, "learning_rate": 1.5657467160968468e-05, "loss": 1.5372, "step": 150570 }, { "epoch": 6.88, "learning_rate": 1.5655178726715182e-05, "loss": 1.3994, "step": 150580 }, { "epoch": 6.88, "learning_rate": 1.5652890292461896e-05, "loss": 1.5335, "step": 150590 }, { "epoch": 6.88, "learning_rate": 1.5650601858208614e-05, "loss": 1.5466, "step": 150600 }, { "epoch": 6.88, "learning_rate": 1.564831342395533e-05, "loss": 1.4349, "step": 150610 }, { "epoch": 6.88, "learning_rate": 1.5646024989702045e-05, "loss": 1.228, "step": 150620 }, { "epoch": 6.88, "learning_rate": 1.5643736555448763e-05, "loss": 1.323, "step": 150630 }, { "epoch": 6.88, "learning_rate": 1.564144812119548e-05, "loss": 1.6026, "step": 150640 }, { "epoch": 6.88, "learning_rate": 1.5639159686942194e-05, "loss": 1.3574, "step": 150650 }, { "epoch": 6.88, "learning_rate": 1.5636871252688912e-05, "loss": 1.3685, "step": 150660 }, { "epoch": 6.88, "learning_rate": 1.563458281843563e-05, "loss": 1.4136, "step": 150670 }, { "epoch": 6.88, "learning_rate": 1.5632294384182344e-05, "loss": 1.4528, "step": 150680 }, { "epoch": 6.88, "learning_rate": 1.5630005949929058e-05, "loss": 1.4753, "step": 150690 }, { "epoch": 6.88, "learning_rate": 1.5627717515675775e-05, "loss": 1.2724, "step": 150700 }, { "epoch": 6.88, "learning_rate": 1.562542908142249e-05, "loss": 1.5006, "step": 150710 }, { "epoch": 6.88, "learning_rate": 1.5623140647169207e-05, "loss": 1.3605, "step": 150720 }, { "epoch": 6.88, "learning_rate": 1.5620852212915924e-05, "loss": 1.3738, "step": 150730 }, { "epoch": 6.88, "learning_rate": 1.561856377866264e-05, "loss": 1.7197, "step": 150740 }, { "epoch": 6.88, "learning_rate": 1.5616275344409356e-05, "loss": 1.3478, "step": 150750 }, { "epoch": 6.88, "learning_rate": 1.5613986910156074e-05, "loss": 1.3839, "step": 150760 }, { "epoch": 6.88, "learning_rate": 1.5611698475902788e-05, "loss": 1.4817, "step": 150770 }, { "epoch": 6.89, "learning_rate": 1.5609410041649505e-05, "loss": 1.3999, "step": 150780 }, { "epoch": 6.89, "learning_rate": 1.560712160739622e-05, "loss": 1.3488, "step": 150790 }, { "epoch": 6.89, "learning_rate": 1.5604833173142937e-05, "loss": 1.4471, "step": 150800 }, { "epoch": 6.89, "learning_rate": 1.560254473888965e-05, "loss": 1.2575, "step": 150810 }, { "epoch": 6.89, "learning_rate": 1.560025630463637e-05, "loss": 1.4996, "step": 150820 }, { "epoch": 6.89, "learning_rate": 1.5597967870383086e-05, "loss": 1.4283, "step": 150830 }, { "epoch": 6.89, "learning_rate": 1.55956794361298e-05, "loss": 1.3275, "step": 150840 }, { "epoch": 6.89, "learning_rate": 1.5593391001876518e-05, "loss": 1.3877, "step": 150850 }, { "epoch": 6.89, "learning_rate": 1.5591102567623235e-05, "loss": 1.4977, "step": 150860 }, { "epoch": 6.89, "learning_rate": 1.558881413336995e-05, "loss": 1.2429, "step": 150870 }, { "epoch": 6.89, "learning_rate": 1.5586525699116667e-05, "loss": 1.4923, "step": 150880 }, { "epoch": 6.89, "learning_rate": 1.558423726486338e-05, "loss": 1.2197, "step": 150890 }, { "epoch": 6.89, "learning_rate": 1.5581948830610095e-05, "loss": 1.4681, "step": 150900 }, { "epoch": 6.89, "learning_rate": 1.5579660396356813e-05, "loss": 1.5364, "step": 150910 }, { "epoch": 6.89, "learning_rate": 1.557737196210353e-05, "loss": 1.3305, "step": 150920 }, { "epoch": 6.89, "learning_rate": 1.5575083527850244e-05, "loss": 1.4656, "step": 150930 }, { "epoch": 6.89, "learning_rate": 1.5572795093596962e-05, "loss": 1.3353, "step": 150940 }, { "epoch": 6.89, "learning_rate": 1.557050665934368e-05, "loss": 1.3131, "step": 150950 }, { "epoch": 6.89, "learning_rate": 1.5568218225090393e-05, "loss": 1.4288, "step": 150960 }, { "epoch": 6.89, "learning_rate": 1.556592979083711e-05, "loss": 1.3401, "step": 150970 }, { "epoch": 6.89, "learning_rate": 1.556364135658383e-05, "loss": 1.3618, "step": 150980 }, { "epoch": 6.89, "learning_rate": 1.5561352922330543e-05, "loss": 1.2992, "step": 150990 }, { "epoch": 6.9, "learning_rate": 1.5559064488077257e-05, "loss": 1.5106, "step": 151000 }, { "epoch": 6.9, "learning_rate": 1.5556776053823974e-05, "loss": 1.2847, "step": 151010 }, { "epoch": 6.9, "learning_rate": 1.555448761957069e-05, "loss": 1.3896, "step": 151020 }, { "epoch": 6.9, "learning_rate": 1.5552199185317406e-05, "loss": 1.358, "step": 151030 }, { "epoch": 6.9, "learning_rate": 1.5549910751064123e-05, "loss": 1.2941, "step": 151040 }, { "epoch": 6.9, "learning_rate": 1.5547622316810838e-05, "loss": 1.4448, "step": 151050 }, { "epoch": 6.9, "learning_rate": 1.5545333882557555e-05, "loss": 1.2127, "step": 151060 }, { "epoch": 6.9, "learning_rate": 1.5543045448304273e-05, "loss": 1.4681, "step": 151070 }, { "epoch": 6.9, "learning_rate": 1.5540757014050987e-05, "loss": 1.39, "step": 151080 }, { "epoch": 6.9, "learning_rate": 1.55384685797977e-05, "loss": 1.4224, "step": 151090 }, { "epoch": 6.9, "learning_rate": 1.553618014554442e-05, "loss": 1.4019, "step": 151100 }, { "epoch": 6.9, "learning_rate": 1.5533891711291136e-05, "loss": 1.4974, "step": 151110 }, { "epoch": 6.9, "learning_rate": 1.553160327703785e-05, "loss": 1.3558, "step": 151120 }, { "epoch": 6.9, "learning_rate": 1.5529314842784568e-05, "loss": 1.337, "step": 151130 }, { "epoch": 6.9, "learning_rate": 1.5527026408531285e-05, "loss": 1.4056, "step": 151140 }, { "epoch": 6.9, "learning_rate": 1.5524737974278e-05, "loss": 1.342, "step": 151150 }, { "epoch": 6.9, "learning_rate": 1.5522449540024717e-05, "loss": 1.5395, "step": 151160 }, { "epoch": 6.9, "learning_rate": 1.5520161105771434e-05, "loss": 1.3925, "step": 151170 }, { "epoch": 6.9, "learning_rate": 1.551787267151815e-05, "loss": 1.5258, "step": 151180 }, { "epoch": 6.9, "learning_rate": 1.5515584237264863e-05, "loss": 1.271, "step": 151190 }, { "epoch": 6.9, "learning_rate": 1.551329580301158e-05, "loss": 1.3905, "step": 151200 }, { "epoch": 6.9, "learning_rate": 1.5511007368758294e-05, "loss": 1.451, "step": 151210 }, { "epoch": 6.91, "learning_rate": 1.5508718934505012e-05, "loss": 1.6875, "step": 151220 }, { "epoch": 6.91, "learning_rate": 1.550643050025173e-05, "loss": 1.4763, "step": 151230 }, { "epoch": 6.91, "learning_rate": 1.5504142065998443e-05, "loss": 1.3349, "step": 151240 }, { "epoch": 6.91, "learning_rate": 1.550185363174516e-05, "loss": 1.3826, "step": 151250 }, { "epoch": 6.91, "learning_rate": 1.549956519749188e-05, "loss": 1.2385, "step": 151260 }, { "epoch": 6.91, "learning_rate": 1.5497276763238593e-05, "loss": 1.4486, "step": 151270 }, { "epoch": 6.91, "learning_rate": 1.5494988328985307e-05, "loss": 1.6158, "step": 151280 }, { "epoch": 6.91, "learning_rate": 1.5492699894732024e-05, "loss": 1.5236, "step": 151290 }, { "epoch": 6.91, "learning_rate": 1.5490411460478742e-05, "loss": 1.452, "step": 151300 }, { "epoch": 6.91, "learning_rate": 1.5488123026225456e-05, "loss": 1.4363, "step": 151310 }, { "epoch": 6.91, "learning_rate": 1.5485834591972173e-05, "loss": 1.4698, "step": 151320 }, { "epoch": 6.91, "learning_rate": 1.548354615771889e-05, "loss": 1.446, "step": 151330 }, { "epoch": 6.91, "learning_rate": 1.5481257723465605e-05, "loss": 1.4396, "step": 151340 }, { "epoch": 6.91, "learning_rate": 1.5478969289212323e-05, "loss": 1.2714, "step": 151350 }, { "epoch": 6.91, "learning_rate": 1.547668085495904e-05, "loss": 1.4255, "step": 151360 }, { "epoch": 6.91, "learning_rate": 1.5474392420705754e-05, "loss": 1.4165, "step": 151370 }, { "epoch": 6.91, "learning_rate": 1.547210398645247e-05, "loss": 1.6696, "step": 151380 }, { "epoch": 6.91, "learning_rate": 1.5469815552199186e-05, "loss": 1.3837, "step": 151390 }, { "epoch": 6.91, "learning_rate": 1.54675271179459e-05, "loss": 1.4597, "step": 151400 }, { "epoch": 6.91, "learning_rate": 1.5465238683692618e-05, "loss": 1.4161, "step": 151410 }, { "epoch": 6.91, "learning_rate": 1.5462950249439335e-05, "loss": 1.3732, "step": 151420 }, { "epoch": 6.91, "learning_rate": 1.546066181518605e-05, "loss": 1.2757, "step": 151430 }, { "epoch": 6.92, "learning_rate": 1.5458373380932767e-05, "loss": 1.3111, "step": 151440 }, { "epoch": 6.92, "learning_rate": 1.5456084946679484e-05, "loss": 1.3527, "step": 151450 }, { "epoch": 6.92, "learning_rate": 1.54537965124262e-05, "loss": 1.6799, "step": 151460 }, { "epoch": 6.92, "learning_rate": 1.5451508078172916e-05, "loss": 1.3841, "step": 151470 }, { "epoch": 6.92, "learning_rate": 1.544921964391963e-05, "loss": 1.4911, "step": 151480 }, { "epoch": 6.92, "learning_rate": 1.5446931209666348e-05, "loss": 1.5205, "step": 151490 }, { "epoch": 6.92, "learning_rate": 1.5444642775413062e-05, "loss": 1.2932, "step": 151500 }, { "epoch": 6.92, "learning_rate": 1.544235434115978e-05, "loss": 1.3818, "step": 151510 }, { "epoch": 6.92, "learning_rate": 1.5440065906906497e-05, "loss": 1.494, "step": 151520 }, { "epoch": 6.92, "learning_rate": 1.543777747265321e-05, "loss": 1.4106, "step": 151530 }, { "epoch": 6.92, "learning_rate": 1.543548903839993e-05, "loss": 1.457, "step": 151540 }, { "epoch": 6.92, "learning_rate": 1.5433200604146646e-05, "loss": 1.4236, "step": 151550 }, { "epoch": 6.92, "learning_rate": 1.543091216989336e-05, "loss": 1.3614, "step": 151560 }, { "epoch": 6.92, "learning_rate": 1.5428623735640078e-05, "loss": 1.324, "step": 151570 }, { "epoch": 6.92, "learning_rate": 1.5426335301386792e-05, "loss": 1.4553, "step": 151580 }, { "epoch": 6.92, "learning_rate": 1.5424046867133506e-05, "loss": 1.3798, "step": 151590 }, { "epoch": 6.92, "learning_rate": 1.5421758432880223e-05, "loss": 1.4498, "step": 151600 }, { "epoch": 6.92, "learning_rate": 1.541946999862694e-05, "loss": 1.4662, "step": 151610 }, { "epoch": 6.92, "learning_rate": 1.5417181564373655e-05, "loss": 1.3375, "step": 151620 }, { "epoch": 6.92, "learning_rate": 1.5414893130120373e-05, "loss": 1.3881, "step": 151630 }, { "epoch": 6.92, "learning_rate": 1.541260469586709e-05, "loss": 1.4538, "step": 151640 }, { "epoch": 6.92, "learning_rate": 1.5410316261613804e-05, "loss": 1.4717, "step": 151650 }, { "epoch": 6.93, "learning_rate": 1.5408027827360522e-05, "loss": 1.4487, "step": 151660 }, { "epoch": 6.93, "learning_rate": 1.540573939310724e-05, "loss": 1.4474, "step": 151670 }, { "epoch": 6.93, "learning_rate": 1.540345095885395e-05, "loss": 1.3676, "step": 151680 }, { "epoch": 6.93, "learning_rate": 1.5401162524600668e-05, "loss": 1.4508, "step": 151690 }, { "epoch": 6.93, "learning_rate": 1.5398874090347385e-05, "loss": 1.4538, "step": 151700 }, { "epoch": 6.93, "learning_rate": 1.53965856560941e-05, "loss": 1.366, "step": 151710 }, { "epoch": 6.93, "learning_rate": 1.5394297221840817e-05, "loss": 1.5096, "step": 151720 }, { "epoch": 6.93, "learning_rate": 1.5392008787587534e-05, "loss": 1.4638, "step": 151730 }, { "epoch": 6.93, "learning_rate": 1.538972035333425e-05, "loss": 1.2762, "step": 151740 }, { "epoch": 6.93, "learning_rate": 1.5387431919080966e-05, "loss": 1.5618, "step": 151750 }, { "epoch": 6.93, "learning_rate": 1.5385143484827683e-05, "loss": 1.5608, "step": 151760 }, { "epoch": 6.93, "learning_rate": 1.5382855050574398e-05, "loss": 1.3472, "step": 151770 }, { "epoch": 6.93, "learning_rate": 1.538056661632111e-05, "loss": 1.2627, "step": 151780 }, { "epoch": 6.93, "learning_rate": 1.537827818206783e-05, "loss": 1.3339, "step": 151790 }, { "epoch": 6.93, "learning_rate": 1.5375989747814547e-05, "loss": 1.3966, "step": 151800 }, { "epoch": 6.93, "learning_rate": 1.537370131356126e-05, "loss": 1.5339, "step": 151810 }, { "epoch": 6.93, "learning_rate": 1.537141287930798e-05, "loss": 1.3752, "step": 151820 }, { "epoch": 6.93, "learning_rate": 1.5369124445054696e-05, "loss": 1.4041, "step": 151830 }, { "epoch": 6.93, "learning_rate": 1.536683601080141e-05, "loss": 1.311, "step": 151840 }, { "epoch": 6.93, "learning_rate": 1.5364547576548128e-05, "loss": 1.4365, "step": 151850 }, { "epoch": 6.93, "learning_rate": 1.5362259142294845e-05, "loss": 1.3215, "step": 151860 }, { "epoch": 6.93, "learning_rate": 1.535997070804156e-05, "loss": 1.4052, "step": 151870 }, { "epoch": 6.94, "learning_rate": 1.5357682273788273e-05, "loss": 1.5566, "step": 151880 }, { "epoch": 6.94, "learning_rate": 1.535539383953499e-05, "loss": 1.3678, "step": 151890 }, { "epoch": 6.94, "learning_rate": 1.5353105405281705e-05, "loss": 1.4412, "step": 151900 }, { "epoch": 6.94, "learning_rate": 1.5350816971028423e-05, "loss": 1.5178, "step": 151910 }, { "epoch": 6.94, "learning_rate": 1.534852853677514e-05, "loss": 1.4376, "step": 151920 }, { "epoch": 6.94, "learning_rate": 1.5346240102521854e-05, "loss": 1.4498, "step": 151930 }, { "epoch": 6.94, "learning_rate": 1.534395166826857e-05, "loss": 1.3756, "step": 151940 }, { "epoch": 6.94, "learning_rate": 1.534166323401529e-05, "loss": 1.3967, "step": 151950 }, { "epoch": 6.94, "learning_rate": 1.5339374799762003e-05, "loss": 1.4918, "step": 151960 }, { "epoch": 6.94, "learning_rate": 1.533708636550872e-05, "loss": 1.395, "step": 151970 }, { "epoch": 6.94, "learning_rate": 1.5334797931255435e-05, "loss": 1.3758, "step": 151980 }, { "epoch": 6.94, "learning_rate": 1.5332509497002153e-05, "loss": 1.282, "step": 151990 }, { "epoch": 6.94, "learning_rate": 1.5330221062748867e-05, "loss": 1.2932, "step": 152000 }, { "epoch": 6.94, "learning_rate": 1.5327932628495584e-05, "loss": 1.4704, "step": 152010 }, { "epoch": 6.94, "learning_rate": 1.53256441942423e-05, "loss": 1.4597, "step": 152020 }, { "epoch": 6.94, "learning_rate": 1.5323355759989016e-05, "loss": 1.4424, "step": 152030 }, { "epoch": 6.94, "learning_rate": 1.5321067325735733e-05, "loss": 1.3899, "step": 152040 }, { "epoch": 6.94, "learning_rate": 1.531877889148245e-05, "loss": 1.5697, "step": 152050 }, { "epoch": 6.94, "learning_rate": 1.5316490457229165e-05, "loss": 1.4763, "step": 152060 }, { "epoch": 6.94, "learning_rate": 1.5314202022975883e-05, "loss": 1.4997, "step": 152070 }, { "epoch": 6.94, "learning_rate": 1.5311913588722597e-05, "loss": 1.4044, "step": 152080 }, { "epoch": 6.94, "learning_rate": 1.530962515446931e-05, "loss": 1.443, "step": 152090 }, { "epoch": 6.95, "learning_rate": 1.530733672021603e-05, "loss": 1.369, "step": 152100 }, { "epoch": 6.95, "learning_rate": 1.5305048285962746e-05, "loss": 1.4116, "step": 152110 }, { "epoch": 6.95, "learning_rate": 1.530275985170946e-05, "loss": 1.4186, "step": 152120 }, { "epoch": 6.95, "learning_rate": 1.5300471417456177e-05, "loss": 1.4907, "step": 152130 }, { "epoch": 6.95, "learning_rate": 1.5298182983202895e-05, "loss": 1.4264, "step": 152140 }, { "epoch": 6.95, "learning_rate": 1.529589454894961e-05, "loss": 1.4069, "step": 152150 }, { "epoch": 6.95, "learning_rate": 1.5293606114696327e-05, "loss": 1.5974, "step": 152160 }, { "epoch": 6.95, "learning_rate": 1.529131768044304e-05, "loss": 1.3111, "step": 152170 }, { "epoch": 6.95, "learning_rate": 1.528902924618976e-05, "loss": 1.3691, "step": 152180 }, { "epoch": 6.95, "learning_rate": 1.5286740811936472e-05, "loss": 1.4775, "step": 152190 }, { "epoch": 6.95, "learning_rate": 1.528445237768319e-05, "loss": 1.3944, "step": 152200 }, { "epoch": 6.95, "learning_rate": 1.5282163943429904e-05, "loss": 1.4323, "step": 152210 }, { "epoch": 6.95, "learning_rate": 1.527987550917662e-05, "loss": 1.3983, "step": 152220 }, { "epoch": 6.95, "learning_rate": 1.527758707492334e-05, "loss": 1.4661, "step": 152230 }, { "epoch": 6.95, "learning_rate": 1.5275298640670053e-05, "loss": 1.4588, "step": 152240 }, { "epoch": 6.95, "learning_rate": 1.527301020641677e-05, "loss": 1.6515, "step": 152250 }, { "epoch": 6.95, "learning_rate": 1.527072177216349e-05, "loss": 1.3123, "step": 152260 }, { "epoch": 6.95, "learning_rate": 1.5268433337910202e-05, "loss": 1.4797, "step": 152270 }, { "epoch": 6.95, "learning_rate": 1.5266144903656917e-05, "loss": 1.327, "step": 152280 }, { "epoch": 6.95, "learning_rate": 1.5263856469403634e-05, "loss": 1.2631, "step": 152290 }, { "epoch": 6.95, "learning_rate": 1.526156803515035e-05, "loss": 1.3703, "step": 152300 }, { "epoch": 6.95, "learning_rate": 1.5259279600897066e-05, "loss": 1.447, "step": 152310 }, { "epoch": 6.96, "learning_rate": 1.5256991166643783e-05, "loss": 1.4573, "step": 152320 }, { "epoch": 6.96, "learning_rate": 1.5254702732390499e-05, "loss": 1.3671, "step": 152330 }, { "epoch": 6.96, "learning_rate": 1.5252414298137217e-05, "loss": 1.2906, "step": 152340 }, { "epoch": 6.96, "learning_rate": 1.5250125863883932e-05, "loss": 1.4473, "step": 152350 }, { "epoch": 6.96, "learning_rate": 1.5247837429630648e-05, "loss": 1.3503, "step": 152360 }, { "epoch": 6.96, "learning_rate": 1.5245548995377362e-05, "loss": 1.364, "step": 152370 }, { "epoch": 6.96, "learning_rate": 1.5243260561124078e-05, "loss": 1.3318, "step": 152380 }, { "epoch": 6.96, "learning_rate": 1.5240972126870796e-05, "loss": 1.2992, "step": 152390 }, { "epoch": 6.96, "learning_rate": 1.5238683692617512e-05, "loss": 1.4311, "step": 152400 }, { "epoch": 6.96, "learning_rate": 1.5236395258364227e-05, "loss": 1.5427, "step": 152410 }, { "epoch": 6.96, "learning_rate": 1.5234106824110945e-05, "loss": 1.2341, "step": 152420 }, { "epoch": 6.96, "learning_rate": 1.523181838985766e-05, "loss": 1.6086, "step": 152430 }, { "epoch": 6.96, "learning_rate": 1.5229529955604377e-05, "loss": 1.4144, "step": 152440 }, { "epoch": 6.96, "learning_rate": 1.5227241521351092e-05, "loss": 1.4508, "step": 152450 }, { "epoch": 6.96, "learning_rate": 1.522495308709781e-05, "loss": 1.3994, "step": 152460 }, { "epoch": 6.96, "learning_rate": 1.5222664652844524e-05, "loss": 1.3535, "step": 152470 }, { "epoch": 6.96, "learning_rate": 1.522037621859124e-05, "loss": 1.4093, "step": 152480 }, { "epoch": 6.96, "learning_rate": 1.5218087784337956e-05, "loss": 1.3804, "step": 152490 }, { "epoch": 6.96, "learning_rate": 1.5215799350084672e-05, "loss": 1.4778, "step": 152500 }, { "epoch": 6.96, "learning_rate": 1.5213510915831389e-05, "loss": 1.4975, "step": 152510 }, { "epoch": 6.96, "learning_rate": 1.5211222481578105e-05, "loss": 1.7392, "step": 152520 }, { "epoch": 6.96, "learning_rate": 1.520893404732482e-05, "loss": 1.5458, "step": 152530 }, { "epoch": 6.97, "learning_rate": 1.5206645613071538e-05, "loss": 1.357, "step": 152540 }, { "epoch": 6.97, "learning_rate": 1.5204357178818254e-05, "loss": 1.4723, "step": 152550 }, { "epoch": 6.97, "learning_rate": 1.520206874456497e-05, "loss": 1.4886, "step": 152560 }, { "epoch": 6.97, "learning_rate": 1.5199780310311684e-05, "loss": 1.3144, "step": 152570 }, { "epoch": 6.97, "learning_rate": 1.51974918760584e-05, "loss": 1.3943, "step": 152580 }, { "epoch": 6.97, "learning_rate": 1.5195203441805117e-05, "loss": 1.4136, "step": 152590 }, { "epoch": 6.97, "learning_rate": 1.5192915007551833e-05, "loss": 1.2466, "step": 152600 }, { "epoch": 6.97, "learning_rate": 1.5190626573298549e-05, "loss": 1.3378, "step": 152610 }, { "epoch": 6.97, "learning_rate": 1.5188338139045267e-05, "loss": 1.3201, "step": 152620 }, { "epoch": 6.97, "learning_rate": 1.5186049704791982e-05, "loss": 1.4956, "step": 152630 }, { "epoch": 6.97, "learning_rate": 1.5183761270538698e-05, "loss": 1.4973, "step": 152640 }, { "epoch": 6.97, "learning_rate": 1.5181472836285416e-05, "loss": 1.4364, "step": 152650 }, { "epoch": 6.97, "learning_rate": 1.5179184402032132e-05, "loss": 1.4666, "step": 152660 }, { "epoch": 6.97, "learning_rate": 1.5176895967778846e-05, "loss": 1.4285, "step": 152670 }, { "epoch": 6.97, "learning_rate": 1.5174607533525562e-05, "loss": 1.3785, "step": 152680 }, { "epoch": 6.97, "learning_rate": 1.5172319099272277e-05, "loss": 1.3449, "step": 152690 }, { "epoch": 6.97, "learning_rate": 1.5170030665018995e-05, "loss": 1.4615, "step": 152700 }, { "epoch": 6.97, "learning_rate": 1.516774223076571e-05, "loss": 1.3327, "step": 152710 }, { "epoch": 6.97, "learning_rate": 1.5165453796512427e-05, "loss": 1.5282, "step": 152720 }, { "epoch": 6.97, "learning_rate": 1.5163165362259144e-05, "loss": 1.3943, "step": 152730 }, { "epoch": 6.97, "learning_rate": 1.516087692800586e-05, "loss": 1.3065, "step": 152740 }, { "epoch": 6.97, "learning_rate": 1.5158588493752576e-05, "loss": 1.566, "step": 152750 }, { "epoch": 6.98, "learning_rate": 1.5156300059499293e-05, "loss": 1.3877, "step": 152760 }, { "epoch": 6.98, "learning_rate": 1.5154011625246006e-05, "loss": 1.3111, "step": 152770 }, { "epoch": 6.98, "learning_rate": 1.5151723190992723e-05, "loss": 1.5239, "step": 152780 }, { "epoch": 6.98, "learning_rate": 1.5149434756739439e-05, "loss": 1.4966, "step": 152790 }, { "epoch": 6.98, "learning_rate": 1.5147146322486155e-05, "loss": 1.2935, "step": 152800 }, { "epoch": 6.98, "learning_rate": 1.5144857888232872e-05, "loss": 1.3929, "step": 152810 }, { "epoch": 6.98, "learning_rate": 1.5142569453979588e-05, "loss": 1.4088, "step": 152820 }, { "epoch": 6.98, "learning_rate": 1.5140281019726304e-05, "loss": 1.4232, "step": 152830 }, { "epoch": 6.98, "learning_rate": 1.5137992585473022e-05, "loss": 1.2774, "step": 152840 }, { "epoch": 6.98, "learning_rate": 1.5135704151219737e-05, "loss": 1.4942, "step": 152850 }, { "epoch": 6.98, "learning_rate": 1.5133415716966453e-05, "loss": 1.3705, "step": 152860 }, { "epoch": 6.98, "learning_rate": 1.5131127282713167e-05, "loss": 1.4799, "step": 152870 }, { "epoch": 6.98, "learning_rate": 1.5128838848459883e-05, "loss": 1.4788, "step": 152880 }, { "epoch": 6.98, "learning_rate": 1.51265504142066e-05, "loss": 1.3847, "step": 152890 }, { "epoch": 6.98, "learning_rate": 1.5124261979953317e-05, "loss": 1.3078, "step": 152900 }, { "epoch": 6.98, "learning_rate": 1.5121973545700032e-05, "loss": 1.4589, "step": 152910 }, { "epoch": 6.98, "learning_rate": 1.511968511144675e-05, "loss": 1.385, "step": 152920 }, { "epoch": 6.98, "learning_rate": 1.5117396677193466e-05, "loss": 1.5575, "step": 152930 }, { "epoch": 6.98, "learning_rate": 1.5115108242940182e-05, "loss": 1.4441, "step": 152940 }, { "epoch": 6.98, "learning_rate": 1.5112819808686899e-05, "loss": 1.3925, "step": 152950 }, { "epoch": 6.98, "learning_rate": 1.5110531374433612e-05, "loss": 1.4226, "step": 152960 }, { "epoch": 6.99, "learning_rate": 1.5108242940180329e-05, "loss": 1.3998, "step": 152970 }, { "epoch": 6.99, "learning_rate": 1.5105954505927045e-05, "loss": 1.4397, "step": 152980 }, { "epoch": 6.99, "learning_rate": 1.510366607167376e-05, "loss": 1.3922, "step": 152990 }, { "epoch": 6.99, "learning_rate": 1.5101377637420478e-05, "loss": 1.586, "step": 153000 }, { "epoch": 6.99, "learning_rate": 1.5099089203167194e-05, "loss": 1.5795, "step": 153010 }, { "epoch": 6.99, "learning_rate": 1.509680076891391e-05, "loss": 1.4475, "step": 153020 }, { "epoch": 6.99, "learning_rate": 1.5094512334660626e-05, "loss": 1.4341, "step": 153030 }, { "epoch": 6.99, "learning_rate": 1.5092223900407343e-05, "loss": 1.2714, "step": 153040 }, { "epoch": 6.99, "learning_rate": 1.5089935466154059e-05, "loss": 1.3822, "step": 153050 }, { "epoch": 6.99, "learning_rate": 1.5087647031900773e-05, "loss": 1.335, "step": 153060 }, { "epoch": 6.99, "learning_rate": 1.5085358597647489e-05, "loss": 1.565, "step": 153070 }, { "epoch": 6.99, "learning_rate": 1.5083070163394205e-05, "loss": 1.5548, "step": 153080 }, { "epoch": 6.99, "learning_rate": 1.5080781729140922e-05, "loss": 1.3044, "step": 153090 }, { "epoch": 6.99, "learning_rate": 1.5078493294887638e-05, "loss": 1.4187, "step": 153100 }, { "epoch": 6.99, "learning_rate": 1.5076204860634354e-05, "loss": 1.4552, "step": 153110 }, { "epoch": 6.99, "learning_rate": 1.5073916426381072e-05, "loss": 1.4442, "step": 153120 }, { "epoch": 6.99, "learning_rate": 1.5071627992127787e-05, "loss": 1.523, "step": 153130 }, { "epoch": 6.99, "learning_rate": 1.5069339557874503e-05, "loss": 1.6092, "step": 153140 }, { "epoch": 6.99, "learning_rate": 1.506705112362122e-05, "loss": 1.4922, "step": 153150 }, { "epoch": 6.99, "learning_rate": 1.5064762689367933e-05, "loss": 1.3474, "step": 153160 }, { "epoch": 6.99, "learning_rate": 1.506247425511465e-05, "loss": 1.3563, "step": 153170 }, { "epoch": 6.99, "learning_rate": 1.5060185820861366e-05, "loss": 1.2536, "step": 153180 }, { "epoch": 7.0, "learning_rate": 1.5057897386608082e-05, "loss": 1.3711, "step": 153190 }, { "epoch": 7.0, "learning_rate": 1.50556089523548e-05, "loss": 1.3558, "step": 153200 }, { "epoch": 7.0, "learning_rate": 1.5053320518101516e-05, "loss": 1.4111, "step": 153210 }, { "epoch": 7.0, "learning_rate": 1.5051032083848231e-05, "loss": 1.2889, "step": 153220 }, { "epoch": 7.0, "learning_rate": 1.5048743649594949e-05, "loss": 1.494, "step": 153230 }, { "epoch": 7.0, "learning_rate": 1.5046455215341665e-05, "loss": 1.3535, "step": 153240 }, { "epoch": 7.0, "learning_rate": 1.504416678108838e-05, "loss": 1.583, "step": 153250 }, { "epoch": 7.0, "learning_rate": 1.5041878346835095e-05, "loss": 1.4301, "step": 153260 }, { "epoch": 7.0, "learning_rate": 1.503958991258181e-05, "loss": 1.3476, "step": 153270 }, { "epoch": 7.0, "learning_rate": 1.5037301478328528e-05, "loss": 1.4673, "step": 153280 }, { "epoch": 7.0, "learning_rate": 1.5035013044075244e-05, "loss": 1.3817, "step": 153290 }, { "epoch": 7.0, "eval_cer": 0.6754929286084853, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.3372503519058228, "eval_runtime": 2700.7021, "eval_samples_per_second": 3.914, "eval_steps_per_second": 1.957, "eval_wer": 0.9927152317880795, "step": 153298 }, { "epoch": 7.0, "learning_rate": 1.503272460982196e-05, "loss": 1.3892, "step": 153300 }, { "epoch": 7.0, "learning_rate": 1.5030436175568677e-05, "loss": 1.4167, "step": 153310 }, { "epoch": 7.0, "learning_rate": 1.5028147741315393e-05, "loss": 1.4047, "step": 153320 }, { "epoch": 7.0, "learning_rate": 1.5025859307062109e-05, "loss": 1.4589, "step": 153330 }, { "epoch": 7.0, "learning_rate": 1.5023570872808827e-05, "loss": 1.4594, "step": 153340 }, { "epoch": 7.0, "learning_rate": 1.5021282438555542e-05, "loss": 1.1701, "step": 153350 }, { "epoch": 7.0, "learning_rate": 1.5018994004302256e-05, "loss": 1.2826, "step": 153360 }, { "epoch": 7.0, "learning_rate": 1.5016705570048972e-05, "loss": 1.4335, "step": 153370 }, { "epoch": 7.0, "learning_rate": 1.5014417135795688e-05, "loss": 1.3415, "step": 153380 }, { "epoch": 7.0, "learning_rate": 1.5012128701542406e-05, "loss": 1.3006, "step": 153390 }, { "epoch": 7.0, "learning_rate": 1.5009840267289121e-05, "loss": 1.4393, "step": 153400 }, { "epoch": 7.01, "learning_rate": 1.5007551833035837e-05, "loss": 1.4178, "step": 153410 }, { "epoch": 7.01, "learning_rate": 1.5005263398782555e-05, "loss": 1.5472, "step": 153420 }, { "epoch": 7.01, "learning_rate": 1.500297496452927e-05, "loss": 1.407, "step": 153430 }, { "epoch": 7.01, "learning_rate": 1.5000686530275986e-05, "loss": 1.422, "step": 153440 }, { "epoch": 7.01, "learning_rate": 1.4998398096022704e-05, "loss": 1.3015, "step": 153450 }, { "epoch": 7.01, "learning_rate": 1.4996109661769416e-05, "loss": 1.4648, "step": 153460 }, { "epoch": 7.01, "learning_rate": 1.4993821227516134e-05, "loss": 1.4612, "step": 153470 }, { "epoch": 7.01, "learning_rate": 1.499153279326285e-05, "loss": 1.361, "step": 153480 }, { "epoch": 7.01, "learning_rate": 1.4989244359009566e-05, "loss": 1.3503, "step": 153490 }, { "epoch": 7.01, "learning_rate": 1.4986955924756283e-05, "loss": 1.3572, "step": 153500 }, { "epoch": 7.01, "learning_rate": 1.4984667490502999e-05, "loss": 1.3501, "step": 153510 }, { "epoch": 7.01, "learning_rate": 1.4982379056249715e-05, "loss": 1.3952, "step": 153520 }, { "epoch": 7.01, "learning_rate": 1.4980090621996432e-05, "loss": 1.4021, "step": 153530 }, { "epoch": 7.01, "learning_rate": 1.4977802187743148e-05, "loss": 1.3814, "step": 153540 }, { "epoch": 7.01, "learning_rate": 1.4975513753489864e-05, "loss": 1.3466, "step": 153550 }, { "epoch": 7.01, "learning_rate": 1.4973225319236578e-05, "loss": 1.5059, "step": 153560 }, { "epoch": 7.01, "learning_rate": 1.4970936884983294e-05, "loss": 1.3475, "step": 153570 }, { "epoch": 7.01, "learning_rate": 1.4968648450730011e-05, "loss": 1.4629, "step": 153580 }, { "epoch": 7.01, "learning_rate": 1.4966360016476727e-05, "loss": 1.5056, "step": 153590 }, { "epoch": 7.01, "learning_rate": 1.4964071582223443e-05, "loss": 1.4158, "step": 153600 }, { "epoch": 7.01, "learning_rate": 1.496178314797016e-05, "loss": 1.2685, "step": 153610 }, { "epoch": 7.01, "learning_rate": 1.4959494713716876e-05, "loss": 1.2736, "step": 153620 }, { "epoch": 7.02, "learning_rate": 1.4957206279463592e-05, "loss": 1.5095, "step": 153630 }, { "epoch": 7.02, "learning_rate": 1.4954917845210308e-05, "loss": 1.6018, "step": 153640 }, { "epoch": 7.02, "learning_rate": 1.4952629410957026e-05, "loss": 1.3471, "step": 153650 }, { "epoch": 7.02, "learning_rate": 1.4950340976703738e-05, "loss": 1.2787, "step": 153660 }, { "epoch": 7.02, "learning_rate": 1.4948052542450456e-05, "loss": 1.3281, "step": 153670 }, { "epoch": 7.02, "learning_rate": 1.4945764108197171e-05, "loss": 1.3239, "step": 153680 }, { "epoch": 7.02, "learning_rate": 1.4943475673943887e-05, "loss": 1.353, "step": 153690 }, { "epoch": 7.02, "learning_rate": 1.4941187239690605e-05, "loss": 1.2554, "step": 153700 }, { "epoch": 7.02, "learning_rate": 1.493889880543732e-05, "loss": 1.3095, "step": 153710 }, { "epoch": 7.02, "learning_rate": 1.4936610371184036e-05, "loss": 1.308, "step": 153720 }, { "epoch": 7.02, "learning_rate": 1.4934321936930754e-05, "loss": 1.479, "step": 153730 }, { "epoch": 7.02, "learning_rate": 1.493203350267747e-05, "loss": 1.3755, "step": 153740 }, { "epoch": 7.02, "learning_rate": 1.4929745068424184e-05, "loss": 1.221, "step": 153750 }, { "epoch": 7.02, "learning_rate": 1.49274566341709e-05, "loss": 1.3919, "step": 153760 }, { "epoch": 7.02, "learning_rate": 1.4925168199917616e-05, "loss": 1.4613, "step": 153770 }, { "epoch": 7.02, "learning_rate": 1.4922879765664333e-05, "loss": 1.5723, "step": 153780 }, { "epoch": 7.02, "learning_rate": 1.4920591331411049e-05, "loss": 1.3989, "step": 153790 }, { "epoch": 7.02, "learning_rate": 1.4918302897157765e-05, "loss": 1.3906, "step": 153800 }, { "epoch": 7.02, "learning_rate": 1.4916014462904482e-05, "loss": 1.5286, "step": 153810 }, { "epoch": 7.02, "learning_rate": 1.4913726028651198e-05, "loss": 1.4021, "step": 153820 }, { "epoch": 7.02, "learning_rate": 1.4911437594397914e-05, "loss": 1.4732, "step": 153830 }, { "epoch": 7.02, "learning_rate": 1.4909149160144631e-05, "loss": 1.4366, "step": 153840 }, { "epoch": 7.03, "learning_rate": 1.4906860725891344e-05, "loss": 1.3592, "step": 153850 }, { "epoch": 7.03, "learning_rate": 1.4904572291638061e-05, "loss": 1.3487, "step": 153860 }, { "epoch": 7.03, "learning_rate": 1.4902283857384777e-05, "loss": 1.3641, "step": 153870 }, { "epoch": 7.03, "learning_rate": 1.4899995423131493e-05, "loss": 1.5671, "step": 153880 }, { "epoch": 7.03, "learning_rate": 1.489770698887821e-05, "loss": 1.4014, "step": 153890 }, { "epoch": 7.03, "learning_rate": 1.4895418554624926e-05, "loss": 1.4292, "step": 153900 }, { "epoch": 7.03, "learning_rate": 1.4893130120371642e-05, "loss": 1.5013, "step": 153910 }, { "epoch": 7.03, "learning_rate": 1.489084168611836e-05, "loss": 1.2868, "step": 153920 }, { "epoch": 7.03, "learning_rate": 1.4888553251865076e-05, "loss": 1.4193, "step": 153930 }, { "epoch": 7.03, "learning_rate": 1.4886264817611791e-05, "loss": 1.481, "step": 153940 }, { "epoch": 7.03, "learning_rate": 1.4883976383358506e-05, "loss": 1.3743, "step": 153950 }, { "epoch": 7.03, "learning_rate": 1.4881687949105221e-05, "loss": 1.3161, "step": 153960 }, { "epoch": 7.03, "learning_rate": 1.4879399514851939e-05, "loss": 1.4736, "step": 153970 }, { "epoch": 7.03, "learning_rate": 1.4877111080598655e-05, "loss": 1.2813, "step": 153980 }, { "epoch": 7.03, "learning_rate": 1.487482264634537e-05, "loss": 1.5204, "step": 153990 }, { "epoch": 7.03, "learning_rate": 1.4872534212092088e-05, "loss": 1.4448, "step": 154000 }, { "epoch": 7.03, "learning_rate": 1.4870245777838804e-05, "loss": 1.4332, "step": 154010 }, { "epoch": 7.03, "learning_rate": 1.486795734358552e-05, "loss": 1.4352, "step": 154020 }, { "epoch": 7.03, "learning_rate": 1.4865668909332237e-05, "loss": 1.2455, "step": 154030 }, { "epoch": 7.03, "learning_rate": 1.4863380475078953e-05, "loss": 1.3575, "step": 154040 }, { "epoch": 7.03, "learning_rate": 1.4861092040825667e-05, "loss": 1.5026, "step": 154050 }, { "epoch": 7.03, "learning_rate": 1.4858803606572383e-05, "loss": 1.4493, "step": 154060 }, { "epoch": 7.04, "learning_rate": 1.4856515172319099e-05, "loss": 1.4299, "step": 154070 }, { "epoch": 7.04, "learning_rate": 1.4854226738065816e-05, "loss": 1.3344, "step": 154080 }, { "epoch": 7.04, "learning_rate": 1.4851938303812532e-05, "loss": 1.348, "step": 154090 }, { "epoch": 7.04, "learning_rate": 1.4849649869559248e-05, "loss": 1.3582, "step": 154100 }, { "epoch": 7.04, "learning_rate": 1.4847361435305966e-05, "loss": 1.4279, "step": 154110 }, { "epoch": 7.04, "learning_rate": 1.4845073001052681e-05, "loss": 1.3815, "step": 154120 }, { "epoch": 7.04, "learning_rate": 1.4842784566799397e-05, "loss": 1.3825, "step": 154130 }, { "epoch": 7.04, "learning_rate": 1.4840496132546115e-05, "loss": 1.5347, "step": 154140 }, { "epoch": 7.04, "learning_rate": 1.4838207698292827e-05, "loss": 1.4419, "step": 154150 }, { "epoch": 7.04, "learning_rate": 1.4835919264039545e-05, "loss": 1.3614, "step": 154160 }, { "epoch": 7.04, "learning_rate": 1.483363082978626e-05, "loss": 1.2758, "step": 154170 }, { "epoch": 7.04, "learning_rate": 1.4831342395532976e-05, "loss": 1.4372, "step": 154180 }, { "epoch": 7.04, "learning_rate": 1.4829053961279694e-05, "loss": 1.4173, "step": 154190 }, { "epoch": 7.04, "learning_rate": 1.482676552702641e-05, "loss": 1.5792, "step": 154200 }, { "epoch": 7.04, "learning_rate": 1.4824477092773126e-05, "loss": 1.4161, "step": 154210 }, { "epoch": 7.04, "learning_rate": 1.4822188658519841e-05, "loss": 1.1228, "step": 154220 }, { "epoch": 7.04, "learning_rate": 1.4819900224266559e-05, "loss": 1.4254, "step": 154230 }, { "epoch": 7.04, "learning_rate": 1.4817611790013275e-05, "loss": 1.2476, "step": 154240 }, { "epoch": 7.04, "learning_rate": 1.4815323355759989e-05, "loss": 1.4582, "step": 154250 }, { "epoch": 7.04, "learning_rate": 1.4813034921506705e-05, "loss": 1.2641, "step": 154260 }, { "epoch": 7.04, "learning_rate": 1.481074648725342e-05, "loss": 1.4669, "step": 154270 }, { "epoch": 7.04, "learning_rate": 1.4808458053000138e-05, "loss": 1.4686, "step": 154280 }, { "epoch": 7.05, "learning_rate": 1.4806169618746854e-05, "loss": 1.3723, "step": 154290 }, { "epoch": 7.05, "learning_rate": 1.480388118449357e-05, "loss": 1.3622, "step": 154300 }, { "epoch": 7.05, "learning_rate": 1.4801592750240287e-05, "loss": 1.4401, "step": 154310 }, { "epoch": 7.05, "learning_rate": 1.4799304315987003e-05, "loss": 1.4907, "step": 154320 }, { "epoch": 7.05, "learning_rate": 1.4797015881733719e-05, "loss": 1.3271, "step": 154330 }, { "epoch": 7.05, "learning_rate": 1.4794727447480436e-05, "loss": 1.4229, "step": 154340 }, { "epoch": 7.05, "learning_rate": 1.4792439013227149e-05, "loss": 1.454, "step": 154350 }, { "epoch": 7.05, "learning_rate": 1.4790150578973866e-05, "loss": 1.547, "step": 154360 }, { "epoch": 7.05, "learning_rate": 1.4787862144720582e-05, "loss": 1.4912, "step": 154370 }, { "epoch": 7.05, "learning_rate": 1.4785573710467298e-05, "loss": 1.311, "step": 154380 }, { "epoch": 7.05, "learning_rate": 1.4783285276214016e-05, "loss": 1.4852, "step": 154390 }, { "epoch": 7.05, "learning_rate": 1.4780996841960731e-05, "loss": 1.2744, "step": 154400 }, { "epoch": 7.05, "learning_rate": 1.4778708407707447e-05, "loss": 1.4358, "step": 154410 }, { "epoch": 7.05, "learning_rate": 1.4776419973454165e-05, "loss": 1.5151, "step": 154420 }, { "epoch": 7.05, "learning_rate": 1.477413153920088e-05, "loss": 1.3067, "step": 154430 }, { "epoch": 7.05, "learning_rate": 1.4771843104947596e-05, "loss": 1.4682, "step": 154440 }, { "epoch": 7.05, "learning_rate": 1.476955467069431e-05, "loss": 1.4695, "step": 154450 }, { "epoch": 7.05, "learning_rate": 1.4767266236441026e-05, "loss": 1.4411, "step": 154460 }, { "epoch": 7.05, "learning_rate": 1.4764977802187744e-05, "loss": 1.4983, "step": 154470 }, { "epoch": 7.05, "learning_rate": 1.476268936793446e-05, "loss": 1.5336, "step": 154480 }, { "epoch": 7.05, "learning_rate": 1.4760400933681175e-05, "loss": 1.5278, "step": 154490 }, { "epoch": 7.05, "learning_rate": 1.4758112499427893e-05, "loss": 1.327, "step": 154500 }, { "epoch": 7.06, "learning_rate": 1.4755824065174609e-05, "loss": 1.2275, "step": 154510 }, { "epoch": 7.06, "learning_rate": 1.4753535630921325e-05, "loss": 1.3743, "step": 154520 }, { "epoch": 7.06, "learning_rate": 1.4751247196668042e-05, "loss": 1.2745, "step": 154530 }, { "epoch": 7.06, "learning_rate": 1.4748958762414755e-05, "loss": 1.3952, "step": 154540 }, { "epoch": 7.06, "learning_rate": 1.4746670328161472e-05, "loss": 1.3804, "step": 154550 }, { "epoch": 7.06, "learning_rate": 1.4744381893908188e-05, "loss": 1.3141, "step": 154560 }, { "epoch": 7.06, "learning_rate": 1.4742093459654904e-05, "loss": 1.2792, "step": 154570 }, { "epoch": 7.06, "learning_rate": 1.4739805025401621e-05, "loss": 1.4698, "step": 154580 }, { "epoch": 7.06, "learning_rate": 1.4737516591148337e-05, "loss": 1.3824, "step": 154590 }, { "epoch": 7.06, "learning_rate": 1.4735228156895053e-05, "loss": 1.4374, "step": 154600 }, { "epoch": 7.06, "learning_rate": 1.473293972264177e-05, "loss": 1.2362, "step": 154610 }, { "epoch": 7.06, "learning_rate": 1.4730651288388486e-05, "loss": 1.4737, "step": 154620 }, { "epoch": 7.06, "learning_rate": 1.4728362854135202e-05, "loss": 1.3105, "step": 154630 }, { "epoch": 7.06, "learning_rate": 1.4726074419881916e-05, "loss": 1.2524, "step": 154640 }, { "epoch": 7.06, "learning_rate": 1.4723785985628632e-05, "loss": 1.4994, "step": 154650 }, { "epoch": 7.06, "learning_rate": 1.472149755137535e-05, "loss": 1.5007, "step": 154660 }, { "epoch": 7.06, "learning_rate": 1.4719209117122065e-05, "loss": 1.6114, "step": 154670 }, { "epoch": 7.06, "learning_rate": 1.4716920682868781e-05, "loss": 1.2959, "step": 154680 }, { "epoch": 7.06, "learning_rate": 1.4714632248615499e-05, "loss": 1.4153, "step": 154690 }, { "epoch": 7.06, "learning_rate": 1.4712343814362215e-05, "loss": 1.2521, "step": 154700 }, { "epoch": 7.06, "learning_rate": 1.471005538010893e-05, "loss": 1.2723, "step": 154710 }, { "epoch": 7.06, "learning_rate": 1.4707766945855648e-05, "loss": 1.3282, "step": 154720 }, { "epoch": 7.07, "learning_rate": 1.4705478511602364e-05, "loss": 1.4146, "step": 154730 }, { "epoch": 7.07, "learning_rate": 1.4703190077349078e-05, "loss": 1.412, "step": 154740 }, { "epoch": 7.07, "learning_rate": 1.4700901643095794e-05, "loss": 1.4688, "step": 154750 }, { "epoch": 7.07, "learning_rate": 1.469861320884251e-05, "loss": 1.3008, "step": 154760 }, { "epoch": 7.07, "learning_rate": 1.4696324774589227e-05, "loss": 1.3565, "step": 154770 }, { "epoch": 7.07, "learning_rate": 1.4694036340335943e-05, "loss": 1.3674, "step": 154780 }, { "epoch": 7.07, "learning_rate": 1.4691747906082659e-05, "loss": 1.4747, "step": 154790 }, { "epoch": 7.07, "learning_rate": 1.4689459471829375e-05, "loss": 1.4739, "step": 154800 }, { "epoch": 7.07, "learning_rate": 1.4687171037576092e-05, "loss": 1.3869, "step": 154810 }, { "epoch": 7.07, "learning_rate": 1.4684882603322808e-05, "loss": 1.2716, "step": 154820 }, { "epoch": 7.07, "learning_rate": 1.4682594169069524e-05, "loss": 1.3945, "step": 154830 }, { "epoch": 7.07, "learning_rate": 1.4680305734816238e-05, "loss": 1.4098, "step": 154840 }, { "epoch": 7.07, "learning_rate": 1.4678017300562954e-05, "loss": 1.3308, "step": 154850 }, { "epoch": 7.07, "learning_rate": 1.4675728866309671e-05, "loss": 1.4272, "step": 154860 }, { "epoch": 7.07, "learning_rate": 1.4673440432056387e-05, "loss": 1.3459, "step": 154870 }, { "epoch": 7.07, "learning_rate": 1.4671151997803103e-05, "loss": 1.4848, "step": 154880 }, { "epoch": 7.07, "learning_rate": 1.466886356354982e-05, "loss": 1.2505, "step": 154890 }, { "epoch": 7.07, "learning_rate": 1.4666575129296536e-05, "loss": 1.6248, "step": 154900 }, { "epoch": 7.07, "learning_rate": 1.4664286695043252e-05, "loss": 1.3398, "step": 154910 }, { "epoch": 7.07, "learning_rate": 1.466199826078997e-05, "loss": 1.2512, "step": 154920 }, { "epoch": 7.07, "learning_rate": 1.4659709826536685e-05, "loss": 1.4683, "step": 154930 }, { "epoch": 7.07, "learning_rate": 1.46574213922834e-05, "loss": 1.436, "step": 154940 }, { "epoch": 7.08, "learning_rate": 1.4655132958030115e-05, "loss": 1.527, "step": 154950 }, { "epoch": 7.08, "learning_rate": 1.4652844523776831e-05, "loss": 1.4343, "step": 154960 }, { "epoch": 7.08, "learning_rate": 1.4650556089523549e-05, "loss": 1.3926, "step": 154970 }, { "epoch": 7.08, "learning_rate": 1.4648267655270265e-05, "loss": 1.2924, "step": 154980 }, { "epoch": 7.08, "learning_rate": 1.464597922101698e-05, "loss": 1.4584, "step": 154990 }, { "epoch": 7.08, "learning_rate": 1.4643690786763698e-05, "loss": 1.4051, "step": 155000 }, { "epoch": 7.08, "learning_rate": 1.4641402352510414e-05, "loss": 1.5457, "step": 155010 }, { "epoch": 7.08, "learning_rate": 1.463911391825713e-05, "loss": 1.3954, "step": 155020 }, { "epoch": 7.08, "learning_rate": 1.4636825484003847e-05, "loss": 1.3353, "step": 155030 }, { "epoch": 7.08, "learning_rate": 1.463453704975056e-05, "loss": 1.4126, "step": 155040 }, { "epoch": 7.08, "learning_rate": 1.4632248615497277e-05, "loss": 1.457, "step": 155050 }, { "epoch": 7.08, "learning_rate": 1.4629960181243993e-05, "loss": 1.4956, "step": 155060 }, { "epoch": 7.08, "learning_rate": 1.4627671746990709e-05, "loss": 1.431, "step": 155070 }, { "epoch": 7.08, "learning_rate": 1.4625383312737426e-05, "loss": 1.3018, "step": 155080 }, { "epoch": 7.08, "learning_rate": 1.4623094878484142e-05, "loss": 1.3368, "step": 155090 }, { "epoch": 7.08, "learning_rate": 1.4620806444230858e-05, "loss": 1.387, "step": 155100 }, { "epoch": 7.08, "learning_rate": 1.4618518009977575e-05, "loss": 1.4285, "step": 155110 }, { "epoch": 7.08, "learning_rate": 1.4616229575724291e-05, "loss": 1.3133, "step": 155120 }, { "epoch": 7.08, "learning_rate": 1.4613941141471007e-05, "loss": 1.1542, "step": 155130 }, { "epoch": 7.08, "learning_rate": 1.4611652707217721e-05, "loss": 1.4258, "step": 155140 }, { "epoch": 7.08, "learning_rate": 1.4609364272964437e-05, "loss": 1.4756, "step": 155150 }, { "epoch": 7.09, "learning_rate": 1.4607075838711155e-05, "loss": 1.4626, "step": 155160 }, { "epoch": 7.09, "learning_rate": 1.460478740445787e-05, "loss": 1.5528, "step": 155170 }, { "epoch": 7.09, "learning_rate": 1.4602498970204586e-05, "loss": 1.2974, "step": 155180 }, { "epoch": 7.09, "learning_rate": 1.4600210535951304e-05, "loss": 1.3695, "step": 155190 }, { "epoch": 7.09, "learning_rate": 1.459792210169802e-05, "loss": 1.4227, "step": 155200 }, { "epoch": 7.09, "learning_rate": 1.4595633667444735e-05, "loss": 1.3859, "step": 155210 }, { "epoch": 7.09, "learning_rate": 1.4593345233191453e-05, "loss": 1.3115, "step": 155220 }, { "epoch": 7.09, "learning_rate": 1.4591056798938169e-05, "loss": 1.3978, "step": 155230 }, { "epoch": 7.09, "learning_rate": 1.4588768364684883e-05, "loss": 1.4095, "step": 155240 }, { "epoch": 7.09, "learning_rate": 1.4586479930431599e-05, "loss": 1.4399, "step": 155250 }, { "epoch": 7.09, "learning_rate": 1.4584191496178315e-05, "loss": 1.3688, "step": 155260 }, { "epoch": 7.09, "learning_rate": 1.4581903061925032e-05, "loss": 1.2954, "step": 155270 }, { "epoch": 7.09, "learning_rate": 1.4579614627671748e-05, "loss": 1.4904, "step": 155280 }, { "epoch": 7.09, "learning_rate": 1.4577326193418464e-05, "loss": 1.3541, "step": 155290 }, { "epoch": 7.09, "learning_rate": 1.4575037759165181e-05, "loss": 1.4358, "step": 155300 }, { "epoch": 7.09, "learning_rate": 1.4572749324911897e-05, "loss": 1.289, "step": 155310 }, { "epoch": 7.09, "learning_rate": 1.4570460890658613e-05, "loss": 1.3479, "step": 155320 }, { "epoch": 7.09, "learning_rate": 1.4568172456405327e-05, "loss": 1.408, "step": 155330 }, { "epoch": 7.09, "learning_rate": 1.4565884022152043e-05, "loss": 1.4479, "step": 155340 }, { "epoch": 7.09, "learning_rate": 1.456359558789876e-05, "loss": 1.3457, "step": 155350 }, { "epoch": 7.09, "learning_rate": 1.4561307153645476e-05, "loss": 1.4439, "step": 155360 }, { "epoch": 7.09, "learning_rate": 1.4559018719392192e-05, "loss": 1.2604, "step": 155370 }, { "epoch": 7.1, "learning_rate": 1.4556730285138908e-05, "loss": 1.2912, "step": 155380 }, { "epoch": 7.1, "learning_rate": 1.4554441850885625e-05, "loss": 1.3315, "step": 155390 }, { "epoch": 7.1, "learning_rate": 1.4552153416632341e-05, "loss": 1.3261, "step": 155400 }, { "epoch": 7.1, "learning_rate": 1.4549864982379057e-05, "loss": 1.3716, "step": 155410 }, { "epoch": 7.1, "learning_rate": 1.4547576548125775e-05, "loss": 1.5237, "step": 155420 }, { "epoch": 7.1, "learning_rate": 1.4545288113872487e-05, "loss": 1.3897, "step": 155430 }, { "epoch": 7.1, "learning_rate": 1.4542999679619205e-05, "loss": 1.4148, "step": 155440 }, { "epoch": 7.1, "learning_rate": 1.454071124536592e-05, "loss": 1.3992, "step": 155450 }, { "epoch": 7.1, "learning_rate": 1.4538422811112636e-05, "loss": 1.2536, "step": 155460 }, { "epoch": 7.1, "learning_rate": 1.4536134376859354e-05, "loss": 1.3586, "step": 155470 }, { "epoch": 7.1, "learning_rate": 1.453384594260607e-05, "loss": 1.3538, "step": 155480 }, { "epoch": 7.1, "learning_rate": 1.4531557508352785e-05, "loss": 1.3444, "step": 155490 }, { "epoch": 7.1, "learning_rate": 1.4529269074099503e-05, "loss": 1.4502, "step": 155500 }, { "epoch": 7.1, "learning_rate": 1.4526980639846219e-05, "loss": 1.4156, "step": 155510 }, { "epoch": 7.1, "learning_rate": 1.4524692205592935e-05, "loss": 1.5499, "step": 155520 }, { "epoch": 7.1, "learning_rate": 1.4522403771339649e-05, "loss": 1.4465, "step": 155530 }, { "epoch": 7.1, "learning_rate": 1.4520115337086364e-05, "loss": 1.3921, "step": 155540 }, { "epoch": 7.1, "learning_rate": 1.4517826902833082e-05, "loss": 1.3622, "step": 155550 }, { "epoch": 7.1, "learning_rate": 1.4515538468579798e-05, "loss": 1.466, "step": 155560 }, { "epoch": 7.1, "learning_rate": 1.4513250034326514e-05, "loss": 1.3938, "step": 155570 }, { "epoch": 7.1, "learning_rate": 1.4510961600073231e-05, "loss": 1.416, "step": 155580 }, { "epoch": 7.1, "learning_rate": 1.4508673165819947e-05, "loss": 1.3752, "step": 155590 }, { "epoch": 7.11, "learning_rate": 1.4506384731566663e-05, "loss": 1.345, "step": 155600 }, { "epoch": 7.11, "learning_rate": 1.450409629731338e-05, "loss": 1.3866, "step": 155610 }, { "epoch": 7.11, "learning_rate": 1.4501807863060096e-05, "loss": 1.3911, "step": 155620 }, { "epoch": 7.11, "learning_rate": 1.449951942880681e-05, "loss": 1.4788, "step": 155630 }, { "epoch": 7.11, "learning_rate": 1.4497230994553526e-05, "loss": 1.4415, "step": 155640 }, { "epoch": 7.11, "learning_rate": 1.4494942560300242e-05, "loss": 1.3783, "step": 155650 }, { "epoch": 7.11, "learning_rate": 1.449265412604696e-05, "loss": 1.3555, "step": 155660 }, { "epoch": 7.11, "learning_rate": 1.4490365691793675e-05, "loss": 1.3633, "step": 155670 }, { "epoch": 7.11, "learning_rate": 1.4488077257540391e-05, "loss": 1.4838, "step": 155680 }, { "epoch": 7.11, "learning_rate": 1.4485788823287109e-05, "loss": 1.441, "step": 155690 }, { "epoch": 7.11, "learning_rate": 1.4483500389033825e-05, "loss": 1.3394, "step": 155700 }, { "epoch": 7.11, "learning_rate": 1.448121195478054e-05, "loss": 1.2478, "step": 155710 }, { "epoch": 7.11, "learning_rate": 1.4478923520527258e-05, "loss": 1.474, "step": 155720 }, { "epoch": 7.11, "learning_rate": 1.447663508627397e-05, "loss": 1.1864, "step": 155730 }, { "epoch": 7.11, "learning_rate": 1.4474346652020688e-05, "loss": 1.374, "step": 155740 }, { "epoch": 7.11, "learning_rate": 1.4472058217767404e-05, "loss": 1.4968, "step": 155750 }, { "epoch": 7.11, "learning_rate": 1.446976978351412e-05, "loss": 1.4164, "step": 155760 }, { "epoch": 7.11, "learning_rate": 1.4467481349260837e-05, "loss": 1.29, "step": 155770 }, { "epoch": 7.11, "learning_rate": 1.4465192915007553e-05, "loss": 1.3094, "step": 155780 }, { "epoch": 7.11, "learning_rate": 1.4462904480754269e-05, "loss": 1.4452, "step": 155790 }, { "epoch": 7.11, "learning_rate": 1.4460616046500986e-05, "loss": 1.4107, "step": 155800 }, { "epoch": 7.11, "learning_rate": 1.4458327612247702e-05, "loss": 1.4011, "step": 155810 }, { "epoch": 7.12, "learning_rate": 1.4456039177994418e-05, "loss": 1.2226, "step": 155820 }, { "epoch": 7.12, "learning_rate": 1.4453750743741132e-05, "loss": 1.3926, "step": 155830 }, { "epoch": 7.12, "learning_rate": 1.4451462309487848e-05, "loss": 1.3102, "step": 155840 }, { "epoch": 7.12, "learning_rate": 1.4449173875234565e-05, "loss": 1.3711, "step": 155850 }, { "epoch": 7.12, "learning_rate": 1.4446885440981281e-05, "loss": 1.3873, "step": 155860 }, { "epoch": 7.12, "learning_rate": 1.4444597006727997e-05, "loss": 1.5111, "step": 155870 }, { "epoch": 7.12, "learning_rate": 1.4442308572474714e-05, "loss": 1.3628, "step": 155880 }, { "epoch": 7.12, "learning_rate": 1.444002013822143e-05, "loss": 1.3202, "step": 155890 }, { "epoch": 7.12, "learning_rate": 1.4437731703968146e-05, "loss": 1.4047, "step": 155900 }, { "epoch": 7.12, "learning_rate": 1.4435443269714864e-05, "loss": 1.3987, "step": 155910 }, { "epoch": 7.12, "learning_rate": 1.443315483546158e-05, "loss": 1.3258, "step": 155920 }, { "epoch": 7.12, "learning_rate": 1.4430866401208294e-05, "loss": 1.4559, "step": 155930 }, { "epoch": 7.12, "learning_rate": 1.442857796695501e-05, "loss": 1.4132, "step": 155940 }, { "epoch": 7.12, "learning_rate": 1.4426289532701725e-05, "loss": 1.5816, "step": 155950 }, { "epoch": 7.12, "learning_rate": 1.4424001098448441e-05, "loss": 1.3319, "step": 155960 }, { "epoch": 7.12, "learning_rate": 1.4421712664195159e-05, "loss": 1.4502, "step": 155970 }, { "epoch": 7.12, "learning_rate": 1.4419424229941874e-05, "loss": 1.2991, "step": 155980 }, { "epoch": 7.12, "learning_rate": 1.441713579568859e-05, "loss": 1.3824, "step": 155990 }, { "epoch": 7.12, "learning_rate": 1.4414847361435308e-05, "loss": 1.1754, "step": 156000 }, { "epoch": 7.12, "learning_rate": 1.4412558927182024e-05, "loss": 1.6014, "step": 156010 }, { "epoch": 7.12, "learning_rate": 1.441027049292874e-05, "loss": 1.3098, "step": 156020 }, { "epoch": 7.12, "learning_rate": 1.4407982058675454e-05, "loss": 1.4365, "step": 156030 }, { "epoch": 7.13, "learning_rate": 1.440569362442217e-05, "loss": 1.2421, "step": 156040 }, { "epoch": 7.13, "learning_rate": 1.4403405190168887e-05, "loss": 1.457, "step": 156050 }, { "epoch": 7.13, "learning_rate": 1.4401116755915603e-05, "loss": 1.4338, "step": 156060 }, { "epoch": 7.13, "learning_rate": 1.4398828321662319e-05, "loss": 1.2603, "step": 156070 }, { "epoch": 7.13, "learning_rate": 1.4396539887409036e-05, "loss": 1.2757, "step": 156080 }, { "epoch": 7.13, "learning_rate": 1.4394251453155752e-05, "loss": 1.2862, "step": 156090 }, { "epoch": 7.13, "learning_rate": 1.4391963018902468e-05, "loss": 1.412, "step": 156100 }, { "epoch": 7.13, "learning_rate": 1.4389674584649185e-05, "loss": 1.3939, "step": 156110 }, { "epoch": 7.13, "learning_rate": 1.4387386150395898e-05, "loss": 1.3235, "step": 156120 }, { "epoch": 7.13, "learning_rate": 1.4385097716142615e-05, "loss": 1.5012, "step": 156130 }, { "epoch": 7.13, "learning_rate": 1.4382809281889331e-05, "loss": 1.2786, "step": 156140 }, { "epoch": 7.13, "learning_rate": 1.4380520847636047e-05, "loss": 1.425, "step": 156150 }, { "epoch": 7.13, "learning_rate": 1.4378232413382764e-05, "loss": 1.3705, "step": 156160 }, { "epoch": 7.13, "learning_rate": 1.437594397912948e-05, "loss": 1.3697, "step": 156170 }, { "epoch": 7.13, "learning_rate": 1.4373655544876196e-05, "loss": 1.2459, "step": 156180 }, { "epoch": 7.13, "learning_rate": 1.4371367110622914e-05, "loss": 1.4665, "step": 156190 }, { "epoch": 7.13, "learning_rate": 1.436907867636963e-05, "loss": 1.3621, "step": 156200 }, { "epoch": 7.13, "learning_rate": 1.4366790242116345e-05, "loss": 1.3309, "step": 156210 }, { "epoch": 7.13, "learning_rate": 1.436450180786306e-05, "loss": 1.3981, "step": 156220 }, { "epoch": 7.13, "learning_rate": 1.4362213373609775e-05, "loss": 1.4651, "step": 156230 }, { "epoch": 7.13, "learning_rate": 1.4359924939356493e-05, "loss": 1.3802, "step": 156240 }, { "epoch": 7.13, "learning_rate": 1.4357636505103209e-05, "loss": 1.5803, "step": 156250 }, { "epoch": 7.14, "learning_rate": 1.4355348070849924e-05, "loss": 1.2419, "step": 156260 }, { "epoch": 7.14, "learning_rate": 1.4353059636596642e-05, "loss": 1.4438, "step": 156270 }, { "epoch": 7.14, "learning_rate": 1.4350771202343358e-05, "loss": 1.21, "step": 156280 }, { "epoch": 7.14, "learning_rate": 1.4348482768090074e-05, "loss": 1.393, "step": 156290 }, { "epoch": 7.14, "learning_rate": 1.4346194333836791e-05, "loss": 1.3392, "step": 156300 }, { "epoch": 7.14, "learning_rate": 1.4343905899583507e-05, "loss": 1.3405, "step": 156310 }, { "epoch": 7.14, "learning_rate": 1.4341617465330221e-05, "loss": 1.454, "step": 156320 }, { "epoch": 7.14, "learning_rate": 1.4339329031076937e-05, "loss": 1.4091, "step": 156330 }, { "epoch": 7.14, "learning_rate": 1.4337040596823653e-05, "loss": 1.4124, "step": 156340 }, { "epoch": 7.14, "learning_rate": 1.433475216257037e-05, "loss": 1.3772, "step": 156350 }, { "epoch": 7.14, "learning_rate": 1.4332463728317086e-05, "loss": 1.6031, "step": 156360 }, { "epoch": 7.14, "learning_rate": 1.4330175294063802e-05, "loss": 1.323, "step": 156370 }, { "epoch": 7.14, "learning_rate": 1.432788685981052e-05, "loss": 1.374, "step": 156380 }, { "epoch": 7.14, "learning_rate": 1.4325598425557235e-05, "loss": 1.4334, "step": 156390 }, { "epoch": 7.14, "learning_rate": 1.4323309991303951e-05, "loss": 1.4219, "step": 156400 }, { "epoch": 7.14, "learning_rate": 1.4321021557050669e-05, "loss": 1.4201, "step": 156410 }, { "epoch": 7.14, "learning_rate": 1.4318733122797381e-05, "loss": 1.2582, "step": 156420 }, { "epoch": 7.14, "learning_rate": 1.4316444688544099e-05, "loss": 1.3292, "step": 156430 }, { "epoch": 7.14, "learning_rate": 1.4314156254290814e-05, "loss": 1.4422, "step": 156440 }, { "epoch": 7.14, "learning_rate": 1.431186782003753e-05, "loss": 1.2867, "step": 156450 }, { "epoch": 7.14, "learning_rate": 1.4309579385784248e-05, "loss": 1.3406, "step": 156460 }, { "epoch": 7.14, "learning_rate": 1.4307290951530964e-05, "loss": 1.3229, "step": 156470 }, { "epoch": 7.15, "learning_rate": 1.430500251727768e-05, "loss": 1.5219, "step": 156480 }, { "epoch": 7.15, "learning_rate": 1.4302714083024397e-05, "loss": 1.4166, "step": 156490 }, { "epoch": 7.15, "learning_rate": 1.4300425648771113e-05, "loss": 1.3096, "step": 156500 }, { "epoch": 7.15, "learning_rate": 1.4298137214517829e-05, "loss": 1.4426, "step": 156510 }, { "epoch": 7.15, "learning_rate": 1.4295848780264543e-05, "loss": 1.3663, "step": 156520 }, { "epoch": 7.15, "learning_rate": 1.4293560346011259e-05, "loss": 1.2459, "step": 156530 }, { "epoch": 7.15, "learning_rate": 1.4291271911757974e-05, "loss": 1.3028, "step": 156540 }, { "epoch": 7.15, "learning_rate": 1.4288983477504692e-05, "loss": 1.4028, "step": 156550 }, { "epoch": 7.15, "learning_rate": 1.4286695043251408e-05, "loss": 1.5453, "step": 156560 }, { "epoch": 7.15, "learning_rate": 1.4284406608998124e-05, "loss": 1.2643, "step": 156570 }, { "epoch": 7.15, "learning_rate": 1.4282118174744841e-05, "loss": 1.46, "step": 156580 }, { "epoch": 7.15, "learning_rate": 1.4279829740491557e-05, "loss": 1.4311, "step": 156590 }, { "epoch": 7.15, "learning_rate": 1.4277541306238273e-05, "loss": 1.2945, "step": 156600 }, { "epoch": 7.15, "learning_rate": 1.427525287198499e-05, "loss": 1.4509, "step": 156610 }, { "epoch": 7.15, "learning_rate": 1.4272964437731703e-05, "loss": 1.3124, "step": 156620 }, { "epoch": 7.15, "learning_rate": 1.427067600347842e-05, "loss": 1.3092, "step": 156630 }, { "epoch": 7.15, "learning_rate": 1.4268387569225136e-05, "loss": 1.2427, "step": 156640 }, { "epoch": 7.15, "learning_rate": 1.4266099134971852e-05, "loss": 1.3588, "step": 156650 }, { "epoch": 7.15, "learning_rate": 1.426381070071857e-05, "loss": 1.3228, "step": 156660 }, { "epoch": 7.15, "learning_rate": 1.4261522266465285e-05, "loss": 1.3104, "step": 156670 }, { "epoch": 7.15, "learning_rate": 1.4259233832212001e-05, "loss": 1.3307, "step": 156680 }, { "epoch": 7.15, "learning_rate": 1.4256945397958719e-05, "loss": 1.5391, "step": 156690 }, { "epoch": 7.16, "learning_rate": 1.4254656963705434e-05, "loss": 1.407, "step": 156700 }, { "epoch": 7.16, "learning_rate": 1.425236852945215e-05, "loss": 1.3613, "step": 156710 }, { "epoch": 7.16, "learning_rate": 1.4250080095198864e-05, "loss": 1.3915, "step": 156720 }, { "epoch": 7.16, "learning_rate": 1.424779166094558e-05, "loss": 1.3359, "step": 156730 }, { "epoch": 7.16, "learning_rate": 1.4245503226692298e-05, "loss": 1.3839, "step": 156740 }, { "epoch": 7.16, "learning_rate": 1.4243214792439014e-05, "loss": 1.3697, "step": 156750 }, { "epoch": 7.16, "learning_rate": 1.424092635818573e-05, "loss": 1.282, "step": 156760 }, { "epoch": 7.16, "learning_rate": 1.4238637923932447e-05, "loss": 1.3547, "step": 156770 }, { "epoch": 7.16, "learning_rate": 1.4236349489679163e-05, "loss": 1.3955, "step": 156780 }, { "epoch": 7.16, "learning_rate": 1.4234061055425879e-05, "loss": 1.5411, "step": 156790 }, { "epoch": 7.16, "learning_rate": 1.4231772621172596e-05, "loss": 1.3473, "step": 156800 }, { "epoch": 7.16, "learning_rate": 1.4229484186919312e-05, "loss": 1.3555, "step": 156810 }, { "epoch": 7.16, "learning_rate": 1.4227195752666026e-05, "loss": 1.3506, "step": 156820 }, { "epoch": 7.16, "learning_rate": 1.4224907318412742e-05, "loss": 1.421, "step": 156830 }, { "epoch": 7.16, "learning_rate": 1.4222618884159458e-05, "loss": 1.3935, "step": 156840 }, { "epoch": 7.16, "learning_rate": 1.4220330449906175e-05, "loss": 1.4044, "step": 156850 }, { "epoch": 7.16, "learning_rate": 1.4218042015652891e-05, "loss": 1.38, "step": 156860 }, { "epoch": 7.16, "learning_rate": 1.4215753581399607e-05, "loss": 1.5851, "step": 156870 }, { "epoch": 7.16, "learning_rate": 1.4213465147146324e-05, "loss": 1.4273, "step": 156880 }, { "epoch": 7.16, "learning_rate": 1.421117671289304e-05, "loss": 1.3896, "step": 156890 }, { "epoch": 7.16, "learning_rate": 1.4208888278639756e-05, "loss": 1.2611, "step": 156900 }, { "epoch": 7.16, "learning_rate": 1.420659984438647e-05, "loss": 1.3985, "step": 156910 }, { "epoch": 7.17, "learning_rate": 1.4204311410133186e-05, "loss": 1.4398, "step": 156920 }, { "epoch": 7.17, "learning_rate": 1.4202022975879903e-05, "loss": 1.4783, "step": 156930 }, { "epoch": 7.17, "learning_rate": 1.419973454162662e-05, "loss": 1.4878, "step": 156940 }, { "epoch": 7.17, "learning_rate": 1.4197446107373335e-05, "loss": 1.3026, "step": 156950 }, { "epoch": 7.17, "learning_rate": 1.4195157673120053e-05, "loss": 1.43, "step": 156960 }, { "epoch": 7.17, "learning_rate": 1.4192869238866768e-05, "loss": 1.3619, "step": 156970 }, { "epoch": 7.17, "learning_rate": 1.4190580804613484e-05, "loss": 1.5112, "step": 156980 }, { "epoch": 7.17, "learning_rate": 1.4188292370360202e-05, "loss": 1.5092, "step": 156990 }, { "epoch": 7.17, "learning_rate": 1.4186003936106918e-05, "loss": 1.3037, "step": 157000 }, { "epoch": 7.17, "learning_rate": 1.4183715501853632e-05, "loss": 1.5099, "step": 157010 }, { "epoch": 7.17, "learning_rate": 1.4181427067600348e-05, "loss": 1.3937, "step": 157020 }, { "epoch": 7.17, "learning_rate": 1.4179138633347063e-05, "loss": 1.3751, "step": 157030 }, { "epoch": 7.17, "learning_rate": 1.4176850199093781e-05, "loss": 1.4088, "step": 157040 }, { "epoch": 7.17, "learning_rate": 1.4174561764840497e-05, "loss": 1.2534, "step": 157050 }, { "epoch": 7.17, "learning_rate": 1.4172273330587213e-05, "loss": 1.4242, "step": 157060 }, { "epoch": 7.17, "learning_rate": 1.416998489633393e-05, "loss": 1.4052, "step": 157070 }, { "epoch": 7.17, "learning_rate": 1.4167696462080646e-05, "loss": 1.2391, "step": 157080 }, { "epoch": 7.17, "learning_rate": 1.4165408027827362e-05, "loss": 1.4364, "step": 157090 }, { "epoch": 7.17, "learning_rate": 1.4163119593574078e-05, "loss": 1.3046, "step": 157100 }, { "epoch": 7.17, "learning_rate": 1.4160831159320792e-05, "loss": 1.1861, "step": 157110 }, { "epoch": 7.17, "learning_rate": 1.415854272506751e-05, "loss": 1.3766, "step": 157120 }, { "epoch": 7.17, "learning_rate": 1.4156254290814225e-05, "loss": 1.3751, "step": 157130 }, { "epoch": 7.18, "learning_rate": 1.4153965856560941e-05, "loss": 1.2523, "step": 157140 }, { "epoch": 7.18, "learning_rate": 1.4151677422307657e-05, "loss": 1.4632, "step": 157150 }, { "epoch": 7.18, "learning_rate": 1.4149388988054374e-05, "loss": 1.4596, "step": 157160 }, { "epoch": 7.18, "learning_rate": 1.414710055380109e-05, "loss": 1.3467, "step": 157170 }, { "epoch": 7.18, "learning_rate": 1.4144812119547806e-05, "loss": 1.4539, "step": 157180 }, { "epoch": 7.18, "learning_rate": 1.4142523685294523e-05, "loss": 1.3787, "step": 157190 }, { "epoch": 7.18, "learning_rate": 1.414023525104124e-05, "loss": 1.3273, "step": 157200 }, { "epoch": 7.18, "learning_rate": 1.4137946816787953e-05, "loss": 1.4391, "step": 157210 }, { "epoch": 7.18, "learning_rate": 1.413565838253467e-05, "loss": 1.3768, "step": 157220 }, { "epoch": 7.18, "learning_rate": 1.4133369948281385e-05, "loss": 1.4022, "step": 157230 }, { "epoch": 7.18, "learning_rate": 1.4131081514028103e-05, "loss": 1.2928, "step": 157240 }, { "epoch": 7.18, "learning_rate": 1.4128793079774818e-05, "loss": 1.3797, "step": 157250 }, { "epoch": 7.18, "learning_rate": 1.4126504645521534e-05, "loss": 1.5228, "step": 157260 }, { "epoch": 7.18, "learning_rate": 1.4124216211268252e-05, "loss": 1.3412, "step": 157270 }, { "epoch": 7.18, "learning_rate": 1.4121927777014968e-05, "loss": 1.3737, "step": 157280 }, { "epoch": 7.18, "learning_rate": 1.4119639342761683e-05, "loss": 1.4483, "step": 157290 }, { "epoch": 7.18, "learning_rate": 1.4117350908508401e-05, "loss": 1.4595, "step": 157300 }, { "epoch": 7.18, "learning_rate": 1.4115062474255113e-05, "loss": 1.3499, "step": 157310 }, { "epoch": 7.18, "learning_rate": 1.4112774040001831e-05, "loss": 1.4625, "step": 157320 }, { "epoch": 7.18, "learning_rate": 1.4110485605748547e-05, "loss": 1.4047, "step": 157330 }, { "epoch": 7.18, "learning_rate": 1.4108197171495263e-05, "loss": 1.3025, "step": 157340 }, { "epoch": 7.19, "learning_rate": 1.410590873724198e-05, "loss": 1.5305, "step": 157350 }, { "epoch": 7.19, "learning_rate": 1.4103620302988696e-05, "loss": 1.3886, "step": 157360 }, { "epoch": 7.19, "learning_rate": 1.4101331868735412e-05, "loss": 1.3427, "step": 157370 }, { "epoch": 7.19, "learning_rate": 1.409904343448213e-05, "loss": 1.3687, "step": 157380 }, { "epoch": 7.19, "learning_rate": 1.4096755000228845e-05, "loss": 1.371, "step": 157390 }, { "epoch": 7.19, "learning_rate": 1.4094466565975561e-05, "loss": 1.5839, "step": 157400 }, { "epoch": 7.19, "learning_rate": 1.4092178131722275e-05, "loss": 1.3014, "step": 157410 }, { "epoch": 7.19, "learning_rate": 1.4089889697468991e-05, "loss": 1.4111, "step": 157420 }, { "epoch": 7.19, "learning_rate": 1.4087601263215708e-05, "loss": 1.5407, "step": 157430 }, { "epoch": 7.19, "learning_rate": 1.4085312828962424e-05, "loss": 1.3324, "step": 157440 }, { "epoch": 7.19, "learning_rate": 1.408302439470914e-05, "loss": 1.3661, "step": 157450 }, { "epoch": 7.19, "learning_rate": 1.4080735960455858e-05, "loss": 1.4149, "step": 157460 }, { "epoch": 7.19, "learning_rate": 1.4078447526202573e-05, "loss": 1.4897, "step": 157470 }, { "epoch": 7.19, "learning_rate": 1.407615909194929e-05, "loss": 1.5907, "step": 157480 }, { "epoch": 7.19, "learning_rate": 1.4073870657696007e-05, "loss": 1.5812, "step": 157490 }, { "epoch": 7.19, "learning_rate": 1.4071582223442723e-05, "loss": 1.3087, "step": 157500 }, { "epoch": 7.19, "learning_rate": 1.4069293789189437e-05, "loss": 1.3139, "step": 157510 }, { "epoch": 7.19, "learning_rate": 1.4067005354936153e-05, "loss": 1.3756, "step": 157520 }, { "epoch": 7.19, "learning_rate": 1.4064716920682868e-05, "loss": 1.3361, "step": 157530 }, { "epoch": 7.19, "learning_rate": 1.4062428486429586e-05, "loss": 1.5273, "step": 157540 }, { "epoch": 7.19, "learning_rate": 1.4060140052176302e-05, "loss": 1.4173, "step": 157550 }, { "epoch": 7.19, "learning_rate": 1.4057851617923018e-05, "loss": 1.4742, "step": 157560 }, { "epoch": 7.2, "learning_rate": 1.4055563183669735e-05, "loss": 1.3638, "step": 157570 }, { "epoch": 7.2, "learning_rate": 1.4053274749416451e-05, "loss": 1.3089, "step": 157580 }, { "epoch": 7.2, "learning_rate": 1.4050986315163167e-05, "loss": 1.3628, "step": 157590 }, { "epoch": 7.2, "learning_rate": 1.4048697880909884e-05, "loss": 1.3862, "step": 157600 }, { "epoch": 7.2, "learning_rate": 1.4046409446656597e-05, "loss": 1.378, "step": 157610 }, { "epoch": 7.2, "learning_rate": 1.4044121012403314e-05, "loss": 1.3551, "step": 157620 }, { "epoch": 7.2, "learning_rate": 1.404183257815003e-05, "loss": 1.2107, "step": 157630 }, { "epoch": 7.2, "learning_rate": 1.4039544143896746e-05, "loss": 1.3478, "step": 157640 }, { "epoch": 7.2, "learning_rate": 1.4037255709643463e-05, "loss": 1.3923, "step": 157650 }, { "epoch": 7.2, "learning_rate": 1.403496727539018e-05, "loss": 1.3255, "step": 157660 }, { "epoch": 7.2, "learning_rate": 1.4032678841136895e-05, "loss": 1.3176, "step": 157670 }, { "epoch": 7.2, "learning_rate": 1.4030390406883611e-05, "loss": 1.4785, "step": 157680 }, { "epoch": 7.2, "learning_rate": 1.4028101972630328e-05, "loss": 1.3188, "step": 157690 }, { "epoch": 7.2, "learning_rate": 1.4025813538377044e-05, "loss": 1.3775, "step": 157700 }, { "epoch": 7.2, "learning_rate": 1.4023525104123758e-05, "loss": 1.3021, "step": 157710 }, { "epoch": 7.2, "learning_rate": 1.4021236669870474e-05, "loss": 1.3858, "step": 157720 }, { "epoch": 7.2, "learning_rate": 1.401894823561719e-05, "loss": 1.2934, "step": 157730 }, { "epoch": 7.2, "learning_rate": 1.4016659801363908e-05, "loss": 1.377, "step": 157740 }, { "epoch": 7.2, "learning_rate": 1.4014371367110623e-05, "loss": 1.3282, "step": 157750 }, { "epoch": 7.2, "learning_rate": 1.401208293285734e-05, "loss": 1.4578, "step": 157760 }, { "epoch": 7.2, "learning_rate": 1.4009794498604057e-05, "loss": 1.4212, "step": 157770 }, { "epoch": 7.2, "learning_rate": 1.4007506064350773e-05, "loss": 1.3684, "step": 157780 }, { "epoch": 7.21, "learning_rate": 1.4005217630097488e-05, "loss": 1.4182, "step": 157790 }, { "epoch": 7.21, "learning_rate": 1.4002929195844203e-05, "loss": 1.5122, "step": 157800 }, { "epoch": 7.21, "learning_rate": 1.4000640761590918e-05, "loss": 1.5008, "step": 157810 }, { "epoch": 7.21, "learning_rate": 1.3998352327337636e-05, "loss": 1.3109, "step": 157820 }, { "epoch": 7.21, "learning_rate": 1.3996063893084352e-05, "loss": 1.3864, "step": 157830 }, { "epoch": 7.21, "learning_rate": 1.3993775458831068e-05, "loss": 1.3148, "step": 157840 }, { "epoch": 7.21, "learning_rate": 1.3991487024577785e-05, "loss": 1.4492, "step": 157850 }, { "epoch": 7.21, "learning_rate": 1.3989198590324501e-05, "loss": 1.5216, "step": 157860 }, { "epoch": 7.21, "learning_rate": 1.3986910156071217e-05, "loss": 1.4903, "step": 157870 }, { "epoch": 7.21, "learning_rate": 1.3984621721817934e-05, "loss": 1.2547, "step": 157880 }, { "epoch": 7.21, "learning_rate": 1.398233328756465e-05, "loss": 1.3987, "step": 157890 }, { "epoch": 7.21, "learning_rate": 1.3980044853311364e-05, "loss": 1.2512, "step": 157900 }, { "epoch": 7.21, "learning_rate": 1.397775641905808e-05, "loss": 1.3273, "step": 157910 }, { "epoch": 7.21, "learning_rate": 1.3975467984804796e-05, "loss": 1.5282, "step": 157920 }, { "epoch": 7.21, "learning_rate": 1.3973179550551513e-05, "loss": 1.4249, "step": 157930 }, { "epoch": 7.21, "learning_rate": 1.397089111629823e-05, "loss": 1.4717, "step": 157940 }, { "epoch": 7.21, "learning_rate": 1.3968602682044945e-05, "loss": 1.5294, "step": 157950 }, { "epoch": 7.21, "learning_rate": 1.3966314247791663e-05, "loss": 1.5322, "step": 157960 }, { "epoch": 7.21, "learning_rate": 1.3964025813538378e-05, "loss": 1.4368, "step": 157970 }, { "epoch": 7.21, "learning_rate": 1.3961737379285094e-05, "loss": 1.5355, "step": 157980 }, { "epoch": 7.21, "learning_rate": 1.3959448945031812e-05, "loss": 1.2534, "step": 157990 }, { "epoch": 7.21, "learning_rate": 1.3957160510778524e-05, "loss": 1.4964, "step": 158000 }, { "epoch": 7.22, "learning_rate": 1.3954872076525242e-05, "loss": 1.4099, "step": 158010 }, { "epoch": 7.22, "learning_rate": 1.3952583642271957e-05, "loss": 1.4117, "step": 158020 }, { "epoch": 7.22, "learning_rate": 1.3950295208018673e-05, "loss": 1.5264, "step": 158030 }, { "epoch": 7.22, "learning_rate": 1.3948006773765391e-05, "loss": 1.4304, "step": 158040 }, { "epoch": 7.22, "learning_rate": 1.3945718339512107e-05, "loss": 1.3819, "step": 158050 }, { "epoch": 7.22, "learning_rate": 1.3943429905258823e-05, "loss": 1.4378, "step": 158060 }, { "epoch": 7.22, "learning_rate": 1.394114147100554e-05, "loss": 1.4461, "step": 158070 }, { "epoch": 7.22, "learning_rate": 1.3938853036752256e-05, "loss": 1.4501, "step": 158080 }, { "epoch": 7.22, "learning_rate": 1.3936564602498972e-05, "loss": 1.4423, "step": 158090 }, { "epoch": 7.22, "learning_rate": 1.3934276168245686e-05, "loss": 1.4745, "step": 158100 }, { "epoch": 7.22, "learning_rate": 1.3931987733992402e-05, "loss": 1.3876, "step": 158110 }, { "epoch": 7.22, "learning_rate": 1.392969929973912e-05, "loss": 1.3514, "step": 158120 }, { "epoch": 7.22, "learning_rate": 1.3927410865485835e-05, "loss": 1.2697, "step": 158130 }, { "epoch": 7.22, "learning_rate": 1.392512243123255e-05, "loss": 1.4978, "step": 158140 }, { "epoch": 7.22, "learning_rate": 1.3922833996979268e-05, "loss": 1.391, "step": 158150 }, { "epoch": 7.22, "learning_rate": 1.3920545562725984e-05, "loss": 1.3703, "step": 158160 }, { "epoch": 7.22, "learning_rate": 1.39182571284727e-05, "loss": 1.3554, "step": 158170 }, { "epoch": 7.22, "learning_rate": 1.3915968694219418e-05, "loss": 1.4196, "step": 158180 }, { "epoch": 7.22, "learning_rate": 1.3913680259966133e-05, "loss": 1.3566, "step": 158190 }, { "epoch": 7.22, "learning_rate": 1.3911391825712847e-05, "loss": 1.4714, "step": 158200 }, { "epoch": 7.22, "learning_rate": 1.3909103391459563e-05, "loss": 1.316, "step": 158210 }, { "epoch": 7.22, "learning_rate": 1.3906814957206279e-05, "loss": 1.4023, "step": 158220 }, { "epoch": 7.23, "learning_rate": 1.3904526522952997e-05, "loss": 1.3148, "step": 158230 }, { "epoch": 7.23, "learning_rate": 1.3902238088699712e-05, "loss": 1.3998, "step": 158240 }, { "epoch": 7.23, "learning_rate": 1.3899949654446428e-05, "loss": 1.4446, "step": 158250 }, { "epoch": 7.23, "learning_rate": 1.3897661220193144e-05, "loss": 1.2233, "step": 158260 }, { "epoch": 7.23, "learning_rate": 1.3895372785939862e-05, "loss": 1.339, "step": 158270 }, { "epoch": 7.23, "learning_rate": 1.3893084351686577e-05, "loss": 1.3568, "step": 158280 }, { "epoch": 7.23, "learning_rate": 1.3890795917433293e-05, "loss": 1.4585, "step": 158290 }, { "epoch": 7.23, "learning_rate": 1.3888507483180007e-05, "loss": 1.3643, "step": 158300 }, { "epoch": 7.23, "learning_rate": 1.3886219048926723e-05, "loss": 1.5015, "step": 158310 }, { "epoch": 7.23, "learning_rate": 1.388393061467344e-05, "loss": 1.4547, "step": 158320 }, { "epoch": 7.23, "learning_rate": 1.3881642180420157e-05, "loss": 1.3218, "step": 158330 }, { "epoch": 7.23, "learning_rate": 1.3879353746166872e-05, "loss": 1.4331, "step": 158340 }, { "epoch": 7.23, "learning_rate": 1.387706531191359e-05, "loss": 1.4423, "step": 158350 }, { "epoch": 7.23, "learning_rate": 1.3874776877660306e-05, "loss": 1.5247, "step": 158360 }, { "epoch": 7.23, "learning_rate": 1.3872488443407022e-05, "loss": 1.4156, "step": 158370 }, { "epoch": 7.23, "learning_rate": 1.3870200009153739e-05, "loss": 1.4517, "step": 158380 }, { "epoch": 7.23, "learning_rate": 1.3867911574900455e-05, "loss": 1.3909, "step": 158390 }, { "epoch": 7.23, "learning_rate": 1.3865623140647169e-05, "loss": 1.4215, "step": 158400 }, { "epoch": 7.23, "learning_rate": 1.3863334706393885e-05, "loss": 1.5216, "step": 158410 }, { "epoch": 7.23, "learning_rate": 1.38610462721406e-05, "loss": 1.4586, "step": 158420 }, { "epoch": 7.23, "learning_rate": 1.3858757837887318e-05, "loss": 1.4852, "step": 158430 }, { "epoch": 7.23, "learning_rate": 1.3856469403634034e-05, "loss": 1.4162, "step": 158440 }, { "epoch": 7.24, "learning_rate": 1.385418096938075e-05, "loss": 1.4616, "step": 158450 }, { "epoch": 7.24, "learning_rate": 1.3851892535127467e-05, "loss": 1.4142, "step": 158460 }, { "epoch": 7.24, "learning_rate": 1.3849604100874183e-05, "loss": 1.4293, "step": 158470 }, { "epoch": 7.24, "learning_rate": 1.3847315666620899e-05, "loss": 1.2947, "step": 158480 }, { "epoch": 7.24, "learning_rate": 1.3845027232367617e-05, "loss": 1.4862, "step": 158490 }, { "epoch": 7.24, "learning_rate": 1.3842738798114329e-05, "loss": 1.3362, "step": 158500 }, { "epoch": 7.24, "learning_rate": 1.3840450363861047e-05, "loss": 1.3523, "step": 158510 }, { "epoch": 7.24, "learning_rate": 1.3838161929607762e-05, "loss": 1.4493, "step": 158520 }, { "epoch": 7.24, "learning_rate": 1.3835873495354478e-05, "loss": 1.2281, "step": 158530 }, { "epoch": 7.24, "learning_rate": 1.3833585061101196e-05, "loss": 1.2172, "step": 158540 }, { "epoch": 7.24, "learning_rate": 1.3831296626847912e-05, "loss": 1.3162, "step": 158550 }, { "epoch": 7.24, "learning_rate": 1.3829008192594627e-05, "loss": 1.3964, "step": 158560 }, { "epoch": 7.24, "learning_rate": 1.3826719758341345e-05, "loss": 1.4781, "step": 158570 }, { "epoch": 7.24, "learning_rate": 1.382443132408806e-05, "loss": 1.3244, "step": 158580 }, { "epoch": 7.24, "learning_rate": 1.3822142889834775e-05, "loss": 1.4348, "step": 158590 }, { "epoch": 7.24, "learning_rate": 1.381985445558149e-05, "loss": 1.4484, "step": 158600 }, { "epoch": 7.24, "learning_rate": 1.3817566021328207e-05, "loss": 1.3932, "step": 158610 }, { "epoch": 7.24, "learning_rate": 1.3815277587074924e-05, "loss": 1.35, "step": 158620 }, { "epoch": 7.24, "learning_rate": 1.381298915282164e-05, "loss": 1.3093, "step": 158630 }, { "epoch": 7.24, "learning_rate": 1.3810700718568356e-05, "loss": 1.3947, "step": 158640 }, { "epoch": 7.24, "learning_rate": 1.3808412284315073e-05, "loss": 1.4561, "step": 158650 }, { "epoch": 7.24, "learning_rate": 1.3806123850061789e-05, "loss": 1.397, "step": 158660 }, { "epoch": 7.25, "learning_rate": 1.3803835415808505e-05, "loss": 1.2423, "step": 158670 }, { "epoch": 7.25, "learning_rate": 1.3801546981555222e-05, "loss": 1.2278, "step": 158680 }, { "epoch": 7.25, "learning_rate": 1.3799258547301935e-05, "loss": 1.3316, "step": 158690 }, { "epoch": 7.25, "learning_rate": 1.3796970113048652e-05, "loss": 1.4066, "step": 158700 }, { "epoch": 7.25, "learning_rate": 1.3794681678795368e-05, "loss": 1.2973, "step": 158710 }, { "epoch": 7.25, "learning_rate": 1.3792393244542084e-05, "loss": 1.3761, "step": 158720 }, { "epoch": 7.25, "learning_rate": 1.3790104810288802e-05, "loss": 1.499, "step": 158730 }, { "epoch": 7.25, "learning_rate": 1.3787816376035517e-05, "loss": 1.4487, "step": 158740 }, { "epoch": 7.25, "learning_rate": 1.3785527941782233e-05, "loss": 1.3529, "step": 158750 }, { "epoch": 7.25, "learning_rate": 1.378323950752895e-05, "loss": 1.341, "step": 158760 }, { "epoch": 7.25, "learning_rate": 1.3780951073275667e-05, "loss": 1.3085, "step": 158770 }, { "epoch": 7.25, "learning_rate": 1.3778662639022382e-05, "loss": 1.3623, "step": 158780 }, { "epoch": 7.25, "learning_rate": 1.3776374204769097e-05, "loss": 1.3574, "step": 158790 }, { "epoch": 7.25, "learning_rate": 1.3774085770515812e-05, "loss": 1.3325, "step": 158800 }, { "epoch": 7.25, "learning_rate": 1.377179733626253e-05, "loss": 1.272, "step": 158810 }, { "epoch": 7.25, "learning_rate": 1.3769508902009246e-05, "loss": 1.4293, "step": 158820 }, { "epoch": 7.25, "learning_rate": 1.3767220467755962e-05, "loss": 1.2375, "step": 158830 }, { "epoch": 7.25, "learning_rate": 1.3764932033502679e-05, "loss": 1.2276, "step": 158840 }, { "epoch": 7.25, "learning_rate": 1.3762643599249395e-05, "loss": 1.3359, "step": 158850 }, { "epoch": 7.25, "learning_rate": 1.376035516499611e-05, "loss": 1.3427, "step": 158860 }, { "epoch": 7.25, "learning_rate": 1.3758066730742827e-05, "loss": 1.4157, "step": 158870 }, { "epoch": 7.25, "learning_rate": 1.3755778296489544e-05, "loss": 1.3835, "step": 158880 }, { "epoch": 7.26, "learning_rate": 1.3753489862236257e-05, "loss": 1.3313, "step": 158890 }, { "epoch": 7.26, "learning_rate": 1.3751201427982974e-05, "loss": 1.2887, "step": 158900 }, { "epoch": 7.26, "learning_rate": 1.374891299372969e-05, "loss": 1.3645, "step": 158910 }, { "epoch": 7.26, "learning_rate": 1.3746624559476406e-05, "loss": 1.3767, "step": 158920 }, { "epoch": 7.26, "learning_rate": 1.3744336125223123e-05, "loss": 1.4032, "step": 158930 }, { "epoch": 7.26, "learning_rate": 1.3742047690969839e-05, "loss": 1.3127, "step": 158940 }, { "epoch": 7.26, "learning_rate": 1.3739759256716555e-05, "loss": 1.5032, "step": 158950 }, { "epoch": 7.26, "learning_rate": 1.3737470822463272e-05, "loss": 1.3221, "step": 158960 }, { "epoch": 7.26, "learning_rate": 1.3735182388209988e-05, "loss": 1.3826, "step": 158970 }, { "epoch": 7.26, "learning_rate": 1.3732893953956704e-05, "loss": 1.3092, "step": 158980 }, { "epoch": 7.26, "learning_rate": 1.3730605519703418e-05, "loss": 1.3381, "step": 158990 }, { "epoch": 7.26, "learning_rate": 1.3728317085450134e-05, "loss": 1.4759, "step": 159000 }, { "epoch": 7.26, "learning_rate": 1.3726028651196852e-05, "loss": 1.3223, "step": 159010 }, { "epoch": 7.26, "learning_rate": 1.3723740216943567e-05, "loss": 1.3229, "step": 159020 }, { "epoch": 7.26, "learning_rate": 1.3721451782690283e-05, "loss": 1.3619, "step": 159030 }, { "epoch": 7.26, "learning_rate": 1.3719163348437e-05, "loss": 1.267, "step": 159040 }, { "epoch": 7.26, "learning_rate": 1.3716874914183717e-05, "loss": 1.4005, "step": 159050 }, { "epoch": 7.26, "learning_rate": 1.3714586479930432e-05, "loss": 1.3387, "step": 159060 }, { "epoch": 7.26, "learning_rate": 1.371229804567715e-05, "loss": 1.4706, "step": 159070 }, { "epoch": 7.26, "learning_rate": 1.3710009611423866e-05, "loss": 1.4757, "step": 159080 }, { "epoch": 7.26, "learning_rate": 1.370772117717058e-05, "loss": 1.3864, "step": 159090 }, { "epoch": 7.26, "learning_rate": 1.3705432742917296e-05, "loss": 1.3277, "step": 159100 }, { "epoch": 7.27, "learning_rate": 1.3703144308664012e-05, "loss": 1.4155, "step": 159110 }, { "epoch": 7.27, "learning_rate": 1.3700855874410729e-05, "loss": 1.4871, "step": 159120 }, { "epoch": 7.27, "learning_rate": 1.3698567440157445e-05, "loss": 1.483, "step": 159130 }, { "epoch": 7.27, "learning_rate": 1.369627900590416e-05, "loss": 1.4444, "step": 159140 }, { "epoch": 7.27, "learning_rate": 1.3693990571650878e-05, "loss": 1.3841, "step": 159150 }, { "epoch": 7.27, "learning_rate": 1.3691702137397594e-05, "loss": 1.4933, "step": 159160 }, { "epoch": 7.27, "learning_rate": 1.368941370314431e-05, "loss": 1.3139, "step": 159170 }, { "epoch": 7.27, "learning_rate": 1.3687125268891027e-05, "loss": 1.3558, "step": 159180 }, { "epoch": 7.27, "learning_rate": 1.368483683463774e-05, "loss": 1.4203, "step": 159190 }, { "epoch": 7.27, "learning_rate": 1.3682548400384457e-05, "loss": 1.5131, "step": 159200 }, { "epoch": 7.27, "learning_rate": 1.3680259966131173e-05, "loss": 1.4459, "step": 159210 }, { "epoch": 7.27, "learning_rate": 1.3677971531877889e-05, "loss": 1.4709, "step": 159220 }, { "epoch": 7.27, "learning_rate": 1.3675683097624607e-05, "loss": 1.3544, "step": 159230 }, { "epoch": 7.27, "learning_rate": 1.3673394663371322e-05, "loss": 1.4399, "step": 159240 }, { "epoch": 7.27, "learning_rate": 1.3671106229118038e-05, "loss": 1.3669, "step": 159250 }, { "epoch": 7.27, "learning_rate": 1.3668817794864756e-05, "loss": 1.3265, "step": 159260 }, { "epoch": 7.27, "learning_rate": 1.3666529360611472e-05, "loss": 1.1898, "step": 159270 }, { "epoch": 7.27, "learning_rate": 1.3664240926358187e-05, "loss": 1.505, "step": 159280 }, { "epoch": 7.27, "learning_rate": 1.3661952492104901e-05, "loss": 1.5805, "step": 159290 }, { "epoch": 7.27, "learning_rate": 1.3659664057851617e-05, "loss": 1.2777, "step": 159300 }, { "epoch": 7.27, "learning_rate": 1.3657375623598335e-05, "loss": 1.5158, "step": 159310 }, { "epoch": 7.27, "learning_rate": 1.365508718934505e-05, "loss": 1.4278, "step": 159320 }, { "epoch": 7.28, "learning_rate": 1.3652798755091766e-05, "loss": 1.3957, "step": 159330 }, { "epoch": 7.28, "learning_rate": 1.3650510320838484e-05, "loss": 1.2587, "step": 159340 }, { "epoch": 7.28, "learning_rate": 1.36482218865852e-05, "loss": 1.3907, "step": 159350 }, { "epoch": 7.28, "learning_rate": 1.3645933452331916e-05, "loss": 1.3099, "step": 159360 }, { "epoch": 7.28, "learning_rate": 1.3643645018078633e-05, "loss": 1.2597, "step": 159370 }, { "epoch": 7.28, "learning_rate": 1.3641356583825346e-05, "loss": 1.4686, "step": 159380 }, { "epoch": 7.28, "learning_rate": 1.3639068149572063e-05, "loss": 1.3269, "step": 159390 }, { "epoch": 7.28, "learning_rate": 1.3636779715318779e-05, "loss": 1.2933, "step": 159400 }, { "epoch": 7.28, "learning_rate": 1.3634491281065495e-05, "loss": 1.5559, "step": 159410 }, { "epoch": 7.28, "learning_rate": 1.3632202846812212e-05, "loss": 1.3856, "step": 159420 }, { "epoch": 7.28, "learning_rate": 1.3629914412558928e-05, "loss": 1.417, "step": 159430 }, { "epoch": 7.28, "learning_rate": 1.3627625978305644e-05, "loss": 1.5109, "step": 159440 }, { "epoch": 7.28, "learning_rate": 1.362533754405236e-05, "loss": 1.2076, "step": 159450 }, { "epoch": 7.28, "learning_rate": 1.3623049109799077e-05, "loss": 1.265, "step": 159460 }, { "epoch": 7.28, "learning_rate": 1.3620760675545793e-05, "loss": 1.4029, "step": 159470 }, { "epoch": 7.28, "learning_rate": 1.3618472241292507e-05, "loss": 1.3729, "step": 159480 }, { "epoch": 7.28, "learning_rate": 1.3616183807039223e-05, "loss": 1.4288, "step": 159490 }, { "epoch": 7.28, "learning_rate": 1.3613895372785939e-05, "loss": 1.4827, "step": 159500 }, { "epoch": 7.28, "learning_rate": 1.3611606938532656e-05, "loss": 1.5185, "step": 159510 }, { "epoch": 7.28, "learning_rate": 1.3609318504279372e-05, "loss": 1.4339, "step": 159520 }, { "epoch": 7.28, "learning_rate": 1.3607030070026088e-05, "loss": 1.4548, "step": 159530 }, { "epoch": 7.29, "learning_rate": 1.3604741635772806e-05, "loss": 1.425, "step": 159540 }, { "epoch": 7.29, "learning_rate": 1.3602453201519521e-05, "loss": 1.3653, "step": 159550 }, { "epoch": 7.29, "learning_rate": 1.3600164767266237e-05, "loss": 1.4824, "step": 159560 }, { "epoch": 7.29, "learning_rate": 1.3597876333012955e-05, "loss": 1.3652, "step": 159570 }, { "epoch": 7.29, "learning_rate": 1.3595587898759667e-05, "loss": 1.2046, "step": 159580 }, { "epoch": 7.29, "learning_rate": 1.3593299464506385e-05, "loss": 1.3181, "step": 159590 }, { "epoch": 7.29, "learning_rate": 1.35910110302531e-05, "loss": 1.4602, "step": 159600 }, { "epoch": 7.29, "learning_rate": 1.3588722595999816e-05, "loss": 1.3364, "step": 159610 }, { "epoch": 7.29, "learning_rate": 1.3586434161746534e-05, "loss": 1.2829, "step": 159620 }, { "epoch": 7.29, "learning_rate": 1.358414572749325e-05, "loss": 1.3071, "step": 159630 }, { "epoch": 7.29, "learning_rate": 1.3581857293239966e-05, "loss": 1.3925, "step": 159640 }, { "epoch": 7.29, "learning_rate": 1.3579568858986683e-05, "loss": 1.3701, "step": 159650 }, { "epoch": 7.29, "learning_rate": 1.3577280424733399e-05, "loss": 1.3567, "step": 159660 }, { "epoch": 7.29, "learning_rate": 1.3574991990480115e-05, "loss": 1.4688, "step": 159670 }, { "epoch": 7.29, "learning_rate": 1.3572703556226829e-05, "loss": 1.3478, "step": 159680 }, { "epoch": 7.29, "learning_rate": 1.3570415121973545e-05, "loss": 1.402, "step": 159690 }, { "epoch": 7.29, "learning_rate": 1.3568126687720262e-05, "loss": 1.4729, "step": 159700 }, { "epoch": 7.29, "learning_rate": 1.3565838253466978e-05, "loss": 1.5824, "step": 159710 }, { "epoch": 7.29, "learning_rate": 1.3563549819213694e-05, "loss": 1.3056, "step": 159720 }, { "epoch": 7.29, "learning_rate": 1.3561261384960411e-05, "loss": 1.4725, "step": 159730 }, { "epoch": 7.29, "learning_rate": 1.3558972950707127e-05, "loss": 1.4216, "step": 159740 }, { "epoch": 7.29, "learning_rate": 1.3556684516453843e-05, "loss": 1.3184, "step": 159750 }, { "epoch": 7.3, "learning_rate": 1.355439608220056e-05, "loss": 1.6112, "step": 159760 }, { "epoch": 7.3, "learning_rate": 1.3552107647947276e-05, "loss": 1.3972, "step": 159770 }, { "epoch": 7.3, "learning_rate": 1.354981921369399e-05, "loss": 1.4616, "step": 159780 }, { "epoch": 7.3, "learning_rate": 1.3547530779440706e-05, "loss": 1.3239, "step": 159790 }, { "epoch": 7.3, "learning_rate": 1.3545242345187422e-05, "loss": 1.4747, "step": 159800 }, { "epoch": 7.3, "learning_rate": 1.354295391093414e-05, "loss": 1.3749, "step": 159810 }, { "epoch": 7.3, "learning_rate": 1.3540665476680856e-05, "loss": 1.3656, "step": 159820 }, { "epoch": 7.3, "learning_rate": 1.3538377042427571e-05, "loss": 1.4028, "step": 159830 }, { "epoch": 7.3, "learning_rate": 1.3536088608174289e-05, "loss": 1.3913, "step": 159840 }, { "epoch": 7.3, "learning_rate": 1.3533800173921005e-05, "loss": 1.276, "step": 159850 }, { "epoch": 7.3, "learning_rate": 1.353151173966772e-05, "loss": 1.4921, "step": 159860 }, { "epoch": 7.3, "learning_rate": 1.3529223305414438e-05, "loss": 1.4822, "step": 159870 }, { "epoch": 7.3, "learning_rate": 1.352693487116115e-05, "loss": 1.3616, "step": 159880 }, { "epoch": 7.3, "learning_rate": 1.3524646436907868e-05, "loss": 1.3648, "step": 159890 }, { "epoch": 7.3, "learning_rate": 1.3522358002654584e-05, "loss": 1.2448, "step": 159900 }, { "epoch": 7.3, "learning_rate": 1.35200695684013e-05, "loss": 1.2919, "step": 159910 }, { "epoch": 7.3, "learning_rate": 1.3517781134148017e-05, "loss": 1.4538, "step": 159920 }, { "epoch": 7.3, "learning_rate": 1.3515492699894733e-05, "loss": 1.4322, "step": 159930 }, { "epoch": 7.3, "learning_rate": 1.3513204265641449e-05, "loss": 1.3325, "step": 159940 }, { "epoch": 7.3, "learning_rate": 1.3510915831388166e-05, "loss": 1.4887, "step": 159950 }, { "epoch": 7.3, "learning_rate": 1.3508627397134882e-05, "loss": 1.3377, "step": 159960 }, { "epoch": 7.3, "learning_rate": 1.3506338962881598e-05, "loss": 1.3936, "step": 159970 }, { "epoch": 7.31, "learning_rate": 1.3504050528628312e-05, "loss": 1.4441, "step": 159980 }, { "epoch": 7.31, "learning_rate": 1.3501762094375028e-05, "loss": 1.486, "step": 159990 }, { "epoch": 7.31, "learning_rate": 1.3499473660121746e-05, "loss": 1.4035, "step": 160000 }, { "epoch": 7.31, "learning_rate": 1.3497185225868461e-05, "loss": 1.5144, "step": 160010 }, { "epoch": 7.31, "learning_rate": 1.3494896791615177e-05, "loss": 1.3635, "step": 160020 }, { "epoch": 7.31, "learning_rate": 1.3492608357361893e-05, "loss": 1.3753, "step": 160030 }, { "epoch": 7.31, "learning_rate": 1.349031992310861e-05, "loss": 1.344, "step": 160040 }, { "epoch": 7.31, "learning_rate": 1.3488031488855326e-05, "loss": 1.3848, "step": 160050 }, { "epoch": 7.31, "learning_rate": 1.3485743054602042e-05, "loss": 1.4015, "step": 160060 }, { "epoch": 7.31, "learning_rate": 1.348345462034876e-05, "loss": 1.4111, "step": 160070 }, { "epoch": 7.31, "learning_rate": 1.3481166186095472e-05, "loss": 1.2609, "step": 160080 }, { "epoch": 7.31, "learning_rate": 1.347887775184219e-05, "loss": 1.4395, "step": 160090 }, { "epoch": 7.31, "learning_rate": 1.3476589317588906e-05, "loss": 1.4614, "step": 160100 }, { "epoch": 7.31, "learning_rate": 1.3474300883335621e-05, "loss": 1.3182, "step": 160110 }, { "epoch": 7.31, "learning_rate": 1.3472012449082339e-05, "loss": 1.4897, "step": 160120 }, { "epoch": 7.31, "learning_rate": 1.3469724014829055e-05, "loss": 1.278, "step": 160130 }, { "epoch": 7.31, "learning_rate": 1.346743558057577e-05, "loss": 1.4118, "step": 160140 }, { "epoch": 7.31, "learning_rate": 1.3465147146322488e-05, "loss": 1.4769, "step": 160150 }, { "epoch": 7.31, "learning_rate": 1.3462858712069204e-05, "loss": 1.3861, "step": 160160 }, { "epoch": 7.31, "learning_rate": 1.3460570277815918e-05, "loss": 1.4174, "step": 160170 }, { "epoch": 7.31, "learning_rate": 1.3458281843562634e-05, "loss": 1.3863, "step": 160180 }, { "epoch": 7.31, "learning_rate": 1.345599340930935e-05, "loss": 1.351, "step": 160190 }, { "epoch": 7.32, "learning_rate": 1.3453704975056067e-05, "loss": 1.302, "step": 160200 }, { "epoch": 7.32, "learning_rate": 1.3451416540802783e-05, "loss": 1.5685, "step": 160210 }, { "epoch": 7.32, "learning_rate": 1.3449128106549499e-05, "loss": 1.4982, "step": 160220 }, { "epoch": 7.32, "learning_rate": 1.3446839672296216e-05, "loss": 1.3731, "step": 160230 }, { "epoch": 7.32, "learning_rate": 1.3444551238042932e-05, "loss": 1.4417, "step": 160240 }, { "epoch": 7.32, "learning_rate": 1.3442262803789648e-05, "loss": 1.3564, "step": 160250 }, { "epoch": 7.32, "learning_rate": 1.3439974369536366e-05, "loss": 1.3565, "step": 160260 }, { "epoch": 7.32, "learning_rate": 1.3437685935283078e-05, "loss": 1.3093, "step": 160270 }, { "epoch": 7.32, "learning_rate": 1.3435397501029796e-05, "loss": 1.3782, "step": 160280 }, { "epoch": 7.32, "learning_rate": 1.3433109066776511e-05, "loss": 1.4414, "step": 160290 }, { "epoch": 7.32, "learning_rate": 1.3430820632523227e-05, "loss": 1.5333, "step": 160300 }, { "epoch": 7.32, "learning_rate": 1.3428532198269945e-05, "loss": 1.4509, "step": 160310 }, { "epoch": 7.32, "learning_rate": 1.342624376401666e-05, "loss": 1.453, "step": 160320 }, { "epoch": 7.32, "learning_rate": 1.3423955329763376e-05, "loss": 1.3609, "step": 160330 }, { "epoch": 7.32, "learning_rate": 1.3421666895510094e-05, "loss": 1.3594, "step": 160340 }, { "epoch": 7.32, "learning_rate": 1.341937846125681e-05, "loss": 1.5691, "step": 160350 }, { "epoch": 7.32, "learning_rate": 1.3417090027003526e-05, "loss": 1.4951, "step": 160360 }, { "epoch": 7.32, "learning_rate": 1.341480159275024e-05, "loss": 1.3986, "step": 160370 }, { "epoch": 7.32, "learning_rate": 1.3412513158496955e-05, "loss": 1.3825, "step": 160380 }, { "epoch": 7.32, "learning_rate": 1.3410224724243673e-05, "loss": 1.4342, "step": 160390 }, { "epoch": 7.32, "learning_rate": 1.3407936289990389e-05, "loss": 1.2919, "step": 160400 }, { "epoch": 7.32, "learning_rate": 1.3405647855737105e-05, "loss": 1.3668, "step": 160410 }, { "epoch": 7.33, "learning_rate": 1.3403359421483822e-05, "loss": 1.5201, "step": 160420 }, { "epoch": 7.33, "learning_rate": 1.3401070987230538e-05, "loss": 1.3965, "step": 160430 }, { "epoch": 7.33, "learning_rate": 1.3398782552977254e-05, "loss": 1.43, "step": 160440 }, { "epoch": 7.33, "learning_rate": 1.3396494118723971e-05, "loss": 1.2843, "step": 160450 }, { "epoch": 7.33, "learning_rate": 1.3394205684470687e-05, "loss": 1.3932, "step": 160460 }, { "epoch": 7.33, "learning_rate": 1.3391917250217401e-05, "loss": 1.5138, "step": 160470 }, { "epoch": 7.33, "learning_rate": 1.3389628815964117e-05, "loss": 1.3908, "step": 160480 }, { "epoch": 7.33, "learning_rate": 1.3387340381710833e-05, "loss": 1.5522, "step": 160490 }, { "epoch": 7.33, "learning_rate": 1.338505194745755e-05, "loss": 1.4337, "step": 160500 }, { "epoch": 7.33, "learning_rate": 1.3382763513204266e-05, "loss": 1.3295, "step": 160510 }, { "epoch": 7.33, "learning_rate": 1.3380475078950982e-05, "loss": 1.4237, "step": 160520 }, { "epoch": 7.33, "learning_rate": 1.33781866446977e-05, "loss": 1.3206, "step": 160530 }, { "epoch": 7.33, "learning_rate": 1.3375898210444416e-05, "loss": 1.3901, "step": 160540 }, { "epoch": 7.33, "learning_rate": 1.3373609776191131e-05, "loss": 1.3591, "step": 160550 }, { "epoch": 7.33, "learning_rate": 1.3371321341937849e-05, "loss": 1.4206, "step": 160560 }, { "epoch": 7.33, "learning_rate": 1.3369032907684561e-05, "loss": 1.2069, "step": 160570 }, { "epoch": 7.33, "learning_rate": 1.3366744473431279e-05, "loss": 1.4668, "step": 160580 }, { "epoch": 7.33, "learning_rate": 1.3364456039177995e-05, "loss": 1.4218, "step": 160590 }, { "epoch": 7.33, "learning_rate": 1.336216760492471e-05, "loss": 1.2446, "step": 160600 }, { "epoch": 7.33, "learning_rate": 1.3359879170671426e-05, "loss": 1.4138, "step": 160610 }, { "epoch": 7.33, "learning_rate": 1.3357590736418144e-05, "loss": 1.3247, "step": 160620 }, { "epoch": 7.33, "learning_rate": 1.335530230216486e-05, "loss": 1.441, "step": 160630 }, { "epoch": 7.34, "learning_rate": 1.3353013867911575e-05, "loss": 1.4185, "step": 160640 }, { "epoch": 7.34, "learning_rate": 1.3350725433658293e-05, "loss": 1.364, "step": 160650 }, { "epoch": 7.34, "learning_rate": 1.3348436999405009e-05, "loss": 1.4827, "step": 160660 }, { "epoch": 7.34, "learning_rate": 1.3346148565151723e-05, "loss": 1.3055, "step": 160670 }, { "epoch": 7.34, "learning_rate": 1.3343860130898439e-05, "loss": 1.3667, "step": 160680 }, { "epoch": 7.34, "learning_rate": 1.3341571696645155e-05, "loss": 1.3435, "step": 160690 }, { "epoch": 7.34, "learning_rate": 1.3339283262391872e-05, "loss": 1.3012, "step": 160700 }, { "epoch": 7.34, "learning_rate": 1.3336994828138588e-05, "loss": 1.2043, "step": 160710 }, { "epoch": 7.34, "learning_rate": 1.3334706393885304e-05, "loss": 1.2395, "step": 160720 }, { "epoch": 7.34, "learning_rate": 1.3332417959632021e-05, "loss": 1.2677, "step": 160730 }, { "epoch": 7.34, "learning_rate": 1.3330129525378737e-05, "loss": 1.4788, "step": 160740 }, { "epoch": 7.34, "learning_rate": 1.3327841091125453e-05, "loss": 1.5206, "step": 160750 }, { "epoch": 7.34, "learning_rate": 1.332555265687217e-05, "loss": 1.3696, "step": 160760 }, { "epoch": 7.34, "learning_rate": 1.3323264222618883e-05, "loss": 1.3792, "step": 160770 }, { "epoch": 7.34, "learning_rate": 1.33209757883656e-05, "loss": 1.5475, "step": 160780 }, { "epoch": 7.34, "learning_rate": 1.3318687354112316e-05, "loss": 1.4332, "step": 160790 }, { "epoch": 7.34, "learning_rate": 1.3316398919859032e-05, "loss": 1.3195, "step": 160800 }, { "epoch": 7.34, "learning_rate": 1.331411048560575e-05, "loss": 1.4961, "step": 160810 }, { "epoch": 7.34, "learning_rate": 1.3311822051352465e-05, "loss": 1.3241, "step": 160820 }, { "epoch": 7.34, "learning_rate": 1.3309533617099181e-05, "loss": 1.3161, "step": 160830 }, { "epoch": 7.34, "learning_rate": 1.3307245182845899e-05, "loss": 1.4418, "step": 160840 }, { "epoch": 7.34, "learning_rate": 1.3304956748592615e-05, "loss": 1.4699, "step": 160850 }, { "epoch": 7.35, "learning_rate": 1.330266831433933e-05, "loss": 1.3349, "step": 160860 }, { "epoch": 7.35, "learning_rate": 1.3300379880086045e-05, "loss": 1.3732, "step": 160870 }, { "epoch": 7.35, "learning_rate": 1.329809144583276e-05, "loss": 1.3966, "step": 160880 }, { "epoch": 7.35, "learning_rate": 1.3295803011579478e-05, "loss": 1.2873, "step": 160890 }, { "epoch": 7.35, "learning_rate": 1.3293514577326194e-05, "loss": 1.5529, "step": 160900 }, { "epoch": 7.35, "learning_rate": 1.329122614307291e-05, "loss": 1.3569, "step": 160910 }, { "epoch": 7.35, "learning_rate": 1.3288937708819627e-05, "loss": 1.4043, "step": 160920 }, { "epoch": 7.35, "learning_rate": 1.3286649274566343e-05, "loss": 1.2939, "step": 160930 }, { "epoch": 7.35, "learning_rate": 1.3284360840313059e-05, "loss": 1.3421, "step": 160940 }, { "epoch": 7.35, "learning_rate": 1.3282072406059776e-05, "loss": 1.4473, "step": 160950 }, { "epoch": 7.35, "learning_rate": 1.3279783971806489e-05, "loss": 1.3093, "step": 160960 }, { "epoch": 7.35, "learning_rate": 1.3277495537553206e-05, "loss": 1.462, "step": 160970 }, { "epoch": 7.35, "learning_rate": 1.3275207103299922e-05, "loss": 1.4024, "step": 160980 }, { "epoch": 7.35, "learning_rate": 1.3272918669046638e-05, "loss": 1.307, "step": 160990 }, { "epoch": 7.35, "learning_rate": 1.3270630234793355e-05, "loss": 1.3872, "step": 161000 }, { "epoch": 7.35, "learning_rate": 1.3268341800540071e-05, "loss": 1.4502, "step": 161010 }, { "epoch": 7.35, "learning_rate": 1.3266053366286787e-05, "loss": 1.2759, "step": 161020 }, { "epoch": 7.35, "learning_rate": 1.3263764932033505e-05, "loss": 1.4127, "step": 161030 }, { "epoch": 7.35, "learning_rate": 1.326147649778022e-05, "loss": 1.2284, "step": 161040 }, { "epoch": 7.35, "learning_rate": 1.3259188063526936e-05, "loss": 1.404, "step": 161050 }, { "epoch": 7.35, "learning_rate": 1.325689962927365e-05, "loss": 1.3714, "step": 161060 }, { "epoch": 7.35, "learning_rate": 1.3254611195020366e-05, "loss": 1.4022, "step": 161070 }, { "epoch": 7.36, "learning_rate": 1.3252322760767084e-05, "loss": 1.4095, "step": 161080 }, { "epoch": 7.36, "learning_rate": 1.32500343265138e-05, "loss": 1.3976, "step": 161090 }, { "epoch": 7.36, "learning_rate": 1.3247745892260515e-05, "loss": 1.2579, "step": 161100 }, { "epoch": 7.36, "learning_rate": 1.3245457458007233e-05, "loss": 1.3212, "step": 161110 }, { "epoch": 7.36, "learning_rate": 1.3243169023753949e-05, "loss": 1.4677, "step": 161120 }, { "epoch": 7.36, "learning_rate": 1.3240880589500665e-05, "loss": 1.1964, "step": 161130 }, { "epoch": 7.36, "learning_rate": 1.3238592155247382e-05, "loss": 1.3897, "step": 161140 }, { "epoch": 7.36, "learning_rate": 1.3236303720994098e-05, "loss": 1.4345, "step": 161150 }, { "epoch": 7.36, "learning_rate": 1.3234015286740812e-05, "loss": 1.4154, "step": 161160 }, { "epoch": 7.36, "learning_rate": 1.3231726852487528e-05, "loss": 1.2718, "step": 161170 }, { "epoch": 7.36, "learning_rate": 1.3229438418234244e-05, "loss": 1.3309, "step": 161180 }, { "epoch": 7.36, "learning_rate": 1.322714998398096e-05, "loss": 1.3452, "step": 161190 }, { "epoch": 7.36, "learning_rate": 1.3224861549727677e-05, "loss": 1.2769, "step": 161200 }, { "epoch": 7.36, "learning_rate": 1.3222573115474393e-05, "loss": 1.3956, "step": 161210 }, { "epoch": 7.36, "learning_rate": 1.3220284681221109e-05, "loss": 1.2824, "step": 161220 }, { "epoch": 7.36, "learning_rate": 1.3217996246967826e-05, "loss": 1.3587, "step": 161230 }, { "epoch": 7.36, "learning_rate": 1.3215707812714542e-05, "loss": 1.5202, "step": 161240 }, { "epoch": 7.36, "learning_rate": 1.3213419378461258e-05, "loss": 1.5974, "step": 161250 }, { "epoch": 7.36, "learning_rate": 1.3211130944207972e-05, "loss": 1.4731, "step": 161260 }, { "epoch": 7.36, "learning_rate": 1.3208842509954688e-05, "loss": 1.3988, "step": 161270 }, { "epoch": 7.36, "learning_rate": 1.3206554075701405e-05, "loss": 1.3802, "step": 161280 }, { "epoch": 7.36, "learning_rate": 1.3204265641448121e-05, "loss": 1.2608, "step": 161290 }, { "epoch": 7.37, "learning_rate": 1.3201977207194837e-05, "loss": 1.4712, "step": 161300 }, { "epoch": 7.37, "learning_rate": 1.3199688772941555e-05, "loss": 1.4463, "step": 161310 }, { "epoch": 7.37, "learning_rate": 1.319740033868827e-05, "loss": 1.3798, "step": 161320 }, { "epoch": 7.37, "learning_rate": 1.3195111904434986e-05, "loss": 1.3043, "step": 161330 }, { "epoch": 7.37, "learning_rate": 1.3192823470181704e-05, "loss": 1.413, "step": 161340 }, { "epoch": 7.37, "learning_rate": 1.319053503592842e-05, "loss": 1.3625, "step": 161350 }, { "epoch": 7.37, "learning_rate": 1.3188246601675134e-05, "loss": 1.4525, "step": 161360 }, { "epoch": 7.37, "learning_rate": 1.318595816742185e-05, "loss": 1.4545, "step": 161370 }, { "epoch": 7.37, "learning_rate": 1.3183669733168565e-05, "loss": 1.2825, "step": 161380 }, { "epoch": 7.37, "learning_rate": 1.3181381298915283e-05, "loss": 1.281, "step": 161390 }, { "epoch": 7.37, "learning_rate": 1.3179092864661999e-05, "loss": 1.2909, "step": 161400 }, { "epoch": 7.37, "learning_rate": 1.3176804430408715e-05, "loss": 1.3904, "step": 161410 }, { "epoch": 7.37, "learning_rate": 1.3174515996155432e-05, "loss": 1.2524, "step": 161420 }, { "epoch": 7.37, "learning_rate": 1.3172227561902148e-05, "loss": 1.3242, "step": 161430 }, { "epoch": 7.37, "learning_rate": 1.3169939127648864e-05, "loss": 1.3075, "step": 161440 }, { "epoch": 7.37, "learning_rate": 1.3167650693395581e-05, "loss": 1.3666, "step": 161450 }, { "epoch": 7.37, "learning_rate": 1.3165362259142294e-05, "loss": 1.3065, "step": 161460 }, { "epoch": 7.37, "learning_rate": 1.3163073824889011e-05, "loss": 1.332, "step": 161470 }, { "epoch": 7.37, "learning_rate": 1.3160785390635727e-05, "loss": 1.5284, "step": 161480 }, { "epoch": 7.37, "learning_rate": 1.3158496956382443e-05, "loss": 1.4032, "step": 161490 }, { "epoch": 7.37, "learning_rate": 1.315620852212916e-05, "loss": 1.5225, "step": 161500 }, { "epoch": 7.37, "learning_rate": 1.3153920087875876e-05, "loss": 1.4552, "step": 161510 }, { "epoch": 7.38, "learning_rate": 1.3151631653622592e-05, "loss": 1.3831, "step": 161520 }, { "epoch": 7.38, "learning_rate": 1.314934321936931e-05, "loss": 1.4808, "step": 161530 }, { "epoch": 7.38, "learning_rate": 1.3147054785116025e-05, "loss": 1.376, "step": 161540 }, { "epoch": 7.38, "learning_rate": 1.3144766350862741e-05, "loss": 1.4378, "step": 161550 }, { "epoch": 7.38, "learning_rate": 1.3142477916609455e-05, "loss": 1.2318, "step": 161560 }, { "epoch": 7.38, "learning_rate": 1.3140189482356171e-05, "loss": 1.3572, "step": 161570 }, { "epoch": 7.38, "learning_rate": 1.3137901048102889e-05, "loss": 1.3585, "step": 161580 }, { "epoch": 7.38, "learning_rate": 1.3135612613849605e-05, "loss": 1.3151, "step": 161590 }, { "epoch": 7.38, "learning_rate": 1.313332417959632e-05, "loss": 1.2479, "step": 161600 }, { "epoch": 7.38, "learning_rate": 1.3131035745343038e-05, "loss": 1.3609, "step": 161610 }, { "epoch": 7.38, "learning_rate": 1.3128747311089754e-05, "loss": 1.4885, "step": 161620 }, { "epoch": 7.38, "learning_rate": 1.312645887683647e-05, "loss": 1.265, "step": 161630 }, { "epoch": 7.38, "learning_rate": 1.3124170442583187e-05, "loss": 1.4369, "step": 161640 }, { "epoch": 7.38, "learning_rate": 1.3121882008329903e-05, "loss": 1.4493, "step": 161650 }, { "epoch": 7.38, "learning_rate": 1.3119593574076617e-05, "loss": 1.2758, "step": 161660 }, { "epoch": 7.38, "learning_rate": 1.3117305139823333e-05, "loss": 1.3469, "step": 161670 }, { "epoch": 7.38, "learning_rate": 1.3115016705570049e-05, "loss": 1.2357, "step": 161680 }, { "epoch": 7.38, "learning_rate": 1.3112728271316766e-05, "loss": 1.4605, "step": 161690 }, { "epoch": 7.38, "learning_rate": 1.3110439837063482e-05, "loss": 1.3323, "step": 161700 }, { "epoch": 7.38, "learning_rate": 1.3108151402810198e-05, "loss": 1.3246, "step": 161710 }, { "epoch": 7.38, "learning_rate": 1.3105862968556915e-05, "loss": 1.3789, "step": 161720 }, { "epoch": 7.39, "learning_rate": 1.3103574534303631e-05, "loss": 1.4362, "step": 161730 }, { "epoch": 7.39, "learning_rate": 1.3101286100050347e-05, "loss": 1.4282, "step": 161740 }, { "epoch": 7.39, "learning_rate": 1.3098997665797061e-05, "loss": 1.5112, "step": 161750 }, { "epoch": 7.39, "learning_rate": 1.3096709231543777e-05, "loss": 1.3181, "step": 161760 }, { "epoch": 7.39, "learning_rate": 1.3094420797290493e-05, "loss": 1.5135, "step": 161770 }, { "epoch": 7.39, "learning_rate": 1.309213236303721e-05, "loss": 1.3033, "step": 161780 }, { "epoch": 7.39, "learning_rate": 1.3089843928783926e-05, "loss": 1.3537, "step": 161790 }, { "epoch": 7.39, "learning_rate": 1.3087555494530642e-05, "loss": 1.3609, "step": 161800 }, { "epoch": 7.39, "learning_rate": 1.308526706027736e-05, "loss": 1.4365, "step": 161810 }, { "epoch": 7.39, "learning_rate": 1.3082978626024075e-05, "loss": 1.4267, "step": 161820 }, { "epoch": 7.39, "learning_rate": 1.3080690191770791e-05, "loss": 1.5283, "step": 161830 }, { "epoch": 7.39, "learning_rate": 1.3078401757517509e-05, "loss": 1.4172, "step": 161840 }, { "epoch": 7.39, "learning_rate": 1.3076113323264221e-05, "loss": 1.3192, "step": 161850 }, { "epoch": 7.39, "learning_rate": 1.3073824889010939e-05, "loss": 1.2069, "step": 161860 }, { "epoch": 7.39, "learning_rate": 1.3071536454757654e-05, "loss": 1.4498, "step": 161870 }, { "epoch": 7.39, "learning_rate": 1.306924802050437e-05, "loss": 1.3712, "step": 161880 }, { "epoch": 7.39, "learning_rate": 1.3066959586251088e-05, "loss": 1.422, "step": 161890 }, { "epoch": 7.39, "learning_rate": 1.3064671151997804e-05, "loss": 1.3218, "step": 161900 }, { "epoch": 7.39, "learning_rate": 1.306238271774452e-05, "loss": 1.2811, "step": 161910 }, { "epoch": 7.39, "learning_rate": 1.3060094283491237e-05, "loss": 1.2503, "step": 161920 }, { "epoch": 7.39, "learning_rate": 1.3057805849237953e-05, "loss": 1.4298, "step": 161930 }, { "epoch": 7.39, "learning_rate": 1.3055517414984669e-05, "loss": 1.4782, "step": 161940 }, { "epoch": 7.4, "learning_rate": 1.3053228980731383e-05, "loss": 1.4683, "step": 161950 }, { "epoch": 7.4, "learning_rate": 1.3050940546478099e-05, "loss": 1.378, "step": 161960 }, { "epoch": 7.4, "learning_rate": 1.3048652112224816e-05, "loss": 1.3902, "step": 161970 }, { "epoch": 7.4, "learning_rate": 1.3046363677971532e-05, "loss": 1.4224, "step": 161980 }, { "epoch": 7.4, "learning_rate": 1.3044075243718248e-05, "loss": 1.3228, "step": 161990 }, { "epoch": 7.4, "learning_rate": 1.3041786809464965e-05, "loss": 1.3489, "step": 162000 }, { "epoch": 7.4, "learning_rate": 1.3039498375211681e-05, "loss": 1.4089, "step": 162010 }, { "epoch": 7.4, "learning_rate": 1.3037209940958397e-05, "loss": 1.4929, "step": 162020 }, { "epoch": 7.4, "learning_rate": 1.3034921506705114e-05, "loss": 1.6135, "step": 162030 }, { "epoch": 7.4, "learning_rate": 1.303263307245183e-05, "loss": 1.2633, "step": 162040 }, { "epoch": 7.4, "learning_rate": 1.3030344638198544e-05, "loss": 1.3417, "step": 162050 }, { "epoch": 7.4, "learning_rate": 1.302805620394526e-05, "loss": 1.3887, "step": 162060 }, { "epoch": 7.4, "learning_rate": 1.3025767769691976e-05, "loss": 1.5812, "step": 162070 }, { "epoch": 7.4, "learning_rate": 1.3023479335438694e-05, "loss": 1.3433, "step": 162080 }, { "epoch": 7.4, "learning_rate": 1.302119090118541e-05, "loss": 1.3822, "step": 162090 }, { "epoch": 7.4, "learning_rate": 1.3018902466932125e-05, "loss": 1.3306, "step": 162100 }, { "epoch": 7.4, "learning_rate": 1.3016614032678843e-05, "loss": 1.31, "step": 162110 }, { "epoch": 7.4, "learning_rate": 1.3014325598425559e-05, "loss": 1.4592, "step": 162120 }, { "epoch": 7.4, "learning_rate": 1.3012037164172274e-05, "loss": 1.4527, "step": 162130 }, { "epoch": 7.4, "learning_rate": 1.3009748729918992e-05, "loss": 1.4704, "step": 162140 }, { "epoch": 7.4, "learning_rate": 1.3007460295665704e-05, "loss": 1.3859, "step": 162150 }, { "epoch": 7.4, "learning_rate": 1.3005171861412422e-05, "loss": 1.2015, "step": 162160 }, { "epoch": 7.41, "learning_rate": 1.3002883427159138e-05, "loss": 1.4267, "step": 162170 }, { "epoch": 7.41, "learning_rate": 1.3000594992905854e-05, "loss": 1.3409, "step": 162180 }, { "epoch": 7.41, "learning_rate": 1.2998306558652571e-05, "loss": 1.3893, "step": 162190 }, { "epoch": 7.41, "learning_rate": 1.2996018124399287e-05, "loss": 1.5024, "step": 162200 }, { "epoch": 7.41, "learning_rate": 1.2993729690146003e-05, "loss": 1.4073, "step": 162210 }, { "epoch": 7.41, "learning_rate": 1.299144125589272e-05, "loss": 1.4522, "step": 162220 }, { "epoch": 7.41, "learning_rate": 1.2989152821639436e-05, "loss": 1.2148, "step": 162230 }, { "epoch": 7.41, "learning_rate": 1.2986864387386152e-05, "loss": 1.4771, "step": 162240 }, { "epoch": 7.41, "learning_rate": 1.2984575953132866e-05, "loss": 1.602, "step": 162250 }, { "epoch": 7.41, "learning_rate": 1.2982287518879582e-05, "loss": 1.3681, "step": 162260 }, { "epoch": 7.41, "learning_rate": 1.29799990846263e-05, "loss": 1.3236, "step": 162270 }, { "epoch": 7.41, "learning_rate": 1.2977710650373015e-05, "loss": 1.3796, "step": 162280 }, { "epoch": 7.41, "learning_rate": 1.2975422216119731e-05, "loss": 1.4176, "step": 162290 }, { "epoch": 7.41, "learning_rate": 1.2973133781866449e-05, "loss": 1.4698, "step": 162300 }, { "epoch": 7.41, "learning_rate": 1.2970845347613164e-05, "loss": 1.3443, "step": 162310 }, { "epoch": 7.41, "learning_rate": 1.296855691335988e-05, "loss": 1.2588, "step": 162320 }, { "epoch": 7.41, "learning_rate": 1.2966268479106596e-05, "loss": 1.3905, "step": 162330 }, { "epoch": 7.41, "learning_rate": 1.2963980044853314e-05, "loss": 1.2614, "step": 162340 }, { "epoch": 7.41, "learning_rate": 1.2961691610600028e-05, "loss": 1.2457, "step": 162350 }, { "epoch": 7.41, "learning_rate": 1.2959403176346744e-05, "loss": 1.2176, "step": 162360 }, { "epoch": 7.41, "learning_rate": 1.295711474209346e-05, "loss": 1.5651, "step": 162370 }, { "epoch": 7.41, "learning_rate": 1.2954826307840175e-05, "loss": 1.4506, "step": 162380 }, { "epoch": 7.42, "learning_rate": 1.2952537873586893e-05, "loss": 1.3797, "step": 162390 }, { "epoch": 7.42, "learning_rate": 1.2950249439333609e-05, "loss": 1.2553, "step": 162400 }, { "epoch": 7.42, "learning_rate": 1.2947961005080324e-05, "loss": 1.1505, "step": 162410 }, { "epoch": 7.42, "learning_rate": 1.2945672570827042e-05, "loss": 1.3785, "step": 162420 }, { "epoch": 7.42, "learning_rate": 1.2943384136573758e-05, "loss": 1.2986, "step": 162430 }, { "epoch": 7.42, "learning_rate": 1.2941095702320474e-05, "loss": 1.5249, "step": 162440 }, { "epoch": 7.42, "learning_rate": 1.2938807268067188e-05, "loss": 1.3024, "step": 162450 }, { "epoch": 7.42, "learning_rate": 1.2936518833813904e-05, "loss": 1.2828, "step": 162460 }, { "epoch": 7.42, "learning_rate": 1.2934230399560621e-05, "loss": 1.2008, "step": 162470 }, { "epoch": 7.42, "learning_rate": 1.2931941965307337e-05, "loss": 1.4481, "step": 162480 }, { "epoch": 7.42, "learning_rate": 1.2929653531054053e-05, "loss": 1.4383, "step": 162490 }, { "epoch": 7.42, "learning_rate": 1.292736509680077e-05, "loss": 1.3342, "step": 162500 }, { "epoch": 7.42, "learning_rate": 1.2925076662547486e-05, "loss": 1.2787, "step": 162510 }, { "epoch": 7.42, "learning_rate": 1.2922788228294202e-05, "loss": 1.2263, "step": 162520 }, { "epoch": 7.42, "learning_rate": 1.292049979404092e-05, "loss": 1.4951, "step": 162530 }, { "epoch": 7.42, "learning_rate": 1.2918211359787635e-05, "loss": 1.5329, "step": 162540 }, { "epoch": 7.42, "learning_rate": 1.291592292553435e-05, "loss": 1.3106, "step": 162550 }, { "epoch": 7.42, "learning_rate": 1.2913634491281065e-05, "loss": 1.423, "step": 162560 }, { "epoch": 7.42, "learning_rate": 1.2911346057027781e-05, "loss": 1.3257, "step": 162570 }, { "epoch": 7.42, "learning_rate": 1.2909057622774499e-05, "loss": 1.3967, "step": 162580 }, { "epoch": 7.42, "learning_rate": 1.2906769188521214e-05, "loss": 1.3212, "step": 162590 }, { "epoch": 7.42, "learning_rate": 1.290448075426793e-05, "loss": 1.537, "step": 162600 }, { "epoch": 7.43, "learning_rate": 1.2902192320014648e-05, "loss": 1.3677, "step": 162610 }, { "epoch": 7.43, "learning_rate": 1.2899903885761364e-05, "loss": 1.4427, "step": 162620 }, { "epoch": 7.43, "learning_rate": 1.289761545150808e-05, "loss": 1.462, "step": 162630 }, { "epoch": 7.43, "learning_rate": 1.2895327017254794e-05, "loss": 1.307, "step": 162640 }, { "epoch": 7.43, "learning_rate": 1.289303858300151e-05, "loss": 1.1705, "step": 162650 }, { "epoch": 7.43, "learning_rate": 1.2890750148748227e-05, "loss": 1.6137, "step": 162660 }, { "epoch": 7.43, "learning_rate": 1.2888461714494943e-05, "loss": 1.4356, "step": 162670 }, { "epoch": 7.43, "learning_rate": 1.2886173280241659e-05, "loss": 1.3502, "step": 162680 }, { "epoch": 7.43, "learning_rate": 1.2883884845988376e-05, "loss": 1.4084, "step": 162690 }, { "epoch": 7.43, "learning_rate": 1.2881596411735092e-05, "loss": 1.3394, "step": 162700 }, { "epoch": 7.43, "learning_rate": 1.2879307977481808e-05, "loss": 1.4964, "step": 162710 }, { "epoch": 7.43, "learning_rate": 1.2877019543228525e-05, "loss": 1.4436, "step": 162720 }, { "epoch": 7.43, "learning_rate": 1.2874731108975241e-05, "loss": 1.4909, "step": 162730 }, { "epoch": 7.43, "learning_rate": 1.2872442674721955e-05, "loss": 1.3145, "step": 162740 }, { "epoch": 7.43, "learning_rate": 1.2870154240468671e-05, "loss": 1.3207, "step": 162750 }, { "epoch": 7.43, "learning_rate": 1.2867865806215387e-05, "loss": 1.5119, "step": 162760 }, { "epoch": 7.43, "learning_rate": 1.2865577371962104e-05, "loss": 1.6753, "step": 162770 }, { "epoch": 7.43, "learning_rate": 1.286328893770882e-05, "loss": 1.3267, "step": 162780 }, { "epoch": 7.43, "learning_rate": 1.2861000503455536e-05, "loss": 1.3149, "step": 162790 }, { "epoch": 7.43, "learning_rate": 1.2858712069202254e-05, "loss": 1.4277, "step": 162800 }, { "epoch": 7.43, "learning_rate": 1.285642363494897e-05, "loss": 1.3376, "step": 162810 }, { "epoch": 7.43, "learning_rate": 1.2854135200695685e-05, "loss": 1.3519, "step": 162820 }, { "epoch": 7.44, "learning_rate": 1.2851846766442403e-05, "loss": 1.4189, "step": 162830 }, { "epoch": 7.44, "learning_rate": 1.2849558332189115e-05, "loss": 1.4288, "step": 162840 }, { "epoch": 7.44, "learning_rate": 1.2847269897935833e-05, "loss": 1.3515, "step": 162850 }, { "epoch": 7.44, "learning_rate": 1.2844981463682549e-05, "loss": 1.5565, "step": 162860 }, { "epoch": 7.44, "learning_rate": 1.2842693029429264e-05, "loss": 1.4982, "step": 162870 }, { "epoch": 7.44, "learning_rate": 1.2840404595175982e-05, "loss": 1.4245, "step": 162880 }, { "epoch": 7.44, "learning_rate": 1.2838116160922698e-05, "loss": 1.5114, "step": 162890 }, { "epoch": 7.44, "learning_rate": 1.2835827726669414e-05, "loss": 1.4472, "step": 162900 }, { "epoch": 7.44, "learning_rate": 1.283353929241613e-05, "loss": 1.3087, "step": 162910 }, { "epoch": 7.44, "learning_rate": 1.2831250858162847e-05, "loss": 1.3288, "step": 162920 }, { "epoch": 7.44, "learning_rate": 1.2828962423909563e-05, "loss": 1.397, "step": 162930 }, { "epoch": 7.44, "learning_rate": 1.2826673989656277e-05, "loss": 1.3818, "step": 162940 }, { "epoch": 7.44, "learning_rate": 1.2824385555402993e-05, "loss": 1.3618, "step": 162950 }, { "epoch": 7.44, "learning_rate": 1.2822097121149708e-05, "loss": 1.4202, "step": 162960 }, { "epoch": 7.44, "learning_rate": 1.2819808686896426e-05, "loss": 1.48, "step": 162970 }, { "epoch": 7.44, "learning_rate": 1.2817520252643142e-05, "loss": 1.3717, "step": 162980 }, { "epoch": 7.44, "learning_rate": 1.2815231818389858e-05, "loss": 1.2562, "step": 162990 }, { "epoch": 7.44, "learning_rate": 1.2812943384136575e-05, "loss": 1.4564, "step": 163000 }, { "epoch": 7.44, "learning_rate": 1.2810654949883291e-05, "loss": 1.4724, "step": 163010 }, { "epoch": 7.44, "learning_rate": 1.2808366515630007e-05, "loss": 1.4558, "step": 163020 }, { "epoch": 7.44, "learning_rate": 1.2806078081376724e-05, "loss": 1.3242, "step": 163030 }, { "epoch": 7.44, "learning_rate": 1.2803789647123437e-05, "loss": 1.4399, "step": 163040 }, { "epoch": 7.45, "learning_rate": 1.2801501212870154e-05, "loss": 1.3659, "step": 163050 }, { "epoch": 7.45, "learning_rate": 1.279921277861687e-05, "loss": 1.5124, "step": 163060 }, { "epoch": 7.45, "learning_rate": 1.2796924344363586e-05, "loss": 1.4011, "step": 163070 }, { "epoch": 7.45, "learning_rate": 1.2794635910110303e-05, "loss": 1.4152, "step": 163080 }, { "epoch": 7.45, "learning_rate": 1.279234747585702e-05, "loss": 1.5766, "step": 163090 }, { "epoch": 7.45, "learning_rate": 1.2790059041603735e-05, "loss": 1.3756, "step": 163100 }, { "epoch": 7.45, "learning_rate": 1.2787770607350453e-05, "loss": 1.2886, "step": 163110 }, { "epoch": 7.45, "learning_rate": 1.2785482173097168e-05, "loss": 1.2858, "step": 163120 }, { "epoch": 7.45, "learning_rate": 1.2783193738843884e-05, "loss": 1.3499, "step": 163130 }, { "epoch": 7.45, "learning_rate": 1.2780905304590598e-05, "loss": 1.3907, "step": 163140 }, { "epoch": 7.45, "learning_rate": 1.2778616870337314e-05, "loss": 1.3849, "step": 163150 }, { "epoch": 7.45, "learning_rate": 1.2776328436084032e-05, "loss": 1.3555, "step": 163160 }, { "epoch": 7.45, "learning_rate": 1.2774040001830748e-05, "loss": 1.383, "step": 163170 }, { "epoch": 7.45, "learning_rate": 1.2771751567577463e-05, "loss": 1.4372, "step": 163180 }, { "epoch": 7.45, "learning_rate": 1.2769463133324181e-05, "loss": 1.4036, "step": 163190 }, { "epoch": 7.45, "learning_rate": 1.2767174699070897e-05, "loss": 1.4168, "step": 163200 }, { "epoch": 7.45, "learning_rate": 1.2764886264817613e-05, "loss": 1.4726, "step": 163210 }, { "epoch": 7.45, "learning_rate": 1.276259783056433e-05, "loss": 1.3814, "step": 163220 }, { "epoch": 7.45, "learning_rate": 1.2760309396311046e-05, "loss": 1.4477, "step": 163230 }, { "epoch": 7.45, "learning_rate": 1.275802096205776e-05, "loss": 1.5384, "step": 163240 }, { "epoch": 7.45, "learning_rate": 1.2755732527804476e-05, "loss": 1.4505, "step": 163250 }, { "epoch": 7.45, "learning_rate": 1.2753444093551192e-05, "loss": 1.4298, "step": 163260 }, { "epoch": 7.46, "learning_rate": 1.275115565929791e-05, "loss": 1.3664, "step": 163270 }, { "epoch": 7.46, "learning_rate": 1.2748867225044625e-05, "loss": 1.5036, "step": 163280 }, { "epoch": 7.46, "learning_rate": 1.2746578790791341e-05, "loss": 1.4199, "step": 163290 }, { "epoch": 7.46, "learning_rate": 1.2744290356538058e-05, "loss": 1.3731, "step": 163300 }, { "epoch": 7.46, "learning_rate": 1.2742001922284774e-05, "loss": 1.2781, "step": 163310 }, { "epoch": 7.46, "learning_rate": 1.273971348803149e-05, "loss": 1.2077, "step": 163320 }, { "epoch": 7.46, "learning_rate": 1.2737425053778208e-05, "loss": 1.3169, "step": 163330 }, { "epoch": 7.46, "learning_rate": 1.273513661952492e-05, "loss": 1.3532, "step": 163340 }, { "epoch": 7.46, "learning_rate": 1.2732848185271638e-05, "loss": 1.4812, "step": 163350 }, { "epoch": 7.46, "learning_rate": 1.2730559751018353e-05, "loss": 1.202, "step": 163360 }, { "epoch": 7.46, "learning_rate": 1.272827131676507e-05, "loss": 1.3713, "step": 163370 }, { "epoch": 7.46, "learning_rate": 1.2725982882511787e-05, "loss": 1.2935, "step": 163380 }, { "epoch": 7.46, "learning_rate": 1.2723694448258503e-05, "loss": 1.541, "step": 163390 }, { "epoch": 7.46, "learning_rate": 1.2721406014005218e-05, "loss": 1.2928, "step": 163400 }, { "epoch": 7.46, "learning_rate": 1.2719117579751936e-05, "loss": 1.5176, "step": 163410 }, { "epoch": 7.46, "learning_rate": 1.2716829145498652e-05, "loss": 1.3849, "step": 163420 }, { "epoch": 7.46, "learning_rate": 1.2714540711245366e-05, "loss": 1.3226, "step": 163430 }, { "epoch": 7.46, "learning_rate": 1.2712252276992082e-05, "loss": 1.3487, "step": 163440 }, { "epoch": 7.46, "learning_rate": 1.2709963842738798e-05, "loss": 1.2202, "step": 163450 }, { "epoch": 7.46, "learning_rate": 1.2707675408485515e-05, "loss": 1.4273, "step": 163460 }, { "epoch": 7.46, "learning_rate": 1.2705386974232231e-05, "loss": 1.3779, "step": 163470 }, { "epoch": 7.46, "learning_rate": 1.2703098539978947e-05, "loss": 1.3708, "step": 163480 }, { "epoch": 7.47, "learning_rate": 1.2700810105725664e-05, "loss": 1.3648, "step": 163490 }, { "epoch": 7.47, "learning_rate": 1.269852167147238e-05, "loss": 1.3105, "step": 163500 }, { "epoch": 7.47, "learning_rate": 1.2696233237219096e-05, "loss": 1.3668, "step": 163510 }, { "epoch": 7.47, "learning_rate": 1.2693944802965812e-05, "loss": 1.3855, "step": 163520 }, { "epoch": 7.47, "learning_rate": 1.2691656368712526e-05, "loss": 1.3366, "step": 163530 }, { "epoch": 7.47, "learning_rate": 1.2689367934459242e-05, "loss": 1.3332, "step": 163540 }, { "epoch": 7.47, "learning_rate": 1.268707950020596e-05, "loss": 1.3695, "step": 163550 }, { "epoch": 7.47, "learning_rate": 1.2684791065952675e-05, "loss": 1.3852, "step": 163560 }, { "epoch": 7.47, "learning_rate": 1.2682502631699391e-05, "loss": 1.4193, "step": 163570 }, { "epoch": 7.47, "learning_rate": 1.2680214197446108e-05, "loss": 1.4746, "step": 163580 }, { "epoch": 7.47, "learning_rate": 1.2677925763192824e-05, "loss": 1.4528, "step": 163590 }, { "epoch": 7.47, "learning_rate": 1.267563732893954e-05, "loss": 1.353, "step": 163600 }, { "epoch": 7.47, "learning_rate": 1.2673348894686258e-05, "loss": 1.2183, "step": 163610 }, { "epoch": 7.47, "learning_rate": 1.2671060460432973e-05, "loss": 1.3222, "step": 163620 }, { "epoch": 7.47, "learning_rate": 1.2668772026179688e-05, "loss": 1.3014, "step": 163630 }, { "epoch": 7.47, "learning_rate": 1.2666483591926403e-05, "loss": 1.4361, "step": 163640 }, { "epoch": 7.47, "learning_rate": 1.266419515767312e-05, "loss": 1.534, "step": 163650 }, { "epoch": 7.47, "learning_rate": 1.2661906723419837e-05, "loss": 1.4593, "step": 163660 }, { "epoch": 7.47, "learning_rate": 1.2659618289166553e-05, "loss": 1.4828, "step": 163670 }, { "epoch": 7.47, "learning_rate": 1.2657329854913268e-05, "loss": 1.426, "step": 163680 }, { "epoch": 7.47, "learning_rate": 1.2655041420659986e-05, "loss": 1.4373, "step": 163690 }, { "epoch": 7.47, "learning_rate": 1.2652752986406702e-05, "loss": 1.3606, "step": 163700 }, { "epoch": 7.48, "learning_rate": 1.2650464552153418e-05, "loss": 1.4822, "step": 163710 }, { "epoch": 7.48, "learning_rate": 1.2648176117900135e-05, "loss": 1.3277, "step": 163720 }, { "epoch": 7.48, "learning_rate": 1.2645887683646848e-05, "loss": 1.4109, "step": 163730 }, { "epoch": 7.48, "learning_rate": 1.2643599249393565e-05, "loss": 1.2783, "step": 163740 }, { "epoch": 7.48, "learning_rate": 1.2641310815140281e-05, "loss": 1.2737, "step": 163750 }, { "epoch": 7.48, "learning_rate": 1.2639022380886997e-05, "loss": 1.6112, "step": 163760 }, { "epoch": 7.48, "learning_rate": 1.2636733946633714e-05, "loss": 1.4253, "step": 163770 }, { "epoch": 7.48, "learning_rate": 1.263444551238043e-05, "loss": 1.272, "step": 163780 }, { "epoch": 7.48, "learning_rate": 1.2632157078127146e-05, "loss": 1.4702, "step": 163790 }, { "epoch": 7.48, "learning_rate": 1.2629868643873863e-05, "loss": 1.1988, "step": 163800 }, { "epoch": 7.48, "learning_rate": 1.262758020962058e-05, "loss": 1.2918, "step": 163810 }, { "epoch": 7.48, "learning_rate": 1.2625291775367295e-05, "loss": 1.3898, "step": 163820 }, { "epoch": 7.48, "learning_rate": 1.262300334111401e-05, "loss": 1.3881, "step": 163830 }, { "epoch": 7.48, "learning_rate": 1.2620714906860725e-05, "loss": 1.4288, "step": 163840 }, { "epoch": 7.48, "learning_rate": 1.2618426472607443e-05, "loss": 1.5764, "step": 163850 }, { "epoch": 7.48, "learning_rate": 1.2616138038354158e-05, "loss": 1.2509, "step": 163860 }, { "epoch": 7.48, "learning_rate": 1.2613849604100874e-05, "loss": 1.4006, "step": 163870 }, { "epoch": 7.48, "learning_rate": 1.2611561169847592e-05, "loss": 1.5033, "step": 163880 }, { "epoch": 7.48, "learning_rate": 1.2609272735594308e-05, "loss": 1.4944, "step": 163890 }, { "epoch": 7.48, "learning_rate": 1.2606984301341023e-05, "loss": 1.3585, "step": 163900 }, { "epoch": 7.48, "learning_rate": 1.2604695867087741e-05, "loss": 1.397, "step": 163910 }, { "epoch": 7.49, "learning_rate": 1.2602407432834457e-05, "loss": 1.4458, "step": 163920 }, { "epoch": 7.49, "learning_rate": 1.2600118998581171e-05, "loss": 1.2609, "step": 163930 }, { "epoch": 7.49, "learning_rate": 1.2597830564327887e-05, "loss": 1.4154, "step": 163940 }, { "epoch": 7.49, "learning_rate": 1.2595542130074603e-05, "loss": 1.364, "step": 163950 }, { "epoch": 7.49, "learning_rate": 1.259325369582132e-05, "loss": 1.4663, "step": 163960 }, { "epoch": 7.49, "learning_rate": 1.2590965261568036e-05, "loss": 1.5856, "step": 163970 }, { "epoch": 7.49, "learning_rate": 1.2588676827314752e-05, "loss": 1.386, "step": 163980 }, { "epoch": 7.49, "learning_rate": 1.258638839306147e-05, "loss": 1.3271, "step": 163990 }, { "epoch": 7.49, "learning_rate": 1.2584099958808185e-05, "loss": 1.2955, "step": 164000 }, { "epoch": 7.49, "learning_rate": 1.2581811524554901e-05, "loss": 1.3375, "step": 164010 }, { "epoch": 7.49, "learning_rate": 1.2579523090301618e-05, "loss": 1.2027, "step": 164020 }, { "epoch": 7.49, "learning_rate": 1.257723465604833e-05, "loss": 1.2894, "step": 164030 }, { "epoch": 7.49, "learning_rate": 1.2574946221795048e-05, "loss": 1.2362, "step": 164040 }, { "epoch": 7.49, "learning_rate": 1.2572657787541764e-05, "loss": 1.4114, "step": 164050 }, { "epoch": 7.49, "learning_rate": 1.257036935328848e-05, "loss": 1.4068, "step": 164060 }, { "epoch": 7.49, "learning_rate": 1.2568080919035198e-05, "loss": 1.4659, "step": 164070 }, { "epoch": 7.49, "learning_rate": 1.2565792484781913e-05, "loss": 1.309, "step": 164080 }, { "epoch": 7.49, "learning_rate": 1.256350405052863e-05, "loss": 1.4287, "step": 164090 }, { "epoch": 7.49, "learning_rate": 1.2561215616275345e-05, "loss": 1.3815, "step": 164100 }, { "epoch": 7.49, "learning_rate": 1.2558927182022063e-05, "loss": 1.4403, "step": 164110 }, { "epoch": 7.49, "learning_rate": 1.2556638747768778e-05, "loss": 1.4776, "step": 164120 }, { "epoch": 7.49, "learning_rate": 1.2554350313515492e-05, "loss": 1.3979, "step": 164130 }, { "epoch": 7.5, "learning_rate": 1.2552061879262208e-05, "loss": 1.3382, "step": 164140 }, { "epoch": 7.5, "learning_rate": 1.2549773445008924e-05, "loss": 1.3499, "step": 164150 }, { "epoch": 7.5, "learning_rate": 1.2547485010755642e-05, "loss": 1.3772, "step": 164160 }, { "epoch": 7.5, "learning_rate": 1.2545196576502357e-05, "loss": 1.4606, "step": 164170 }, { "epoch": 7.5, "learning_rate": 1.2542908142249073e-05, "loss": 1.2824, "step": 164180 }, { "epoch": 7.5, "learning_rate": 1.2540619707995791e-05, "loss": 1.5117, "step": 164190 }, { "epoch": 7.5, "learning_rate": 1.2538331273742507e-05, "loss": 1.4292, "step": 164200 }, { "epoch": 7.5, "learning_rate": 1.2536042839489223e-05, "loss": 1.37, "step": 164210 }, { "epoch": 7.5, "learning_rate": 1.2533754405235937e-05, "loss": 1.2843, "step": 164220 }, { "epoch": 7.5, "learning_rate": 1.2531465970982652e-05, "loss": 1.3225, "step": 164230 }, { "epoch": 7.5, "learning_rate": 1.252917753672937e-05, "loss": 1.3727, "step": 164240 }, { "epoch": 7.5, "learning_rate": 1.2526889102476086e-05, "loss": 1.2957, "step": 164250 }, { "epoch": 7.5, "learning_rate": 1.2524600668222802e-05, "loss": 1.463, "step": 164260 }, { "epoch": 7.5, "learning_rate": 1.252231223396952e-05, "loss": 1.429, "step": 164270 }, { "epoch": 7.5, "learning_rate": 1.2520023799716235e-05, "loss": 1.1563, "step": 164280 }, { "epoch": 7.5, "learning_rate": 1.251773536546295e-05, "loss": 1.5437, "step": 164290 }, { "epoch": 7.5, "learning_rate": 1.2515446931209668e-05, "loss": 1.3371, "step": 164300 }, { "epoch": 7.5, "learning_rate": 1.2513158496956384e-05, "loss": 1.3619, "step": 164310 }, { "epoch": 7.5, "learning_rate": 1.2510870062703098e-05, "loss": 1.326, "step": 164320 }, { "epoch": 7.5, "learning_rate": 1.2508581628449814e-05, "loss": 1.2661, "step": 164330 }, { "epoch": 7.5, "learning_rate": 1.250629319419653e-05, "loss": 1.3718, "step": 164340 }, { "epoch": 7.5, "learning_rate": 1.2504004759943247e-05, "loss": 1.4221, "step": 164350 }, { "epoch": 7.51, "learning_rate": 1.2501716325689963e-05, "loss": 1.4499, "step": 164360 }, { "epoch": 7.51, "learning_rate": 1.2499427891436679e-05, "loss": 1.33, "step": 164370 }, { "epoch": 7.51, "learning_rate": 1.2497139457183397e-05, "loss": 1.3736, "step": 164380 }, { "epoch": 7.51, "learning_rate": 1.2494851022930112e-05, "loss": 1.4328, "step": 164390 }, { "epoch": 7.51, "learning_rate": 1.2492562588676827e-05, "loss": 1.3949, "step": 164400 }, { "epoch": 7.51, "learning_rate": 1.2490274154423544e-05, "loss": 1.3022, "step": 164410 }, { "epoch": 7.51, "learning_rate": 1.248798572017026e-05, "loss": 1.5679, "step": 164420 }, { "epoch": 7.51, "learning_rate": 1.2485697285916976e-05, "loss": 1.2986, "step": 164430 }, { "epoch": 7.51, "learning_rate": 1.2483408851663693e-05, "loss": 1.5335, "step": 164440 }, { "epoch": 7.51, "learning_rate": 1.2481120417410407e-05, "loss": 1.4336, "step": 164450 }, { "epoch": 7.51, "learning_rate": 1.2478831983157125e-05, "loss": 1.4203, "step": 164460 }, { "epoch": 7.51, "learning_rate": 1.247654354890384e-05, "loss": 1.2498, "step": 164470 }, { "epoch": 7.51, "learning_rate": 1.2474255114650557e-05, "loss": 1.2988, "step": 164480 }, { "epoch": 7.51, "learning_rate": 1.2471966680397274e-05, "loss": 1.2971, "step": 164490 }, { "epoch": 7.51, "learning_rate": 1.2469678246143988e-05, "loss": 1.3863, "step": 164500 }, { "epoch": 7.51, "learning_rate": 1.2467389811890704e-05, "loss": 1.3994, "step": 164510 }, { "epoch": 7.51, "learning_rate": 1.2465101377637422e-05, "loss": 1.3824, "step": 164520 }, { "epoch": 7.51, "learning_rate": 1.2462812943384137e-05, "loss": 1.425, "step": 164530 }, { "epoch": 7.51, "learning_rate": 1.2460524509130853e-05, "loss": 1.5212, "step": 164540 }, { "epoch": 7.51, "learning_rate": 1.2458236074877569e-05, "loss": 1.4009, "step": 164550 }, { "epoch": 7.51, "learning_rate": 1.2455947640624285e-05, "loss": 1.3343, "step": 164560 }, { "epoch": 7.51, "learning_rate": 1.2453659206371002e-05, "loss": 1.3073, "step": 164570 }, { "epoch": 7.52, "learning_rate": 1.2451370772117718e-05, "loss": 1.3744, "step": 164580 }, { "epoch": 7.52, "learning_rate": 1.2449082337864432e-05, "loss": 1.2788, "step": 164590 }, { "epoch": 7.52, "learning_rate": 1.244679390361115e-05, "loss": 1.442, "step": 164600 }, { "epoch": 7.52, "learning_rate": 1.2444505469357866e-05, "loss": 1.6167, "step": 164610 }, { "epoch": 7.52, "learning_rate": 1.2442217035104582e-05, "loss": 1.309, "step": 164620 }, { "epoch": 7.52, "learning_rate": 1.2439928600851299e-05, "loss": 1.146, "step": 164630 }, { "epoch": 7.52, "learning_rate": 1.2437640166598013e-05, "loss": 1.4067, "step": 164640 }, { "epoch": 7.52, "learning_rate": 1.243535173234473e-05, "loss": 1.4287, "step": 164650 }, { "epoch": 7.52, "learning_rate": 1.2433063298091447e-05, "loss": 1.4567, "step": 164660 }, { "epoch": 7.52, "learning_rate": 1.2430774863838162e-05, "loss": 1.2241, "step": 164670 }, { "epoch": 7.52, "learning_rate": 1.2428486429584878e-05, "loss": 1.3316, "step": 164680 }, { "epoch": 7.52, "learning_rate": 1.2426197995331594e-05, "loss": 1.4129, "step": 164690 }, { "epoch": 7.52, "learning_rate": 1.242390956107831e-05, "loss": 1.4705, "step": 164700 }, { "epoch": 7.52, "learning_rate": 1.2421621126825027e-05, "loss": 1.2143, "step": 164710 }, { "epoch": 7.52, "learning_rate": 1.2419332692571743e-05, "loss": 1.3427, "step": 164720 }, { "epoch": 7.52, "learning_rate": 1.2417044258318459e-05, "loss": 1.3163, "step": 164730 }, { "epoch": 7.52, "learning_rate": 1.2414755824065175e-05, "loss": 1.3637, "step": 164740 }, { "epoch": 7.52, "learning_rate": 1.241246738981189e-05, "loss": 1.342, "step": 164750 }, { "epoch": 7.52, "learning_rate": 1.2410178955558607e-05, "loss": 1.2256, "step": 164760 }, { "epoch": 7.52, "learning_rate": 1.2407890521305324e-05, "loss": 1.3654, "step": 164770 }, { "epoch": 7.52, "learning_rate": 1.240560208705204e-05, "loss": 1.4349, "step": 164780 }, { "epoch": 7.52, "learning_rate": 1.2403313652798756e-05, "loss": 1.3698, "step": 164790 }, { "epoch": 7.53, "learning_rate": 1.2401025218545472e-05, "loss": 1.5883, "step": 164800 }, { "epoch": 7.53, "learning_rate": 1.2398736784292187e-05, "loss": 1.272, "step": 164810 }, { "epoch": 7.53, "learning_rate": 1.2396448350038905e-05, "loss": 1.3654, "step": 164820 }, { "epoch": 7.53, "learning_rate": 1.239415991578562e-05, "loss": 1.3106, "step": 164830 }, { "epoch": 7.53, "learning_rate": 1.2391871481532335e-05, "loss": 1.3879, "step": 164840 }, { "epoch": 7.53, "learning_rate": 1.2389583047279052e-05, "loss": 1.4417, "step": 164850 }, { "epoch": 7.53, "learning_rate": 1.2387294613025768e-05, "loss": 1.452, "step": 164860 }, { "epoch": 7.53, "learning_rate": 1.2385006178772484e-05, "loss": 1.3942, "step": 164870 }, { "epoch": 7.53, "learning_rate": 1.2382717744519202e-05, "loss": 1.3338, "step": 164880 }, { "epoch": 7.53, "learning_rate": 1.2380429310265916e-05, "loss": 1.3745, "step": 164890 }, { "epoch": 7.53, "learning_rate": 1.2378140876012633e-05, "loss": 1.2497, "step": 164900 }, { "epoch": 7.53, "learning_rate": 1.2375852441759349e-05, "loss": 1.3939, "step": 164910 }, { "epoch": 7.53, "learning_rate": 1.2373564007506065e-05, "loss": 1.3566, "step": 164920 }, { "epoch": 7.53, "learning_rate": 1.2371275573252782e-05, "loss": 1.3254, "step": 164930 }, { "epoch": 7.53, "learning_rate": 1.2368987138999497e-05, "loss": 1.1746, "step": 164940 }, { "epoch": 7.53, "learning_rate": 1.2366698704746212e-05, "loss": 1.3047, "step": 164950 }, { "epoch": 7.53, "learning_rate": 1.236441027049293e-05, "loss": 1.443, "step": 164960 }, { "epoch": 7.53, "learning_rate": 1.2362121836239646e-05, "loss": 1.4745, "step": 164970 }, { "epoch": 7.53, "learning_rate": 1.2359833401986362e-05, "loss": 1.4475, "step": 164980 }, { "epoch": 7.53, "learning_rate": 1.2357544967733077e-05, "loss": 1.4694, "step": 164990 }, { "epoch": 7.53, "learning_rate": 1.2355256533479793e-05, "loss": 1.4357, "step": 165000 }, { "epoch": 7.53, "learning_rate": 1.2352968099226509e-05, "loss": 1.3306, "step": 165010 }, { "epoch": 7.54, "learning_rate": 1.2350679664973227e-05, "loss": 1.3773, "step": 165020 }, { "epoch": 7.54, "learning_rate": 1.2348391230719942e-05, "loss": 1.3467, "step": 165030 }, { "epoch": 7.54, "learning_rate": 1.2346102796466658e-05, "loss": 1.4296, "step": 165040 }, { "epoch": 7.54, "learning_rate": 1.2343814362213374e-05, "loss": 1.2953, "step": 165050 }, { "epoch": 7.54, "learning_rate": 1.234152592796009e-05, "loss": 1.3297, "step": 165060 }, { "epoch": 7.54, "learning_rate": 1.2339237493706807e-05, "loss": 1.5137, "step": 165070 }, { "epoch": 7.54, "learning_rate": 1.2336949059453523e-05, "loss": 1.5698, "step": 165080 }, { "epoch": 7.54, "learning_rate": 1.2334660625200237e-05, "loss": 1.4083, "step": 165090 }, { "epoch": 7.54, "learning_rate": 1.2332372190946955e-05, "loss": 1.3336, "step": 165100 }, { "epoch": 7.54, "learning_rate": 1.233008375669367e-05, "loss": 1.3934, "step": 165110 }, { "epoch": 7.54, "learning_rate": 1.2327795322440387e-05, "loss": 1.5028, "step": 165120 }, { "epoch": 7.54, "learning_rate": 1.2325506888187104e-05, "loss": 1.3065, "step": 165130 }, { "epoch": 7.54, "learning_rate": 1.2323218453933818e-05, "loss": 1.4333, "step": 165140 }, { "epoch": 7.54, "learning_rate": 1.2320930019680536e-05, "loss": 1.2195, "step": 165150 }, { "epoch": 7.54, "learning_rate": 1.2318641585427252e-05, "loss": 1.3146, "step": 165160 }, { "epoch": 7.54, "learning_rate": 1.2316353151173967e-05, "loss": 1.2407, "step": 165170 }, { "epoch": 7.54, "learning_rate": 1.2314064716920685e-05, "loss": 1.4561, "step": 165180 }, { "epoch": 7.54, "learning_rate": 1.2311776282667399e-05, "loss": 1.5658, "step": 165190 }, { "epoch": 7.54, "learning_rate": 1.2309487848414115e-05, "loss": 1.4623, "step": 165200 }, { "epoch": 7.54, "learning_rate": 1.2307199414160832e-05, "loss": 1.3425, "step": 165210 }, { "epoch": 7.54, "learning_rate": 1.2304910979907548e-05, "loss": 1.304, "step": 165220 }, { "epoch": 7.54, "learning_rate": 1.2302622545654264e-05, "loss": 1.4384, "step": 165230 }, { "epoch": 7.55, "learning_rate": 1.230033411140098e-05, "loss": 1.4688, "step": 165240 }, { "epoch": 7.55, "learning_rate": 1.2298045677147696e-05, "loss": 1.3427, "step": 165250 }, { "epoch": 7.55, "learning_rate": 1.2295757242894412e-05, "loss": 1.329, "step": 165260 }, { "epoch": 7.55, "learning_rate": 1.2293468808641129e-05, "loss": 1.4207, "step": 165270 }, { "epoch": 7.55, "learning_rate": 1.2291180374387845e-05, "loss": 1.3671, "step": 165280 }, { "epoch": 7.55, "learning_rate": 1.228889194013456e-05, "loss": 1.4135, "step": 165290 }, { "epoch": 7.55, "learning_rate": 1.2286603505881277e-05, "loss": 1.4593, "step": 165300 }, { "epoch": 7.55, "learning_rate": 1.2284315071627992e-05, "loss": 1.4975, "step": 165310 }, { "epoch": 7.55, "learning_rate": 1.228202663737471e-05, "loss": 1.436, "step": 165320 }, { "epoch": 7.55, "learning_rate": 1.2279738203121426e-05, "loss": 1.4152, "step": 165330 }, { "epoch": 7.55, "learning_rate": 1.227744976886814e-05, "loss": 1.3683, "step": 165340 }, { "epoch": 7.55, "learning_rate": 1.2275161334614857e-05, "loss": 1.4505, "step": 165350 }, { "epoch": 7.55, "learning_rate": 1.2272872900361573e-05, "loss": 1.4688, "step": 165360 }, { "epoch": 7.55, "learning_rate": 1.2270584466108289e-05, "loss": 1.3327, "step": 165370 }, { "epoch": 7.55, "learning_rate": 1.2268296031855005e-05, "loss": 1.3645, "step": 165380 }, { "epoch": 7.55, "learning_rate": 1.226600759760172e-05, "loss": 1.3292, "step": 165390 }, { "epoch": 7.55, "learning_rate": 1.2263719163348438e-05, "loss": 1.4144, "step": 165400 }, { "epoch": 7.55, "learning_rate": 1.2261430729095154e-05, "loss": 1.2931, "step": 165410 }, { "epoch": 7.55, "learning_rate": 1.225914229484187e-05, "loss": 1.4988, "step": 165420 }, { "epoch": 7.55, "learning_rate": 1.2256853860588586e-05, "loss": 1.2402, "step": 165430 }, { "epoch": 7.55, "learning_rate": 1.2254565426335301e-05, "loss": 1.2982, "step": 165440 }, { "epoch": 7.55, "learning_rate": 1.2252276992082017e-05, "loss": 1.2444, "step": 165450 }, { "epoch": 7.56, "learning_rate": 1.2249988557828735e-05, "loss": 1.2047, "step": 165460 }, { "epoch": 7.56, "learning_rate": 1.224770012357545e-05, "loss": 1.3286, "step": 165470 }, { "epoch": 7.56, "learning_rate": 1.2245411689322166e-05, "loss": 1.5937, "step": 165480 }, { "epoch": 7.56, "learning_rate": 1.2243123255068882e-05, "loss": 1.4013, "step": 165490 }, { "epoch": 7.56, "learning_rate": 1.2240834820815598e-05, "loss": 1.2852, "step": 165500 }, { "epoch": 7.56, "learning_rate": 1.2238546386562316e-05, "loss": 1.4445, "step": 165510 }, { "epoch": 7.56, "learning_rate": 1.2236257952309031e-05, "loss": 1.4186, "step": 165520 }, { "epoch": 7.56, "learning_rate": 1.2233969518055746e-05, "loss": 1.4235, "step": 165530 }, { "epoch": 7.56, "learning_rate": 1.2231681083802463e-05, "loss": 1.4818, "step": 165540 }, { "epoch": 7.56, "learning_rate": 1.2229392649549179e-05, "loss": 1.2967, "step": 165550 }, { "epoch": 7.56, "learning_rate": 1.2227104215295895e-05, "loss": 1.4206, "step": 165560 }, { "epoch": 7.56, "learning_rate": 1.2224815781042612e-05, "loss": 1.3851, "step": 165570 }, { "epoch": 7.56, "learning_rate": 1.2222527346789326e-05, "loss": 1.3526, "step": 165580 }, { "epoch": 7.56, "learning_rate": 1.2220238912536042e-05, "loss": 1.6267, "step": 165590 }, { "epoch": 7.56, "learning_rate": 1.221795047828276e-05, "loss": 1.6403, "step": 165600 }, { "epoch": 7.56, "learning_rate": 1.2215662044029476e-05, "loss": 1.4701, "step": 165610 }, { "epoch": 7.56, "learning_rate": 1.2213373609776191e-05, "loss": 1.2615, "step": 165620 }, { "epoch": 7.56, "learning_rate": 1.2211085175522907e-05, "loss": 1.277, "step": 165630 }, { "epoch": 7.56, "learning_rate": 1.2208796741269623e-05, "loss": 1.4993, "step": 165640 }, { "epoch": 7.56, "learning_rate": 1.220650830701634e-05, "loss": 1.3945, "step": 165650 }, { "epoch": 7.56, "learning_rate": 1.2204219872763056e-05, "loss": 1.4674, "step": 165660 }, { "epoch": 7.56, "learning_rate": 1.2201931438509772e-05, "loss": 1.2767, "step": 165670 }, { "epoch": 7.57, "learning_rate": 1.2199643004256488e-05, "loss": 1.4526, "step": 165680 }, { "epoch": 7.57, "learning_rate": 1.2197354570003204e-05, "loss": 1.3153, "step": 165690 }, { "epoch": 7.57, "learning_rate": 1.219506613574992e-05, "loss": 1.3757, "step": 165700 }, { "epoch": 7.57, "learning_rate": 1.2192777701496637e-05, "loss": 1.3272, "step": 165710 }, { "epoch": 7.57, "learning_rate": 1.2190489267243353e-05, "loss": 1.2851, "step": 165720 }, { "epoch": 7.57, "learning_rate": 1.2188200832990069e-05, "loss": 1.335, "step": 165730 }, { "epoch": 7.57, "learning_rate": 1.2185912398736785e-05, "loss": 1.3267, "step": 165740 }, { "epoch": 7.57, "learning_rate": 1.21836239644835e-05, "loss": 1.4601, "step": 165750 }, { "epoch": 7.57, "learning_rate": 1.2181335530230218e-05, "loss": 1.4347, "step": 165760 }, { "epoch": 7.57, "learning_rate": 1.2179047095976934e-05, "loss": 1.337, "step": 165770 }, { "epoch": 7.57, "learning_rate": 1.2176758661723648e-05, "loss": 1.3672, "step": 165780 }, { "epoch": 7.57, "learning_rate": 1.2174470227470366e-05, "loss": 1.482, "step": 165790 }, { "epoch": 7.57, "learning_rate": 1.2172181793217081e-05, "loss": 1.3421, "step": 165800 }, { "epoch": 7.57, "learning_rate": 1.2169893358963797e-05, "loss": 1.3537, "step": 165810 }, { "epoch": 7.57, "learning_rate": 1.2167604924710515e-05, "loss": 1.3493, "step": 165820 }, { "epoch": 7.57, "learning_rate": 1.2165316490457229e-05, "loss": 1.3934, "step": 165830 }, { "epoch": 7.57, "learning_rate": 1.2163028056203945e-05, "loss": 1.4327, "step": 165840 }, { "epoch": 7.57, "learning_rate": 1.2160739621950662e-05, "loss": 1.2842, "step": 165850 }, { "epoch": 7.57, "learning_rate": 1.2158451187697378e-05, "loss": 1.4069, "step": 165860 }, { "epoch": 7.57, "learning_rate": 1.2156162753444094e-05, "loss": 1.3878, "step": 165870 }, { "epoch": 7.57, "learning_rate": 1.215387431919081e-05, "loss": 1.4756, "step": 165880 }, { "epoch": 7.57, "learning_rate": 1.2151585884937526e-05, "loss": 1.4637, "step": 165890 }, { "epoch": 7.58, "learning_rate": 1.2149297450684243e-05, "loss": 1.4804, "step": 165900 }, { "epoch": 7.58, "learning_rate": 1.2147009016430959e-05, "loss": 1.3012, "step": 165910 }, { "epoch": 7.58, "learning_rate": 1.2144720582177675e-05, "loss": 1.4543, "step": 165920 }, { "epoch": 7.58, "learning_rate": 1.214243214792439e-05, "loss": 1.1578, "step": 165930 }, { "epoch": 7.58, "learning_rate": 1.2140143713671106e-05, "loss": 1.371, "step": 165940 }, { "epoch": 7.58, "learning_rate": 1.2137855279417822e-05, "loss": 1.258, "step": 165950 }, { "epoch": 7.58, "learning_rate": 1.213556684516454e-05, "loss": 1.3576, "step": 165960 }, { "epoch": 7.58, "learning_rate": 1.2133278410911256e-05, "loss": 1.4083, "step": 165970 }, { "epoch": 7.58, "learning_rate": 1.2130989976657971e-05, "loss": 1.4359, "step": 165980 }, { "epoch": 7.58, "learning_rate": 1.2128701542404687e-05, "loss": 1.3592, "step": 165990 }, { "epoch": 7.58, "learning_rate": 1.2126413108151403e-05, "loss": 1.3849, "step": 166000 }, { "epoch": 7.58, "learning_rate": 1.212412467389812e-05, "loss": 1.2373, "step": 166010 }, { "epoch": 7.58, "learning_rate": 1.2121836239644836e-05, "loss": 1.2488, "step": 166020 }, { "epoch": 7.58, "learning_rate": 1.211954780539155e-05, "loss": 1.3098, "step": 166030 }, { "epoch": 7.58, "learning_rate": 1.2117259371138268e-05, "loss": 1.4068, "step": 166040 }, { "epoch": 7.58, "learning_rate": 1.2114970936884984e-05, "loss": 1.4485, "step": 166050 }, { "epoch": 7.58, "learning_rate": 1.21126825026317e-05, "loss": 1.2709, "step": 166060 }, { "epoch": 7.58, "learning_rate": 1.2110394068378417e-05, "loss": 1.4021, "step": 166070 }, { "epoch": 7.58, "learning_rate": 1.2108105634125131e-05, "loss": 1.411, "step": 166080 }, { "epoch": 7.58, "learning_rate": 1.2105817199871849e-05, "loss": 1.36, "step": 166090 }, { "epoch": 7.58, "learning_rate": 1.2103528765618565e-05, "loss": 1.2736, "step": 166100 }, { "epoch": 7.59, "learning_rate": 1.210124033136528e-05, "loss": 1.4252, "step": 166110 }, { "epoch": 7.59, "learning_rate": 1.2098951897111996e-05, "loss": 1.4399, "step": 166120 }, { "epoch": 7.59, "learning_rate": 1.2096663462858712e-05, "loss": 1.5084, "step": 166130 }, { "epoch": 7.59, "learning_rate": 1.2094375028605428e-05, "loss": 1.2368, "step": 166140 }, { "epoch": 7.59, "learning_rate": 1.2092086594352146e-05, "loss": 1.3195, "step": 166150 }, { "epoch": 7.59, "learning_rate": 1.2089798160098861e-05, "loss": 1.4341, "step": 166160 }, { "epoch": 7.59, "learning_rate": 1.2087509725845577e-05, "loss": 1.4949, "step": 166170 }, { "epoch": 7.59, "learning_rate": 1.2085221291592293e-05, "loss": 1.4592, "step": 166180 }, { "epoch": 7.59, "learning_rate": 1.2082932857339009e-05, "loss": 1.3732, "step": 166190 }, { "epoch": 7.59, "learning_rate": 1.2080644423085725e-05, "loss": 1.3692, "step": 166200 }, { "epoch": 7.59, "learning_rate": 1.2078355988832442e-05, "loss": 1.4536, "step": 166210 }, { "epoch": 7.59, "learning_rate": 1.2076067554579156e-05, "loss": 1.4964, "step": 166220 }, { "epoch": 7.59, "learning_rate": 1.2073779120325874e-05, "loss": 1.4323, "step": 166230 }, { "epoch": 7.59, "learning_rate": 1.207149068607259e-05, "loss": 1.4312, "step": 166240 }, { "epoch": 7.59, "learning_rate": 1.2069202251819306e-05, "loss": 1.3334, "step": 166250 }, { "epoch": 7.59, "learning_rate": 1.2066913817566023e-05, "loss": 1.4165, "step": 166260 }, { "epoch": 7.59, "learning_rate": 1.2064625383312737e-05, "loss": 1.2547, "step": 166270 }, { "epoch": 7.59, "learning_rate": 1.2062336949059453e-05, "loss": 1.3967, "step": 166280 }, { "epoch": 7.59, "learning_rate": 1.206004851480617e-05, "loss": 1.4054, "step": 166290 }, { "epoch": 7.59, "learning_rate": 1.2057760080552886e-05, "loss": 1.4099, "step": 166300 }, { "epoch": 7.59, "learning_rate": 1.2055471646299602e-05, "loss": 1.3564, "step": 166310 }, { "epoch": 7.59, "learning_rate": 1.2053183212046318e-05, "loss": 1.3117, "step": 166320 }, { "epoch": 7.6, "learning_rate": 1.2050894777793034e-05, "loss": 1.2981, "step": 166330 }, { "epoch": 7.6, "learning_rate": 1.2048606343539751e-05, "loss": 1.2438, "step": 166340 }, { "epoch": 7.6, "learning_rate": 1.2046317909286467e-05, "loss": 1.3524, "step": 166350 }, { "epoch": 7.6, "learning_rate": 1.2044029475033183e-05, "loss": 1.2979, "step": 166360 }, { "epoch": 7.6, "learning_rate": 1.2041741040779899e-05, "loss": 1.4721, "step": 166370 }, { "epoch": 7.6, "learning_rate": 1.2039452606526615e-05, "loss": 1.579, "step": 166380 }, { "epoch": 7.6, "learning_rate": 1.203716417227333e-05, "loss": 1.3963, "step": 166390 }, { "epoch": 7.6, "learning_rate": 1.2034875738020048e-05, "loss": 1.4646, "step": 166400 }, { "epoch": 7.6, "learning_rate": 1.2032587303766764e-05, "loss": 1.298, "step": 166410 }, { "epoch": 7.6, "learning_rate": 1.2030298869513478e-05, "loss": 1.5718, "step": 166420 }, { "epoch": 7.6, "learning_rate": 1.2028010435260196e-05, "loss": 1.3597, "step": 166430 }, { "epoch": 7.6, "learning_rate": 1.2025722001006911e-05, "loss": 1.4068, "step": 166440 }, { "epoch": 7.6, "learning_rate": 1.2023433566753627e-05, "loss": 1.4581, "step": 166450 }, { "epoch": 7.6, "learning_rate": 1.2021145132500345e-05, "loss": 1.4192, "step": 166460 }, { "epoch": 7.6, "learning_rate": 1.2018856698247059e-05, "loss": 1.477, "step": 166470 }, { "epoch": 7.6, "learning_rate": 1.2016568263993776e-05, "loss": 1.3384, "step": 166480 }, { "epoch": 7.6, "learning_rate": 1.2014279829740492e-05, "loss": 1.4498, "step": 166490 }, { "epoch": 7.6, "learning_rate": 1.2011991395487208e-05, "loss": 1.2167, "step": 166500 }, { "epoch": 7.6, "learning_rate": 1.2009702961233926e-05, "loss": 1.4482, "step": 166510 }, { "epoch": 7.6, "learning_rate": 1.200741452698064e-05, "loss": 1.3185, "step": 166520 }, { "epoch": 7.6, "learning_rate": 1.2005126092727355e-05, "loss": 1.4401, "step": 166530 }, { "epoch": 7.6, "learning_rate": 1.2002837658474073e-05, "loss": 1.4031, "step": 166540 }, { "epoch": 7.61, "learning_rate": 1.2000549224220789e-05, "loss": 1.4611, "step": 166550 }, { "epoch": 7.61, "learning_rate": 1.1998260789967505e-05, "loss": 1.3241, "step": 166560 }, { "epoch": 7.61, "learning_rate": 1.199597235571422e-05, "loss": 1.2095, "step": 166570 }, { "epoch": 7.61, "learning_rate": 1.1993683921460936e-05, "loss": 1.4161, "step": 166580 }, { "epoch": 7.61, "learning_rate": 1.1991395487207654e-05, "loss": 1.3391, "step": 166590 }, { "epoch": 7.61, "learning_rate": 1.198910705295437e-05, "loss": 1.3093, "step": 166600 }, { "epoch": 7.61, "learning_rate": 1.1986818618701086e-05, "loss": 1.2439, "step": 166610 }, { "epoch": 7.61, "learning_rate": 1.1984530184447801e-05, "loss": 1.4564, "step": 166620 }, { "epoch": 7.61, "learning_rate": 1.1982241750194517e-05, "loss": 1.4673, "step": 166630 }, { "epoch": 7.61, "learning_rate": 1.1979953315941233e-05, "loss": 1.2781, "step": 166640 }, { "epoch": 7.61, "learning_rate": 1.197766488168795e-05, "loss": 1.2529, "step": 166650 }, { "epoch": 7.61, "learning_rate": 1.1975376447434666e-05, "loss": 1.4777, "step": 166660 }, { "epoch": 7.61, "learning_rate": 1.1973088013181382e-05, "loss": 1.3669, "step": 166670 }, { "epoch": 7.61, "learning_rate": 1.1970799578928098e-05, "loss": 1.4715, "step": 166680 }, { "epoch": 7.61, "learning_rate": 1.1968511144674814e-05, "loss": 1.434, "step": 166690 }, { "epoch": 7.61, "learning_rate": 1.196622271042153e-05, "loss": 1.411, "step": 166700 }, { "epoch": 7.61, "learning_rate": 1.1963934276168247e-05, "loss": 1.3557, "step": 166710 }, { "epoch": 7.61, "learning_rate": 1.1961645841914961e-05, "loss": 1.3629, "step": 166720 }, { "epoch": 7.61, "learning_rate": 1.1959357407661679e-05, "loss": 1.4874, "step": 166730 }, { "epoch": 7.61, "learning_rate": 1.1957068973408395e-05, "loss": 1.3213, "step": 166740 }, { "epoch": 7.61, "learning_rate": 1.195478053915511e-05, "loss": 1.3523, "step": 166750 }, { "epoch": 7.61, "learning_rate": 1.1952492104901828e-05, "loss": 1.4161, "step": 166760 }, { "epoch": 7.62, "learning_rate": 1.1950203670648542e-05, "loss": 1.3921, "step": 166770 }, { "epoch": 7.62, "learning_rate": 1.1947915236395258e-05, "loss": 1.4292, "step": 166780 }, { "epoch": 7.62, "learning_rate": 1.1945626802141975e-05, "loss": 1.2935, "step": 166790 }, { "epoch": 7.62, "learning_rate": 1.1943338367888691e-05, "loss": 1.4565, "step": 166800 }, { "epoch": 7.62, "learning_rate": 1.1941049933635407e-05, "loss": 1.2793, "step": 166810 }, { "epoch": 7.62, "learning_rate": 1.1938761499382123e-05, "loss": 1.4558, "step": 166820 }, { "epoch": 7.62, "learning_rate": 1.1936473065128839e-05, "loss": 1.4582, "step": 166830 }, { "epoch": 7.62, "learning_rate": 1.1934184630875556e-05, "loss": 1.294, "step": 166840 }, { "epoch": 7.62, "learning_rate": 1.1931896196622272e-05, "loss": 1.3449, "step": 166850 }, { "epoch": 7.62, "learning_rate": 1.1929607762368988e-05, "loss": 1.3218, "step": 166860 }, { "epoch": 7.62, "learning_rate": 1.1927319328115704e-05, "loss": 1.2588, "step": 166870 }, { "epoch": 7.62, "learning_rate": 1.192503089386242e-05, "loss": 1.2947, "step": 166880 }, { "epoch": 7.62, "learning_rate": 1.1922742459609135e-05, "loss": 1.4431, "step": 166890 }, { "epoch": 7.62, "learning_rate": 1.1920454025355853e-05, "loss": 1.396, "step": 166900 }, { "epoch": 7.62, "learning_rate": 1.1918165591102569e-05, "loss": 1.3383, "step": 166910 }, { "epoch": 7.62, "learning_rate": 1.1915877156849285e-05, "loss": 1.499, "step": 166920 }, { "epoch": 7.62, "learning_rate": 1.1913588722596e-05, "loss": 1.3891, "step": 166930 }, { "epoch": 7.62, "learning_rate": 1.1911300288342716e-05, "loss": 1.3886, "step": 166940 }, { "epoch": 7.62, "learning_rate": 1.1909011854089434e-05, "loss": 1.2556, "step": 166950 }, { "epoch": 7.62, "learning_rate": 1.190672341983615e-05, "loss": 1.4731, "step": 166960 }, { "epoch": 7.62, "learning_rate": 1.1904434985582864e-05, "loss": 1.4284, "step": 166970 }, { "epoch": 7.62, "learning_rate": 1.1902146551329581e-05, "loss": 1.3831, "step": 166980 }, { "epoch": 7.63, "learning_rate": 1.1899858117076297e-05, "loss": 1.6101, "step": 166990 }, { "epoch": 7.63, "learning_rate": 1.1897569682823013e-05, "loss": 1.5042, "step": 167000 }, { "epoch": 7.63, "learning_rate": 1.1895281248569729e-05, "loss": 1.338, "step": 167010 }, { "epoch": 7.63, "learning_rate": 1.1892992814316445e-05, "loss": 1.2906, "step": 167020 }, { "epoch": 7.63, "learning_rate": 1.189070438006316e-05, "loss": 1.4247, "step": 167030 }, { "epoch": 7.63, "learning_rate": 1.1888415945809878e-05, "loss": 1.2816, "step": 167040 }, { "epoch": 7.63, "learning_rate": 1.1886127511556594e-05, "loss": 1.4167, "step": 167050 }, { "epoch": 7.63, "learning_rate": 1.188383907730331e-05, "loss": 1.466, "step": 167060 }, { "epoch": 7.63, "learning_rate": 1.1881550643050025e-05, "loss": 1.3834, "step": 167070 }, { "epoch": 7.63, "learning_rate": 1.1879262208796741e-05, "loss": 1.4269, "step": 167080 }, { "epoch": 7.63, "learning_rate": 1.1876973774543459e-05, "loss": 1.5693, "step": 167090 }, { "epoch": 7.63, "learning_rate": 1.1874685340290175e-05, "loss": 1.3917, "step": 167100 }, { "epoch": 7.63, "learning_rate": 1.1872396906036889e-05, "loss": 1.4999, "step": 167110 }, { "epoch": 7.63, "learning_rate": 1.1870108471783606e-05, "loss": 1.2566, "step": 167120 }, { "epoch": 7.63, "learning_rate": 1.1867820037530322e-05, "loss": 1.3768, "step": 167130 }, { "epoch": 7.63, "learning_rate": 1.1865531603277038e-05, "loss": 1.4043, "step": 167140 }, { "epoch": 7.63, "learning_rate": 1.1863243169023755e-05, "loss": 1.3173, "step": 167150 }, { "epoch": 7.63, "learning_rate": 1.186095473477047e-05, "loss": 1.3684, "step": 167160 }, { "epoch": 7.63, "learning_rate": 1.1858666300517187e-05, "loss": 1.4919, "step": 167170 }, { "epoch": 7.63, "learning_rate": 1.1856377866263903e-05, "loss": 1.3681, "step": 167180 }, { "epoch": 7.63, "learning_rate": 1.1854089432010619e-05, "loss": 1.3908, "step": 167190 }, { "epoch": 7.63, "learning_rate": 1.1851800997757336e-05, "loss": 1.3851, "step": 167200 }, { "epoch": 7.64, "learning_rate": 1.184951256350405e-05, "loss": 1.322, "step": 167210 }, { "epoch": 7.64, "learning_rate": 1.1847224129250766e-05, "loss": 1.4945, "step": 167220 }, { "epoch": 7.64, "learning_rate": 1.1844935694997484e-05, "loss": 1.2506, "step": 167230 }, { "epoch": 7.64, "learning_rate": 1.18426472607442e-05, "loss": 1.3755, "step": 167240 }, { "epoch": 7.64, "learning_rate": 1.1840358826490915e-05, "loss": 1.4712, "step": 167250 }, { "epoch": 7.64, "learning_rate": 1.1838070392237631e-05, "loss": 1.1747, "step": 167260 }, { "epoch": 7.64, "learning_rate": 1.1835781957984347e-05, "loss": 1.3582, "step": 167270 }, { "epoch": 7.64, "learning_rate": 1.1833493523731063e-05, "loss": 1.3852, "step": 167280 }, { "epoch": 7.64, "learning_rate": 1.183120508947778e-05, "loss": 1.2988, "step": 167290 }, { "epoch": 7.64, "learning_rate": 1.1828916655224496e-05, "loss": 1.2199, "step": 167300 }, { "epoch": 7.64, "learning_rate": 1.1826628220971212e-05, "loss": 1.4805, "step": 167310 }, { "epoch": 7.64, "learning_rate": 1.1824339786717928e-05, "loss": 1.4284, "step": 167320 }, { "epoch": 7.64, "learning_rate": 1.1822051352464644e-05, "loss": 1.4168, "step": 167330 }, { "epoch": 7.64, "learning_rate": 1.1819762918211361e-05, "loss": 1.4413, "step": 167340 }, { "epoch": 7.64, "learning_rate": 1.1817474483958077e-05, "loss": 1.4186, "step": 167350 }, { "epoch": 7.64, "learning_rate": 1.1815186049704791e-05, "loss": 1.419, "step": 167360 }, { "epoch": 7.64, "learning_rate": 1.1812897615451509e-05, "loss": 1.3487, "step": 167370 }, { "epoch": 7.64, "learning_rate": 1.1810609181198225e-05, "loss": 1.4349, "step": 167380 }, { "epoch": 7.64, "learning_rate": 1.180832074694494e-05, "loss": 1.4548, "step": 167390 }, { "epoch": 7.64, "learning_rate": 1.1806032312691658e-05, "loss": 1.4723, "step": 167400 }, { "epoch": 7.64, "learning_rate": 1.1803743878438372e-05, "loss": 1.4047, "step": 167410 }, { "epoch": 7.64, "learning_rate": 1.180145544418509e-05, "loss": 1.3764, "step": 167420 }, { "epoch": 7.65, "learning_rate": 1.1799167009931805e-05, "loss": 1.3454, "step": 167430 }, { "epoch": 7.65, "learning_rate": 1.1796878575678521e-05, "loss": 1.261, "step": 167440 }, { "epoch": 7.65, "learning_rate": 1.1794590141425239e-05, "loss": 1.3799, "step": 167450 }, { "epoch": 7.65, "learning_rate": 1.1792301707171953e-05, "loss": 1.3142, "step": 167460 }, { "epoch": 7.65, "learning_rate": 1.1790013272918669e-05, "loss": 1.5089, "step": 167470 }, { "epoch": 7.65, "learning_rate": 1.1787724838665386e-05, "loss": 1.3624, "step": 167480 }, { "epoch": 7.65, "learning_rate": 1.1785436404412102e-05, "loss": 1.3737, "step": 167490 }, { "epoch": 7.65, "learning_rate": 1.1783147970158818e-05, "loss": 1.2859, "step": 167500 }, { "epoch": 7.65, "learning_rate": 1.1780859535905534e-05, "loss": 1.4348, "step": 167510 }, { "epoch": 7.65, "learning_rate": 1.177857110165225e-05, "loss": 1.3114, "step": 167520 }, { "epoch": 7.65, "learning_rate": 1.1776282667398967e-05, "loss": 1.4302, "step": 167530 }, { "epoch": 7.65, "learning_rate": 1.1773994233145683e-05, "loss": 1.4777, "step": 167540 }, { "epoch": 7.65, "learning_rate": 1.1771705798892399e-05, "loss": 1.3688, "step": 167550 }, { "epoch": 7.65, "learning_rate": 1.1769417364639115e-05, "loss": 1.2932, "step": 167560 }, { "epoch": 7.65, "learning_rate": 1.176712893038583e-05, "loss": 1.5191, "step": 167570 }, { "epoch": 7.65, "learning_rate": 1.1764840496132546e-05, "loss": 1.4268, "step": 167580 }, { "epoch": 7.65, "learning_rate": 1.1762552061879264e-05, "loss": 1.3564, "step": 167590 }, { "epoch": 7.65, "learning_rate": 1.176026362762598e-05, "loss": 1.443, "step": 167600 }, { "epoch": 7.65, "learning_rate": 1.1757975193372694e-05, "loss": 1.4064, "step": 167610 }, { "epoch": 7.65, "learning_rate": 1.1755686759119411e-05, "loss": 1.3318, "step": 167620 }, { "epoch": 7.65, "learning_rate": 1.1753398324866127e-05, "loss": 1.3873, "step": 167630 }, { "epoch": 7.65, "learning_rate": 1.1751109890612843e-05, "loss": 1.2902, "step": 167640 }, { "epoch": 7.66, "learning_rate": 1.174882145635956e-05, "loss": 1.5559, "step": 167650 }, { "epoch": 7.66, "learning_rate": 1.1746533022106275e-05, "loss": 1.39, "step": 167660 }, { "epoch": 7.66, "learning_rate": 1.1744244587852992e-05, "loss": 1.5689, "step": 167670 }, { "epoch": 7.66, "learning_rate": 1.1741956153599708e-05, "loss": 1.3527, "step": 167680 }, { "epoch": 7.66, "learning_rate": 1.1739667719346424e-05, "loss": 1.2875, "step": 167690 }, { "epoch": 7.66, "learning_rate": 1.1737379285093141e-05, "loss": 1.3295, "step": 167700 }, { "epoch": 7.66, "learning_rate": 1.1735090850839855e-05, "loss": 1.4812, "step": 167710 }, { "epoch": 7.66, "learning_rate": 1.1732802416586571e-05, "loss": 1.3333, "step": 167720 }, { "epoch": 7.66, "learning_rate": 1.1730513982333289e-05, "loss": 1.4532, "step": 167730 }, { "epoch": 7.66, "learning_rate": 1.1728225548080005e-05, "loss": 1.4818, "step": 167740 }, { "epoch": 7.66, "learning_rate": 1.172593711382672e-05, "loss": 1.4752, "step": 167750 }, { "epoch": 7.66, "learning_rate": 1.1723648679573436e-05, "loss": 1.2696, "step": 167760 }, { "epoch": 7.66, "learning_rate": 1.1721360245320152e-05, "loss": 1.4982, "step": 167770 }, { "epoch": 7.66, "learning_rate": 1.171907181106687e-05, "loss": 1.442, "step": 167780 }, { "epoch": 7.66, "learning_rate": 1.1716783376813585e-05, "loss": 1.3789, "step": 167790 }, { "epoch": 7.66, "learning_rate": 1.17144949425603e-05, "loss": 1.3301, "step": 167800 }, { "epoch": 7.66, "learning_rate": 1.1712206508307017e-05, "loss": 1.4873, "step": 167810 }, { "epoch": 7.66, "learning_rate": 1.1709918074053733e-05, "loss": 1.38, "step": 167820 }, { "epoch": 7.66, "learning_rate": 1.1707629639800449e-05, "loss": 1.3436, "step": 167830 }, { "epoch": 7.66, "learning_rate": 1.1705341205547166e-05, "loss": 1.2725, "step": 167840 }, { "epoch": 7.66, "learning_rate": 1.170305277129388e-05, "loss": 1.3129, "step": 167850 }, { "epoch": 7.66, "learning_rate": 1.1700764337040598e-05, "loss": 1.5116, "step": 167860 }, { "epoch": 7.67, "learning_rate": 1.1698475902787314e-05, "loss": 1.3388, "step": 167870 }, { "epoch": 7.67, "learning_rate": 1.169618746853403e-05, "loss": 1.3401, "step": 167880 }, { "epoch": 7.67, "learning_rate": 1.1693899034280745e-05, "loss": 1.4448, "step": 167890 }, { "epoch": 7.67, "learning_rate": 1.1691610600027461e-05, "loss": 1.3698, "step": 167900 }, { "epoch": 7.67, "learning_rate": 1.1689322165774177e-05, "loss": 1.4023, "step": 167910 }, { "epoch": 7.67, "learning_rate": 1.1687033731520894e-05, "loss": 1.3762, "step": 167920 }, { "epoch": 7.67, "learning_rate": 1.168474529726761e-05, "loss": 1.4085, "step": 167930 }, { "epoch": 7.67, "learning_rate": 1.1682456863014326e-05, "loss": 1.3757, "step": 167940 }, { "epoch": 7.67, "learning_rate": 1.1680168428761042e-05, "loss": 1.4692, "step": 167950 }, { "epoch": 7.67, "learning_rate": 1.1677879994507758e-05, "loss": 1.3979, "step": 167960 }, { "epoch": 7.67, "learning_rate": 1.1675591560254474e-05, "loss": 1.4115, "step": 167970 }, { "epoch": 7.67, "learning_rate": 1.1673303126001191e-05, "loss": 1.2871, "step": 167980 }, { "epoch": 7.67, "learning_rate": 1.1671014691747907e-05, "loss": 1.2894, "step": 167990 }, { "epoch": 7.67, "learning_rate": 1.1668726257494623e-05, "loss": 1.4662, "step": 168000 }, { "epoch": 7.67, "learning_rate": 1.1666437823241339e-05, "loss": 1.2659, "step": 168010 }, { "epoch": 7.67, "learning_rate": 1.1664149388988054e-05, "loss": 1.527, "step": 168020 }, { "epoch": 7.67, "learning_rate": 1.1661860954734772e-05, "loss": 1.2124, "step": 168030 }, { "epoch": 7.67, "learning_rate": 1.1659572520481488e-05, "loss": 1.3883, "step": 168040 }, { "epoch": 7.67, "learning_rate": 1.1657284086228202e-05, "loss": 1.401, "step": 168050 }, { "epoch": 7.67, "learning_rate": 1.165499565197492e-05, "loss": 1.2908, "step": 168060 }, { "epoch": 7.67, "learning_rate": 1.1652707217721635e-05, "loss": 1.36, "step": 168070 }, { "epoch": 7.67, "learning_rate": 1.1650418783468351e-05, "loss": 1.2222, "step": 168080 }, { "epoch": 7.68, "learning_rate": 1.1648130349215069e-05, "loss": 1.3218, "step": 168090 }, { "epoch": 7.68, "learning_rate": 1.1645841914961783e-05, "loss": 1.3271, "step": 168100 }, { "epoch": 7.68, "learning_rate": 1.16435534807085e-05, "loss": 1.3933, "step": 168110 }, { "epoch": 7.68, "learning_rate": 1.1641265046455216e-05, "loss": 1.5105, "step": 168120 }, { "epoch": 7.68, "learning_rate": 1.1638976612201932e-05, "loss": 1.305, "step": 168130 }, { "epoch": 7.68, "learning_rate": 1.1636688177948648e-05, "loss": 1.3606, "step": 168140 }, { "epoch": 7.68, "learning_rate": 1.1634399743695364e-05, "loss": 1.4841, "step": 168150 }, { "epoch": 7.68, "learning_rate": 1.163211130944208e-05, "loss": 1.2506, "step": 168160 }, { "epoch": 7.68, "learning_rate": 1.1629822875188797e-05, "loss": 1.321, "step": 168170 }, { "epoch": 7.68, "learning_rate": 1.1627534440935513e-05, "loss": 1.321, "step": 168180 }, { "epoch": 7.68, "learning_rate": 1.1625246006682229e-05, "loss": 1.4458, "step": 168190 }, { "epoch": 7.68, "learning_rate": 1.1622957572428944e-05, "loss": 1.4334, "step": 168200 }, { "epoch": 7.68, "learning_rate": 1.162066913817566e-05, "loss": 1.3189, "step": 168210 }, { "epoch": 7.68, "learning_rate": 1.1618380703922376e-05, "loss": 1.4018, "step": 168220 }, { "epoch": 7.68, "learning_rate": 1.1616092269669094e-05, "loss": 1.5425, "step": 168230 }, { "epoch": 7.68, "learning_rate": 1.161380383541581e-05, "loss": 1.4203, "step": 168240 }, { "epoch": 7.68, "learning_rate": 1.1611515401162525e-05, "loss": 1.2813, "step": 168250 }, { "epoch": 7.68, "learning_rate": 1.1609226966909241e-05, "loss": 1.3484, "step": 168260 }, { "epoch": 7.68, "learning_rate": 1.1606938532655957e-05, "loss": 1.42, "step": 168270 }, { "epoch": 7.68, "learning_rate": 1.1604650098402674e-05, "loss": 1.2845, "step": 168280 }, { "epoch": 7.68, "learning_rate": 1.160236166414939e-05, "loss": 1.4177, "step": 168290 }, { "epoch": 7.69, "learning_rate": 1.1600073229896104e-05, "loss": 1.4524, "step": 168300 }, { "epoch": 7.69, "learning_rate": 1.1597784795642822e-05, "loss": 1.2614, "step": 168310 }, { "epoch": 7.69, "learning_rate": 1.1595496361389538e-05, "loss": 1.3118, "step": 168320 }, { "epoch": 7.69, "learning_rate": 1.1593207927136254e-05, "loss": 1.262, "step": 168330 }, { "epoch": 7.69, "learning_rate": 1.1590919492882971e-05, "loss": 1.1706, "step": 168340 }, { "epoch": 7.69, "learning_rate": 1.1588631058629685e-05, "loss": 1.3167, "step": 168350 }, { "epoch": 7.69, "learning_rate": 1.1586342624376403e-05, "loss": 1.3164, "step": 168360 }, { "epoch": 7.69, "learning_rate": 1.1584054190123119e-05, "loss": 1.3504, "step": 168370 }, { "epoch": 7.69, "learning_rate": 1.1581765755869834e-05, "loss": 1.4801, "step": 168380 }, { "epoch": 7.69, "learning_rate": 1.1579477321616552e-05, "loss": 1.3892, "step": 168390 }, { "epoch": 7.69, "learning_rate": 1.1577188887363266e-05, "loss": 1.324, "step": 168400 }, { "epoch": 7.69, "learning_rate": 1.1574900453109982e-05, "loss": 1.4902, "step": 168410 }, { "epoch": 7.69, "learning_rate": 1.15726120188567e-05, "loss": 1.3889, "step": 168420 }, { "epoch": 7.69, "learning_rate": 1.1570323584603415e-05, "loss": 1.5481, "step": 168430 }, { "epoch": 7.69, "learning_rate": 1.1568035150350131e-05, "loss": 1.27, "step": 168440 }, { "epoch": 7.69, "learning_rate": 1.1565746716096847e-05, "loss": 1.3463, "step": 168450 }, { "epoch": 7.69, "learning_rate": 1.1563458281843563e-05, "loss": 1.3682, "step": 168460 }, { "epoch": 7.69, "learning_rate": 1.1561169847590279e-05, "loss": 1.5344, "step": 168470 }, { "epoch": 7.69, "learning_rate": 1.1558881413336996e-05, "loss": 1.3481, "step": 168480 }, { "epoch": 7.69, "learning_rate": 1.1556592979083712e-05, "loss": 1.5055, "step": 168490 }, { "epoch": 7.69, "learning_rate": 1.1554304544830428e-05, "loss": 1.4146, "step": 168500 }, { "epoch": 7.69, "learning_rate": 1.1552016110577144e-05, "loss": 1.4024, "step": 168510 }, { "epoch": 7.7, "learning_rate": 1.154972767632386e-05, "loss": 1.4617, "step": 168520 }, { "epoch": 7.7, "learning_rate": 1.1547439242070577e-05, "loss": 1.3515, "step": 168530 }, { "epoch": 7.7, "learning_rate": 1.1545150807817293e-05, "loss": 1.437, "step": 168540 }, { "epoch": 7.7, "learning_rate": 1.1542862373564007e-05, "loss": 1.4628, "step": 168550 }, { "epoch": 7.7, "learning_rate": 1.1540573939310724e-05, "loss": 1.308, "step": 168560 }, { "epoch": 7.7, "learning_rate": 1.153828550505744e-05, "loss": 1.2572, "step": 168570 }, { "epoch": 7.7, "learning_rate": 1.1535997070804156e-05, "loss": 1.3548, "step": 168580 }, { "epoch": 7.7, "learning_rate": 1.1533708636550874e-05, "loss": 1.4776, "step": 168590 }, { "epoch": 7.7, "learning_rate": 1.1531420202297588e-05, "loss": 1.3329, "step": 168600 }, { "epoch": 7.7, "learning_rate": 1.1529131768044305e-05, "loss": 1.2974, "step": 168610 }, { "epoch": 7.7, "learning_rate": 1.1526843333791021e-05, "loss": 1.4351, "step": 168620 }, { "epoch": 7.7, "learning_rate": 1.1524554899537737e-05, "loss": 1.4617, "step": 168630 }, { "epoch": 7.7, "learning_rate": 1.1522266465284453e-05, "loss": 1.1442, "step": 168640 }, { "epoch": 7.7, "learning_rate": 1.1519978031031169e-05, "loss": 1.3982, "step": 168650 }, { "epoch": 7.7, "learning_rate": 1.1517689596777884e-05, "loss": 1.3936, "step": 168660 }, { "epoch": 7.7, "learning_rate": 1.1515401162524602e-05, "loss": 1.4303, "step": 168670 }, { "epoch": 7.7, "learning_rate": 1.1513112728271318e-05, "loss": 1.3547, "step": 168680 }, { "epoch": 7.7, "learning_rate": 1.1510824294018034e-05, "loss": 1.4082, "step": 168690 }, { "epoch": 7.7, "learning_rate": 1.150853585976475e-05, "loss": 1.3978, "step": 168700 }, { "epoch": 7.7, "learning_rate": 1.1506247425511465e-05, "loss": 1.4867, "step": 168710 }, { "epoch": 7.7, "learning_rate": 1.1503958991258183e-05, "loss": 1.3528, "step": 168720 }, { "epoch": 7.7, "learning_rate": 1.1501670557004899e-05, "loss": 1.5235, "step": 168730 }, { "epoch": 7.71, "learning_rate": 1.1499382122751613e-05, "loss": 1.3635, "step": 168740 }, { "epoch": 7.71, "learning_rate": 1.149709368849833e-05, "loss": 1.5037, "step": 168750 }, { "epoch": 7.71, "learning_rate": 1.1494805254245046e-05, "loss": 1.3535, "step": 168760 }, { "epoch": 7.71, "learning_rate": 1.1492516819991762e-05, "loss": 1.3499, "step": 168770 }, { "epoch": 7.71, "learning_rate": 1.149022838573848e-05, "loss": 1.2938, "step": 168780 }, { "epoch": 7.71, "learning_rate": 1.1487939951485194e-05, "loss": 1.3634, "step": 168790 }, { "epoch": 7.71, "learning_rate": 1.148565151723191e-05, "loss": 1.4564, "step": 168800 }, { "epoch": 7.71, "learning_rate": 1.1483363082978627e-05, "loss": 1.2383, "step": 168810 }, { "epoch": 7.71, "learning_rate": 1.1481074648725343e-05, "loss": 1.396, "step": 168820 }, { "epoch": 7.71, "learning_rate": 1.1478786214472059e-05, "loss": 1.5241, "step": 168830 }, { "epoch": 7.71, "learning_rate": 1.1476497780218774e-05, "loss": 1.382, "step": 168840 }, { "epoch": 7.71, "learning_rate": 1.147420934596549e-05, "loss": 1.4083, "step": 168850 }, { "epoch": 7.71, "learning_rate": 1.1471920911712208e-05, "loss": 1.3868, "step": 168860 }, { "epoch": 7.71, "learning_rate": 1.1469632477458924e-05, "loss": 1.2952, "step": 168870 }, { "epoch": 7.71, "learning_rate": 1.146734404320564e-05, "loss": 1.4281, "step": 168880 }, { "epoch": 7.71, "learning_rate": 1.1465055608952355e-05, "loss": 1.3791, "step": 168890 }, { "epoch": 7.71, "learning_rate": 1.1462767174699071e-05, "loss": 1.3498, "step": 168900 }, { "epoch": 7.71, "learning_rate": 1.1460478740445787e-05, "loss": 1.4118, "step": 168910 }, { "epoch": 7.71, "learning_rate": 1.1458190306192504e-05, "loss": 1.2899, "step": 168920 }, { "epoch": 7.71, "learning_rate": 1.145590187193922e-05, "loss": 1.344, "step": 168930 }, { "epoch": 7.71, "learning_rate": 1.1453613437685936e-05, "loss": 1.395, "step": 168940 }, { "epoch": 7.71, "learning_rate": 1.1451325003432652e-05, "loss": 1.2558, "step": 168950 }, { "epoch": 7.72, "learning_rate": 1.1449036569179368e-05, "loss": 1.4073, "step": 168960 }, { "epoch": 7.72, "learning_rate": 1.1446748134926085e-05, "loss": 1.54, "step": 168970 }, { "epoch": 7.72, "learning_rate": 1.1444459700672801e-05, "loss": 1.2688, "step": 168980 }, { "epoch": 7.72, "learning_rate": 1.1442171266419515e-05, "loss": 1.3643, "step": 168990 }, { "epoch": 7.72, "learning_rate": 1.1439882832166233e-05, "loss": 1.3511, "step": 169000 }, { "epoch": 7.72, "learning_rate": 1.1437594397912949e-05, "loss": 1.1991, "step": 169010 }, { "epoch": 7.72, "learning_rate": 1.1435305963659664e-05, "loss": 1.1877, "step": 169020 }, { "epoch": 7.72, "learning_rate": 1.1433017529406382e-05, "loss": 1.3487, "step": 169030 }, { "epoch": 7.72, "learning_rate": 1.1430729095153096e-05, "loss": 1.363, "step": 169040 }, { "epoch": 7.72, "learning_rate": 1.1428440660899812e-05, "loss": 1.4311, "step": 169050 }, { "epoch": 7.72, "learning_rate": 1.142615222664653e-05, "loss": 1.4073, "step": 169060 }, { "epoch": 7.72, "learning_rate": 1.1423863792393245e-05, "loss": 1.3044, "step": 169070 }, { "epoch": 7.72, "learning_rate": 1.1421575358139961e-05, "loss": 1.3606, "step": 169080 }, { "epoch": 7.72, "learning_rate": 1.1419286923886677e-05, "loss": 1.1949, "step": 169090 }, { "epoch": 7.72, "learning_rate": 1.1416998489633393e-05, "loss": 1.2935, "step": 169100 }, { "epoch": 7.72, "learning_rate": 1.141471005538011e-05, "loss": 1.4625, "step": 169110 }, { "epoch": 7.72, "learning_rate": 1.1412421621126826e-05, "loss": 1.2359, "step": 169120 }, { "epoch": 7.72, "learning_rate": 1.1410133186873542e-05, "loss": 1.3195, "step": 169130 }, { "epoch": 7.72, "learning_rate": 1.1407844752620258e-05, "loss": 1.2526, "step": 169140 }, { "epoch": 7.72, "learning_rate": 1.1405556318366973e-05, "loss": 1.376, "step": 169150 }, { "epoch": 7.72, "learning_rate": 1.140326788411369e-05, "loss": 1.3625, "step": 169160 }, { "epoch": 7.72, "learning_rate": 1.1400979449860407e-05, "loss": 1.24, "step": 169170 }, { "epoch": 7.73, "learning_rate": 1.1398691015607123e-05, "loss": 1.3829, "step": 169180 }, { "epoch": 7.73, "learning_rate": 1.1396402581353838e-05, "loss": 1.3971, "step": 169190 }, { "epoch": 7.73, "learning_rate": 1.1394114147100554e-05, "loss": 1.311, "step": 169200 }, { "epoch": 7.73, "learning_rate": 1.139182571284727e-05, "loss": 1.4249, "step": 169210 }, { "epoch": 7.73, "learning_rate": 1.1389537278593988e-05, "loss": 1.4938, "step": 169220 }, { "epoch": 7.73, "learning_rate": 1.1387248844340703e-05, "loss": 1.3241, "step": 169230 }, { "epoch": 7.73, "learning_rate": 1.1384960410087418e-05, "loss": 1.4647, "step": 169240 }, { "epoch": 7.73, "learning_rate": 1.1382671975834135e-05, "loss": 1.4875, "step": 169250 }, { "epoch": 7.73, "learning_rate": 1.1380383541580851e-05, "loss": 1.3913, "step": 169260 }, { "epoch": 7.73, "learning_rate": 1.1378095107327567e-05, "loss": 1.36, "step": 169270 }, { "epoch": 7.73, "learning_rate": 1.1375806673074284e-05, "loss": 1.3571, "step": 169280 }, { "epoch": 7.73, "learning_rate": 1.1373518238820998e-05, "loss": 1.3992, "step": 169290 }, { "epoch": 7.73, "learning_rate": 1.1371229804567716e-05, "loss": 1.3224, "step": 169300 }, { "epoch": 7.73, "learning_rate": 1.1368941370314432e-05, "loss": 1.1181, "step": 169310 }, { "epoch": 7.73, "learning_rate": 1.1366652936061148e-05, "loss": 1.422, "step": 169320 }, { "epoch": 7.73, "learning_rate": 1.1364364501807863e-05, "loss": 1.3082, "step": 169330 }, { "epoch": 7.73, "learning_rate": 1.136207606755458e-05, "loss": 1.2926, "step": 169340 }, { "epoch": 7.73, "learning_rate": 1.1359787633301295e-05, "loss": 1.2985, "step": 169350 }, { "epoch": 7.73, "learning_rate": 1.1357499199048013e-05, "loss": 1.4663, "step": 169360 }, { "epoch": 7.73, "learning_rate": 1.1355210764794728e-05, "loss": 1.3755, "step": 169370 }, { "epoch": 7.73, "learning_rate": 1.1352922330541444e-05, "loss": 1.3956, "step": 169380 }, { "epoch": 7.73, "learning_rate": 1.135063389628816e-05, "loss": 1.3318, "step": 169390 }, { "epoch": 7.74, "learning_rate": 1.1348345462034876e-05, "loss": 1.3189, "step": 169400 }, { "epoch": 7.74, "learning_rate": 1.1346057027781592e-05, "loss": 1.3676, "step": 169410 }, { "epoch": 7.74, "learning_rate": 1.134376859352831e-05, "loss": 1.5141, "step": 169420 }, { "epoch": 7.74, "learning_rate": 1.1341480159275023e-05, "loss": 1.4236, "step": 169430 }, { "epoch": 7.74, "learning_rate": 1.1339191725021741e-05, "loss": 1.3058, "step": 169440 }, { "epoch": 7.74, "learning_rate": 1.1336903290768457e-05, "loss": 1.2908, "step": 169450 }, { "epoch": 7.74, "learning_rate": 1.1334614856515173e-05, "loss": 1.3465, "step": 169460 }, { "epoch": 7.74, "learning_rate": 1.133232642226189e-05, "loss": 1.2446, "step": 169470 }, { "epoch": 7.74, "learning_rate": 1.1330037988008604e-05, "loss": 1.4707, "step": 169480 }, { "epoch": 7.74, "learning_rate": 1.132774955375532e-05, "loss": 1.5626, "step": 169490 }, { "epoch": 7.74, "learning_rate": 1.1325461119502038e-05, "loss": 1.3722, "step": 169500 }, { "epoch": 7.74, "learning_rate": 1.1323172685248753e-05, "loss": 1.2418, "step": 169510 }, { "epoch": 7.74, "learning_rate": 1.132088425099547e-05, "loss": 1.4364, "step": 169520 }, { "epoch": 7.74, "learning_rate": 1.1318595816742185e-05, "loss": 1.379, "step": 169530 }, { "epoch": 7.74, "learning_rate": 1.1316307382488901e-05, "loss": 1.4101, "step": 169540 }, { "epoch": 7.74, "learning_rate": 1.1314018948235618e-05, "loss": 1.237, "step": 169550 }, { "epoch": 7.74, "learning_rate": 1.1311730513982334e-05, "loss": 1.3534, "step": 169560 }, { "epoch": 7.74, "learning_rate": 1.130944207972905e-05, "loss": 1.4146, "step": 169570 }, { "epoch": 7.74, "learning_rate": 1.1307153645475766e-05, "loss": 1.4379, "step": 169580 }, { "epoch": 7.74, "learning_rate": 1.1304865211222482e-05, "loss": 1.3592, "step": 169590 }, { "epoch": 7.74, "learning_rate": 1.1302576776969198e-05, "loss": 1.3791, "step": 169600 }, { "epoch": 7.74, "learning_rate": 1.1300288342715915e-05, "loss": 1.2579, "step": 169610 }, { "epoch": 7.75, "learning_rate": 1.1297999908462631e-05, "loss": 1.4615, "step": 169620 }, { "epoch": 7.75, "learning_rate": 1.1295711474209345e-05, "loss": 1.4327, "step": 169630 }, { "epoch": 7.75, "learning_rate": 1.1293423039956063e-05, "loss": 1.3045, "step": 169640 }, { "epoch": 7.75, "learning_rate": 1.1291134605702778e-05, "loss": 1.3398, "step": 169650 }, { "epoch": 7.75, "learning_rate": 1.1288846171449494e-05, "loss": 1.338, "step": 169660 }, { "epoch": 7.75, "learning_rate": 1.1286557737196212e-05, "loss": 1.348, "step": 169670 }, { "epoch": 7.75, "learning_rate": 1.1284269302942926e-05, "loss": 1.4758, "step": 169680 }, { "epoch": 7.75, "learning_rate": 1.1281980868689643e-05, "loss": 1.3952, "step": 169690 }, { "epoch": 7.75, "learning_rate": 1.127969243443636e-05, "loss": 1.3434, "step": 169700 }, { "epoch": 7.75, "learning_rate": 1.1277404000183075e-05, "loss": 1.375, "step": 169710 }, { "epoch": 7.75, "learning_rate": 1.1275115565929793e-05, "loss": 1.3149, "step": 169720 }, { "epoch": 7.75, "learning_rate": 1.1272827131676507e-05, "loss": 1.3969, "step": 169730 }, { "epoch": 7.75, "learning_rate": 1.1270538697423223e-05, "loss": 1.5694, "step": 169740 }, { "epoch": 7.75, "learning_rate": 1.126825026316994e-05, "loss": 1.2277, "step": 169750 }, { "epoch": 7.75, "learning_rate": 1.1265961828916656e-05, "loss": 1.2341, "step": 169760 }, { "epoch": 7.75, "learning_rate": 1.1263673394663372e-05, "loss": 1.6838, "step": 169770 }, { "epoch": 7.75, "learning_rate": 1.1261384960410088e-05, "loss": 1.2216, "step": 169780 }, { "epoch": 7.75, "learning_rate": 1.1259096526156803e-05, "loss": 1.1591, "step": 169790 }, { "epoch": 7.75, "learning_rate": 1.1256808091903521e-05, "loss": 1.3716, "step": 169800 }, { "epoch": 7.75, "learning_rate": 1.1254519657650237e-05, "loss": 1.3142, "step": 169810 }, { "epoch": 7.75, "learning_rate": 1.1252231223396953e-05, "loss": 1.4136, "step": 169820 }, { "epoch": 7.75, "learning_rate": 1.1249942789143668e-05, "loss": 1.493, "step": 169830 }, { "epoch": 7.76, "learning_rate": 1.1247654354890384e-05, "loss": 1.4356, "step": 169840 }, { "epoch": 7.76, "learning_rate": 1.12453659206371e-05, "loss": 1.4343, "step": 169850 }, { "epoch": 7.76, "learning_rate": 1.1243077486383818e-05, "loss": 1.3632, "step": 169860 }, { "epoch": 7.76, "learning_rate": 1.1240789052130533e-05, "loss": 1.3644, "step": 169870 }, { "epoch": 7.76, "learning_rate": 1.123850061787725e-05, "loss": 1.36, "step": 169880 }, { "epoch": 7.76, "learning_rate": 1.1236212183623965e-05, "loss": 1.344, "step": 169890 }, { "epoch": 7.76, "learning_rate": 1.1233923749370681e-05, "loss": 1.3333, "step": 169900 }, { "epoch": 7.76, "learning_rate": 1.1231635315117397e-05, "loss": 1.4015, "step": 169910 }, { "epoch": 7.76, "learning_rate": 1.1229346880864114e-05, "loss": 1.3752, "step": 169920 }, { "epoch": 7.76, "learning_rate": 1.1227058446610828e-05, "loss": 1.3188, "step": 169930 }, { "epoch": 7.76, "learning_rate": 1.1224770012357546e-05, "loss": 1.4545, "step": 169940 }, { "epoch": 7.76, "learning_rate": 1.1222481578104262e-05, "loss": 1.2994, "step": 169950 }, { "epoch": 7.76, "learning_rate": 1.1220193143850978e-05, "loss": 1.252, "step": 169960 }, { "epoch": 7.76, "learning_rate": 1.1217904709597695e-05, "loss": 1.5391, "step": 169970 }, { "epoch": 7.76, "learning_rate": 1.121561627534441e-05, "loss": 1.3624, "step": 169980 }, { "epoch": 7.76, "learning_rate": 1.1213327841091125e-05, "loss": 1.4307, "step": 169990 }, { "epoch": 7.76, "learning_rate": 1.1211039406837843e-05, "loss": 1.2734, "step": 170000 }, { "epoch": 7.76, "learning_rate": 1.1208750972584558e-05, "loss": 1.3142, "step": 170010 }, { "epoch": 7.76, "learning_rate": 1.1206462538331274e-05, "loss": 1.3988, "step": 170020 }, { "epoch": 7.76, "learning_rate": 1.120417410407799e-05, "loss": 1.2375, "step": 170030 }, { "epoch": 7.76, "learning_rate": 1.1201885669824706e-05, "loss": 1.581, "step": 170040 }, { "epoch": 7.76, "learning_rate": 1.1199597235571423e-05, "loss": 1.2512, "step": 170050 }, { "epoch": 7.77, "learning_rate": 1.119730880131814e-05, "loss": 1.5163, "step": 170060 }, { "epoch": 7.77, "learning_rate": 1.1195020367064855e-05, "loss": 1.3292, "step": 170070 }, { "epoch": 7.77, "learning_rate": 1.1192731932811571e-05, "loss": 1.3415, "step": 170080 }, { "epoch": 7.77, "learning_rate": 1.1190443498558287e-05, "loss": 1.4079, "step": 170090 }, { "epoch": 7.77, "learning_rate": 1.1188155064305003e-05, "loss": 1.438, "step": 170100 }, { "epoch": 7.77, "learning_rate": 1.118586663005172e-05, "loss": 1.4141, "step": 170110 }, { "epoch": 7.77, "learning_rate": 1.1183578195798436e-05, "loss": 1.3482, "step": 170120 }, { "epoch": 7.77, "learning_rate": 1.1181289761545152e-05, "loss": 1.4171, "step": 170130 }, { "epoch": 7.77, "learning_rate": 1.1179001327291868e-05, "loss": 1.3864, "step": 170140 }, { "epoch": 7.77, "learning_rate": 1.1176712893038583e-05, "loss": 1.4036, "step": 170150 }, { "epoch": 7.77, "learning_rate": 1.1174424458785301e-05, "loss": 1.324, "step": 170160 }, { "epoch": 7.77, "learning_rate": 1.1172136024532017e-05, "loss": 1.4003, "step": 170170 }, { "epoch": 7.77, "learning_rate": 1.116984759027873e-05, "loss": 1.6048, "step": 170180 }, { "epoch": 7.77, "learning_rate": 1.1167559156025448e-05, "loss": 1.1846, "step": 170190 }, { "epoch": 7.77, "learning_rate": 1.1165270721772164e-05, "loss": 1.2654, "step": 170200 }, { "epoch": 7.77, "learning_rate": 1.116298228751888e-05, "loss": 1.5462, "step": 170210 }, { "epoch": 7.77, "learning_rate": 1.1160693853265596e-05, "loss": 1.4398, "step": 170220 }, { "epoch": 7.77, "learning_rate": 1.1158405419012312e-05, "loss": 1.5455, "step": 170230 }, { "epoch": 7.77, "learning_rate": 1.1156116984759027e-05, "loss": 1.4791, "step": 170240 }, { "epoch": 7.77, "learning_rate": 1.1153828550505745e-05, "loss": 1.5024, "step": 170250 }, { "epoch": 7.77, "learning_rate": 1.115154011625246e-05, "loss": 1.2772, "step": 170260 }, { "epoch": 7.77, "learning_rate": 1.1149251681999177e-05, "loss": 1.2925, "step": 170270 }, { "epoch": 7.78, "learning_rate": 1.1146963247745892e-05, "loss": 1.2692, "step": 170280 }, { "epoch": 7.78, "learning_rate": 1.1144674813492608e-05, "loss": 1.1959, "step": 170290 }, { "epoch": 7.78, "learning_rate": 1.1142386379239326e-05, "loss": 1.1712, "step": 170300 }, { "epoch": 7.78, "learning_rate": 1.1140097944986042e-05, "loss": 1.2516, "step": 170310 }, { "epoch": 7.78, "learning_rate": 1.1137809510732756e-05, "loss": 1.393, "step": 170320 }, { "epoch": 7.78, "learning_rate": 1.1135521076479473e-05, "loss": 1.3142, "step": 170330 }, { "epoch": 7.78, "learning_rate": 1.113323264222619e-05, "loss": 1.1994, "step": 170340 }, { "epoch": 7.78, "learning_rate": 1.1130944207972905e-05, "loss": 1.3884, "step": 170350 }, { "epoch": 7.78, "learning_rate": 1.1128655773719623e-05, "loss": 1.4188, "step": 170360 }, { "epoch": 7.78, "learning_rate": 1.1126367339466337e-05, "loss": 1.5877, "step": 170370 }, { "epoch": 7.78, "learning_rate": 1.1124078905213054e-05, "loss": 1.3779, "step": 170380 }, { "epoch": 7.78, "learning_rate": 1.112179047095977e-05, "loss": 1.372, "step": 170390 }, { "epoch": 7.78, "learning_rate": 1.1119502036706486e-05, "loss": 1.2173, "step": 170400 }, { "epoch": 7.78, "learning_rate": 1.1117213602453203e-05, "loss": 1.4586, "step": 170410 }, { "epoch": 7.78, "learning_rate": 1.1114925168199917e-05, "loss": 1.3005, "step": 170420 }, { "epoch": 7.78, "learning_rate": 1.1112636733946633e-05, "loss": 1.34, "step": 170430 }, { "epoch": 7.78, "learning_rate": 1.111034829969335e-05, "loss": 1.4811, "step": 170440 }, { "epoch": 7.78, "learning_rate": 1.1108059865440067e-05, "loss": 1.422, "step": 170450 }, { "epoch": 7.78, "learning_rate": 1.1105771431186782e-05, "loss": 1.4454, "step": 170460 }, { "epoch": 7.78, "learning_rate": 1.1103482996933498e-05, "loss": 1.347, "step": 170470 }, { "epoch": 7.78, "learning_rate": 1.1101194562680214e-05, "loss": 1.3787, "step": 170480 }, { "epoch": 7.79, "learning_rate": 1.109890612842693e-05, "loss": 1.3075, "step": 170490 }, { "epoch": 7.79, "learning_rate": 1.1096617694173647e-05, "loss": 1.5407, "step": 170500 }, { "epoch": 7.79, "learning_rate": 1.1094329259920363e-05, "loss": 1.318, "step": 170510 }, { "epoch": 7.79, "learning_rate": 1.1092040825667079e-05, "loss": 1.2586, "step": 170520 }, { "epoch": 7.79, "learning_rate": 1.1089752391413795e-05, "loss": 1.4677, "step": 170530 }, { "epoch": 7.79, "learning_rate": 1.108746395716051e-05, "loss": 1.3006, "step": 170540 }, { "epoch": 7.79, "learning_rate": 1.1085175522907228e-05, "loss": 1.388, "step": 170550 }, { "epoch": 7.79, "learning_rate": 1.1082887088653944e-05, "loss": 1.4824, "step": 170560 }, { "epoch": 7.79, "learning_rate": 1.1080598654400658e-05, "loss": 1.2772, "step": 170570 }, { "epoch": 7.79, "learning_rate": 1.1078310220147376e-05, "loss": 1.5018, "step": 170580 }, { "epoch": 7.79, "learning_rate": 1.1076021785894092e-05, "loss": 1.2735, "step": 170590 }, { "epoch": 7.79, "learning_rate": 1.1073733351640807e-05, "loss": 1.3941, "step": 170600 }, { "epoch": 7.79, "learning_rate": 1.1071444917387525e-05, "loss": 1.3799, "step": 170610 }, { "epoch": 7.79, "learning_rate": 1.1069156483134239e-05, "loss": 1.3552, "step": 170620 }, { "epoch": 7.79, "learning_rate": 1.1066868048880957e-05, "loss": 1.5773, "step": 170630 }, { "epoch": 7.79, "learning_rate": 1.1064579614627672e-05, "loss": 1.2839, "step": 170640 }, { "epoch": 7.79, "learning_rate": 1.1062291180374388e-05, "loss": 1.5477, "step": 170650 }, { "epoch": 7.79, "learning_rate": 1.1060002746121106e-05, "loss": 1.3355, "step": 170660 }, { "epoch": 7.79, "learning_rate": 1.105771431186782e-05, "loss": 1.3128, "step": 170670 }, { "epoch": 7.79, "learning_rate": 1.1055425877614536e-05, "loss": 1.2702, "step": 170680 }, { "epoch": 7.79, "learning_rate": 1.1053137443361253e-05, "loss": 1.4109, "step": 170690 }, { "epoch": 7.79, "learning_rate": 1.1050849009107969e-05, "loss": 1.4722, "step": 170700 }, { "epoch": 7.8, "learning_rate": 1.1048560574854685e-05, "loss": 1.2998, "step": 170710 }, { "epoch": 7.8, "learning_rate": 1.10462721406014e-05, "loss": 1.3511, "step": 170720 }, { "epoch": 7.8, "learning_rate": 1.1043983706348117e-05, "loss": 1.4268, "step": 170730 }, { "epoch": 7.8, "learning_rate": 1.1041695272094834e-05, "loss": 1.3562, "step": 170740 }, { "epoch": 7.8, "learning_rate": 1.103940683784155e-05, "loss": 1.3239, "step": 170750 }, { "epoch": 7.8, "learning_rate": 1.1037118403588266e-05, "loss": 1.3221, "step": 170760 }, { "epoch": 7.8, "learning_rate": 1.1034829969334982e-05, "loss": 1.3677, "step": 170770 }, { "epoch": 7.8, "learning_rate": 1.1032541535081697e-05, "loss": 1.4033, "step": 170780 }, { "epoch": 7.8, "learning_rate": 1.1030253100828413e-05, "loss": 1.2767, "step": 170790 }, { "epoch": 7.8, "learning_rate": 1.102796466657513e-05, "loss": 1.3842, "step": 170800 }, { "epoch": 7.8, "learning_rate": 1.1025676232321847e-05, "loss": 1.3188, "step": 170810 }, { "epoch": 7.8, "learning_rate": 1.102338779806856e-05, "loss": 1.1281, "step": 170820 }, { "epoch": 7.8, "learning_rate": 1.1021099363815278e-05, "loss": 1.3977, "step": 170830 }, { "epoch": 7.8, "learning_rate": 1.1018810929561994e-05, "loss": 1.1969, "step": 170840 }, { "epoch": 7.8, "learning_rate": 1.101652249530871e-05, "loss": 1.4852, "step": 170850 }, { "epoch": 7.8, "learning_rate": 1.1014234061055427e-05, "loss": 1.4701, "step": 170860 }, { "epoch": 7.8, "learning_rate": 1.1011945626802142e-05, "loss": 1.3904, "step": 170870 }, { "epoch": 7.8, "learning_rate": 1.1009657192548859e-05, "loss": 1.4102, "step": 170880 }, { "epoch": 7.8, "learning_rate": 1.1007368758295575e-05, "loss": 1.3162, "step": 170890 }, { "epoch": 7.8, "learning_rate": 1.100508032404229e-05, "loss": 1.2228, "step": 170900 }, { "epoch": 7.8, "learning_rate": 1.1002791889789008e-05, "loss": 1.4534, "step": 170910 }, { "epoch": 7.8, "learning_rate": 1.1000503455535722e-05, "loss": 1.4799, "step": 170920 }, { "epoch": 7.81, "learning_rate": 1.0998215021282438e-05, "loss": 1.367, "step": 170930 }, { "epoch": 7.81, "learning_rate": 1.0995926587029156e-05, "loss": 1.3745, "step": 170940 }, { "epoch": 7.81, "learning_rate": 1.0993638152775872e-05, "loss": 1.4225, "step": 170950 }, { "epoch": 7.81, "learning_rate": 1.0991349718522587e-05, "loss": 1.3499, "step": 170960 }, { "epoch": 7.81, "learning_rate": 1.0989061284269303e-05, "loss": 1.6021, "step": 170970 }, { "epoch": 7.81, "learning_rate": 1.0986772850016019e-05, "loss": 1.4112, "step": 170980 }, { "epoch": 7.81, "learning_rate": 1.0984484415762737e-05, "loss": 1.3502, "step": 170990 }, { "epoch": 7.81, "learning_rate": 1.0982195981509452e-05, "loss": 1.4807, "step": 171000 }, { "epoch": 7.81, "learning_rate": 1.0979907547256168e-05, "loss": 1.3144, "step": 171010 }, { "epoch": 7.81, "learning_rate": 1.0977619113002884e-05, "loss": 1.3843, "step": 171020 }, { "epoch": 7.81, "learning_rate": 1.09753306787496e-05, "loss": 1.4086, "step": 171030 }, { "epoch": 7.81, "learning_rate": 1.0973042244496316e-05, "loss": 1.4103, "step": 171040 }, { "epoch": 7.81, "learning_rate": 1.0970753810243033e-05, "loss": 1.251, "step": 171050 }, { "epoch": 7.81, "learning_rate": 1.0968465375989747e-05, "loss": 1.3084, "step": 171060 }, { "epoch": 7.81, "learning_rate": 1.0966176941736463e-05, "loss": 1.3814, "step": 171070 }, { "epoch": 7.81, "learning_rate": 1.096388850748318e-05, "loss": 1.5016, "step": 171080 }, { "epoch": 7.81, "learning_rate": 1.0961600073229897e-05, "loss": 1.4375, "step": 171090 }, { "epoch": 7.81, "learning_rate": 1.0959311638976612e-05, "loss": 1.4509, "step": 171100 }, { "epoch": 7.81, "learning_rate": 1.0957023204723328e-05, "loss": 1.2616, "step": 171110 }, { "epoch": 7.81, "learning_rate": 1.0954734770470044e-05, "loss": 1.3376, "step": 171120 }, { "epoch": 7.81, "learning_rate": 1.0952446336216762e-05, "loss": 1.4407, "step": 171130 }, { "epoch": 7.81, "learning_rate": 1.0950157901963477e-05, "loss": 1.3593, "step": 171140 }, { "epoch": 7.82, "learning_rate": 1.0947869467710193e-05, "loss": 1.3893, "step": 171150 }, { "epoch": 7.82, "learning_rate": 1.0945581033456909e-05, "loss": 1.562, "step": 171160 }, { "epoch": 7.82, "learning_rate": 1.0943292599203625e-05, "loss": 1.4537, "step": 171170 }, { "epoch": 7.82, "learning_rate": 1.094100416495034e-05, "loss": 1.4994, "step": 171180 }, { "epoch": 7.82, "learning_rate": 1.0938715730697058e-05, "loss": 1.5529, "step": 171190 }, { "epoch": 7.82, "learning_rate": 1.0936427296443774e-05, "loss": 1.3796, "step": 171200 }, { "epoch": 7.82, "learning_rate": 1.093413886219049e-05, "loss": 1.3377, "step": 171210 }, { "epoch": 7.82, "learning_rate": 1.0931850427937206e-05, "loss": 1.4266, "step": 171220 }, { "epoch": 7.82, "learning_rate": 1.0929561993683922e-05, "loss": 1.4196, "step": 171230 }, { "epoch": 7.82, "learning_rate": 1.0927273559430639e-05, "loss": 1.46, "step": 171240 }, { "epoch": 7.82, "learning_rate": 1.0924985125177355e-05, "loss": 1.3502, "step": 171250 }, { "epoch": 7.82, "learning_rate": 1.0922696690924069e-05, "loss": 1.362, "step": 171260 }, { "epoch": 7.82, "learning_rate": 1.0920408256670787e-05, "loss": 1.2259, "step": 171270 }, { "epoch": 7.82, "learning_rate": 1.0918119822417502e-05, "loss": 1.4563, "step": 171280 }, { "epoch": 7.82, "learning_rate": 1.0915831388164218e-05, "loss": 1.4139, "step": 171290 }, { "epoch": 7.82, "learning_rate": 1.0913542953910936e-05, "loss": 1.4175, "step": 171300 }, { "epoch": 7.82, "learning_rate": 1.091125451965765e-05, "loss": 1.3703, "step": 171310 }, { "epoch": 7.82, "learning_rate": 1.0908966085404367e-05, "loss": 1.2718, "step": 171320 }, { "epoch": 7.82, "learning_rate": 1.0906677651151083e-05, "loss": 1.4587, "step": 171330 }, { "epoch": 7.82, "learning_rate": 1.0904389216897799e-05, "loss": 1.2624, "step": 171340 }, { "epoch": 7.82, "learning_rate": 1.0902100782644515e-05, "loss": 1.2325, "step": 171350 }, { "epoch": 7.82, "learning_rate": 1.089981234839123e-05, "loss": 1.3697, "step": 171360 }, { "epoch": 7.83, "learning_rate": 1.0897523914137947e-05, "loss": 1.4583, "step": 171370 }, { "epoch": 7.83, "learning_rate": 1.0895235479884664e-05, "loss": 1.3377, "step": 171380 }, { "epoch": 7.83, "learning_rate": 1.089294704563138e-05, "loss": 1.4313, "step": 171390 }, { "epoch": 7.83, "learning_rate": 1.0890658611378096e-05, "loss": 1.2471, "step": 171400 }, { "epoch": 7.83, "learning_rate": 1.0888370177124812e-05, "loss": 1.2852, "step": 171410 }, { "epoch": 7.83, "learning_rate": 1.0886081742871527e-05, "loss": 1.3781, "step": 171420 }, { "epoch": 7.83, "learning_rate": 1.0883793308618243e-05, "loss": 1.5246, "step": 171430 }, { "epoch": 7.83, "learning_rate": 1.088150487436496e-05, "loss": 1.4239, "step": 171440 }, { "epoch": 7.83, "learning_rate": 1.0879216440111677e-05, "loss": 1.3528, "step": 171450 }, { "epoch": 7.83, "learning_rate": 1.0876928005858392e-05, "loss": 1.3485, "step": 171460 }, { "epoch": 7.83, "learning_rate": 1.0874639571605108e-05, "loss": 1.3945, "step": 171470 }, { "epoch": 7.83, "learning_rate": 1.0872351137351824e-05, "loss": 1.3313, "step": 171480 }, { "epoch": 7.83, "learning_rate": 1.0870062703098542e-05, "loss": 1.418, "step": 171490 }, { "epoch": 7.83, "learning_rate": 1.0867774268845257e-05, "loss": 1.3292, "step": 171500 }, { "epoch": 7.83, "learning_rate": 1.0865485834591971e-05, "loss": 1.4132, "step": 171510 }, { "epoch": 7.83, "learning_rate": 1.0863197400338689e-05, "loss": 1.4347, "step": 171520 }, { "epoch": 7.83, "learning_rate": 1.0860908966085405e-05, "loss": 1.3643, "step": 171530 }, { "epoch": 7.83, "learning_rate": 1.085862053183212e-05, "loss": 1.279, "step": 171540 }, { "epoch": 7.83, "learning_rate": 1.0856332097578838e-05, "loss": 1.3607, "step": 171550 }, { "epoch": 7.83, "learning_rate": 1.0854043663325552e-05, "loss": 1.3876, "step": 171560 }, { "epoch": 7.83, "learning_rate": 1.085175522907227e-05, "loss": 1.484, "step": 171570 }, { "epoch": 7.83, "learning_rate": 1.0849466794818986e-05, "loss": 1.4091, "step": 171580 }, { "epoch": 7.84, "learning_rate": 1.0847178360565701e-05, "loss": 1.531, "step": 171590 }, { "epoch": 7.84, "learning_rate": 1.0844889926312419e-05, "loss": 1.4617, "step": 171600 }, { "epoch": 7.84, "learning_rate": 1.0842601492059133e-05, "loss": 1.42, "step": 171610 }, { "epoch": 7.84, "learning_rate": 1.0840313057805849e-05, "loss": 1.3919, "step": 171620 }, { "epoch": 7.84, "learning_rate": 1.0838024623552566e-05, "loss": 1.3186, "step": 171630 }, { "epoch": 7.84, "learning_rate": 1.0835736189299282e-05, "loss": 1.4284, "step": 171640 }, { "epoch": 7.84, "learning_rate": 1.0833447755045998e-05, "loss": 1.4153, "step": 171650 }, { "epoch": 7.84, "learning_rate": 1.0831159320792714e-05, "loss": 1.2867, "step": 171660 }, { "epoch": 7.84, "learning_rate": 1.082887088653943e-05, "loss": 1.2936, "step": 171670 }, { "epoch": 7.84, "learning_rate": 1.0826582452286146e-05, "loss": 1.4577, "step": 171680 }, { "epoch": 7.84, "learning_rate": 1.0824294018032863e-05, "loss": 1.3218, "step": 171690 }, { "epoch": 7.84, "learning_rate": 1.0822005583779579e-05, "loss": 1.5059, "step": 171700 }, { "epoch": 7.84, "learning_rate": 1.0819717149526295e-05, "loss": 1.4046, "step": 171710 }, { "epoch": 7.84, "learning_rate": 1.081742871527301e-05, "loss": 1.4521, "step": 171720 }, { "epoch": 7.84, "learning_rate": 1.0815140281019726e-05, "loss": 1.423, "step": 171730 }, { "epoch": 7.84, "learning_rate": 1.0812851846766444e-05, "loss": 1.4894, "step": 171740 }, { "epoch": 7.84, "learning_rate": 1.081056341251316e-05, "loss": 1.3341, "step": 171750 }, { "epoch": 7.84, "learning_rate": 1.0808274978259874e-05, "loss": 1.41, "step": 171760 }, { "epoch": 7.84, "learning_rate": 1.0805986544006591e-05, "loss": 1.2693, "step": 171770 }, { "epoch": 7.84, "learning_rate": 1.0803698109753307e-05, "loss": 1.4881, "step": 171780 }, { "epoch": 7.84, "learning_rate": 1.0801409675500023e-05, "loss": 1.5022, "step": 171790 }, { "epoch": 7.84, "learning_rate": 1.079912124124674e-05, "loss": 1.5962, "step": 171800 }, { "epoch": 7.85, "learning_rate": 1.0796832806993455e-05, "loss": 1.5049, "step": 171810 }, { "epoch": 7.85, "learning_rate": 1.0794544372740172e-05, "loss": 1.3256, "step": 171820 }, { "epoch": 7.85, "learning_rate": 1.0792255938486888e-05, "loss": 1.4345, "step": 171830 }, { "epoch": 7.85, "learning_rate": 1.0789967504233604e-05, "loss": 1.3931, "step": 171840 }, { "epoch": 7.85, "learning_rate": 1.078767906998032e-05, "loss": 1.3557, "step": 171850 }, { "epoch": 7.85, "learning_rate": 1.0785390635727036e-05, "loss": 1.2207, "step": 171860 }, { "epoch": 7.85, "learning_rate": 1.0783102201473751e-05, "loss": 1.4805, "step": 171870 }, { "epoch": 7.85, "learning_rate": 1.0780813767220469e-05, "loss": 1.3651, "step": 171880 }, { "epoch": 7.85, "learning_rate": 1.0778525332967185e-05, "loss": 1.4251, "step": 171890 }, { "epoch": 7.85, "learning_rate": 1.07762368987139e-05, "loss": 1.2264, "step": 171900 }, { "epoch": 7.85, "learning_rate": 1.0773948464460616e-05, "loss": 1.4206, "step": 171910 }, { "epoch": 7.85, "learning_rate": 1.0771660030207332e-05, "loss": 1.2989, "step": 171920 }, { "epoch": 7.85, "learning_rate": 1.0769371595954048e-05, "loss": 1.2648, "step": 171930 }, { "epoch": 7.85, "learning_rate": 1.0767083161700766e-05, "loss": 1.2861, "step": 171940 }, { "epoch": 7.85, "learning_rate": 1.076479472744748e-05, "loss": 1.3136, "step": 171950 }, { "epoch": 7.85, "learning_rate": 1.0762506293194197e-05, "loss": 1.3474, "step": 171960 }, { "epoch": 7.85, "learning_rate": 1.0760217858940913e-05, "loss": 1.3261, "step": 171970 }, { "epoch": 7.85, "learning_rate": 1.0757929424687629e-05, "loss": 1.3249, "step": 171980 }, { "epoch": 7.85, "learning_rate": 1.0755640990434346e-05, "loss": 1.5174, "step": 171990 }, { "epoch": 7.85, "learning_rate": 1.075335255618106e-05, "loss": 1.3741, "step": 172000 }, { "epoch": 7.85, "learning_rate": 1.0751064121927776e-05, "loss": 1.3789, "step": 172010 }, { "epoch": 7.85, "learning_rate": 1.0748775687674494e-05, "loss": 1.4373, "step": 172020 }, { "epoch": 7.86, "learning_rate": 1.074648725342121e-05, "loss": 1.2938, "step": 172030 }, { "epoch": 7.86, "learning_rate": 1.0744198819167926e-05, "loss": 1.2861, "step": 172040 }, { "epoch": 7.86, "learning_rate": 1.0741910384914641e-05, "loss": 1.3186, "step": 172050 }, { "epoch": 7.86, "learning_rate": 1.0739621950661357e-05, "loss": 1.2973, "step": 172060 }, { "epoch": 7.86, "learning_rate": 1.0737333516408075e-05, "loss": 1.3135, "step": 172070 }, { "epoch": 7.86, "learning_rate": 1.073504508215479e-05, "loss": 1.2688, "step": 172080 }, { "epoch": 7.86, "learning_rate": 1.0732756647901506e-05, "loss": 1.4581, "step": 172090 }, { "epoch": 7.86, "learning_rate": 1.0730468213648222e-05, "loss": 1.2436, "step": 172100 }, { "epoch": 7.86, "learning_rate": 1.0728179779394938e-05, "loss": 1.501, "step": 172110 }, { "epoch": 7.86, "learning_rate": 1.0725891345141654e-05, "loss": 1.2807, "step": 172120 }, { "epoch": 7.86, "learning_rate": 1.0723602910888371e-05, "loss": 1.4639, "step": 172130 }, { "epoch": 7.86, "learning_rate": 1.0721314476635087e-05, "loss": 1.6157, "step": 172140 }, { "epoch": 7.86, "learning_rate": 1.0719026042381803e-05, "loss": 1.47, "step": 172150 }, { "epoch": 7.86, "learning_rate": 1.0716737608128519e-05, "loss": 1.2621, "step": 172160 }, { "epoch": 7.86, "learning_rate": 1.0714449173875235e-05, "loss": 1.2558, "step": 172170 }, { "epoch": 7.86, "learning_rate": 1.0712160739621952e-05, "loss": 1.4091, "step": 172180 }, { "epoch": 7.86, "learning_rate": 1.0709872305368668e-05, "loss": 1.1529, "step": 172190 }, { "epoch": 7.86, "learning_rate": 1.0707583871115382e-05, "loss": 1.3252, "step": 172200 }, { "epoch": 7.86, "learning_rate": 1.07052954368621e-05, "loss": 1.2918, "step": 172210 }, { "epoch": 7.86, "learning_rate": 1.0703007002608816e-05, "loss": 1.3116, "step": 172220 }, { "epoch": 7.86, "learning_rate": 1.0700718568355531e-05, "loss": 1.449, "step": 172230 }, { "epoch": 7.86, "learning_rate": 1.0698430134102249e-05, "loss": 1.3544, "step": 172240 }, { "epoch": 7.87, "learning_rate": 1.0696141699848963e-05, "loss": 1.4252, "step": 172250 }, { "epoch": 7.87, "learning_rate": 1.0693853265595679e-05, "loss": 1.2504, "step": 172260 }, { "epoch": 7.87, "learning_rate": 1.0691564831342396e-05, "loss": 1.4482, "step": 172270 }, { "epoch": 7.87, "learning_rate": 1.0689276397089112e-05, "loss": 1.3429, "step": 172280 }, { "epoch": 7.87, "learning_rate": 1.0686987962835828e-05, "loss": 1.4506, "step": 172290 }, { "epoch": 7.87, "learning_rate": 1.0684699528582544e-05, "loss": 1.2654, "step": 172300 }, { "epoch": 7.87, "learning_rate": 1.068241109432926e-05, "loss": 1.3325, "step": 172310 }, { "epoch": 7.87, "learning_rate": 1.0680122660075977e-05, "loss": 1.297, "step": 172320 }, { "epoch": 7.87, "learning_rate": 1.0677834225822693e-05, "loss": 1.2718, "step": 172330 }, { "epoch": 7.87, "learning_rate": 1.0675545791569409e-05, "loss": 1.3406, "step": 172340 }, { "epoch": 7.87, "learning_rate": 1.0673257357316125e-05, "loss": 1.4222, "step": 172350 }, { "epoch": 7.87, "learning_rate": 1.067096892306284e-05, "loss": 1.4875, "step": 172360 }, { "epoch": 7.87, "learning_rate": 1.0668680488809556e-05, "loss": 1.4556, "step": 172370 }, { "epoch": 7.87, "learning_rate": 1.0666392054556274e-05, "loss": 1.258, "step": 172380 }, { "epoch": 7.87, "learning_rate": 1.066410362030299e-05, "loss": 1.2854, "step": 172390 }, { "epoch": 7.87, "learning_rate": 1.0661815186049706e-05, "loss": 1.5083, "step": 172400 }, { "epoch": 7.87, "learning_rate": 1.0659526751796421e-05, "loss": 1.4383, "step": 172410 }, { "epoch": 7.87, "learning_rate": 1.0657238317543137e-05, "loss": 1.5152, "step": 172420 }, { "epoch": 7.87, "learning_rate": 1.0654949883289855e-05, "loss": 1.4483, "step": 172430 }, { "epoch": 7.87, "learning_rate": 1.065266144903657e-05, "loss": 1.4564, "step": 172440 }, { "epoch": 7.87, "learning_rate": 1.0650373014783285e-05, "loss": 1.638, "step": 172450 }, { "epoch": 7.87, "learning_rate": 1.0648084580530002e-05, "loss": 1.2889, "step": 172460 }, { "epoch": 7.88, "learning_rate": 1.0645796146276718e-05, "loss": 1.2989, "step": 172470 }, { "epoch": 7.88, "learning_rate": 1.0643507712023434e-05, "loss": 1.3074, "step": 172480 }, { "epoch": 7.88, "learning_rate": 1.0641219277770151e-05, "loss": 1.4481, "step": 172490 }, { "epoch": 7.88, "learning_rate": 1.0638930843516866e-05, "loss": 1.4721, "step": 172500 }, { "epoch": 7.88, "learning_rate": 1.0636642409263581e-05, "loss": 1.1632, "step": 172510 }, { "epoch": 7.88, "learning_rate": 1.0634353975010299e-05, "loss": 1.2227, "step": 172520 }, { "epoch": 7.88, "learning_rate": 1.0632065540757015e-05, "loss": 1.3572, "step": 172530 }, { "epoch": 7.88, "learning_rate": 1.062977710650373e-05, "loss": 1.3855, "step": 172540 }, { "epoch": 7.88, "learning_rate": 1.0627488672250446e-05, "loss": 1.3284, "step": 172550 }, { "epoch": 7.88, "learning_rate": 1.0625200237997162e-05, "loss": 1.3622, "step": 172560 }, { "epoch": 7.88, "learning_rate": 1.062291180374388e-05, "loss": 1.4359, "step": 172570 }, { "epoch": 7.88, "learning_rate": 1.0620623369490596e-05, "loss": 1.319, "step": 172580 }, { "epoch": 7.88, "learning_rate": 1.0618334935237311e-05, "loss": 1.3694, "step": 172590 }, { "epoch": 7.88, "learning_rate": 1.0616046500984027e-05, "loss": 1.3865, "step": 172600 }, { "epoch": 7.88, "learning_rate": 1.0613758066730743e-05, "loss": 1.4719, "step": 172610 }, { "epoch": 7.88, "learning_rate": 1.0611469632477459e-05, "loss": 1.4485, "step": 172620 }, { "epoch": 7.88, "learning_rate": 1.0609181198224176e-05, "loss": 1.3437, "step": 172630 }, { "epoch": 7.88, "learning_rate": 1.060689276397089e-05, "loss": 1.5146, "step": 172640 }, { "epoch": 7.88, "learning_rate": 1.0604604329717608e-05, "loss": 1.4737, "step": 172650 }, { "epoch": 7.88, "learning_rate": 1.0602315895464324e-05, "loss": 1.3758, "step": 172660 }, { "epoch": 7.88, "learning_rate": 1.060002746121104e-05, "loss": 1.248, "step": 172670 }, { "epoch": 7.89, "learning_rate": 1.0597739026957757e-05, "loss": 1.5965, "step": 172680 }, { "epoch": 7.89, "learning_rate": 1.0595450592704471e-05, "loss": 1.4256, "step": 172690 }, { "epoch": 7.89, "learning_rate": 1.0593162158451187e-05, "loss": 1.3808, "step": 172700 }, { "epoch": 7.89, "learning_rate": 1.0590873724197905e-05, "loss": 1.4432, "step": 172710 }, { "epoch": 7.89, "learning_rate": 1.058858528994462e-05, "loss": 1.2748, "step": 172720 }, { "epoch": 7.89, "learning_rate": 1.0586296855691336e-05, "loss": 1.5336, "step": 172730 }, { "epoch": 7.89, "learning_rate": 1.0584008421438052e-05, "loss": 1.2697, "step": 172740 }, { "epoch": 7.89, "learning_rate": 1.0581719987184768e-05, "loss": 1.2855, "step": 172750 }, { "epoch": 7.89, "learning_rate": 1.0579431552931486e-05, "loss": 1.3285, "step": 172760 }, { "epoch": 7.89, "learning_rate": 1.0577143118678201e-05, "loss": 1.5147, "step": 172770 }, { "epoch": 7.89, "learning_rate": 1.0574854684424917e-05, "loss": 1.3246, "step": 172780 }, { "epoch": 7.89, "learning_rate": 1.0572566250171633e-05, "loss": 1.5945, "step": 172790 }, { "epoch": 7.89, "learning_rate": 1.0570277815918349e-05, "loss": 1.38, "step": 172800 }, { "epoch": 7.89, "learning_rate": 1.0567989381665065e-05, "loss": 1.4107, "step": 172810 }, { "epoch": 7.89, "learning_rate": 1.0565700947411782e-05, "loss": 1.3374, "step": 172820 }, { "epoch": 7.89, "learning_rate": 1.0563412513158498e-05, "loss": 1.5526, "step": 172830 }, { "epoch": 7.89, "learning_rate": 1.0561124078905212e-05, "loss": 1.2719, "step": 172840 }, { "epoch": 7.89, "learning_rate": 1.055883564465193e-05, "loss": 1.3186, "step": 172850 }, { "epoch": 7.89, "learning_rate": 1.0556547210398645e-05, "loss": 1.3666, "step": 172860 }, { "epoch": 7.89, "learning_rate": 1.0554258776145361e-05, "loss": 1.2641, "step": 172870 }, { "epoch": 7.89, "learning_rate": 1.0551970341892079e-05, "loss": 1.4116, "step": 172880 }, { "epoch": 7.89, "learning_rate": 1.0549681907638793e-05, "loss": 1.267, "step": 172890 }, { "epoch": 7.9, "learning_rate": 1.054739347338551e-05, "loss": 1.3289, "step": 172900 }, { "epoch": 7.9, "learning_rate": 1.0545105039132226e-05, "loss": 1.2576, "step": 172910 }, { "epoch": 7.9, "learning_rate": 1.0542816604878942e-05, "loss": 1.4986, "step": 172920 }, { "epoch": 7.9, "learning_rate": 1.054052817062566e-05, "loss": 1.3414, "step": 172930 }, { "epoch": 7.9, "learning_rate": 1.0538239736372374e-05, "loss": 1.5277, "step": 172940 }, { "epoch": 7.9, "learning_rate": 1.053595130211909e-05, "loss": 1.4033, "step": 172950 }, { "epoch": 7.9, "learning_rate": 1.0533662867865807e-05, "loss": 1.3564, "step": 172960 }, { "epoch": 7.9, "learning_rate": 1.0531374433612523e-05, "loss": 1.2604, "step": 172970 }, { "epoch": 7.9, "learning_rate": 1.0529085999359239e-05, "loss": 1.2863, "step": 172980 }, { "epoch": 7.9, "learning_rate": 1.0526797565105955e-05, "loss": 1.1879, "step": 172990 }, { "epoch": 7.9, "learning_rate": 1.052450913085267e-05, "loss": 1.1389, "step": 173000 }, { "epoch": 7.9, "learning_rate": 1.0522220696599388e-05, "loss": 1.4467, "step": 173010 }, { "epoch": 7.9, "learning_rate": 1.0519932262346104e-05, "loss": 1.4402, "step": 173020 }, { "epoch": 7.9, "learning_rate": 1.051764382809282e-05, "loss": 1.2994, "step": 173030 }, { "epoch": 7.9, "learning_rate": 1.0515355393839535e-05, "loss": 1.3288, "step": 173040 }, { "epoch": 7.9, "learning_rate": 1.0513066959586251e-05, "loss": 1.4618, "step": 173050 }, { "epoch": 7.9, "learning_rate": 1.0510778525332967e-05, "loss": 1.3449, "step": 173060 }, { "epoch": 7.9, "learning_rate": 1.0508490091079685e-05, "loss": 1.5206, "step": 173070 }, { "epoch": 7.9, "learning_rate": 1.05062016568264e-05, "loss": 1.3312, "step": 173080 }, { "epoch": 7.9, "learning_rate": 1.0503913222573116e-05, "loss": 1.6179, "step": 173090 }, { "epoch": 7.9, "learning_rate": 1.0501624788319832e-05, "loss": 1.2298, "step": 173100 }, { "epoch": 7.9, "learning_rate": 1.0499336354066548e-05, "loss": 1.2888, "step": 173110 }, { "epoch": 7.91, "learning_rate": 1.0497047919813264e-05, "loss": 1.3933, "step": 173120 }, { "epoch": 7.91, "learning_rate": 1.0494759485559981e-05, "loss": 1.4316, "step": 173130 }, { "epoch": 7.91, "learning_rate": 1.0492471051306695e-05, "loss": 1.5607, "step": 173140 }, { "epoch": 7.91, "learning_rate": 1.0490182617053413e-05, "loss": 1.3461, "step": 173150 }, { "epoch": 7.91, "learning_rate": 1.0487894182800129e-05, "loss": 1.2242, "step": 173160 }, { "epoch": 7.91, "learning_rate": 1.0485605748546845e-05, "loss": 1.3993, "step": 173170 }, { "epoch": 7.91, "learning_rate": 1.0483317314293562e-05, "loss": 1.328, "step": 173180 }, { "epoch": 7.91, "learning_rate": 1.0481028880040276e-05, "loss": 1.4752, "step": 173190 }, { "epoch": 7.91, "learning_rate": 1.0478740445786992e-05, "loss": 1.4401, "step": 173200 }, { "epoch": 7.91, "learning_rate": 1.047645201153371e-05, "loss": 1.2964, "step": 173210 }, { "epoch": 7.91, "learning_rate": 1.0474163577280425e-05, "loss": 1.3822, "step": 173220 }, { "epoch": 7.91, "learning_rate": 1.0471875143027141e-05, "loss": 1.289, "step": 173230 }, { "epoch": 7.91, "learning_rate": 1.0469586708773857e-05, "loss": 1.2794, "step": 173240 }, { "epoch": 7.91, "learning_rate": 1.0467298274520573e-05, "loss": 1.1917, "step": 173250 }, { "epoch": 7.91, "learning_rate": 1.046500984026729e-05, "loss": 1.318, "step": 173260 }, { "epoch": 7.91, "learning_rate": 1.0462721406014006e-05, "loss": 1.4136, "step": 173270 }, { "epoch": 7.91, "learning_rate": 1.0460432971760722e-05, "loss": 1.3474, "step": 173280 }, { "epoch": 7.91, "learning_rate": 1.0458144537507438e-05, "loss": 1.2677, "step": 173290 }, { "epoch": 7.91, "learning_rate": 1.0455856103254154e-05, "loss": 1.4373, "step": 173300 }, { "epoch": 7.91, "learning_rate": 1.045356766900087e-05, "loss": 1.3407, "step": 173310 }, { "epoch": 7.91, "learning_rate": 1.0451279234747587e-05, "loss": 1.2926, "step": 173320 }, { "epoch": 7.91, "learning_rate": 1.0448990800494303e-05, "loss": 1.4024, "step": 173330 }, { "epoch": 7.92, "learning_rate": 1.0446702366241019e-05, "loss": 1.3955, "step": 173340 }, { "epoch": 7.92, "learning_rate": 1.0444413931987735e-05, "loss": 1.4965, "step": 173350 }, { "epoch": 7.92, "learning_rate": 1.044212549773445e-05, "loss": 1.3298, "step": 173360 }, { "epoch": 7.92, "learning_rate": 1.0439837063481166e-05, "loss": 1.4826, "step": 173370 }, { "epoch": 7.92, "learning_rate": 1.0437548629227884e-05, "loss": 1.3919, "step": 173380 }, { "epoch": 7.92, "learning_rate": 1.0435260194974598e-05, "loss": 1.4816, "step": 173390 }, { "epoch": 7.92, "learning_rate": 1.0432971760721315e-05, "loss": 1.3649, "step": 173400 }, { "epoch": 7.92, "learning_rate": 1.0430683326468031e-05, "loss": 1.4099, "step": 173410 }, { "epoch": 7.92, "learning_rate": 1.0428394892214747e-05, "loss": 1.354, "step": 173420 }, { "epoch": 7.92, "learning_rate": 1.0426106457961465e-05, "loss": 1.4014, "step": 173430 }, { "epoch": 7.92, "learning_rate": 1.0423818023708179e-05, "loss": 1.3186, "step": 173440 }, { "epoch": 7.92, "learning_rate": 1.0421529589454895e-05, "loss": 1.3798, "step": 173450 }, { "epoch": 7.92, "learning_rate": 1.0419241155201612e-05, "loss": 1.454, "step": 173460 }, { "epoch": 7.92, "learning_rate": 1.0416952720948328e-05, "loss": 1.4594, "step": 173470 }, { "epoch": 7.92, "learning_rate": 1.0414664286695044e-05, "loss": 1.1988, "step": 173480 }, { "epoch": 7.92, "learning_rate": 1.041237585244176e-05, "loss": 1.5283, "step": 173490 }, { "epoch": 7.92, "learning_rate": 1.0410087418188475e-05, "loss": 1.4096, "step": 173500 }, { "epoch": 7.92, "learning_rate": 1.0407798983935193e-05, "loss": 1.3757, "step": 173510 }, { "epoch": 7.92, "learning_rate": 1.0405510549681909e-05, "loss": 1.3736, "step": 173520 }, { "epoch": 7.92, "learning_rate": 1.0403222115428623e-05, "loss": 1.3083, "step": 173530 }, { "epoch": 7.92, "learning_rate": 1.040093368117534e-05, "loss": 1.3382, "step": 173540 }, { "epoch": 7.92, "learning_rate": 1.0398645246922056e-05, "loss": 1.316, "step": 173550 }, { "epoch": 7.93, "learning_rate": 1.0396356812668772e-05, "loss": 1.3094, "step": 173560 }, { "epoch": 7.93, "learning_rate": 1.039406837841549e-05, "loss": 1.3051, "step": 173570 }, { "epoch": 7.93, "learning_rate": 1.0391779944162204e-05, "loss": 1.3819, "step": 173580 }, { "epoch": 7.93, "learning_rate": 1.0389491509908921e-05, "loss": 1.3238, "step": 173590 }, { "epoch": 7.93, "learning_rate": 1.0387203075655637e-05, "loss": 1.3901, "step": 173600 }, { "epoch": 7.93, "learning_rate": 1.0384914641402353e-05, "loss": 1.3346, "step": 173610 }, { "epoch": 7.93, "learning_rate": 1.038262620714907e-05, "loss": 1.266, "step": 173620 }, { "epoch": 7.93, "learning_rate": 1.0380337772895785e-05, "loss": 1.266, "step": 173630 }, { "epoch": 7.93, "learning_rate": 1.03780493386425e-05, "loss": 1.2869, "step": 173640 }, { "epoch": 7.93, "learning_rate": 1.0375760904389218e-05, "loss": 1.2666, "step": 173650 }, { "epoch": 7.93, "learning_rate": 1.0373472470135934e-05, "loss": 1.4002, "step": 173660 }, { "epoch": 7.93, "learning_rate": 1.037118403588265e-05, "loss": 1.336, "step": 173670 }, { "epoch": 7.93, "learning_rate": 1.0368895601629365e-05, "loss": 1.3803, "step": 173680 }, { "epoch": 7.93, "learning_rate": 1.0366607167376081e-05, "loss": 1.4578, "step": 173690 }, { "epoch": 7.93, "learning_rate": 1.0364318733122797e-05, "loss": 1.2637, "step": 173700 }, { "epoch": 7.93, "learning_rate": 1.0362030298869515e-05, "loss": 1.2924, "step": 173710 }, { "epoch": 7.93, "learning_rate": 1.035974186461623e-05, "loss": 1.4201, "step": 173720 }, { "epoch": 7.93, "learning_rate": 1.0357453430362946e-05, "loss": 1.3981, "step": 173730 }, { "epoch": 7.93, "learning_rate": 1.0355164996109662e-05, "loss": 1.3354, "step": 173740 }, { "epoch": 7.93, "learning_rate": 1.0352876561856378e-05, "loss": 1.3311, "step": 173750 }, { "epoch": 7.93, "learning_rate": 1.0350588127603095e-05, "loss": 1.3311, "step": 173760 }, { "epoch": 7.93, "learning_rate": 1.0348299693349811e-05, "loss": 1.4828, "step": 173770 }, { "epoch": 7.94, "learning_rate": 1.0346011259096525e-05, "loss": 1.4163, "step": 173780 }, { "epoch": 7.94, "learning_rate": 1.0343722824843243e-05, "loss": 1.43, "step": 173790 }, { "epoch": 7.94, "learning_rate": 1.0341434390589959e-05, "loss": 1.3295, "step": 173800 }, { "epoch": 7.94, "learning_rate": 1.0339145956336675e-05, "loss": 1.2887, "step": 173810 }, { "epoch": 7.94, "learning_rate": 1.0336857522083392e-05, "loss": 1.361, "step": 173820 }, { "epoch": 7.94, "learning_rate": 1.0334569087830106e-05, "loss": 1.419, "step": 173830 }, { "epoch": 7.94, "learning_rate": 1.0332280653576824e-05, "loss": 1.2651, "step": 173840 }, { "epoch": 7.94, "learning_rate": 1.032999221932354e-05, "loss": 1.5172, "step": 173850 }, { "epoch": 7.94, "learning_rate": 1.0327703785070255e-05, "loss": 1.208, "step": 173860 }, { "epoch": 7.94, "learning_rate": 1.0325415350816973e-05, "loss": 1.3917, "step": 173870 }, { "epoch": 7.94, "learning_rate": 1.0323126916563687e-05, "loss": 1.233, "step": 173880 }, { "epoch": 7.94, "learning_rate": 1.0320838482310403e-05, "loss": 1.3543, "step": 173890 }, { "epoch": 7.94, "learning_rate": 1.031855004805712e-05, "loss": 1.3907, "step": 173900 }, { "epoch": 7.94, "learning_rate": 1.0316261613803836e-05, "loss": 1.3332, "step": 173910 }, { "epoch": 7.94, "learning_rate": 1.0313973179550552e-05, "loss": 1.4501, "step": 173920 }, { "epoch": 7.94, "learning_rate": 1.0311684745297268e-05, "loss": 1.4337, "step": 173930 }, { "epoch": 7.94, "learning_rate": 1.0309396311043984e-05, "loss": 1.4742, "step": 173940 }, { "epoch": 7.94, "learning_rate": 1.0307107876790701e-05, "loss": 1.303, "step": 173950 }, { "epoch": 7.94, "learning_rate": 1.0304819442537417e-05, "loss": 1.4472, "step": 173960 }, { "epoch": 7.94, "learning_rate": 1.0302531008284133e-05, "loss": 1.4358, "step": 173970 }, { "epoch": 7.94, "learning_rate": 1.0300242574030849e-05, "loss": 1.3326, "step": 173980 }, { "epoch": 7.94, "learning_rate": 1.0297954139777564e-05, "loss": 1.3173, "step": 173990 }, { "epoch": 7.95, "learning_rate": 1.029566570552428e-05, "loss": 1.4168, "step": 174000 }, { "epoch": 7.95, "learning_rate": 1.0293377271270998e-05, "loss": 1.2458, "step": 174010 }, { "epoch": 7.95, "learning_rate": 1.0291088837017714e-05, "loss": 1.4611, "step": 174020 }, { "epoch": 7.95, "learning_rate": 1.0288800402764428e-05, "loss": 1.3955, "step": 174030 }, { "epoch": 7.95, "learning_rate": 1.0286511968511145e-05, "loss": 1.4479, "step": 174040 }, { "epoch": 7.95, "learning_rate": 1.0284223534257861e-05, "loss": 1.2077, "step": 174050 }, { "epoch": 7.95, "learning_rate": 1.0281935100004577e-05, "loss": 1.3387, "step": 174060 }, { "epoch": 7.95, "learning_rate": 1.0279646665751294e-05, "loss": 1.4739, "step": 174070 }, { "epoch": 7.95, "learning_rate": 1.0277358231498009e-05, "loss": 1.3884, "step": 174080 }, { "epoch": 7.95, "learning_rate": 1.0275069797244726e-05, "loss": 1.4464, "step": 174090 }, { "epoch": 7.95, "learning_rate": 1.0272781362991442e-05, "loss": 1.2769, "step": 174100 }, { "epoch": 7.95, "learning_rate": 1.0270492928738158e-05, "loss": 1.4079, "step": 174110 }, { "epoch": 7.95, "learning_rate": 1.0268204494484875e-05, "loss": 1.4237, "step": 174120 }, { "epoch": 7.95, "learning_rate": 1.026591606023159e-05, "loss": 1.2661, "step": 174130 }, { "epoch": 7.95, "learning_rate": 1.0263627625978305e-05, "loss": 1.4289, "step": 174140 }, { "epoch": 7.95, "learning_rate": 1.0261339191725023e-05, "loss": 1.4149, "step": 174150 }, { "epoch": 7.95, "learning_rate": 1.0259050757471739e-05, "loss": 1.319, "step": 174160 }, { "epoch": 7.95, "learning_rate": 1.0256762323218454e-05, "loss": 1.4082, "step": 174170 }, { "epoch": 7.95, "learning_rate": 1.025447388896517e-05, "loss": 1.51, "step": 174180 }, { "epoch": 7.95, "learning_rate": 1.0252185454711886e-05, "loss": 1.4436, "step": 174190 }, { "epoch": 7.95, "learning_rate": 1.0249897020458604e-05, "loss": 1.4422, "step": 174200 }, { "epoch": 7.95, "learning_rate": 1.024760858620532e-05, "loss": 1.2488, "step": 174210 }, { "epoch": 7.96, "learning_rate": 1.0245320151952035e-05, "loss": 1.389, "step": 174220 }, { "epoch": 7.96, "learning_rate": 1.0243031717698751e-05, "loss": 1.2879, "step": 174230 }, { "epoch": 7.96, "learning_rate": 1.0240743283445467e-05, "loss": 1.2423, "step": 174240 }, { "epoch": 7.96, "learning_rate": 1.0238454849192183e-05, "loss": 1.2989, "step": 174250 }, { "epoch": 7.96, "learning_rate": 1.02361664149389e-05, "loss": 1.3385, "step": 174260 }, { "epoch": 7.96, "learning_rate": 1.0233877980685614e-05, "loss": 1.3255, "step": 174270 }, { "epoch": 7.96, "learning_rate": 1.023158954643233e-05, "loss": 1.3774, "step": 174280 }, { "epoch": 7.96, "learning_rate": 1.0229301112179048e-05, "loss": 1.4001, "step": 174290 }, { "epoch": 7.96, "learning_rate": 1.0227012677925764e-05, "loss": 1.1696, "step": 174300 }, { "epoch": 7.96, "learning_rate": 1.022472424367248e-05, "loss": 1.4261, "step": 174310 }, { "epoch": 7.96, "learning_rate": 1.0222435809419195e-05, "loss": 1.5972, "step": 174320 }, { "epoch": 7.96, "learning_rate": 1.0220147375165911e-05, "loss": 1.3708, "step": 174330 }, { "epoch": 7.96, "learning_rate": 1.0217858940912629e-05, "loss": 1.1804, "step": 174340 }, { "epoch": 7.96, "learning_rate": 1.0215570506659344e-05, "loss": 1.3482, "step": 174350 }, { "epoch": 7.96, "learning_rate": 1.021328207240606e-05, "loss": 1.3747, "step": 174360 }, { "epoch": 7.96, "learning_rate": 1.0210993638152776e-05, "loss": 1.2912, "step": 174370 }, { "epoch": 7.96, "learning_rate": 1.0208705203899492e-05, "loss": 1.3653, "step": 174380 }, { "epoch": 7.96, "learning_rate": 1.0206416769646208e-05, "loss": 1.3493, "step": 174390 }, { "epoch": 7.96, "learning_rate": 1.0204128335392925e-05, "loss": 1.4228, "step": 174400 }, { "epoch": 7.96, "learning_rate": 1.0201839901139641e-05, "loss": 1.4311, "step": 174410 }, { "epoch": 7.96, "learning_rate": 1.0199551466886357e-05, "loss": 1.2418, "step": 174420 }, { "epoch": 7.96, "learning_rate": 1.0197263032633073e-05, "loss": 1.5414, "step": 174430 }, { "epoch": 7.97, "learning_rate": 1.0194974598379789e-05, "loss": 1.3015, "step": 174440 }, { "epoch": 7.97, "learning_rate": 1.0192686164126506e-05, "loss": 1.4545, "step": 174450 }, { "epoch": 7.97, "learning_rate": 1.0190397729873222e-05, "loss": 1.3549, "step": 174460 }, { "epoch": 7.97, "learning_rate": 1.0188109295619936e-05, "loss": 1.3758, "step": 174470 }, { "epoch": 7.97, "learning_rate": 1.0185820861366654e-05, "loss": 1.3431, "step": 174480 }, { "epoch": 7.97, "learning_rate": 1.018353242711337e-05, "loss": 1.2716, "step": 174490 }, { "epoch": 7.97, "learning_rate": 1.0181243992860085e-05, "loss": 1.2845, "step": 174500 }, { "epoch": 7.97, "learning_rate": 1.0178955558606803e-05, "loss": 1.3345, "step": 174510 }, { "epoch": 7.97, "learning_rate": 1.0176667124353517e-05, "loss": 1.2952, "step": 174520 }, { "epoch": 7.97, "learning_rate": 1.0174378690100234e-05, "loss": 1.3713, "step": 174530 }, { "epoch": 7.97, "learning_rate": 1.017209025584695e-05, "loss": 1.31, "step": 174540 }, { "epoch": 7.97, "learning_rate": 1.0169801821593666e-05, "loss": 1.4145, "step": 174550 }, { "epoch": 7.97, "learning_rate": 1.0167513387340382e-05, "loss": 1.4687, "step": 174560 }, { "epoch": 7.97, "learning_rate": 1.0165224953087098e-05, "loss": 1.3881, "step": 174570 }, { "epoch": 7.97, "learning_rate": 1.0162936518833814e-05, "loss": 1.3096, "step": 174580 }, { "epoch": 7.97, "learning_rate": 1.0160648084580531e-05, "loss": 1.327, "step": 174590 }, { "epoch": 7.97, "learning_rate": 1.0158359650327247e-05, "loss": 1.325, "step": 174600 }, { "epoch": 7.97, "learning_rate": 1.0156071216073963e-05, "loss": 1.3993, "step": 174610 }, { "epoch": 7.97, "learning_rate": 1.0153782781820679e-05, "loss": 1.3691, "step": 174620 }, { "epoch": 7.97, "learning_rate": 1.0151494347567394e-05, "loss": 1.2659, "step": 174630 }, { "epoch": 7.97, "learning_rate": 1.014920591331411e-05, "loss": 1.3503, "step": 174640 }, { "epoch": 7.97, "learning_rate": 1.0146917479060828e-05, "loss": 1.269, "step": 174650 }, { "epoch": 7.98, "learning_rate": 1.0144629044807544e-05, "loss": 1.3489, "step": 174660 }, { "epoch": 7.98, "learning_rate": 1.014234061055426e-05, "loss": 1.3962, "step": 174670 }, { "epoch": 7.98, "learning_rate": 1.0140052176300975e-05, "loss": 1.4133, "step": 174680 }, { "epoch": 7.98, "learning_rate": 1.0137763742047691e-05, "loss": 1.2902, "step": 174690 }, { "epoch": 7.98, "learning_rate": 1.0135475307794409e-05, "loss": 1.2629, "step": 174700 }, { "epoch": 7.98, "learning_rate": 1.0133186873541124e-05, "loss": 1.4123, "step": 174710 }, { "epoch": 7.98, "learning_rate": 1.0130898439287839e-05, "loss": 1.3985, "step": 174720 }, { "epoch": 7.98, "learning_rate": 1.0128610005034556e-05, "loss": 1.3523, "step": 174730 }, { "epoch": 7.98, "learning_rate": 1.0126321570781272e-05, "loss": 1.3421, "step": 174740 }, { "epoch": 7.98, "learning_rate": 1.0124033136527988e-05, "loss": 1.4046, "step": 174750 }, { "epoch": 7.98, "learning_rate": 1.0121744702274705e-05, "loss": 1.41, "step": 174760 }, { "epoch": 7.98, "learning_rate": 1.011945626802142e-05, "loss": 1.1904, "step": 174770 }, { "epoch": 7.98, "learning_rate": 1.0117167833768137e-05, "loss": 1.4239, "step": 174780 }, { "epoch": 7.98, "learning_rate": 1.0114879399514853e-05, "loss": 1.2772, "step": 174790 }, { "epoch": 7.98, "learning_rate": 1.0112590965261569e-05, "loss": 1.5398, "step": 174800 }, { "epoch": 7.98, "learning_rate": 1.0110302531008286e-05, "loss": 1.3251, "step": 174810 }, { "epoch": 7.98, "learning_rate": 1.0108014096755e-05, "loss": 1.3844, "step": 174820 }, { "epoch": 7.98, "learning_rate": 1.0105725662501716e-05, "loss": 1.1198, "step": 174830 }, { "epoch": 7.98, "learning_rate": 1.0103437228248434e-05, "loss": 1.4766, "step": 174840 }, { "epoch": 7.98, "learning_rate": 1.010114879399515e-05, "loss": 1.2925, "step": 174850 }, { "epoch": 7.98, "learning_rate": 1.0098860359741865e-05, "loss": 1.4189, "step": 174860 }, { "epoch": 7.99, "learning_rate": 1.0096571925488581e-05, "loss": 1.4598, "step": 174870 }, { "epoch": 7.99, "learning_rate": 1.0094283491235297e-05, "loss": 1.2661, "step": 174880 }, { "epoch": 7.99, "learning_rate": 1.0091995056982013e-05, "loss": 1.3389, "step": 174890 }, { "epoch": 7.99, "learning_rate": 1.008970662272873e-05, "loss": 1.3064, "step": 174900 }, { "epoch": 7.99, "learning_rate": 1.0087418188475446e-05, "loss": 1.2123, "step": 174910 }, { "epoch": 7.99, "learning_rate": 1.0085129754222162e-05, "loss": 1.3114, "step": 174920 }, { "epoch": 7.99, "learning_rate": 1.0082841319968878e-05, "loss": 1.4517, "step": 174930 }, { "epoch": 7.99, "learning_rate": 1.0080552885715594e-05, "loss": 1.3321, "step": 174940 }, { "epoch": 7.99, "learning_rate": 1.0078264451462311e-05, "loss": 1.5037, "step": 174950 }, { "epoch": 7.99, "learning_rate": 1.0075976017209027e-05, "loss": 1.2725, "step": 174960 }, { "epoch": 7.99, "learning_rate": 1.0073687582955741e-05, "loss": 1.4154, "step": 174970 }, { "epoch": 7.99, "learning_rate": 1.0071399148702459e-05, "loss": 1.4483, "step": 174980 }, { "epoch": 7.99, "learning_rate": 1.0069110714449174e-05, "loss": 1.3178, "step": 174990 }, { "epoch": 7.99, "learning_rate": 1.006682228019589e-05, "loss": 1.4536, "step": 175000 }, { "epoch": 7.99, "learning_rate": 1.0064533845942608e-05, "loss": 1.4369, "step": 175010 }, { "epoch": 7.99, "learning_rate": 1.0062245411689322e-05, "loss": 1.4612, "step": 175020 }, { "epoch": 7.99, "learning_rate": 1.005995697743604e-05, "loss": 1.3623, "step": 175030 }, { "epoch": 7.99, "learning_rate": 1.0057668543182755e-05, "loss": 1.3402, "step": 175040 }, { "epoch": 7.99, "learning_rate": 1.0055380108929471e-05, "loss": 1.2712, "step": 175050 }, { "epoch": 7.99, "learning_rate": 1.0053091674676187e-05, "loss": 1.4323, "step": 175060 }, { "epoch": 7.99, "learning_rate": 1.0050803240422903e-05, "loss": 1.3139, "step": 175070 }, { "epoch": 7.99, "learning_rate": 1.0048514806169618e-05, "loss": 1.3688, "step": 175080 }, { "epoch": 8.0, "learning_rate": 1.0046226371916336e-05, "loss": 1.4166, "step": 175090 }, { "epoch": 8.0, "learning_rate": 1.0043937937663052e-05, "loss": 1.5471, "step": 175100 }, { "epoch": 8.0, "learning_rate": 1.0041649503409768e-05, "loss": 1.2826, "step": 175110 }, { "epoch": 8.0, "learning_rate": 1.0039361069156484e-05, "loss": 1.4062, "step": 175120 }, { "epoch": 8.0, "learning_rate": 1.00370726349032e-05, "loss": 1.3232, "step": 175130 }, { "epoch": 8.0, "learning_rate": 1.0034784200649915e-05, "loss": 1.3379, "step": 175140 }, { "epoch": 8.0, "learning_rate": 1.0032495766396633e-05, "loss": 1.2385, "step": 175150 }, { "epoch": 8.0, "learning_rate": 1.0030207332143347e-05, "loss": 1.4079, "step": 175160 }, { "epoch": 8.0, "learning_rate": 1.0027918897890064e-05, "loss": 1.3681, "step": 175170 }, { "epoch": 8.0, "learning_rate": 1.002563046363678e-05, "loss": 1.2914, "step": 175180 }, { "epoch": 8.0, "learning_rate": 1.0023342029383496e-05, "loss": 1.4215, "step": 175190 }, { "epoch": 8.0, "eval_cer": 0.6751028645782899, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.3231837749481201, "eval_runtime": 2694.4853, "eval_samples_per_second": 3.923, "eval_steps_per_second": 1.961, "eval_wer": 0.9927152317880795, "step": 175198 }, { "epoch": 8.0, "learning_rate": 1.0021053595130214e-05, "loss": 1.3772, "step": 175200 }, { "epoch": 8.0, "learning_rate": 1.0018765160876928e-05, "loss": 1.2335, "step": 175210 }, { "epoch": 8.0, "learning_rate": 1.0016476726623643e-05, "loss": 1.4625, "step": 175220 }, { "epoch": 8.0, "learning_rate": 1.0014188292370361e-05, "loss": 1.3713, "step": 175230 }, { "epoch": 8.0, "learning_rate": 1.0011899858117077e-05, "loss": 1.3056, "step": 175240 }, { "epoch": 8.0, "learning_rate": 1.0009611423863793e-05, "loss": 1.4106, "step": 175250 }, { "epoch": 8.0, "learning_rate": 1.0007322989610508e-05, "loss": 1.3325, "step": 175260 }, { "epoch": 8.0, "learning_rate": 1.0005034555357224e-05, "loss": 1.308, "step": 175270 }, { "epoch": 8.0, "learning_rate": 1.0002746121103942e-05, "loss": 1.3933, "step": 175280 }, { "epoch": 8.0, "learning_rate": 1.0000457686850658e-05, "loss": 1.3976, "step": 175290 }, { "epoch": 8.0, "learning_rate": 9.998169252597373e-06, "loss": 1.4265, "step": 175300 }, { "epoch": 8.01, "learning_rate": 9.99588081834409e-06, "loss": 1.2489, "step": 175310 }, { "epoch": 8.01, "learning_rate": 9.993592384090805e-06, "loss": 1.5231, "step": 175320 }, { "epoch": 8.01, "learning_rate": 9.991303949837521e-06, "loss": 1.3149, "step": 175330 }, { "epoch": 8.01, "learning_rate": 9.989015515584238e-06, "loss": 1.36, "step": 175340 }, { "epoch": 8.01, "learning_rate": 9.986727081330954e-06, "loss": 1.3316, "step": 175350 }, { "epoch": 8.01, "learning_rate": 9.98443864707767e-06, "loss": 1.4836, "step": 175360 }, { "epoch": 8.01, "learning_rate": 9.982150212824386e-06, "loss": 1.2169, "step": 175370 }, { "epoch": 8.01, "learning_rate": 9.979861778571102e-06, "loss": 1.3095, "step": 175380 }, { "epoch": 8.01, "learning_rate": 9.97757334431782e-06, "loss": 1.303, "step": 175390 }, { "epoch": 8.01, "learning_rate": 9.975284910064535e-06, "loss": 1.4716, "step": 175400 }, { "epoch": 8.01, "learning_rate": 9.97299647581125e-06, "loss": 1.5768, "step": 175410 }, { "epoch": 8.01, "learning_rate": 9.970708041557967e-06, "loss": 1.3822, "step": 175420 }, { "epoch": 8.01, "learning_rate": 9.968419607304683e-06, "loss": 1.3495, "step": 175430 }, { "epoch": 8.01, "learning_rate": 9.966131173051398e-06, "loss": 1.2961, "step": 175440 }, { "epoch": 8.01, "learning_rate": 9.963842738798116e-06, "loss": 1.2696, "step": 175450 }, { "epoch": 8.01, "learning_rate": 9.96155430454483e-06, "loss": 1.3994, "step": 175460 }, { "epoch": 8.01, "learning_rate": 9.959265870291546e-06, "loss": 1.3088, "step": 175470 }, { "epoch": 8.01, "learning_rate": 9.956977436038263e-06, "loss": 1.3053, "step": 175480 }, { "epoch": 8.01, "learning_rate": 9.95468900178498e-06, "loss": 1.3637, "step": 175490 }, { "epoch": 8.01, "learning_rate": 9.952400567531695e-06, "loss": 1.3717, "step": 175500 }, { "epoch": 8.01, "learning_rate": 9.950112133278411e-06, "loss": 1.2667, "step": 175510 }, { "epoch": 8.01, "learning_rate": 9.947823699025127e-06, "loss": 1.331, "step": 175520 }, { "epoch": 8.02, "learning_rate": 9.945535264771844e-06, "loss": 1.4289, "step": 175530 }, { "epoch": 8.02, "learning_rate": 9.94324683051856e-06, "loss": 1.4006, "step": 175540 }, { "epoch": 8.02, "learning_rate": 9.940958396265276e-06, "loss": 1.3865, "step": 175550 }, { "epoch": 8.02, "learning_rate": 9.938669962011992e-06, "loss": 1.3536, "step": 175560 }, { "epoch": 8.02, "learning_rate": 9.936381527758708e-06, "loss": 1.5017, "step": 175570 }, { "epoch": 8.02, "learning_rate": 9.934093093505423e-06, "loss": 1.288, "step": 175580 }, { "epoch": 8.02, "learning_rate": 9.931804659252141e-06, "loss": 1.4148, "step": 175590 }, { "epoch": 8.02, "learning_rate": 9.929516224998857e-06, "loss": 1.4562, "step": 175600 }, { "epoch": 8.02, "learning_rate": 9.927227790745573e-06, "loss": 1.2761, "step": 175610 }, { "epoch": 8.02, "learning_rate": 9.924939356492288e-06, "loss": 1.398, "step": 175620 }, { "epoch": 8.02, "learning_rate": 9.922650922239004e-06, "loss": 1.3156, "step": 175630 }, { "epoch": 8.02, "learning_rate": 9.920362487985722e-06, "loss": 1.3824, "step": 175640 }, { "epoch": 8.02, "learning_rate": 9.918074053732438e-06, "loss": 1.3049, "step": 175650 }, { "epoch": 8.02, "learning_rate": 9.915785619479152e-06, "loss": 1.3699, "step": 175660 }, { "epoch": 8.02, "learning_rate": 9.91349718522587e-06, "loss": 1.318, "step": 175670 }, { "epoch": 8.02, "learning_rate": 9.911208750972585e-06, "loss": 1.4058, "step": 175680 }, { "epoch": 8.02, "learning_rate": 9.908920316719301e-06, "loss": 1.3584, "step": 175690 }, { "epoch": 8.02, "learning_rate": 9.906631882466018e-06, "loss": 1.4245, "step": 175700 }, { "epoch": 8.02, "learning_rate": 9.904343448212733e-06, "loss": 1.3704, "step": 175710 }, { "epoch": 8.02, "learning_rate": 9.902055013959448e-06, "loss": 1.2243, "step": 175720 }, { "epoch": 8.02, "learning_rate": 9.899766579706166e-06, "loss": 1.2693, "step": 175730 }, { "epoch": 8.02, "learning_rate": 9.897478145452882e-06, "loss": 1.1898, "step": 175740 }, { "epoch": 8.03, "learning_rate": 9.895189711199598e-06, "loss": 1.4171, "step": 175750 }, { "epoch": 8.03, "learning_rate": 9.892901276946313e-06, "loss": 1.2713, "step": 175760 }, { "epoch": 8.03, "learning_rate": 9.89061284269303e-06, "loss": 1.3817, "step": 175770 }, { "epoch": 8.03, "learning_rate": 9.888324408439747e-06, "loss": 1.3211, "step": 175780 }, { "epoch": 8.03, "learning_rate": 9.886035974186463e-06, "loss": 1.3347, "step": 175790 }, { "epoch": 8.03, "learning_rate": 9.883747539933178e-06, "loss": 1.3098, "step": 175800 }, { "epoch": 8.03, "learning_rate": 9.881459105679894e-06, "loss": 1.4353, "step": 175810 }, { "epoch": 8.03, "learning_rate": 9.87917067142661e-06, "loss": 1.4129, "step": 175820 }, { "epoch": 8.03, "learning_rate": 9.876882237173326e-06, "loss": 1.3535, "step": 175830 }, { "epoch": 8.03, "learning_rate": 9.874593802920043e-06, "loss": 1.3918, "step": 175840 }, { "epoch": 8.03, "learning_rate": 9.87230536866676e-06, "loss": 1.4746, "step": 175850 }, { "epoch": 8.03, "learning_rate": 9.870016934413475e-06, "loss": 1.3359, "step": 175860 }, { "epoch": 8.03, "learning_rate": 9.867728500160191e-06, "loss": 1.3004, "step": 175870 }, { "epoch": 8.03, "learning_rate": 9.865440065906907e-06, "loss": 1.3944, "step": 175880 }, { "epoch": 8.03, "learning_rate": 9.863151631653624e-06, "loss": 1.433, "step": 175890 }, { "epoch": 8.03, "learning_rate": 9.860863197400338e-06, "loss": 1.393, "step": 175900 }, { "epoch": 8.03, "learning_rate": 9.858574763147054e-06, "loss": 1.3478, "step": 175910 }, { "epoch": 8.03, "learning_rate": 9.856286328893772e-06, "loss": 1.3217, "step": 175920 }, { "epoch": 8.03, "learning_rate": 9.853997894640488e-06, "loss": 1.4378, "step": 175930 }, { "epoch": 8.03, "learning_rate": 9.851709460387203e-06, "loss": 1.3029, "step": 175940 }, { "epoch": 8.03, "learning_rate": 9.84942102613392e-06, "loss": 1.3271, "step": 175950 }, { "epoch": 8.03, "learning_rate": 9.847132591880635e-06, "loss": 1.2342, "step": 175960 }, { "epoch": 8.04, "learning_rate": 9.844844157627353e-06, "loss": 1.2759, "step": 175970 }, { "epoch": 8.04, "learning_rate": 9.842555723374068e-06, "loss": 1.3466, "step": 175980 }, { "epoch": 8.04, "learning_rate": 9.840267289120784e-06, "loss": 1.3053, "step": 175990 }, { "epoch": 8.04, "learning_rate": 9.8379788548675e-06, "loss": 1.3726, "step": 176000 }, { "epoch": 8.04, "learning_rate": 9.835690420614216e-06, "loss": 1.4025, "step": 176010 }, { "epoch": 8.04, "learning_rate": 9.833401986360932e-06, "loss": 1.3239, "step": 176020 }, { "epoch": 8.04, "learning_rate": 9.83111355210765e-06, "loss": 1.4574, "step": 176030 }, { "epoch": 8.04, "learning_rate": 9.828825117854365e-06, "loss": 1.1827, "step": 176040 }, { "epoch": 8.04, "learning_rate": 9.82653668360108e-06, "loss": 1.339, "step": 176050 }, { "epoch": 8.04, "learning_rate": 9.824248249347797e-06, "loss": 1.4035, "step": 176060 }, { "epoch": 8.04, "learning_rate": 9.821959815094513e-06, "loss": 1.3768, "step": 176070 }, { "epoch": 8.04, "learning_rate": 9.819671380841228e-06, "loss": 1.5357, "step": 176080 }, { "epoch": 8.04, "learning_rate": 9.817382946587946e-06, "loss": 1.254, "step": 176090 }, { "epoch": 8.04, "learning_rate": 9.81509451233466e-06, "loss": 1.3949, "step": 176100 }, { "epoch": 8.04, "learning_rate": 9.812806078081378e-06, "loss": 1.3024, "step": 176110 }, { "epoch": 8.04, "learning_rate": 9.810517643828093e-06, "loss": 1.3846, "step": 176120 }, { "epoch": 8.04, "learning_rate": 9.80822920957481e-06, "loss": 1.3064, "step": 176130 }, { "epoch": 8.04, "learning_rate": 9.805940775321527e-06, "loss": 1.2338, "step": 176140 }, { "epoch": 8.04, "learning_rate": 9.803652341068241e-06, "loss": 1.3803, "step": 176150 }, { "epoch": 8.04, "learning_rate": 9.801363906814957e-06, "loss": 1.3564, "step": 176160 }, { "epoch": 8.04, "learning_rate": 9.799075472561674e-06, "loss": 1.4103, "step": 176170 }, { "epoch": 8.04, "learning_rate": 9.79678703830839e-06, "loss": 1.175, "step": 176180 }, { "epoch": 8.05, "learning_rate": 9.794498604055106e-06, "loss": 1.4081, "step": 176190 }, { "epoch": 8.05, "learning_rate": 9.792210169801822e-06, "loss": 1.3185, "step": 176200 }, { "epoch": 8.05, "learning_rate": 9.789921735548538e-06, "loss": 1.3038, "step": 176210 }, { "epoch": 8.05, "learning_rate": 9.787633301295255e-06, "loss": 1.4916, "step": 176220 }, { "epoch": 8.05, "learning_rate": 9.785344867041971e-06, "loss": 1.2765, "step": 176230 }, { "epoch": 8.05, "learning_rate": 9.783056432788687e-06, "loss": 1.6095, "step": 176240 }, { "epoch": 8.05, "learning_rate": 9.780767998535403e-06, "loss": 1.3678, "step": 176250 }, { "epoch": 8.05, "learning_rate": 9.778479564282118e-06, "loss": 1.3502, "step": 176260 }, { "epoch": 8.05, "learning_rate": 9.776191130028834e-06, "loss": 1.3378, "step": 176270 }, { "epoch": 8.05, "learning_rate": 9.773902695775552e-06, "loss": 1.4032, "step": 176280 }, { "epoch": 8.05, "learning_rate": 9.771614261522268e-06, "loss": 1.2188, "step": 176290 }, { "epoch": 8.05, "learning_rate": 9.769325827268982e-06, "loss": 1.4558, "step": 176300 }, { "epoch": 8.05, "learning_rate": 9.7670373930157e-06, "loss": 1.2823, "step": 176310 }, { "epoch": 8.05, "learning_rate": 9.764748958762415e-06, "loss": 1.4445, "step": 176320 }, { "epoch": 8.05, "learning_rate": 9.76246052450913e-06, "loss": 1.2851, "step": 176330 }, { "epoch": 8.05, "learning_rate": 9.760172090255848e-06, "loss": 1.2765, "step": 176340 }, { "epoch": 8.05, "learning_rate": 9.757883656002562e-06, "loss": 1.3068, "step": 176350 }, { "epoch": 8.05, "learning_rate": 9.75559522174928e-06, "loss": 1.4251, "step": 176360 }, { "epoch": 8.05, "learning_rate": 9.753306787495996e-06, "loss": 1.4869, "step": 176370 }, { "epoch": 8.05, "learning_rate": 9.751018353242712e-06, "loss": 1.26, "step": 176380 }, { "epoch": 8.05, "learning_rate": 9.74872991898943e-06, "loss": 1.4693, "step": 176390 }, { "epoch": 8.05, "learning_rate": 9.746441484736143e-06, "loss": 1.3628, "step": 176400 }, { "epoch": 8.06, "learning_rate": 9.744153050482859e-06, "loss": 1.3607, "step": 176410 }, { "epoch": 8.06, "learning_rate": 9.741864616229577e-06, "loss": 1.4849, "step": 176420 }, { "epoch": 8.06, "learning_rate": 9.739576181976292e-06, "loss": 1.4481, "step": 176430 }, { "epoch": 8.06, "learning_rate": 9.737287747723008e-06, "loss": 1.3354, "step": 176440 }, { "epoch": 8.06, "learning_rate": 9.734999313469724e-06, "loss": 1.3491, "step": 176450 }, { "epoch": 8.06, "learning_rate": 9.73271087921644e-06, "loss": 1.2755, "step": 176460 }, { "epoch": 8.06, "learning_rate": 9.730422444963157e-06, "loss": 1.3003, "step": 176470 }, { "epoch": 8.06, "learning_rate": 9.728134010709873e-06, "loss": 1.3335, "step": 176480 }, { "epoch": 8.06, "learning_rate": 9.72584557645659e-06, "loss": 1.3264, "step": 176490 }, { "epoch": 8.06, "learning_rate": 9.723557142203305e-06, "loss": 1.3223, "step": 176500 }, { "epoch": 8.06, "learning_rate": 9.72126870795002e-06, "loss": 1.5255, "step": 176510 }, { "epoch": 8.06, "learning_rate": 9.718980273696737e-06, "loss": 1.2869, "step": 176520 }, { "epoch": 8.06, "learning_rate": 9.716691839443454e-06, "loss": 1.2151, "step": 176530 }, { "epoch": 8.06, "learning_rate": 9.71440340519017e-06, "loss": 1.2564, "step": 176540 }, { "epoch": 8.06, "learning_rate": 9.712114970936886e-06, "loss": 1.4341, "step": 176550 }, { "epoch": 8.06, "learning_rate": 9.709826536683602e-06, "loss": 1.3484, "step": 176560 }, { "epoch": 8.06, "learning_rate": 9.707538102430317e-06, "loss": 1.4192, "step": 176570 }, { "epoch": 8.06, "learning_rate": 9.705249668177033e-06, "loss": 1.3194, "step": 176580 }, { "epoch": 8.06, "learning_rate": 9.70296123392375e-06, "loss": 1.2553, "step": 176590 }, { "epoch": 8.06, "learning_rate": 9.700672799670465e-06, "loss": 1.4399, "step": 176600 }, { "epoch": 8.06, "learning_rate": 9.698384365417182e-06, "loss": 1.3886, "step": 176610 }, { "epoch": 8.06, "learning_rate": 9.696095931163898e-06, "loss": 1.3506, "step": 176620 }, { "epoch": 8.07, "learning_rate": 9.693807496910614e-06, "loss": 1.2038, "step": 176630 }, { "epoch": 8.07, "learning_rate": 9.691519062657332e-06, "loss": 1.2581, "step": 176640 }, { "epoch": 8.07, "learning_rate": 9.689230628404046e-06, "loss": 1.1848, "step": 176650 }, { "epoch": 8.07, "learning_rate": 9.686942194150762e-06, "loss": 1.5676, "step": 176660 }, { "epoch": 8.07, "learning_rate": 9.684653759897479e-06, "loss": 1.2079, "step": 176670 }, { "epoch": 8.07, "learning_rate": 9.682365325644195e-06, "loss": 1.3677, "step": 176680 }, { "epoch": 8.07, "learning_rate": 9.68007689139091e-06, "loss": 1.5198, "step": 176690 }, { "epoch": 8.07, "learning_rate": 9.677788457137627e-06, "loss": 1.3247, "step": 176700 }, { "epoch": 8.07, "learning_rate": 9.675500022884342e-06, "loss": 1.4129, "step": 176710 }, { "epoch": 8.07, "learning_rate": 9.67321158863106e-06, "loss": 1.2588, "step": 176720 }, { "epoch": 8.07, "learning_rate": 9.670923154377776e-06, "loss": 1.3338, "step": 176730 }, { "epoch": 8.07, "learning_rate": 9.66863472012449e-06, "loss": 1.4243, "step": 176740 }, { "epoch": 8.07, "learning_rate": 9.666346285871207e-06, "loss": 1.4129, "step": 176750 }, { "epoch": 8.07, "learning_rate": 9.664057851617923e-06, "loss": 1.549, "step": 176760 }, { "epoch": 8.07, "learning_rate": 9.661769417364639e-06, "loss": 1.3521, "step": 176770 }, { "epoch": 8.07, "learning_rate": 9.659480983111357e-06, "loss": 1.4603, "step": 176780 }, { "epoch": 8.07, "learning_rate": 9.65719254885807e-06, "loss": 1.1995, "step": 176790 }, { "epoch": 8.07, "learning_rate": 9.654904114604788e-06, "loss": 1.4622, "step": 176800 }, { "epoch": 8.07, "learning_rate": 9.652615680351504e-06, "loss": 1.3811, "step": 176810 }, { "epoch": 8.07, "learning_rate": 9.65032724609822e-06, "loss": 1.2574, "step": 176820 }, { "epoch": 8.07, "learning_rate": 9.648038811844937e-06, "loss": 1.2528, "step": 176830 }, { "epoch": 8.07, "learning_rate": 9.645750377591652e-06, "loss": 1.307, "step": 176840 }, { "epoch": 8.08, "learning_rate": 9.643461943338367e-06, "loss": 1.2706, "step": 176850 }, { "epoch": 8.08, "learning_rate": 9.641173509085085e-06, "loss": 1.4762, "step": 176860 }, { "epoch": 8.08, "learning_rate": 9.6388850748318e-06, "loss": 1.2238, "step": 176870 }, { "epoch": 8.08, "learning_rate": 9.636596640578517e-06, "loss": 1.2341, "step": 176880 }, { "epoch": 8.08, "learning_rate": 9.634308206325232e-06, "loss": 1.3665, "step": 176890 }, { "epoch": 8.08, "learning_rate": 9.632019772071948e-06, "loss": 1.3398, "step": 176900 }, { "epoch": 8.08, "learning_rate": 9.629731337818664e-06, "loss": 1.338, "step": 176910 }, { "epoch": 8.08, "learning_rate": 9.627442903565382e-06, "loss": 1.2543, "step": 176920 }, { "epoch": 8.08, "learning_rate": 9.625154469312097e-06, "loss": 1.2822, "step": 176930 }, { "epoch": 8.08, "learning_rate": 9.622866035058813e-06, "loss": 1.495, "step": 176940 }, { "epoch": 8.08, "learning_rate": 9.620577600805529e-06, "loss": 1.4386, "step": 176950 }, { "epoch": 8.08, "learning_rate": 9.618289166552245e-06, "loss": 1.5572, "step": 176960 }, { "epoch": 8.08, "learning_rate": 9.616000732298962e-06, "loss": 1.4223, "step": 176970 }, { "epoch": 8.08, "learning_rate": 9.613712298045678e-06, "loss": 1.2819, "step": 176980 }, { "epoch": 8.08, "learning_rate": 9.611423863792392e-06, "loss": 1.4128, "step": 176990 }, { "epoch": 8.08, "learning_rate": 9.60913542953911e-06, "loss": 1.4222, "step": 177000 }, { "epoch": 8.08, "learning_rate": 9.606846995285826e-06, "loss": 1.2192, "step": 177010 }, { "epoch": 8.08, "learning_rate": 9.604558561032542e-06, "loss": 1.27, "step": 177020 }, { "epoch": 8.08, "learning_rate": 9.602270126779259e-06, "loss": 1.4496, "step": 177030 }, { "epoch": 8.08, "learning_rate": 9.599981692525973e-06, "loss": 1.4564, "step": 177040 }, { "epoch": 8.08, "learning_rate": 9.59769325827269e-06, "loss": 1.357, "step": 177050 }, { "epoch": 8.09, "learning_rate": 9.595404824019407e-06, "loss": 1.452, "step": 177060 }, { "epoch": 8.09, "learning_rate": 9.593116389766122e-06, "loss": 1.5119, "step": 177070 }, { "epoch": 8.09, "learning_rate": 9.59082795551284e-06, "loss": 1.4333, "step": 177080 }, { "epoch": 8.09, "learning_rate": 9.588539521259554e-06, "loss": 1.2418, "step": 177090 }, { "epoch": 8.09, "learning_rate": 9.58625108700627e-06, "loss": 1.3011, "step": 177100 }, { "epoch": 8.09, "learning_rate": 9.583962652752987e-06, "loss": 1.5045, "step": 177110 }, { "epoch": 8.09, "learning_rate": 9.581674218499703e-06, "loss": 1.2935, "step": 177120 }, { "epoch": 8.09, "learning_rate": 9.579385784246419e-06, "loss": 1.2814, "step": 177130 }, { "epoch": 8.09, "learning_rate": 9.577097349993135e-06, "loss": 1.3041, "step": 177140 }, { "epoch": 8.09, "learning_rate": 9.57480891573985e-06, "loss": 1.3846, "step": 177150 }, { "epoch": 8.09, "learning_rate": 9.572520481486567e-06, "loss": 1.4124, "step": 177160 }, { "epoch": 8.09, "learning_rate": 9.570232047233284e-06, "loss": 1.3771, "step": 177170 }, { "epoch": 8.09, "learning_rate": 9.56794361298e-06, "loss": 1.4515, "step": 177180 }, { "epoch": 8.09, "learning_rate": 9.565655178726716e-06, "loss": 1.4051, "step": 177190 }, { "epoch": 8.09, "learning_rate": 9.563366744473432e-06, "loss": 1.7128, "step": 177200 }, { "epoch": 8.09, "learning_rate": 9.561078310220147e-06, "loss": 1.4986, "step": 177210 }, { "epoch": 8.09, "learning_rate": 9.558789875966865e-06, "loss": 1.3908, "step": 177220 }, { "epoch": 8.09, "learning_rate": 9.55650144171358e-06, "loss": 1.3374, "step": 177230 }, { "epoch": 8.09, "learning_rate": 9.554213007460295e-06, "loss": 1.4261, "step": 177240 }, { "epoch": 8.09, "learning_rate": 9.551924573207012e-06, "loss": 1.3238, "step": 177250 }, { "epoch": 8.09, "learning_rate": 9.549636138953728e-06, "loss": 1.4963, "step": 177260 }, { "epoch": 8.09, "learning_rate": 9.547347704700444e-06, "loss": 1.3564, "step": 177270 }, { "epoch": 8.1, "learning_rate": 9.545059270447162e-06, "loss": 1.5424, "step": 177280 }, { "epoch": 8.1, "learning_rate": 9.542770836193876e-06, "loss": 1.5896, "step": 177290 }, { "epoch": 8.1, "learning_rate": 9.540482401940593e-06, "loss": 1.4175, "step": 177300 }, { "epoch": 8.1, "learning_rate": 9.538193967687309e-06, "loss": 1.3984, "step": 177310 }, { "epoch": 8.1, "learning_rate": 9.535905533434025e-06, "loss": 1.2822, "step": 177320 }, { "epoch": 8.1, "learning_rate": 9.533617099180742e-06, "loss": 1.548, "step": 177330 }, { "epoch": 8.1, "learning_rate": 9.531328664927457e-06, "loss": 1.4727, "step": 177340 }, { "epoch": 8.1, "learning_rate": 9.529040230674172e-06, "loss": 1.3308, "step": 177350 }, { "epoch": 8.1, "learning_rate": 9.52675179642089e-06, "loss": 1.3613, "step": 177360 }, { "epoch": 8.1, "learning_rate": 9.524463362167606e-06, "loss": 1.3643, "step": 177370 }, { "epoch": 8.1, "learning_rate": 9.522174927914322e-06, "loss": 1.276, "step": 177380 }, { "epoch": 8.1, "learning_rate": 9.519886493661037e-06, "loss": 1.3373, "step": 177390 }, { "epoch": 8.1, "learning_rate": 9.517598059407753e-06, "loss": 1.3042, "step": 177400 }, { "epoch": 8.1, "learning_rate": 9.51530962515447e-06, "loss": 1.4772, "step": 177410 }, { "epoch": 8.1, "learning_rate": 9.513021190901187e-06, "loss": 1.3463, "step": 177420 }, { "epoch": 8.1, "learning_rate": 9.510732756647902e-06, "loss": 1.2021, "step": 177430 }, { "epoch": 8.1, "learning_rate": 9.508444322394618e-06, "loss": 1.3707, "step": 177440 }, { "epoch": 8.1, "learning_rate": 9.506155888141334e-06, "loss": 1.2741, "step": 177450 }, { "epoch": 8.1, "learning_rate": 9.50386745388805e-06, "loss": 1.3124, "step": 177460 }, { "epoch": 8.1, "learning_rate": 9.501579019634767e-06, "loss": 1.3472, "step": 177470 }, { "epoch": 8.1, "learning_rate": 9.499290585381481e-06, "loss": 1.2464, "step": 177480 }, { "epoch": 8.1, "learning_rate": 9.497002151128197e-06, "loss": 1.3533, "step": 177490 }, { "epoch": 8.11, "learning_rate": 9.494713716874915e-06, "loss": 1.3423, "step": 177500 }, { "epoch": 8.11, "learning_rate": 9.49242528262163e-06, "loss": 1.3664, "step": 177510 }, { "epoch": 8.11, "learning_rate": 9.490136848368347e-06, "loss": 1.5175, "step": 177520 }, { "epoch": 8.11, "learning_rate": 9.487848414115062e-06, "loss": 1.3208, "step": 177530 }, { "epoch": 8.11, "learning_rate": 9.485559979861778e-06, "loss": 1.3237, "step": 177540 }, { "epoch": 8.11, "learning_rate": 9.483271545608496e-06, "loss": 1.2604, "step": 177550 }, { "epoch": 8.11, "learning_rate": 9.480983111355212e-06, "loss": 1.4621, "step": 177560 }, { "epoch": 8.11, "learning_rate": 9.478694677101927e-06, "loss": 1.3074, "step": 177570 }, { "epoch": 8.11, "learning_rate": 9.476406242848643e-06, "loss": 1.342, "step": 177580 }, { "epoch": 8.11, "learning_rate": 9.474117808595359e-06, "loss": 1.1736, "step": 177590 }, { "epoch": 8.11, "learning_rate": 9.471829374342075e-06, "loss": 1.2793, "step": 177600 }, { "epoch": 8.11, "learning_rate": 9.469540940088792e-06, "loss": 1.3033, "step": 177610 }, { "epoch": 8.11, "learning_rate": 9.467252505835508e-06, "loss": 1.5099, "step": 177620 }, { "epoch": 8.11, "learning_rate": 9.464964071582224e-06, "loss": 1.3122, "step": 177630 }, { "epoch": 8.11, "learning_rate": 9.46267563732894e-06, "loss": 1.4214, "step": 177640 }, { "epoch": 8.11, "learning_rate": 9.460387203075656e-06, "loss": 1.5014, "step": 177650 }, { "epoch": 8.11, "learning_rate": 9.458098768822373e-06, "loss": 1.2211, "step": 177660 }, { "epoch": 8.11, "learning_rate": 9.455810334569089e-06, "loss": 1.3779, "step": 177670 }, { "epoch": 8.11, "learning_rate": 9.453521900315803e-06, "loss": 1.2235, "step": 177680 }, { "epoch": 8.11, "learning_rate": 9.45123346606252e-06, "loss": 1.4847, "step": 177690 }, { "epoch": 8.11, "learning_rate": 9.448945031809236e-06, "loss": 1.5016, "step": 177700 }, { "epoch": 8.11, "learning_rate": 9.446656597555952e-06, "loss": 1.4327, "step": 177710 }, { "epoch": 8.12, "learning_rate": 9.44436816330267e-06, "loss": 1.3419, "step": 177720 }, { "epoch": 8.12, "learning_rate": 9.442079729049384e-06, "loss": 1.3205, "step": 177730 }, { "epoch": 8.12, "learning_rate": 9.4397912947961e-06, "loss": 1.4674, "step": 177740 }, { "epoch": 8.12, "learning_rate": 9.437502860542817e-06, "loss": 1.2077, "step": 177750 }, { "epoch": 8.12, "learning_rate": 9.435214426289533e-06, "loss": 1.4709, "step": 177760 }, { "epoch": 8.12, "learning_rate": 9.432925992036249e-06, "loss": 1.3718, "step": 177770 }, { "epoch": 8.12, "learning_rate": 9.430637557782965e-06, "loss": 1.4309, "step": 177780 }, { "epoch": 8.12, "learning_rate": 9.42834912352968e-06, "loss": 1.3434, "step": 177790 }, { "epoch": 8.12, "learning_rate": 9.426060689276398e-06, "loss": 1.4605, "step": 177800 }, { "epoch": 8.12, "learning_rate": 9.423772255023114e-06, "loss": 1.43, "step": 177810 }, { "epoch": 8.12, "learning_rate": 9.42148382076983e-06, "loss": 1.4049, "step": 177820 }, { "epoch": 8.12, "learning_rate": 9.419195386516546e-06, "loss": 1.4559, "step": 177830 }, { "epoch": 8.12, "learning_rate": 9.416906952263261e-06, "loss": 1.3348, "step": 177840 }, { "epoch": 8.12, "learning_rate": 9.414618518009977e-06, "loss": 1.4329, "step": 177850 }, { "epoch": 8.12, "learning_rate": 9.412330083756695e-06, "loss": 1.3368, "step": 177860 }, { "epoch": 8.12, "learning_rate": 9.41004164950341e-06, "loss": 1.2611, "step": 177870 }, { "epoch": 8.12, "learning_rate": 9.407753215250126e-06, "loss": 1.283, "step": 177880 }, { "epoch": 8.12, "learning_rate": 9.405464780996842e-06, "loss": 1.3314, "step": 177890 }, { "epoch": 8.12, "learning_rate": 9.403176346743558e-06, "loss": 1.3521, "step": 177900 }, { "epoch": 8.12, "learning_rate": 9.400887912490276e-06, "loss": 1.3018, "step": 177910 }, { "epoch": 8.12, "learning_rate": 9.398599478236991e-06, "loss": 1.3042, "step": 177920 }, { "epoch": 8.12, "learning_rate": 9.396311043983706e-06, "loss": 1.4502, "step": 177930 }, { "epoch": 8.13, "learning_rate": 9.394022609730423e-06, "loss": 1.3568, "step": 177940 }, { "epoch": 8.13, "learning_rate": 9.391734175477139e-06, "loss": 1.5372, "step": 177950 }, { "epoch": 8.13, "learning_rate": 9.389445741223855e-06, "loss": 1.2922, "step": 177960 }, { "epoch": 8.13, "learning_rate": 9.387157306970572e-06, "loss": 1.3197, "step": 177970 }, { "epoch": 8.13, "learning_rate": 9.384868872717286e-06, "loss": 1.3227, "step": 177980 }, { "epoch": 8.13, "learning_rate": 9.382580438464004e-06, "loss": 1.3705, "step": 177990 }, { "epoch": 8.13, "learning_rate": 9.38029200421072e-06, "loss": 1.4417, "step": 178000 }, { "epoch": 8.13, "learning_rate": 9.378003569957436e-06, "loss": 1.2359, "step": 178010 }, { "epoch": 8.13, "learning_rate": 9.375715135704151e-06, "loss": 1.4957, "step": 178020 }, { "epoch": 8.13, "learning_rate": 9.373426701450867e-06, "loss": 1.4244, "step": 178030 }, { "epoch": 8.13, "learning_rate": 9.371138267197583e-06, "loss": 1.3169, "step": 178040 }, { "epoch": 8.13, "learning_rate": 9.3688498329443e-06, "loss": 1.3401, "step": 178050 }, { "epoch": 8.13, "learning_rate": 9.366561398691016e-06, "loss": 1.249, "step": 178060 }, { "epoch": 8.13, "learning_rate": 9.364272964437732e-06, "loss": 1.1721, "step": 178070 }, { "epoch": 8.13, "learning_rate": 9.361984530184448e-06, "loss": 1.3618, "step": 178080 }, { "epoch": 8.13, "learning_rate": 9.359696095931164e-06, "loss": 1.43, "step": 178090 }, { "epoch": 8.13, "learning_rate": 9.35740766167788e-06, "loss": 1.4169, "step": 178100 }, { "epoch": 8.13, "learning_rate": 9.355119227424597e-06, "loss": 1.4531, "step": 178110 }, { "epoch": 8.13, "learning_rate": 9.352830793171313e-06, "loss": 1.322, "step": 178120 }, { "epoch": 8.13, "learning_rate": 9.350542358918029e-06, "loss": 1.5617, "step": 178130 }, { "epoch": 8.13, "learning_rate": 9.348253924664745e-06, "loss": 1.3599, "step": 178140 }, { "epoch": 8.13, "learning_rate": 9.34596549041146e-06, "loss": 1.3842, "step": 178150 }, { "epoch": 8.14, "learning_rate": 9.343677056158178e-06, "loss": 1.3372, "step": 178160 }, { "epoch": 8.14, "learning_rate": 9.341388621904894e-06, "loss": 1.2622, "step": 178170 }, { "epoch": 8.14, "learning_rate": 9.339100187651608e-06, "loss": 1.3224, "step": 178180 }, { "epoch": 8.14, "learning_rate": 9.336811753398326e-06, "loss": 1.4479, "step": 178190 }, { "epoch": 8.14, "learning_rate": 9.334523319145041e-06, "loss": 1.3674, "step": 178200 }, { "epoch": 8.14, "learning_rate": 9.332234884891757e-06, "loss": 1.2647, "step": 178210 }, { "epoch": 8.14, "learning_rate": 9.329946450638475e-06, "loss": 1.4022, "step": 178220 }, { "epoch": 8.14, "learning_rate": 9.327658016385189e-06, "loss": 1.3164, "step": 178230 }, { "epoch": 8.14, "learning_rate": 9.325369582131906e-06, "loss": 1.3588, "step": 178240 }, { "epoch": 8.14, "learning_rate": 9.323081147878622e-06, "loss": 1.3763, "step": 178250 }, { "epoch": 8.14, "learning_rate": 9.320792713625338e-06, "loss": 1.2845, "step": 178260 }, { "epoch": 8.14, "learning_rate": 9.318504279372056e-06, "loss": 1.3845, "step": 178270 }, { "epoch": 8.14, "learning_rate": 9.31621584511877e-06, "loss": 1.2758, "step": 178280 }, { "epoch": 8.14, "learning_rate": 9.313927410865486e-06, "loss": 1.2439, "step": 178290 }, { "epoch": 8.14, "learning_rate": 9.311638976612203e-06, "loss": 1.2844, "step": 178300 }, { "epoch": 8.14, "learning_rate": 9.309350542358919e-06, "loss": 1.4104, "step": 178310 }, { "epoch": 8.14, "learning_rate": 9.307062108105635e-06, "loss": 1.3665, "step": 178320 }, { "epoch": 8.14, "learning_rate": 9.30477367385235e-06, "loss": 1.4962, "step": 178330 }, { "epoch": 8.14, "learning_rate": 9.302485239599066e-06, "loss": 1.3064, "step": 178340 }, { "epoch": 8.14, "learning_rate": 9.300196805345782e-06, "loss": 1.3996, "step": 178350 }, { "epoch": 8.14, "learning_rate": 9.2979083710925e-06, "loss": 1.4993, "step": 178360 }, { "epoch": 8.14, "learning_rate": 9.295619936839214e-06, "loss": 1.391, "step": 178370 }, { "epoch": 8.15, "learning_rate": 9.293331502585931e-06, "loss": 1.4466, "step": 178380 }, { "epoch": 8.15, "learning_rate": 9.291043068332647e-06, "loss": 1.3106, "step": 178390 }, { "epoch": 8.15, "learning_rate": 9.288754634079363e-06, "loss": 1.3193, "step": 178400 }, { "epoch": 8.15, "learning_rate": 9.28646619982608e-06, "loss": 1.4655, "step": 178410 }, { "epoch": 8.15, "learning_rate": 9.284177765572795e-06, "loss": 1.4025, "step": 178420 }, { "epoch": 8.15, "learning_rate": 9.28188933131951e-06, "loss": 1.452, "step": 178430 }, { "epoch": 8.15, "learning_rate": 9.279600897066228e-06, "loss": 1.1902, "step": 178440 }, { "epoch": 8.15, "learning_rate": 9.277312462812944e-06, "loss": 1.2868, "step": 178450 }, { "epoch": 8.15, "learning_rate": 9.27502402855966e-06, "loss": 1.2773, "step": 178460 }, { "epoch": 8.15, "learning_rate": 9.272735594306376e-06, "loss": 1.3126, "step": 178470 }, { "epoch": 8.15, "learning_rate": 9.270447160053091e-06, "loss": 1.2424, "step": 178480 }, { "epoch": 8.15, "learning_rate": 9.268158725799809e-06, "loss": 1.4637, "step": 178490 }, { "epoch": 8.15, "learning_rate": 9.265870291546525e-06, "loss": 1.3346, "step": 178500 }, { "epoch": 8.15, "learning_rate": 9.26358185729324e-06, "loss": 1.2892, "step": 178510 }, { "epoch": 8.15, "learning_rate": 9.261293423039956e-06, "loss": 1.1697, "step": 178520 }, { "epoch": 8.15, "learning_rate": 9.259004988786672e-06, "loss": 1.4855, "step": 178530 }, { "epoch": 8.15, "learning_rate": 9.256716554533388e-06, "loss": 1.3744, "step": 178540 }, { "epoch": 8.15, "learning_rate": 9.254428120280106e-06, "loss": 1.5483, "step": 178550 }, { "epoch": 8.15, "learning_rate": 9.252139686026821e-06, "loss": 1.2259, "step": 178560 }, { "epoch": 8.15, "learning_rate": 9.249851251773537e-06, "loss": 1.4897, "step": 178570 }, { "epoch": 8.15, "learning_rate": 9.247562817520253e-06, "loss": 1.3449, "step": 178580 }, { "epoch": 8.15, "learning_rate": 9.245274383266969e-06, "loss": 1.2866, "step": 178590 }, { "epoch": 8.16, "learning_rate": 9.242985949013685e-06, "loss": 1.2673, "step": 178600 }, { "epoch": 8.16, "learning_rate": 9.240697514760402e-06, "loss": 1.3262, "step": 178610 }, { "epoch": 8.16, "learning_rate": 9.238409080507116e-06, "loss": 1.3528, "step": 178620 }, { "epoch": 8.16, "learning_rate": 9.236120646253834e-06, "loss": 1.5103, "step": 178630 }, { "epoch": 8.16, "learning_rate": 9.23383221200055e-06, "loss": 1.4031, "step": 178640 }, { "epoch": 8.16, "learning_rate": 9.231543777747266e-06, "loss": 1.3268, "step": 178650 }, { "epoch": 8.16, "learning_rate": 9.229255343493983e-06, "loss": 1.3428, "step": 178660 }, { "epoch": 8.16, "learning_rate": 9.226966909240697e-06, "loss": 1.2608, "step": 178670 }, { "epoch": 8.16, "learning_rate": 9.224678474987413e-06, "loss": 1.3247, "step": 178680 }, { "epoch": 8.16, "learning_rate": 9.22239004073413e-06, "loss": 1.2405, "step": 178690 }, { "epoch": 8.16, "learning_rate": 9.220101606480846e-06, "loss": 1.3069, "step": 178700 }, { "epoch": 8.16, "learning_rate": 9.217813172227562e-06, "loss": 1.5105, "step": 178710 }, { "epoch": 8.16, "learning_rate": 9.215524737974278e-06, "loss": 1.3572, "step": 178720 }, { "epoch": 8.16, "learning_rate": 9.213236303720994e-06, "loss": 1.2895, "step": 178730 }, { "epoch": 8.16, "learning_rate": 9.210947869467711e-06, "loss": 1.3912, "step": 178740 }, { "epoch": 8.16, "learning_rate": 9.208659435214427e-06, "loss": 1.3706, "step": 178750 }, { "epoch": 8.16, "learning_rate": 9.206371000961143e-06, "loss": 1.4149, "step": 178760 }, { "epoch": 8.16, "learning_rate": 9.204082566707859e-06, "loss": 1.2563, "step": 178770 }, { "epoch": 8.16, "learning_rate": 9.201794132454575e-06, "loss": 1.3292, "step": 178780 }, { "epoch": 8.16, "learning_rate": 9.19950569820129e-06, "loss": 1.3044, "step": 178790 }, { "epoch": 8.16, "learning_rate": 9.197217263948008e-06, "loss": 1.3789, "step": 178800 }, { "epoch": 8.16, "learning_rate": 9.194928829694724e-06, "loss": 1.2591, "step": 178810 }, { "epoch": 8.17, "learning_rate": 9.19264039544144e-06, "loss": 1.1763, "step": 178820 }, { "epoch": 8.17, "learning_rate": 9.190351961188155e-06, "loss": 1.3083, "step": 178830 }, { "epoch": 8.17, "learning_rate": 9.188063526934871e-06, "loss": 1.2926, "step": 178840 }, { "epoch": 8.17, "learning_rate": 9.185775092681589e-06, "loss": 1.4615, "step": 178850 }, { "epoch": 8.17, "learning_rate": 9.183486658428305e-06, "loss": 1.4701, "step": 178860 }, { "epoch": 8.17, "learning_rate": 9.181198224175019e-06, "loss": 1.2912, "step": 178870 }, { "epoch": 8.17, "learning_rate": 9.178909789921736e-06, "loss": 1.1868, "step": 178880 }, { "epoch": 8.17, "learning_rate": 9.176621355668452e-06, "loss": 1.4362, "step": 178890 }, { "epoch": 8.17, "learning_rate": 9.174332921415168e-06, "loss": 1.4718, "step": 178900 }, { "epoch": 8.17, "learning_rate": 9.172044487161886e-06, "loss": 1.2713, "step": 178910 }, { "epoch": 8.17, "learning_rate": 9.1697560529086e-06, "loss": 1.3169, "step": 178920 }, { "epoch": 8.17, "learning_rate": 9.167467618655315e-06, "loss": 1.3505, "step": 178930 }, { "epoch": 8.17, "learning_rate": 9.165179184402033e-06, "loss": 1.1556, "step": 178940 }, { "epoch": 8.17, "learning_rate": 9.162890750148749e-06, "loss": 1.3379, "step": 178950 }, { "epoch": 8.17, "learning_rate": 9.160602315895465e-06, "loss": 1.4679, "step": 178960 }, { "epoch": 8.17, "learning_rate": 9.15831388164218e-06, "loss": 1.3719, "step": 178970 }, { "epoch": 8.17, "learning_rate": 9.156025447388896e-06, "loss": 1.2955, "step": 178980 }, { "epoch": 8.17, "learning_rate": 9.153737013135614e-06, "loss": 1.3741, "step": 178990 }, { "epoch": 8.17, "learning_rate": 9.15144857888233e-06, "loss": 1.2436, "step": 179000 }, { "epoch": 8.17, "learning_rate": 9.149160144629045e-06, "loss": 1.3059, "step": 179010 }, { "epoch": 8.17, "learning_rate": 9.146871710375761e-06, "loss": 1.3462, "step": 179020 }, { "epoch": 8.17, "learning_rate": 9.144583276122477e-06, "loss": 1.4436, "step": 179030 }, { "epoch": 8.18, "learning_rate": 9.142294841869193e-06, "loss": 1.2783, "step": 179040 }, { "epoch": 8.18, "learning_rate": 9.14000640761591e-06, "loss": 1.2881, "step": 179050 }, { "epoch": 8.18, "learning_rate": 9.137717973362626e-06, "loss": 1.3654, "step": 179060 }, { "epoch": 8.18, "learning_rate": 9.135429539109342e-06, "loss": 1.3953, "step": 179070 }, { "epoch": 8.18, "learning_rate": 9.133141104856058e-06, "loss": 1.2339, "step": 179080 }, { "epoch": 8.18, "learning_rate": 9.130852670602774e-06, "loss": 1.3858, "step": 179090 }, { "epoch": 8.18, "learning_rate": 9.128564236349491e-06, "loss": 1.3535, "step": 179100 }, { "epoch": 8.18, "learning_rate": 9.126275802096205e-06, "loss": 1.3669, "step": 179110 }, { "epoch": 8.18, "learning_rate": 9.123987367842921e-06, "loss": 1.31, "step": 179120 }, { "epoch": 8.18, "learning_rate": 9.121698933589639e-06, "loss": 1.339, "step": 179130 }, { "epoch": 8.18, "learning_rate": 9.119410499336355e-06, "loss": 1.4074, "step": 179140 }, { "epoch": 8.18, "learning_rate": 9.11712206508307e-06, "loss": 1.3119, "step": 179150 }, { "epoch": 8.18, "learning_rate": 9.114833630829786e-06, "loss": 1.3824, "step": 179160 }, { "epoch": 8.18, "learning_rate": 9.112545196576502e-06, "loss": 1.3062, "step": 179170 }, { "epoch": 8.18, "learning_rate": 9.11025676232322e-06, "loss": 1.56, "step": 179180 }, { "epoch": 8.18, "learning_rate": 9.107968328069935e-06, "loss": 1.2902, "step": 179190 }, { "epoch": 8.18, "learning_rate": 9.105679893816651e-06, "loss": 1.4137, "step": 179200 }, { "epoch": 8.18, "learning_rate": 9.103391459563367e-06, "loss": 1.371, "step": 179210 }, { "epoch": 8.18, "learning_rate": 9.101103025310083e-06, "loss": 1.3054, "step": 179220 }, { "epoch": 8.18, "learning_rate": 9.098814591056799e-06, "loss": 1.3877, "step": 179230 }, { "epoch": 8.18, "learning_rate": 9.096526156803516e-06, "loss": 1.4724, "step": 179240 }, { "epoch": 8.19, "learning_rate": 9.094237722550232e-06, "loss": 1.2439, "step": 179250 }, { "epoch": 8.19, "learning_rate": 9.091949288296946e-06, "loss": 1.4102, "step": 179260 }, { "epoch": 8.19, "learning_rate": 9.089660854043664e-06, "loss": 1.5323, "step": 179270 }, { "epoch": 8.19, "learning_rate": 9.08737241979038e-06, "loss": 1.521, "step": 179280 }, { "epoch": 8.19, "learning_rate": 9.085083985537095e-06, "loss": 1.1752, "step": 179290 }, { "epoch": 8.19, "learning_rate": 9.082795551283813e-06, "loss": 1.2973, "step": 179300 }, { "epoch": 8.19, "learning_rate": 9.080507117030527e-06, "loss": 1.3605, "step": 179310 }, { "epoch": 8.19, "learning_rate": 9.078218682777245e-06, "loss": 1.3392, "step": 179320 }, { "epoch": 8.19, "learning_rate": 9.07593024852396e-06, "loss": 1.3429, "step": 179330 }, { "epoch": 8.19, "learning_rate": 9.073641814270676e-06, "loss": 1.3662, "step": 179340 }, { "epoch": 8.19, "learning_rate": 9.071353380017394e-06, "loss": 1.4102, "step": 179350 }, { "epoch": 8.19, "learning_rate": 9.069064945764108e-06, "loss": 1.3982, "step": 179360 }, { "epoch": 8.19, "learning_rate": 9.066776511510824e-06, "loss": 1.3841, "step": 179370 }, { "epoch": 8.19, "learning_rate": 9.064488077257541e-06, "loss": 1.4621, "step": 179380 }, { "epoch": 8.19, "learning_rate": 9.062199643004257e-06, "loss": 1.3528, "step": 179390 }, { "epoch": 8.19, "learning_rate": 9.059911208750973e-06, "loss": 1.332, "step": 179400 }, { "epoch": 8.19, "learning_rate": 9.057622774497689e-06, "loss": 1.4086, "step": 179410 }, { "epoch": 8.19, "learning_rate": 9.055334340244405e-06, "loss": 1.4281, "step": 179420 }, { "epoch": 8.19, "learning_rate": 9.053045905991122e-06, "loss": 1.439, "step": 179430 }, { "epoch": 8.19, "learning_rate": 9.050757471737838e-06, "loss": 1.3735, "step": 179440 }, { "epoch": 8.19, "learning_rate": 9.048469037484554e-06, "loss": 1.3692, "step": 179450 }, { "epoch": 8.19, "learning_rate": 9.04618060323127e-06, "loss": 1.4591, "step": 179460 }, { "epoch": 8.2, "learning_rate": 9.043892168977985e-06, "loss": 1.3337, "step": 179470 }, { "epoch": 8.2, "learning_rate": 9.041603734724701e-06, "loss": 1.3957, "step": 179480 }, { "epoch": 8.2, "learning_rate": 9.039315300471419e-06, "loss": 1.4647, "step": 179490 }, { "epoch": 8.2, "learning_rate": 9.037026866218135e-06, "loss": 1.3583, "step": 179500 }, { "epoch": 8.2, "learning_rate": 9.034738431964849e-06, "loss": 1.4154, "step": 179510 }, { "epoch": 8.2, "learning_rate": 9.032449997711566e-06, "loss": 1.2216, "step": 179520 }, { "epoch": 8.2, "learning_rate": 9.030161563458282e-06, "loss": 1.2863, "step": 179530 }, { "epoch": 8.2, "learning_rate": 9.027873129204998e-06, "loss": 1.3127, "step": 179540 }, { "epoch": 8.2, "learning_rate": 9.025584694951715e-06, "loss": 1.3609, "step": 179550 }, { "epoch": 8.2, "learning_rate": 9.02329626069843e-06, "loss": 1.358, "step": 179560 }, { "epoch": 8.2, "learning_rate": 9.021007826445147e-06, "loss": 1.4886, "step": 179570 }, { "epoch": 8.2, "learning_rate": 9.018719392191863e-06, "loss": 1.4273, "step": 179580 }, { "epoch": 8.2, "learning_rate": 9.016430957938579e-06, "loss": 1.5157, "step": 179590 }, { "epoch": 8.2, "learning_rate": 9.014142523685296e-06, "loss": 1.1856, "step": 179600 }, { "epoch": 8.2, "learning_rate": 9.01185408943201e-06, "loss": 1.4788, "step": 179610 }, { "epoch": 8.2, "learning_rate": 9.009565655178726e-06, "loss": 1.4298, "step": 179620 }, { "epoch": 8.2, "learning_rate": 9.007277220925444e-06, "loss": 1.3555, "step": 179630 }, { "epoch": 8.2, "learning_rate": 9.00498878667216e-06, "loss": 1.3139, "step": 179640 }, { "epoch": 8.2, "learning_rate": 9.002700352418875e-06, "loss": 1.2997, "step": 179650 }, { "epoch": 8.2, "learning_rate": 9.000411918165591e-06, "loss": 1.2748, "step": 179660 }, { "epoch": 8.2, "learning_rate": 8.998123483912307e-06, "loss": 1.4452, "step": 179670 }, { "epoch": 8.2, "learning_rate": 8.995835049659025e-06, "loss": 1.3821, "step": 179680 }, { "epoch": 8.21, "learning_rate": 8.99354661540574e-06, "loss": 1.2876, "step": 179690 }, { "epoch": 8.21, "learning_rate": 8.991258181152456e-06, "loss": 1.5494, "step": 179700 }, { "epoch": 8.21, "learning_rate": 8.988969746899172e-06, "loss": 1.3621, "step": 179710 }, { "epoch": 8.21, "learning_rate": 8.986681312645888e-06, "loss": 1.2406, "step": 179720 }, { "epoch": 8.21, "learning_rate": 8.984392878392604e-06, "loss": 1.3344, "step": 179730 }, { "epoch": 8.21, "learning_rate": 8.982104444139321e-06, "loss": 1.269, "step": 179740 }, { "epoch": 8.21, "learning_rate": 8.979816009886037e-06, "loss": 1.357, "step": 179750 }, { "epoch": 8.21, "learning_rate": 8.977527575632753e-06, "loss": 1.297, "step": 179760 }, { "epoch": 8.21, "learning_rate": 8.975239141379469e-06, "loss": 1.4536, "step": 179770 }, { "epoch": 8.21, "learning_rate": 8.972950707126185e-06, "loss": 1.3607, "step": 179780 }, { "epoch": 8.21, "learning_rate": 8.9706622728729e-06, "loss": 1.3229, "step": 179790 }, { "epoch": 8.21, "learning_rate": 8.968373838619618e-06, "loss": 1.361, "step": 179800 }, { "epoch": 8.21, "learning_rate": 8.966085404366332e-06, "loss": 1.2995, "step": 179810 }, { "epoch": 8.21, "learning_rate": 8.96379697011305e-06, "loss": 1.4489, "step": 179820 }, { "epoch": 8.21, "learning_rate": 8.961508535859765e-06, "loss": 1.2977, "step": 179830 }, { "epoch": 8.21, "learning_rate": 8.959220101606481e-06, "loss": 1.2873, "step": 179840 }, { "epoch": 8.21, "learning_rate": 8.956931667353199e-06, "loss": 1.4373, "step": 179850 }, { "epoch": 8.21, "learning_rate": 8.954643233099913e-06, "loss": 1.3107, "step": 179860 }, { "epoch": 8.21, "learning_rate": 8.952354798846629e-06, "loss": 1.3139, "step": 179870 }, { "epoch": 8.21, "learning_rate": 8.950066364593346e-06, "loss": 1.2618, "step": 179880 }, { "epoch": 8.21, "learning_rate": 8.947777930340062e-06, "loss": 1.2787, "step": 179890 }, { "epoch": 8.21, "learning_rate": 8.945489496086778e-06, "loss": 1.4052, "step": 179900 }, { "epoch": 8.22, "learning_rate": 8.943201061833494e-06, "loss": 1.3683, "step": 179910 }, { "epoch": 8.22, "learning_rate": 8.94091262758021e-06, "loss": 1.2969, "step": 179920 }, { "epoch": 8.22, "learning_rate": 8.938624193326927e-06, "loss": 1.2916, "step": 179930 }, { "epoch": 8.22, "learning_rate": 8.936335759073643e-06, "loss": 1.428, "step": 179940 }, { "epoch": 8.22, "learning_rate": 8.934047324820357e-06, "loss": 1.3215, "step": 179950 }, { "epoch": 8.22, "learning_rate": 8.931758890567075e-06, "loss": 1.5204, "step": 179960 }, { "epoch": 8.22, "learning_rate": 8.92947045631379e-06, "loss": 1.2272, "step": 179970 }, { "epoch": 8.22, "learning_rate": 8.927182022060506e-06, "loss": 1.3583, "step": 179980 }, { "epoch": 8.22, "learning_rate": 8.924893587807224e-06, "loss": 1.362, "step": 179990 }, { "epoch": 8.22, "learning_rate": 8.922605153553938e-06, "loss": 1.2622, "step": 180000 }, { "epoch": 8.22, "learning_rate": 8.920316719300655e-06, "loss": 1.389, "step": 180010 }, { "epoch": 8.22, "learning_rate": 8.918028285047371e-06, "loss": 1.4318, "step": 180020 }, { "epoch": 8.22, "learning_rate": 8.915739850794087e-06, "loss": 1.3738, "step": 180030 }, { "epoch": 8.22, "learning_rate": 8.913451416540805e-06, "loss": 1.4801, "step": 180040 }, { "epoch": 8.22, "learning_rate": 8.911162982287519e-06, "loss": 1.3217, "step": 180050 }, { "epoch": 8.22, "learning_rate": 8.908874548034234e-06, "loss": 1.5004, "step": 180060 }, { "epoch": 8.22, "learning_rate": 8.906586113780952e-06, "loss": 1.3776, "step": 180070 }, { "epoch": 8.22, "learning_rate": 8.904297679527668e-06, "loss": 1.3327, "step": 180080 }, { "epoch": 8.22, "learning_rate": 8.902009245274384e-06, "loss": 1.2709, "step": 180090 }, { "epoch": 8.22, "learning_rate": 8.8997208110211e-06, "loss": 1.4207, "step": 180100 }, { "epoch": 8.22, "learning_rate": 8.897432376767815e-06, "loss": 1.2538, "step": 180110 }, { "epoch": 8.22, "learning_rate": 8.895143942514531e-06, "loss": 1.1738, "step": 180120 }, { "epoch": 8.23, "learning_rate": 8.892855508261249e-06, "loss": 1.3692, "step": 180130 }, { "epoch": 8.23, "learning_rate": 8.890567074007964e-06, "loss": 1.2631, "step": 180140 }, { "epoch": 8.23, "learning_rate": 8.88827863975468e-06, "loss": 1.5464, "step": 180150 }, { "epoch": 8.23, "learning_rate": 8.885990205501396e-06, "loss": 1.4743, "step": 180160 }, { "epoch": 8.23, "learning_rate": 8.883701771248112e-06, "loss": 1.254, "step": 180170 }, { "epoch": 8.23, "learning_rate": 8.88141333699483e-06, "loss": 1.4059, "step": 180180 }, { "epoch": 8.23, "learning_rate": 8.879124902741545e-06, "loss": 1.3672, "step": 180190 }, { "epoch": 8.23, "learning_rate": 8.87683646848826e-06, "loss": 1.3657, "step": 180200 }, { "epoch": 8.23, "learning_rate": 8.874548034234977e-06, "loss": 1.1417, "step": 180210 }, { "epoch": 8.23, "learning_rate": 8.872259599981693e-06, "loss": 1.5003, "step": 180220 }, { "epoch": 8.23, "learning_rate": 8.869971165728409e-06, "loss": 1.3932, "step": 180230 }, { "epoch": 8.23, "learning_rate": 8.867682731475126e-06, "loss": 1.482, "step": 180240 }, { "epoch": 8.23, "learning_rate": 8.86539429722184e-06, "loss": 1.2789, "step": 180250 }, { "epoch": 8.23, "learning_rate": 8.863105862968558e-06, "loss": 1.2475, "step": 180260 }, { "epoch": 8.23, "learning_rate": 8.860817428715274e-06, "loss": 1.2658, "step": 180270 }, { "epoch": 8.23, "learning_rate": 8.85852899446199e-06, "loss": 1.3404, "step": 180280 }, { "epoch": 8.23, "learning_rate": 8.856240560208707e-06, "loss": 1.4283, "step": 180290 }, { "epoch": 8.23, "learning_rate": 8.853952125955421e-06, "loss": 1.3103, "step": 180300 }, { "epoch": 8.23, "learning_rate": 8.851663691702137e-06, "loss": 1.4181, "step": 180310 }, { "epoch": 8.23, "learning_rate": 8.849375257448854e-06, "loss": 1.5538, "step": 180320 }, { "epoch": 8.23, "learning_rate": 8.84708682319557e-06, "loss": 1.298, "step": 180330 }, { "epoch": 8.23, "learning_rate": 8.844798388942286e-06, "loss": 1.3977, "step": 180340 }, { "epoch": 8.24, "learning_rate": 8.842509954689002e-06, "loss": 1.3421, "step": 180350 }, { "epoch": 8.24, "learning_rate": 8.840221520435718e-06, "loss": 1.445, "step": 180360 }, { "epoch": 8.24, "learning_rate": 8.837933086182434e-06, "loss": 1.2702, "step": 180370 }, { "epoch": 8.24, "learning_rate": 8.835644651929151e-06, "loss": 1.3094, "step": 180380 }, { "epoch": 8.24, "learning_rate": 8.833356217675867e-06, "loss": 1.3514, "step": 180390 }, { "epoch": 8.24, "learning_rate": 8.831067783422583e-06, "loss": 1.422, "step": 180400 }, { "epoch": 8.24, "learning_rate": 8.828779349169299e-06, "loss": 1.3716, "step": 180410 }, { "epoch": 8.24, "learning_rate": 8.826490914916014e-06, "loss": 1.4291, "step": 180420 }, { "epoch": 8.24, "learning_rate": 8.824202480662732e-06, "loss": 1.4684, "step": 180430 }, { "epoch": 8.24, "learning_rate": 8.821914046409448e-06, "loss": 1.4119, "step": 180440 }, { "epoch": 8.24, "learning_rate": 8.819625612156162e-06, "loss": 1.3484, "step": 180450 }, { "epoch": 8.24, "learning_rate": 8.81733717790288e-06, "loss": 1.2273, "step": 180460 }, { "epoch": 8.24, "learning_rate": 8.815048743649595e-06, "loss": 1.5135, "step": 180470 }, { "epoch": 8.24, "learning_rate": 8.812760309396311e-06, "loss": 1.4765, "step": 180480 }, { "epoch": 8.24, "learning_rate": 8.810471875143029e-06, "loss": 1.3292, "step": 180490 }, { "epoch": 8.24, "learning_rate": 8.808183440889743e-06, "loss": 1.2791, "step": 180500 }, { "epoch": 8.24, "learning_rate": 8.80589500663646e-06, "loss": 1.5379, "step": 180510 }, { "epoch": 8.24, "learning_rate": 8.803606572383176e-06, "loss": 1.2922, "step": 180520 }, { "epoch": 8.24, "learning_rate": 8.801318138129892e-06, "loss": 1.3054, "step": 180530 }, { "epoch": 8.24, "learning_rate": 8.79902970387661e-06, "loss": 1.3593, "step": 180540 }, { "epoch": 8.24, "learning_rate": 8.796741269623324e-06, "loss": 1.2773, "step": 180550 }, { "epoch": 8.24, "learning_rate": 8.79445283537004e-06, "loss": 1.2225, "step": 180560 }, { "epoch": 8.25, "learning_rate": 8.792164401116757e-06, "loss": 1.296, "step": 180570 }, { "epoch": 8.25, "learning_rate": 8.789875966863473e-06, "loss": 1.4207, "step": 180580 }, { "epoch": 8.25, "learning_rate": 8.787587532610189e-06, "loss": 1.3534, "step": 180590 }, { "epoch": 8.25, "learning_rate": 8.785299098356904e-06, "loss": 1.3158, "step": 180600 }, { "epoch": 8.25, "learning_rate": 8.78301066410362e-06, "loss": 1.4042, "step": 180610 }, { "epoch": 8.25, "learning_rate": 8.780722229850338e-06, "loss": 1.2146, "step": 180620 }, { "epoch": 8.25, "learning_rate": 8.778433795597054e-06, "loss": 1.4011, "step": 180630 }, { "epoch": 8.25, "learning_rate": 8.77614536134377e-06, "loss": 1.3874, "step": 180640 }, { "epoch": 8.25, "learning_rate": 8.773856927090485e-06, "loss": 1.4004, "step": 180650 }, { "epoch": 8.25, "learning_rate": 8.771568492837201e-06, "loss": 1.3779, "step": 180660 }, { "epoch": 8.25, "learning_rate": 8.769280058583917e-06, "loss": 1.2741, "step": 180670 }, { "epoch": 8.25, "learning_rate": 8.766991624330634e-06, "loss": 1.4021, "step": 180680 }, { "epoch": 8.25, "learning_rate": 8.76470319007735e-06, "loss": 1.4409, "step": 180690 }, { "epoch": 8.25, "learning_rate": 8.762414755824064e-06, "loss": 1.349, "step": 180700 }, { "epoch": 8.25, "learning_rate": 8.760126321570782e-06, "loss": 1.239, "step": 180710 }, { "epoch": 8.25, "learning_rate": 8.757837887317498e-06, "loss": 1.3872, "step": 180720 }, { "epoch": 8.25, "learning_rate": 8.755549453064214e-06, "loss": 1.203, "step": 180730 }, { "epoch": 8.25, "learning_rate": 8.75326101881093e-06, "loss": 1.3787, "step": 180740 }, { "epoch": 8.25, "learning_rate": 8.750972584557645e-06, "loss": 1.3605, "step": 180750 }, { "epoch": 8.25, "learning_rate": 8.748684150304363e-06, "loss": 1.4491, "step": 180760 }, { "epoch": 8.25, "learning_rate": 8.746395716051079e-06, "loss": 1.4086, "step": 180770 }, { "epoch": 8.25, "learning_rate": 8.744107281797794e-06, "loss": 1.3039, "step": 180780 }, { "epoch": 8.26, "learning_rate": 8.74181884754451e-06, "loss": 1.2376, "step": 180790 }, { "epoch": 8.26, "learning_rate": 8.739530413291226e-06, "loss": 1.1444, "step": 180800 }, { "epoch": 8.26, "learning_rate": 8.737241979037942e-06, "loss": 1.3947, "step": 180810 }, { "epoch": 8.26, "learning_rate": 8.73495354478466e-06, "loss": 1.3653, "step": 180820 }, { "epoch": 8.26, "learning_rate": 8.732665110531375e-06, "loss": 1.4653, "step": 180830 }, { "epoch": 8.26, "learning_rate": 8.730376676278091e-06, "loss": 1.2875, "step": 180840 }, { "epoch": 8.26, "learning_rate": 8.728088242024807e-06, "loss": 1.3683, "step": 180850 }, { "epoch": 8.26, "learning_rate": 8.725799807771523e-06, "loss": 1.2959, "step": 180860 }, { "epoch": 8.26, "learning_rate": 8.72351137351824e-06, "loss": 1.4007, "step": 180870 }, { "epoch": 8.26, "learning_rate": 8.721222939264956e-06, "loss": 1.2896, "step": 180880 }, { "epoch": 8.26, "learning_rate": 8.71893450501167e-06, "loss": 1.4236, "step": 180890 }, { "epoch": 8.26, "learning_rate": 8.716646070758388e-06, "loss": 1.3437, "step": 180900 }, { "epoch": 8.26, "learning_rate": 8.714357636505104e-06, "loss": 1.2703, "step": 180910 }, { "epoch": 8.26, "learning_rate": 8.71206920225182e-06, "loss": 1.5093, "step": 180920 }, { "epoch": 8.26, "learning_rate": 8.709780767998537e-06, "loss": 1.3852, "step": 180930 }, { "epoch": 8.26, "learning_rate": 8.707492333745251e-06, "loss": 1.2056, "step": 180940 }, { "epoch": 8.26, "learning_rate": 8.705203899491967e-06, "loss": 1.4029, "step": 180950 }, { "epoch": 8.26, "learning_rate": 8.702915465238684e-06, "loss": 1.2969, "step": 180960 }, { "epoch": 8.26, "learning_rate": 8.7006270309854e-06, "loss": 1.4397, "step": 180970 }, { "epoch": 8.26, "learning_rate": 8.698338596732116e-06, "loss": 1.4878, "step": 180980 }, { "epoch": 8.26, "learning_rate": 8.696050162478832e-06, "loss": 1.529, "step": 180990 }, { "epoch": 8.26, "learning_rate": 8.693761728225548e-06, "loss": 1.2213, "step": 181000 }, { "epoch": 8.27, "learning_rate": 8.691473293972265e-06, "loss": 1.3267, "step": 181010 }, { "epoch": 8.27, "learning_rate": 8.689184859718981e-06, "loss": 1.463, "step": 181020 }, { "epoch": 8.27, "learning_rate": 8.686896425465697e-06, "loss": 1.4431, "step": 181030 }, { "epoch": 8.27, "learning_rate": 8.684607991212413e-06, "loss": 1.2402, "step": 181040 }, { "epoch": 8.27, "learning_rate": 8.682319556959129e-06, "loss": 1.3641, "step": 181050 }, { "epoch": 8.27, "learning_rate": 8.680031122705844e-06, "loss": 1.2909, "step": 181060 }, { "epoch": 8.27, "learning_rate": 8.677742688452562e-06, "loss": 1.2311, "step": 181070 }, { "epoch": 8.27, "learning_rate": 8.675454254199278e-06, "loss": 1.307, "step": 181080 }, { "epoch": 8.27, "learning_rate": 8.673165819945994e-06, "loss": 1.3576, "step": 181090 }, { "epoch": 8.27, "learning_rate": 8.67087738569271e-06, "loss": 1.365, "step": 181100 }, { "epoch": 8.27, "learning_rate": 8.668588951439425e-06, "loss": 1.3277, "step": 181110 }, { "epoch": 8.27, "learning_rate": 8.666300517186143e-06, "loss": 1.3049, "step": 181120 }, { "epoch": 8.27, "learning_rate": 8.664012082932859e-06, "loss": 1.3037, "step": 181130 }, { "epoch": 8.27, "learning_rate": 8.661723648679573e-06, "loss": 1.2173, "step": 181140 }, { "epoch": 8.27, "learning_rate": 8.65943521442629e-06, "loss": 1.3929, "step": 181150 }, { "epoch": 8.27, "learning_rate": 8.657146780173006e-06, "loss": 1.3536, "step": 181160 }, { "epoch": 8.27, "learning_rate": 8.654858345919722e-06, "loss": 1.3144, "step": 181170 }, { "epoch": 8.27, "learning_rate": 8.65256991166644e-06, "loss": 1.4367, "step": 181180 }, { "epoch": 8.27, "learning_rate": 8.650281477413153e-06, "loss": 1.2997, "step": 181190 }, { "epoch": 8.27, "learning_rate": 8.647993043159871e-06, "loss": 1.4219, "step": 181200 }, { "epoch": 8.27, "learning_rate": 8.645704608906587e-06, "loss": 1.4235, "step": 181210 }, { "epoch": 8.27, "learning_rate": 8.643416174653303e-06, "loss": 1.3601, "step": 181220 }, { "epoch": 8.28, "learning_rate": 8.641127740400018e-06, "loss": 1.3645, "step": 181230 }, { "epoch": 8.28, "learning_rate": 8.638839306146734e-06, "loss": 1.3247, "step": 181240 }, { "epoch": 8.28, "learning_rate": 8.63655087189345e-06, "loss": 1.3119, "step": 181250 }, { "epoch": 8.28, "learning_rate": 8.634262437640168e-06, "loss": 1.2739, "step": 181260 }, { "epoch": 8.28, "learning_rate": 8.631974003386884e-06, "loss": 1.2861, "step": 181270 }, { "epoch": 8.28, "learning_rate": 8.6296855691336e-06, "loss": 1.4249, "step": 181280 }, { "epoch": 8.28, "learning_rate": 8.627397134880315e-06, "loss": 1.3471, "step": 181290 }, { "epoch": 8.28, "learning_rate": 8.625108700627031e-06, "loss": 1.2959, "step": 181300 }, { "epoch": 8.28, "learning_rate": 8.622820266373747e-06, "loss": 1.3241, "step": 181310 }, { "epoch": 8.28, "learning_rate": 8.620531832120464e-06, "loss": 1.303, "step": 181320 }, { "epoch": 8.28, "learning_rate": 8.61824339786718e-06, "loss": 1.4808, "step": 181330 }, { "epoch": 8.28, "learning_rate": 8.615954963613896e-06, "loss": 1.3043, "step": 181340 }, { "epoch": 8.28, "learning_rate": 8.613666529360612e-06, "loss": 1.3367, "step": 181350 }, { "epoch": 8.28, "learning_rate": 8.611378095107328e-06, "loss": 1.3994, "step": 181360 }, { "epoch": 8.28, "learning_rate": 8.609089660854045e-06, "loss": 1.3336, "step": 181370 }, { "epoch": 8.28, "learning_rate": 8.606801226600761e-06, "loss": 1.5044, "step": 181380 }, { "epoch": 8.28, "learning_rate": 8.604512792347475e-06, "loss": 1.3651, "step": 181390 }, { "epoch": 8.28, "learning_rate": 8.602224358094193e-06, "loss": 1.416, "step": 181400 }, { "epoch": 8.28, "learning_rate": 8.599935923840908e-06, "loss": 1.4314, "step": 181410 }, { "epoch": 8.28, "learning_rate": 8.597647489587624e-06, "loss": 1.3632, "step": 181420 }, { "epoch": 8.28, "learning_rate": 8.595359055334342e-06, "loss": 1.4377, "step": 181430 }, { "epoch": 8.29, "learning_rate": 8.593070621081056e-06, "loss": 1.4141, "step": 181440 }, { "epoch": 8.29, "learning_rate": 8.590782186827773e-06, "loss": 1.3512, "step": 181450 }, { "epoch": 8.29, "learning_rate": 8.58849375257449e-06, "loss": 1.3021, "step": 181460 }, { "epoch": 8.29, "learning_rate": 8.586205318321205e-06, "loss": 1.5489, "step": 181470 }, { "epoch": 8.29, "learning_rate": 8.583916884067923e-06, "loss": 1.2684, "step": 181480 }, { "epoch": 8.29, "learning_rate": 8.581628449814637e-06, "loss": 1.4895, "step": 181490 }, { "epoch": 8.29, "learning_rate": 8.579340015561353e-06, "loss": 1.2974, "step": 181500 }, { "epoch": 8.29, "learning_rate": 8.57705158130807e-06, "loss": 1.238, "step": 181510 }, { "epoch": 8.29, "learning_rate": 8.574763147054786e-06, "loss": 1.2734, "step": 181520 }, { "epoch": 8.29, "learning_rate": 8.5724747128015e-06, "loss": 1.3207, "step": 181530 }, { "epoch": 8.29, "learning_rate": 8.570186278548218e-06, "loss": 1.2655, "step": 181540 }, { "epoch": 8.29, "learning_rate": 8.567897844294933e-06, "loss": 1.3482, "step": 181550 }, { "epoch": 8.29, "learning_rate": 8.56560941004165e-06, "loss": 1.3013, "step": 181560 }, { "epoch": 8.29, "learning_rate": 8.563320975788367e-06, "loss": 1.2299, "step": 181570 }, { "epoch": 8.29, "learning_rate": 8.561032541535081e-06, "loss": 1.3594, "step": 181580 }, { "epoch": 8.29, "learning_rate": 8.558744107281798e-06, "loss": 1.2259, "step": 181590 }, { "epoch": 8.29, "learning_rate": 8.556455673028514e-06, "loss": 1.3401, "step": 181600 }, { "epoch": 8.29, "learning_rate": 8.55416723877523e-06, "loss": 1.217, "step": 181610 }, { "epoch": 8.29, "learning_rate": 8.551878804521948e-06, "loss": 1.2367, "step": 181620 }, { "epoch": 8.29, "learning_rate": 8.549590370268662e-06, "loss": 1.2618, "step": 181630 }, { "epoch": 8.29, "learning_rate": 8.547301936015378e-06, "loss": 1.3443, "step": 181640 }, { "epoch": 8.29, "learning_rate": 8.545013501762095e-06, "loss": 1.2881, "step": 181650 }, { "epoch": 8.3, "learning_rate": 8.542725067508811e-06, "loss": 1.4899, "step": 181660 }, { "epoch": 8.3, "learning_rate": 8.540436633255527e-06, "loss": 1.3947, "step": 181670 }, { "epoch": 8.3, "learning_rate": 8.538148199002243e-06, "loss": 1.3102, "step": 181680 }, { "epoch": 8.3, "learning_rate": 8.535859764748958e-06, "loss": 1.4541, "step": 181690 }, { "epoch": 8.3, "learning_rate": 8.533571330495676e-06, "loss": 1.3272, "step": 181700 }, { "epoch": 8.3, "learning_rate": 8.531282896242392e-06, "loss": 1.6059, "step": 181710 }, { "epoch": 8.3, "learning_rate": 8.528994461989108e-06, "loss": 1.2318, "step": 181720 }, { "epoch": 8.3, "learning_rate": 8.526706027735823e-06, "loss": 1.2803, "step": 181730 }, { "epoch": 8.3, "learning_rate": 8.52441759348254e-06, "loss": 1.3929, "step": 181740 }, { "epoch": 8.3, "learning_rate": 8.522129159229255e-06, "loss": 1.359, "step": 181750 }, { "epoch": 8.3, "learning_rate": 8.519840724975973e-06, "loss": 1.3632, "step": 181760 }, { "epoch": 8.3, "learning_rate": 8.517552290722688e-06, "loss": 1.3136, "step": 181770 }, { "epoch": 8.3, "learning_rate": 8.515263856469404e-06, "loss": 1.3157, "step": 181780 }, { "epoch": 8.3, "learning_rate": 8.51297542221612e-06, "loss": 1.3048, "step": 181790 }, { "epoch": 8.3, "learning_rate": 8.510686987962836e-06, "loss": 1.36, "step": 181800 }, { "epoch": 8.3, "learning_rate": 8.508398553709552e-06, "loss": 1.3447, "step": 181810 }, { "epoch": 8.3, "learning_rate": 8.50611011945627e-06, "loss": 1.3323, "step": 181820 }, { "epoch": 8.3, "learning_rate": 8.503821685202983e-06, "loss": 1.3831, "step": 181830 }, { "epoch": 8.3, "learning_rate": 8.501533250949701e-06, "loss": 1.2463, "step": 181840 }, { "epoch": 8.3, "learning_rate": 8.499244816696417e-06, "loss": 1.2594, "step": 181850 }, { "epoch": 8.3, "learning_rate": 8.496956382443133e-06, "loss": 1.4284, "step": 181860 }, { "epoch": 8.3, "learning_rate": 8.49466794818985e-06, "loss": 1.4013, "step": 181870 }, { "epoch": 8.31, "learning_rate": 8.492379513936564e-06, "loss": 1.422, "step": 181880 }, { "epoch": 8.31, "learning_rate": 8.49009107968328e-06, "loss": 1.3439, "step": 181890 }, { "epoch": 8.31, "learning_rate": 8.487802645429998e-06, "loss": 1.3787, "step": 181900 }, { "epoch": 8.31, "learning_rate": 8.485514211176713e-06, "loss": 1.4156, "step": 181910 }, { "epoch": 8.31, "learning_rate": 8.48322577692343e-06, "loss": 1.4663, "step": 181920 }, { "epoch": 8.31, "learning_rate": 8.480937342670145e-06, "loss": 1.2846, "step": 181930 }, { "epoch": 8.31, "learning_rate": 8.478648908416861e-06, "loss": 1.3514, "step": 181940 }, { "epoch": 8.31, "learning_rate": 8.476360474163578e-06, "loss": 1.339, "step": 181950 }, { "epoch": 8.31, "learning_rate": 8.474072039910294e-06, "loss": 1.4425, "step": 181960 }, { "epoch": 8.31, "learning_rate": 8.47178360565701e-06, "loss": 1.3818, "step": 181970 }, { "epoch": 8.31, "learning_rate": 8.469495171403726e-06, "loss": 1.4103, "step": 181980 }, { "epoch": 8.31, "learning_rate": 8.467206737150442e-06, "loss": 1.3994, "step": 181990 }, { "epoch": 8.31, "learning_rate": 8.464918302897158e-06, "loss": 1.4838, "step": 182000 }, { "epoch": 8.31, "learning_rate": 8.462629868643875e-06, "loss": 1.2648, "step": 182010 }, { "epoch": 8.31, "learning_rate": 8.460341434390591e-06, "loss": 1.3471, "step": 182020 }, { "epoch": 8.31, "learning_rate": 8.458053000137307e-06, "loss": 1.4325, "step": 182030 }, { "epoch": 8.31, "learning_rate": 8.455764565884023e-06, "loss": 1.2736, "step": 182040 }, { "epoch": 8.31, "learning_rate": 8.453476131630738e-06, "loss": 1.3847, "step": 182050 }, { "epoch": 8.31, "learning_rate": 8.451187697377456e-06, "loss": 1.4589, "step": 182060 }, { "epoch": 8.31, "learning_rate": 8.448899263124172e-06, "loss": 1.3759, "step": 182070 }, { "epoch": 8.31, "learning_rate": 8.446610828870886e-06, "loss": 1.2942, "step": 182080 }, { "epoch": 8.31, "learning_rate": 8.444322394617603e-06, "loss": 1.4298, "step": 182090 }, { "epoch": 8.32, "learning_rate": 8.44203396036432e-06, "loss": 1.3361, "step": 182100 }, { "epoch": 8.32, "learning_rate": 8.439745526111035e-06, "loss": 1.453, "step": 182110 }, { "epoch": 8.32, "learning_rate": 8.437457091857753e-06, "loss": 1.1925, "step": 182120 }, { "epoch": 8.32, "learning_rate": 8.435168657604467e-06, "loss": 1.5678, "step": 182130 }, { "epoch": 8.32, "learning_rate": 8.432880223351183e-06, "loss": 1.207, "step": 182140 }, { "epoch": 8.32, "learning_rate": 8.4305917890979e-06, "loss": 1.3731, "step": 182150 }, { "epoch": 8.32, "learning_rate": 8.428303354844616e-06, "loss": 1.4069, "step": 182160 }, { "epoch": 8.32, "learning_rate": 8.426014920591332e-06, "loss": 1.3078, "step": 182170 }, { "epoch": 8.32, "learning_rate": 8.423726486338048e-06, "loss": 1.4245, "step": 182180 }, { "epoch": 8.32, "learning_rate": 8.421438052084763e-06, "loss": 1.3452, "step": 182190 }, { "epoch": 8.32, "learning_rate": 8.419149617831481e-06, "loss": 1.5017, "step": 182200 }, { "epoch": 8.32, "learning_rate": 8.416861183578197e-06, "loss": 1.4004, "step": 182210 }, { "epoch": 8.32, "learning_rate": 8.414572749324913e-06, "loss": 1.4187, "step": 182220 }, { "epoch": 8.32, "learning_rate": 8.412284315071628e-06, "loss": 1.2502, "step": 182230 }, { "epoch": 8.32, "learning_rate": 8.409995880818344e-06, "loss": 1.2896, "step": 182240 }, { "epoch": 8.32, "learning_rate": 8.40770744656506e-06, "loss": 1.3728, "step": 182250 }, { "epoch": 8.32, "learning_rate": 8.405419012311778e-06, "loss": 1.4087, "step": 182260 }, { "epoch": 8.32, "learning_rate": 8.403130578058493e-06, "loss": 1.2397, "step": 182270 }, { "epoch": 8.32, "learning_rate": 8.40084214380521e-06, "loss": 1.5189, "step": 182280 }, { "epoch": 8.32, "learning_rate": 8.398553709551925e-06, "loss": 1.1896, "step": 182290 }, { "epoch": 8.32, "learning_rate": 8.396265275298641e-06, "loss": 1.316, "step": 182300 }, { "epoch": 8.32, "learning_rate": 8.393976841045358e-06, "loss": 1.3913, "step": 182310 }, { "epoch": 8.33, "learning_rate": 8.391688406792073e-06, "loss": 1.375, "step": 182320 }, { "epoch": 8.33, "learning_rate": 8.389399972538788e-06, "loss": 1.386, "step": 182330 }, { "epoch": 8.33, "learning_rate": 8.387111538285506e-06, "loss": 1.3416, "step": 182340 }, { "epoch": 8.33, "learning_rate": 8.384823104032222e-06, "loss": 1.1601, "step": 182350 }, { "epoch": 8.33, "learning_rate": 8.382534669778938e-06, "loss": 1.4233, "step": 182360 }, { "epoch": 8.33, "learning_rate": 8.380246235525653e-06, "loss": 1.2871, "step": 182370 }, { "epoch": 8.33, "learning_rate": 8.37795780127237e-06, "loss": 1.3583, "step": 182380 }, { "epoch": 8.33, "learning_rate": 8.375669367019085e-06, "loss": 1.2989, "step": 182390 }, { "epoch": 8.33, "learning_rate": 8.373380932765803e-06, "loss": 1.3457, "step": 182400 }, { "epoch": 8.33, "learning_rate": 8.371092498512518e-06, "loss": 1.4392, "step": 182410 }, { "epoch": 8.33, "learning_rate": 8.368804064259234e-06, "loss": 1.344, "step": 182420 }, { "epoch": 8.33, "learning_rate": 8.36651563000595e-06, "loss": 1.3811, "step": 182430 }, { "epoch": 8.33, "learning_rate": 8.364227195752666e-06, "loss": 1.5706, "step": 182440 }, { "epoch": 8.33, "learning_rate": 8.361938761499383e-06, "loss": 1.3475, "step": 182450 }, { "epoch": 8.33, "learning_rate": 8.3596503272461e-06, "loss": 1.4921, "step": 182460 }, { "epoch": 8.33, "learning_rate": 8.357361892992813e-06, "loss": 1.4329, "step": 182470 }, { "epoch": 8.33, "learning_rate": 8.35507345873953e-06, "loss": 1.2396, "step": 182480 }, { "epoch": 8.33, "learning_rate": 8.352785024486247e-06, "loss": 1.3453, "step": 182490 }, { "epoch": 8.33, "learning_rate": 8.350496590232962e-06, "loss": 1.4389, "step": 182500 }, { "epoch": 8.33, "learning_rate": 8.34820815597968e-06, "loss": 1.4182, "step": 182510 }, { "epoch": 8.33, "learning_rate": 8.345919721726394e-06, "loss": 1.2597, "step": 182520 }, { "epoch": 8.33, "learning_rate": 8.343631287473112e-06, "loss": 1.2267, "step": 182530 }, { "epoch": 8.34, "learning_rate": 8.341342853219827e-06, "loss": 1.3797, "step": 182540 }, { "epoch": 8.34, "learning_rate": 8.339054418966543e-06, "loss": 1.291, "step": 182550 }, { "epoch": 8.34, "learning_rate": 8.33676598471326e-06, "loss": 1.4409, "step": 182560 }, { "epoch": 8.34, "learning_rate": 8.334477550459975e-06, "loss": 1.4238, "step": 182570 }, { "epoch": 8.34, "learning_rate": 8.33218911620669e-06, "loss": 1.486, "step": 182580 }, { "epoch": 8.34, "learning_rate": 8.329900681953408e-06, "loss": 1.4181, "step": 182590 }, { "epoch": 8.34, "learning_rate": 8.327612247700124e-06, "loss": 1.2095, "step": 182600 }, { "epoch": 8.34, "learning_rate": 8.32532381344684e-06, "loss": 1.3759, "step": 182610 }, { "epoch": 8.34, "learning_rate": 8.323035379193556e-06, "loss": 1.3926, "step": 182620 }, { "epoch": 8.34, "learning_rate": 8.320746944940272e-06, "loss": 1.1771, "step": 182630 }, { "epoch": 8.34, "learning_rate": 8.31845851068699e-06, "loss": 1.3769, "step": 182640 }, { "epoch": 8.34, "learning_rate": 8.316170076433705e-06, "loss": 1.3836, "step": 182650 }, { "epoch": 8.34, "learning_rate": 8.31388164218042e-06, "loss": 1.4157, "step": 182660 }, { "epoch": 8.34, "learning_rate": 8.311593207927137e-06, "loss": 1.2864, "step": 182670 }, { "epoch": 8.34, "learning_rate": 8.309304773673852e-06, "loss": 1.3525, "step": 182680 }, { "epoch": 8.34, "learning_rate": 8.307016339420568e-06, "loss": 1.3869, "step": 182690 }, { "epoch": 8.34, "learning_rate": 8.304727905167286e-06, "loss": 1.4382, "step": 182700 }, { "epoch": 8.34, "learning_rate": 8.302439470914002e-06, "loss": 1.4762, "step": 182710 }, { "epoch": 8.34, "learning_rate": 8.300151036660716e-06, "loss": 1.3765, "step": 182720 }, { "epoch": 8.34, "learning_rate": 8.297862602407433e-06, "loss": 1.2339, "step": 182730 }, { "epoch": 8.34, "learning_rate": 8.295574168154149e-06, "loss": 1.5215, "step": 182740 }, { "epoch": 8.34, "learning_rate": 8.293285733900865e-06, "loss": 1.395, "step": 182750 }, { "epoch": 8.35, "learning_rate": 8.290997299647582e-06, "loss": 1.4826, "step": 182760 }, { "epoch": 8.35, "learning_rate": 8.288708865394297e-06, "loss": 1.4306, "step": 182770 }, { "epoch": 8.35, "learning_rate": 8.286420431141014e-06, "loss": 1.3698, "step": 182780 }, { "epoch": 8.35, "learning_rate": 8.28413199688773e-06, "loss": 1.3813, "step": 182790 }, { "epoch": 8.35, "learning_rate": 8.281843562634446e-06, "loss": 1.3129, "step": 182800 }, { "epoch": 8.35, "learning_rate": 8.279555128381163e-06, "loss": 1.3976, "step": 182810 }, { "epoch": 8.35, "learning_rate": 8.277266694127877e-06, "loss": 1.3089, "step": 182820 }, { "epoch": 8.35, "learning_rate": 8.274978259874593e-06, "loss": 1.1439, "step": 182830 }, { "epoch": 8.35, "learning_rate": 8.27268982562131e-06, "loss": 1.3474, "step": 182840 }, { "epoch": 8.35, "learning_rate": 8.270401391368027e-06, "loss": 1.4268, "step": 182850 }, { "epoch": 8.35, "learning_rate": 8.268112957114742e-06, "loss": 1.2753, "step": 182860 }, { "epoch": 8.35, "learning_rate": 8.265824522861458e-06, "loss": 1.4391, "step": 182870 }, { "epoch": 8.35, "learning_rate": 8.263536088608174e-06, "loss": 1.3332, "step": 182880 }, { "epoch": 8.35, "learning_rate": 8.261247654354892e-06, "loss": 1.2797, "step": 182890 }, { "epoch": 8.35, "learning_rate": 8.258959220101607e-06, "loss": 1.3265, "step": 182900 }, { "epoch": 8.35, "learning_rate": 8.256670785848323e-06, "loss": 1.3542, "step": 182910 }, { "epoch": 8.35, "learning_rate": 8.254382351595039e-06, "loss": 1.3998, "step": 182920 }, { "epoch": 8.35, "learning_rate": 8.252093917341755e-06, "loss": 1.312, "step": 182930 }, { "epoch": 8.35, "learning_rate": 8.24980548308847e-06, "loss": 1.4423, "step": 182940 }, { "epoch": 8.35, "learning_rate": 8.247517048835188e-06, "loss": 1.425, "step": 182950 }, { "epoch": 8.35, "learning_rate": 8.245228614581904e-06, "loss": 1.3403, "step": 182960 }, { "epoch": 8.35, "learning_rate": 8.24294018032862e-06, "loss": 1.317, "step": 182970 }, { "epoch": 8.36, "learning_rate": 8.240651746075336e-06, "loss": 1.4102, "step": 182980 }, { "epoch": 8.36, "learning_rate": 8.238363311822052e-06, "loss": 1.3633, "step": 182990 }, { "epoch": 8.36, "learning_rate": 8.236074877568767e-06, "loss": 1.2356, "step": 183000 }, { "epoch": 8.36, "learning_rate": 8.233786443315485e-06, "loss": 1.2717, "step": 183010 }, { "epoch": 8.36, "learning_rate": 8.231498009062199e-06, "loss": 1.1528, "step": 183020 }, { "epoch": 8.36, "learning_rate": 8.229209574808917e-06, "loss": 1.3699, "step": 183030 }, { "epoch": 8.36, "learning_rate": 8.226921140555632e-06, "loss": 1.3978, "step": 183040 }, { "epoch": 8.36, "learning_rate": 8.224632706302348e-06, "loss": 1.3068, "step": 183050 }, { "epoch": 8.36, "learning_rate": 8.222344272049066e-06, "loss": 1.327, "step": 183060 }, { "epoch": 8.36, "learning_rate": 8.22005583779578e-06, "loss": 1.4802, "step": 183070 }, { "epoch": 8.36, "learning_rate": 8.217767403542496e-06, "loss": 1.3714, "step": 183080 }, { "epoch": 8.36, "learning_rate": 8.215478969289213e-06, "loss": 1.5383, "step": 183090 }, { "epoch": 8.36, "learning_rate": 8.213190535035929e-06, "loss": 1.2219, "step": 183100 }, { "epoch": 8.36, "learning_rate": 8.210902100782645e-06, "loss": 1.2805, "step": 183110 }, { "epoch": 8.36, "learning_rate": 8.20861366652936e-06, "loss": 1.2931, "step": 183120 }, { "epoch": 8.36, "learning_rate": 8.206325232276077e-06, "loss": 1.4896, "step": 183130 }, { "epoch": 8.36, "learning_rate": 8.204036798022794e-06, "loss": 1.5033, "step": 183140 }, { "epoch": 8.36, "learning_rate": 8.20174836376951e-06, "loss": 1.3898, "step": 183150 }, { "epoch": 8.36, "learning_rate": 8.199459929516224e-06, "loss": 1.3005, "step": 183160 }, { "epoch": 8.36, "learning_rate": 8.197171495262942e-06, "loss": 1.421, "step": 183170 }, { "epoch": 8.36, "learning_rate": 8.194883061009657e-06, "loss": 1.6757, "step": 183180 }, { "epoch": 8.36, "learning_rate": 8.192594626756373e-06, "loss": 1.4104, "step": 183190 }, { "epoch": 8.37, "learning_rate": 8.19030619250309e-06, "loss": 1.4009, "step": 183200 }, { "epoch": 8.37, "learning_rate": 8.188017758249805e-06, "loss": 1.3416, "step": 183210 }, { "epoch": 8.37, "learning_rate": 8.185729323996522e-06, "loss": 1.2556, "step": 183220 }, { "epoch": 8.37, "learning_rate": 8.183440889743238e-06, "loss": 1.4236, "step": 183230 }, { "epoch": 8.37, "learning_rate": 8.181152455489954e-06, "loss": 1.1786, "step": 183240 }, { "epoch": 8.37, "learning_rate": 8.17886402123667e-06, "loss": 1.3352, "step": 183250 }, { "epoch": 8.37, "learning_rate": 8.176575586983386e-06, "loss": 1.4578, "step": 183260 }, { "epoch": 8.37, "learning_rate": 8.174287152730102e-06, "loss": 1.3477, "step": 183270 }, { "epoch": 8.37, "learning_rate": 8.171998718476819e-06, "loss": 1.2711, "step": 183280 }, { "epoch": 8.37, "learning_rate": 8.169710284223535e-06, "loss": 1.5173, "step": 183290 }, { "epoch": 8.37, "learning_rate": 8.16742184997025e-06, "loss": 1.3638, "step": 183300 }, { "epoch": 8.37, "learning_rate": 8.165133415716967e-06, "loss": 1.3157, "step": 183310 }, { "epoch": 8.37, "learning_rate": 8.162844981463682e-06, "loss": 1.3813, "step": 183320 }, { "epoch": 8.37, "learning_rate": 8.160556547210398e-06, "loss": 1.5127, "step": 183330 }, { "epoch": 8.37, "learning_rate": 8.158268112957116e-06, "loss": 1.2486, "step": 183340 }, { "epoch": 8.37, "learning_rate": 8.155979678703832e-06, "loss": 1.3559, "step": 183350 }, { "epoch": 8.37, "learning_rate": 8.153691244450547e-06, "loss": 1.3676, "step": 183360 }, { "epoch": 8.37, "learning_rate": 8.151402810197263e-06, "loss": 1.3113, "step": 183370 }, { "epoch": 8.37, "learning_rate": 8.149114375943979e-06, "loss": 1.3245, "step": 183380 }, { "epoch": 8.37, "learning_rate": 8.146825941690697e-06, "loss": 1.3512, "step": 183390 }, { "epoch": 8.37, "learning_rate": 8.144537507437412e-06, "loss": 1.1337, "step": 183400 }, { "epoch": 8.37, "learning_rate": 8.142249073184127e-06, "loss": 1.342, "step": 183410 }, { "epoch": 8.38, "learning_rate": 8.139960638930844e-06, "loss": 1.5789, "step": 183420 }, { "epoch": 8.38, "learning_rate": 8.13767220467756e-06, "loss": 1.3827, "step": 183430 }, { "epoch": 8.38, "learning_rate": 8.135383770424276e-06, "loss": 1.3657, "step": 183440 }, { "epoch": 8.38, "learning_rate": 8.133095336170993e-06, "loss": 1.5243, "step": 183450 }, { "epoch": 8.38, "learning_rate": 8.130806901917707e-06, "loss": 1.2827, "step": 183460 }, { "epoch": 8.38, "learning_rate": 8.128518467664425e-06, "loss": 1.345, "step": 183470 }, { "epoch": 8.38, "learning_rate": 8.12623003341114e-06, "loss": 1.3396, "step": 183480 }, { "epoch": 8.38, "learning_rate": 8.123941599157857e-06, "loss": 1.4403, "step": 183490 }, { "epoch": 8.38, "learning_rate": 8.121653164904574e-06, "loss": 1.1908, "step": 183500 }, { "epoch": 8.38, "learning_rate": 8.119364730651288e-06, "loss": 1.4538, "step": 183510 }, { "epoch": 8.38, "learning_rate": 8.117076296398004e-06, "loss": 1.2383, "step": 183520 }, { "epoch": 8.38, "learning_rate": 8.114787862144722e-06, "loss": 1.4029, "step": 183530 }, { "epoch": 8.38, "learning_rate": 8.112499427891437e-06, "loss": 1.2744, "step": 183540 }, { "epoch": 8.38, "learning_rate": 8.110210993638153e-06, "loss": 1.4421, "step": 183550 }, { "epoch": 8.38, "learning_rate": 8.107922559384869e-06, "loss": 1.5049, "step": 183560 }, { "epoch": 8.38, "learning_rate": 8.105634125131585e-06, "loss": 1.2819, "step": 183570 }, { "epoch": 8.38, "learning_rate": 8.1033456908783e-06, "loss": 1.4846, "step": 183580 }, { "epoch": 8.38, "learning_rate": 8.101057256625018e-06, "loss": 1.5007, "step": 183590 }, { "epoch": 8.38, "learning_rate": 8.098768822371734e-06, "loss": 1.4935, "step": 183600 }, { "epoch": 8.38, "learning_rate": 8.09648038811845e-06, "loss": 1.4146, "step": 183610 }, { "epoch": 8.38, "learning_rate": 8.094191953865166e-06, "loss": 1.4263, "step": 183620 }, { "epoch": 8.39, "learning_rate": 8.091903519611881e-06, "loss": 1.2726, "step": 183630 }, { "epoch": 8.39, "learning_rate": 8.089615085358599e-06, "loss": 1.4367, "step": 183640 }, { "epoch": 8.39, "learning_rate": 8.087326651105315e-06, "loss": 1.3641, "step": 183650 }, { "epoch": 8.39, "learning_rate": 8.085038216852029e-06, "loss": 1.414, "step": 183660 }, { "epoch": 8.39, "learning_rate": 8.082749782598747e-06, "loss": 1.3208, "step": 183670 }, { "epoch": 8.39, "learning_rate": 8.080461348345462e-06, "loss": 1.3457, "step": 183680 }, { "epoch": 8.39, "learning_rate": 8.078172914092178e-06, "loss": 1.3995, "step": 183690 }, { "epoch": 8.39, "learning_rate": 8.075884479838896e-06, "loss": 1.2691, "step": 183700 }, { "epoch": 8.39, "learning_rate": 8.07359604558561e-06, "loss": 1.4491, "step": 183710 }, { "epoch": 8.39, "learning_rate": 8.071307611332327e-06, "loss": 1.3974, "step": 183720 }, { "epoch": 8.39, "learning_rate": 8.069019177079043e-06, "loss": 1.4116, "step": 183730 }, { "epoch": 8.39, "learning_rate": 8.066730742825759e-06, "loss": 1.3215, "step": 183740 }, { "epoch": 8.39, "learning_rate": 8.064442308572477e-06, "loss": 1.1768, "step": 183750 }, { "epoch": 8.39, "learning_rate": 8.06215387431919e-06, "loss": 1.425, "step": 183760 }, { "epoch": 8.39, "learning_rate": 8.059865440065906e-06, "loss": 1.3404, "step": 183770 }, { "epoch": 8.39, "learning_rate": 8.057577005812624e-06, "loss": 1.3216, "step": 183780 }, { "epoch": 8.39, "learning_rate": 8.05528857155934e-06, "loss": 1.3866, "step": 183790 }, { "epoch": 8.39, "learning_rate": 8.053000137306056e-06, "loss": 1.3893, "step": 183800 }, { "epoch": 8.39, "learning_rate": 8.050711703052771e-06, "loss": 1.4025, "step": 183810 }, { "epoch": 8.39, "learning_rate": 8.048423268799487e-06, "loss": 1.47, "step": 183820 }, { "epoch": 8.39, "learning_rate": 8.046134834546205e-06, "loss": 1.3936, "step": 183830 }, { "epoch": 8.39, "learning_rate": 8.04384640029292e-06, "loss": 1.3971, "step": 183840 }, { "epoch": 8.4, "learning_rate": 8.041557966039636e-06, "loss": 1.4063, "step": 183850 }, { "epoch": 8.4, "learning_rate": 8.039269531786352e-06, "loss": 1.3832, "step": 183860 }, { "epoch": 8.4, "learning_rate": 8.036981097533068e-06, "loss": 1.4002, "step": 183870 }, { "epoch": 8.4, "learning_rate": 8.034692663279784e-06, "loss": 1.3483, "step": 183880 }, { "epoch": 8.4, "learning_rate": 8.032404229026501e-06, "loss": 1.2498, "step": 183890 }, { "epoch": 8.4, "learning_rate": 8.030115794773217e-06, "loss": 1.4928, "step": 183900 }, { "epoch": 8.4, "learning_rate": 8.027827360519931e-06, "loss": 1.2097, "step": 183910 }, { "epoch": 8.4, "learning_rate": 8.025538926266649e-06, "loss": 1.1754, "step": 183920 }, { "epoch": 8.4, "learning_rate": 8.023250492013365e-06, "loss": 1.3235, "step": 183930 }, { "epoch": 8.4, "learning_rate": 8.02096205776008e-06, "loss": 1.3176, "step": 183940 }, { "epoch": 8.4, "learning_rate": 8.018673623506796e-06, "loss": 1.4285, "step": 183950 }, { "epoch": 8.4, "learning_rate": 8.016385189253512e-06, "loss": 1.4338, "step": 183960 }, { "epoch": 8.4, "learning_rate": 8.01409675500023e-06, "loss": 1.3856, "step": 183970 }, { "epoch": 8.4, "learning_rate": 8.011808320746946e-06, "loss": 1.3355, "step": 183980 }, { "epoch": 8.4, "learning_rate": 8.009519886493661e-06, "loss": 1.279, "step": 183990 }, { "epoch": 8.4, "learning_rate": 8.007231452240377e-06, "loss": 1.3824, "step": 184000 }, { "epoch": 8.4, "learning_rate": 8.004943017987093e-06, "loss": 1.4087, "step": 184010 }, { "epoch": 8.4, "learning_rate": 8.002654583733809e-06, "loss": 1.2488, "step": 184020 }, { "epoch": 8.4, "learning_rate": 8.000366149480526e-06, "loss": 1.3255, "step": 184030 }, { "epoch": 8.4, "learning_rate": 7.998077715227242e-06, "loss": 1.2432, "step": 184040 }, { "epoch": 8.4, "learning_rate": 7.995789280973958e-06, "loss": 1.3539, "step": 184050 }, { "epoch": 8.4, "learning_rate": 7.993500846720674e-06, "loss": 1.3804, "step": 184060 }, { "epoch": 8.41, "learning_rate": 7.99121241246739e-06, "loss": 1.5275, "step": 184070 }, { "epoch": 8.41, "learning_rate": 7.988923978214107e-06, "loss": 1.2453, "step": 184080 }, { "epoch": 8.41, "learning_rate": 7.986635543960823e-06, "loss": 1.2507, "step": 184090 }, { "epoch": 8.41, "learning_rate": 7.984347109707537e-06, "loss": 1.3595, "step": 184100 }, { "epoch": 8.41, "learning_rate": 7.982058675454255e-06, "loss": 1.3433, "step": 184110 }, { "epoch": 8.41, "learning_rate": 7.97977024120097e-06, "loss": 1.1857, "step": 184120 }, { "epoch": 8.41, "learning_rate": 7.977481806947686e-06, "loss": 1.3065, "step": 184130 }, { "epoch": 8.41, "learning_rate": 7.975193372694404e-06, "loss": 1.25, "step": 184140 }, { "epoch": 8.41, "learning_rate": 7.972904938441118e-06, "loss": 1.2345, "step": 184150 }, { "epoch": 8.41, "learning_rate": 7.970616504187834e-06, "loss": 1.1817, "step": 184160 }, { "epoch": 8.41, "learning_rate": 7.968328069934551e-06, "loss": 1.3033, "step": 184170 }, { "epoch": 8.41, "learning_rate": 7.966039635681267e-06, "loss": 1.2534, "step": 184180 }, { "epoch": 8.41, "learning_rate": 7.963751201427983e-06, "loss": 1.3795, "step": 184190 }, { "epoch": 8.41, "learning_rate": 7.961462767174699e-06, "loss": 1.3297, "step": 184200 }, { "epoch": 8.41, "learning_rate": 7.959174332921415e-06, "loss": 1.2174, "step": 184210 }, { "epoch": 8.41, "learning_rate": 7.956885898668132e-06, "loss": 1.4103, "step": 184220 }, { "epoch": 8.41, "learning_rate": 7.954597464414848e-06, "loss": 1.283, "step": 184230 }, { "epoch": 8.41, "learning_rate": 7.952309030161564e-06, "loss": 1.3308, "step": 184240 }, { "epoch": 8.41, "learning_rate": 7.95002059590828e-06, "loss": 1.4995, "step": 184250 }, { "epoch": 8.41, "learning_rate": 7.947732161654996e-06, "loss": 1.1661, "step": 184260 }, { "epoch": 8.41, "learning_rate": 7.945443727401711e-06, "loss": 1.1577, "step": 184270 }, { "epoch": 8.41, "learning_rate": 7.943155293148429e-06, "loss": 1.5177, "step": 184280 }, { "epoch": 8.42, "learning_rate": 7.940866858895145e-06, "loss": 1.4634, "step": 184290 }, { "epoch": 8.42, "learning_rate": 7.93857842464186e-06, "loss": 1.239, "step": 184300 }, { "epoch": 8.42, "learning_rate": 7.936289990388576e-06, "loss": 1.4564, "step": 184310 }, { "epoch": 8.42, "learning_rate": 7.934001556135292e-06, "loss": 1.2109, "step": 184320 }, { "epoch": 8.42, "learning_rate": 7.93171312188201e-06, "loss": 1.3973, "step": 184330 }, { "epoch": 8.42, "learning_rate": 7.929424687628726e-06, "loss": 1.3115, "step": 184340 }, { "epoch": 8.42, "learning_rate": 7.92713625337544e-06, "loss": 1.3522, "step": 184350 }, { "epoch": 8.42, "learning_rate": 7.924847819122157e-06, "loss": 1.5352, "step": 184360 }, { "epoch": 8.42, "learning_rate": 7.922559384868873e-06, "loss": 1.2881, "step": 184370 }, { "epoch": 8.42, "learning_rate": 7.920270950615589e-06, "loss": 1.1969, "step": 184380 }, { "epoch": 8.42, "learning_rate": 7.917982516362306e-06, "loss": 1.4275, "step": 184390 }, { "epoch": 8.42, "learning_rate": 7.91569408210902e-06, "loss": 1.3637, "step": 184400 }, { "epoch": 8.42, "learning_rate": 7.913405647855738e-06, "loss": 1.4293, "step": 184410 }, { "epoch": 8.42, "learning_rate": 7.911117213602454e-06, "loss": 1.3906, "step": 184420 }, { "epoch": 8.42, "learning_rate": 7.90882877934917e-06, "loss": 1.3112, "step": 184430 }, { "epoch": 8.42, "learning_rate": 7.906540345095886e-06, "loss": 1.2578, "step": 184440 }, { "epoch": 8.42, "learning_rate": 7.904251910842601e-06, "loss": 1.2982, "step": 184450 }, { "epoch": 8.42, "learning_rate": 7.901963476589317e-06, "loss": 1.3194, "step": 184460 }, { "epoch": 8.42, "learning_rate": 7.899675042336035e-06, "loss": 1.4453, "step": 184470 }, { "epoch": 8.42, "learning_rate": 7.89738660808275e-06, "loss": 1.1778, "step": 184480 }, { "epoch": 8.42, "learning_rate": 7.895098173829466e-06, "loss": 1.3561, "step": 184490 }, { "epoch": 8.42, "learning_rate": 7.892809739576182e-06, "loss": 1.2962, "step": 184500 }, { "epoch": 8.43, "learning_rate": 7.890521305322898e-06, "loss": 1.3631, "step": 184510 }, { "epoch": 8.43, "learning_rate": 7.888232871069614e-06, "loss": 1.4013, "step": 184520 }, { "epoch": 8.43, "learning_rate": 7.885944436816331e-06, "loss": 1.3026, "step": 184530 }, { "epoch": 8.43, "learning_rate": 7.883656002563047e-06, "loss": 1.3602, "step": 184540 }, { "epoch": 8.43, "learning_rate": 7.881367568309763e-06, "loss": 1.296, "step": 184550 }, { "epoch": 8.43, "learning_rate": 7.879079134056479e-06, "loss": 1.2318, "step": 184560 }, { "epoch": 8.43, "learning_rate": 7.876790699803195e-06, "loss": 1.2663, "step": 184570 }, { "epoch": 8.43, "learning_rate": 7.874502265549912e-06, "loss": 1.4067, "step": 184580 }, { "epoch": 8.43, "learning_rate": 7.872213831296628e-06, "loss": 1.3636, "step": 184590 }, { "epoch": 8.43, "learning_rate": 7.869925397043342e-06, "loss": 1.308, "step": 184600 }, { "epoch": 8.43, "learning_rate": 7.86763696279006e-06, "loss": 1.476, "step": 184610 }, { "epoch": 8.43, "learning_rate": 7.865348528536776e-06, "loss": 1.3896, "step": 184620 }, { "epoch": 8.43, "learning_rate": 7.863060094283491e-06, "loss": 1.2875, "step": 184630 }, { "epoch": 8.43, "learning_rate": 7.860771660030209e-06, "loss": 1.4263, "step": 184640 }, { "epoch": 8.43, "learning_rate": 7.858483225776923e-06, "loss": 1.3502, "step": 184650 }, { "epoch": 8.43, "learning_rate": 7.85619479152364e-06, "loss": 1.2098, "step": 184660 }, { "epoch": 8.43, "learning_rate": 7.853906357270356e-06, "loss": 1.3556, "step": 184670 }, { "epoch": 8.43, "learning_rate": 7.851617923017072e-06, "loss": 1.3942, "step": 184680 }, { "epoch": 8.43, "learning_rate": 7.84932948876379e-06, "loss": 1.3421, "step": 184690 }, { "epoch": 8.43, "learning_rate": 7.847041054510504e-06, "loss": 1.5034, "step": 184700 }, { "epoch": 8.43, "learning_rate": 7.84475262025722e-06, "loss": 1.4187, "step": 184710 }, { "epoch": 8.43, "learning_rate": 7.842464186003937e-06, "loss": 1.4025, "step": 184720 }, { "epoch": 8.44, "learning_rate": 7.840175751750653e-06, "loss": 1.305, "step": 184730 }, { "epoch": 8.44, "learning_rate": 7.837887317497367e-06, "loss": 1.3384, "step": 184740 }, { "epoch": 8.44, "learning_rate": 7.835598883244085e-06, "loss": 1.6405, "step": 184750 }, { "epoch": 8.44, "learning_rate": 7.8333104489908e-06, "loss": 1.4115, "step": 184760 }, { "epoch": 8.44, "learning_rate": 7.831022014737516e-06, "loss": 1.2158, "step": 184770 }, { "epoch": 8.44, "learning_rate": 7.828733580484234e-06, "loss": 1.2468, "step": 184780 }, { "epoch": 8.44, "learning_rate": 7.826445146230948e-06, "loss": 1.4329, "step": 184790 }, { "epoch": 8.44, "learning_rate": 7.824156711977666e-06, "loss": 1.306, "step": 184800 }, { "epoch": 8.44, "learning_rate": 7.821868277724381e-06, "loss": 1.3722, "step": 184810 }, { "epoch": 8.44, "learning_rate": 7.819579843471097e-06, "loss": 1.3456, "step": 184820 }, { "epoch": 8.44, "learning_rate": 7.817291409217815e-06, "loss": 1.3475, "step": 184830 }, { "epoch": 8.44, "learning_rate": 7.815002974964529e-06, "loss": 1.4247, "step": 184840 }, { "epoch": 8.44, "learning_rate": 7.812714540711245e-06, "loss": 1.3298, "step": 184850 }, { "epoch": 8.44, "learning_rate": 7.810426106457962e-06, "loss": 1.4159, "step": 184860 }, { "epoch": 8.44, "learning_rate": 7.808137672204678e-06, "loss": 1.3647, "step": 184870 }, { "epoch": 8.44, "learning_rate": 7.805849237951394e-06, "loss": 1.3903, "step": 184880 }, { "epoch": 8.44, "learning_rate": 7.80356080369811e-06, "loss": 1.4755, "step": 184890 }, { "epoch": 8.44, "learning_rate": 7.801272369444825e-06, "loss": 1.216, "step": 184900 }, { "epoch": 8.44, "learning_rate": 7.798983935191543e-06, "loss": 1.2946, "step": 184910 }, { "epoch": 8.44, "learning_rate": 7.796695500938259e-06, "loss": 1.3177, "step": 184920 }, { "epoch": 8.44, "learning_rate": 7.794407066684975e-06, "loss": 1.4376, "step": 184930 }, { "epoch": 8.44, "learning_rate": 7.79211863243169e-06, "loss": 1.2385, "step": 184940 }, { "epoch": 8.45, "learning_rate": 7.789830198178406e-06, "loss": 1.3948, "step": 184950 }, { "epoch": 8.45, "learning_rate": 7.787541763925122e-06, "loss": 1.3154, "step": 184960 }, { "epoch": 8.45, "learning_rate": 7.78525332967184e-06, "loss": 1.2838, "step": 184970 }, { "epoch": 8.45, "learning_rate": 7.782964895418555e-06, "loss": 1.4155, "step": 184980 }, { "epoch": 8.45, "learning_rate": 7.780676461165271e-06, "loss": 1.3574, "step": 184990 }, { "epoch": 8.45, "learning_rate": 7.778388026911987e-06, "loss": 1.3631, "step": 185000 }, { "epoch": 8.45, "learning_rate": 7.776099592658703e-06, "loss": 1.4584, "step": 185010 }, { "epoch": 8.45, "learning_rate": 7.773811158405419e-06, "loss": 1.31, "step": 185020 }, { "epoch": 8.45, "learning_rate": 7.771522724152136e-06, "loss": 1.2745, "step": 185030 }, { "epoch": 8.45, "learning_rate": 7.76923428989885e-06, "loss": 1.5536, "step": 185040 }, { "epoch": 8.45, "learning_rate": 7.766945855645568e-06, "loss": 1.4685, "step": 185050 }, { "epoch": 8.45, "learning_rate": 7.764657421392284e-06, "loss": 1.3219, "step": 185060 }, { "epoch": 8.45, "learning_rate": 7.762368987139e-06, "loss": 1.3458, "step": 185070 }, { "epoch": 8.45, "learning_rate": 7.760080552885717e-06, "loss": 1.3297, "step": 185080 }, { "epoch": 8.45, "learning_rate": 7.757792118632431e-06, "loss": 1.383, "step": 185090 }, { "epoch": 8.45, "learning_rate": 7.755503684379147e-06, "loss": 1.3085, "step": 185100 }, { "epoch": 8.45, "learning_rate": 7.753215250125865e-06, "loss": 1.3478, "step": 185110 }, { "epoch": 8.45, "learning_rate": 7.75092681587258e-06, "loss": 1.3757, "step": 185120 }, { "epoch": 8.45, "learning_rate": 7.748638381619296e-06, "loss": 1.3832, "step": 185130 }, { "epoch": 8.45, "learning_rate": 7.746349947366012e-06, "loss": 1.3449, "step": 185140 }, { "epoch": 8.45, "learning_rate": 7.744061513112728e-06, "loss": 1.2398, "step": 185150 }, { "epoch": 8.45, "learning_rate": 7.741773078859445e-06, "loss": 1.3018, "step": 185160 }, { "epoch": 8.46, "learning_rate": 7.739484644606161e-06, "loss": 1.2767, "step": 185170 }, { "epoch": 8.46, "learning_rate": 7.737196210352877e-06, "loss": 1.4406, "step": 185180 }, { "epoch": 8.46, "learning_rate": 7.734907776099593e-06, "loss": 1.2685, "step": 185190 }, { "epoch": 8.46, "learning_rate": 7.732619341846309e-06, "loss": 1.279, "step": 185200 }, { "epoch": 8.46, "learning_rate": 7.730330907593025e-06, "loss": 1.151, "step": 185210 }, { "epoch": 8.46, "learning_rate": 7.728042473339742e-06, "loss": 1.2423, "step": 185220 }, { "epoch": 8.46, "learning_rate": 7.725754039086458e-06, "loss": 1.4177, "step": 185230 }, { "epoch": 8.46, "learning_rate": 7.723465604833174e-06, "loss": 1.3284, "step": 185240 }, { "epoch": 8.46, "learning_rate": 7.72117717057989e-06, "loss": 1.5168, "step": 185250 }, { "epoch": 8.46, "learning_rate": 7.718888736326605e-06, "loss": 1.3525, "step": 185260 }, { "epoch": 8.46, "learning_rate": 7.716600302073323e-06, "loss": 1.3687, "step": 185270 }, { "epoch": 8.46, "learning_rate": 7.714311867820039e-06, "loss": 1.3901, "step": 185280 }, { "epoch": 8.46, "learning_rate": 7.712023433566753e-06, "loss": 1.383, "step": 185290 }, { "epoch": 8.46, "learning_rate": 7.70973499931347e-06, "loss": 1.4455, "step": 185300 }, { "epoch": 8.46, "learning_rate": 7.707446565060186e-06, "loss": 1.3349, "step": 185310 }, { "epoch": 8.46, "learning_rate": 7.705158130806902e-06, "loss": 1.3601, "step": 185320 }, { "epoch": 8.46, "learning_rate": 7.70286969655362e-06, "loss": 1.3559, "step": 185330 }, { "epoch": 8.46, "learning_rate": 7.700581262300334e-06, "loss": 1.332, "step": 185340 }, { "epoch": 8.46, "learning_rate": 7.69829282804705e-06, "loss": 1.3586, "step": 185350 }, { "epoch": 8.46, "learning_rate": 7.696004393793767e-06, "loss": 1.3694, "step": 185360 }, { "epoch": 8.46, "learning_rate": 7.693715959540483e-06, "loss": 1.3233, "step": 185370 }, { "epoch": 8.46, "learning_rate": 7.691427525287199e-06, "loss": 1.4071, "step": 185380 }, { "epoch": 8.47, "learning_rate": 7.689139091033915e-06, "loss": 1.3233, "step": 185390 }, { "epoch": 8.47, "learning_rate": 7.68685065678063e-06, "loss": 1.5055, "step": 185400 }, { "epoch": 8.47, "learning_rate": 7.684562222527348e-06, "loss": 1.3181, "step": 185410 }, { "epoch": 8.47, "learning_rate": 7.682273788274064e-06, "loss": 1.5032, "step": 185420 }, { "epoch": 8.47, "learning_rate": 7.67998535402078e-06, "loss": 1.5088, "step": 185430 }, { "epoch": 8.47, "learning_rate": 7.677696919767495e-06, "loss": 1.3418, "step": 185440 }, { "epoch": 8.47, "learning_rate": 7.675408485514211e-06, "loss": 1.2381, "step": 185450 }, { "epoch": 8.47, "learning_rate": 7.673120051260927e-06, "loss": 1.3582, "step": 185460 }, { "epoch": 8.47, "learning_rate": 7.670831617007645e-06, "loss": 1.3857, "step": 185470 }, { "epoch": 8.47, "learning_rate": 7.66854318275436e-06, "loss": 1.2516, "step": 185480 }, { "epoch": 8.47, "learning_rate": 7.666254748501076e-06, "loss": 1.4145, "step": 185490 }, { "epoch": 8.47, "learning_rate": 7.663966314247792e-06, "loss": 1.3061, "step": 185500 }, { "epoch": 8.47, "learning_rate": 7.661677879994508e-06, "loss": 1.3949, "step": 185510 }, { "epoch": 8.47, "learning_rate": 7.659389445741225e-06, "loss": 1.277, "step": 185520 }, { "epoch": 8.47, "learning_rate": 7.657101011487941e-06, "loss": 1.2478, "step": 185530 }, { "epoch": 8.47, "learning_rate": 7.654812577234655e-06, "loss": 1.4984, "step": 185540 }, { "epoch": 8.47, "learning_rate": 7.652524142981373e-06, "loss": 1.3243, "step": 185550 }, { "epoch": 8.47, "learning_rate": 7.650235708728089e-06, "loss": 1.4121, "step": 185560 }, { "epoch": 8.47, "learning_rate": 7.647947274474805e-06, "loss": 1.3846, "step": 185570 }, { "epoch": 8.47, "learning_rate": 7.64565884022152e-06, "loss": 1.3908, "step": 185580 }, { "epoch": 8.47, "learning_rate": 7.643370405968236e-06, "loss": 1.4316, "step": 185590 }, { "epoch": 8.47, "learning_rate": 7.641081971714952e-06, "loss": 1.2946, "step": 185600 }, { "epoch": 8.48, "learning_rate": 7.63879353746167e-06, "loss": 1.4188, "step": 185610 }, { "epoch": 8.48, "learning_rate": 7.636505103208385e-06, "loss": 1.375, "step": 185620 }, { "epoch": 8.48, "learning_rate": 7.634216668955101e-06, "loss": 1.4251, "step": 185630 }, { "epoch": 8.48, "learning_rate": 7.631928234701817e-06, "loss": 1.5047, "step": 185640 }, { "epoch": 8.48, "learning_rate": 7.629639800448533e-06, "loss": 1.353, "step": 185650 }, { "epoch": 8.48, "learning_rate": 7.6273513661952496e-06, "loss": 1.3409, "step": 185660 }, { "epoch": 8.48, "learning_rate": 7.625062931941966e-06, "loss": 1.3611, "step": 185670 }, { "epoch": 8.48, "learning_rate": 7.622774497688681e-06, "loss": 1.3535, "step": 185680 }, { "epoch": 8.48, "learning_rate": 7.620486063435398e-06, "loss": 1.4825, "step": 185690 }, { "epoch": 8.48, "learning_rate": 7.618197629182114e-06, "loss": 1.2492, "step": 185700 }, { "epoch": 8.48, "learning_rate": 7.61590919492883e-06, "loss": 1.5099, "step": 185710 }, { "epoch": 8.48, "learning_rate": 7.613620760675546e-06, "loss": 1.3603, "step": 185720 }, { "epoch": 8.48, "learning_rate": 7.611332326422262e-06, "loss": 1.3268, "step": 185730 }, { "epoch": 8.48, "learning_rate": 7.609043892168978e-06, "loss": 1.3868, "step": 185740 }, { "epoch": 8.48, "learning_rate": 7.6067554579156945e-06, "loss": 1.2226, "step": 185750 }, { "epoch": 8.48, "learning_rate": 7.60446702366241e-06, "loss": 1.3531, "step": 185760 }, { "epoch": 8.48, "learning_rate": 7.602178589409127e-06, "loss": 1.5203, "step": 185770 }, { "epoch": 8.48, "learning_rate": 7.599890155155842e-06, "loss": 1.319, "step": 185780 }, { "epoch": 8.48, "learning_rate": 7.597601720902559e-06, "loss": 1.3693, "step": 185790 }, { "epoch": 8.48, "learning_rate": 7.5953132866492745e-06, "loss": 1.3278, "step": 185800 }, { "epoch": 8.48, "learning_rate": 7.593024852395991e-06, "loss": 1.3502, "step": 185810 }, { "epoch": 8.49, "learning_rate": 7.590736418142708e-06, "loss": 1.4686, "step": 185820 }, { "epoch": 8.49, "learning_rate": 7.588447983889423e-06, "loss": 1.4484, "step": 185830 }, { "epoch": 8.49, "learning_rate": 7.586159549636139e-06, "loss": 1.4491, "step": 185840 }, { "epoch": 8.49, "learning_rate": 7.583871115382855e-06, "loss": 1.3713, "step": 185850 }, { "epoch": 8.49, "learning_rate": 7.581582681129572e-06, "loss": 1.346, "step": 185860 }, { "epoch": 8.49, "learning_rate": 7.579294246876288e-06, "loss": 1.2747, "step": 185870 }, { "epoch": 8.49, "learning_rate": 7.577005812623003e-06, "loss": 1.4366, "step": 185880 }, { "epoch": 8.49, "learning_rate": 7.5747173783697195e-06, "loss": 1.2972, "step": 185890 }, { "epoch": 8.49, "learning_rate": 7.572428944116436e-06, "loss": 1.3733, "step": 185900 }, { "epoch": 8.49, "learning_rate": 7.570140509863152e-06, "loss": 1.3374, "step": 185910 }, { "epoch": 8.49, "learning_rate": 7.567852075609869e-06, "loss": 1.358, "step": 185920 }, { "epoch": 8.49, "learning_rate": 7.565563641356584e-06, "loss": 1.2991, "step": 185930 }, { "epoch": 8.49, "learning_rate": 7.5632752071033e-06, "loss": 1.4465, "step": 185940 }, { "epoch": 8.49, "learning_rate": 7.560986772850016e-06, "loss": 1.3831, "step": 185950 }, { "epoch": 8.49, "learning_rate": 7.558698338596733e-06, "loss": 1.3662, "step": 185960 }, { "epoch": 8.49, "learning_rate": 7.5564099043434495e-06, "loss": 1.3351, "step": 185970 }, { "epoch": 8.49, "learning_rate": 7.5541214700901645e-06, "loss": 1.2846, "step": 185980 }, { "epoch": 8.49, "learning_rate": 7.55183303583688e-06, "loss": 1.2523, "step": 185990 }, { "epoch": 8.49, "learning_rate": 7.549544601583597e-06, "loss": 1.4294, "step": 186000 }, { "epoch": 8.49, "learning_rate": 7.547256167330313e-06, "loss": 1.3395, "step": 186010 }, { "epoch": 8.49, "learning_rate": 7.5449677330770295e-06, "loss": 1.3735, "step": 186020 }, { "epoch": 8.49, "learning_rate": 7.5426792988237445e-06, "loss": 1.2092, "step": 186030 }, { "epoch": 8.5, "learning_rate": 7.540390864570461e-06, "loss": 1.2614, "step": 186040 }, { "epoch": 8.5, "learning_rate": 7.538102430317177e-06, "loss": 1.3452, "step": 186050 }, { "epoch": 8.5, "learning_rate": 7.535813996063894e-06, "loss": 1.4219, "step": 186060 }, { "epoch": 8.5, "learning_rate": 7.53352556181061e-06, "loss": 1.3675, "step": 186070 }, { "epoch": 8.5, "learning_rate": 7.531237127557325e-06, "loss": 1.2942, "step": 186080 }, { "epoch": 8.5, "learning_rate": 7.528948693304041e-06, "loss": 1.4468, "step": 186090 }, { "epoch": 8.5, "learning_rate": 7.526660259050758e-06, "loss": 1.4415, "step": 186100 }, { "epoch": 8.5, "learning_rate": 7.5243718247974745e-06, "loss": 1.4312, "step": 186110 }, { "epoch": 8.5, "learning_rate": 7.52208339054419e-06, "loss": 1.364, "step": 186120 }, { "epoch": 8.5, "learning_rate": 7.519794956290905e-06, "loss": 1.3763, "step": 186130 }, { "epoch": 8.5, "learning_rate": 7.517506522037622e-06, "loss": 1.2929, "step": 186140 }, { "epoch": 8.5, "learning_rate": 7.515218087784339e-06, "loss": 1.2869, "step": 186150 }, { "epoch": 8.5, "learning_rate": 7.5129296535310545e-06, "loss": 1.4711, "step": 186160 }, { "epoch": 8.5, "learning_rate": 7.510641219277771e-06, "loss": 1.2509, "step": 186170 }, { "epoch": 8.5, "learning_rate": 7.508352785024486e-06, "loss": 1.4107, "step": 186180 }, { "epoch": 8.5, "learning_rate": 7.506064350771203e-06, "loss": 1.3793, "step": 186190 }, { "epoch": 8.5, "learning_rate": 7.503775916517919e-06, "loss": 1.3303, "step": 186200 }, { "epoch": 8.5, "learning_rate": 7.501487482264635e-06, "loss": 1.2851, "step": 186210 }, { "epoch": 8.5, "learning_rate": 7.499199048011352e-06, "loss": 1.3066, "step": 186220 }, { "epoch": 8.5, "learning_rate": 7.496910613758067e-06, "loss": 1.3016, "step": 186230 }, { "epoch": 8.5, "learning_rate": 7.494622179504783e-06, "loss": 1.4135, "step": 186240 }, { "epoch": 8.5, "learning_rate": 7.4923337452514995e-06, "loss": 1.3477, "step": 186250 }, { "epoch": 8.51, "learning_rate": 7.490045310998216e-06, "loss": 1.479, "step": 186260 }, { "epoch": 8.51, "learning_rate": 7.487756876744932e-06, "loss": 1.4273, "step": 186270 }, { "epoch": 8.51, "learning_rate": 7.485468442491647e-06, "loss": 1.305, "step": 186280 }, { "epoch": 8.51, "learning_rate": 7.483180008238364e-06, "loss": 1.2474, "step": 186290 }, { "epoch": 8.51, "learning_rate": 7.48089157398508e-06, "loss": 1.4949, "step": 186300 }, { "epoch": 8.51, "learning_rate": 7.478603139731796e-06, "loss": 1.2315, "step": 186310 }, { "epoch": 8.51, "learning_rate": 7.476314705478513e-06, "loss": 1.3369, "step": 186320 }, { "epoch": 8.51, "learning_rate": 7.474026271225228e-06, "loss": 1.502, "step": 186330 }, { "epoch": 8.51, "learning_rate": 7.471737836971944e-06, "loss": 1.301, "step": 186340 }, { "epoch": 8.51, "learning_rate": 7.46944940271866e-06, "loss": 1.2998, "step": 186350 }, { "epoch": 8.51, "learning_rate": 7.467160968465377e-06, "loss": 1.4362, "step": 186360 }, { "epoch": 8.51, "learning_rate": 7.464872534212092e-06, "loss": 1.3479, "step": 186370 }, { "epoch": 8.51, "learning_rate": 7.462584099958808e-06, "loss": 1.2182, "step": 186380 }, { "epoch": 8.51, "learning_rate": 7.4602956657055245e-06, "loss": 1.4368, "step": 186390 }, { "epoch": 8.51, "learning_rate": 7.458007231452241e-06, "loss": 1.36, "step": 186400 }, { "epoch": 8.51, "learning_rate": 7.455718797198957e-06, "loss": 1.266, "step": 186410 }, { "epoch": 8.51, "learning_rate": 7.453430362945672e-06, "loss": 1.3531, "step": 186420 }, { "epoch": 8.51, "learning_rate": 7.451141928692389e-06, "loss": 1.4576, "step": 186430 }, { "epoch": 8.51, "learning_rate": 7.448853494439105e-06, "loss": 1.3448, "step": 186440 }, { "epoch": 8.51, "learning_rate": 7.446565060185821e-06, "loss": 1.5181, "step": 186450 }, { "epoch": 8.51, "learning_rate": 7.444276625932538e-06, "loss": 1.3374, "step": 186460 }, { "epoch": 8.51, "learning_rate": 7.441988191679253e-06, "loss": 1.3176, "step": 186470 }, { "epoch": 8.52, "learning_rate": 7.4396997574259694e-06, "loss": 1.5137, "step": 186480 }, { "epoch": 8.52, "learning_rate": 7.437411323172685e-06, "loss": 1.3543, "step": 186490 }, { "epoch": 8.52, "learning_rate": 7.435122888919402e-06, "loss": 1.4075, "step": 186500 }, { "epoch": 8.52, "learning_rate": 7.432834454666119e-06, "loss": 1.3317, "step": 186510 }, { "epoch": 8.52, "learning_rate": 7.430546020412834e-06, "loss": 1.3846, "step": 186520 }, { "epoch": 8.52, "learning_rate": 7.4282575861595494e-06, "loss": 1.2845, "step": 186530 }, { "epoch": 8.52, "learning_rate": 7.425969151906266e-06, "loss": 1.2175, "step": 186540 }, { "epoch": 8.52, "learning_rate": 7.423680717652983e-06, "loss": 1.2164, "step": 186550 }, { "epoch": 8.52, "learning_rate": 7.421392283399699e-06, "loss": 1.2764, "step": 186560 }, { "epoch": 8.52, "learning_rate": 7.419103849146414e-06, "loss": 1.3525, "step": 186570 }, { "epoch": 8.52, "learning_rate": 7.41681541489313e-06, "loss": 1.2644, "step": 186580 }, { "epoch": 8.52, "learning_rate": 7.414526980639847e-06, "loss": 1.4073, "step": 186590 }, { "epoch": 8.52, "learning_rate": 7.412238546386563e-06, "loss": 1.4354, "step": 186600 }, { "epoch": 8.52, "learning_rate": 7.4099501121332794e-06, "loss": 1.3818, "step": 186610 }, { "epoch": 8.52, "learning_rate": 7.407661677879994e-06, "loss": 1.5492, "step": 186620 }, { "epoch": 8.52, "learning_rate": 7.40537324362671e-06, "loss": 1.3146, "step": 186630 }, { "epoch": 8.52, "learning_rate": 7.403084809373427e-06, "loss": 1.1904, "step": 186640 }, { "epoch": 8.52, "learning_rate": 7.400796375120144e-06, "loss": 1.4617, "step": 186650 }, { "epoch": 8.52, "learning_rate": 7.3985079408668594e-06, "loss": 1.287, "step": 186660 }, { "epoch": 8.52, "learning_rate": 7.396219506613574e-06, "loss": 1.2967, "step": 186670 }, { "epoch": 8.52, "learning_rate": 7.393931072360291e-06, "loss": 1.4714, "step": 186680 }, { "epoch": 8.52, "learning_rate": 7.391642638107008e-06, "loss": 1.4557, "step": 186690 }, { "epoch": 8.53, "learning_rate": 7.389354203853724e-06, "loss": 1.3238, "step": 186700 }, { "epoch": 8.53, "learning_rate": 7.38706576960044e-06, "loss": 1.3776, "step": 186710 }, { "epoch": 8.53, "learning_rate": 7.384777335347155e-06, "loss": 1.4271, "step": 186720 }, { "epoch": 8.53, "learning_rate": 7.382488901093872e-06, "loss": 1.3178, "step": 186730 }, { "epoch": 8.53, "learning_rate": 7.380200466840588e-06, "loss": 1.2649, "step": 186740 }, { "epoch": 8.53, "learning_rate": 7.377912032587304e-06, "loss": 1.5038, "step": 186750 }, { "epoch": 8.53, "learning_rate": 7.375623598334021e-06, "loss": 1.4251, "step": 186760 }, { "epoch": 8.53, "learning_rate": 7.373335164080736e-06, "loss": 1.3445, "step": 186770 }, { "epoch": 8.53, "learning_rate": 7.371046729827452e-06, "loss": 1.4193, "step": 186780 }, { "epoch": 8.53, "learning_rate": 7.3687582955741686e-06, "loss": 1.4063, "step": 186790 }, { "epoch": 8.53, "learning_rate": 7.366469861320885e-06, "loss": 1.3645, "step": 186800 }, { "epoch": 8.53, "learning_rate": 7.364181427067601e-06, "loss": 1.3209, "step": 186810 }, { "epoch": 8.53, "learning_rate": 7.361892992814316e-06, "loss": 1.395, "step": 186820 }, { "epoch": 8.53, "learning_rate": 7.359604558561033e-06, "loss": 1.3005, "step": 186830 }, { "epoch": 8.53, "learning_rate": 7.357316124307749e-06, "loss": 1.3875, "step": 186840 }, { "epoch": 8.53, "learning_rate": 7.355027690054465e-06, "loss": 1.2639, "step": 186850 }, { "epoch": 8.53, "learning_rate": 7.352739255801182e-06, "loss": 1.4622, "step": 186860 }, { "epoch": 8.53, "learning_rate": 7.350450821547897e-06, "loss": 1.3767, "step": 186870 }, { "epoch": 8.53, "learning_rate": 7.3481623872946136e-06, "loss": 1.4078, "step": 186880 }, { "epoch": 8.53, "learning_rate": 7.345873953041329e-06, "loss": 1.3569, "step": 186890 }, { "epoch": 8.53, "learning_rate": 7.343585518788046e-06, "loss": 1.5046, "step": 186900 }, { "epoch": 8.53, "learning_rate": 7.341297084534762e-06, "loss": 1.2716, "step": 186910 }, { "epoch": 8.54, "learning_rate": 7.339008650281477e-06, "loss": 1.3354, "step": 186920 }, { "epoch": 8.54, "learning_rate": 7.3367202160281935e-06, "loss": 1.3, "step": 186930 }, { "epoch": 8.54, "learning_rate": 7.33443178177491e-06, "loss": 1.3405, "step": 186940 }, { "epoch": 8.54, "learning_rate": 7.332143347521626e-06, "loss": 1.4064, "step": 186950 }, { "epoch": 8.54, "learning_rate": 7.329854913268343e-06, "loss": 1.3569, "step": 186960 }, { "epoch": 8.54, "learning_rate": 7.327566479015058e-06, "loss": 1.4598, "step": 186970 }, { "epoch": 8.54, "learning_rate": 7.325278044761774e-06, "loss": 1.3185, "step": 186980 }, { "epoch": 8.54, "learning_rate": 7.32298961050849e-06, "loss": 1.3073, "step": 186990 }, { "epoch": 8.54, "learning_rate": 7.320701176255207e-06, "loss": 1.3247, "step": 187000 }, { "epoch": 8.54, "learning_rate": 7.3184127420019236e-06, "loss": 1.3925, "step": 187010 }, { "epoch": 8.54, "learning_rate": 7.3161243077486385e-06, "loss": 1.189, "step": 187020 }, { "epoch": 8.54, "learning_rate": 7.313835873495354e-06, "loss": 1.3108, "step": 187030 }, { "epoch": 8.54, "learning_rate": 7.311547439242071e-06, "loss": 1.4525, "step": 187040 }, { "epoch": 8.54, "learning_rate": 7.309259004988788e-06, "loss": 1.3129, "step": 187050 }, { "epoch": 8.54, "learning_rate": 7.3069705707355035e-06, "loss": 1.4129, "step": 187060 }, { "epoch": 8.54, "learning_rate": 7.3046821364822185e-06, "loss": 1.31, "step": 187070 }, { "epoch": 8.54, "learning_rate": 7.302393702228935e-06, "loss": 1.3223, "step": 187080 }, { "epoch": 8.54, "learning_rate": 7.300105267975652e-06, "loss": 1.3959, "step": 187090 }, { "epoch": 8.54, "learning_rate": 7.297816833722368e-06, "loss": 1.201, "step": 187100 }, { "epoch": 8.54, "learning_rate": 7.295528399469084e-06, "loss": 1.306, "step": 187110 }, { "epoch": 8.54, "learning_rate": 7.293239965215799e-06, "loss": 1.2562, "step": 187120 }, { "epoch": 8.54, "learning_rate": 7.290951530962516e-06, "loss": 1.3433, "step": 187130 }, { "epoch": 8.55, "learning_rate": 7.288663096709232e-06, "loss": 1.3551, "step": 187140 }, { "epoch": 8.55, "learning_rate": 7.2863746624559485e-06, "loss": 1.4196, "step": 187150 }, { "epoch": 8.55, "learning_rate": 7.2840862282026635e-06, "loss": 1.4784, "step": 187160 }, { "epoch": 8.55, "learning_rate": 7.28179779394938e-06, "loss": 1.3946, "step": 187170 }, { "epoch": 8.55, "learning_rate": 7.279509359696096e-06, "loss": 1.2898, "step": 187180 }, { "epoch": 8.55, "learning_rate": 7.277220925442813e-06, "loss": 1.4122, "step": 187190 }, { "epoch": 8.55, "learning_rate": 7.2749324911895285e-06, "loss": 1.3242, "step": 187200 }, { "epoch": 8.55, "learning_rate": 7.2726440569362435e-06, "loss": 1.3178, "step": 187210 }, { "epoch": 8.55, "learning_rate": 7.27035562268296e-06, "loss": 1.4181, "step": 187220 }, { "epoch": 8.55, "learning_rate": 7.268067188429677e-06, "loss": 1.4823, "step": 187230 }, { "epoch": 8.55, "learning_rate": 7.265778754176393e-06, "loss": 1.2539, "step": 187240 }, { "epoch": 8.55, "learning_rate": 7.263490319923109e-06, "loss": 1.5932, "step": 187250 }, { "epoch": 8.55, "learning_rate": 7.261201885669824e-06, "loss": 1.3124, "step": 187260 }, { "epoch": 8.55, "learning_rate": 7.258913451416541e-06, "loss": 1.426, "step": 187270 }, { "epoch": 8.55, "learning_rate": 7.256625017163257e-06, "loss": 1.4199, "step": 187280 }, { "epoch": 8.55, "learning_rate": 7.2543365829099735e-06, "loss": 1.3084, "step": 187290 }, { "epoch": 8.55, "learning_rate": 7.25204814865669e-06, "loss": 1.3203, "step": 187300 }, { "epoch": 8.55, "learning_rate": 7.249759714403405e-06, "loss": 1.2547, "step": 187310 }, { "epoch": 8.55, "learning_rate": 7.247471280150121e-06, "loss": 1.2589, "step": 187320 }, { "epoch": 8.55, "learning_rate": 7.245182845896838e-06, "loss": 1.4907, "step": 187330 }, { "epoch": 8.55, "learning_rate": 7.242894411643554e-06, "loss": 1.3142, "step": 187340 }, { "epoch": 8.55, "learning_rate": 7.24060597739027e-06, "loss": 1.2879, "step": 187350 }, { "epoch": 8.56, "learning_rate": 7.238317543136985e-06, "loss": 1.4474, "step": 187360 }, { "epoch": 8.56, "learning_rate": 7.236029108883702e-06, "loss": 1.1041, "step": 187370 }, { "epoch": 8.56, "learning_rate": 7.2337406746304185e-06, "loss": 1.2979, "step": 187380 }, { "epoch": 8.56, "learning_rate": 7.231452240377134e-06, "loss": 1.4866, "step": 187390 }, { "epoch": 8.56, "learning_rate": 7.229163806123851e-06, "loss": 1.212, "step": 187400 }, { "epoch": 8.56, "learning_rate": 7.226875371870566e-06, "loss": 1.4859, "step": 187410 }, { "epoch": 8.56, "learning_rate": 7.224586937617283e-06, "loss": 1.3175, "step": 187420 }, { "epoch": 8.56, "learning_rate": 7.2222985033639985e-06, "loss": 1.2694, "step": 187430 }, { "epoch": 8.56, "learning_rate": 7.220010069110715e-06, "loss": 1.2975, "step": 187440 }, { "epoch": 8.56, "learning_rate": 7.217721634857432e-06, "loss": 1.3301, "step": 187450 }, { "epoch": 8.56, "learning_rate": 7.215433200604147e-06, "loss": 1.3285, "step": 187460 }, { "epoch": 8.56, "learning_rate": 7.213144766350863e-06, "loss": 1.3981, "step": 187470 }, { "epoch": 8.56, "learning_rate": 7.210856332097579e-06, "loss": 1.5636, "step": 187480 }, { "epoch": 8.56, "learning_rate": 7.208567897844295e-06, "loss": 1.1448, "step": 187490 }, { "epoch": 8.56, "learning_rate": 7.206279463591012e-06, "loss": 1.293, "step": 187500 }, { "epoch": 8.56, "learning_rate": 7.203991029337727e-06, "loss": 1.3142, "step": 187510 }, { "epoch": 8.56, "learning_rate": 7.2017025950844435e-06, "loss": 1.4175, "step": 187520 }, { "epoch": 8.56, "learning_rate": 7.199414160831159e-06, "loss": 1.3011, "step": 187530 }, { "epoch": 8.56, "learning_rate": 7.197125726577876e-06, "loss": 1.4803, "step": 187540 }, { "epoch": 8.56, "learning_rate": 7.194837292324593e-06, "loss": 1.3254, "step": 187550 }, { "epoch": 8.56, "learning_rate": 7.192548858071308e-06, "loss": 1.3223, "step": 187560 }, { "epoch": 8.56, "learning_rate": 7.1902604238180235e-06, "loss": 1.5063, "step": 187570 }, { "epoch": 8.57, "learning_rate": 7.18797198956474e-06, "loss": 1.4311, "step": 187580 }, { "epoch": 8.57, "learning_rate": 7.185683555311457e-06, "loss": 1.4321, "step": 187590 }, { "epoch": 8.57, "learning_rate": 7.183395121058173e-06, "loss": 1.2186, "step": 187600 }, { "epoch": 8.57, "learning_rate": 7.181106686804888e-06, "loss": 1.2927, "step": 187610 }, { "epoch": 8.57, "learning_rate": 7.178818252551604e-06, "loss": 1.3654, "step": 187620 }, { "epoch": 8.57, "learning_rate": 7.176529818298321e-06, "loss": 1.3638, "step": 187630 }, { "epoch": 8.57, "learning_rate": 7.174241384045037e-06, "loss": 1.3358, "step": 187640 }, { "epoch": 8.57, "learning_rate": 7.1719529497917535e-06, "loss": 1.3625, "step": 187650 }, { "epoch": 8.57, "learning_rate": 7.1696645155384684e-06, "loss": 1.2225, "step": 187660 }, { "epoch": 8.57, "learning_rate": 7.167376081285185e-06, "loss": 1.3667, "step": 187670 }, { "epoch": 8.57, "learning_rate": 7.165087647031901e-06, "loss": 1.3412, "step": 187680 }, { "epoch": 8.57, "learning_rate": 7.162799212778618e-06, "loss": 1.2552, "step": 187690 }, { "epoch": 8.57, "learning_rate": 7.160510778525334e-06, "loss": 1.286, "step": 187700 }, { "epoch": 8.57, "learning_rate": 7.158222344272049e-06, "loss": 1.3671, "step": 187710 }, { "epoch": 8.57, "learning_rate": 7.155933910018765e-06, "loss": 1.4022, "step": 187720 }, { "epoch": 8.57, "learning_rate": 7.153645475765482e-06, "loss": 1.4444, "step": 187730 }, { "epoch": 8.57, "learning_rate": 7.1513570415121985e-06, "loss": 1.2628, "step": 187740 }, { "epoch": 8.57, "learning_rate": 7.149068607258914e-06, "loss": 1.2965, "step": 187750 }, { "epoch": 8.57, "learning_rate": 7.146780173005629e-06, "loss": 1.3081, "step": 187760 }, { "epoch": 8.57, "learning_rate": 7.144491738752346e-06, "loss": 1.2551, "step": 187770 }, { "epoch": 8.57, "learning_rate": 7.142203304499062e-06, "loss": 1.2722, "step": 187780 }, { "epoch": 8.57, "learning_rate": 7.1399148702457784e-06, "loss": 1.2609, "step": 187790 }, { "epoch": 8.58, "learning_rate": 7.137626435992495e-06, "loss": 1.2456, "step": 187800 }, { "epoch": 8.58, "learning_rate": 7.13533800173921e-06, "loss": 1.3448, "step": 187810 }, { "epoch": 8.58, "learning_rate": 7.133049567485926e-06, "loss": 1.3709, "step": 187820 }, { "epoch": 8.58, "learning_rate": 7.130761133232643e-06, "loss": 1.2983, "step": 187830 }, { "epoch": 8.58, "learning_rate": 7.128472698979359e-06, "loss": 1.2453, "step": 187840 }, { "epoch": 8.58, "learning_rate": 7.126184264726075e-06, "loss": 1.2943, "step": 187850 }, { "epoch": 8.58, "learning_rate": 7.12389583047279e-06, "loss": 1.3657, "step": 187860 }, { "epoch": 8.58, "learning_rate": 7.121607396219507e-06, "loss": 1.4517, "step": 187870 }, { "epoch": 8.58, "learning_rate": 7.1193189619662234e-06, "loss": 1.1642, "step": 187880 }, { "epoch": 8.58, "learning_rate": 7.117030527712939e-06, "loss": 1.3573, "step": 187890 }, { "epoch": 8.58, "learning_rate": 7.114742093459656e-06, "loss": 1.267, "step": 187900 }, { "epoch": 8.58, "learning_rate": 7.112453659206371e-06, "loss": 1.259, "step": 187910 }, { "epoch": 8.58, "learning_rate": 7.110165224953088e-06, "loss": 1.254, "step": 187920 }, { "epoch": 8.58, "learning_rate": 7.107876790699803e-06, "loss": 1.3028, "step": 187930 }, { "epoch": 8.58, "learning_rate": 7.10558835644652e-06, "loss": 1.333, "step": 187940 }, { "epoch": 8.58, "learning_rate": 7.103299922193235e-06, "loss": 1.234, "step": 187950 }, { "epoch": 8.58, "learning_rate": 7.101011487939952e-06, "loss": 1.2696, "step": 187960 }, { "epoch": 8.58, "learning_rate": 7.0987230536866676e-06, "loss": 1.2376, "step": 187970 }, { "epoch": 8.58, "learning_rate": 7.096434619433384e-06, "loss": 1.2957, "step": 187980 }, { "epoch": 8.58, "learning_rate": 7.094146185180101e-06, "loss": 1.3697, "step": 187990 }, { "epoch": 8.58, "learning_rate": 7.091857750926816e-06, "loss": 1.2585, "step": 188000 }, { "epoch": 8.59, "learning_rate": 7.089569316673532e-06, "loss": 1.5102, "step": 188010 }, { "epoch": 8.59, "learning_rate": 7.087280882420248e-06, "loss": 1.3768, "step": 188020 }, { "epoch": 8.59, "learning_rate": 7.084992448166965e-06, "loss": 1.3588, "step": 188030 }, { "epoch": 8.59, "learning_rate": 7.082704013913681e-06, "loss": 1.243, "step": 188040 }, { "epoch": 8.59, "learning_rate": 7.080415579660396e-06, "loss": 1.4124, "step": 188050 }, { "epoch": 8.59, "learning_rate": 7.0781271454071126e-06, "loss": 1.4082, "step": 188060 }, { "epoch": 8.59, "learning_rate": 7.075838711153828e-06, "loss": 1.2669, "step": 188070 }, { "epoch": 8.59, "learning_rate": 7.073550276900545e-06, "loss": 1.4253, "step": 188080 }, { "epoch": 8.59, "learning_rate": 7.071261842647262e-06, "loss": 1.3057, "step": 188090 }, { "epoch": 8.59, "learning_rate": 7.068973408393977e-06, "loss": 1.4086, "step": 188100 }, { "epoch": 8.59, "learning_rate": 7.0666849741406925e-06, "loss": 1.2854, "step": 188110 }, { "epoch": 8.59, "learning_rate": 7.064396539887409e-06, "loss": 1.1684, "step": 188120 }, { "epoch": 8.59, "learning_rate": 7.062108105634126e-06, "loss": 1.2713, "step": 188130 }, { "epoch": 8.59, "learning_rate": 7.059819671380842e-06, "loss": 1.1297, "step": 188140 }, { "epoch": 8.59, "learning_rate": 7.057531237127557e-06, "loss": 1.5129, "step": 188150 }, { "epoch": 8.59, "learning_rate": 7.055242802874273e-06, "loss": 1.5811, "step": 188160 }, { "epoch": 8.59, "learning_rate": 7.05295436862099e-06, "loss": 1.33, "step": 188170 }, { "epoch": 8.59, "learning_rate": 7.050665934367706e-06, "loss": 1.2816, "step": 188180 }, { "epoch": 8.59, "learning_rate": 7.0483775001144226e-06, "loss": 1.2813, "step": 188190 }, { "epoch": 8.59, "learning_rate": 7.0460890658611375e-06, "loss": 1.2672, "step": 188200 }, { "epoch": 8.59, "learning_rate": 7.043800631607854e-06, "loss": 1.2258, "step": 188210 }, { "epoch": 8.59, "learning_rate": 7.04151219735457e-06, "loss": 1.5363, "step": 188220 }, { "epoch": 8.6, "learning_rate": 7.039223763101287e-06, "loss": 1.3642, "step": 188230 }, { "epoch": 8.6, "learning_rate": 7.036935328848003e-06, "loss": 1.3808, "step": 188240 }, { "epoch": 8.6, "learning_rate": 7.034646894594718e-06, "loss": 1.3785, "step": 188250 }, { "epoch": 8.6, "learning_rate": 7.032358460341434e-06, "loss": 1.362, "step": 188260 }, { "epoch": 8.6, "learning_rate": 7.030070026088151e-06, "loss": 1.3187, "step": 188270 }, { "epoch": 8.6, "learning_rate": 7.0277815918348675e-06, "loss": 1.3267, "step": 188280 }, { "epoch": 8.6, "learning_rate": 7.025493157581583e-06, "loss": 1.4055, "step": 188290 }, { "epoch": 8.6, "learning_rate": 7.023204723328298e-06, "loss": 1.3322, "step": 188300 }, { "epoch": 8.6, "learning_rate": 7.020916289075015e-06, "loss": 1.3163, "step": 188310 }, { "epoch": 8.6, "learning_rate": 7.018627854821732e-06, "loss": 1.2957, "step": 188320 }, { "epoch": 8.6, "learning_rate": 7.0163394205684475e-06, "loss": 1.4, "step": 188330 }, { "epoch": 8.6, "learning_rate": 7.014050986315164e-06, "loss": 1.3847, "step": 188340 }, { "epoch": 8.6, "learning_rate": 7.011762552061879e-06, "loss": 1.1688, "step": 188350 }, { "epoch": 8.6, "learning_rate": 7.009474117808595e-06, "loss": 1.5253, "step": 188360 }, { "epoch": 8.6, "learning_rate": 7.007185683555312e-06, "loss": 1.3457, "step": 188370 }, { "epoch": 8.6, "learning_rate": 7.004897249302028e-06, "loss": 1.4912, "step": 188380 }, { "epoch": 8.6, "learning_rate": 7.002608815048744e-06, "loss": 1.2351, "step": 188390 }, { "epoch": 8.6, "learning_rate": 7.000320380795459e-06, "loss": 1.4545, "step": 188400 }, { "epoch": 8.6, "learning_rate": 6.998031946542176e-06, "loss": 1.3889, "step": 188410 }, { "epoch": 8.6, "learning_rate": 6.9957435122888925e-06, "loss": 1.4225, "step": 188420 }, { "epoch": 8.6, "learning_rate": 6.993455078035608e-06, "loss": 1.3475, "step": 188430 }, { "epoch": 8.6, "learning_rate": 6.991166643782325e-06, "loss": 1.38, "step": 188440 }, { "epoch": 8.61, "learning_rate": 6.98887820952904e-06, "loss": 1.3419, "step": 188450 }, { "epoch": 8.61, "learning_rate": 6.986589775275757e-06, "loss": 1.4502, "step": 188460 }, { "epoch": 8.61, "learning_rate": 6.9843013410224725e-06, "loss": 1.3653, "step": 188470 }, { "epoch": 8.61, "learning_rate": 6.982012906769189e-06, "loss": 1.3742, "step": 188480 }, { "epoch": 8.61, "learning_rate": 6.979724472515906e-06, "loss": 1.359, "step": 188490 }, { "epoch": 8.61, "learning_rate": 6.977436038262621e-06, "loss": 1.4472, "step": 188500 }, { "epoch": 8.61, "learning_rate": 6.975147604009337e-06, "loss": 1.248, "step": 188510 }, { "epoch": 8.61, "learning_rate": 6.972859169756053e-06, "loss": 1.3197, "step": 188520 }, { "epoch": 8.61, "learning_rate": 6.97057073550277e-06, "loss": 1.2917, "step": 188530 }, { "epoch": 8.61, "learning_rate": 6.968282301249486e-06, "loss": 1.4832, "step": 188540 }, { "epoch": 8.61, "learning_rate": 6.965993866996201e-06, "loss": 1.3844, "step": 188550 }, { "epoch": 8.61, "learning_rate": 6.9637054327429175e-06, "loss": 1.4942, "step": 188560 }, { "epoch": 8.61, "learning_rate": 6.961416998489634e-06, "loss": 1.4092, "step": 188570 }, { "epoch": 8.61, "learning_rate": 6.95912856423635e-06, "loss": 1.3382, "step": 188580 }, { "epoch": 8.61, "learning_rate": 6.956840129983067e-06, "loss": 1.3329, "step": 188590 }, { "epoch": 8.61, "learning_rate": 6.954551695729782e-06, "loss": 1.3356, "step": 188600 }, { "epoch": 8.61, "learning_rate": 6.952263261476498e-06, "loss": 1.2799, "step": 188610 }, { "epoch": 8.61, "learning_rate": 6.949974827223214e-06, "loss": 1.1934, "step": 188620 }, { "epoch": 8.61, "learning_rate": 6.947686392969931e-06, "loss": 1.3052, "step": 188630 }, { "epoch": 8.61, "learning_rate": 6.945397958716647e-06, "loss": 1.489, "step": 188640 }, { "epoch": 8.61, "learning_rate": 6.943109524463362e-06, "loss": 1.2899, "step": 188650 }, { "epoch": 8.61, "learning_rate": 6.940821090210078e-06, "loss": 1.362, "step": 188660 }, { "epoch": 8.62, "learning_rate": 6.938532655956795e-06, "loss": 1.3891, "step": 188670 }, { "epoch": 8.62, "learning_rate": 6.936244221703511e-06, "loss": 1.3832, "step": 188680 }, { "epoch": 8.62, "learning_rate": 6.9339557874502275e-06, "loss": 1.2574, "step": 188690 }, { "epoch": 8.62, "learning_rate": 6.9316673531969425e-06, "loss": 1.3528, "step": 188700 }, { "epoch": 8.62, "learning_rate": 6.929378918943659e-06, "loss": 1.298, "step": 188710 }, { "epoch": 8.62, "learning_rate": 6.927090484690375e-06, "loss": 1.3867, "step": 188720 }, { "epoch": 8.62, "learning_rate": 6.924802050437092e-06, "loss": 1.2674, "step": 188730 }, { "epoch": 8.62, "learning_rate": 6.922513616183808e-06, "loss": 1.2619, "step": 188740 }, { "epoch": 8.62, "learning_rate": 6.920225181930523e-06, "loss": 1.3684, "step": 188750 }, { "epoch": 8.62, "learning_rate": 6.917936747677239e-06, "loss": 1.2934, "step": 188760 }, { "epoch": 8.62, "learning_rate": 6.915648313423956e-06, "loss": 1.3855, "step": 188770 }, { "epoch": 8.62, "learning_rate": 6.9133598791706725e-06, "loss": 1.4078, "step": 188780 }, { "epoch": 8.62, "learning_rate": 6.9110714449173875e-06, "loss": 1.2407, "step": 188790 }, { "epoch": 8.62, "learning_rate": 6.908783010664103e-06, "loss": 1.3895, "step": 188800 }, { "epoch": 8.62, "learning_rate": 6.90649457641082e-06, "loss": 1.2858, "step": 188810 }, { "epoch": 8.62, "learning_rate": 6.904206142157537e-06, "loss": 1.3146, "step": 188820 }, { "epoch": 8.62, "learning_rate": 6.9019177079042525e-06, "loss": 1.2915, "step": 188830 }, { "epoch": 8.62, "learning_rate": 6.8996292736509674e-06, "loss": 1.3211, "step": 188840 }, { "epoch": 8.62, "learning_rate": 6.897340839397684e-06, "loss": 1.348, "step": 188850 }, { "epoch": 8.62, "learning_rate": 6.895052405144401e-06, "loss": 1.4405, "step": 188860 }, { "epoch": 8.62, "learning_rate": 6.892763970891117e-06, "loss": 1.3436, "step": 188870 }, { "epoch": 8.62, "learning_rate": 6.890475536637833e-06, "loss": 1.2924, "step": 188880 }, { "epoch": 8.63, "learning_rate": 6.888187102384548e-06, "loss": 1.4462, "step": 188890 }, { "epoch": 8.63, "learning_rate": 6.885898668131265e-06, "loss": 1.3919, "step": 188900 }, { "epoch": 8.63, "learning_rate": 6.883610233877981e-06, "loss": 1.2081, "step": 188910 }, { "epoch": 8.63, "learning_rate": 6.8813217996246975e-06, "loss": 1.3866, "step": 188920 }, { "epoch": 8.63, "learning_rate": 6.879033365371413e-06, "loss": 1.3217, "step": 188930 }, { "epoch": 8.63, "learning_rate": 6.876744931118128e-06, "loss": 1.4396, "step": 188940 }, { "epoch": 8.63, "learning_rate": 6.874456496864845e-06, "loss": 1.446, "step": 188950 }, { "epoch": 8.63, "learning_rate": 6.872168062611562e-06, "loss": 1.4167, "step": 188960 }, { "epoch": 8.63, "learning_rate": 6.8698796283582774e-06, "loss": 1.3046, "step": 188970 }, { "epoch": 8.63, "learning_rate": 6.867591194104994e-06, "loss": 1.2819, "step": 188980 }, { "epoch": 8.63, "learning_rate": 6.865302759851709e-06, "loss": 1.2737, "step": 188990 }, { "epoch": 8.63, "learning_rate": 6.863014325598426e-06, "loss": 1.5321, "step": 189000 }, { "epoch": 8.63, "learning_rate": 6.860725891345142e-06, "loss": 1.3771, "step": 189010 }, { "epoch": 8.63, "learning_rate": 6.858437457091858e-06, "loss": 1.413, "step": 189020 }, { "epoch": 8.63, "learning_rate": 6.856149022838575e-06, "loss": 1.3666, "step": 189030 }, { "epoch": 8.63, "learning_rate": 6.85386058858529e-06, "loss": 1.386, "step": 189040 }, { "epoch": 8.63, "learning_rate": 6.851572154332006e-06, "loss": 1.2656, "step": 189050 }, { "epoch": 8.63, "learning_rate": 6.8492837200787224e-06, "loss": 1.4932, "step": 189060 }, { "epoch": 8.63, "learning_rate": 6.846995285825439e-06, "loss": 1.3165, "step": 189070 }, { "epoch": 8.63, "learning_rate": 6.844706851572155e-06, "loss": 1.4492, "step": 189080 }, { "epoch": 8.63, "learning_rate": 6.84241841731887e-06, "loss": 1.2494, "step": 189090 }, { "epoch": 8.63, "learning_rate": 6.840129983065587e-06, "loss": 1.2662, "step": 189100 }, { "epoch": 8.64, "learning_rate": 6.837841548812303e-06, "loss": 1.3915, "step": 189110 }, { "epoch": 8.64, "learning_rate": 6.835553114559019e-06, "loss": 1.3291, "step": 189120 }, { "epoch": 8.64, "learning_rate": 6.833264680305736e-06, "loss": 1.5118, "step": 189130 }, { "epoch": 8.64, "learning_rate": 6.830976246052451e-06, "loss": 1.3322, "step": 189140 }, { "epoch": 8.64, "learning_rate": 6.828687811799167e-06, "loss": 1.346, "step": 189150 }, { "epoch": 8.64, "learning_rate": 6.826399377545883e-06, "loss": 1.266, "step": 189160 }, { "epoch": 8.64, "learning_rate": 6.8241109432926e-06, "loss": 1.3111, "step": 189170 }, { "epoch": 8.64, "learning_rate": 6.821822509039317e-06, "loss": 1.3944, "step": 189180 }, { "epoch": 8.64, "learning_rate": 6.8195340747860316e-06, "loss": 1.3635, "step": 189190 }, { "epoch": 8.64, "learning_rate": 6.817245640532747e-06, "loss": 1.3404, "step": 189200 }, { "epoch": 8.64, "learning_rate": 6.814957206279464e-06, "loss": 1.3186, "step": 189210 }, { "epoch": 8.64, "learning_rate": 6.81266877202618e-06, "loss": 1.3142, "step": 189220 }, { "epoch": 8.64, "learning_rate": 6.810380337772897e-06, "loss": 1.5144, "step": 189230 }, { "epoch": 8.64, "learning_rate": 6.8080919035196116e-06, "loss": 1.2661, "step": 189240 }, { "epoch": 8.64, "learning_rate": 6.805803469266328e-06, "loss": 1.2215, "step": 189250 }, { "epoch": 8.64, "learning_rate": 6.803515035013044e-06, "loss": 1.3166, "step": 189260 }, { "epoch": 8.64, "learning_rate": 6.801226600759761e-06, "loss": 1.429, "step": 189270 }, { "epoch": 8.64, "learning_rate": 6.798938166506477e-06, "loss": 1.38, "step": 189280 }, { "epoch": 8.64, "learning_rate": 6.796649732253192e-06, "loss": 1.3536, "step": 189290 }, { "epoch": 8.64, "learning_rate": 6.794361297999908e-06, "loss": 1.5386, "step": 189300 }, { "epoch": 8.64, "learning_rate": 6.792072863746625e-06, "loss": 1.2714, "step": 189310 }, { "epoch": 8.64, "learning_rate": 6.7897844294933416e-06, "loss": 1.343, "step": 189320 }, { "epoch": 8.65, "learning_rate": 6.787495995240057e-06, "loss": 1.3737, "step": 189330 }, { "epoch": 8.65, "learning_rate": 6.785207560986772e-06, "loss": 1.4301, "step": 189340 }, { "epoch": 8.65, "learning_rate": 6.782919126733489e-06, "loss": 1.5216, "step": 189350 }, { "epoch": 8.65, "learning_rate": 6.780630692480206e-06, "loss": 1.376, "step": 189360 }, { "epoch": 8.65, "learning_rate": 6.7783422582269216e-06, "loss": 1.288, "step": 189370 }, { "epoch": 8.65, "learning_rate": 6.776053823973638e-06, "loss": 1.1538, "step": 189380 }, { "epoch": 8.65, "learning_rate": 6.773765389720353e-06, "loss": 1.4924, "step": 189390 }, { "epoch": 8.65, "learning_rate": 6.77147695546707e-06, "loss": 1.3207, "step": 189400 }, { "epoch": 8.65, "learning_rate": 6.769188521213786e-06, "loss": 1.4779, "step": 189410 }, { "epoch": 8.65, "learning_rate": 6.766900086960502e-06, "loss": 1.3007, "step": 189420 }, { "epoch": 8.65, "learning_rate": 6.764611652707219e-06, "loss": 1.3155, "step": 189430 }, { "epoch": 8.65, "learning_rate": 6.762323218453934e-06, "loss": 1.5352, "step": 189440 }, { "epoch": 8.65, "learning_rate": 6.76003478420065e-06, "loss": 1.4299, "step": 189450 }, { "epoch": 8.65, "learning_rate": 6.7577463499473665e-06, "loss": 1.2576, "step": 189460 }, { "epoch": 8.65, "learning_rate": 6.755457915694083e-06, "loss": 1.4036, "step": 189470 }, { "epoch": 8.65, "learning_rate": 6.753169481440799e-06, "loss": 1.3152, "step": 189480 }, { "epoch": 8.65, "learning_rate": 6.750881047187514e-06, "loss": 1.4346, "step": 189490 }, { "epoch": 8.65, "learning_rate": 6.748592612934231e-06, "loss": 1.2306, "step": 189500 }, { "epoch": 8.65, "learning_rate": 6.7463041786809465e-06, "loss": 1.3815, "step": 189510 }, { "epoch": 8.65, "learning_rate": 6.744015744427663e-06, "loss": 1.3767, "step": 189520 }, { "epoch": 8.65, "learning_rate": 6.74172731017438e-06, "loss": 1.4148, "step": 189530 }, { "epoch": 8.65, "learning_rate": 6.739438875921095e-06, "loss": 1.3347, "step": 189540 }, { "epoch": 8.66, "learning_rate": 6.737150441667811e-06, "loss": 1.5371, "step": 189550 }, { "epoch": 8.66, "learning_rate": 6.734862007414527e-06, "loss": 1.3681, "step": 189560 }, { "epoch": 8.66, "learning_rate": 6.732573573161244e-06, "loss": 1.3916, "step": 189570 }, { "epoch": 8.66, "learning_rate": 6.730285138907959e-06, "loss": 1.2952, "step": 189580 }, { "epoch": 8.66, "learning_rate": 6.727996704654675e-06, "loss": 1.3833, "step": 189590 }, { "epoch": 8.66, "learning_rate": 6.7257082704013915e-06, "loss": 1.3001, "step": 189600 }, { "epoch": 8.66, "learning_rate": 6.723419836148108e-06, "loss": 1.4331, "step": 189610 }, { "epoch": 8.66, "learning_rate": 6.721131401894824e-06, "loss": 1.4196, "step": 189620 }, { "epoch": 8.66, "learning_rate": 6.718842967641539e-06, "loss": 1.3989, "step": 189630 }, { "epoch": 8.66, "learning_rate": 6.716554533388256e-06, "loss": 1.4763, "step": 189640 }, { "epoch": 8.66, "learning_rate": 6.714266099134972e-06, "loss": 1.2041, "step": 189650 }, { "epoch": 8.66, "learning_rate": 6.711977664881688e-06, "loss": 1.1694, "step": 189660 }, { "epoch": 8.66, "learning_rate": 6.709689230628405e-06, "loss": 1.3763, "step": 189670 }, { "epoch": 8.66, "learning_rate": 6.70740079637512e-06, "loss": 1.2982, "step": 189680 }, { "epoch": 8.66, "learning_rate": 6.7051123621218365e-06, "loss": 1.3298, "step": 189690 }, { "epoch": 8.66, "learning_rate": 6.702823927868552e-06, "loss": 1.377, "step": 189700 }, { "epoch": 8.66, "learning_rate": 6.700535493615269e-06, "loss": 1.5079, "step": 189710 }, { "epoch": 8.66, "learning_rate": 6.698247059361986e-06, "loss": 1.2416, "step": 189720 }, { "epoch": 8.66, "learning_rate": 6.695958625108701e-06, "loss": 1.3735, "step": 189730 }, { "epoch": 8.66, "learning_rate": 6.6936701908554165e-06, "loss": 1.2932, "step": 189740 }, { "epoch": 8.66, "learning_rate": 6.691381756602133e-06, "loss": 1.4518, "step": 189750 }, { "epoch": 8.66, "learning_rate": 6.68909332234885e-06, "loss": 1.4262, "step": 189760 }, { "epoch": 8.67, "learning_rate": 6.686804888095566e-06, "loss": 1.3882, "step": 189770 }, { "epoch": 8.67, "learning_rate": 6.684516453842281e-06, "loss": 1.4253, "step": 189780 }, { "epoch": 8.67, "learning_rate": 6.682228019588997e-06, "loss": 1.2551, "step": 189790 }, { "epoch": 8.67, "learning_rate": 6.679939585335713e-06, "loss": 1.5464, "step": 189800 }, { "epoch": 8.67, "learning_rate": 6.67765115108243e-06, "loss": 1.3149, "step": 189810 }, { "epoch": 8.67, "learning_rate": 6.6753627168291465e-06, "loss": 1.3565, "step": 189820 }, { "epoch": 8.67, "learning_rate": 6.6730742825758615e-06, "loss": 1.3661, "step": 189830 }, { "epoch": 8.67, "learning_rate": 6.670785848322577e-06, "loss": 1.3166, "step": 189840 }, { "epoch": 8.67, "learning_rate": 6.668497414069294e-06, "loss": 1.3292, "step": 189850 }, { "epoch": 8.67, "learning_rate": 6.666208979816011e-06, "loss": 1.2477, "step": 189860 }, { "epoch": 8.67, "learning_rate": 6.6639205455627265e-06, "loss": 1.211, "step": 189870 }, { "epoch": 8.67, "learning_rate": 6.6616321113094415e-06, "loss": 1.4304, "step": 189880 }, { "epoch": 8.67, "learning_rate": 6.659343677056158e-06, "loss": 1.3676, "step": 189890 }, { "epoch": 8.67, "learning_rate": 6.657055242802875e-06, "loss": 1.2924, "step": 189900 }, { "epoch": 8.67, "learning_rate": 6.654766808549591e-06, "loss": 1.4002, "step": 189910 }, { "epoch": 8.67, "learning_rate": 6.652478374296307e-06, "loss": 1.4025, "step": 189920 }, { "epoch": 8.67, "learning_rate": 6.650189940043022e-06, "loss": 1.2286, "step": 189930 }, { "epoch": 8.67, "learning_rate": 6.647901505789739e-06, "loss": 1.4039, "step": 189940 }, { "epoch": 8.67, "learning_rate": 6.645613071536455e-06, "loss": 1.3418, "step": 189950 }, { "epoch": 8.67, "learning_rate": 6.6433246372831715e-06, "loss": 1.3984, "step": 189960 }, { "epoch": 8.67, "learning_rate": 6.641036203029888e-06, "loss": 1.389, "step": 189970 }, { "epoch": 8.67, "learning_rate": 6.638747768776603e-06, "loss": 1.3818, "step": 189980 }, { "epoch": 8.68, "learning_rate": 6.636459334523319e-06, "loss": 1.3629, "step": 189990 }, { "epoch": 8.68, "learning_rate": 6.634170900270036e-06, "loss": 1.3029, "step": 190000 }, { "epoch": 8.68, "learning_rate": 6.631882466016752e-06, "loss": 1.4276, "step": 190010 }, { "epoch": 8.68, "learning_rate": 6.629594031763468e-06, "loss": 1.2527, "step": 190020 }, { "epoch": 8.68, "learning_rate": 6.627305597510183e-06, "loss": 1.4387, "step": 190030 }, { "epoch": 8.68, "learning_rate": 6.6250171632569e-06, "loss": 1.3209, "step": 190040 }, { "epoch": 8.68, "learning_rate": 6.6227287290036165e-06, "loss": 1.3852, "step": 190050 }, { "epoch": 8.68, "learning_rate": 6.620440294750332e-06, "loss": 1.3234, "step": 190060 }, { "epoch": 8.68, "learning_rate": 6.618151860497049e-06, "loss": 1.2286, "step": 190070 }, { "epoch": 8.68, "learning_rate": 6.615863426243764e-06, "loss": 1.1976, "step": 190080 }, { "epoch": 8.68, "learning_rate": 6.61357499199048e-06, "loss": 1.2578, "step": 190090 }, { "epoch": 8.68, "learning_rate": 6.6112865577371965e-06, "loss": 1.245, "step": 190100 }, { "epoch": 8.68, "learning_rate": 6.608998123483913e-06, "loss": 1.4167, "step": 190110 }, { "epoch": 8.68, "learning_rate": 6.606709689230629e-06, "loss": 1.3885, "step": 190120 }, { "epoch": 8.68, "learning_rate": 6.604421254977344e-06, "loss": 1.3456, "step": 190130 }, { "epoch": 8.68, "learning_rate": 6.602132820724061e-06, "loss": 1.448, "step": 190140 }, { "epoch": 8.68, "learning_rate": 6.599844386470777e-06, "loss": 1.5949, "step": 190150 }, { "epoch": 8.68, "learning_rate": 6.597555952217493e-06, "loss": 1.2802, "step": 190160 }, { "epoch": 8.68, "learning_rate": 6.59526751796421e-06, "loss": 1.2922, "step": 190170 }, { "epoch": 8.68, "learning_rate": 6.592979083710925e-06, "loss": 1.3882, "step": 190180 }, { "epoch": 8.68, "learning_rate": 6.5906906494576414e-06, "loss": 1.3133, "step": 190190 }, { "epoch": 8.69, "learning_rate": 6.588402215204357e-06, "loss": 1.451, "step": 190200 }, { "epoch": 8.69, "learning_rate": 6.586113780951074e-06, "loss": 1.3831, "step": 190210 }, { "epoch": 8.69, "learning_rate": 6.583825346697791e-06, "loss": 1.4194, "step": 190220 }, { "epoch": 8.69, "learning_rate": 6.581536912444506e-06, "loss": 1.3644, "step": 190230 }, { "epoch": 8.69, "learning_rate": 6.5792484781912214e-06, "loss": 1.5277, "step": 190240 }, { "epoch": 8.69, "learning_rate": 6.576960043937938e-06, "loss": 1.3973, "step": 190250 }, { "epoch": 8.69, "learning_rate": 6.574671609684655e-06, "loss": 1.4324, "step": 190260 }, { "epoch": 8.69, "learning_rate": 6.572383175431371e-06, "loss": 1.3297, "step": 190270 }, { "epoch": 8.69, "learning_rate": 6.570094741178086e-06, "loss": 1.3752, "step": 190280 }, { "epoch": 8.69, "learning_rate": 6.567806306924802e-06, "loss": 1.46, "step": 190290 }, { "epoch": 8.69, "learning_rate": 6.565517872671519e-06, "loss": 1.4307, "step": 190300 }, { "epoch": 8.69, "learning_rate": 6.563229438418235e-06, "loss": 1.4921, "step": 190310 }, { "epoch": 8.69, "learning_rate": 6.5609410041649514e-06, "loss": 1.2205, "step": 190320 }, { "epoch": 8.69, "learning_rate": 6.558652569911666e-06, "loss": 1.371, "step": 190330 }, { "epoch": 8.69, "learning_rate": 6.556364135658383e-06, "loss": 1.5374, "step": 190340 }, { "epoch": 8.69, "learning_rate": 6.554075701405099e-06, "loss": 1.2369, "step": 190350 }, { "epoch": 8.69, "learning_rate": 6.551787267151816e-06, "loss": 1.3176, "step": 190360 }, { "epoch": 8.69, "learning_rate": 6.5494988328985306e-06, "loss": 1.3326, "step": 190370 }, { "epoch": 8.69, "learning_rate": 6.547210398645246e-06, "loss": 1.4053, "step": 190380 }, { "epoch": 8.69, "learning_rate": 6.544921964391963e-06, "loss": 1.2666, "step": 190390 }, { "epoch": 8.69, "learning_rate": 6.54263353013868e-06, "loss": 1.3855, "step": 190400 }, { "epoch": 8.69, "learning_rate": 6.540345095885396e-06, "loss": 1.2634, "step": 190410 }, { "epoch": 8.7, "learning_rate": 6.5380566616321106e-06, "loss": 1.1922, "step": 190420 }, { "epoch": 8.7, "learning_rate": 6.535768227378827e-06, "loss": 1.2113, "step": 190430 }, { "epoch": 8.7, "learning_rate": 6.533479793125544e-06, "loss": 1.4092, "step": 190440 }, { "epoch": 8.7, "learning_rate": 6.53119135887226e-06, "loss": 1.393, "step": 190450 }, { "epoch": 8.7, "learning_rate": 6.528902924618976e-06, "loss": 1.3655, "step": 190460 }, { "epoch": 8.7, "learning_rate": 6.526614490365691e-06, "loss": 1.4204, "step": 190470 }, { "epoch": 8.7, "learning_rate": 6.524326056112408e-06, "loss": 1.3132, "step": 190480 }, { "epoch": 8.7, "learning_rate": 6.522037621859124e-06, "loss": 1.4717, "step": 190490 }, { "epoch": 8.7, "learning_rate": 6.5197491876058406e-06, "loss": 1.2184, "step": 190500 }, { "epoch": 8.7, "learning_rate": 6.517460753352557e-06, "loss": 1.4879, "step": 190510 }, { "epoch": 8.7, "learning_rate": 6.515172319099272e-06, "loss": 1.3455, "step": 190520 }, { "epoch": 8.7, "learning_rate": 6.512883884845988e-06, "loss": 1.3581, "step": 190530 }, { "epoch": 8.7, "learning_rate": 6.510595450592705e-06, "loss": 1.3479, "step": 190540 }, { "epoch": 8.7, "learning_rate": 6.508307016339421e-06, "loss": 1.3624, "step": 190550 }, { "epoch": 8.7, "learning_rate": 6.506018582086137e-06, "loss": 1.2496, "step": 190560 }, { "epoch": 8.7, "learning_rate": 6.503730147832852e-06, "loss": 1.3559, "step": 190570 }, { "epoch": 8.7, "learning_rate": 6.501441713579569e-06, "loss": 1.3277, "step": 190580 }, { "epoch": 8.7, "learning_rate": 6.4991532793262856e-06, "loss": 1.2502, "step": 190590 }, { "epoch": 8.7, "learning_rate": 6.496864845073001e-06, "loss": 1.5404, "step": 190600 }, { "epoch": 8.7, "learning_rate": 6.494576410819718e-06, "loss": 1.1463, "step": 190610 }, { "epoch": 8.7, "learning_rate": 6.492287976566433e-06, "loss": 1.3543, "step": 190620 }, { "epoch": 8.7, "learning_rate": 6.48999954231315e-06, "loss": 1.4025, "step": 190630 }, { "epoch": 8.71, "learning_rate": 6.4877111080598655e-06, "loss": 1.2428, "step": 190640 }, { "epoch": 8.71, "learning_rate": 6.485422673806582e-06, "loss": 1.4026, "step": 190650 }, { "epoch": 8.71, "learning_rate": 6.483134239553298e-06, "loss": 1.308, "step": 190660 }, { "epoch": 8.71, "learning_rate": 6.480845805300014e-06, "loss": 1.4533, "step": 190670 }, { "epoch": 8.71, "learning_rate": 6.47855737104673e-06, "loss": 1.1797, "step": 190680 }, { "epoch": 8.71, "learning_rate": 6.476268936793446e-06, "loss": 1.4167, "step": 190690 }, { "epoch": 8.71, "learning_rate": 6.473980502540162e-06, "loss": 1.3375, "step": 190700 }, { "epoch": 8.71, "learning_rate": 6.471692068286879e-06, "loss": 1.3354, "step": 190710 }, { "epoch": 8.71, "learning_rate": 6.469403634033594e-06, "loss": 1.3524, "step": 190720 }, { "epoch": 8.71, "learning_rate": 6.4671151997803105e-06, "loss": 1.3175, "step": 190730 }, { "epoch": 8.71, "learning_rate": 6.464826765527026e-06, "loss": 1.4995, "step": 190740 }, { "epoch": 8.71, "learning_rate": 6.462538331273743e-06, "loss": 1.4448, "step": 190750 }, { "epoch": 8.71, "learning_rate": 6.46024989702046e-06, "loss": 1.3715, "step": 190760 }, { "epoch": 8.71, "learning_rate": 6.457961462767175e-06, "loss": 1.2911, "step": 190770 }, { "epoch": 8.71, "learning_rate": 6.4556730285138905e-06, "loss": 1.3273, "step": 190780 }, { "epoch": 8.71, "learning_rate": 6.453384594260607e-06, "loss": 1.3499, "step": 190790 }, { "epoch": 8.71, "learning_rate": 6.451096160007324e-06, "loss": 1.3388, "step": 190800 }, { "epoch": 8.71, "learning_rate": 6.44880772575404e-06, "loss": 1.3394, "step": 190810 }, { "epoch": 8.71, "learning_rate": 6.446519291500755e-06, "loss": 1.339, "step": 190820 }, { "epoch": 8.71, "learning_rate": 6.444230857247471e-06, "loss": 1.3697, "step": 190830 }, { "epoch": 8.71, "learning_rate": 6.441942422994188e-06, "loss": 1.3604, "step": 190840 }, { "epoch": 8.71, "learning_rate": 6.439653988740904e-06, "loss": 1.3575, "step": 190850 }, { "epoch": 8.72, "learning_rate": 6.4373655544876205e-06, "loss": 1.4538, "step": 190860 }, { "epoch": 8.72, "learning_rate": 6.4350771202343355e-06, "loss": 1.4506, "step": 190870 }, { "epoch": 8.72, "learning_rate": 6.432788685981052e-06, "loss": 1.5351, "step": 190880 }, { "epoch": 8.72, "learning_rate": 6.430500251727768e-06, "loss": 1.2524, "step": 190890 }, { "epoch": 8.72, "learning_rate": 6.428211817474485e-06, "loss": 1.3006, "step": 190900 }, { "epoch": 8.72, "learning_rate": 6.425923383221201e-06, "loss": 1.2955, "step": 190910 }, { "epoch": 8.72, "learning_rate": 6.423634948967916e-06, "loss": 1.2975, "step": 190920 }, { "epoch": 8.72, "learning_rate": 6.421346514714632e-06, "loss": 1.3821, "step": 190930 }, { "epoch": 8.72, "learning_rate": 6.419058080461349e-06, "loss": 1.3802, "step": 190940 }, { "epoch": 8.72, "learning_rate": 6.416769646208065e-06, "loss": 1.3334, "step": 190950 }, { "epoch": 8.72, "learning_rate": 6.414481211954781e-06, "loss": 1.2809, "step": 190960 }, { "epoch": 8.72, "learning_rate": 6.412192777701496e-06, "loss": 1.1641, "step": 190970 }, { "epoch": 8.72, "learning_rate": 6.409904343448213e-06, "loss": 1.3771, "step": 190980 }, { "epoch": 8.72, "learning_rate": 6.407615909194929e-06, "loss": 1.3067, "step": 190990 }, { "epoch": 8.72, "learning_rate": 6.4053274749416455e-06, "loss": 1.3664, "step": 191000 }, { "epoch": 8.72, "learning_rate": 6.403039040688362e-06, "loss": 1.416, "step": 191010 }, { "epoch": 8.72, "learning_rate": 6.400750606435077e-06, "loss": 1.4785, "step": 191020 }, { "epoch": 8.72, "learning_rate": 6.398462172181793e-06, "loss": 1.3954, "step": 191030 }, { "epoch": 8.72, "learning_rate": 6.39617373792851e-06, "loss": 1.2712, "step": 191040 }, { "epoch": 8.72, "learning_rate": 6.393885303675226e-06, "loss": 1.3549, "step": 191050 }, { "epoch": 8.72, "learning_rate": 6.391596869421942e-06, "loss": 1.3098, "step": 191060 }, { "epoch": 8.72, "learning_rate": 6.389308435168657e-06, "loss": 1.2375, "step": 191070 }, { "epoch": 8.73, "learning_rate": 6.387020000915374e-06, "loss": 1.4512, "step": 191080 }, { "epoch": 8.73, "learning_rate": 6.3847315666620905e-06, "loss": 1.21, "step": 191090 }, { "epoch": 8.73, "learning_rate": 6.382443132408806e-06, "loss": 1.4368, "step": 191100 }, { "epoch": 8.73, "learning_rate": 6.380154698155523e-06, "loss": 1.2981, "step": 191110 }, { "epoch": 8.73, "learning_rate": 6.377866263902238e-06, "loss": 1.3393, "step": 191120 }, { "epoch": 8.73, "learning_rate": 6.375577829648955e-06, "loss": 1.3939, "step": 191130 }, { "epoch": 8.73, "learning_rate": 6.3732893953956705e-06, "loss": 1.4462, "step": 191140 }, { "epoch": 8.73, "learning_rate": 6.371000961142387e-06, "loss": 1.4013, "step": 191150 }, { "epoch": 8.73, "learning_rate": 6.368712526889104e-06, "loss": 1.4207, "step": 191160 }, { "epoch": 8.73, "learning_rate": 6.366424092635819e-06, "loss": 1.3458, "step": 191170 }, { "epoch": 8.73, "learning_rate": 6.364135658382535e-06, "loss": 1.3913, "step": 191180 }, { "epoch": 8.73, "learning_rate": 6.361847224129251e-06, "loss": 1.4544, "step": 191190 }, { "epoch": 8.73, "learning_rate": 6.359558789875968e-06, "loss": 1.2691, "step": 191200 }, { "epoch": 8.73, "learning_rate": 6.357270355622683e-06, "loss": 1.4231, "step": 191210 }, { "epoch": 8.73, "learning_rate": 6.354981921369399e-06, "loss": 1.463, "step": 191220 }, { "epoch": 8.73, "learning_rate": 6.3526934871161155e-06, "loss": 1.2123, "step": 191230 }, { "epoch": 8.73, "learning_rate": 6.350405052862832e-06, "loss": 1.4214, "step": 191240 }, { "epoch": 8.73, "learning_rate": 6.348116618609548e-06, "loss": 1.3678, "step": 191250 }, { "epoch": 8.73, "learning_rate": 6.345828184356263e-06, "loss": 1.4226, "step": 191260 }, { "epoch": 8.73, "learning_rate": 6.34353975010298e-06, "loss": 1.4077, "step": 191270 }, { "epoch": 8.73, "learning_rate": 6.3412513158496955e-06, "loss": 1.2814, "step": 191280 }, { "epoch": 8.73, "learning_rate": 6.338962881596412e-06, "loss": 1.6127, "step": 191290 }, { "epoch": 8.74, "learning_rate": 6.336674447343129e-06, "loss": 1.4108, "step": 191300 }, { "epoch": 8.74, "learning_rate": 6.334386013089844e-06, "loss": 1.2647, "step": 191310 }, { "epoch": 8.74, "learning_rate": 6.33209757883656e-06, "loss": 1.3836, "step": 191320 }, { "epoch": 8.74, "learning_rate": 6.329809144583276e-06, "loss": 1.4934, "step": 191330 }, { "epoch": 8.74, "learning_rate": 6.327520710329993e-06, "loss": 1.2379, "step": 191340 }, { "epoch": 8.74, "learning_rate": 6.325232276076709e-06, "loss": 1.2649, "step": 191350 }, { "epoch": 8.74, "learning_rate": 6.322943841823424e-06, "loss": 1.4142, "step": 191360 }, { "epoch": 8.74, "learning_rate": 6.3206554075701404e-06, "loss": 1.3254, "step": 191370 }, { "epoch": 8.74, "learning_rate": 6.318366973316857e-06, "loss": 1.303, "step": 191380 }, { "epoch": 8.74, "learning_rate": 6.316078539063573e-06, "loss": 1.4715, "step": 191390 }, { "epoch": 8.74, "learning_rate": 6.31379010481029e-06, "loss": 1.3051, "step": 191400 }, { "epoch": 8.74, "learning_rate": 6.311501670557005e-06, "loss": 1.4791, "step": 191410 }, { "epoch": 8.74, "learning_rate": 6.309213236303721e-06, "loss": 1.366, "step": 191420 }, { "epoch": 8.74, "learning_rate": 6.306924802050437e-06, "loss": 1.4091, "step": 191430 }, { "epoch": 8.74, "learning_rate": 6.304636367797154e-06, "loss": 1.281, "step": 191440 }, { "epoch": 8.74, "learning_rate": 6.3023479335438704e-06, "loss": 1.4123, "step": 191450 }, { "epoch": 8.74, "learning_rate": 6.3000594992905854e-06, "loss": 1.3204, "step": 191460 }, { "epoch": 8.74, "learning_rate": 6.297771065037301e-06, "loss": 1.4448, "step": 191470 }, { "epoch": 8.74, "learning_rate": 6.295482630784018e-06, "loss": 1.4286, "step": 191480 }, { "epoch": 8.74, "learning_rate": 6.293194196530735e-06, "loss": 1.2631, "step": 191490 }, { "epoch": 8.74, "learning_rate": 6.2909057622774504e-06, "loss": 1.3787, "step": 191500 }, { "epoch": 8.74, "learning_rate": 6.288617328024165e-06, "loss": 1.3408, "step": 191510 }, { "epoch": 8.75, "learning_rate": 6.286328893770882e-06, "loss": 1.3835, "step": 191520 }, { "epoch": 8.75, "learning_rate": 6.284040459517599e-06, "loss": 1.3553, "step": 191530 }, { "epoch": 8.75, "learning_rate": 6.281752025264315e-06, "loss": 1.4496, "step": 191540 }, { "epoch": 8.75, "learning_rate": 6.279463591011031e-06, "loss": 1.5858, "step": 191550 }, { "epoch": 8.75, "learning_rate": 6.277175156757746e-06, "loss": 1.4581, "step": 191560 }, { "epoch": 8.75, "learning_rate": 6.274886722504462e-06, "loss": 1.4903, "step": 191570 }, { "epoch": 8.75, "learning_rate": 6.272598288251179e-06, "loss": 1.4902, "step": 191580 }, { "epoch": 8.75, "learning_rate": 6.2703098539978954e-06, "loss": 1.4544, "step": 191590 }, { "epoch": 8.75, "learning_rate": 6.268021419744611e-06, "loss": 1.314, "step": 191600 }, { "epoch": 8.75, "learning_rate": 6.265732985491326e-06, "loss": 1.4399, "step": 191610 }, { "epoch": 8.75, "learning_rate": 6.263444551238043e-06, "loss": 1.2651, "step": 191620 }, { "epoch": 8.75, "learning_rate": 6.26115611698476e-06, "loss": 1.4433, "step": 191630 }, { "epoch": 8.75, "learning_rate": 6.258867682731475e-06, "loss": 1.3159, "step": 191640 }, { "epoch": 8.75, "learning_rate": 6.256579248478192e-06, "loss": 1.1948, "step": 191650 }, { "epoch": 8.75, "learning_rate": 6.254290814224907e-06, "loss": 1.4286, "step": 191660 }, { "epoch": 8.75, "learning_rate": 6.252002379971624e-06, "loss": 1.6264, "step": 191670 }, { "epoch": 8.75, "learning_rate": 6.2497139457183396e-06, "loss": 1.4598, "step": 191680 }, { "epoch": 8.75, "learning_rate": 6.247425511465056e-06, "loss": 1.4792, "step": 191690 }, { "epoch": 8.75, "learning_rate": 6.245137077211772e-06, "loss": 1.3801, "step": 191700 }, { "epoch": 8.75, "learning_rate": 6.242848642958488e-06, "loss": 1.4811, "step": 191710 }, { "epoch": 8.75, "learning_rate": 6.240560208705204e-06, "loss": 1.4524, "step": 191720 }, { "epoch": 8.75, "learning_rate": 6.23827177445192e-06, "loss": 1.2839, "step": 191730 }, { "epoch": 8.76, "learning_rate": 6.235983340198637e-06, "loss": 1.3319, "step": 191740 }, { "epoch": 8.76, "learning_rate": 6.233694905945352e-06, "loss": 1.3766, "step": 191750 }, { "epoch": 8.76, "learning_rate": 6.231406471692069e-06, "loss": 1.361, "step": 191760 }, { "epoch": 8.76, "learning_rate": 6.2291180374387846e-06, "loss": 1.2951, "step": 191770 }, { "epoch": 8.76, "learning_rate": 6.226829603185501e-06, "loss": 1.3377, "step": 191780 }, { "epoch": 8.76, "learning_rate": 6.224541168932216e-06, "loss": 1.4594, "step": 191790 }, { "epoch": 8.76, "learning_rate": 6.222252734678933e-06, "loss": 1.2717, "step": 191800 }, { "epoch": 8.76, "learning_rate": 6.2199643004256496e-06, "loss": 1.4633, "step": 191810 }, { "epoch": 8.76, "learning_rate": 6.217675866172365e-06, "loss": 1.4137, "step": 191820 }, { "epoch": 8.76, "learning_rate": 6.215387431919081e-06, "loss": 1.4672, "step": 191830 }, { "epoch": 8.76, "learning_rate": 6.213098997665797e-06, "loss": 1.3699, "step": 191840 }, { "epoch": 8.76, "learning_rate": 6.210810563412514e-06, "loss": 1.1966, "step": 191850 }, { "epoch": 8.76, "learning_rate": 6.2085221291592295e-06, "loss": 1.4124, "step": 191860 }, { "epoch": 8.76, "learning_rate": 6.206233694905945e-06, "loss": 1.435, "step": 191870 }, { "epoch": 8.76, "learning_rate": 6.203945260652662e-06, "loss": 1.2796, "step": 191880 }, { "epoch": 8.76, "learning_rate": 6.201656826399378e-06, "loss": 1.3486, "step": 191890 }, { "epoch": 8.76, "learning_rate": 6.199368392146094e-06, "loss": 1.3416, "step": 191900 }, { "epoch": 8.76, "learning_rate": 6.19707995789281e-06, "loss": 1.4136, "step": 191910 }, { "epoch": 8.76, "learning_rate": 6.194791523639526e-06, "loss": 1.2241, "step": 191920 }, { "epoch": 8.76, "learning_rate": 6.192503089386242e-06, "loss": 1.2774, "step": 191930 }, { "epoch": 8.76, "learning_rate": 6.190214655132958e-06, "loss": 1.2805, "step": 191940 }, { "epoch": 8.76, "learning_rate": 6.1879262208796745e-06, "loss": 1.3678, "step": 191950 }, { "epoch": 8.77, "learning_rate": 6.185637786626391e-06, "loss": 1.3797, "step": 191960 }, { "epoch": 8.77, "learning_rate": 6.183349352373106e-06, "loss": 1.448, "step": 191970 }, { "epoch": 8.77, "learning_rate": 6.181060918119823e-06, "loss": 1.3746, "step": 191980 }, { "epoch": 8.77, "learning_rate": 6.178772483866539e-06, "loss": 1.2243, "step": 191990 }, { "epoch": 8.77, "learning_rate": 6.1764840496132545e-06, "loss": 1.5162, "step": 192000 }, { "epoch": 8.77, "learning_rate": 6.174195615359971e-06, "loss": 1.1751, "step": 192010 }, { "epoch": 8.77, "learning_rate": 6.171907181106687e-06, "loss": 1.4293, "step": 192020 }, { "epoch": 8.77, "learning_rate": 6.169618746853404e-06, "loss": 1.2733, "step": 192030 }, { "epoch": 8.77, "learning_rate": 6.167330312600119e-06, "loss": 1.3267, "step": 192040 }, { "epoch": 8.77, "learning_rate": 6.165041878346835e-06, "loss": 1.4558, "step": 192050 }, { "epoch": 8.77, "learning_rate": 6.162753444093552e-06, "loss": 1.2554, "step": 192060 }, { "epoch": 8.77, "learning_rate": 6.160465009840268e-06, "loss": 1.3585, "step": 192070 }, { "epoch": 8.77, "learning_rate": 6.158176575586984e-06, "loss": 1.2426, "step": 192080 }, { "epoch": 8.77, "learning_rate": 6.1558881413336995e-06, "loss": 1.4176, "step": 192090 }, { "epoch": 8.77, "learning_rate": 6.153599707080416e-06, "loss": 1.4232, "step": 192100 }, { "epoch": 8.77, "learning_rate": 6.151311272827132e-06, "loss": 1.2594, "step": 192110 }, { "epoch": 8.77, "learning_rate": 6.149022838573848e-06, "loss": 1.2817, "step": 192120 }, { "epoch": 8.77, "learning_rate": 6.1467344043205645e-06, "loss": 1.3988, "step": 192130 }, { "epoch": 8.77, "learning_rate": 6.14444597006728e-06, "loss": 1.3886, "step": 192140 }, { "epoch": 8.77, "learning_rate": 6.142157535813996e-06, "loss": 1.222, "step": 192150 }, { "epoch": 8.77, "learning_rate": 6.139869101560713e-06, "loss": 1.5243, "step": 192160 }, { "epoch": 8.77, "learning_rate": 6.137580667307429e-06, "loss": 1.3596, "step": 192170 }, { "epoch": 8.78, "learning_rate": 6.1352922330541445e-06, "loss": 1.3501, "step": 192180 }, { "epoch": 8.78, "learning_rate": 6.13300379880086e-06, "loss": 1.387, "step": 192190 }, { "epoch": 8.78, "learning_rate": 6.130715364547577e-06, "loss": 1.2763, "step": 192200 }, { "epoch": 8.78, "learning_rate": 6.128426930294293e-06, "loss": 1.3315, "step": 192210 }, { "epoch": 8.78, "learning_rate": 6.126138496041009e-06, "loss": 1.4683, "step": 192220 }, { "epoch": 8.78, "learning_rate": 6.123850061787725e-06, "loss": 1.3434, "step": 192230 }, { "epoch": 8.78, "learning_rate": 6.121561627534441e-06, "loss": 1.2457, "step": 192240 }, { "epoch": 8.78, "learning_rate": 6.119273193281158e-06, "loss": 1.264, "step": 192250 }, { "epoch": 8.78, "learning_rate": 6.116984759027873e-06, "loss": 1.422, "step": 192260 }, { "epoch": 8.78, "learning_rate": 6.1146963247745895e-06, "loss": 1.3675, "step": 192270 }, { "epoch": 8.78, "learning_rate": 6.112407890521306e-06, "loss": 1.3652, "step": 192280 }, { "epoch": 8.78, "learning_rate": 6.110119456268021e-06, "loss": 1.3944, "step": 192290 }, { "epoch": 8.78, "learning_rate": 6.107831022014738e-06, "loss": 1.4125, "step": 192300 }, { "epoch": 8.78, "learning_rate": 6.105542587761454e-06, "loss": 1.3137, "step": 192310 }, { "epoch": 8.78, "learning_rate": 6.10325415350817e-06, "loss": 1.3047, "step": 192320 }, { "epoch": 8.78, "learning_rate": 6.100965719254886e-06, "loss": 1.3606, "step": 192330 }, { "epoch": 8.78, "learning_rate": 6.098677285001602e-06, "loss": 1.4037, "step": 192340 }, { "epoch": 8.78, "learning_rate": 6.096388850748319e-06, "loss": 1.3442, "step": 192350 }, { "epoch": 8.78, "learning_rate": 6.0941004164950345e-06, "loss": 1.4339, "step": 192360 }, { "epoch": 8.78, "learning_rate": 6.09181198224175e-06, "loss": 1.296, "step": 192370 }, { "epoch": 8.78, "learning_rate": 6.089523547988467e-06, "loss": 1.512, "step": 192380 }, { "epoch": 8.79, "learning_rate": 6.087235113735183e-06, "loss": 1.3758, "step": 192390 }, { "epoch": 8.79, "learning_rate": 6.084946679481899e-06, "loss": 1.3796, "step": 192400 }, { "epoch": 8.79, "learning_rate": 6.0826582452286145e-06, "loss": 1.2102, "step": 192410 }, { "epoch": 8.79, "learning_rate": 6.080369810975331e-06, "loss": 1.3144, "step": 192420 }, { "epoch": 8.79, "learning_rate": 6.078081376722047e-06, "loss": 1.302, "step": 192430 }, { "epoch": 8.79, "learning_rate": 6.075792942468763e-06, "loss": 1.506, "step": 192440 }, { "epoch": 8.79, "learning_rate": 6.0735045082154795e-06, "loss": 1.408, "step": 192450 }, { "epoch": 8.79, "learning_rate": 6.071216073962195e-06, "loss": 1.3606, "step": 192460 }, { "epoch": 8.79, "learning_rate": 6.068927639708911e-06, "loss": 1.3036, "step": 192470 }, { "epoch": 8.79, "learning_rate": 6.066639205455628e-06, "loss": 1.3439, "step": 192480 }, { "epoch": 8.79, "learning_rate": 6.064350771202344e-06, "loss": 1.5459, "step": 192490 }, { "epoch": 8.79, "learning_rate": 6.06206233694906e-06, "loss": 1.3697, "step": 192500 }, { "epoch": 8.79, "learning_rate": 6.059773902695775e-06, "loss": 1.2828, "step": 192510 }, { "epoch": 8.79, "learning_rate": 6.057485468442492e-06, "loss": 1.3352, "step": 192520 }, { "epoch": 8.79, "learning_rate": 6.055197034189209e-06, "loss": 1.3491, "step": 192530 }, { "epoch": 8.79, "learning_rate": 6.0529085999359245e-06, "loss": 1.348, "step": 192540 }, { "epoch": 8.79, "learning_rate": 6.05062016568264e-06, "loss": 1.2622, "step": 192550 }, { "epoch": 8.79, "learning_rate": 6.048331731429356e-06, "loss": 1.4316, "step": 192560 }, { "epoch": 8.79, "learning_rate": 6.046043297176073e-06, "loss": 1.311, "step": 192570 }, { "epoch": 8.79, "learning_rate": 6.043754862922789e-06, "loss": 1.5669, "step": 192580 }, { "epoch": 8.79, "learning_rate": 6.0414664286695044e-06, "loss": 1.5102, "step": 192590 }, { "epoch": 8.79, "learning_rate": 6.039177994416221e-06, "loss": 1.3338, "step": 192600 }, { "epoch": 8.8, "learning_rate": 6.036889560162937e-06, "loss": 1.2911, "step": 192610 }, { "epoch": 8.8, "learning_rate": 6.034601125909653e-06, "loss": 1.2642, "step": 192620 }, { "epoch": 8.8, "learning_rate": 6.032312691656369e-06, "loss": 1.2617, "step": 192630 }, { "epoch": 8.8, "learning_rate": 6.030024257403085e-06, "loss": 1.3864, "step": 192640 }, { "epoch": 8.8, "learning_rate": 6.027735823149801e-06, "loss": 1.364, "step": 192650 }, { "epoch": 8.8, "learning_rate": 6.025447388896517e-06, "loss": 1.307, "step": 192660 }, { "epoch": 8.8, "learning_rate": 6.023158954643234e-06, "loss": 1.5486, "step": 192670 }, { "epoch": 8.8, "learning_rate": 6.0208705203899494e-06, "loss": 1.2451, "step": 192680 }, { "epoch": 8.8, "learning_rate": 6.018582086136665e-06, "loss": 1.453, "step": 192690 }, { "epoch": 8.8, "learning_rate": 6.016293651883382e-06, "loss": 1.3705, "step": 192700 }, { "epoch": 8.8, "learning_rate": 6.014005217630098e-06, "loss": 1.4219, "step": 192710 }, { "epoch": 8.8, "learning_rate": 6.011716783376814e-06, "loss": 1.2705, "step": 192720 }, { "epoch": 8.8, "learning_rate": 6.009428349123529e-06, "loss": 1.4189, "step": 192730 }, { "epoch": 8.8, "learning_rate": 6.007139914870246e-06, "loss": 1.3826, "step": 192740 }, { "epoch": 8.8, "learning_rate": 6.004851480616963e-06, "loss": 1.4142, "step": 192750 }, { "epoch": 8.8, "learning_rate": 6.002563046363678e-06, "loss": 1.3017, "step": 192760 }, { "epoch": 8.8, "learning_rate": 6.000274612110394e-06, "loss": 1.2787, "step": 192770 }, { "epoch": 8.8, "learning_rate": 5.99798617785711e-06, "loss": 1.3292, "step": 192780 }, { "epoch": 8.8, "learning_rate": 5.995697743603827e-06, "loss": 1.425, "step": 192790 }, { "epoch": 8.8, "learning_rate": 5.993409309350543e-06, "loss": 1.2055, "step": 192800 }, { "epoch": 8.8, "learning_rate": 5.991120875097259e-06, "loss": 1.3994, "step": 192810 }, { "epoch": 8.8, "learning_rate": 5.988832440843975e-06, "loss": 1.3379, "step": 192820 }, { "epoch": 8.81, "learning_rate": 5.986544006590691e-06, "loss": 1.3917, "step": 192830 }, { "epoch": 8.81, "learning_rate": 5.984255572337407e-06, "loss": 1.3651, "step": 192840 }, { "epoch": 8.81, "learning_rate": 5.981967138084124e-06, "loss": 1.4534, "step": 192850 }, { "epoch": 8.81, "learning_rate": 5.979678703830839e-06, "loss": 1.4844, "step": 192860 }, { "epoch": 8.81, "learning_rate": 5.977390269577555e-06, "loss": 1.2501, "step": 192870 }, { "epoch": 8.81, "learning_rate": 5.975101835324271e-06, "loss": 1.3179, "step": 192880 }, { "epoch": 8.81, "learning_rate": 5.972813401070988e-06, "loss": 1.4645, "step": 192890 }, { "epoch": 8.81, "learning_rate": 5.9705249668177036e-06, "loss": 1.5714, "step": 192900 }, { "epoch": 8.81, "learning_rate": 5.968236532564419e-06, "loss": 1.3061, "step": 192910 }, { "epoch": 8.81, "learning_rate": 5.965948098311136e-06, "loss": 1.476, "step": 192920 }, { "epoch": 8.81, "learning_rate": 5.963659664057852e-06, "loss": 1.3013, "step": 192930 }, { "epoch": 8.81, "learning_rate": 5.961371229804568e-06, "loss": 1.4417, "step": 192940 }, { "epoch": 8.81, "learning_rate": 5.959082795551284e-06, "loss": 1.4896, "step": 192950 }, { "epoch": 8.81, "learning_rate": 5.956794361298e-06, "loss": 1.223, "step": 192960 }, { "epoch": 8.81, "learning_rate": 5.954505927044717e-06, "loss": 1.321, "step": 192970 }, { "epoch": 8.81, "learning_rate": 5.952217492791432e-06, "loss": 1.3955, "step": 192980 }, { "epoch": 8.81, "learning_rate": 5.9499290585381486e-06, "loss": 1.3613, "step": 192990 }, { "epoch": 8.81, "learning_rate": 5.947640624284864e-06, "loss": 1.2802, "step": 193000 }, { "epoch": 8.81, "learning_rate": 5.94535219003158e-06, "loss": 1.3859, "step": 193010 }, { "epoch": 8.81, "learning_rate": 5.943063755778297e-06, "loss": 1.3185, "step": 193020 }, { "epoch": 8.81, "learning_rate": 5.940775321525013e-06, "loss": 1.2936, "step": 193030 }, { "epoch": 8.81, "learning_rate": 5.938486887271729e-06, "loss": 1.4442, "step": 193040 }, { "epoch": 8.82, "learning_rate": 5.936198453018444e-06, "loss": 1.2815, "step": 193050 }, { "epoch": 8.82, "learning_rate": 5.933910018765161e-06, "loss": 1.26, "step": 193060 }, { "epoch": 8.82, "learning_rate": 5.931621584511878e-06, "loss": 1.1883, "step": 193070 }, { "epoch": 8.82, "learning_rate": 5.9293331502585935e-06, "loss": 1.2376, "step": 193080 }, { "epoch": 8.82, "learning_rate": 5.927044716005309e-06, "loss": 1.2759, "step": 193090 }, { "epoch": 8.82, "learning_rate": 5.924756281752025e-06, "loss": 1.3135, "step": 193100 }, { "epoch": 8.82, "learning_rate": 5.922467847498742e-06, "loss": 1.3078, "step": 193110 }, { "epoch": 8.82, "learning_rate": 5.920179413245458e-06, "loss": 1.4088, "step": 193120 }, { "epoch": 8.82, "learning_rate": 5.9178909789921735e-06, "loss": 1.3926, "step": 193130 }, { "epoch": 8.82, "learning_rate": 5.91560254473889e-06, "loss": 1.3409, "step": 193140 }, { "epoch": 8.82, "learning_rate": 5.913314110485606e-06, "loss": 1.4319, "step": 193150 }, { "epoch": 8.82, "learning_rate": 5.911025676232322e-06, "loss": 1.4334, "step": 193160 }, { "epoch": 8.82, "learning_rate": 5.9087372419790385e-06, "loss": 1.2838, "step": 193170 }, { "epoch": 8.82, "learning_rate": 5.906448807725754e-06, "loss": 1.3192, "step": 193180 }, { "epoch": 8.82, "learning_rate": 5.90416037347247e-06, "loss": 1.3232, "step": 193190 }, { "epoch": 8.82, "learning_rate": 5.901871939219186e-06, "loss": 1.3387, "step": 193200 }, { "epoch": 8.82, "learning_rate": 5.899583504965903e-06, "loss": 1.2351, "step": 193210 }, { "epoch": 8.82, "learning_rate": 5.897295070712619e-06, "loss": 1.1664, "step": 193220 }, { "epoch": 8.82, "learning_rate": 5.895006636459334e-06, "loss": 1.4378, "step": 193230 }, { "epoch": 8.82, "learning_rate": 5.892718202206051e-06, "loss": 1.4171, "step": 193240 }, { "epoch": 8.82, "learning_rate": 5.890429767952767e-06, "loss": 1.4374, "step": 193250 }, { "epoch": 8.82, "learning_rate": 5.8881413336994835e-06, "loss": 1.4736, "step": 193260 }, { "epoch": 8.83, "learning_rate": 5.885852899446199e-06, "loss": 1.3655, "step": 193270 }, { "epoch": 8.83, "learning_rate": 5.883564465192915e-06, "loss": 1.4231, "step": 193280 }, { "epoch": 8.83, "learning_rate": 5.881276030939632e-06, "loss": 1.2963, "step": 193290 }, { "epoch": 8.83, "learning_rate": 5.878987596686347e-06, "loss": 1.3429, "step": 193300 }, { "epoch": 8.83, "learning_rate": 5.8766991624330635e-06, "loss": 1.2732, "step": 193310 }, { "epoch": 8.83, "learning_rate": 5.87441072817978e-06, "loss": 1.3065, "step": 193320 }, { "epoch": 8.83, "learning_rate": 5.872122293926496e-06, "loss": 1.3241, "step": 193330 }, { "epoch": 8.83, "learning_rate": 5.869833859673212e-06, "loss": 1.2658, "step": 193340 }, { "epoch": 8.83, "learning_rate": 5.867545425419928e-06, "loss": 1.4454, "step": 193350 }, { "epoch": 8.83, "learning_rate": 5.865256991166644e-06, "loss": 1.4125, "step": 193360 }, { "epoch": 8.83, "learning_rate": 5.86296855691336e-06, "loss": 1.3142, "step": 193370 }, { "epoch": 8.83, "learning_rate": 5.860680122660076e-06, "loss": 1.3874, "step": 193380 }, { "epoch": 8.83, "learning_rate": 5.858391688406793e-06, "loss": 1.2848, "step": 193390 }, { "epoch": 8.83, "learning_rate": 5.8561032541535085e-06, "loss": 1.293, "step": 193400 }, { "epoch": 8.83, "learning_rate": 5.853814819900224e-06, "loss": 1.4546, "step": 193410 }, { "epoch": 8.83, "learning_rate": 5.85152638564694e-06, "loss": 1.302, "step": 193420 }, { "epoch": 8.83, "learning_rate": 5.849237951393657e-06, "loss": 1.3363, "step": 193430 }, { "epoch": 8.83, "learning_rate": 5.846949517140373e-06, "loss": 1.2959, "step": 193440 }, { "epoch": 8.83, "learning_rate": 5.8446610828870885e-06, "loss": 1.2246, "step": 193450 }, { "epoch": 8.83, "learning_rate": 5.842372648633805e-06, "loss": 1.1819, "step": 193460 }, { "epoch": 8.83, "learning_rate": 5.840084214380521e-06, "loss": 1.441, "step": 193470 }, { "epoch": 8.83, "learning_rate": 5.837795780127237e-06, "loss": 1.2169, "step": 193480 }, { "epoch": 8.84, "learning_rate": 5.8355073458739535e-06, "loss": 1.5089, "step": 193490 }, { "epoch": 8.84, "learning_rate": 5.833218911620669e-06, "loss": 1.3109, "step": 193500 }, { "epoch": 8.84, "learning_rate": 5.830930477367386e-06, "loss": 1.2028, "step": 193510 }, { "epoch": 8.84, "learning_rate": 5.828642043114101e-06, "loss": 1.277, "step": 193520 }, { "epoch": 8.84, "learning_rate": 5.826353608860818e-06, "loss": 1.3104, "step": 193530 }, { "epoch": 8.84, "learning_rate": 5.824065174607534e-06, "loss": 1.4118, "step": 193540 }, { "epoch": 8.84, "learning_rate": 5.82177674035425e-06, "loss": 1.2173, "step": 193550 }, { "epoch": 8.84, "learning_rate": 5.819488306100966e-06, "loss": 1.4023, "step": 193560 }, { "epoch": 8.84, "learning_rate": 5.817199871847682e-06, "loss": 1.3634, "step": 193570 }, { "epoch": 8.84, "learning_rate": 5.8149114375943985e-06, "loss": 1.4612, "step": 193580 }, { "epoch": 8.84, "learning_rate": 5.812623003341114e-06, "loss": 1.3823, "step": 193590 }, { "epoch": 8.84, "learning_rate": 5.81033456908783e-06, "loss": 1.3961, "step": 193600 }, { "epoch": 8.84, "learning_rate": 5.808046134834547e-06, "loss": 1.3533, "step": 193610 }, { "epoch": 8.84, "learning_rate": 5.805757700581263e-06, "loss": 1.3965, "step": 193620 }, { "epoch": 8.84, "learning_rate": 5.8034692663279785e-06, "loss": 1.2038, "step": 193630 }, { "epoch": 8.84, "learning_rate": 5.801180832074695e-06, "loss": 1.3557, "step": 193640 }, { "epoch": 8.84, "learning_rate": 5.798892397821411e-06, "loss": 1.3956, "step": 193650 }, { "epoch": 8.84, "learning_rate": 5.796603963568127e-06, "loss": 1.4105, "step": 193660 }, { "epoch": 8.84, "learning_rate": 5.794315529314843e-06, "loss": 1.2821, "step": 193670 }, { "epoch": 8.84, "learning_rate": 5.792027095061559e-06, "loss": 1.4159, "step": 193680 }, { "epoch": 8.84, "learning_rate": 5.789738660808276e-06, "loss": 1.3939, "step": 193690 }, { "epoch": 8.84, "learning_rate": 5.787450226554991e-06, "loss": 1.2958, "step": 193700 }, { "epoch": 8.85, "learning_rate": 5.785161792301708e-06, "loss": 1.421, "step": 193710 }, { "epoch": 8.85, "learning_rate": 5.7828733580484235e-06, "loss": 1.2461, "step": 193720 }, { "epoch": 8.85, "learning_rate": 5.780584923795139e-06, "loss": 1.4281, "step": 193730 }, { "epoch": 8.85, "learning_rate": 5.778296489541856e-06, "loss": 1.3849, "step": 193740 }, { "epoch": 8.85, "learning_rate": 5.776008055288572e-06, "loss": 1.4919, "step": 193750 }, { "epoch": 8.85, "learning_rate": 5.7737196210352885e-06, "loss": 1.4192, "step": 193760 }, { "epoch": 8.85, "learning_rate": 5.7714311867820034e-06, "loss": 1.501, "step": 193770 }, { "epoch": 8.85, "learning_rate": 5.76914275252872e-06, "loss": 1.3716, "step": 193780 }, { "epoch": 8.85, "learning_rate": 5.766854318275437e-06, "loss": 1.1991, "step": 193790 }, { "epoch": 8.85, "learning_rate": 5.764565884022153e-06, "loss": 1.2375, "step": 193800 }, { "epoch": 8.85, "learning_rate": 5.7622774497688684e-06, "loss": 1.2149, "step": 193810 }, { "epoch": 8.85, "learning_rate": 5.759989015515584e-06, "loss": 1.459, "step": 193820 }, { "epoch": 8.85, "learning_rate": 5.757700581262301e-06, "loss": 1.31, "step": 193830 }, { "epoch": 8.85, "learning_rate": 5.755412147009017e-06, "loss": 1.3169, "step": 193840 }, { "epoch": 8.85, "learning_rate": 5.753123712755733e-06, "loss": 1.3026, "step": 193850 }, { "epoch": 8.85, "learning_rate": 5.750835278502449e-06, "loss": 1.2939, "step": 193860 }, { "epoch": 8.85, "learning_rate": 5.748546844249165e-06, "loss": 1.2725, "step": 193870 }, { "epoch": 8.85, "learning_rate": 5.746258409995881e-06, "loss": 1.2156, "step": 193880 }, { "epoch": 8.85, "learning_rate": 5.743969975742597e-06, "loss": 1.3295, "step": 193890 }, { "epoch": 8.85, "learning_rate": 5.7416815414893134e-06, "loss": 1.3453, "step": 193900 }, { "epoch": 8.85, "learning_rate": 5.739393107236029e-06, "loss": 1.352, "step": 193910 }, { "epoch": 8.85, "learning_rate": 5.737104672982745e-06, "loss": 1.316, "step": 193920 }, { "epoch": 8.86, "learning_rate": 5.734816238729462e-06, "loss": 1.2983, "step": 193930 }, { "epoch": 8.86, "learning_rate": 5.732527804476178e-06, "loss": 1.2247, "step": 193940 }, { "epoch": 8.86, "learning_rate": 5.730239370222893e-06, "loss": 1.3407, "step": 193950 }, { "epoch": 8.86, "learning_rate": 5.72795093596961e-06, "loss": 1.304, "step": 193960 }, { "epoch": 8.86, "learning_rate": 5.725662501716326e-06, "loss": 1.4647, "step": 193970 }, { "epoch": 8.86, "learning_rate": 5.723374067463043e-06, "loss": 1.2491, "step": 193980 }, { "epoch": 8.86, "learning_rate": 5.721085633209758e-06, "loss": 1.2429, "step": 193990 }, { "epoch": 8.86, "learning_rate": 5.718797198956474e-06, "loss": 1.3085, "step": 194000 }, { "epoch": 8.86, "learning_rate": 5.716508764703191e-06, "loss": 1.5189, "step": 194010 }, { "epoch": 8.86, "learning_rate": 5.714220330449906e-06, "loss": 1.422, "step": 194020 }, { "epoch": 8.86, "learning_rate": 5.711931896196623e-06, "loss": 1.2261, "step": 194030 }, { "epoch": 8.86, "learning_rate": 5.709643461943338e-06, "loss": 1.3142, "step": 194040 }, { "epoch": 8.86, "learning_rate": 5.707355027690055e-06, "loss": 1.3706, "step": 194050 }, { "epoch": 8.86, "learning_rate": 5.705066593436771e-06, "loss": 1.3133, "step": 194060 }, { "epoch": 8.86, "learning_rate": 5.702778159183487e-06, "loss": 1.3807, "step": 194070 }, { "epoch": 8.86, "learning_rate": 5.700489724930203e-06, "loss": 1.2005, "step": 194080 }, { "epoch": 8.86, "learning_rate": 5.698201290676919e-06, "loss": 1.3915, "step": 194090 }, { "epoch": 8.86, "learning_rate": 5.695912856423635e-06, "loss": 1.3546, "step": 194100 }, { "epoch": 8.86, "learning_rate": 5.693624422170352e-06, "loss": 1.4227, "step": 194110 }, { "epoch": 8.86, "learning_rate": 5.6913359879170676e-06, "loss": 1.3223, "step": 194120 }, { "epoch": 8.86, "learning_rate": 5.689047553663783e-06, "loss": 1.2617, "step": 194130 }, { "epoch": 8.86, "learning_rate": 5.686759119410499e-06, "loss": 1.5158, "step": 194140 }, { "epoch": 8.87, "learning_rate": 5.684470685157216e-06, "loss": 1.136, "step": 194150 }, { "epoch": 8.87, "learning_rate": 5.682182250903932e-06, "loss": 1.3727, "step": 194160 }, { "epoch": 8.87, "learning_rate": 5.6798938166506476e-06, "loss": 1.4345, "step": 194170 }, { "epoch": 8.87, "learning_rate": 5.677605382397364e-06, "loss": 1.2983, "step": 194180 }, { "epoch": 8.87, "learning_rate": 5.67531694814408e-06, "loss": 1.5403, "step": 194190 }, { "epoch": 8.87, "learning_rate": 5.673028513890796e-06, "loss": 1.3252, "step": 194200 }, { "epoch": 8.87, "learning_rate": 5.670740079637512e-06, "loss": 1.3099, "step": 194210 }, { "epoch": 8.87, "learning_rate": 5.668451645384228e-06, "loss": 1.464, "step": 194220 }, { "epoch": 8.87, "learning_rate": 5.666163211130945e-06, "loss": 1.3021, "step": 194230 }, { "epoch": 8.87, "learning_rate": 5.66387477687766e-06, "loss": 1.2427, "step": 194240 }, { "epoch": 8.87, "learning_rate": 5.661586342624377e-06, "loss": 1.4502, "step": 194250 }, { "epoch": 8.87, "learning_rate": 5.6592979083710925e-06, "loss": 1.3214, "step": 194260 }, { "epoch": 8.87, "learning_rate": 5.657009474117809e-06, "loss": 1.3753, "step": 194270 }, { "epoch": 8.87, "learning_rate": 5.654721039864525e-06, "loss": 1.3592, "step": 194280 }, { "epoch": 8.87, "learning_rate": 5.652432605611241e-06, "loss": 1.3061, "step": 194290 }, { "epoch": 8.87, "learning_rate": 5.6501441713579576e-06, "loss": 1.372, "step": 194300 }, { "epoch": 8.87, "learning_rate": 5.6478557371046725e-06, "loss": 1.3772, "step": 194310 }, { "epoch": 8.87, "learning_rate": 5.645567302851389e-06, "loss": 1.4255, "step": 194320 }, { "epoch": 8.87, "learning_rate": 5.643278868598106e-06, "loss": 1.3908, "step": 194330 }, { "epoch": 8.87, "learning_rate": 5.640990434344822e-06, "loss": 1.3438, "step": 194340 }, { "epoch": 8.87, "learning_rate": 5.6387020000915375e-06, "loss": 1.3633, "step": 194350 }, { "epoch": 8.87, "learning_rate": 5.636413565838253e-06, "loss": 1.3056, "step": 194360 }, { "epoch": 8.88, "learning_rate": 5.63412513158497e-06, "loss": 1.4296, "step": 194370 }, { "epoch": 8.88, "learning_rate": 5.631836697331686e-06, "loss": 1.3895, "step": 194380 }, { "epoch": 8.88, "learning_rate": 5.629548263078402e-06, "loss": 1.4067, "step": 194390 }, { "epoch": 8.88, "learning_rate": 5.627259828825118e-06, "loss": 1.4345, "step": 194400 }, { "epoch": 8.88, "learning_rate": 5.624971394571834e-06, "loss": 1.5166, "step": 194410 }, { "epoch": 8.88, "learning_rate": 5.62268296031855e-06, "loss": 1.3514, "step": 194420 }, { "epoch": 8.88, "learning_rate": 5.620394526065267e-06, "loss": 1.4205, "step": 194430 }, { "epoch": 8.88, "learning_rate": 5.6181060918119825e-06, "loss": 1.3652, "step": 194440 }, { "epoch": 8.88, "learning_rate": 5.615817657558698e-06, "loss": 1.4031, "step": 194450 }, { "epoch": 8.88, "learning_rate": 5.613529223305414e-06, "loss": 1.2796, "step": 194460 }, { "epoch": 8.88, "learning_rate": 5.611240789052131e-06, "loss": 1.5049, "step": 194470 }, { "epoch": 8.88, "learning_rate": 5.6089523547988475e-06, "loss": 1.4159, "step": 194480 }, { "epoch": 8.88, "learning_rate": 5.6066639205455625e-06, "loss": 1.3953, "step": 194490 }, { "epoch": 8.88, "learning_rate": 5.604375486292279e-06, "loss": 1.3595, "step": 194500 }, { "epoch": 8.88, "learning_rate": 5.602087052038995e-06, "loss": 1.3491, "step": 194510 }, { "epoch": 8.88, "learning_rate": 5.599798617785712e-06, "loss": 1.2272, "step": 194520 }, { "epoch": 8.88, "learning_rate": 5.5975101835324275e-06, "loss": 1.3859, "step": 194530 }, { "epoch": 8.88, "learning_rate": 5.595221749279143e-06, "loss": 1.4763, "step": 194540 }, { "epoch": 8.88, "learning_rate": 5.59293331502586e-06, "loss": 1.3684, "step": 194550 }, { "epoch": 8.88, "learning_rate": 5.590644880772576e-06, "loss": 1.3467, "step": 194560 }, { "epoch": 8.88, "learning_rate": 5.588356446519292e-06, "loss": 1.281, "step": 194570 }, { "epoch": 8.89, "learning_rate": 5.586068012266008e-06, "loss": 1.3723, "step": 194580 }, { "epoch": 8.89, "learning_rate": 5.583779578012724e-06, "loss": 1.4741, "step": 194590 }, { "epoch": 8.89, "learning_rate": 5.58149114375944e-06, "loss": 1.4049, "step": 194600 }, { "epoch": 8.89, "learning_rate": 5.579202709506156e-06, "loss": 1.4201, "step": 194610 }, { "epoch": 8.89, "learning_rate": 5.5769142752528725e-06, "loss": 1.393, "step": 194620 }, { "epoch": 8.89, "learning_rate": 5.574625840999588e-06, "loss": 1.4538, "step": 194630 }, { "epoch": 8.89, "learning_rate": 5.572337406746304e-06, "loss": 1.2277, "step": 194640 }, { "epoch": 8.89, "learning_rate": 5.570048972493021e-06, "loss": 1.1891, "step": 194650 }, { "epoch": 8.89, "learning_rate": 5.567760538239737e-06, "loss": 1.3469, "step": 194660 }, { "epoch": 8.89, "learning_rate": 5.5654721039864525e-06, "loss": 1.2517, "step": 194670 }, { "epoch": 8.89, "learning_rate": 5.563183669733168e-06, "loss": 1.3367, "step": 194680 }, { "epoch": 8.89, "learning_rate": 5.560895235479885e-06, "loss": 1.1986, "step": 194690 }, { "epoch": 8.89, "learning_rate": 5.558606801226602e-06, "loss": 1.3938, "step": 194700 }, { "epoch": 8.89, "learning_rate": 5.556318366973317e-06, "loss": 1.2148, "step": 194710 }, { "epoch": 8.89, "learning_rate": 5.554029932720033e-06, "loss": 1.3148, "step": 194720 }, { "epoch": 8.89, "learning_rate": 5.551741498466749e-06, "loss": 1.3943, "step": 194730 }, { "epoch": 8.89, "learning_rate": 5.549453064213465e-06, "loss": 1.4627, "step": 194740 }, { "epoch": 8.89, "learning_rate": 5.547164629960182e-06, "loss": 1.329, "step": 194750 }, { "epoch": 8.89, "learning_rate": 5.5448761957068975e-06, "loss": 1.4091, "step": 194760 }, { "epoch": 8.89, "learning_rate": 5.542587761453614e-06, "loss": 1.3371, "step": 194770 }, { "epoch": 8.89, "learning_rate": 5.540299327200329e-06, "loss": 1.2967, "step": 194780 }, { "epoch": 8.89, "learning_rate": 5.538010892947046e-06, "loss": 1.3187, "step": 194790 }, { "epoch": 8.9, "learning_rate": 5.5357224586937625e-06, "loss": 1.2356, "step": 194800 }, { "epoch": 8.9, "learning_rate": 5.533434024440478e-06, "loss": 1.4385, "step": 194810 }, { "epoch": 8.9, "learning_rate": 5.531145590187194e-06, "loss": 1.394, "step": 194820 }, { "epoch": 8.9, "learning_rate": 5.52885715593391e-06, "loss": 1.2947, "step": 194830 }, { "epoch": 8.9, "learning_rate": 5.526568721680627e-06, "loss": 1.2935, "step": 194840 }, { "epoch": 8.9, "learning_rate": 5.5242802874273425e-06, "loss": 1.3426, "step": 194850 }, { "epoch": 8.9, "learning_rate": 5.521991853174058e-06, "loss": 1.3699, "step": 194860 }, { "epoch": 8.9, "learning_rate": 5.519703418920775e-06, "loss": 1.2737, "step": 194870 }, { "epoch": 8.9, "learning_rate": 5.517414984667491e-06, "loss": 1.4122, "step": 194880 }, { "epoch": 8.9, "learning_rate": 5.515126550414207e-06, "loss": 1.3569, "step": 194890 }, { "epoch": 8.9, "learning_rate": 5.512838116160923e-06, "loss": 1.4633, "step": 194900 }, { "epoch": 8.9, "learning_rate": 5.510549681907639e-06, "loss": 1.2702, "step": 194910 }, { "epoch": 8.9, "learning_rate": 5.508261247654355e-06, "loss": 1.3303, "step": 194920 }, { "epoch": 8.9, "learning_rate": 5.505972813401071e-06, "loss": 1.4282, "step": 194930 }, { "epoch": 8.9, "learning_rate": 5.5036843791477875e-06, "loss": 1.3244, "step": 194940 }, { "epoch": 8.9, "learning_rate": 5.501395944894504e-06, "loss": 1.5765, "step": 194950 }, { "epoch": 8.9, "learning_rate": 5.499107510641219e-06, "loss": 1.3559, "step": 194960 }, { "epoch": 8.9, "learning_rate": 5.496819076387936e-06, "loss": 1.5545, "step": 194970 }, { "epoch": 8.9, "learning_rate": 5.494530642134652e-06, "loss": 1.4263, "step": 194980 }, { "epoch": 8.9, "learning_rate": 5.492242207881368e-06, "loss": 1.3312, "step": 194990 }, { "epoch": 8.9, "learning_rate": 5.489953773628084e-06, "loss": 1.4059, "step": 195000 }, { "epoch": 8.9, "learning_rate": 5.4876653393748e-06, "loss": 1.3827, "step": 195010 }, { "epoch": 8.91, "learning_rate": 5.485376905121517e-06, "loss": 1.4043, "step": 195020 }, { "epoch": 8.91, "learning_rate": 5.483088470868232e-06, "loss": 1.3142, "step": 195030 }, { "epoch": 8.91, "learning_rate": 5.480800036614948e-06, "loss": 1.2109, "step": 195040 }, { "epoch": 8.91, "learning_rate": 5.478511602361664e-06, "loss": 1.3119, "step": 195050 }, { "epoch": 8.91, "learning_rate": 5.476223168108381e-06, "loss": 1.3363, "step": 195060 }, { "epoch": 8.91, "learning_rate": 5.473934733855097e-06, "loss": 1.3329, "step": 195070 }, { "epoch": 8.91, "learning_rate": 5.4716462996018124e-06, "loss": 1.4905, "step": 195080 }, { "epoch": 8.91, "learning_rate": 5.469357865348529e-06, "loss": 1.2815, "step": 195090 }, { "epoch": 8.91, "learning_rate": 5.467069431095245e-06, "loss": 1.4072, "step": 195100 }, { "epoch": 8.91, "learning_rate": 5.464780996841961e-06, "loss": 1.3365, "step": 195110 }, { "epoch": 8.91, "learning_rate": 5.4624925625886774e-06, "loss": 1.2722, "step": 195120 }, { "epoch": 8.91, "learning_rate": 5.460204128335393e-06, "loss": 1.4872, "step": 195130 }, { "epoch": 8.91, "learning_rate": 5.457915694082109e-06, "loss": 1.2687, "step": 195140 }, { "epoch": 8.91, "learning_rate": 5.455627259828825e-06, "loss": 1.3843, "step": 195150 }, { "epoch": 8.91, "learning_rate": 5.453338825575542e-06, "loss": 1.3686, "step": 195160 }, { "epoch": 8.91, "learning_rate": 5.4510503913222574e-06, "loss": 1.3308, "step": 195170 }, { "epoch": 8.91, "learning_rate": 5.448761957068973e-06, "loss": 1.3314, "step": 195180 }, { "epoch": 8.91, "learning_rate": 5.44647352281569e-06, "loss": 1.354, "step": 195190 }, { "epoch": 8.91, "learning_rate": 5.444185088562406e-06, "loss": 1.4014, "step": 195200 }, { "epoch": 8.91, "learning_rate": 5.441896654309122e-06, "loss": 1.2874, "step": 195210 }, { "epoch": 8.91, "learning_rate": 5.439608220055838e-06, "loss": 1.2447, "step": 195220 }, { "epoch": 8.91, "learning_rate": 5.437319785802554e-06, "loss": 1.3538, "step": 195230 }, { "epoch": 8.92, "learning_rate": 5.435031351549271e-06, "loss": 1.3847, "step": 195240 }, { "epoch": 8.92, "learning_rate": 5.432742917295986e-06, "loss": 1.414, "step": 195250 }, { "epoch": 8.92, "learning_rate": 5.430454483042702e-06, "loss": 1.3673, "step": 195260 }, { "epoch": 8.92, "learning_rate": 5.428166048789419e-06, "loss": 1.2816, "step": 195270 }, { "epoch": 8.92, "learning_rate": 5.425877614536135e-06, "loss": 1.329, "step": 195280 }, { "epoch": 8.92, "learning_rate": 5.423589180282851e-06, "loss": 1.435, "step": 195290 }, { "epoch": 8.92, "learning_rate": 5.4213007460295666e-06, "loss": 1.3197, "step": 195300 }, { "epoch": 8.92, "learning_rate": 5.419012311776283e-06, "loss": 1.206, "step": 195310 }, { "epoch": 8.92, "learning_rate": 5.416723877522999e-06, "loss": 1.2423, "step": 195320 }, { "epoch": 8.92, "learning_rate": 5.414435443269715e-06, "loss": 1.2237, "step": 195330 }, { "epoch": 8.92, "learning_rate": 5.4121470090164316e-06, "loss": 1.2324, "step": 195340 }, { "epoch": 8.92, "learning_rate": 5.409858574763147e-06, "loss": 1.4225, "step": 195350 }, { "epoch": 8.92, "learning_rate": 5.407570140509863e-06, "loss": 1.5027, "step": 195360 }, { "epoch": 8.92, "learning_rate": 5.40528170625658e-06, "loss": 1.3285, "step": 195370 }, { "epoch": 8.92, "learning_rate": 5.402993272003296e-06, "loss": 1.2468, "step": 195380 }, { "epoch": 8.92, "learning_rate": 5.4007048377500116e-06, "loss": 1.3499, "step": 195390 }, { "epoch": 8.92, "learning_rate": 5.398416403496727e-06, "loss": 1.2841, "step": 195400 }, { "epoch": 8.92, "learning_rate": 5.396127969243444e-06, "loss": 1.3965, "step": 195410 }, { "epoch": 8.92, "learning_rate": 5.39383953499016e-06, "loss": 1.1853, "step": 195420 }, { "epoch": 8.92, "learning_rate": 5.391551100736876e-06, "loss": 1.2338, "step": 195430 }, { "epoch": 8.92, "learning_rate": 5.389262666483592e-06, "loss": 1.2981, "step": 195440 }, { "epoch": 8.92, "learning_rate": 5.386974232230308e-06, "loss": 1.2362, "step": 195450 }, { "epoch": 8.93, "learning_rate": 5.384685797977024e-06, "loss": 1.4338, "step": 195460 }, { "epoch": 8.93, "learning_rate": 5.38239736372374e-06, "loss": 1.2601, "step": 195470 }, { "epoch": 8.93, "learning_rate": 5.3801089294704565e-06, "loss": 1.2014, "step": 195480 }, { "epoch": 8.93, "learning_rate": 5.377820495217173e-06, "loss": 1.2498, "step": 195490 }, { "epoch": 8.93, "learning_rate": 5.375532060963888e-06, "loss": 1.4064, "step": 195500 }, { "epoch": 8.93, "learning_rate": 5.373243626710605e-06, "loss": 1.3945, "step": 195510 }, { "epoch": 8.93, "learning_rate": 5.370955192457321e-06, "loss": 1.2995, "step": 195520 }, { "epoch": 8.93, "learning_rate": 5.368666758204037e-06, "loss": 1.3299, "step": 195530 }, { "epoch": 8.93, "learning_rate": 5.366378323950753e-06, "loss": 1.4274, "step": 195540 }, { "epoch": 8.93, "learning_rate": 5.364089889697469e-06, "loss": 1.429, "step": 195550 }, { "epoch": 8.93, "learning_rate": 5.361801455444186e-06, "loss": 1.3469, "step": 195560 }, { "epoch": 8.93, "learning_rate": 5.3595130211909015e-06, "loss": 1.5532, "step": 195570 }, { "epoch": 8.93, "learning_rate": 5.357224586937617e-06, "loss": 1.4919, "step": 195580 }, { "epoch": 8.93, "learning_rate": 5.354936152684334e-06, "loss": 1.3256, "step": 195590 }, { "epoch": 8.93, "learning_rate": 5.35264771843105e-06, "loss": 1.2631, "step": 195600 }, { "epoch": 8.93, "learning_rate": 5.350359284177766e-06, "loss": 1.2641, "step": 195610 }, { "epoch": 8.93, "learning_rate": 5.3480708499244815e-06, "loss": 1.2363, "step": 195620 }, { "epoch": 8.93, "learning_rate": 5.345782415671198e-06, "loss": 1.346, "step": 195630 }, { "epoch": 8.93, "learning_rate": 5.343493981417914e-06, "loss": 1.3561, "step": 195640 }, { "epoch": 8.93, "learning_rate": 5.34120554716463e-06, "loss": 1.3245, "step": 195650 }, { "epoch": 8.93, "learning_rate": 5.3389171129113465e-06, "loss": 1.5448, "step": 195660 }, { "epoch": 8.93, "learning_rate": 5.336628678658062e-06, "loss": 1.2665, "step": 195670 }, { "epoch": 8.94, "learning_rate": 5.334340244404778e-06, "loss": 1.444, "step": 195680 }, { "epoch": 8.94, "learning_rate": 5.332051810151495e-06, "loss": 1.3875, "step": 195690 }, { "epoch": 8.94, "learning_rate": 5.329763375898211e-06, "loss": 1.4113, "step": 195700 }, { "epoch": 8.94, "learning_rate": 5.327474941644927e-06, "loss": 1.2857, "step": 195710 }, { "epoch": 8.94, "learning_rate": 5.325186507391642e-06, "loss": 1.3562, "step": 195720 }, { "epoch": 8.94, "learning_rate": 5.322898073138359e-06, "loss": 1.4259, "step": 195730 }, { "epoch": 8.94, "learning_rate": 5.320609638885076e-06, "loss": 1.2646, "step": 195740 }, { "epoch": 8.94, "learning_rate": 5.318321204631791e-06, "loss": 1.3243, "step": 195750 }, { "epoch": 8.94, "learning_rate": 5.316032770378507e-06, "loss": 1.2889, "step": 195760 }, { "epoch": 8.94, "learning_rate": 5.313744336125223e-06, "loss": 1.4083, "step": 195770 }, { "epoch": 8.94, "learning_rate": 5.31145590187194e-06, "loss": 1.2686, "step": 195780 }, { "epoch": 8.94, "learning_rate": 5.309167467618656e-06, "loss": 1.3277, "step": 195790 }, { "epoch": 8.94, "learning_rate": 5.3068790333653715e-06, "loss": 1.3342, "step": 195800 }, { "epoch": 8.94, "learning_rate": 5.304590599112088e-06, "loss": 1.1565, "step": 195810 }, { "epoch": 8.94, "learning_rate": 5.302302164858804e-06, "loss": 1.5372, "step": 195820 }, { "epoch": 8.94, "learning_rate": 5.30001373060552e-06, "loss": 1.3996, "step": 195830 }, { "epoch": 8.94, "learning_rate": 5.297725296352236e-06, "loss": 1.515, "step": 195840 }, { "epoch": 8.94, "learning_rate": 5.295436862098952e-06, "loss": 1.3988, "step": 195850 }, { "epoch": 8.94, "learning_rate": 5.293148427845668e-06, "loss": 1.3774, "step": 195860 }, { "epoch": 8.94, "learning_rate": 5.290859993592384e-06, "loss": 1.404, "step": 195870 }, { "epoch": 8.94, "learning_rate": 5.288571559339101e-06, "loss": 1.3324, "step": 195880 }, { "epoch": 8.94, "learning_rate": 5.2862831250858165e-06, "loss": 1.4611, "step": 195890 }, { "epoch": 8.95, "learning_rate": 5.283994690832532e-06, "loss": 1.2446, "step": 195900 }, { "epoch": 8.95, "learning_rate": 5.281706256579249e-06, "loss": 1.3701, "step": 195910 }, { "epoch": 8.95, "learning_rate": 5.279417822325965e-06, "loss": 1.486, "step": 195920 }, { "epoch": 8.95, "learning_rate": 5.277129388072681e-06, "loss": 1.3894, "step": 195930 }, { "epoch": 8.95, "learning_rate": 5.2748409538193965e-06, "loss": 1.3945, "step": 195940 }, { "epoch": 8.95, "learning_rate": 5.272552519566113e-06, "loss": 1.2857, "step": 195950 }, { "epoch": 8.95, "learning_rate": 5.27026408531283e-06, "loss": 1.2605, "step": 195960 }, { "epoch": 8.95, "learning_rate": 5.267975651059545e-06, "loss": 1.3261, "step": 195970 }, { "epoch": 8.95, "learning_rate": 5.2656872168062615e-06, "loss": 1.3087, "step": 195980 }, { "epoch": 8.95, "learning_rate": 5.263398782552977e-06, "loss": 1.4045, "step": 195990 }, { "epoch": 8.95, "learning_rate": 5.261110348299694e-06, "loss": 1.3342, "step": 196000 }, { "epoch": 8.95, "learning_rate": 5.25882191404641e-06, "loss": 1.3604, "step": 196010 }, { "epoch": 8.95, "learning_rate": 5.256533479793126e-06, "loss": 1.3995, "step": 196020 }, { "epoch": 8.95, "learning_rate": 5.254245045539842e-06, "loss": 1.4756, "step": 196030 }, { "epoch": 8.95, "learning_rate": 5.251956611286558e-06, "loss": 1.2755, "step": 196040 }, { "epoch": 8.95, "learning_rate": 5.249668177033274e-06, "loss": 1.3113, "step": 196050 }, { "epoch": 8.95, "learning_rate": 5.247379742779991e-06, "loss": 1.3167, "step": 196060 }, { "epoch": 8.95, "learning_rate": 5.2450913085267065e-06, "loss": 1.4113, "step": 196070 }, { "epoch": 8.95, "learning_rate": 5.242802874273422e-06, "loss": 1.3501, "step": 196080 }, { "epoch": 8.95, "learning_rate": 5.240514440020138e-06, "loss": 1.3826, "step": 196090 }, { "epoch": 8.95, "learning_rate": 5.238226005766855e-06, "loss": 1.2528, "step": 196100 }, { "epoch": 8.95, "learning_rate": 5.235937571513571e-06, "loss": 1.3977, "step": 196110 }, { "epoch": 8.96, "learning_rate": 5.2336491372602865e-06, "loss": 1.4311, "step": 196120 }, { "epoch": 8.96, "learning_rate": 5.231360703007003e-06, "loss": 1.3401, "step": 196130 }, { "epoch": 8.96, "learning_rate": 5.229072268753719e-06, "loss": 1.4228, "step": 196140 }, { "epoch": 8.96, "learning_rate": 5.226783834500435e-06, "loss": 1.3793, "step": 196150 }, { "epoch": 8.96, "learning_rate": 5.2244954002471515e-06, "loss": 1.2138, "step": 196160 }, { "epoch": 8.96, "learning_rate": 5.222206965993867e-06, "loss": 1.3496, "step": 196170 }, { "epoch": 8.96, "learning_rate": 5.219918531740583e-06, "loss": 1.1563, "step": 196180 }, { "epoch": 8.96, "learning_rate": 5.217630097487299e-06, "loss": 1.2697, "step": 196190 }, { "epoch": 8.96, "learning_rate": 5.215341663234016e-06, "loss": 1.1481, "step": 196200 }, { "epoch": 8.96, "learning_rate": 5.213053228980732e-06, "loss": 1.3925, "step": 196210 }, { "epoch": 8.96, "learning_rate": 5.210764794727447e-06, "loss": 1.2867, "step": 196220 }, { "epoch": 8.96, "learning_rate": 5.208476360474164e-06, "loss": 1.3189, "step": 196230 }, { "epoch": 8.96, "learning_rate": 5.20618792622088e-06, "loss": 1.3407, "step": 196240 }, { "epoch": 8.96, "learning_rate": 5.2038994919675965e-06, "loss": 1.4165, "step": 196250 }, { "epoch": 8.96, "learning_rate": 5.2016110577143114e-06, "loss": 1.4411, "step": 196260 }, { "epoch": 8.96, "learning_rate": 5.199322623461028e-06, "loss": 1.2462, "step": 196270 }, { "epoch": 8.96, "learning_rate": 5.197034189207745e-06, "loss": 1.3297, "step": 196280 }, { "epoch": 8.96, "learning_rate": 5.194745754954461e-06, "loss": 1.3533, "step": 196290 }, { "epoch": 8.96, "learning_rate": 5.1924573207011764e-06, "loss": 1.4001, "step": 196300 }, { "epoch": 8.96, "learning_rate": 5.190168886447892e-06, "loss": 1.3811, "step": 196310 }, { "epoch": 8.96, "learning_rate": 5.187880452194609e-06, "loss": 1.2652, "step": 196320 }, { "epoch": 8.96, "learning_rate": 5.185592017941325e-06, "loss": 1.2785, "step": 196330 }, { "epoch": 8.97, "learning_rate": 5.183303583688041e-06, "loss": 1.3777, "step": 196340 }, { "epoch": 8.97, "learning_rate": 5.181015149434757e-06, "loss": 1.3589, "step": 196350 }, { "epoch": 8.97, "learning_rate": 5.178726715181473e-06, "loss": 1.3827, "step": 196360 }, { "epoch": 8.97, "learning_rate": 5.176438280928189e-06, "loss": 1.3983, "step": 196370 }, { "epoch": 8.97, "learning_rate": 5.174149846674906e-06, "loss": 1.3525, "step": 196380 }, { "epoch": 8.97, "learning_rate": 5.1718614124216214e-06, "loss": 1.5639, "step": 196390 }, { "epoch": 8.97, "learning_rate": 5.169572978168337e-06, "loss": 1.1843, "step": 196400 }, { "epoch": 8.97, "learning_rate": 5.167284543915053e-06, "loss": 1.3322, "step": 196410 }, { "epoch": 8.97, "learning_rate": 5.16499610966177e-06, "loss": 1.3807, "step": 196420 }, { "epoch": 8.97, "learning_rate": 5.1627076754084864e-06, "loss": 1.4827, "step": 196430 }, { "epoch": 8.97, "learning_rate": 5.160419241155201e-06, "loss": 1.2403, "step": 196440 }, { "epoch": 8.97, "learning_rate": 5.158130806901918e-06, "loss": 1.366, "step": 196450 }, { "epoch": 8.97, "learning_rate": 5.155842372648634e-06, "loss": 1.4239, "step": 196460 }, { "epoch": 8.97, "learning_rate": 5.153553938395351e-06, "loss": 1.2908, "step": 196470 }, { "epoch": 8.97, "learning_rate": 5.151265504142066e-06, "loss": 1.3872, "step": 196480 }, { "epoch": 8.97, "learning_rate": 5.148977069888782e-06, "loss": 1.339, "step": 196490 }, { "epoch": 8.97, "learning_rate": 5.146688635635499e-06, "loss": 1.5133, "step": 196500 }, { "epoch": 8.97, "learning_rate": 5.144400201382214e-06, "loss": 1.3938, "step": 196510 }, { "epoch": 8.97, "learning_rate": 5.1421117671289306e-06, "loss": 1.4018, "step": 196520 }, { "epoch": 8.97, "learning_rate": 5.139823332875647e-06, "loss": 1.3677, "step": 196530 }, { "epoch": 8.97, "learning_rate": 5.137534898622363e-06, "loss": 1.2568, "step": 196540 }, { "epoch": 8.97, "learning_rate": 5.135246464369079e-06, "loss": 1.3867, "step": 196550 }, { "epoch": 8.98, "learning_rate": 5.132958030115795e-06, "loss": 1.2956, "step": 196560 }, { "epoch": 8.98, "learning_rate": 5.130669595862511e-06, "loss": 1.2854, "step": 196570 }, { "epoch": 8.98, "learning_rate": 5.128381161609227e-06, "loss": 1.3984, "step": 196580 }, { "epoch": 8.98, "learning_rate": 5.126092727355943e-06, "loss": 1.3697, "step": 196590 }, { "epoch": 8.98, "learning_rate": 5.12380429310266e-06, "loss": 1.4475, "step": 196600 }, { "epoch": 8.98, "learning_rate": 5.1215158588493756e-06, "loss": 1.2567, "step": 196610 }, { "epoch": 8.98, "learning_rate": 5.119227424596091e-06, "loss": 1.3845, "step": 196620 }, { "epoch": 8.98, "learning_rate": 5.116938990342807e-06, "loss": 1.2819, "step": 196630 }, { "epoch": 8.98, "learning_rate": 5.114650556089524e-06, "loss": 1.303, "step": 196640 }, { "epoch": 8.98, "learning_rate": 5.11236212183624e-06, "loss": 1.4131, "step": 196650 }, { "epoch": 8.98, "learning_rate": 5.1100736875829555e-06, "loss": 1.4304, "step": 196660 }, { "epoch": 8.98, "learning_rate": 5.107785253329672e-06, "loss": 1.1349, "step": 196670 }, { "epoch": 8.98, "learning_rate": 5.105496819076388e-06, "loss": 1.4132, "step": 196680 }, { "epoch": 8.98, "learning_rate": 5.103208384823104e-06, "loss": 1.4396, "step": 196690 }, { "epoch": 8.98, "learning_rate": 5.1009199505698206e-06, "loss": 1.2975, "step": 196700 }, { "epoch": 8.98, "learning_rate": 5.098631516316536e-06, "loss": 1.407, "step": 196710 }, { "epoch": 8.98, "learning_rate": 5.096343082063253e-06, "loss": 1.3121, "step": 196720 }, { "epoch": 8.98, "learning_rate": 5.094054647809968e-06, "loss": 1.3957, "step": 196730 }, { "epoch": 8.98, "learning_rate": 5.091766213556685e-06, "loss": 1.3509, "step": 196740 }, { "epoch": 8.98, "learning_rate": 5.089477779303401e-06, "loss": 1.2444, "step": 196750 }, { "epoch": 8.98, "learning_rate": 5.087189345050117e-06, "loss": 1.3767, "step": 196760 }, { "epoch": 8.99, "learning_rate": 5.084900910796833e-06, "loss": 1.3471, "step": 196770 }, { "epoch": 8.99, "learning_rate": 5.082612476543549e-06, "loss": 1.227, "step": 196780 }, { "epoch": 8.99, "learning_rate": 5.0803240422902655e-06, "loss": 1.3657, "step": 196790 }, { "epoch": 8.99, "learning_rate": 5.078035608036981e-06, "loss": 1.4011, "step": 196800 }, { "epoch": 8.99, "learning_rate": 5.075747173783697e-06, "loss": 1.3184, "step": 196810 }, { "epoch": 8.99, "learning_rate": 5.073458739530414e-06, "loss": 1.2924, "step": 196820 }, { "epoch": 8.99, "learning_rate": 5.07117030527713e-06, "loss": 1.3555, "step": 196830 }, { "epoch": 8.99, "learning_rate": 5.0688818710238455e-06, "loss": 1.3076, "step": 196840 }, { "epoch": 8.99, "learning_rate": 5.066593436770562e-06, "loss": 1.3241, "step": 196850 }, { "epoch": 8.99, "learning_rate": 5.064305002517278e-06, "loss": 1.3686, "step": 196860 }, { "epoch": 8.99, "learning_rate": 5.062016568263994e-06, "loss": 1.3923, "step": 196870 }, { "epoch": 8.99, "learning_rate": 5.05972813401071e-06, "loss": 1.3063, "step": 196880 }, { "epoch": 8.99, "learning_rate": 5.057439699757426e-06, "loss": 1.3366, "step": 196890 }, { "epoch": 8.99, "learning_rate": 5.055151265504143e-06, "loss": 1.4139, "step": 196900 }, { "epoch": 8.99, "learning_rate": 5.052862831250858e-06, "loss": 1.4177, "step": 196910 }, { "epoch": 8.99, "learning_rate": 5.050574396997575e-06, "loss": 1.4423, "step": 196920 }, { "epoch": 8.99, "learning_rate": 5.0482859627442905e-06, "loss": 1.2179, "step": 196930 }, { "epoch": 8.99, "learning_rate": 5.045997528491006e-06, "loss": 1.2944, "step": 196940 }, { "epoch": 8.99, "learning_rate": 5.043709094237723e-06, "loss": 1.3851, "step": 196950 }, { "epoch": 8.99, "learning_rate": 5.041420659984439e-06, "loss": 1.4265, "step": 196960 }, { "epoch": 8.99, "learning_rate": 5.0391322257311555e-06, "loss": 1.3408, "step": 196970 }, { "epoch": 8.99, "learning_rate": 5.0368437914778705e-06, "loss": 1.2308, "step": 196980 }, { "epoch": 9.0, "learning_rate": 5.034555357224587e-06, "loss": 1.3267, "step": 196990 }, { "epoch": 9.0, "learning_rate": 5.032266922971304e-06, "loss": 1.3621, "step": 197000 }, { "epoch": 9.0, "learning_rate": 5.02997848871802e-06, "loss": 1.3115, "step": 197010 }, { "epoch": 9.0, "learning_rate": 5.0276900544647355e-06, "loss": 1.243, "step": 197020 }, { "epoch": 9.0, "learning_rate": 5.025401620211451e-06, "loss": 1.3984, "step": 197030 }, { "epoch": 9.0, "learning_rate": 5.023113185958168e-06, "loss": 1.2844, "step": 197040 }, { "epoch": 9.0, "learning_rate": 5.020824751704884e-06, "loss": 1.246, "step": 197050 }, { "epoch": 9.0, "learning_rate": 5.0185363174516e-06, "loss": 1.3748, "step": 197060 }, { "epoch": 9.0, "learning_rate": 5.016247883198316e-06, "loss": 1.4183, "step": 197070 }, { "epoch": 9.0, "learning_rate": 5.013959448945032e-06, "loss": 1.2999, "step": 197080 }, { "epoch": 9.0, "learning_rate": 5.011671014691748e-06, "loss": 1.4092, "step": 197090 }, { "epoch": 9.0, "eval_cer": 0.6745296162722318, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.3152623176574707, "eval_runtime": 2640.4649, "eval_samples_per_second": 4.003, "eval_steps_per_second": 2.002, "eval_wer": 0.9927152317880795, "step": 197097 }, { "epoch": 9.0, "learning_rate": 5.009382580438464e-06, "loss": 1.4402, "step": 197100 }, { "epoch": 9.0, "learning_rate": 5.0070941461851805e-06, "loss": 1.3704, "step": 197110 }, { "epoch": 9.0, "learning_rate": 5.004805711931896e-06, "loss": 1.5727, "step": 197120 }, { "epoch": 9.0, "learning_rate": 5.002517277678612e-06, "loss": 1.3135, "step": 197130 }, { "epoch": 9.0, "learning_rate": 5.000228843425329e-06, "loss": 1.3914, "step": 197140 }, { "epoch": 9.0, "learning_rate": 4.997940409172045e-06, "loss": 1.3852, "step": 197150 }, { "epoch": 9.0, "learning_rate": 4.9956519749187605e-06, "loss": 1.2143, "step": 197160 }, { "epoch": 9.0, "learning_rate": 4.993363540665477e-06, "loss": 1.4837, "step": 197170 }, { "epoch": 9.0, "learning_rate": 4.991075106412193e-06, "loss": 1.3475, "step": 197180 }, { "epoch": 9.0, "learning_rate": 4.98878667215891e-06, "loss": 1.5026, "step": 197190 }, { "epoch": 9.0, "learning_rate": 4.986498237905625e-06, "loss": 1.1931, "step": 197200 }, { "epoch": 9.01, "learning_rate": 4.984209803652341e-06, "loss": 1.3425, "step": 197210 }, { "epoch": 9.01, "learning_rate": 4.981921369399058e-06, "loss": 1.3729, "step": 197220 }, { "epoch": 9.01, "learning_rate": 4.979632935145773e-06, "loss": 1.4018, "step": 197230 }, { "epoch": 9.01, "learning_rate": 4.97734450089249e-06, "loss": 1.3708, "step": 197240 }, { "epoch": 9.01, "learning_rate": 4.9750560666392055e-06, "loss": 1.2825, "step": 197250 }, { "epoch": 9.01, "learning_rate": 4.972767632385922e-06, "loss": 1.2153, "step": 197260 }, { "epoch": 9.01, "learning_rate": 4.970479198132638e-06, "loss": 1.4154, "step": 197270 }, { "epoch": 9.01, "learning_rate": 4.968190763879354e-06, "loss": 1.2281, "step": 197280 }, { "epoch": 9.01, "learning_rate": 4.9659023296260705e-06, "loss": 1.2775, "step": 197290 }, { "epoch": 9.01, "learning_rate": 4.963613895372786e-06, "loss": 1.4348, "step": 197300 }, { "epoch": 9.01, "learning_rate": 4.961325461119502e-06, "loss": 1.3559, "step": 197310 }, { "epoch": 9.01, "learning_rate": 4.959037026866219e-06, "loss": 1.3383, "step": 197320 }, { "epoch": 9.01, "learning_rate": 4.956748592612935e-06, "loss": 1.4524, "step": 197330 }, { "epoch": 9.01, "learning_rate": 4.9544601583596505e-06, "loss": 1.5838, "step": 197340 }, { "epoch": 9.01, "learning_rate": 4.952171724106366e-06, "loss": 1.3587, "step": 197350 }, { "epoch": 9.01, "learning_rate": 4.949883289853083e-06, "loss": 1.3035, "step": 197360 }, { "epoch": 9.01, "learning_rate": 4.947594855599799e-06, "loss": 1.3177, "step": 197370 }, { "epoch": 9.01, "learning_rate": 4.945306421346515e-06, "loss": 1.2234, "step": 197380 }, { "epoch": 9.01, "learning_rate": 4.943017987093231e-06, "loss": 1.4102, "step": 197390 }, { "epoch": 9.01, "learning_rate": 4.940729552839947e-06, "loss": 1.3085, "step": 197400 }, { "epoch": 9.01, "learning_rate": 4.938441118586663e-06, "loss": 1.2243, "step": 197410 }, { "epoch": 9.01, "learning_rate": 4.93615268433338e-06, "loss": 1.5107, "step": 197420 }, { "epoch": 9.02, "learning_rate": 4.9338642500800955e-06, "loss": 1.3966, "step": 197430 }, { "epoch": 9.02, "learning_rate": 4.931575815826812e-06, "loss": 1.2254, "step": 197440 }, { "epoch": 9.02, "learning_rate": 4.929287381573527e-06, "loss": 1.3727, "step": 197450 }, { "epoch": 9.02, "learning_rate": 4.926998947320244e-06, "loss": 1.3067, "step": 197460 }, { "epoch": 9.02, "learning_rate": 4.92471051306696e-06, "loss": 1.3321, "step": 197470 }, { "epoch": 9.02, "learning_rate": 4.922422078813676e-06, "loss": 1.4709, "step": 197480 }, { "epoch": 9.02, "learning_rate": 4.920133644560392e-06, "loss": 1.4406, "step": 197490 }, { "epoch": 9.02, "learning_rate": 4.917845210307108e-06, "loss": 1.397, "step": 197500 }, { "epoch": 9.02, "learning_rate": 4.915556776053825e-06, "loss": 1.4207, "step": 197510 }, { "epoch": 9.02, "learning_rate": 4.91326834180054e-06, "loss": 1.4013, "step": 197520 }, { "epoch": 9.02, "learning_rate": 4.910979907547256e-06, "loss": 1.2678, "step": 197530 }, { "epoch": 9.02, "learning_rate": 4.908691473293973e-06, "loss": 1.1936, "step": 197540 }, { "epoch": 9.02, "learning_rate": 4.906403039040689e-06, "loss": 1.2901, "step": 197550 }, { "epoch": 9.02, "learning_rate": 4.904114604787405e-06, "loss": 1.4134, "step": 197560 }, { "epoch": 9.02, "learning_rate": 4.9018261705341204e-06, "loss": 1.3377, "step": 197570 }, { "epoch": 9.02, "learning_rate": 4.899537736280837e-06, "loss": 1.4295, "step": 197580 }, { "epoch": 9.02, "learning_rate": 4.897249302027553e-06, "loss": 1.4701, "step": 197590 }, { "epoch": 9.02, "learning_rate": 4.894960867774269e-06, "loss": 1.3223, "step": 197600 }, { "epoch": 9.02, "learning_rate": 4.8926724335209854e-06, "loss": 1.4279, "step": 197610 }, { "epoch": 9.02, "learning_rate": 4.890383999267701e-06, "loss": 1.2641, "step": 197620 }, { "epoch": 9.02, "learning_rate": 4.888095565014417e-06, "loss": 1.4198, "step": 197630 }, { "epoch": 9.02, "learning_rate": 4.885807130761134e-06, "loss": 1.288, "step": 197640 }, { "epoch": 9.03, "learning_rate": 4.88351869650785e-06, "loss": 1.3113, "step": 197650 }, { "epoch": 9.03, "learning_rate": 4.881230262254565e-06, "loss": 1.3957, "step": 197660 }, { "epoch": 9.03, "learning_rate": 4.878941828001281e-06, "loss": 1.2861, "step": 197670 }, { "epoch": 9.03, "learning_rate": 4.876653393747998e-06, "loss": 1.3977, "step": 197680 }, { "epoch": 9.03, "learning_rate": 4.874364959494715e-06, "loss": 1.3303, "step": 197690 }, { "epoch": 9.03, "learning_rate": 4.8720765252414296e-06, "loss": 1.1701, "step": 197700 }, { "epoch": 9.03, "learning_rate": 4.869788090988146e-06, "loss": 1.5013, "step": 197710 }, { "epoch": 9.03, "learning_rate": 4.867499656734862e-06, "loss": 1.2739, "step": 197720 }, { "epoch": 9.03, "learning_rate": 4.865211222481579e-06, "loss": 1.6032, "step": 197730 }, { "epoch": 9.03, "learning_rate": 4.862922788228295e-06, "loss": 1.2762, "step": 197740 }, { "epoch": 9.03, "learning_rate": 4.86063435397501e-06, "loss": 1.3048, "step": 197750 }, { "epoch": 9.03, "learning_rate": 4.858345919721727e-06, "loss": 1.4234, "step": 197760 }, { "epoch": 9.03, "learning_rate": 4.856057485468443e-06, "loss": 1.3629, "step": 197770 }, { "epoch": 9.03, "learning_rate": 4.853769051215159e-06, "loss": 1.2113, "step": 197780 }, { "epoch": 9.03, "learning_rate": 4.851480616961875e-06, "loss": 1.4635, "step": 197790 }, { "epoch": 9.03, "learning_rate": 4.849192182708591e-06, "loss": 1.4, "step": 197800 }, { "epoch": 9.03, "learning_rate": 4.846903748455307e-06, "loss": 1.4021, "step": 197810 }, { "epoch": 9.03, "learning_rate": 4.844615314202023e-06, "loss": 1.3116, "step": 197820 }, { "epoch": 9.03, "learning_rate": 4.8423268799487396e-06, "loss": 1.3096, "step": 197830 }, { "epoch": 9.03, "learning_rate": 4.840038445695455e-06, "loss": 1.3031, "step": 197840 }, { "epoch": 9.03, "learning_rate": 4.837750011442171e-06, "loss": 1.4651, "step": 197850 }, { "epoch": 9.03, "learning_rate": 4.835461577188888e-06, "loss": 1.4292, "step": 197860 }, { "epoch": 9.04, "learning_rate": 4.833173142935604e-06, "loss": 1.2903, "step": 197870 }, { "epoch": 9.04, "learning_rate": 4.8308847086823196e-06, "loss": 1.5077, "step": 197880 }, { "epoch": 9.04, "learning_rate": 4.828596274429035e-06, "loss": 1.3514, "step": 197890 }, { "epoch": 9.04, "learning_rate": 4.826307840175752e-06, "loss": 1.3033, "step": 197900 }, { "epoch": 9.04, "learning_rate": 4.824019405922469e-06, "loss": 1.2113, "step": 197910 }, { "epoch": 9.04, "learning_rate": 4.821730971669184e-06, "loss": 1.5169, "step": 197920 }, { "epoch": 9.04, "learning_rate": 4.8194425374159e-06, "loss": 1.3644, "step": 197930 }, { "epoch": 9.04, "learning_rate": 4.817154103162616e-06, "loss": 1.3153, "step": 197940 }, { "epoch": 9.04, "learning_rate": 4.814865668909332e-06, "loss": 1.2982, "step": 197950 }, { "epoch": 9.04, "learning_rate": 4.812577234656049e-06, "loss": 1.3208, "step": 197960 }, { "epoch": 9.04, "learning_rate": 4.8102888004027645e-06, "loss": 1.5081, "step": 197970 }, { "epoch": 9.04, "learning_rate": 4.808000366149481e-06, "loss": 1.3301, "step": 197980 }, { "epoch": 9.04, "learning_rate": 4.805711931896196e-06, "loss": 1.2587, "step": 197990 }, { "epoch": 9.04, "learning_rate": 4.803423497642913e-06, "loss": 1.4028, "step": 198000 }, { "epoch": 9.04, "learning_rate": 4.8011350633896295e-06, "loss": 1.3818, "step": 198010 }, { "epoch": 9.04, "learning_rate": 4.798846629136345e-06, "loss": 1.3777, "step": 198020 }, { "epoch": 9.04, "learning_rate": 4.796558194883061e-06, "loss": 1.3636, "step": 198030 }, { "epoch": 9.04, "learning_rate": 4.794269760629777e-06, "loss": 1.3967, "step": 198040 }, { "epoch": 9.04, "learning_rate": 4.791981326376494e-06, "loss": 1.434, "step": 198050 }, { "epoch": 9.04, "learning_rate": 4.7896928921232095e-06, "loss": 1.1854, "step": 198060 }, { "epoch": 9.04, "learning_rate": 4.787404457869925e-06, "loss": 1.4059, "step": 198070 }, { "epoch": 9.04, "learning_rate": 4.785116023616642e-06, "loss": 1.3682, "step": 198080 }, { "epoch": 9.05, "learning_rate": 4.782827589363358e-06, "loss": 1.2246, "step": 198090 }, { "epoch": 9.05, "learning_rate": 4.780539155110074e-06, "loss": 1.444, "step": 198100 }, { "epoch": 9.05, "learning_rate": 4.77825072085679e-06, "loss": 1.4454, "step": 198110 }, { "epoch": 9.05, "learning_rate": 4.775962286603506e-06, "loss": 1.3834, "step": 198120 }, { "epoch": 9.05, "learning_rate": 4.773673852350222e-06, "loss": 1.2539, "step": 198130 }, { "epoch": 9.05, "learning_rate": 4.771385418096938e-06, "loss": 1.4379, "step": 198140 }, { "epoch": 9.05, "learning_rate": 4.7690969838436545e-06, "loss": 1.4257, "step": 198150 }, { "epoch": 9.05, "learning_rate": 4.766808549590371e-06, "loss": 1.3384, "step": 198160 }, { "epoch": 9.05, "learning_rate": 4.764520115337086e-06, "loss": 1.5736, "step": 198170 }, { "epoch": 9.05, "learning_rate": 4.762231681083803e-06, "loss": 1.4256, "step": 198180 }, { "epoch": 9.05, "learning_rate": 4.759943246830519e-06, "loss": 1.2612, "step": 198190 }, { "epoch": 9.05, "learning_rate": 4.757654812577235e-06, "loss": 1.347, "step": 198200 }, { "epoch": 9.05, "learning_rate": 4.755366378323951e-06, "loss": 1.3701, "step": 198210 }, { "epoch": 9.05, "learning_rate": 4.753077944070667e-06, "loss": 1.3843, "step": 198220 }, { "epoch": 9.05, "learning_rate": 4.750789509817384e-06, "loss": 1.268, "step": 198230 }, { "epoch": 9.05, "learning_rate": 4.748501075564099e-06, "loss": 1.1368, "step": 198240 }, { "epoch": 9.05, "learning_rate": 4.746212641310815e-06, "loss": 1.479, "step": 198250 }, { "epoch": 9.05, "learning_rate": 4.743924207057531e-06, "loss": 1.5779, "step": 198260 }, { "epoch": 9.05, "learning_rate": 4.741635772804248e-06, "loss": 1.3605, "step": 198270 }, { "epoch": 9.05, "learning_rate": 4.739347338550964e-06, "loss": 1.2983, "step": 198280 }, { "epoch": 9.05, "learning_rate": 4.7370589042976795e-06, "loss": 1.4045, "step": 198290 }, { "epoch": 9.05, "learning_rate": 4.734770470044396e-06, "loss": 1.4084, "step": 198300 }, { "epoch": 9.06, "learning_rate": 4.732482035791112e-06, "loss": 1.4172, "step": 198310 }, { "epoch": 9.06, "learning_rate": 4.730193601537828e-06, "loss": 1.4071, "step": 198320 }, { "epoch": 9.06, "learning_rate": 4.7279051672845445e-06, "loss": 1.3366, "step": 198330 }, { "epoch": 9.06, "learning_rate": 4.72561673303126e-06, "loss": 1.3155, "step": 198340 }, { "epoch": 9.06, "learning_rate": 4.723328298777976e-06, "loss": 1.2306, "step": 198350 }, { "epoch": 9.06, "learning_rate": 4.721039864524692e-06, "loss": 1.301, "step": 198360 }, { "epoch": 9.06, "learning_rate": 4.718751430271409e-06, "loss": 1.4786, "step": 198370 }, { "epoch": 9.06, "learning_rate": 4.7164629960181245e-06, "loss": 1.3188, "step": 198380 }, { "epoch": 9.06, "learning_rate": 4.71417456176484e-06, "loss": 1.2962, "step": 198390 }, { "epoch": 9.06, "learning_rate": 4.711886127511557e-06, "loss": 1.4321, "step": 198400 }, { "epoch": 9.06, "learning_rate": 4.709597693258273e-06, "loss": 1.2498, "step": 198410 }, { "epoch": 9.06, "learning_rate": 4.707309259004989e-06, "loss": 1.3394, "step": 198420 }, { "epoch": 9.06, "learning_rate": 4.705020824751705e-06, "loss": 1.3655, "step": 198430 }, { "epoch": 9.06, "learning_rate": 4.702732390498421e-06, "loss": 1.3425, "step": 198440 }, { "epoch": 9.06, "learning_rate": 4.700443956245138e-06, "loss": 1.0734, "step": 198450 }, { "epoch": 9.06, "learning_rate": 4.698155521991853e-06, "loss": 1.3956, "step": 198460 }, { "epoch": 9.06, "learning_rate": 4.6958670877385695e-06, "loss": 1.2503, "step": 198470 }, { "epoch": 9.06, "learning_rate": 4.693578653485286e-06, "loss": 1.2909, "step": 198480 }, { "epoch": 9.06, "learning_rate": 4.691290219232002e-06, "loss": 1.3925, "step": 198490 }, { "epoch": 9.06, "learning_rate": 4.689001784978718e-06, "loss": 1.3683, "step": 198500 }, { "epoch": 9.06, "learning_rate": 4.686713350725434e-06, "loss": 1.2329, "step": 198510 }, { "epoch": 9.06, "learning_rate": 4.68442491647215e-06, "loss": 1.3975, "step": 198520 }, { "epoch": 9.07, "learning_rate": 4.682136482218866e-06, "loss": 1.2767, "step": 198530 }, { "epoch": 9.07, "learning_rate": 4.679848047965582e-06, "loss": 1.4458, "step": 198540 }, { "epoch": 9.07, "learning_rate": 4.677559613712299e-06, "loss": 1.3131, "step": 198550 }, { "epoch": 9.07, "learning_rate": 4.6752711794590145e-06, "loss": 1.4523, "step": 198560 }, { "epoch": 9.07, "learning_rate": 4.67298274520573e-06, "loss": 1.293, "step": 198570 }, { "epoch": 9.07, "learning_rate": 4.670694310952447e-06, "loss": 1.354, "step": 198580 }, { "epoch": 9.07, "learning_rate": 4.668405876699163e-06, "loss": 1.3553, "step": 198590 }, { "epoch": 9.07, "learning_rate": 4.666117442445879e-06, "loss": 1.4218, "step": 198600 }, { "epoch": 9.07, "learning_rate": 4.6638290081925944e-06, "loss": 1.297, "step": 198610 }, { "epoch": 9.07, "learning_rate": 4.661540573939311e-06, "loss": 1.3439, "step": 198620 }, { "epoch": 9.07, "learning_rate": 4.659252139686028e-06, "loss": 1.4138, "step": 198630 }, { "epoch": 9.07, "learning_rate": 4.656963705432743e-06, "loss": 1.2356, "step": 198640 }, { "epoch": 9.07, "learning_rate": 4.6546752711794595e-06, "loss": 1.4558, "step": 198650 }, { "epoch": 9.07, "learning_rate": 4.652386836926175e-06, "loss": 1.5041, "step": 198660 }, { "epoch": 9.07, "learning_rate": 4.650098402672891e-06, "loss": 1.2175, "step": 198670 }, { "epoch": 9.07, "learning_rate": 4.647809968419607e-06, "loss": 1.3674, "step": 198680 }, { "epoch": 9.07, "learning_rate": 4.645521534166324e-06, "loss": 1.4347, "step": 198690 }, { "epoch": 9.07, "learning_rate": 4.64323309991304e-06, "loss": 1.2137, "step": 198700 }, { "epoch": 9.07, "learning_rate": 4.640944665659755e-06, "loss": 1.3272, "step": 198710 }, { "epoch": 9.07, "learning_rate": 4.638656231406472e-06, "loss": 1.2914, "step": 198720 }, { "epoch": 9.07, "learning_rate": 4.636367797153188e-06, "loss": 1.2403, "step": 198730 }, { "epoch": 9.07, "learning_rate": 4.6340793628999044e-06, "loss": 1.2643, "step": 198740 }, { "epoch": 9.08, "learning_rate": 4.63179092864662e-06, "loss": 1.2342, "step": 198750 }, { "epoch": 9.08, "learning_rate": 4.629502494393336e-06, "loss": 1.2434, "step": 198760 }, { "epoch": 9.08, "learning_rate": 4.627214060140053e-06, "loss": 1.3431, "step": 198770 }, { "epoch": 9.08, "learning_rate": 4.624925625886769e-06, "loss": 1.5335, "step": 198780 }, { "epoch": 9.08, "learning_rate": 4.6226371916334844e-06, "loss": 1.4742, "step": 198790 }, { "epoch": 9.08, "learning_rate": 4.620348757380201e-06, "loss": 1.3543, "step": 198800 }, { "epoch": 9.08, "learning_rate": 4.618060323126917e-06, "loss": 1.3458, "step": 198810 }, { "epoch": 9.08, "learning_rate": 4.615771888873633e-06, "loss": 1.2835, "step": 198820 }, { "epoch": 9.08, "learning_rate": 4.613483454620349e-06, "loss": 1.3173, "step": 198830 }, { "epoch": 9.08, "learning_rate": 4.611195020367065e-06, "loss": 1.4639, "step": 198840 }, { "epoch": 9.08, "learning_rate": 4.608906586113781e-06, "loss": 1.3042, "step": 198850 }, { "epoch": 9.08, "learning_rate": 4.606618151860497e-06, "loss": 1.3407, "step": 198860 }, { "epoch": 9.08, "learning_rate": 4.604329717607214e-06, "loss": 1.3292, "step": 198870 }, { "epoch": 9.08, "learning_rate": 4.602041283353929e-06, "loss": 1.2264, "step": 198880 }, { "epoch": 9.08, "learning_rate": 4.599752849100645e-06, "loss": 1.355, "step": 198890 }, { "epoch": 9.08, "learning_rate": 4.597464414847362e-06, "loss": 1.31, "step": 198900 }, { "epoch": 9.08, "learning_rate": 4.595175980594078e-06, "loss": 1.2238, "step": 198910 }, { "epoch": 9.08, "learning_rate": 4.592887546340794e-06, "loss": 1.3452, "step": 198920 }, { "epoch": 9.08, "learning_rate": 4.590599112087509e-06, "loss": 1.4176, "step": 198930 }, { "epoch": 9.08, "learning_rate": 4.588310677834226e-06, "loss": 1.2391, "step": 198940 }, { "epoch": 9.08, "learning_rate": 4.586022243580943e-06, "loss": 1.416, "step": 198950 }, { "epoch": 9.09, "learning_rate": 4.583733809327658e-06, "loss": 1.4002, "step": 198960 }, { "epoch": 9.09, "learning_rate": 4.581445375074374e-06, "loss": 1.2619, "step": 198970 }, { "epoch": 9.09, "learning_rate": 4.57915694082109e-06, "loss": 1.3661, "step": 198980 }, { "epoch": 9.09, "learning_rate": 4.576868506567807e-06, "loss": 1.2782, "step": 198990 }, { "epoch": 9.09, "learning_rate": 4.574580072314523e-06, "loss": 1.3409, "step": 199000 }, { "epoch": 9.09, "learning_rate": 4.5722916380612386e-06, "loss": 1.3585, "step": 199010 }, { "epoch": 9.09, "learning_rate": 4.570003203807955e-06, "loss": 1.1968, "step": 199020 }, { "epoch": 9.09, "learning_rate": 4.567714769554671e-06, "loss": 1.4228, "step": 199030 }, { "epoch": 9.09, "learning_rate": 4.565426335301387e-06, "loss": 1.4256, "step": 199040 }, { "epoch": 9.09, "learning_rate": 4.563137901048103e-06, "loss": 1.2685, "step": 199050 }, { "epoch": 9.09, "learning_rate": 4.560849466794819e-06, "loss": 1.3919, "step": 199060 }, { "epoch": 9.09, "learning_rate": 4.558561032541535e-06, "loss": 1.5232, "step": 199070 }, { "epoch": 9.09, "learning_rate": 4.556272598288251e-06, "loss": 1.3617, "step": 199080 }, { "epoch": 9.09, "learning_rate": 4.553984164034968e-06, "loss": 1.3435, "step": 199090 }, { "epoch": 9.09, "learning_rate": 4.5516957297816836e-06, "loss": 1.3736, "step": 199100 }, { "epoch": 9.09, "learning_rate": 4.549407295528399e-06, "loss": 1.1714, "step": 199110 }, { "epoch": 9.09, "learning_rate": 4.547118861275116e-06, "loss": 1.2873, "step": 199120 }, { "epoch": 9.09, "learning_rate": 4.544830427021832e-06, "loss": 1.1528, "step": 199130 }, { "epoch": 9.09, "learning_rate": 4.542541992768548e-06, "loss": 1.3822, "step": 199140 }, { "epoch": 9.09, "learning_rate": 4.5402535585152635e-06, "loss": 1.1822, "step": 199150 }, { "epoch": 9.09, "learning_rate": 4.53796512426198e-06, "loss": 1.2402, "step": 199160 }, { "epoch": 9.09, "learning_rate": 4.535676690008697e-06, "loss": 1.492, "step": 199170 }, { "epoch": 9.1, "learning_rate": 4.533388255755412e-06, "loss": 1.3291, "step": 199180 }, { "epoch": 9.1, "learning_rate": 4.5310998215021285e-06, "loss": 1.2038, "step": 199190 }, { "epoch": 9.1, "learning_rate": 4.528811387248844e-06, "loss": 1.3895, "step": 199200 }, { "epoch": 9.1, "learning_rate": 4.526522952995561e-06, "loss": 1.3883, "step": 199210 }, { "epoch": 9.1, "learning_rate": 4.524234518742277e-06, "loss": 1.3039, "step": 199220 }, { "epoch": 9.1, "learning_rate": 4.521946084488993e-06, "loss": 1.1967, "step": 199230 }, { "epoch": 9.1, "learning_rate": 4.519657650235709e-06, "loss": 1.2563, "step": 199240 }, { "epoch": 9.1, "learning_rate": 4.517369215982424e-06, "loss": 1.4514, "step": 199250 }, { "epoch": 9.1, "learning_rate": 4.515080781729141e-06, "loss": 1.3564, "step": 199260 }, { "epoch": 9.1, "learning_rate": 4.512792347475858e-06, "loss": 1.2392, "step": 199270 }, { "epoch": 9.1, "learning_rate": 4.5105039132225735e-06, "loss": 1.3718, "step": 199280 }, { "epoch": 9.1, "learning_rate": 4.508215478969289e-06, "loss": 1.3505, "step": 199290 }, { "epoch": 9.1, "learning_rate": 4.505927044716005e-06, "loss": 1.4204, "step": 199300 }, { "epoch": 9.1, "learning_rate": 4.503638610462722e-06, "loss": 1.3226, "step": 199310 }, { "epoch": 9.1, "learning_rate": 4.501350176209438e-06, "loss": 1.346, "step": 199320 }, { "epoch": 9.1, "learning_rate": 4.4990617419561535e-06, "loss": 1.3599, "step": 199330 }, { "epoch": 9.1, "learning_rate": 4.49677330770287e-06, "loss": 1.3473, "step": 199340 }, { "epoch": 9.1, "learning_rate": 4.494484873449586e-06, "loss": 1.345, "step": 199350 }, { "epoch": 9.1, "learning_rate": 4.492196439196302e-06, "loss": 1.4162, "step": 199360 }, { "epoch": 9.1, "learning_rate": 4.4899080049430185e-06, "loss": 1.2091, "step": 199370 }, { "epoch": 9.1, "learning_rate": 4.487619570689734e-06, "loss": 1.2469, "step": 199380 }, { "epoch": 9.1, "learning_rate": 4.48533113643645e-06, "loss": 1.3265, "step": 199390 }, { "epoch": 9.11, "learning_rate": 4.483042702183166e-06, "loss": 1.3619, "step": 199400 }, { "epoch": 9.11, "learning_rate": 4.480754267929883e-06, "loss": 1.2183, "step": 199410 }, { "epoch": 9.11, "learning_rate": 4.478465833676599e-06, "loss": 1.2518, "step": 199420 }, { "epoch": 9.11, "learning_rate": 4.476177399423314e-06, "loss": 1.3416, "step": 199430 }, { "epoch": 9.11, "learning_rate": 4.473888965170031e-06, "loss": 1.5822, "step": 199440 }, { "epoch": 9.11, "learning_rate": 4.471600530916747e-06, "loss": 1.3868, "step": 199450 }, { "epoch": 9.11, "learning_rate": 4.4693120966634635e-06, "loss": 1.2463, "step": 199460 }, { "epoch": 9.11, "learning_rate": 4.4670236624101785e-06, "loss": 1.2129, "step": 199470 }, { "epoch": 9.11, "learning_rate": 4.464735228156895e-06, "loss": 1.4054, "step": 199480 }, { "epoch": 9.11, "learning_rate": 4.462446793903612e-06, "loss": 1.2636, "step": 199490 }, { "epoch": 9.11, "learning_rate": 4.460158359650328e-06, "loss": 1.5183, "step": 199500 }, { "epoch": 9.11, "learning_rate": 4.4578699253970435e-06, "loss": 1.2641, "step": 199510 }, { "epoch": 9.11, "learning_rate": 4.455581491143759e-06, "loss": 1.3814, "step": 199520 }, { "epoch": 9.11, "learning_rate": 4.453293056890476e-06, "loss": 1.1804, "step": 199530 }, { "epoch": 9.11, "learning_rate": 4.451004622637192e-06, "loss": 1.3848, "step": 199540 }, { "epoch": 9.11, "learning_rate": 4.448716188383908e-06, "loss": 1.2595, "step": 199550 }, { "epoch": 9.11, "learning_rate": 4.446427754130624e-06, "loss": 1.6899, "step": 199560 }, { "epoch": 9.11, "learning_rate": 4.44413931987734e-06, "loss": 1.302, "step": 199570 }, { "epoch": 9.11, "learning_rate": 4.441850885624056e-06, "loss": 1.3659, "step": 199580 }, { "epoch": 9.11, "learning_rate": 4.439562451370773e-06, "loss": 1.3191, "step": 199590 }, { "epoch": 9.11, "learning_rate": 4.4372740171174885e-06, "loss": 1.382, "step": 199600 }, { "epoch": 9.11, "learning_rate": 4.434985582864204e-06, "loss": 1.3212, "step": 199610 }, { "epoch": 9.12, "learning_rate": 4.43269714861092e-06, "loss": 1.4356, "step": 199620 }, { "epoch": 9.12, "learning_rate": 4.430408714357637e-06, "loss": 1.4848, "step": 199630 }, { "epoch": 9.12, "learning_rate": 4.4281202801043535e-06, "loss": 1.3659, "step": 199640 }, { "epoch": 9.12, "learning_rate": 4.4258318458510685e-06, "loss": 1.2813, "step": 199650 }, { "epoch": 9.12, "learning_rate": 4.423543411597785e-06, "loss": 1.3768, "step": 199660 }, { "epoch": 9.12, "learning_rate": 4.421254977344501e-06, "loss": 1.3152, "step": 199670 }, { "epoch": 9.12, "learning_rate": 4.418966543091217e-06, "loss": 1.4952, "step": 199680 }, { "epoch": 9.12, "learning_rate": 4.4166781088379335e-06, "loss": 1.3164, "step": 199690 }, { "epoch": 9.12, "learning_rate": 4.414389674584649e-06, "loss": 1.2553, "step": 199700 }, { "epoch": 9.12, "learning_rate": 4.412101240331366e-06, "loss": 1.5112, "step": 199710 }, { "epoch": 9.12, "learning_rate": 4.409812806078081e-06, "loss": 1.3379, "step": 199720 }, { "epoch": 9.12, "learning_rate": 4.407524371824798e-06, "loss": 1.5296, "step": 199730 }, { "epoch": 9.12, "learning_rate": 4.405235937571514e-06, "loss": 1.3986, "step": 199740 }, { "epoch": 9.12, "learning_rate": 4.40294750331823e-06, "loss": 1.4736, "step": 199750 }, { "epoch": 9.12, "learning_rate": 4.400659069064946e-06, "loss": 1.283, "step": 199760 }, { "epoch": 9.12, "learning_rate": 4.398370634811662e-06, "loss": 1.4194, "step": 199770 }, { "epoch": 9.12, "learning_rate": 4.3960822005583785e-06, "loss": 1.2888, "step": 199780 }, { "epoch": 9.12, "learning_rate": 4.393793766305094e-06, "loss": 1.2471, "step": 199790 }, { "epoch": 9.12, "learning_rate": 4.39150533205181e-06, "loss": 1.3728, "step": 199800 }, { "epoch": 9.12, "learning_rate": 4.389216897798527e-06, "loss": 1.3697, "step": 199810 }, { "epoch": 9.12, "learning_rate": 4.386928463545243e-06, "loss": 1.4339, "step": 199820 }, { "epoch": 9.12, "learning_rate": 4.3846400292919585e-06, "loss": 1.2942, "step": 199830 }, { "epoch": 9.13, "learning_rate": 4.382351595038675e-06, "loss": 1.3977, "step": 199840 }, { "epoch": 9.13, "learning_rate": 4.380063160785391e-06, "loss": 1.3147, "step": 199850 }, { "epoch": 9.13, "learning_rate": 4.377774726532107e-06, "loss": 1.3177, "step": 199860 }, { "epoch": 9.13, "learning_rate": 4.375486292278823e-06, "loss": 1.4534, "step": 199870 }, { "epoch": 9.13, "learning_rate": 4.373197858025539e-06, "loss": 1.2755, "step": 199880 }, { "epoch": 9.13, "learning_rate": 4.370909423772255e-06, "loss": 1.4632, "step": 199890 }, { "epoch": 9.13, "learning_rate": 4.368620989518971e-06, "loss": 1.1588, "step": 199900 }, { "epoch": 9.13, "learning_rate": 4.366332555265688e-06, "loss": 1.3411, "step": 199910 }, { "epoch": 9.13, "learning_rate": 4.3640441210124034e-06, "loss": 1.4713, "step": 199920 }, { "epoch": 9.13, "learning_rate": 4.36175568675912e-06, "loss": 1.2427, "step": 199930 }, { "epoch": 9.13, "learning_rate": 4.359467252505835e-06, "loss": 1.3428, "step": 199940 }, { "epoch": 9.13, "learning_rate": 4.357178818252552e-06, "loss": 1.3262, "step": 199950 }, { "epoch": 9.13, "learning_rate": 4.3548903839992684e-06, "loss": 1.4048, "step": 199960 }, { "epoch": 9.13, "learning_rate": 4.3526019497459834e-06, "loss": 1.3796, "step": 199970 }, { "epoch": 9.13, "learning_rate": 4.3503135154927e-06, "loss": 1.3462, "step": 199980 }, { "epoch": 9.13, "learning_rate": 4.348025081239416e-06, "loss": 1.3772, "step": 199990 }, { "epoch": 9.13, "learning_rate": 4.345736646986133e-06, "loss": 1.4001, "step": 200000 }, { "epoch": 9.13, "learning_rate": 4.3434482127328484e-06, "loss": 1.385, "step": 200010 }, { "epoch": 9.13, "learning_rate": 4.341159778479564e-06, "loss": 1.3353, "step": 200020 }, { "epoch": 9.13, "learning_rate": 4.338871344226281e-06, "loss": 1.3469, "step": 200030 }, { "epoch": 9.13, "learning_rate": 4.336582909972997e-06, "loss": 1.3036, "step": 200040 }, { "epoch": 9.13, "learning_rate": 4.334294475719713e-06, "loss": 1.3189, "step": 200050 }, { "epoch": 9.14, "learning_rate": 4.332006041466429e-06, "loss": 1.4394, "step": 200060 }, { "epoch": 9.14, "learning_rate": 4.329717607213145e-06, "loss": 1.2918, "step": 200070 }, { "epoch": 9.14, "learning_rate": 4.327429172959861e-06, "loss": 1.2958, "step": 200080 }, { "epoch": 9.14, "learning_rate": 4.325140738706577e-06, "loss": 1.3278, "step": 200090 }, { "epoch": 9.14, "learning_rate": 4.322852304453293e-06, "loss": 1.2549, "step": 200100 }, { "epoch": 9.14, "learning_rate": 4.320563870200009e-06, "loss": 1.3378, "step": 200110 }, { "epoch": 9.14, "learning_rate": 4.318275435946725e-06, "loss": 1.4053, "step": 200120 }, { "epoch": 9.14, "learning_rate": 4.315987001693442e-06, "loss": 1.3312, "step": 200130 }, { "epoch": 9.14, "learning_rate": 4.313698567440158e-06, "loss": 1.295, "step": 200140 }, { "epoch": 9.14, "learning_rate": 4.311410133186873e-06, "loss": 1.2358, "step": 200150 }, { "epoch": 9.14, "learning_rate": 4.30912169893359e-06, "loss": 1.2429, "step": 200160 }, { "epoch": 9.14, "learning_rate": 4.306833264680306e-06, "loss": 1.2809, "step": 200170 }, { "epoch": 9.14, "learning_rate": 4.304544830427023e-06, "loss": 1.4662, "step": 200180 }, { "epoch": 9.14, "learning_rate": 4.3022563961737376e-06, "loss": 1.4186, "step": 200190 }, { "epoch": 9.14, "learning_rate": 4.299967961920454e-06, "loss": 1.2358, "step": 200200 }, { "epoch": 9.14, "learning_rate": 4.297679527667171e-06, "loss": 1.3633, "step": 200210 }, { "epoch": 9.14, "learning_rate": 4.295391093413887e-06, "loss": 1.1529, "step": 200220 }, { "epoch": 9.14, "learning_rate": 4.2931026591606026e-06, "loss": 1.3666, "step": 200230 }, { "epoch": 9.14, "learning_rate": 4.290814224907318e-06, "loss": 1.4306, "step": 200240 }, { "epoch": 9.14, "learning_rate": 4.288525790654035e-06, "loss": 1.4218, "step": 200250 }, { "epoch": 9.14, "learning_rate": 4.28623735640075e-06, "loss": 1.2894, "step": 200260 }, { "epoch": 9.14, "learning_rate": 4.283948922147467e-06, "loss": 1.2853, "step": 200270 }, { "epoch": 9.15, "learning_rate": 4.281660487894183e-06, "loss": 1.3558, "step": 200280 }, { "epoch": 9.15, "learning_rate": 4.279372053640899e-06, "loss": 1.4248, "step": 200290 }, { "epoch": 9.15, "learning_rate": 4.277083619387615e-06, "loss": 1.3755, "step": 200300 }, { "epoch": 9.15, "learning_rate": 4.274795185134331e-06, "loss": 1.2131, "step": 200310 }, { "epoch": 9.15, "learning_rate": 4.2725067508810476e-06, "loss": 1.4316, "step": 200320 }, { "epoch": 9.15, "learning_rate": 4.270218316627763e-06, "loss": 1.409, "step": 200330 }, { "epoch": 9.15, "learning_rate": 4.267929882374479e-06, "loss": 1.4292, "step": 200340 }, { "epoch": 9.15, "learning_rate": 4.265641448121196e-06, "loss": 1.3561, "step": 200350 }, { "epoch": 9.15, "learning_rate": 4.263353013867912e-06, "loss": 1.3102, "step": 200360 }, { "epoch": 9.15, "learning_rate": 4.2610645796146275e-06, "loss": 1.3861, "step": 200370 }, { "epoch": 9.15, "learning_rate": 4.258776145361344e-06, "loss": 1.3414, "step": 200380 }, { "epoch": 9.15, "learning_rate": 4.25648771110806e-06, "loss": 1.4091, "step": 200390 }, { "epoch": 9.15, "learning_rate": 4.254199276854776e-06, "loss": 1.1944, "step": 200400 }, { "epoch": 9.15, "learning_rate": 4.251910842601492e-06, "loss": 1.354, "step": 200410 }, { "epoch": 9.15, "learning_rate": 4.249622408348208e-06, "loss": 1.2068, "step": 200420 }, { "epoch": 9.15, "learning_rate": 4.247333974094925e-06, "loss": 1.147, "step": 200430 }, { "epoch": 9.15, "learning_rate": 4.24504553984164e-06, "loss": 1.3865, "step": 200440 }, { "epoch": 9.15, "learning_rate": 4.242757105588357e-06, "loss": 1.3905, "step": 200450 }, { "epoch": 9.15, "learning_rate": 4.2404686713350725e-06, "loss": 1.384, "step": 200460 }, { "epoch": 9.15, "learning_rate": 4.238180237081789e-06, "loss": 1.4657, "step": 200470 }, { "epoch": 9.15, "learning_rate": 4.235891802828505e-06, "loss": 1.3626, "step": 200480 }, { "epoch": 9.15, "learning_rate": 4.233603368575221e-06, "loss": 1.258, "step": 200490 }, { "epoch": 9.16, "learning_rate": 4.2313149343219375e-06, "loss": 1.4756, "step": 200500 }, { "epoch": 9.16, "learning_rate": 4.229026500068653e-06, "loss": 1.272, "step": 200510 }, { "epoch": 9.16, "learning_rate": 4.226738065815369e-06, "loss": 1.2185, "step": 200520 }, { "epoch": 9.16, "learning_rate": 4.224449631562086e-06, "loss": 1.2414, "step": 200530 }, { "epoch": 9.16, "learning_rate": 4.222161197308802e-06, "loss": 1.364, "step": 200540 }, { "epoch": 9.16, "learning_rate": 4.2198727630555175e-06, "loss": 1.433, "step": 200550 }, { "epoch": 9.16, "learning_rate": 4.217584328802233e-06, "loss": 1.3551, "step": 200560 }, { "epoch": 9.16, "learning_rate": 4.21529589454895e-06, "loss": 1.3334, "step": 200570 }, { "epoch": 9.16, "learning_rate": 4.213007460295666e-06, "loss": 1.3973, "step": 200580 }, { "epoch": 9.16, "learning_rate": 4.210719026042382e-06, "loss": 1.3693, "step": 200590 }, { "epoch": 9.16, "learning_rate": 4.208430591789098e-06, "loss": 1.2414, "step": 200600 }, { "epoch": 9.16, "learning_rate": 4.206142157535814e-06, "loss": 1.3692, "step": 200610 }, { "epoch": 9.16, "learning_rate": 4.20385372328253e-06, "loss": 1.452, "step": 200620 }, { "epoch": 9.16, "learning_rate": 4.201565289029247e-06, "loss": 1.2843, "step": 200630 }, { "epoch": 9.16, "learning_rate": 4.1992768547759625e-06, "loss": 1.1938, "step": 200640 }, { "epoch": 9.16, "learning_rate": 4.196988420522679e-06, "loss": 1.2596, "step": 200650 }, { "epoch": 9.16, "learning_rate": 4.194699986269394e-06, "loss": 1.2808, "step": 200660 }, { "epoch": 9.16, "learning_rate": 4.192411552016111e-06, "loss": 1.3661, "step": 200670 }, { "epoch": 9.16, "learning_rate": 4.190123117762827e-06, "loss": 1.3882, "step": 200680 }, { "epoch": 9.16, "learning_rate": 4.1878346835095425e-06, "loss": 1.3756, "step": 200690 }, { "epoch": 9.16, "learning_rate": 4.185546249256259e-06, "loss": 1.2974, "step": 200700 }, { "epoch": 9.16, "learning_rate": 4.183257815002975e-06, "loss": 1.2586, "step": 200710 }, { "epoch": 9.17, "learning_rate": 4.180969380749692e-06, "loss": 1.2031, "step": 200720 }, { "epoch": 9.17, "learning_rate": 4.178680946496407e-06, "loss": 1.4326, "step": 200730 }, { "epoch": 9.17, "learning_rate": 4.176392512243123e-06, "loss": 1.578, "step": 200740 }, { "epoch": 9.17, "learning_rate": 4.17410407798984e-06, "loss": 1.4446, "step": 200750 }, { "epoch": 9.17, "learning_rate": 4.171815643736556e-06, "loss": 1.3356, "step": 200760 }, { "epoch": 9.17, "learning_rate": 4.169527209483272e-06, "loss": 1.3849, "step": 200770 }, { "epoch": 9.17, "learning_rate": 4.1672387752299875e-06, "loss": 1.2968, "step": 200780 }, { "epoch": 9.17, "learning_rate": 4.164950340976704e-06, "loss": 1.4448, "step": 200790 }, { "epoch": 9.17, "learning_rate": 4.16266190672342e-06, "loss": 1.4435, "step": 200800 }, { "epoch": 9.17, "learning_rate": 4.160373472470136e-06, "loss": 1.3918, "step": 200810 }, { "epoch": 9.17, "learning_rate": 4.1580850382168525e-06, "loss": 1.3394, "step": 200820 }, { "epoch": 9.17, "learning_rate": 4.155796603963568e-06, "loss": 1.2544, "step": 200830 }, { "epoch": 9.17, "learning_rate": 4.153508169710284e-06, "loss": 1.4316, "step": 200840 }, { "epoch": 9.17, "learning_rate": 4.151219735457001e-06, "loss": 1.3024, "step": 200850 }, { "epoch": 9.17, "learning_rate": 4.148931301203717e-06, "loss": 1.2204, "step": 200860 }, { "epoch": 9.17, "learning_rate": 4.1466428669504325e-06, "loss": 1.3152, "step": 200870 }, { "epoch": 9.17, "learning_rate": 4.144354432697148e-06, "loss": 1.6311, "step": 200880 }, { "epoch": 9.17, "learning_rate": 4.142065998443865e-06, "loss": 1.3593, "step": 200890 }, { "epoch": 9.17, "learning_rate": 4.139777564190582e-06, "loss": 1.4877, "step": 200900 }, { "epoch": 9.17, "learning_rate": 4.137489129937297e-06, "loss": 1.2604, "step": 200910 }, { "epoch": 9.17, "learning_rate": 4.135200695684013e-06, "loss": 1.3866, "step": 200920 }, { "epoch": 9.17, "learning_rate": 4.132912261430729e-06, "loss": 1.3682, "step": 200930 }, { "epoch": 9.18, "learning_rate": 4.130623827177446e-06, "loss": 1.3822, "step": 200940 }, { "epoch": 9.18, "learning_rate": 4.128335392924162e-06, "loss": 1.3746, "step": 200950 }, { "epoch": 9.18, "learning_rate": 4.1260469586708775e-06, "loss": 1.306, "step": 200960 }, { "epoch": 9.18, "learning_rate": 4.123758524417594e-06, "loss": 1.2926, "step": 200970 }, { "epoch": 9.18, "learning_rate": 4.12147009016431e-06, "loss": 1.3969, "step": 200980 }, { "epoch": 9.18, "learning_rate": 4.119181655911026e-06, "loss": 1.327, "step": 200990 }, { "epoch": 9.18, "learning_rate": 4.1168932216577425e-06, "loss": 1.2935, "step": 201000 }, { "epoch": 9.18, "learning_rate": 4.114604787404458e-06, "loss": 1.2994, "step": 201010 }, { "epoch": 9.18, "learning_rate": 4.112316353151174e-06, "loss": 1.3938, "step": 201020 }, { "epoch": 9.18, "learning_rate": 4.11002791889789e-06, "loss": 1.2672, "step": 201030 }, { "epoch": 9.18, "learning_rate": 4.107739484644607e-06, "loss": 1.352, "step": 201040 }, { "epoch": 9.18, "learning_rate": 4.1054510503913225e-06, "loss": 1.3848, "step": 201050 }, { "epoch": 9.18, "learning_rate": 4.103162616138038e-06, "loss": 1.235, "step": 201060 }, { "epoch": 9.18, "learning_rate": 4.100874181884755e-06, "loss": 1.199, "step": 201070 }, { "epoch": 9.18, "learning_rate": 4.098585747631471e-06, "loss": 1.3209, "step": 201080 }, { "epoch": 9.18, "learning_rate": 4.096297313378187e-06, "loss": 1.3223, "step": 201090 }, { "epoch": 9.18, "learning_rate": 4.0940088791249024e-06, "loss": 1.3196, "step": 201100 }, { "epoch": 9.18, "learning_rate": 4.091720444871619e-06, "loss": 1.3843, "step": 201110 }, { "epoch": 9.18, "learning_rate": 4.089432010618335e-06, "loss": 1.4565, "step": 201120 }, { "epoch": 9.18, "learning_rate": 4.087143576365051e-06, "loss": 1.3501, "step": 201130 }, { "epoch": 9.18, "learning_rate": 4.0848551421117674e-06, "loss": 1.4208, "step": 201140 }, { "epoch": 9.19, "learning_rate": 4.082566707858483e-06, "loss": 1.4219, "step": 201150 }, { "epoch": 9.19, "learning_rate": 4.080278273605199e-06, "loss": 1.4194, "step": 201160 }, { "epoch": 9.19, "learning_rate": 4.077989839351916e-06, "loss": 1.293, "step": 201170 }, { "epoch": 9.19, "learning_rate": 4.075701405098632e-06, "loss": 1.3627, "step": 201180 }, { "epoch": 9.19, "learning_rate": 4.073412970845348e-06, "loss": 1.1809, "step": 201190 }, { "epoch": 9.19, "learning_rate": 4.071124536592063e-06, "loss": 1.1743, "step": 201200 }, { "epoch": 9.19, "learning_rate": 4.06883610233878e-06, "loss": 1.2756, "step": 201210 }, { "epoch": 9.19, "learning_rate": 4.066547668085497e-06, "loss": 1.3087, "step": 201220 }, { "epoch": 9.19, "learning_rate": 4.0642592338322124e-06, "loss": 1.4632, "step": 201230 }, { "epoch": 9.19, "learning_rate": 4.061970799578928e-06, "loss": 1.2536, "step": 201240 }, { "epoch": 9.19, "learning_rate": 4.059682365325644e-06, "loss": 1.3034, "step": 201250 }, { "epoch": 9.19, "learning_rate": 4.057393931072361e-06, "loss": 1.4233, "step": 201260 }, { "epoch": 9.19, "learning_rate": 4.055105496819077e-06, "loss": 1.3157, "step": 201270 }, { "epoch": 9.19, "learning_rate": 4.052817062565792e-06, "loss": 1.3703, "step": 201280 }, { "epoch": 9.19, "learning_rate": 4.050528628312509e-06, "loss": 1.46, "step": 201290 }, { "epoch": 9.19, "learning_rate": 4.048240194059225e-06, "loss": 1.3146, "step": 201300 }, { "epoch": 9.19, "learning_rate": 4.045951759805941e-06, "loss": 1.3519, "step": 201310 }, { "epoch": 9.19, "learning_rate": 4.0436633255526574e-06, "loss": 1.2553, "step": 201320 }, { "epoch": 9.19, "learning_rate": 4.041374891299373e-06, "loss": 1.2902, "step": 201330 }, { "epoch": 9.19, "learning_rate": 4.039086457046089e-06, "loss": 1.3224, "step": 201340 }, { "epoch": 9.19, "learning_rate": 4.036798022792805e-06, "loss": 1.3445, "step": 201350 }, { "epoch": 9.19, "learning_rate": 4.034509588539522e-06, "loss": 1.2318, "step": 201360 }, { "epoch": 9.2, "learning_rate": 4.032221154286238e-06, "loss": 1.2719, "step": 201370 }, { "epoch": 9.2, "learning_rate": 4.029932720032953e-06, "loss": 1.4003, "step": 201380 }, { "epoch": 9.2, "learning_rate": 4.02764428577967e-06, "loss": 1.391, "step": 201390 }, { "epoch": 9.2, "learning_rate": 4.025355851526386e-06, "loss": 1.4179, "step": 201400 }, { "epoch": 9.2, "learning_rate": 4.023067417273102e-06, "loss": 1.555, "step": 201410 }, { "epoch": 9.2, "learning_rate": 4.020778983019818e-06, "loss": 1.2977, "step": 201420 }, { "epoch": 9.2, "learning_rate": 4.018490548766534e-06, "loss": 1.1369, "step": 201430 }, { "epoch": 9.2, "learning_rate": 4.016202114513251e-06, "loss": 1.2409, "step": 201440 }, { "epoch": 9.2, "learning_rate": 4.013913680259966e-06, "loss": 1.3845, "step": 201450 }, { "epoch": 9.2, "learning_rate": 4.011625246006682e-06, "loss": 1.3272, "step": 201460 }, { "epoch": 9.2, "learning_rate": 4.009336811753398e-06, "loss": 1.3979, "step": 201470 }, { "epoch": 9.2, "learning_rate": 4.007048377500115e-06, "loss": 1.331, "step": 201480 }, { "epoch": 9.2, "learning_rate": 4.004759943246831e-06, "loss": 1.1582, "step": 201490 }, { "epoch": 9.2, "learning_rate": 4.0024715089935466e-06, "loss": 1.4977, "step": 201500 }, { "epoch": 9.2, "learning_rate": 4.000183074740263e-06, "loss": 1.3133, "step": 201510 }, { "epoch": 9.2, "learning_rate": 3.997894640486979e-06, "loss": 1.3097, "step": 201520 }, { "epoch": 9.2, "learning_rate": 3.995606206233695e-06, "loss": 1.3593, "step": 201530 }, { "epoch": 9.2, "learning_rate": 3.9933177719804116e-06, "loss": 1.3063, "step": 201540 }, { "epoch": 9.2, "learning_rate": 3.991029337727127e-06, "loss": 1.2766, "step": 201550 }, { "epoch": 9.2, "learning_rate": 3.988740903473843e-06, "loss": 1.3143, "step": 201560 }, { "epoch": 9.2, "learning_rate": 3.986452469220559e-06, "loss": 1.2645, "step": 201570 }, { "epoch": 9.2, "learning_rate": 3.984164034967276e-06, "loss": 1.4851, "step": 201580 }, { "epoch": 9.21, "learning_rate": 3.9818756007139915e-06, "loss": 1.2874, "step": 201590 }, { "epoch": 9.21, "learning_rate": 3.979587166460707e-06, "loss": 1.3437, "step": 201600 }, { "epoch": 9.21, "learning_rate": 3.977298732207424e-06, "loss": 1.3787, "step": 201610 }, { "epoch": 9.21, "learning_rate": 3.97501029795414e-06, "loss": 1.2736, "step": 201620 }, { "epoch": 9.21, "learning_rate": 3.972721863700856e-06, "loss": 1.4412, "step": 201630 }, { "epoch": 9.21, "learning_rate": 3.970433429447572e-06, "loss": 1.2831, "step": 201640 }, { "epoch": 9.21, "learning_rate": 3.968144995194288e-06, "loss": 1.3814, "step": 201650 }, { "epoch": 9.21, "learning_rate": 3.965856560941005e-06, "loss": 1.0766, "step": 201660 }, { "epoch": 9.21, "learning_rate": 3.96356812668772e-06, "loss": 1.3573, "step": 201670 }, { "epoch": 9.21, "learning_rate": 3.9612796924344365e-06, "loss": 1.3197, "step": 201680 }, { "epoch": 9.21, "learning_rate": 3.958991258181153e-06, "loss": 1.1152, "step": 201690 }, { "epoch": 9.21, "learning_rate": 3.956702823927869e-06, "loss": 1.2152, "step": 201700 }, { "epoch": 9.21, "learning_rate": 3.954414389674585e-06, "loss": 1.3893, "step": 201710 }, { "epoch": 9.21, "learning_rate": 3.952125955421301e-06, "loss": 1.4604, "step": 201720 }, { "epoch": 9.21, "learning_rate": 3.949837521168017e-06, "loss": 1.3512, "step": 201730 }, { "epoch": 9.21, "learning_rate": 3.947549086914733e-06, "loss": 1.3465, "step": 201740 }, { "epoch": 9.21, "learning_rate": 3.945260652661449e-06, "loss": 1.4751, "step": 201750 }, { "epoch": 9.21, "learning_rate": 3.942972218408166e-06, "loss": 1.291, "step": 201760 }, { "epoch": 9.21, "learning_rate": 3.9406837841548815e-06, "loss": 1.2741, "step": 201770 }, { "epoch": 9.21, "learning_rate": 3.938395349901597e-06, "loss": 1.3163, "step": 201780 }, { "epoch": 9.21, "learning_rate": 3.936106915648314e-06, "loss": 1.2539, "step": 201790 }, { "epoch": 9.21, "learning_rate": 3.93381848139503e-06, "loss": 1.2851, "step": 201800 }, { "epoch": 9.22, "learning_rate": 3.931530047141746e-06, "loss": 1.3071, "step": 201810 }, { "epoch": 9.22, "learning_rate": 3.9292416128884615e-06, "loss": 1.3634, "step": 201820 }, { "epoch": 9.22, "learning_rate": 3.926953178635178e-06, "loss": 1.321, "step": 201830 }, { "epoch": 9.22, "learning_rate": 3.924664744381895e-06, "loss": 1.2324, "step": 201840 }, { "epoch": 9.22, "learning_rate": 3.92237631012861e-06, "loss": 1.2559, "step": 201850 }, { "epoch": 9.22, "learning_rate": 3.9200878758753265e-06, "loss": 1.3511, "step": 201860 }, { "epoch": 9.22, "learning_rate": 3.917799441622042e-06, "loss": 1.3396, "step": 201870 }, { "epoch": 9.22, "learning_rate": 3.915511007368758e-06, "loss": 1.3038, "step": 201880 }, { "epoch": 9.22, "learning_rate": 3.913222573115474e-06, "loss": 1.262, "step": 201890 }, { "epoch": 9.22, "learning_rate": 3.910934138862191e-06, "loss": 1.4217, "step": 201900 }, { "epoch": 9.22, "learning_rate": 3.908645704608907e-06, "loss": 1.2845, "step": 201910 }, { "epoch": 9.22, "learning_rate": 3.906357270355622e-06, "loss": 1.2478, "step": 201920 }, { "epoch": 9.22, "learning_rate": 3.904068836102339e-06, "loss": 1.2563, "step": 201930 }, { "epoch": 9.22, "learning_rate": 3.901780401849055e-06, "loss": 1.3053, "step": 201940 }, { "epoch": 9.22, "learning_rate": 3.8994919675957715e-06, "loss": 1.4409, "step": 201950 }, { "epoch": 9.22, "learning_rate": 3.897203533342487e-06, "loss": 1.2245, "step": 201960 }, { "epoch": 9.22, "learning_rate": 3.894915099089203e-06, "loss": 1.2773, "step": 201970 }, { "epoch": 9.22, "learning_rate": 3.89262666483592e-06, "loss": 1.1766, "step": 201980 }, { "epoch": 9.22, "learning_rate": 3.890338230582636e-06, "loss": 1.3381, "step": 201990 }, { "epoch": 9.22, "learning_rate": 3.8880497963293515e-06, "loss": 1.3424, "step": 202000 }, { "epoch": 9.22, "learning_rate": 3.885761362076068e-06, "loss": 1.3331, "step": 202010 }, { "epoch": 9.22, "learning_rate": 3.883472927822784e-06, "loss": 1.2348, "step": 202020 }, { "epoch": 9.23, "learning_rate": 3.8811844935695e-06, "loss": 1.3754, "step": 202030 }, { "epoch": 9.23, "learning_rate": 3.878896059316216e-06, "loss": 1.5052, "step": 202040 }, { "epoch": 9.23, "learning_rate": 3.876607625062932e-06, "loss": 1.2327, "step": 202050 }, { "epoch": 9.23, "learning_rate": 3.874319190809648e-06, "loss": 1.3546, "step": 202060 }, { "epoch": 9.23, "learning_rate": 3.872030756556364e-06, "loss": 1.2646, "step": 202070 }, { "epoch": 9.23, "learning_rate": 3.869742322303081e-06, "loss": 1.4252, "step": 202080 }, { "epoch": 9.23, "learning_rate": 3.8674538880497965e-06, "loss": 1.3119, "step": 202090 }, { "epoch": 9.23, "learning_rate": 3.865165453796512e-06, "loss": 1.4101, "step": 202100 }, { "epoch": 9.23, "learning_rate": 3.862877019543229e-06, "loss": 1.4037, "step": 202110 }, { "epoch": 9.23, "learning_rate": 3.860588585289945e-06, "loss": 1.3035, "step": 202120 }, { "epoch": 9.23, "learning_rate": 3.8583001510366615e-06, "loss": 1.3142, "step": 202130 }, { "epoch": 9.23, "learning_rate": 3.8560117167833765e-06, "loss": 1.3614, "step": 202140 }, { "epoch": 9.23, "learning_rate": 3.853723282530093e-06, "loss": 1.3703, "step": 202150 }, { "epoch": 9.23, "learning_rate": 3.85143484827681e-06, "loss": 1.2735, "step": 202160 }, { "epoch": 9.23, "learning_rate": 3.849146414023525e-06, "loss": 1.2984, "step": 202170 }, { "epoch": 9.23, "learning_rate": 3.8468579797702415e-06, "loss": 1.469, "step": 202180 }, { "epoch": 9.23, "learning_rate": 3.844569545516957e-06, "loss": 1.2966, "step": 202190 }, { "epoch": 9.23, "learning_rate": 3.842281111263674e-06, "loss": 1.3925, "step": 202200 }, { "epoch": 9.23, "learning_rate": 3.83999267701039e-06, "loss": 1.2501, "step": 202210 }, { "epoch": 9.23, "learning_rate": 3.837704242757106e-06, "loss": 1.4591, "step": 202220 }, { "epoch": 9.23, "learning_rate": 3.835415808503822e-06, "loss": 1.2289, "step": 202230 }, { "epoch": 9.23, "learning_rate": 3.833127374250538e-06, "loss": 1.4616, "step": 202240 }, { "epoch": 9.24, "learning_rate": 3.830838939997254e-06, "loss": 1.2847, "step": 202250 }, { "epoch": 9.24, "learning_rate": 3.828550505743971e-06, "loss": 1.3876, "step": 202260 }, { "epoch": 9.24, "learning_rate": 3.8262620714906865e-06, "loss": 1.3984, "step": 202270 }, { "epoch": 9.24, "learning_rate": 3.823973637237402e-06, "loss": 1.34, "step": 202280 }, { "epoch": 9.24, "learning_rate": 3.821685202984118e-06, "loss": 1.2635, "step": 202290 }, { "epoch": 9.24, "learning_rate": 3.819396768730835e-06, "loss": 1.1854, "step": 202300 }, { "epoch": 9.24, "learning_rate": 3.817108334477551e-06, "loss": 1.3309, "step": 202310 }, { "epoch": 9.24, "learning_rate": 3.8148199002242664e-06, "loss": 1.1923, "step": 202320 }, { "epoch": 9.24, "learning_rate": 3.812531465970983e-06, "loss": 1.3186, "step": 202330 }, { "epoch": 9.24, "learning_rate": 3.810243031717699e-06, "loss": 1.2144, "step": 202340 }, { "epoch": 9.24, "learning_rate": 3.807954597464415e-06, "loss": 1.3667, "step": 202350 }, { "epoch": 9.24, "learning_rate": 3.805666163211131e-06, "loss": 1.3392, "step": 202360 }, { "epoch": 9.24, "learning_rate": 3.8033777289578473e-06, "loss": 1.2558, "step": 202370 }, { "epoch": 9.24, "learning_rate": 3.8010892947045635e-06, "loss": 1.3435, "step": 202380 }, { "epoch": 9.24, "learning_rate": 3.7988008604512794e-06, "loss": 1.1418, "step": 202390 }, { "epoch": 9.24, "learning_rate": 3.7965124261979956e-06, "loss": 1.4915, "step": 202400 }, { "epoch": 9.24, "learning_rate": 3.7942239919447114e-06, "loss": 1.2692, "step": 202410 }, { "epoch": 9.24, "learning_rate": 3.7919355576914277e-06, "loss": 1.339, "step": 202420 }, { "epoch": 9.24, "learning_rate": 3.789647123438144e-06, "loss": 1.2553, "step": 202430 }, { "epoch": 9.24, "learning_rate": 3.7873586891848598e-06, "loss": 1.3749, "step": 202440 }, { "epoch": 9.24, "learning_rate": 3.785070254931576e-06, "loss": 1.1895, "step": 202450 }, { "epoch": 9.24, "learning_rate": 3.782781820678292e-06, "loss": 1.3758, "step": 202460 }, { "epoch": 9.25, "learning_rate": 3.780493386425008e-06, "loss": 1.2459, "step": 202470 }, { "epoch": 9.25, "learning_rate": 3.7782049521717248e-06, "loss": 1.2923, "step": 202480 }, { "epoch": 9.25, "learning_rate": 3.77591651791844e-06, "loss": 1.2745, "step": 202490 }, { "epoch": 9.25, "learning_rate": 3.7736280836651564e-06, "loss": 1.4309, "step": 202500 }, { "epoch": 9.25, "learning_rate": 3.7713396494118722e-06, "loss": 1.1378, "step": 202510 }, { "epoch": 9.25, "learning_rate": 3.7690512151585885e-06, "loss": 1.3762, "step": 202520 }, { "epoch": 9.25, "learning_rate": 3.766762780905305e-06, "loss": 1.1822, "step": 202530 }, { "epoch": 9.25, "learning_rate": 3.7644743466520206e-06, "loss": 1.3584, "step": 202540 }, { "epoch": 9.25, "learning_rate": 3.7621859123987373e-06, "loss": 1.4283, "step": 202550 }, { "epoch": 9.25, "learning_rate": 3.7598974781454527e-06, "loss": 1.1598, "step": 202560 }, { "epoch": 9.25, "learning_rate": 3.7576090438921693e-06, "loss": 1.3681, "step": 202570 }, { "epoch": 9.25, "learning_rate": 3.7553206096388856e-06, "loss": 1.378, "step": 202580 }, { "epoch": 9.25, "learning_rate": 3.7530321753856014e-06, "loss": 1.229, "step": 202590 }, { "epoch": 9.25, "learning_rate": 3.7507437411323177e-06, "loss": 1.34, "step": 202600 }, { "epoch": 9.25, "learning_rate": 3.7484553068790335e-06, "loss": 1.2036, "step": 202610 }, { "epoch": 9.25, "learning_rate": 3.7461668726257497e-06, "loss": 1.2461, "step": 202620 }, { "epoch": 9.25, "learning_rate": 3.743878438372466e-06, "loss": 1.488, "step": 202630 }, { "epoch": 9.25, "learning_rate": 3.741590004119182e-06, "loss": 1.4918, "step": 202640 }, { "epoch": 9.25, "learning_rate": 3.739301569865898e-06, "loss": 1.3894, "step": 202650 }, { "epoch": 9.25, "learning_rate": 3.737013135612614e-06, "loss": 1.383, "step": 202660 }, { "epoch": 9.25, "learning_rate": 3.73472470135933e-06, "loss": 1.3955, "step": 202670 }, { "epoch": 9.25, "learning_rate": 3.732436267106046e-06, "loss": 1.3503, "step": 202680 }, { "epoch": 9.26, "learning_rate": 3.7301478328527622e-06, "loss": 1.2885, "step": 202690 }, { "epoch": 9.26, "learning_rate": 3.7278593985994785e-06, "loss": 1.3053, "step": 202700 }, { "epoch": 9.26, "learning_rate": 3.7255709643461943e-06, "loss": 1.3984, "step": 202710 }, { "epoch": 9.26, "learning_rate": 3.7232825300929106e-06, "loss": 1.2017, "step": 202720 }, { "epoch": 9.26, "learning_rate": 3.7209940958396264e-06, "loss": 1.2256, "step": 202730 }, { "epoch": 9.26, "learning_rate": 3.7187056615863426e-06, "loss": 1.3281, "step": 202740 }, { "epoch": 9.26, "learning_rate": 3.7164172273330593e-06, "loss": 1.2865, "step": 202750 }, { "epoch": 9.26, "learning_rate": 3.7141287930797747e-06, "loss": 1.2706, "step": 202760 }, { "epoch": 9.26, "learning_rate": 3.7118403588264914e-06, "loss": 1.3915, "step": 202770 }, { "epoch": 9.26, "learning_rate": 3.709551924573207e-06, "loss": 1.6095, "step": 202780 }, { "epoch": 9.26, "learning_rate": 3.7072634903199235e-06, "loss": 1.346, "step": 202790 }, { "epoch": 9.26, "learning_rate": 3.7049750560666397e-06, "loss": 1.3275, "step": 202800 }, { "epoch": 9.26, "learning_rate": 3.702686621813355e-06, "loss": 1.1842, "step": 202810 }, { "epoch": 9.26, "learning_rate": 3.700398187560072e-06, "loss": 1.2586, "step": 202820 }, { "epoch": 9.26, "learning_rate": 3.698109753306787e-06, "loss": 1.2172, "step": 202830 }, { "epoch": 9.26, "learning_rate": 3.695821319053504e-06, "loss": 1.2596, "step": 202840 }, { "epoch": 9.26, "learning_rate": 3.69353288480022e-06, "loss": 1.2965, "step": 202850 }, { "epoch": 9.26, "learning_rate": 3.691244450546936e-06, "loss": 1.5673, "step": 202860 }, { "epoch": 9.26, "learning_rate": 3.688956016293652e-06, "loss": 1.1909, "step": 202870 }, { "epoch": 9.26, "learning_rate": 3.686667582040368e-06, "loss": 1.2083, "step": 202880 }, { "epoch": 9.26, "learning_rate": 3.6843791477870843e-06, "loss": 1.3888, "step": 202890 }, { "epoch": 9.26, "learning_rate": 3.6820907135338005e-06, "loss": 1.3236, "step": 202900 }, { "epoch": 9.27, "learning_rate": 3.6798022792805164e-06, "loss": 1.2922, "step": 202910 }, { "epoch": 9.27, "learning_rate": 3.6775138450272326e-06, "loss": 1.2776, "step": 202920 }, { "epoch": 9.27, "learning_rate": 3.6752254107739484e-06, "loss": 1.3172, "step": 202930 }, { "epoch": 9.27, "learning_rate": 3.6729369765206647e-06, "loss": 1.3799, "step": 202940 }, { "epoch": 9.27, "learning_rate": 3.670648542267381e-06, "loss": 1.2849, "step": 202950 }, { "epoch": 9.27, "learning_rate": 3.6683601080140968e-06, "loss": 1.2018, "step": 202960 }, { "epoch": 9.27, "learning_rate": 3.666071673760813e-06, "loss": 1.3759, "step": 202970 }, { "epoch": 9.27, "learning_rate": 3.663783239507529e-06, "loss": 1.4487, "step": 202980 }, { "epoch": 9.27, "learning_rate": 3.661494805254245e-06, "loss": 1.2677, "step": 202990 }, { "epoch": 9.27, "learning_rate": 3.6592063710009618e-06, "loss": 1.2491, "step": 203000 }, { "epoch": 9.27, "learning_rate": 3.656917936747677e-06, "loss": 1.3661, "step": 203010 }, { "epoch": 9.27, "learning_rate": 3.654629502494394e-06, "loss": 1.3321, "step": 203020 }, { "epoch": 9.27, "learning_rate": 3.6523410682411093e-06, "loss": 1.4631, "step": 203030 }, { "epoch": 9.27, "learning_rate": 3.650052633987826e-06, "loss": 1.2144, "step": 203040 }, { "epoch": 9.27, "learning_rate": 3.647764199734542e-06, "loss": 1.254, "step": 203050 }, { "epoch": 9.27, "learning_rate": 3.645475765481258e-06, "loss": 1.212, "step": 203060 }, { "epoch": 9.27, "learning_rate": 3.6431873312279743e-06, "loss": 1.389, "step": 203070 }, { "epoch": 9.27, "learning_rate": 3.64089889697469e-06, "loss": 1.3417, "step": 203080 }, { "epoch": 9.27, "learning_rate": 3.6386104627214063e-06, "loss": 1.4884, "step": 203090 }, { "epoch": 9.27, "learning_rate": 3.6363220284681217e-06, "loss": 1.4865, "step": 203100 }, { "epoch": 9.27, "learning_rate": 3.6340335942148384e-06, "loss": 1.5123, "step": 203110 }, { "epoch": 9.27, "learning_rate": 3.6317451599615547e-06, "loss": 1.3427, "step": 203120 }, { "epoch": 9.28, "learning_rate": 3.6294567257082705e-06, "loss": 1.4096, "step": 203130 }, { "epoch": 9.28, "learning_rate": 3.6271682914549868e-06, "loss": 1.3864, "step": 203140 }, { "epoch": 9.28, "learning_rate": 3.6248798572017026e-06, "loss": 1.2324, "step": 203150 }, { "epoch": 9.28, "learning_rate": 3.622591422948419e-06, "loss": 1.3435, "step": 203160 }, { "epoch": 9.28, "learning_rate": 3.620302988695135e-06, "loss": 1.2323, "step": 203170 }, { "epoch": 9.28, "learning_rate": 3.618014554441851e-06, "loss": 1.329, "step": 203180 }, { "epoch": 9.28, "learning_rate": 3.615726120188567e-06, "loss": 1.2247, "step": 203190 }, { "epoch": 9.28, "learning_rate": 3.613437685935283e-06, "loss": 1.2986, "step": 203200 }, { "epoch": 9.28, "learning_rate": 3.6111492516819992e-06, "loss": 1.4738, "step": 203210 }, { "epoch": 9.28, "learning_rate": 3.608860817428716e-06, "loss": 1.3047, "step": 203220 }, { "epoch": 9.28, "learning_rate": 3.6065723831754313e-06, "loss": 1.3049, "step": 203230 }, { "epoch": 9.28, "learning_rate": 3.6042839489221476e-06, "loss": 1.3519, "step": 203240 }, { "epoch": 9.28, "learning_rate": 3.6019955146688634e-06, "loss": 1.3376, "step": 203250 }, { "epoch": 9.28, "learning_rate": 3.5997070804155796e-06, "loss": 1.3327, "step": 203260 }, { "epoch": 9.28, "learning_rate": 3.5974186461622963e-06, "loss": 1.5345, "step": 203270 }, { "epoch": 9.28, "learning_rate": 3.5951302119090117e-06, "loss": 1.4315, "step": 203280 }, { "epoch": 9.28, "learning_rate": 3.5928417776557284e-06, "loss": 1.3728, "step": 203290 }, { "epoch": 9.28, "learning_rate": 3.590553343402444e-06, "loss": 1.4048, "step": 203300 }, { "epoch": 9.28, "learning_rate": 3.5882649091491605e-06, "loss": 1.2352, "step": 203310 }, { "epoch": 9.28, "learning_rate": 3.5859764748958767e-06, "loss": 1.3083, "step": 203320 }, { "epoch": 9.28, "learning_rate": 3.5836880406425926e-06, "loss": 1.1992, "step": 203330 }, { "epoch": 9.29, "learning_rate": 3.581399606389309e-06, "loss": 1.3538, "step": 203340 }, { "epoch": 9.29, "learning_rate": 3.5791111721360246e-06, "loss": 1.5477, "step": 203350 }, { "epoch": 9.29, "learning_rate": 3.576822737882741e-06, "loss": 1.1215, "step": 203360 }, { "epoch": 9.29, "learning_rate": 3.574534303629457e-06, "loss": 1.3654, "step": 203370 }, { "epoch": 9.29, "learning_rate": 3.572245869376173e-06, "loss": 1.3247, "step": 203380 }, { "epoch": 9.29, "learning_rate": 3.5699574351228892e-06, "loss": 1.2366, "step": 203390 }, { "epoch": 9.29, "learning_rate": 3.567669000869605e-06, "loss": 1.3473, "step": 203400 }, { "epoch": 9.29, "learning_rate": 3.5653805666163213e-06, "loss": 1.4527, "step": 203410 }, { "epoch": 9.29, "learning_rate": 3.5630921323630375e-06, "loss": 1.3335, "step": 203420 }, { "epoch": 9.29, "learning_rate": 3.5608036981097534e-06, "loss": 1.3065, "step": 203430 }, { "epoch": 9.29, "learning_rate": 3.5585152638564696e-06, "loss": 1.2703, "step": 203440 }, { "epoch": 9.29, "learning_rate": 3.5562268296031855e-06, "loss": 1.2523, "step": 203450 }, { "epoch": 9.29, "learning_rate": 3.5539383953499017e-06, "loss": 1.242, "step": 203460 }, { "epoch": 9.29, "learning_rate": 3.5516499610966175e-06, "loss": 1.4771, "step": 203470 }, { "epoch": 9.29, "learning_rate": 3.5493615268433338e-06, "loss": 1.2756, "step": 203480 }, { "epoch": 9.29, "learning_rate": 3.5470730925900505e-06, "loss": 1.3733, "step": 203490 }, { "epoch": 9.29, "learning_rate": 3.544784658336766e-06, "loss": 1.4586, "step": 203500 }, { "epoch": 9.29, "learning_rate": 3.5424962240834825e-06, "loss": 1.4386, "step": 203510 }, { "epoch": 9.29, "learning_rate": 3.540207789830198e-06, "loss": 1.2717, "step": 203520 }, { "epoch": 9.29, "learning_rate": 3.537919355576914e-06, "loss": 1.3411, "step": 203530 }, { "epoch": 9.29, "learning_rate": 3.535630921323631e-06, "loss": 1.5004, "step": 203540 }, { "epoch": 9.29, "learning_rate": 3.5333424870703463e-06, "loss": 1.3177, "step": 203550 }, { "epoch": 9.3, "learning_rate": 3.531054052817063e-06, "loss": 1.347, "step": 203560 }, { "epoch": 9.3, "learning_rate": 3.5287656185637784e-06, "loss": 1.3994, "step": 203570 }, { "epoch": 9.3, "learning_rate": 3.526477184310495e-06, "loss": 1.2333, "step": 203580 }, { "epoch": 9.3, "learning_rate": 3.5241887500572113e-06, "loss": 1.3384, "step": 203590 }, { "epoch": 9.3, "learning_rate": 3.521900315803927e-06, "loss": 1.293, "step": 203600 }, { "epoch": 9.3, "learning_rate": 3.5196118815506434e-06, "loss": 1.3963, "step": 203610 }, { "epoch": 9.3, "learning_rate": 3.517323447297359e-06, "loss": 1.4919, "step": 203620 }, { "epoch": 9.3, "learning_rate": 3.5150350130440754e-06, "loss": 1.4748, "step": 203630 }, { "epoch": 9.3, "learning_rate": 3.5127465787907917e-06, "loss": 1.3035, "step": 203640 }, { "epoch": 9.3, "learning_rate": 3.5104581445375075e-06, "loss": 1.4917, "step": 203650 }, { "epoch": 9.3, "learning_rate": 3.5081697102842238e-06, "loss": 1.3368, "step": 203660 }, { "epoch": 9.3, "learning_rate": 3.5058812760309396e-06, "loss": 1.2652, "step": 203670 }, { "epoch": 9.3, "learning_rate": 3.503592841777656e-06, "loss": 1.295, "step": 203680 }, { "epoch": 9.3, "learning_rate": 3.501304407524372e-06, "loss": 1.3037, "step": 203690 }, { "epoch": 9.3, "learning_rate": 3.499015973271088e-06, "loss": 1.2487, "step": 203700 }, { "epoch": 9.3, "learning_rate": 3.496727539017804e-06, "loss": 1.2985, "step": 203710 }, { "epoch": 9.3, "learning_rate": 3.49443910476452e-06, "loss": 1.3039, "step": 203720 }, { "epoch": 9.3, "learning_rate": 3.4921506705112363e-06, "loss": 1.4177, "step": 203730 }, { "epoch": 9.3, "learning_rate": 3.489862236257953e-06, "loss": 1.3782, "step": 203740 }, { "epoch": 9.3, "learning_rate": 3.4875738020046683e-06, "loss": 1.296, "step": 203750 }, { "epoch": 9.3, "learning_rate": 3.485285367751385e-06, "loss": 1.2738, "step": 203760 }, { "epoch": 9.3, "learning_rate": 3.4829969334981004e-06, "loss": 1.2966, "step": 203770 }, { "epoch": 9.31, "learning_rate": 3.480708499244817e-06, "loss": 1.3446, "step": 203780 }, { "epoch": 9.31, "learning_rate": 3.4784200649915333e-06, "loss": 1.3717, "step": 203790 }, { "epoch": 9.31, "learning_rate": 3.476131630738249e-06, "loss": 1.3807, "step": 203800 }, { "epoch": 9.31, "learning_rate": 3.4738431964849654e-06, "loss": 1.3054, "step": 203810 }, { "epoch": 9.31, "learning_rate": 3.471554762231681e-06, "loss": 1.2124, "step": 203820 }, { "epoch": 9.31, "learning_rate": 3.4692663279783975e-06, "loss": 1.3575, "step": 203830 }, { "epoch": 9.31, "learning_rate": 3.4669778937251137e-06, "loss": 1.2014, "step": 203840 }, { "epoch": 9.31, "learning_rate": 3.4646894594718296e-06, "loss": 1.2421, "step": 203850 }, { "epoch": 9.31, "learning_rate": 3.462401025218546e-06, "loss": 1.3084, "step": 203860 }, { "epoch": 9.31, "learning_rate": 3.4601125909652617e-06, "loss": 1.1953, "step": 203870 }, { "epoch": 9.31, "learning_rate": 3.457824156711978e-06, "loss": 1.2488, "step": 203880 }, { "epoch": 9.31, "learning_rate": 3.4555357224586937e-06, "loss": 1.298, "step": 203890 }, { "epoch": 9.31, "learning_rate": 3.45324728820541e-06, "loss": 1.3697, "step": 203900 }, { "epoch": 9.31, "learning_rate": 3.4509588539521262e-06, "loss": 1.2238, "step": 203910 }, { "epoch": 9.31, "learning_rate": 3.448670419698842e-06, "loss": 1.4018, "step": 203920 }, { "epoch": 9.31, "learning_rate": 3.4463819854455583e-06, "loss": 1.4479, "step": 203930 }, { "epoch": 9.31, "learning_rate": 3.444093551192274e-06, "loss": 1.4488, "step": 203940 }, { "epoch": 9.31, "learning_rate": 3.4418051169389904e-06, "loss": 1.3906, "step": 203950 }, { "epoch": 9.31, "learning_rate": 3.4395166826857066e-06, "loss": 1.3215, "step": 203960 }, { "epoch": 9.31, "learning_rate": 3.4372282484324225e-06, "loss": 1.2854, "step": 203970 }, { "epoch": 9.31, "learning_rate": 3.4349398141791387e-06, "loss": 1.3797, "step": 203980 }, { "epoch": 9.31, "learning_rate": 3.4326513799258545e-06, "loss": 1.3437, "step": 203990 }, { "epoch": 9.32, "learning_rate": 3.430362945672571e-06, "loss": 1.2034, "step": 204000 }, { "epoch": 9.32, "learning_rate": 3.4280745114192875e-06, "loss": 1.2972, "step": 204010 }, { "epoch": 9.32, "learning_rate": 3.425786077166003e-06, "loss": 1.3216, "step": 204020 }, { "epoch": 9.32, "learning_rate": 3.4234976429127196e-06, "loss": 1.4056, "step": 204030 }, { "epoch": 9.32, "learning_rate": 3.421209208659435e-06, "loss": 1.2262, "step": 204040 }, { "epoch": 9.32, "learning_rate": 3.4189207744061516e-06, "loss": 1.366, "step": 204050 }, { "epoch": 9.32, "learning_rate": 3.416632340152868e-06, "loss": 1.3688, "step": 204060 }, { "epoch": 9.32, "learning_rate": 3.4143439058995837e-06, "loss": 1.3671, "step": 204070 }, { "epoch": 9.32, "learning_rate": 3.4120554716463e-06, "loss": 1.1599, "step": 204080 }, { "epoch": 9.32, "learning_rate": 3.4097670373930158e-06, "loss": 1.3297, "step": 204090 }, { "epoch": 9.32, "learning_rate": 3.407478603139732e-06, "loss": 1.4191, "step": 204100 }, { "epoch": 9.32, "learning_rate": 3.4051901688864483e-06, "loss": 1.2592, "step": 204110 }, { "epoch": 9.32, "learning_rate": 3.402901734633164e-06, "loss": 1.3003, "step": 204120 }, { "epoch": 9.32, "learning_rate": 3.4006133003798804e-06, "loss": 1.3243, "step": 204130 }, { "epoch": 9.32, "learning_rate": 3.398324866126596e-06, "loss": 1.2403, "step": 204140 }, { "epoch": 9.32, "learning_rate": 3.3960364318733124e-06, "loss": 1.2586, "step": 204150 }, { "epoch": 9.32, "learning_rate": 3.3937479976200287e-06, "loss": 1.3908, "step": 204160 }, { "epoch": 9.32, "learning_rate": 3.3914595633667445e-06, "loss": 1.4797, "step": 204170 }, { "epoch": 9.32, "learning_rate": 3.3891711291134608e-06, "loss": 1.2926, "step": 204180 }, { "epoch": 9.32, "learning_rate": 3.3868826948601766e-06, "loss": 1.453, "step": 204190 }, { "epoch": 9.32, "learning_rate": 3.384594260606893e-06, "loss": 1.5018, "step": 204200 }, { "epoch": 9.32, "learning_rate": 3.3823058263536095e-06, "loss": 1.2013, "step": 204210 }, { "epoch": 9.33, "learning_rate": 3.380017392100325e-06, "loss": 1.2722, "step": 204220 }, { "epoch": 9.33, "learning_rate": 3.3777289578470416e-06, "loss": 1.5041, "step": 204230 }, { "epoch": 9.33, "learning_rate": 3.375440523593757e-06, "loss": 1.2101, "step": 204240 }, { "epoch": 9.33, "learning_rate": 3.3731520893404733e-06, "loss": 1.2861, "step": 204250 }, { "epoch": 9.33, "learning_rate": 3.37086365508719e-06, "loss": 1.3062, "step": 204260 }, { "epoch": 9.33, "learning_rate": 3.3685752208339053e-06, "loss": 1.32, "step": 204270 }, { "epoch": 9.33, "learning_rate": 3.366286786580622e-06, "loss": 1.1599, "step": 204280 }, { "epoch": 9.33, "learning_rate": 3.3639983523273374e-06, "loss": 1.3722, "step": 204290 }, { "epoch": 9.33, "learning_rate": 3.361709918074054e-06, "loss": 1.3663, "step": 204300 }, { "epoch": 9.33, "learning_rate": 3.3594214838207695e-06, "loss": 1.2961, "step": 204310 }, { "epoch": 9.33, "learning_rate": 3.357133049567486e-06, "loss": 1.2991, "step": 204320 }, { "epoch": 9.33, "learning_rate": 3.3548446153142024e-06, "loss": 1.2521, "step": 204330 }, { "epoch": 9.33, "learning_rate": 3.3525561810609183e-06, "loss": 1.3989, "step": 204340 }, { "epoch": 9.33, "learning_rate": 3.3502677468076345e-06, "loss": 1.526, "step": 204350 }, { "epoch": 9.33, "learning_rate": 3.3479793125543503e-06, "loss": 1.4187, "step": 204360 }, { "epoch": 9.33, "learning_rate": 3.3456908783010666e-06, "loss": 1.2848, "step": 204370 }, { "epoch": 9.33, "learning_rate": 3.343402444047783e-06, "loss": 1.345, "step": 204380 }, { "epoch": 9.33, "learning_rate": 3.3411140097944987e-06, "loss": 1.2468, "step": 204390 }, { "epoch": 9.33, "learning_rate": 3.338825575541215e-06, "loss": 1.3236, "step": 204400 }, { "epoch": 9.33, "learning_rate": 3.3365371412879307e-06, "loss": 1.3169, "step": 204410 }, { "epoch": 9.33, "learning_rate": 3.334248707034647e-06, "loss": 1.3704, "step": 204420 }, { "epoch": 9.33, "learning_rate": 3.3319602727813632e-06, "loss": 1.2411, "step": 204430 }, { "epoch": 9.34, "learning_rate": 3.329671838528079e-06, "loss": 1.5289, "step": 204440 }, { "epoch": 9.34, "learning_rate": 3.3273834042747953e-06, "loss": 1.4484, "step": 204450 }, { "epoch": 9.34, "learning_rate": 3.325094970021511e-06, "loss": 1.439, "step": 204460 }, { "epoch": 9.34, "learning_rate": 3.3228065357682274e-06, "loss": 1.2444, "step": 204470 }, { "epoch": 9.34, "learning_rate": 3.320518101514944e-06, "loss": 1.4516, "step": 204480 }, { "epoch": 9.34, "learning_rate": 3.3182296672616595e-06, "loss": 1.4259, "step": 204490 }, { "epoch": 9.34, "learning_rate": 3.315941233008376e-06, "loss": 1.2692, "step": 204500 }, { "epoch": 9.34, "learning_rate": 3.3136527987550916e-06, "loss": 1.3332, "step": 204510 }, { "epoch": 9.34, "learning_rate": 3.3113643645018082e-06, "loss": 1.3675, "step": 204520 }, { "epoch": 9.34, "learning_rate": 3.3090759302485245e-06, "loss": 1.4056, "step": 204530 }, { "epoch": 9.34, "learning_rate": 3.30678749599524e-06, "loss": 1.3391, "step": 204540 }, { "epoch": 9.34, "learning_rate": 3.3044990617419566e-06, "loss": 1.3245, "step": 204550 }, { "epoch": 9.34, "learning_rate": 3.302210627488672e-06, "loss": 1.4843, "step": 204560 }, { "epoch": 9.34, "learning_rate": 3.2999221932353886e-06, "loss": 1.2752, "step": 204570 }, { "epoch": 9.34, "learning_rate": 3.297633758982105e-06, "loss": 1.4738, "step": 204580 }, { "epoch": 9.34, "learning_rate": 3.2953453247288207e-06, "loss": 1.3347, "step": 204590 }, { "epoch": 9.34, "learning_rate": 3.293056890475537e-06, "loss": 1.1838, "step": 204600 }, { "epoch": 9.34, "learning_rate": 3.290768456222253e-06, "loss": 1.3856, "step": 204610 }, { "epoch": 9.34, "learning_rate": 3.288480021968969e-06, "loss": 1.2902, "step": 204620 }, { "epoch": 9.34, "learning_rate": 3.2861915877156853e-06, "loss": 1.2726, "step": 204630 }, { "epoch": 9.34, "learning_rate": 3.283903153462401e-06, "loss": 1.2732, "step": 204640 }, { "epoch": 9.34, "learning_rate": 3.2816147192091174e-06, "loss": 1.3654, "step": 204650 }, { "epoch": 9.35, "learning_rate": 3.279326284955833e-06, "loss": 1.21, "step": 204660 }, { "epoch": 9.35, "learning_rate": 3.2770378507025495e-06, "loss": 1.3798, "step": 204670 }, { "epoch": 9.35, "learning_rate": 3.2747494164492653e-06, "loss": 1.2796, "step": 204680 }, { "epoch": 9.35, "learning_rate": 3.2724609821959815e-06, "loss": 1.3086, "step": 204690 }, { "epoch": 9.35, "learning_rate": 3.270172547942698e-06, "loss": 1.2041, "step": 204700 }, { "epoch": 9.35, "learning_rate": 3.2678841136894136e-06, "loss": 1.2389, "step": 204710 }, { "epoch": 9.35, "learning_rate": 3.26559567943613e-06, "loss": 1.428, "step": 204720 }, { "epoch": 9.35, "learning_rate": 3.2633072451828457e-06, "loss": 1.2677, "step": 204730 }, { "epoch": 9.35, "learning_rate": 3.261018810929562e-06, "loss": 1.3658, "step": 204740 }, { "epoch": 9.35, "learning_rate": 3.2587303766762786e-06, "loss": 1.3281, "step": 204750 }, { "epoch": 9.35, "learning_rate": 3.256441942422994e-06, "loss": 1.3374, "step": 204760 }, { "epoch": 9.35, "learning_rate": 3.2541535081697107e-06, "loss": 1.5089, "step": 204770 }, { "epoch": 9.35, "learning_rate": 3.251865073916426e-06, "loss": 1.2414, "step": 204780 }, { "epoch": 9.35, "learning_rate": 3.2495766396631428e-06, "loss": 1.3028, "step": 204790 }, { "epoch": 9.35, "learning_rate": 3.247288205409859e-06, "loss": 1.2776, "step": 204800 }, { "epoch": 9.35, "learning_rate": 3.244999771156575e-06, "loss": 1.2459, "step": 204810 }, { "epoch": 9.35, "learning_rate": 3.242711336903291e-06, "loss": 1.2292, "step": 204820 }, { "epoch": 9.35, "learning_rate": 3.240422902650007e-06, "loss": 1.2773, "step": 204830 }, { "epoch": 9.35, "learning_rate": 3.238134468396723e-06, "loss": 1.2881, "step": 204840 }, { "epoch": 9.35, "learning_rate": 3.2358460341434394e-06, "loss": 1.4971, "step": 204850 }, { "epoch": 9.35, "learning_rate": 3.2335575998901553e-06, "loss": 1.3206, "step": 204860 }, { "epoch": 9.35, "learning_rate": 3.2312691656368715e-06, "loss": 1.3266, "step": 204870 }, { "epoch": 9.36, "learning_rate": 3.2289807313835873e-06, "loss": 1.3019, "step": 204880 }, { "epoch": 9.36, "learning_rate": 3.2266922971303036e-06, "loss": 1.481, "step": 204890 }, { "epoch": 9.36, "learning_rate": 3.22440386287702e-06, "loss": 1.3653, "step": 204900 }, { "epoch": 9.36, "learning_rate": 3.2221154286237357e-06, "loss": 1.2991, "step": 204910 }, { "epoch": 9.36, "learning_rate": 3.219826994370452e-06, "loss": 1.2764, "step": 204920 }, { "epoch": 9.36, "learning_rate": 3.2175385601171678e-06, "loss": 1.3369, "step": 204930 }, { "epoch": 9.36, "learning_rate": 3.215250125863884e-06, "loss": 1.3902, "step": 204940 }, { "epoch": 9.36, "learning_rate": 3.2129616916106007e-06, "loss": 1.2439, "step": 204950 }, { "epoch": 9.36, "learning_rate": 3.210673257357316e-06, "loss": 1.3796, "step": 204960 }, { "epoch": 9.36, "learning_rate": 3.2083848231040323e-06, "loss": 1.28, "step": 204970 }, { "epoch": 9.36, "learning_rate": 3.206096388850748e-06, "loss": 1.2708, "step": 204980 }, { "epoch": 9.36, "learning_rate": 3.2038079545974644e-06, "loss": 1.3253, "step": 204990 }, { "epoch": 9.36, "learning_rate": 3.201519520344181e-06, "loss": 1.1812, "step": 205000 }, { "epoch": 9.36, "learning_rate": 3.1992310860908965e-06, "loss": 1.4871, "step": 205010 }, { "epoch": 9.36, "learning_rate": 3.196942651837613e-06, "loss": 1.4023, "step": 205020 }, { "epoch": 9.36, "learning_rate": 3.1946542175843286e-06, "loss": 1.4786, "step": 205030 }, { "epoch": 9.36, "learning_rate": 3.1923657833310452e-06, "loss": 1.3635, "step": 205040 }, { "epoch": 9.36, "learning_rate": 3.1900773490777615e-06, "loss": 1.3948, "step": 205050 }, { "epoch": 9.36, "learning_rate": 3.1877889148244773e-06, "loss": 1.4127, "step": 205060 }, { "epoch": 9.36, "learning_rate": 3.1855004805711936e-06, "loss": 1.3672, "step": 205070 }, { "epoch": 9.36, "learning_rate": 3.1832120463179094e-06, "loss": 1.3446, "step": 205080 }, { "epoch": 9.36, "learning_rate": 3.1809236120646257e-06, "loss": 1.3642, "step": 205090 }, { "epoch": 9.37, "learning_rate": 3.1786351778113415e-06, "loss": 1.3392, "step": 205100 }, { "epoch": 9.37, "learning_rate": 3.1763467435580577e-06, "loss": 1.2591, "step": 205110 }, { "epoch": 9.37, "learning_rate": 3.174058309304774e-06, "loss": 1.2974, "step": 205120 }, { "epoch": 9.37, "learning_rate": 3.17176987505149e-06, "loss": 1.3077, "step": 205130 }, { "epoch": 9.37, "learning_rate": 3.169481440798206e-06, "loss": 1.2338, "step": 205140 }, { "epoch": 9.37, "learning_rate": 3.167193006544922e-06, "loss": 1.1882, "step": 205150 }, { "epoch": 9.37, "learning_rate": 3.164904572291638e-06, "loss": 1.3321, "step": 205160 }, { "epoch": 9.37, "learning_rate": 3.1626161380383544e-06, "loss": 1.3453, "step": 205170 }, { "epoch": 9.37, "learning_rate": 3.1603277037850702e-06, "loss": 1.3997, "step": 205180 }, { "epoch": 9.37, "learning_rate": 3.1580392695317865e-06, "loss": 1.2613, "step": 205190 }, { "epoch": 9.37, "learning_rate": 3.1557508352785023e-06, "loss": 1.2653, "step": 205200 }, { "epoch": 9.37, "learning_rate": 3.1534624010252185e-06, "loss": 1.4824, "step": 205210 }, { "epoch": 9.37, "learning_rate": 3.1511739667719352e-06, "loss": 1.3115, "step": 205220 }, { "epoch": 9.37, "learning_rate": 3.1488855325186506e-06, "loss": 1.4044, "step": 205230 }, { "epoch": 9.37, "learning_rate": 3.1465970982653673e-06, "loss": 1.3071, "step": 205240 }, { "epoch": 9.37, "learning_rate": 3.1443086640120827e-06, "loss": 1.2418, "step": 205250 }, { "epoch": 9.37, "learning_rate": 3.1420202297587994e-06, "loss": 1.3686, "step": 205260 }, { "epoch": 9.37, "learning_rate": 3.1397317955055156e-06, "loss": 1.2503, "step": 205270 }, { "epoch": 9.37, "learning_rate": 3.137443361252231e-06, "loss": 1.3898, "step": 205280 }, { "epoch": 9.37, "learning_rate": 3.1351549269989477e-06, "loss": 1.2874, "step": 205290 }, { "epoch": 9.37, "learning_rate": 3.132866492745663e-06, "loss": 1.2725, "step": 205300 }, { "epoch": 9.37, "learning_rate": 3.13057805849238e-06, "loss": 1.3665, "step": 205310 }, { "epoch": 9.38, "learning_rate": 3.128289624239096e-06, "loss": 1.3963, "step": 205320 }, { "epoch": 9.38, "learning_rate": 3.126001189985812e-06, "loss": 1.4106, "step": 205330 }, { "epoch": 9.38, "learning_rate": 3.123712755732528e-06, "loss": 1.3171, "step": 205340 }, { "epoch": 9.38, "learning_rate": 3.121424321479244e-06, "loss": 1.2147, "step": 205350 }, { "epoch": 9.38, "learning_rate": 3.11913588722596e-06, "loss": 1.5289, "step": 205360 }, { "epoch": 9.38, "learning_rate": 3.116847452972676e-06, "loss": 1.1786, "step": 205370 }, { "epoch": 9.38, "learning_rate": 3.1145590187193923e-06, "loss": 1.2138, "step": 205380 }, { "epoch": 9.38, "learning_rate": 3.112270584466108e-06, "loss": 1.4544, "step": 205390 }, { "epoch": 9.38, "learning_rate": 3.1099821502128248e-06, "loss": 1.391, "step": 205400 }, { "epoch": 9.38, "learning_rate": 3.1076937159595406e-06, "loss": 1.2998, "step": 205410 }, { "epoch": 9.38, "learning_rate": 3.105405281706257e-06, "loss": 1.3985, "step": 205420 }, { "epoch": 9.38, "learning_rate": 3.1031168474529727e-06, "loss": 1.2484, "step": 205430 }, { "epoch": 9.38, "learning_rate": 3.100828413199689e-06, "loss": 1.4273, "step": 205440 }, { "epoch": 9.38, "learning_rate": 3.098539978946405e-06, "loss": 1.2293, "step": 205450 }, { "epoch": 9.38, "learning_rate": 3.096251544693121e-06, "loss": 1.2569, "step": 205460 }, { "epoch": 9.38, "learning_rate": 3.0939631104398373e-06, "loss": 1.2893, "step": 205470 }, { "epoch": 9.38, "learning_rate": 3.091674676186553e-06, "loss": 1.4839, "step": 205480 }, { "epoch": 9.38, "learning_rate": 3.0893862419332693e-06, "loss": 1.3099, "step": 205490 }, { "epoch": 9.38, "learning_rate": 3.0870978076799856e-06, "loss": 1.2295, "step": 205500 }, { "epoch": 9.38, "learning_rate": 3.084809373426702e-06, "loss": 1.3005, "step": 205510 }, { "epoch": 9.38, "learning_rate": 3.0825209391734177e-06, "loss": 1.2703, "step": 205520 }, { "epoch": 9.39, "learning_rate": 3.080232504920134e-06, "loss": 1.3202, "step": 205530 }, { "epoch": 9.39, "learning_rate": 3.0779440706668498e-06, "loss": 1.3792, "step": 205540 }, { "epoch": 9.39, "learning_rate": 3.075655636413566e-06, "loss": 1.3934, "step": 205550 }, { "epoch": 9.39, "learning_rate": 3.0733672021602823e-06, "loss": 1.438, "step": 205560 }, { "epoch": 9.39, "learning_rate": 3.071078767906998e-06, "loss": 1.2869, "step": 205570 }, { "epoch": 9.39, "learning_rate": 3.0687903336537143e-06, "loss": 1.4013, "step": 205580 }, { "epoch": 9.39, "learning_rate": 3.06650189940043e-06, "loss": 1.4488, "step": 205590 }, { "epoch": 9.39, "learning_rate": 3.0642134651471464e-06, "loss": 1.5872, "step": 205600 }, { "epoch": 9.39, "learning_rate": 3.0619250308938627e-06, "loss": 1.3703, "step": 205610 }, { "epoch": 9.39, "learning_rate": 3.059636596640579e-06, "loss": 1.3825, "step": 205620 }, { "epoch": 9.39, "learning_rate": 3.0573481623872947e-06, "loss": 1.3537, "step": 205630 }, { "epoch": 9.39, "learning_rate": 3.0550597281340106e-06, "loss": 1.2317, "step": 205640 }, { "epoch": 9.39, "learning_rate": 3.052771293880727e-06, "loss": 1.3499, "step": 205650 }, { "epoch": 9.39, "learning_rate": 3.050482859627443e-06, "loss": 1.2823, "step": 205660 }, { "epoch": 9.39, "learning_rate": 3.0481944253741593e-06, "loss": 1.1706, "step": 205670 }, { "epoch": 9.39, "learning_rate": 3.045905991120875e-06, "loss": 1.4098, "step": 205680 }, { "epoch": 9.39, "learning_rate": 3.0436175568675914e-06, "loss": 1.4169, "step": 205690 }, { "epoch": 9.39, "learning_rate": 3.0413291226143072e-06, "loss": 1.22, "step": 205700 }, { "epoch": 9.39, "learning_rate": 3.0390406883610235e-06, "loss": 1.4508, "step": 205710 }, { "epoch": 9.39, "learning_rate": 3.0367522541077397e-06, "loss": 1.3175, "step": 205720 }, { "epoch": 9.39, "learning_rate": 3.0344638198544556e-06, "loss": 1.3247, "step": 205730 }, { "epoch": 9.39, "learning_rate": 3.032175385601172e-06, "loss": 1.3053, "step": 205740 }, { "epoch": 9.4, "learning_rate": 3.0298869513478876e-06, "loss": 1.3382, "step": 205750 }, { "epoch": 9.4, "learning_rate": 3.0275985170946043e-06, "loss": 1.243, "step": 205760 }, { "epoch": 9.4, "learning_rate": 3.02531008284132e-06, "loss": 1.3171, "step": 205770 }, { "epoch": 9.4, "learning_rate": 3.0230216485880364e-06, "loss": 1.2329, "step": 205780 }, { "epoch": 9.4, "learning_rate": 3.0207332143347522e-06, "loss": 1.2951, "step": 205790 }, { "epoch": 9.4, "learning_rate": 3.0184447800814685e-06, "loss": 1.2614, "step": 205800 }, { "epoch": 9.4, "learning_rate": 3.0161563458281843e-06, "loss": 1.4971, "step": 205810 }, { "epoch": 9.4, "learning_rate": 3.0138679115749006e-06, "loss": 1.3089, "step": 205820 }, { "epoch": 9.4, "learning_rate": 3.011579477321617e-06, "loss": 1.198, "step": 205830 }, { "epoch": 9.4, "learning_rate": 3.0092910430683326e-06, "loss": 1.3013, "step": 205840 }, { "epoch": 9.4, "learning_rate": 3.007002608815049e-06, "loss": 1.4717, "step": 205850 }, { "epoch": 9.4, "learning_rate": 3.0047141745617647e-06, "loss": 1.3804, "step": 205860 }, { "epoch": 9.4, "learning_rate": 3.0024257403084814e-06, "loss": 1.4723, "step": 205870 }, { "epoch": 9.4, "learning_rate": 3.000137306055197e-06, "loss": 1.3725, "step": 205880 }, { "epoch": 9.4, "learning_rate": 2.9978488718019135e-06, "loss": 1.0881, "step": 205890 }, { "epoch": 9.4, "learning_rate": 2.9955604375486293e-06, "loss": 1.2079, "step": 205900 }, { "epoch": 9.4, "learning_rate": 2.9932720032953455e-06, "loss": 1.3504, "step": 205910 }, { "epoch": 9.4, "learning_rate": 2.990983569042062e-06, "loss": 1.3075, "step": 205920 }, { "epoch": 9.4, "learning_rate": 2.9886951347887776e-06, "loss": 1.2822, "step": 205930 }, { "epoch": 9.4, "learning_rate": 2.986406700535494e-06, "loss": 1.1449, "step": 205940 }, { "epoch": 9.4, "learning_rate": 2.9841182662822097e-06, "loss": 1.3102, "step": 205950 }, { "epoch": 9.4, "learning_rate": 2.981829832028926e-06, "loss": 1.3082, "step": 205960 }, { "epoch": 9.41, "learning_rate": 2.979541397775642e-06, "loss": 1.3177, "step": 205970 }, { "epoch": 9.41, "learning_rate": 2.9772529635223585e-06, "loss": 1.2787, "step": 205980 }, { "epoch": 9.41, "learning_rate": 2.9749645292690743e-06, "loss": 1.299, "step": 205990 }, { "epoch": 9.41, "learning_rate": 2.97267609501579e-06, "loss": 1.2996, "step": 206000 }, { "epoch": 9.41, "learning_rate": 2.9703876607625064e-06, "loss": 1.2213, "step": 206010 }, { "epoch": 9.41, "learning_rate": 2.968099226509222e-06, "loss": 1.433, "step": 206020 }, { "epoch": 9.41, "learning_rate": 2.965810792255939e-06, "loss": 1.4375, "step": 206030 }, { "epoch": 9.41, "learning_rate": 2.9635223580026547e-06, "loss": 1.4574, "step": 206040 }, { "epoch": 9.41, "learning_rate": 2.961233923749371e-06, "loss": 1.2077, "step": 206050 }, { "epoch": 9.41, "learning_rate": 2.9589454894960868e-06, "loss": 1.3012, "step": 206060 }, { "epoch": 9.41, "learning_rate": 2.956657055242803e-06, "loss": 1.2075, "step": 206070 }, { "epoch": 9.41, "learning_rate": 2.9543686209895193e-06, "loss": 1.5154, "step": 206080 }, { "epoch": 9.41, "learning_rate": 2.952080186736235e-06, "loss": 1.288, "step": 206090 }, { "epoch": 9.41, "learning_rate": 2.9497917524829513e-06, "loss": 1.2805, "step": 206100 }, { "epoch": 9.41, "learning_rate": 2.947503318229667e-06, "loss": 1.274, "step": 206110 }, { "epoch": 9.41, "learning_rate": 2.9452148839763834e-06, "loss": 1.269, "step": 206120 }, { "epoch": 9.41, "learning_rate": 2.9429264497230997e-06, "loss": 1.2455, "step": 206130 }, { "epoch": 9.41, "learning_rate": 2.940638015469816e-06, "loss": 1.3505, "step": 206140 }, { "epoch": 9.41, "learning_rate": 2.9383495812165318e-06, "loss": 1.5979, "step": 206150 }, { "epoch": 9.41, "learning_rate": 2.936061146963248e-06, "loss": 1.3194, "step": 206160 }, { "epoch": 9.41, "learning_rate": 2.933772712709964e-06, "loss": 1.3901, "step": 206170 }, { "epoch": 9.41, "learning_rate": 2.93148427845668e-06, "loss": 1.427, "step": 206180 }, { "epoch": 9.42, "learning_rate": 2.9291958442033963e-06, "loss": 1.3487, "step": 206190 }, { "epoch": 9.42, "learning_rate": 2.926907409950112e-06, "loss": 1.3143, "step": 206200 }, { "epoch": 9.42, "learning_rate": 2.9246189756968284e-06, "loss": 1.3324, "step": 206210 }, { "epoch": 9.42, "learning_rate": 2.9223305414435442e-06, "loss": 1.3538, "step": 206220 }, { "epoch": 9.42, "learning_rate": 2.9200421071902605e-06, "loss": 1.3631, "step": 206230 }, { "epoch": 9.42, "learning_rate": 2.9177536729369767e-06, "loss": 1.2405, "step": 206240 }, { "epoch": 9.42, "learning_rate": 2.915465238683693e-06, "loss": 1.2707, "step": 206250 }, { "epoch": 9.42, "learning_rate": 2.913176804430409e-06, "loss": 1.3527, "step": 206260 }, { "epoch": 9.42, "learning_rate": 2.910888370177125e-06, "loss": 1.2532, "step": 206270 }, { "epoch": 9.42, "learning_rate": 2.908599935923841e-06, "loss": 1.4346, "step": 206280 }, { "epoch": 9.42, "learning_rate": 2.906311501670557e-06, "loss": 1.3782, "step": 206290 }, { "epoch": 9.42, "learning_rate": 2.9040230674172734e-06, "loss": 1.3259, "step": 206300 }, { "epoch": 9.42, "learning_rate": 2.9017346331639892e-06, "loss": 1.2973, "step": 206310 }, { "epoch": 9.42, "learning_rate": 2.8994461989107055e-06, "loss": 1.3575, "step": 206320 }, { "epoch": 9.42, "learning_rate": 2.8971577646574213e-06, "loss": 1.217, "step": 206330 }, { "epoch": 9.42, "learning_rate": 2.894869330404138e-06, "loss": 1.303, "step": 206340 }, { "epoch": 9.42, "learning_rate": 2.892580896150854e-06, "loss": 1.2928, "step": 206350 }, { "epoch": 9.42, "learning_rate": 2.8902924618975696e-06, "loss": 1.4175, "step": 206360 }, { "epoch": 9.42, "learning_rate": 2.888004027644286e-06, "loss": 1.3633, "step": 206370 }, { "epoch": 9.42, "learning_rate": 2.8857155933910017e-06, "loss": 1.2861, "step": 206380 }, { "epoch": 9.42, "learning_rate": 2.8834271591377184e-06, "loss": 1.3849, "step": 206390 }, { "epoch": 9.42, "learning_rate": 2.8811387248844342e-06, "loss": 1.4668, "step": 206400 }, { "epoch": 9.43, "learning_rate": 2.8788502906311505e-06, "loss": 1.2715, "step": 206410 }, { "epoch": 9.43, "learning_rate": 2.8765618563778663e-06, "loss": 1.385, "step": 206420 }, { "epoch": 9.43, "learning_rate": 2.8742734221245826e-06, "loss": 1.2459, "step": 206430 }, { "epoch": 9.43, "learning_rate": 2.8719849878712984e-06, "loss": 1.4487, "step": 206440 }, { "epoch": 9.43, "learning_rate": 2.8696965536180146e-06, "loss": 1.2352, "step": 206450 }, { "epoch": 9.43, "learning_rate": 2.867408119364731e-06, "loss": 1.2867, "step": 206460 }, { "epoch": 9.43, "learning_rate": 2.8651196851114467e-06, "loss": 1.4513, "step": 206470 }, { "epoch": 9.43, "learning_rate": 2.862831250858163e-06, "loss": 1.5033, "step": 206480 }, { "epoch": 9.43, "learning_rate": 2.860542816604879e-06, "loss": 1.326, "step": 206490 }, { "epoch": 9.43, "learning_rate": 2.8582543823515955e-06, "loss": 1.3141, "step": 206500 }, { "epoch": 9.43, "learning_rate": 2.8559659480983113e-06, "loss": 1.3159, "step": 206510 }, { "epoch": 9.43, "learning_rate": 2.8536775138450275e-06, "loss": 1.4307, "step": 206520 }, { "epoch": 9.43, "learning_rate": 2.8513890795917434e-06, "loss": 1.4522, "step": 206530 }, { "epoch": 9.43, "learning_rate": 2.8491006453384596e-06, "loss": 1.3299, "step": 206540 }, { "epoch": 9.43, "learning_rate": 2.846812211085176e-06, "loss": 1.3177, "step": 206550 }, { "epoch": 9.43, "learning_rate": 2.8445237768318917e-06, "loss": 1.3969, "step": 206560 }, { "epoch": 9.43, "learning_rate": 2.842235342578608e-06, "loss": 1.2856, "step": 206570 }, { "epoch": 9.43, "learning_rate": 2.8399469083253238e-06, "loss": 1.3644, "step": 206580 }, { "epoch": 9.43, "learning_rate": 2.83765847407204e-06, "loss": 1.3712, "step": 206590 }, { "epoch": 9.43, "learning_rate": 2.835370039818756e-06, "loss": 1.3989, "step": 206600 }, { "epoch": 9.43, "learning_rate": 2.8330816055654725e-06, "loss": 1.2405, "step": 206610 }, { "epoch": 9.43, "learning_rate": 2.8307931713121884e-06, "loss": 1.3743, "step": 206620 }, { "epoch": 9.44, "learning_rate": 2.8285047370589046e-06, "loss": 1.2969, "step": 206630 }, { "epoch": 9.44, "learning_rate": 2.8262163028056204e-06, "loss": 1.4584, "step": 206640 }, { "epoch": 9.44, "learning_rate": 2.8239278685523363e-06, "loss": 1.39, "step": 206650 }, { "epoch": 9.44, "learning_rate": 2.821639434299053e-06, "loss": 1.4088, "step": 206660 }, { "epoch": 9.44, "learning_rate": 2.8193510000457688e-06, "loss": 1.3483, "step": 206670 }, { "epoch": 9.44, "learning_rate": 2.817062565792485e-06, "loss": 1.3199, "step": 206680 }, { "epoch": 9.44, "learning_rate": 2.814774131539201e-06, "loss": 1.2956, "step": 206690 }, { "epoch": 9.44, "learning_rate": 2.812485697285917e-06, "loss": 1.4447, "step": 206700 }, { "epoch": 9.44, "learning_rate": 2.8101972630326333e-06, "loss": 1.299, "step": 206710 }, { "epoch": 9.44, "learning_rate": 2.807908828779349e-06, "loss": 1.237, "step": 206720 }, { "epoch": 9.44, "learning_rate": 2.8056203945260654e-06, "loss": 1.2084, "step": 206730 }, { "epoch": 9.44, "learning_rate": 2.8033319602727813e-06, "loss": 1.3174, "step": 206740 }, { "epoch": 9.44, "learning_rate": 2.8010435260194975e-06, "loss": 1.2106, "step": 206750 }, { "epoch": 9.44, "learning_rate": 2.7987550917662138e-06, "loss": 1.4779, "step": 206760 }, { "epoch": 9.44, "learning_rate": 2.79646665751293e-06, "loss": 1.2941, "step": 206770 }, { "epoch": 9.44, "learning_rate": 2.794178223259646e-06, "loss": 1.3658, "step": 206780 }, { "epoch": 9.44, "learning_rate": 2.791889789006362e-06, "loss": 1.3053, "step": 206790 }, { "epoch": 9.44, "learning_rate": 2.789601354753078e-06, "loss": 1.2544, "step": 206800 }, { "epoch": 9.44, "learning_rate": 2.787312920499794e-06, "loss": 1.4708, "step": 206810 }, { "epoch": 9.44, "learning_rate": 2.7850244862465104e-06, "loss": 1.2891, "step": 206820 }, { "epoch": 9.44, "learning_rate": 2.7827360519932262e-06, "loss": 1.3043, "step": 206830 }, { "epoch": 9.44, "learning_rate": 2.7804476177399425e-06, "loss": 1.4017, "step": 206840 }, { "epoch": 9.45, "learning_rate": 2.7781591834866583e-06, "loss": 1.2431, "step": 206850 }, { "epoch": 9.45, "learning_rate": 2.7758707492333746e-06, "loss": 1.2351, "step": 206860 }, { "epoch": 9.45, "learning_rate": 2.773582314980091e-06, "loss": 1.3709, "step": 206870 }, { "epoch": 9.45, "learning_rate": 2.771293880726807e-06, "loss": 1.2597, "step": 206880 }, { "epoch": 9.45, "learning_rate": 2.769005446473523e-06, "loss": 1.3056, "step": 206890 }, { "epoch": 9.45, "learning_rate": 2.766717012220239e-06, "loss": 1.3152, "step": 206900 }, { "epoch": 9.45, "learning_rate": 2.764428577966955e-06, "loss": 1.3009, "step": 206910 }, { "epoch": 9.45, "learning_rate": 2.7621401437136712e-06, "loss": 1.3644, "step": 206920 }, { "epoch": 9.45, "learning_rate": 2.7598517094603875e-06, "loss": 1.278, "step": 206930 }, { "epoch": 9.45, "learning_rate": 2.7575632752071033e-06, "loss": 1.311, "step": 206940 }, { "epoch": 9.45, "learning_rate": 2.7552748409538196e-06, "loss": 1.3715, "step": 206950 }, { "epoch": 9.45, "learning_rate": 2.7529864067005354e-06, "loss": 1.3459, "step": 206960 }, { "epoch": 9.45, "learning_rate": 2.750697972447252e-06, "loss": 1.3092, "step": 206970 }, { "epoch": 9.45, "learning_rate": 2.748409538193968e-06, "loss": 1.3339, "step": 206980 }, { "epoch": 9.45, "learning_rate": 2.746121103940684e-06, "loss": 1.185, "step": 206990 }, { "epoch": 9.45, "learning_rate": 2.7438326696874e-06, "loss": 1.2868, "step": 207000 }, { "epoch": 9.45, "learning_rate": 2.741544235434116e-06, "loss": 1.3166, "step": 207010 }, { "epoch": 9.45, "learning_rate": 2.739255801180832e-06, "loss": 1.3461, "step": 207020 }, { "epoch": 9.45, "learning_rate": 2.7369673669275483e-06, "loss": 1.4183, "step": 207030 }, { "epoch": 9.45, "learning_rate": 2.7346789326742646e-06, "loss": 1.2354, "step": 207040 }, { "epoch": 9.45, "learning_rate": 2.7323904984209804e-06, "loss": 1.3057, "step": 207050 }, { "epoch": 9.45, "learning_rate": 2.7301020641676966e-06, "loss": 1.2332, "step": 207060 }, { "epoch": 9.46, "learning_rate": 2.7278136299144125e-06, "loss": 1.4024, "step": 207070 }, { "epoch": 9.46, "learning_rate": 2.7255251956611287e-06, "loss": 1.3529, "step": 207080 }, { "epoch": 9.46, "learning_rate": 2.723236761407845e-06, "loss": 1.2943, "step": 207090 }, { "epoch": 9.46, "learning_rate": 2.720948327154561e-06, "loss": 1.3472, "step": 207100 }, { "epoch": 9.46, "learning_rate": 2.718659892901277e-06, "loss": 1.3688, "step": 207110 }, { "epoch": 9.46, "learning_rate": 2.716371458647993e-06, "loss": 1.2771, "step": 207120 }, { "epoch": 9.46, "learning_rate": 2.7140830243947095e-06, "loss": 1.2107, "step": 207130 }, { "epoch": 9.46, "learning_rate": 2.7117945901414254e-06, "loss": 1.3437, "step": 207140 }, { "epoch": 9.46, "learning_rate": 2.7095061558881416e-06, "loss": 1.521, "step": 207150 }, { "epoch": 9.46, "learning_rate": 2.7072177216348575e-06, "loss": 1.3653, "step": 207160 }, { "epoch": 9.46, "learning_rate": 2.7049292873815737e-06, "loss": 1.378, "step": 207170 }, { "epoch": 9.46, "learning_rate": 2.70264085312829e-06, "loss": 1.2635, "step": 207180 }, { "epoch": 9.46, "learning_rate": 2.7003524188750058e-06, "loss": 1.3815, "step": 207190 }, { "epoch": 9.46, "learning_rate": 2.698063984621722e-06, "loss": 1.3517, "step": 207200 }, { "epoch": 9.46, "learning_rate": 2.695775550368438e-06, "loss": 1.1744, "step": 207210 }, { "epoch": 9.46, "learning_rate": 2.693487116115154e-06, "loss": 1.4003, "step": 207220 }, { "epoch": 9.46, "learning_rate": 2.69119868186187e-06, "loss": 1.2484, "step": 207230 }, { "epoch": 9.46, "learning_rate": 2.6889102476085866e-06, "loss": 1.2165, "step": 207240 }, { "epoch": 9.46, "learning_rate": 2.6866218133553024e-06, "loss": 1.4351, "step": 207250 }, { "epoch": 9.46, "learning_rate": 2.6843333791020187e-06, "loss": 1.2567, "step": 207260 }, { "epoch": 9.46, "learning_rate": 2.6820449448487345e-06, "loss": 1.3495, "step": 207270 }, { "epoch": 9.46, "learning_rate": 2.6797565105954508e-06, "loss": 1.247, "step": 207280 }, { "epoch": 9.47, "learning_rate": 2.677468076342167e-06, "loss": 1.4047, "step": 207290 }, { "epoch": 9.47, "learning_rate": 2.675179642088883e-06, "loss": 1.2845, "step": 207300 }, { "epoch": 9.47, "learning_rate": 2.672891207835599e-06, "loss": 1.3026, "step": 207310 }, { "epoch": 9.47, "learning_rate": 2.670602773582315e-06, "loss": 1.2039, "step": 207320 }, { "epoch": 9.47, "learning_rate": 2.668314339329031e-06, "loss": 1.3379, "step": 207330 }, { "epoch": 9.47, "learning_rate": 2.6660259050757474e-06, "loss": 1.4255, "step": 207340 }, { "epoch": 9.47, "learning_rate": 2.6637374708224637e-06, "loss": 1.3307, "step": 207350 }, { "epoch": 9.47, "learning_rate": 2.6614490365691795e-06, "loss": 1.3869, "step": 207360 }, { "epoch": 9.47, "learning_rate": 2.6591606023158953e-06, "loss": 1.2147, "step": 207370 }, { "epoch": 9.47, "learning_rate": 2.6568721680626116e-06, "loss": 1.37, "step": 207380 }, { "epoch": 9.47, "learning_rate": 2.654583733809328e-06, "loss": 1.3933, "step": 207390 }, { "epoch": 9.47, "learning_rate": 2.652295299556044e-06, "loss": 1.3344, "step": 207400 }, { "epoch": 9.47, "learning_rate": 2.65000686530276e-06, "loss": 1.3915, "step": 207410 }, { "epoch": 9.47, "learning_rate": 2.647718431049476e-06, "loss": 1.4167, "step": 207420 }, { "epoch": 9.47, "learning_rate": 2.645429996796192e-06, "loss": 1.2604, "step": 207430 }, { "epoch": 9.47, "learning_rate": 2.6431415625429082e-06, "loss": 1.3162, "step": 207440 }, { "epoch": 9.47, "learning_rate": 2.6408531282896245e-06, "loss": 1.2897, "step": 207450 }, { "epoch": 9.47, "learning_rate": 2.6385646940363403e-06, "loss": 1.3667, "step": 207460 }, { "epoch": 9.47, "learning_rate": 2.6362762597830566e-06, "loss": 1.5164, "step": 207470 }, { "epoch": 9.47, "learning_rate": 2.6339878255297724e-06, "loss": 1.1839, "step": 207480 }, { "epoch": 9.47, "learning_rate": 2.6316993912764887e-06, "loss": 1.1774, "step": 207490 }, { "epoch": 9.47, "learning_rate": 2.629410957023205e-06, "loss": 1.2895, "step": 207500 }, { "epoch": 9.48, "learning_rate": 2.627122522769921e-06, "loss": 1.2786, "step": 207510 }, { "epoch": 9.48, "learning_rate": 2.624834088516637e-06, "loss": 1.174, "step": 207520 }, { "epoch": 9.48, "learning_rate": 2.6225456542633532e-06, "loss": 1.4169, "step": 207530 }, { "epoch": 9.48, "learning_rate": 2.620257220010069e-06, "loss": 1.4226, "step": 207540 }, { "epoch": 9.48, "learning_rate": 2.6179687857567853e-06, "loss": 1.3327, "step": 207550 }, { "epoch": 9.48, "learning_rate": 2.6156803515035016e-06, "loss": 1.3212, "step": 207560 }, { "epoch": 9.48, "learning_rate": 2.6133919172502174e-06, "loss": 1.37, "step": 207570 }, { "epoch": 9.48, "learning_rate": 2.6111034829969336e-06, "loss": 1.3612, "step": 207580 }, { "epoch": 9.48, "learning_rate": 2.6088150487436495e-06, "loss": 1.2547, "step": 207590 }, { "epoch": 9.48, "learning_rate": 2.606526614490366e-06, "loss": 1.3961, "step": 207600 }, { "epoch": 9.48, "learning_rate": 2.604238180237082e-06, "loss": 1.3399, "step": 207610 }, { "epoch": 9.48, "learning_rate": 2.6019497459837982e-06, "loss": 1.2389, "step": 207620 }, { "epoch": 9.48, "learning_rate": 2.599661311730514e-06, "loss": 1.3064, "step": 207630 }, { "epoch": 9.48, "learning_rate": 2.5973728774772303e-06, "loss": 1.344, "step": 207640 }, { "epoch": 9.48, "learning_rate": 2.595084443223946e-06, "loss": 1.3859, "step": 207650 }, { "epoch": 9.48, "learning_rate": 2.5927960089706624e-06, "loss": 1.423, "step": 207660 }, { "epoch": 9.48, "learning_rate": 2.5905075747173786e-06, "loss": 1.3, "step": 207670 }, { "epoch": 9.48, "learning_rate": 2.5882191404640945e-06, "loss": 1.3008, "step": 207680 }, { "epoch": 9.48, "learning_rate": 2.5859307062108107e-06, "loss": 1.3009, "step": 207690 }, { "epoch": 9.48, "learning_rate": 2.5836422719575265e-06, "loss": 1.3691, "step": 207700 }, { "epoch": 9.48, "learning_rate": 2.5813538377042432e-06, "loss": 1.3566, "step": 207710 }, { "epoch": 9.49, "learning_rate": 2.579065403450959e-06, "loss": 1.3707, "step": 207720 }, { "epoch": 9.49, "learning_rate": 2.5767769691976753e-06, "loss": 1.3784, "step": 207730 }, { "epoch": 9.49, "learning_rate": 2.574488534944391e-06, "loss": 1.4236, "step": 207740 }, { "epoch": 9.49, "learning_rate": 2.572200100691107e-06, "loss": 1.2027, "step": 207750 }, { "epoch": 9.49, "learning_rate": 2.5699116664378236e-06, "loss": 1.4148, "step": 207760 }, { "epoch": 9.49, "learning_rate": 2.5676232321845395e-06, "loss": 1.3042, "step": 207770 }, { "epoch": 9.49, "learning_rate": 2.5653347979312557e-06, "loss": 1.3251, "step": 207780 }, { "epoch": 9.49, "learning_rate": 2.5630463636779715e-06, "loss": 1.3642, "step": 207790 }, { "epoch": 9.49, "learning_rate": 2.5607579294246878e-06, "loss": 1.343, "step": 207800 }, { "epoch": 9.49, "learning_rate": 2.5584694951714036e-06, "loss": 1.2657, "step": 207810 }, { "epoch": 9.49, "learning_rate": 2.55618106091812e-06, "loss": 1.2622, "step": 207820 }, { "epoch": 9.49, "learning_rate": 2.553892626664836e-06, "loss": 1.4114, "step": 207830 }, { "epoch": 9.49, "learning_rate": 2.551604192411552e-06, "loss": 1.3805, "step": 207840 }, { "epoch": 9.49, "learning_rate": 2.549315758158268e-06, "loss": 1.2846, "step": 207850 }, { "epoch": 9.49, "learning_rate": 2.547027323904984e-06, "loss": 1.4222, "step": 207860 }, { "epoch": 9.49, "learning_rate": 2.5447388896517007e-06, "loss": 1.1518, "step": 207870 }, { "epoch": 9.49, "learning_rate": 2.5424504553984165e-06, "loss": 1.3459, "step": 207880 }, { "epoch": 9.49, "learning_rate": 2.5401620211451328e-06, "loss": 1.3388, "step": 207890 }, { "epoch": 9.49, "learning_rate": 2.5378735868918486e-06, "loss": 1.2989, "step": 207900 }, { "epoch": 9.49, "learning_rate": 2.535585152638565e-06, "loss": 1.3206, "step": 207910 }, { "epoch": 9.49, "learning_rate": 2.533296718385281e-06, "loss": 1.2918, "step": 207920 }, { "epoch": 9.49, "learning_rate": 2.531008284131997e-06, "loss": 1.2835, "step": 207930 }, { "epoch": 9.5, "learning_rate": 2.528719849878713e-06, "loss": 1.4281, "step": 207940 }, { "epoch": 9.5, "learning_rate": 2.526431415625429e-06, "loss": 1.3294, "step": 207950 }, { "epoch": 9.5, "learning_rate": 2.5241429813721453e-06, "loss": 1.271, "step": 207960 }, { "epoch": 9.5, "learning_rate": 2.5218545471188615e-06, "loss": 1.3376, "step": 207970 }, { "epoch": 9.5, "learning_rate": 2.5195661128655778e-06, "loss": 1.4179, "step": 207980 }, { "epoch": 9.5, "learning_rate": 2.5172776786122936e-06, "loss": 1.1902, "step": 207990 }, { "epoch": 9.5, "learning_rate": 2.51498924435901e-06, "loss": 1.4644, "step": 208000 }, { "epoch": 9.5, "learning_rate": 2.5127008101057257e-06, "loss": 1.5089, "step": 208010 }, { "epoch": 9.5, "learning_rate": 2.510412375852442e-06, "loss": 1.3967, "step": 208020 }, { "epoch": 9.5, "learning_rate": 2.508123941599158e-06, "loss": 1.4586, "step": 208030 }, { "epoch": 9.5, "learning_rate": 2.505835507345874e-06, "loss": 1.3264, "step": 208040 }, { "epoch": 9.5, "learning_rate": 2.5035470730925902e-06, "loss": 1.47, "step": 208050 }, { "epoch": 9.5, "learning_rate": 2.501258638839306e-06, "loss": 1.4923, "step": 208060 }, { "epoch": 9.5, "learning_rate": 2.4989702045860223e-06, "loss": 1.3223, "step": 208070 }, { "epoch": 9.5, "learning_rate": 2.4966817703327386e-06, "loss": 1.4185, "step": 208080 }, { "epoch": 9.5, "learning_rate": 2.494393336079455e-06, "loss": 1.4403, "step": 208090 }, { "epoch": 9.5, "learning_rate": 2.4921049018261707e-06, "loss": 1.4959, "step": 208100 }, { "epoch": 9.5, "learning_rate": 2.4898164675728865e-06, "loss": 1.3129, "step": 208110 }, { "epoch": 9.5, "learning_rate": 2.4875280333196027e-06, "loss": 1.2832, "step": 208120 }, { "epoch": 9.5, "learning_rate": 2.485239599066319e-06, "loss": 1.3473, "step": 208130 }, { "epoch": 9.5, "learning_rate": 2.4829511648130352e-06, "loss": 1.4933, "step": 208140 }, { "epoch": 9.5, "learning_rate": 2.480662730559751e-06, "loss": 1.4981, "step": 208150 }, { "epoch": 9.51, "learning_rate": 2.4783742963064673e-06, "loss": 1.3355, "step": 208160 }, { "epoch": 9.51, "learning_rate": 2.476085862053183e-06, "loss": 1.3233, "step": 208170 }, { "epoch": 9.51, "learning_rate": 2.4737974277998994e-06, "loss": 1.3052, "step": 208180 }, { "epoch": 9.51, "learning_rate": 2.4715089935466156e-06, "loss": 1.3653, "step": 208190 }, { "epoch": 9.51, "learning_rate": 2.4692205592933315e-06, "loss": 1.3918, "step": 208200 }, { "epoch": 9.51, "learning_rate": 2.4669321250400477e-06, "loss": 1.3209, "step": 208210 }, { "epoch": 9.51, "learning_rate": 2.4646436907867636e-06, "loss": 1.2668, "step": 208220 }, { "epoch": 9.51, "learning_rate": 2.46235525653348e-06, "loss": 1.5006, "step": 208230 }, { "epoch": 9.51, "learning_rate": 2.460066822280196e-06, "loss": 1.3224, "step": 208240 }, { "epoch": 9.51, "learning_rate": 2.4577783880269123e-06, "loss": 1.3709, "step": 208250 }, { "epoch": 9.51, "learning_rate": 2.455489953773628e-06, "loss": 1.3191, "step": 208260 }, { "epoch": 9.51, "learning_rate": 2.4532015195203444e-06, "loss": 1.2665, "step": 208270 }, { "epoch": 9.51, "learning_rate": 2.4509130852670602e-06, "loss": 1.3331, "step": 208280 }, { "epoch": 9.51, "learning_rate": 2.4486246510137765e-06, "loss": 1.4178, "step": 208290 }, { "epoch": 9.51, "learning_rate": 2.4463362167604927e-06, "loss": 1.2979, "step": 208300 }, { "epoch": 9.51, "learning_rate": 2.4440477825072085e-06, "loss": 1.4462, "step": 208310 }, { "epoch": 9.51, "learning_rate": 2.441759348253925e-06, "loss": 1.3079, "step": 208320 }, { "epoch": 9.51, "learning_rate": 2.4394709140006406e-06, "loss": 1.411, "step": 208330 }, { "epoch": 9.51, "learning_rate": 2.4371824797473573e-06, "loss": 1.4125, "step": 208340 }, { "epoch": 9.51, "learning_rate": 2.434894045494073e-06, "loss": 1.3753, "step": 208350 }, { "epoch": 9.51, "learning_rate": 2.4326056112407894e-06, "loss": 1.2649, "step": 208360 }, { "epoch": 9.51, "learning_rate": 2.430317176987505e-06, "loss": 1.3599, "step": 208370 }, { "epoch": 9.52, "learning_rate": 2.4280287427342215e-06, "loss": 1.2849, "step": 208380 }, { "epoch": 9.52, "learning_rate": 2.4257403084809377e-06, "loss": 1.4026, "step": 208390 }, { "epoch": 9.52, "learning_rate": 2.4234518742276535e-06, "loss": 1.3016, "step": 208400 }, { "epoch": 9.52, "learning_rate": 2.4211634399743698e-06, "loss": 1.3035, "step": 208410 }, { "epoch": 9.52, "learning_rate": 2.4188750057210856e-06, "loss": 1.3544, "step": 208420 }, { "epoch": 9.52, "learning_rate": 2.416586571467802e-06, "loss": 1.3402, "step": 208430 }, { "epoch": 9.52, "learning_rate": 2.4142981372145177e-06, "loss": 1.443, "step": 208440 }, { "epoch": 9.52, "learning_rate": 2.4120097029612344e-06, "loss": 1.3221, "step": 208450 }, { "epoch": 9.52, "learning_rate": 2.40972126870795e-06, "loss": 1.2359, "step": 208460 }, { "epoch": 9.52, "learning_rate": 2.407432834454666e-06, "loss": 1.3555, "step": 208470 }, { "epoch": 9.52, "learning_rate": 2.4051444002013823e-06, "loss": 1.3264, "step": 208480 }, { "epoch": 9.52, "learning_rate": 2.402855965948098e-06, "loss": 1.3361, "step": 208490 }, { "epoch": 9.52, "learning_rate": 2.4005675316948148e-06, "loss": 1.4586, "step": 208500 }, { "epoch": 9.52, "learning_rate": 2.3982790974415306e-06, "loss": 1.3805, "step": 208510 }, { "epoch": 9.52, "learning_rate": 2.395990663188247e-06, "loss": 1.4065, "step": 208520 }, { "epoch": 9.52, "learning_rate": 2.3937022289349627e-06, "loss": 1.3497, "step": 208530 }, { "epoch": 9.52, "learning_rate": 2.391413794681679e-06, "loss": 1.4005, "step": 208540 }, { "epoch": 9.52, "learning_rate": 2.389125360428395e-06, "loss": 1.3371, "step": 208550 }, { "epoch": 9.52, "learning_rate": 2.386836926175111e-06, "loss": 1.3341, "step": 208560 }, { "epoch": 9.52, "learning_rate": 2.3845484919218273e-06, "loss": 1.3804, "step": 208570 }, { "epoch": 9.52, "learning_rate": 2.382260057668543e-06, "loss": 1.3521, "step": 208580 }, { "epoch": 9.52, "learning_rate": 2.3799716234152593e-06, "loss": 1.3446, "step": 208590 }, { "epoch": 9.53, "learning_rate": 2.3776831891619756e-06, "loss": 1.2782, "step": 208600 }, { "epoch": 9.53, "learning_rate": 2.375394754908692e-06, "loss": 1.3169, "step": 208610 }, { "epoch": 9.53, "learning_rate": 2.3731063206554077e-06, "loss": 1.3872, "step": 208620 }, { "epoch": 9.53, "learning_rate": 2.370817886402124e-06, "loss": 1.3263, "step": 208630 }, { "epoch": 9.53, "learning_rate": 2.3685294521488397e-06, "loss": 1.4671, "step": 208640 }, { "epoch": 9.53, "learning_rate": 2.366241017895556e-06, "loss": 1.3348, "step": 208650 }, { "epoch": 9.53, "learning_rate": 2.3639525836422722e-06, "loss": 1.2811, "step": 208660 }, { "epoch": 9.53, "learning_rate": 2.361664149388988e-06, "loss": 1.2839, "step": 208670 }, { "epoch": 9.53, "learning_rate": 2.3593757151357043e-06, "loss": 1.4024, "step": 208680 }, { "epoch": 9.53, "learning_rate": 2.35708728088242e-06, "loss": 1.3786, "step": 208690 }, { "epoch": 9.53, "learning_rate": 2.3547988466291364e-06, "loss": 1.2514, "step": 208700 }, { "epoch": 9.53, "learning_rate": 2.3525104123758527e-06, "loss": 1.4851, "step": 208710 }, { "epoch": 9.53, "learning_rate": 2.350221978122569e-06, "loss": 1.1914, "step": 208720 }, { "epoch": 9.53, "learning_rate": 2.3479335438692847e-06, "loss": 1.2818, "step": 208730 }, { "epoch": 9.53, "learning_rate": 2.345645109616001e-06, "loss": 1.2671, "step": 208740 }, { "epoch": 9.53, "learning_rate": 2.343356675362717e-06, "loss": 1.2476, "step": 208750 }, { "epoch": 9.53, "learning_rate": 2.341068241109433e-06, "loss": 1.3533, "step": 208760 }, { "epoch": 9.53, "learning_rate": 2.3387798068561493e-06, "loss": 1.2898, "step": 208770 }, { "epoch": 9.53, "learning_rate": 2.336491372602865e-06, "loss": 1.3204, "step": 208780 }, { "epoch": 9.53, "learning_rate": 2.3342029383495814e-06, "loss": 1.2888, "step": 208790 }, { "epoch": 9.53, "learning_rate": 2.3319145040962972e-06, "loss": 1.339, "step": 208800 }, { "epoch": 9.53, "learning_rate": 2.329626069843014e-06, "loss": 1.3886, "step": 208810 }, { "epoch": 9.54, "learning_rate": 2.3273376355897297e-06, "loss": 1.4503, "step": 208820 }, { "epoch": 9.54, "learning_rate": 2.3250492013364456e-06, "loss": 1.5378, "step": 208830 }, { "epoch": 9.54, "learning_rate": 2.322760767083162e-06, "loss": 1.3886, "step": 208840 }, { "epoch": 9.54, "learning_rate": 2.3204723328298776e-06, "loss": 1.3139, "step": 208850 }, { "epoch": 9.54, "learning_rate": 2.318183898576594e-06, "loss": 1.2812, "step": 208860 }, { "epoch": 9.54, "learning_rate": 2.31589546432331e-06, "loss": 1.3314, "step": 208870 }, { "epoch": 9.54, "learning_rate": 2.3136070300700264e-06, "loss": 1.3563, "step": 208880 }, { "epoch": 9.54, "learning_rate": 2.3113185958167422e-06, "loss": 1.4331, "step": 208890 }, { "epoch": 9.54, "learning_rate": 2.3090301615634585e-06, "loss": 1.2659, "step": 208900 }, { "epoch": 9.54, "learning_rate": 2.3067417273101743e-06, "loss": 1.4248, "step": 208910 }, { "epoch": 9.54, "learning_rate": 2.3044532930568905e-06, "loss": 1.3563, "step": 208920 }, { "epoch": 9.54, "learning_rate": 2.302164858803607e-06, "loss": 1.3207, "step": 208930 }, { "epoch": 9.54, "learning_rate": 2.2998764245503226e-06, "loss": 1.1666, "step": 208940 }, { "epoch": 9.54, "learning_rate": 2.297587990297039e-06, "loss": 1.3709, "step": 208950 }, { "epoch": 9.54, "learning_rate": 2.2952995560437547e-06, "loss": 1.4709, "step": 208960 }, { "epoch": 9.54, "learning_rate": 2.2930111217904714e-06, "loss": 1.3101, "step": 208970 }, { "epoch": 9.54, "learning_rate": 2.290722687537187e-06, "loss": 1.5707, "step": 208980 }, { "epoch": 9.54, "learning_rate": 2.2884342532839035e-06, "loss": 1.3049, "step": 208990 }, { "epoch": 9.54, "learning_rate": 2.2861458190306193e-06, "loss": 1.2966, "step": 209000 }, { "epoch": 9.54, "learning_rate": 2.2838573847773355e-06, "loss": 1.2273, "step": 209010 }, { "epoch": 9.54, "learning_rate": 2.2815689505240514e-06, "loss": 1.5349, "step": 209020 }, { "epoch": 9.54, "learning_rate": 2.2792805162707676e-06, "loss": 1.4027, "step": 209030 }, { "epoch": 9.55, "learning_rate": 2.276992082017484e-06, "loss": 1.3449, "step": 209040 }, { "epoch": 9.55, "learning_rate": 2.2747036477641997e-06, "loss": 1.1935, "step": 209050 }, { "epoch": 9.55, "learning_rate": 2.272415213510916e-06, "loss": 1.3989, "step": 209060 }, { "epoch": 9.55, "learning_rate": 2.2701267792576318e-06, "loss": 1.3372, "step": 209070 }, { "epoch": 9.55, "learning_rate": 2.2678383450043484e-06, "loss": 1.2863, "step": 209080 }, { "epoch": 9.55, "learning_rate": 2.2655499107510643e-06, "loss": 1.4044, "step": 209090 }, { "epoch": 9.55, "learning_rate": 2.2632614764977805e-06, "loss": 1.4718, "step": 209100 }, { "epoch": 9.55, "learning_rate": 2.2609730422444964e-06, "loss": 1.3216, "step": 209110 }, { "epoch": 9.55, "learning_rate": 2.258684607991212e-06, "loss": 1.4497, "step": 209120 }, { "epoch": 9.55, "learning_rate": 2.256396173737929e-06, "loss": 1.2193, "step": 209130 }, { "epoch": 9.55, "learning_rate": 2.2541077394846447e-06, "loss": 1.2828, "step": 209140 }, { "epoch": 9.55, "learning_rate": 2.251819305231361e-06, "loss": 1.3799, "step": 209150 }, { "epoch": 9.55, "learning_rate": 2.2495308709780768e-06, "loss": 1.357, "step": 209160 }, { "epoch": 9.55, "learning_rate": 2.247242436724793e-06, "loss": 1.2978, "step": 209170 }, { "epoch": 9.55, "learning_rate": 2.2449540024715093e-06, "loss": 1.2926, "step": 209180 }, { "epoch": 9.55, "learning_rate": 2.242665568218225e-06, "loss": 1.2929, "step": 209190 }, { "epoch": 9.55, "learning_rate": 2.2403771339649413e-06, "loss": 1.2523, "step": 209200 }, { "epoch": 9.55, "learning_rate": 2.238088699711657e-06, "loss": 1.2664, "step": 209210 }, { "epoch": 9.55, "learning_rate": 2.2358002654583734e-06, "loss": 1.3174, "step": 209220 }, { "epoch": 9.55, "learning_rate": 2.2335118312050892e-06, "loss": 1.3466, "step": 209230 }, { "epoch": 9.55, "learning_rate": 2.231223396951806e-06, "loss": 1.2628, "step": 209240 }, { "epoch": 9.55, "learning_rate": 2.2289349626985217e-06, "loss": 1.3279, "step": 209250 }, { "epoch": 9.56, "learning_rate": 2.226646528445238e-06, "loss": 1.3695, "step": 209260 }, { "epoch": 9.56, "learning_rate": 2.224358094191954e-06, "loss": 1.234, "step": 209270 }, { "epoch": 9.56, "learning_rate": 2.22206965993867e-06, "loss": 1.3707, "step": 209280 }, { "epoch": 9.56, "learning_rate": 2.2197812256853863e-06, "loss": 1.2797, "step": 209290 }, { "epoch": 9.56, "learning_rate": 2.217492791432102e-06, "loss": 1.3961, "step": 209300 }, { "epoch": 9.56, "learning_rate": 2.2152043571788184e-06, "loss": 1.3771, "step": 209310 }, { "epoch": 9.56, "learning_rate": 2.2129159229255342e-06, "loss": 1.2678, "step": 209320 }, { "epoch": 9.56, "learning_rate": 2.2106274886722505e-06, "loss": 1.3146, "step": 209330 }, { "epoch": 9.56, "learning_rate": 2.2083390544189667e-06, "loss": 1.3096, "step": 209340 }, { "epoch": 9.56, "learning_rate": 2.206050620165683e-06, "loss": 1.2935, "step": 209350 }, { "epoch": 9.56, "learning_rate": 2.203762185912399e-06, "loss": 1.3339, "step": 209360 }, { "epoch": 9.56, "learning_rate": 2.201473751659115e-06, "loss": 1.2435, "step": 209370 }, { "epoch": 9.56, "learning_rate": 2.199185317405831e-06, "loss": 1.4128, "step": 209380 }, { "epoch": 9.56, "learning_rate": 2.196896883152547e-06, "loss": 1.2583, "step": 209390 }, { "epoch": 9.56, "learning_rate": 2.1946084488992634e-06, "loss": 1.2497, "step": 209400 }, { "epoch": 9.56, "learning_rate": 2.1923200146459792e-06, "loss": 1.3046, "step": 209410 }, { "epoch": 9.56, "learning_rate": 2.1900315803926955e-06, "loss": 1.3063, "step": 209420 }, { "epoch": 9.56, "learning_rate": 2.1877431461394113e-06, "loss": 1.2866, "step": 209430 }, { "epoch": 9.56, "learning_rate": 2.1854547118861276e-06, "loss": 1.3938, "step": 209440 }, { "epoch": 9.56, "learning_rate": 2.183166277632844e-06, "loss": 1.3637, "step": 209450 }, { "epoch": 9.56, "learning_rate": 2.18087784337956e-06, "loss": 1.2951, "step": 209460 }, { "epoch": 9.56, "learning_rate": 2.178589409126276e-06, "loss": 1.3635, "step": 209470 }, { "epoch": 9.57, "learning_rate": 2.1763009748729917e-06, "loss": 1.2201, "step": 209480 }, { "epoch": 9.57, "learning_rate": 2.174012540619708e-06, "loss": 1.5198, "step": 209490 }, { "epoch": 9.57, "learning_rate": 2.1717241063664242e-06, "loss": 1.4752, "step": 209500 }, { "epoch": 9.57, "learning_rate": 2.1694356721131405e-06, "loss": 1.3663, "step": 209510 }, { "epoch": 9.57, "learning_rate": 2.1671472378598563e-06, "loss": 1.3768, "step": 209520 }, { "epoch": 9.57, "learning_rate": 2.1648588036065725e-06, "loss": 1.2878, "step": 209530 }, { "epoch": 9.57, "learning_rate": 2.1625703693532884e-06, "loss": 1.3654, "step": 209540 }, { "epoch": 9.57, "learning_rate": 2.1602819351000046e-06, "loss": 1.4364, "step": 209550 }, { "epoch": 9.57, "learning_rate": 2.157993500846721e-06, "loss": 1.1166, "step": 209560 }, { "epoch": 9.57, "learning_rate": 2.1557050665934367e-06, "loss": 1.2346, "step": 209570 }, { "epoch": 9.57, "learning_rate": 2.153416632340153e-06, "loss": 1.3388, "step": 209580 }, { "epoch": 9.57, "learning_rate": 2.1511281980868688e-06, "loss": 1.2626, "step": 209590 }, { "epoch": 9.57, "learning_rate": 2.1488397638335855e-06, "loss": 1.3484, "step": 209600 }, { "epoch": 9.57, "learning_rate": 2.1465513295803013e-06, "loss": 1.3622, "step": 209610 }, { "epoch": 9.57, "learning_rate": 2.1442628953270175e-06, "loss": 1.362, "step": 209620 }, { "epoch": 9.57, "learning_rate": 2.1419744610737334e-06, "loss": 1.2691, "step": 209630 }, { "epoch": 9.57, "learning_rate": 2.1396860268204496e-06, "loss": 1.3562, "step": 209640 }, { "epoch": 9.57, "learning_rate": 2.1373975925671654e-06, "loss": 1.3137, "step": 209650 }, { "epoch": 9.57, "learning_rate": 2.1351091583138817e-06, "loss": 1.2103, "step": 209660 }, { "epoch": 9.57, "learning_rate": 2.132820724060598e-06, "loss": 1.3341, "step": 209670 }, { "epoch": 9.57, "learning_rate": 2.1305322898073138e-06, "loss": 1.3513, "step": 209680 }, { "epoch": 9.57, "learning_rate": 2.12824385555403e-06, "loss": 1.4137, "step": 209690 }, { "epoch": 9.58, "learning_rate": 2.125955421300746e-06, "loss": 1.3963, "step": 209700 }, { "epoch": 9.58, "learning_rate": 2.1236669870474625e-06, "loss": 1.286, "step": 209710 }, { "epoch": 9.58, "learning_rate": 2.1213785527941784e-06, "loss": 1.3737, "step": 209720 }, { "epoch": 9.58, "learning_rate": 2.1190901185408946e-06, "loss": 1.3543, "step": 209730 }, { "epoch": 9.58, "learning_rate": 2.1168016842876104e-06, "loss": 1.2836, "step": 209740 }, { "epoch": 9.58, "learning_rate": 2.1145132500343267e-06, "loss": 1.2925, "step": 209750 }, { "epoch": 9.58, "learning_rate": 2.112224815781043e-06, "loss": 1.4144, "step": 209760 }, { "epoch": 9.58, "learning_rate": 2.1099363815277588e-06, "loss": 1.2758, "step": 209770 }, { "epoch": 9.58, "learning_rate": 2.107647947274475e-06, "loss": 1.2126, "step": 209780 }, { "epoch": 9.58, "learning_rate": 2.105359513021191e-06, "loss": 1.1838, "step": 209790 }, { "epoch": 9.58, "learning_rate": 2.103071078767907e-06, "loss": 1.3213, "step": 209800 }, { "epoch": 9.58, "learning_rate": 2.1007826445146233e-06, "loss": 1.4595, "step": 209810 }, { "epoch": 9.58, "learning_rate": 2.0984942102613396e-06, "loss": 1.4221, "step": 209820 }, { "epoch": 9.58, "learning_rate": 2.0962057760080554e-06, "loss": 1.3651, "step": 209830 }, { "epoch": 9.58, "learning_rate": 2.0939173417547712e-06, "loss": 1.3108, "step": 209840 }, { "epoch": 9.58, "learning_rate": 2.0916289075014875e-06, "loss": 1.479, "step": 209850 }, { "epoch": 9.58, "learning_rate": 2.0893404732482033e-06, "loss": 1.3381, "step": 209860 }, { "epoch": 9.58, "learning_rate": 2.08705203899492e-06, "loss": 1.4262, "step": 209870 }, { "epoch": 9.58, "learning_rate": 2.084763604741636e-06, "loss": 1.3308, "step": 209880 }, { "epoch": 9.58, "learning_rate": 2.082475170488352e-06, "loss": 1.2747, "step": 209890 }, { "epoch": 9.58, "learning_rate": 2.080186736235068e-06, "loss": 1.2892, "step": 209900 }, { "epoch": 9.59, "learning_rate": 2.077898301981784e-06, "loss": 1.2522, "step": 209910 }, { "epoch": 9.59, "learning_rate": 2.0756098677285004e-06, "loss": 1.2372, "step": 209920 }, { "epoch": 9.59, "learning_rate": 2.0733214334752162e-06, "loss": 1.3004, "step": 209930 }, { "epoch": 9.59, "learning_rate": 2.0710329992219325e-06, "loss": 1.385, "step": 209940 }, { "epoch": 9.59, "learning_rate": 2.0687445649686483e-06, "loss": 1.3453, "step": 209950 }, { "epoch": 9.59, "learning_rate": 2.0664561307153646e-06, "loss": 1.3783, "step": 209960 }, { "epoch": 9.59, "learning_rate": 2.064167696462081e-06, "loss": 1.2931, "step": 209970 }, { "epoch": 9.59, "learning_rate": 2.061879262208797e-06, "loss": 1.5567, "step": 209980 }, { "epoch": 9.59, "learning_rate": 2.059590827955513e-06, "loss": 1.2606, "step": 209990 }, { "epoch": 9.59, "learning_rate": 2.057302393702229e-06, "loss": 1.3153, "step": 210000 }, { "epoch": 9.59, "learning_rate": 2.055013959448945e-06, "loss": 1.1277, "step": 210010 }, { "epoch": 9.59, "learning_rate": 2.0527255251956612e-06, "loss": 1.2723, "step": 210020 }, { "epoch": 9.59, "learning_rate": 2.0504370909423775e-06, "loss": 1.0951, "step": 210030 }, { "epoch": 9.59, "learning_rate": 2.0481486566890933e-06, "loss": 1.4536, "step": 210040 }, { "epoch": 9.59, "learning_rate": 2.0458602224358096e-06, "loss": 1.3014, "step": 210050 }, { "epoch": 9.59, "learning_rate": 2.0435717881825254e-06, "loss": 1.3691, "step": 210060 }, { "epoch": 9.59, "learning_rate": 2.0412833539292416e-06, "loss": 1.2369, "step": 210070 }, { "epoch": 9.59, "learning_rate": 2.038994919675958e-06, "loss": 1.3265, "step": 210080 }, { "epoch": 9.59, "learning_rate": 2.036706485422674e-06, "loss": 1.642, "step": 210090 }, { "epoch": 9.59, "learning_rate": 2.03441805116939e-06, "loss": 1.3496, "step": 210100 }, { "epoch": 9.59, "learning_rate": 2.0321296169161062e-06, "loss": 1.2757, "step": 210110 }, { "epoch": 9.59, "learning_rate": 2.029841182662822e-06, "loss": 1.2995, "step": 210120 }, { "epoch": 9.6, "learning_rate": 2.0275527484095383e-06, "loss": 1.2768, "step": 210130 }, { "epoch": 9.6, "learning_rate": 2.0252643141562545e-06, "loss": 1.2594, "step": 210140 }, { "epoch": 9.6, "learning_rate": 2.0229758799029704e-06, "loss": 1.321, "step": 210150 }, { "epoch": 9.6, "learning_rate": 2.0206874456496866e-06, "loss": 1.3823, "step": 210160 }, { "epoch": 9.6, "learning_rate": 2.0183990113964025e-06, "loss": 1.4758, "step": 210170 }, { "epoch": 9.6, "learning_rate": 2.016110577143119e-06, "loss": 1.5011, "step": 210180 }, { "epoch": 9.6, "learning_rate": 2.013822142889835e-06, "loss": 1.1816, "step": 210190 }, { "epoch": 9.6, "learning_rate": 2.011533708636551e-06, "loss": 1.3542, "step": 210200 }, { "epoch": 9.6, "learning_rate": 2.009245274383267e-06, "loss": 1.2175, "step": 210210 }, { "epoch": 9.6, "learning_rate": 2.006956840129983e-06, "loss": 1.2849, "step": 210220 }, { "epoch": 9.6, "learning_rate": 2.004668405876699e-06, "loss": 1.3348, "step": 210230 }, { "epoch": 9.6, "learning_rate": 2.0023799716234154e-06, "loss": 1.163, "step": 210240 }, { "epoch": 9.6, "learning_rate": 2.0000915373701316e-06, "loss": 1.2182, "step": 210250 }, { "epoch": 9.6, "learning_rate": 1.9978031031168474e-06, "loss": 1.3784, "step": 210260 }, { "epoch": 9.6, "learning_rate": 1.9955146688635637e-06, "loss": 1.3426, "step": 210270 }, { "epoch": 9.6, "learning_rate": 1.9932262346102795e-06, "loss": 1.4383, "step": 210280 }, { "epoch": 9.6, "learning_rate": 1.9909378003569958e-06, "loss": 1.4134, "step": 210290 }, { "epoch": 9.6, "learning_rate": 1.988649366103712e-06, "loss": 1.3287, "step": 210300 }, { "epoch": 9.6, "learning_rate": 1.986360931850428e-06, "loss": 1.3458, "step": 210310 }, { "epoch": 9.6, "learning_rate": 1.984072497597144e-06, "loss": 1.2721, "step": 210320 }, { "epoch": 9.6, "learning_rate": 1.98178406334386e-06, "loss": 1.433, "step": 210330 }, { "epoch": 9.6, "learning_rate": 1.9794956290905766e-06, "loss": 1.2518, "step": 210340 }, { "epoch": 9.61, "learning_rate": 1.9772071948372924e-06, "loss": 1.2633, "step": 210350 }, { "epoch": 9.61, "learning_rate": 1.9749187605840087e-06, "loss": 1.6191, "step": 210360 }, { "epoch": 9.61, "learning_rate": 1.9726303263307245e-06, "loss": 1.4394, "step": 210370 }, { "epoch": 9.61, "learning_rate": 1.9703418920774408e-06, "loss": 1.3689, "step": 210380 }, { "epoch": 9.61, "learning_rate": 1.968053457824157e-06, "loss": 1.2861, "step": 210390 }, { "epoch": 9.61, "learning_rate": 1.965765023570873e-06, "loss": 1.2104, "step": 210400 }, { "epoch": 9.61, "learning_rate": 1.963476589317589e-06, "loss": 1.3745, "step": 210410 }, { "epoch": 9.61, "learning_rate": 1.961188155064305e-06, "loss": 1.3804, "step": 210420 }, { "epoch": 9.61, "learning_rate": 1.958899720811021e-06, "loss": 1.3313, "step": 210430 }, { "epoch": 9.61, "learning_rate": 1.956611286557737e-06, "loss": 1.4041, "step": 210440 }, { "epoch": 9.61, "learning_rate": 1.9543228523044537e-06, "loss": 1.2879, "step": 210450 }, { "epoch": 9.61, "learning_rate": 1.9520344180511695e-06, "loss": 1.4079, "step": 210460 }, { "epoch": 9.61, "learning_rate": 1.9497459837978858e-06, "loss": 1.4521, "step": 210470 }, { "epoch": 9.61, "learning_rate": 1.9474575495446016e-06, "loss": 1.4996, "step": 210480 }, { "epoch": 9.61, "learning_rate": 1.945169115291318e-06, "loss": 1.4115, "step": 210490 }, { "epoch": 9.61, "learning_rate": 1.942880681038034e-06, "loss": 1.3592, "step": 210500 }, { "epoch": 9.61, "learning_rate": 1.94059224678475e-06, "loss": 1.3427, "step": 210510 }, { "epoch": 9.61, "learning_rate": 1.938303812531466e-06, "loss": 1.4688, "step": 210520 }, { "epoch": 9.61, "learning_rate": 1.936015378278182e-06, "loss": 1.3413, "step": 210530 }, { "epoch": 9.61, "learning_rate": 1.9337269440248982e-06, "loss": 1.4189, "step": 210540 }, { "epoch": 9.61, "learning_rate": 1.9314385097716145e-06, "loss": 1.5299, "step": 210550 }, { "epoch": 9.61, "learning_rate": 1.9291500755183307e-06, "loss": 1.3677, "step": 210560 }, { "epoch": 9.62, "learning_rate": 1.9268616412650466e-06, "loss": 1.4086, "step": 210570 }, { "epoch": 9.62, "learning_rate": 1.9245732070117624e-06, "loss": 1.396, "step": 210580 }, { "epoch": 9.62, "learning_rate": 1.9222847727584786e-06, "loss": 1.3475, "step": 210590 }, { "epoch": 9.62, "learning_rate": 1.919996338505195e-06, "loss": 1.4699, "step": 210600 }, { "epoch": 9.62, "learning_rate": 1.917707904251911e-06, "loss": 1.2445, "step": 210610 }, { "epoch": 9.62, "learning_rate": 1.915419469998627e-06, "loss": 1.3924, "step": 210620 }, { "epoch": 9.62, "learning_rate": 1.9131310357453432e-06, "loss": 1.4215, "step": 210630 }, { "epoch": 9.62, "learning_rate": 1.910842601492059e-06, "loss": 1.3442, "step": 210640 }, { "epoch": 9.62, "learning_rate": 1.9085541672387753e-06, "loss": 1.2659, "step": 210650 }, { "epoch": 9.62, "learning_rate": 1.9062657329854916e-06, "loss": 1.3292, "step": 210660 }, { "epoch": 9.62, "learning_rate": 1.9039772987322076e-06, "loss": 1.2792, "step": 210670 }, { "epoch": 9.62, "learning_rate": 1.9016888644789236e-06, "loss": 1.3473, "step": 210680 }, { "epoch": 9.62, "learning_rate": 1.8994004302256397e-06, "loss": 1.211, "step": 210690 }, { "epoch": 9.62, "learning_rate": 1.8971119959723557e-06, "loss": 1.4044, "step": 210700 }, { "epoch": 9.62, "learning_rate": 1.894823561719072e-06, "loss": 1.3547, "step": 210710 }, { "epoch": 9.62, "learning_rate": 1.892535127465788e-06, "loss": 1.1906, "step": 210720 }, { "epoch": 9.62, "learning_rate": 1.890246693212504e-06, "loss": 1.2442, "step": 210730 }, { "epoch": 9.62, "learning_rate": 1.88795825895922e-06, "loss": 1.2676, "step": 210740 }, { "epoch": 9.62, "learning_rate": 1.8856698247059361e-06, "loss": 1.3276, "step": 210750 }, { "epoch": 9.62, "learning_rate": 1.8833813904526526e-06, "loss": 1.1897, "step": 210760 }, { "epoch": 9.62, "learning_rate": 1.8810929561993686e-06, "loss": 1.3015, "step": 210770 }, { "epoch": 9.62, "learning_rate": 1.8788045219460847e-06, "loss": 1.6078, "step": 210780 }, { "epoch": 9.63, "learning_rate": 1.8765160876928007e-06, "loss": 1.1955, "step": 210790 }, { "epoch": 9.63, "learning_rate": 1.8742276534395167e-06, "loss": 1.2393, "step": 210800 }, { "epoch": 9.63, "learning_rate": 1.871939219186233e-06, "loss": 1.3684, "step": 210810 }, { "epoch": 9.63, "learning_rate": 1.869650784932949e-06, "loss": 1.285, "step": 210820 }, { "epoch": 9.63, "learning_rate": 1.867362350679665e-06, "loss": 1.2588, "step": 210830 }, { "epoch": 9.63, "learning_rate": 1.8650739164263811e-06, "loss": 1.4778, "step": 210840 }, { "epoch": 9.63, "learning_rate": 1.8627854821730972e-06, "loss": 1.3058, "step": 210850 }, { "epoch": 9.63, "learning_rate": 1.8604970479198132e-06, "loss": 1.3876, "step": 210860 }, { "epoch": 9.63, "learning_rate": 1.8582086136665297e-06, "loss": 1.4434, "step": 210870 }, { "epoch": 9.63, "learning_rate": 1.8559201794132457e-06, "loss": 1.3888, "step": 210880 }, { "epoch": 9.63, "learning_rate": 1.8536317451599617e-06, "loss": 1.32, "step": 210890 }, { "epoch": 9.63, "learning_rate": 1.8513433109066776e-06, "loss": 1.3206, "step": 210900 }, { "epoch": 9.63, "learning_rate": 1.8490548766533936e-06, "loss": 1.3449, "step": 210910 }, { "epoch": 9.63, "learning_rate": 1.84676644240011e-06, "loss": 1.2619, "step": 210920 }, { "epoch": 9.63, "learning_rate": 1.844478008146826e-06, "loss": 1.3394, "step": 210930 }, { "epoch": 9.63, "learning_rate": 1.8421895738935421e-06, "loss": 1.453, "step": 210940 }, { "epoch": 9.63, "learning_rate": 1.8399011396402582e-06, "loss": 1.3839, "step": 210950 }, { "epoch": 9.63, "learning_rate": 1.8376127053869742e-06, "loss": 1.4273, "step": 210960 }, { "epoch": 9.63, "learning_rate": 1.8353242711336905e-06, "loss": 1.3141, "step": 210970 }, { "epoch": 9.63, "learning_rate": 1.8330358368804065e-06, "loss": 1.1679, "step": 210980 }, { "epoch": 9.63, "learning_rate": 1.8307474026271226e-06, "loss": 1.3467, "step": 210990 }, { "epoch": 9.63, "learning_rate": 1.8284589683738386e-06, "loss": 1.3189, "step": 211000 }, { "epoch": 9.64, "learning_rate": 1.8261705341205546e-06, "loss": 1.3505, "step": 211010 }, { "epoch": 9.64, "learning_rate": 1.823882099867271e-06, "loss": 1.2695, "step": 211020 }, { "epoch": 9.64, "learning_rate": 1.8215936656139871e-06, "loss": 1.3373, "step": 211030 }, { "epoch": 9.64, "learning_rate": 1.8193052313607032e-06, "loss": 1.3691, "step": 211040 }, { "epoch": 9.64, "learning_rate": 1.8170167971074192e-06, "loss": 1.4405, "step": 211050 }, { "epoch": 9.64, "learning_rate": 1.8147283628541353e-06, "loss": 1.2482, "step": 211060 }, { "epoch": 9.64, "learning_rate": 1.8124399286008513e-06, "loss": 1.4486, "step": 211070 }, { "epoch": 9.64, "learning_rate": 1.8101514943475675e-06, "loss": 1.4834, "step": 211080 }, { "epoch": 9.64, "learning_rate": 1.8078630600942836e-06, "loss": 1.3349, "step": 211090 }, { "epoch": 9.64, "learning_rate": 1.8055746258409996e-06, "loss": 1.5009, "step": 211100 }, { "epoch": 9.64, "learning_rate": 1.8032861915877157e-06, "loss": 1.3753, "step": 211110 }, { "epoch": 9.64, "learning_rate": 1.8009977573344317e-06, "loss": 1.2978, "step": 211120 }, { "epoch": 9.64, "learning_rate": 1.7987093230811482e-06, "loss": 1.3403, "step": 211130 }, { "epoch": 9.64, "learning_rate": 1.7964208888278642e-06, "loss": 1.2822, "step": 211140 }, { "epoch": 9.64, "learning_rate": 1.7941324545745802e-06, "loss": 1.3397, "step": 211150 }, { "epoch": 9.64, "learning_rate": 1.7918440203212963e-06, "loss": 1.3667, "step": 211160 }, { "epoch": 9.64, "learning_rate": 1.7895555860680123e-06, "loss": 1.4154, "step": 211170 }, { "epoch": 9.64, "learning_rate": 1.7872671518147286e-06, "loss": 1.2414, "step": 211180 }, { "epoch": 9.64, "learning_rate": 1.7849787175614446e-06, "loss": 1.3449, "step": 211190 }, { "epoch": 9.64, "learning_rate": 1.7826902833081606e-06, "loss": 1.3133, "step": 211200 }, { "epoch": 9.64, "learning_rate": 1.7804018490548767e-06, "loss": 1.3001, "step": 211210 }, { "epoch": 9.64, "learning_rate": 1.7781134148015927e-06, "loss": 1.3218, "step": 211220 }, { "epoch": 9.65, "learning_rate": 1.7758249805483088e-06, "loss": 1.2754, "step": 211230 }, { "epoch": 9.65, "learning_rate": 1.7735365462950252e-06, "loss": 1.38, "step": 211240 }, { "epoch": 9.65, "learning_rate": 1.7712481120417413e-06, "loss": 1.2045, "step": 211250 }, { "epoch": 9.65, "learning_rate": 1.768959677788457e-06, "loss": 1.398, "step": 211260 }, { "epoch": 9.65, "learning_rate": 1.7666712435351731e-06, "loss": 1.2535, "step": 211270 }, { "epoch": 9.65, "learning_rate": 1.7643828092818892e-06, "loss": 1.2379, "step": 211280 }, { "epoch": 9.65, "learning_rate": 1.7620943750286056e-06, "loss": 1.3237, "step": 211290 }, { "epoch": 9.65, "learning_rate": 1.7598059407753217e-06, "loss": 1.3755, "step": 211300 }, { "epoch": 9.65, "learning_rate": 1.7575175065220377e-06, "loss": 1.3402, "step": 211310 }, { "epoch": 9.65, "learning_rate": 1.7552290722687538e-06, "loss": 1.2918, "step": 211320 }, { "epoch": 9.65, "learning_rate": 1.7529406380154698e-06, "loss": 1.2697, "step": 211330 }, { "epoch": 9.65, "learning_rate": 1.750652203762186e-06, "loss": 1.4602, "step": 211340 }, { "epoch": 9.65, "learning_rate": 1.748363769508902e-06, "loss": 1.3879, "step": 211350 }, { "epoch": 9.65, "learning_rate": 1.7460753352556181e-06, "loss": 1.3198, "step": 211360 }, { "epoch": 9.65, "learning_rate": 1.7437869010023342e-06, "loss": 1.314, "step": 211370 }, { "epoch": 9.65, "learning_rate": 1.7414984667490502e-06, "loss": 1.1799, "step": 211380 }, { "epoch": 9.65, "learning_rate": 1.7392100324957667e-06, "loss": 1.3287, "step": 211390 }, { "epoch": 9.65, "learning_rate": 1.7369215982424827e-06, "loss": 1.4469, "step": 211400 }, { "epoch": 9.65, "learning_rate": 1.7346331639891987e-06, "loss": 1.2692, "step": 211410 }, { "epoch": 9.65, "learning_rate": 1.7323447297359148e-06, "loss": 1.3153, "step": 211420 }, { "epoch": 9.65, "learning_rate": 1.7300562954826308e-06, "loss": 1.3961, "step": 211430 }, { "epoch": 9.65, "learning_rate": 1.7277678612293469e-06, "loss": 1.2327, "step": 211440 }, { "epoch": 9.66, "learning_rate": 1.7254794269760631e-06, "loss": 1.2861, "step": 211450 }, { "epoch": 9.66, "learning_rate": 1.7231909927227792e-06, "loss": 1.3018, "step": 211460 }, { "epoch": 9.66, "learning_rate": 1.7209025584694952e-06, "loss": 1.3327, "step": 211470 }, { "epoch": 9.66, "learning_rate": 1.7186141242162112e-06, "loss": 1.3981, "step": 211480 }, { "epoch": 9.66, "learning_rate": 1.7163256899629273e-06, "loss": 1.2983, "step": 211490 }, { "epoch": 9.66, "learning_rate": 1.7140372557096437e-06, "loss": 1.3552, "step": 211500 }, { "epoch": 9.66, "learning_rate": 1.7117488214563598e-06, "loss": 1.3639, "step": 211510 }, { "epoch": 9.66, "learning_rate": 1.7094603872030758e-06, "loss": 1.2853, "step": 211520 }, { "epoch": 9.66, "learning_rate": 1.7071719529497919e-06, "loss": 1.4201, "step": 211530 }, { "epoch": 9.66, "learning_rate": 1.7048835186965079e-06, "loss": 1.4101, "step": 211540 }, { "epoch": 9.66, "learning_rate": 1.7025950844432241e-06, "loss": 1.201, "step": 211550 }, { "epoch": 9.66, "learning_rate": 1.7003066501899402e-06, "loss": 1.4097, "step": 211560 }, { "epoch": 9.66, "learning_rate": 1.6980182159366562e-06, "loss": 1.3314, "step": 211570 }, { "epoch": 9.66, "learning_rate": 1.6957297816833723e-06, "loss": 1.4345, "step": 211580 }, { "epoch": 9.66, "learning_rate": 1.6934413474300883e-06, "loss": 1.3715, "step": 211590 }, { "epoch": 9.66, "learning_rate": 1.6911529131768048e-06, "loss": 1.3059, "step": 211600 }, { "epoch": 9.66, "learning_rate": 1.6888644789235208e-06, "loss": 1.2655, "step": 211610 }, { "epoch": 9.66, "learning_rate": 1.6865760446702366e-06, "loss": 1.5437, "step": 211620 }, { "epoch": 9.66, "learning_rate": 1.6842876104169527e-06, "loss": 1.4901, "step": 211630 }, { "epoch": 9.66, "learning_rate": 1.6819991761636687e-06, "loss": 1.3438, "step": 211640 }, { "epoch": 9.66, "learning_rate": 1.6797107419103848e-06, "loss": 1.3739, "step": 211650 }, { "epoch": 9.66, "learning_rate": 1.6774223076571012e-06, "loss": 1.3696, "step": 211660 }, { "epoch": 9.67, "learning_rate": 1.6751338734038173e-06, "loss": 1.348, "step": 211670 }, { "epoch": 9.67, "learning_rate": 1.6728454391505333e-06, "loss": 1.3018, "step": 211680 }, { "epoch": 9.67, "learning_rate": 1.6705570048972493e-06, "loss": 1.2904, "step": 211690 }, { "epoch": 9.67, "learning_rate": 1.6682685706439654e-06, "loss": 1.3347, "step": 211700 }, { "epoch": 9.67, "learning_rate": 1.6659801363906816e-06, "loss": 1.349, "step": 211710 }, { "epoch": 9.67, "learning_rate": 1.6636917021373977e-06, "loss": 1.2852, "step": 211720 }, { "epoch": 9.67, "learning_rate": 1.6614032678841137e-06, "loss": 1.3347, "step": 211730 }, { "epoch": 9.67, "learning_rate": 1.6591148336308297e-06, "loss": 1.3328, "step": 211740 }, { "epoch": 9.67, "learning_rate": 1.6568263993775458e-06, "loss": 1.3048, "step": 211750 }, { "epoch": 9.67, "learning_rate": 1.6545379651242622e-06, "loss": 1.3313, "step": 211760 }, { "epoch": 9.67, "learning_rate": 1.6522495308709783e-06, "loss": 1.4682, "step": 211770 }, { "epoch": 9.67, "learning_rate": 1.6499610966176943e-06, "loss": 1.419, "step": 211780 }, { "epoch": 9.67, "learning_rate": 1.6476726623644104e-06, "loss": 1.3856, "step": 211790 }, { "epoch": 9.67, "learning_rate": 1.6453842281111264e-06, "loss": 1.4521, "step": 211800 }, { "epoch": 9.67, "learning_rate": 1.6430957938578427e-06, "loss": 1.2205, "step": 211810 }, { "epoch": 9.67, "learning_rate": 1.6408073596045587e-06, "loss": 1.2211, "step": 211820 }, { "epoch": 9.67, "learning_rate": 1.6385189253512747e-06, "loss": 1.4132, "step": 211830 }, { "epoch": 9.67, "learning_rate": 1.6362304910979908e-06, "loss": 1.4667, "step": 211840 }, { "epoch": 9.67, "learning_rate": 1.6339420568447068e-06, "loss": 1.292, "step": 211850 }, { "epoch": 9.67, "learning_rate": 1.6316536225914228e-06, "loss": 1.2541, "step": 211860 }, { "epoch": 9.67, "learning_rate": 1.6293651883381393e-06, "loss": 1.2293, "step": 211870 }, { "epoch": 9.67, "learning_rate": 1.6270767540848553e-06, "loss": 1.2857, "step": 211880 }, { "epoch": 9.68, "learning_rate": 1.6247883198315714e-06, "loss": 1.4098, "step": 211890 }, { "epoch": 9.68, "learning_rate": 1.6224998855782874e-06, "loss": 1.3645, "step": 211900 }, { "epoch": 9.68, "learning_rate": 1.6202114513250035e-06, "loss": 1.2758, "step": 211910 }, { "epoch": 9.68, "learning_rate": 1.6179230170717197e-06, "loss": 1.2463, "step": 211920 }, { "epoch": 9.68, "learning_rate": 1.6156345828184358e-06, "loss": 1.2347, "step": 211930 }, { "epoch": 9.68, "learning_rate": 1.6133461485651518e-06, "loss": 1.3166, "step": 211940 }, { "epoch": 9.68, "learning_rate": 1.6110577143118678e-06, "loss": 1.2442, "step": 211950 }, { "epoch": 9.68, "learning_rate": 1.6087692800585839e-06, "loss": 1.3645, "step": 211960 }, { "epoch": 9.68, "learning_rate": 1.6064808458053003e-06, "loss": 1.3083, "step": 211970 }, { "epoch": 9.68, "learning_rate": 1.6041924115520162e-06, "loss": 1.345, "step": 211980 }, { "epoch": 9.68, "learning_rate": 1.6019039772987322e-06, "loss": 1.3976, "step": 211990 }, { "epoch": 9.68, "learning_rate": 1.5996155430454482e-06, "loss": 1.1332, "step": 212000 }, { "epoch": 9.68, "learning_rate": 1.5973271087921643e-06, "loss": 1.3375, "step": 212010 }, { "epoch": 9.68, "learning_rate": 1.5950386745388807e-06, "loss": 1.3264, "step": 212020 }, { "epoch": 9.68, "learning_rate": 1.5927502402855968e-06, "loss": 1.5829, "step": 212030 }, { "epoch": 9.68, "learning_rate": 1.5904618060323128e-06, "loss": 1.4373, "step": 212040 }, { "epoch": 9.68, "learning_rate": 1.5881733717790289e-06, "loss": 1.4497, "step": 212050 }, { "epoch": 9.68, "learning_rate": 1.585884937525745e-06, "loss": 1.3548, "step": 212060 }, { "epoch": 9.68, "learning_rate": 1.583596503272461e-06, "loss": 1.2923, "step": 212070 }, { "epoch": 9.68, "learning_rate": 1.5813080690191772e-06, "loss": 1.5671, "step": 212080 }, { "epoch": 9.68, "learning_rate": 1.5790196347658932e-06, "loss": 1.3627, "step": 212090 }, { "epoch": 9.69, "learning_rate": 1.5767312005126093e-06, "loss": 1.2321, "step": 212100 }, { "epoch": 9.69, "learning_rate": 1.5744427662593253e-06, "loss": 1.4703, "step": 212110 }, { "epoch": 9.69, "learning_rate": 1.5721543320060414e-06, "loss": 1.2276, "step": 212120 }, { "epoch": 9.69, "learning_rate": 1.5698658977527578e-06, "loss": 1.3227, "step": 212130 }, { "epoch": 9.69, "learning_rate": 1.5675774634994739e-06, "loss": 1.2893, "step": 212140 }, { "epoch": 9.69, "learning_rate": 1.56528902924619e-06, "loss": 1.3573, "step": 212150 }, { "epoch": 9.69, "learning_rate": 1.563000594992906e-06, "loss": 1.2596, "step": 212160 }, { "epoch": 9.69, "learning_rate": 1.560712160739622e-06, "loss": 1.2438, "step": 212170 }, { "epoch": 9.69, "learning_rate": 1.558423726486338e-06, "loss": 1.2885, "step": 212180 }, { "epoch": 9.69, "learning_rate": 1.556135292233054e-06, "loss": 1.2916, "step": 212190 }, { "epoch": 9.69, "learning_rate": 1.5538468579797703e-06, "loss": 1.395, "step": 212200 }, { "epoch": 9.69, "learning_rate": 1.5515584237264863e-06, "loss": 1.1781, "step": 212210 }, { "epoch": 9.69, "learning_rate": 1.5492699894732026e-06, "loss": 1.2638, "step": 212220 }, { "epoch": 9.69, "learning_rate": 1.5469815552199186e-06, "loss": 1.3989, "step": 212230 }, { "epoch": 9.69, "learning_rate": 1.5446931209666347e-06, "loss": 1.39, "step": 212240 }, { "epoch": 9.69, "learning_rate": 1.542404686713351e-06, "loss": 1.4124, "step": 212250 }, { "epoch": 9.69, "learning_rate": 1.540116252460067e-06, "loss": 1.2642, "step": 212260 }, { "epoch": 9.69, "learning_rate": 1.537827818206783e-06, "loss": 1.3213, "step": 212270 }, { "epoch": 9.69, "learning_rate": 1.535539383953499e-06, "loss": 1.4648, "step": 212280 }, { "epoch": 9.69, "learning_rate": 1.533250949700215e-06, "loss": 1.4661, "step": 212290 }, { "epoch": 9.69, "learning_rate": 1.5309625154469313e-06, "loss": 1.3404, "step": 212300 }, { "epoch": 9.69, "learning_rate": 1.5286740811936474e-06, "loss": 1.4663, "step": 212310 }, { "epoch": 9.7, "learning_rate": 1.5263856469403634e-06, "loss": 1.2736, "step": 212320 }, { "epoch": 9.7, "learning_rate": 1.5240972126870797e-06, "loss": 1.3361, "step": 212330 }, { "epoch": 9.7, "learning_rate": 1.5218087784337957e-06, "loss": 1.3892, "step": 212340 }, { "epoch": 9.7, "learning_rate": 1.5195203441805117e-06, "loss": 1.3018, "step": 212350 }, { "epoch": 9.7, "learning_rate": 1.5172319099272278e-06, "loss": 1.3022, "step": 212360 }, { "epoch": 9.7, "learning_rate": 1.5149434756739438e-06, "loss": 1.3042, "step": 212370 }, { "epoch": 9.7, "learning_rate": 1.51265504142066e-06, "loss": 1.4875, "step": 212380 }, { "epoch": 9.7, "learning_rate": 1.5103666071673761e-06, "loss": 1.3513, "step": 212390 }, { "epoch": 9.7, "learning_rate": 1.5080781729140922e-06, "loss": 1.3961, "step": 212400 }, { "epoch": 9.7, "learning_rate": 1.5057897386608084e-06, "loss": 1.3086, "step": 212410 }, { "epoch": 9.7, "learning_rate": 1.5035013044075244e-06, "loss": 1.1857, "step": 212420 }, { "epoch": 9.7, "learning_rate": 1.5012128701542407e-06, "loss": 1.2534, "step": 212430 }, { "epoch": 9.7, "learning_rate": 1.4989244359009567e-06, "loss": 1.3889, "step": 212440 }, { "epoch": 9.7, "learning_rate": 1.4966360016476728e-06, "loss": 1.453, "step": 212450 }, { "epoch": 9.7, "learning_rate": 1.4943475673943888e-06, "loss": 1.2576, "step": 212460 }, { "epoch": 9.7, "learning_rate": 1.4920591331411048e-06, "loss": 1.3752, "step": 212470 }, { "epoch": 9.7, "learning_rate": 1.489770698887821e-06, "loss": 1.2568, "step": 212480 }, { "epoch": 9.7, "learning_rate": 1.4874822646345371e-06, "loss": 1.2265, "step": 212490 }, { "epoch": 9.7, "learning_rate": 1.4851938303812532e-06, "loss": 1.3347, "step": 212500 }, { "epoch": 9.7, "learning_rate": 1.4829053961279694e-06, "loss": 1.3534, "step": 212510 }, { "epoch": 9.7, "learning_rate": 1.4806169618746855e-06, "loss": 1.3799, "step": 212520 }, { "epoch": 9.7, "learning_rate": 1.4783285276214015e-06, "loss": 1.3323, "step": 212530 }, { "epoch": 9.71, "learning_rate": 1.4760400933681175e-06, "loss": 1.3516, "step": 212540 }, { "epoch": 9.71, "learning_rate": 1.4737516591148336e-06, "loss": 1.4473, "step": 212550 }, { "epoch": 9.71, "learning_rate": 1.4714632248615498e-06, "loss": 1.4624, "step": 212560 }, { "epoch": 9.71, "learning_rate": 1.4691747906082659e-06, "loss": 1.3083, "step": 212570 }, { "epoch": 9.71, "learning_rate": 1.466886356354982e-06, "loss": 1.2968, "step": 212580 }, { "epoch": 9.71, "learning_rate": 1.4645979221016982e-06, "loss": 1.2288, "step": 212590 }, { "epoch": 9.71, "learning_rate": 1.4623094878484142e-06, "loss": 1.2929, "step": 212600 }, { "epoch": 9.71, "learning_rate": 1.4600210535951302e-06, "loss": 1.2934, "step": 212610 }, { "epoch": 9.71, "learning_rate": 1.4577326193418465e-06, "loss": 1.3988, "step": 212620 }, { "epoch": 9.71, "learning_rate": 1.4554441850885625e-06, "loss": 1.4046, "step": 212630 }, { "epoch": 9.71, "learning_rate": 1.4531557508352786e-06, "loss": 1.3893, "step": 212640 }, { "epoch": 9.71, "learning_rate": 1.4508673165819946e-06, "loss": 1.262, "step": 212650 }, { "epoch": 9.71, "learning_rate": 1.4485788823287107e-06, "loss": 1.342, "step": 212660 }, { "epoch": 9.71, "learning_rate": 1.446290448075427e-06, "loss": 1.2236, "step": 212670 }, { "epoch": 9.71, "learning_rate": 1.444002013822143e-06, "loss": 1.3347, "step": 212680 }, { "epoch": 9.71, "learning_rate": 1.4417135795688592e-06, "loss": 1.3241, "step": 212690 }, { "epoch": 9.71, "learning_rate": 1.4394251453155752e-06, "loss": 1.2157, "step": 212700 }, { "epoch": 9.71, "learning_rate": 1.4371367110622913e-06, "loss": 1.3262, "step": 212710 }, { "epoch": 9.71, "learning_rate": 1.4348482768090073e-06, "loss": 1.3676, "step": 212720 }, { "epoch": 9.71, "learning_rate": 1.4325598425557234e-06, "loss": 1.423, "step": 212730 }, { "epoch": 9.71, "learning_rate": 1.4302714083024394e-06, "loss": 1.2841, "step": 212740 }, { "epoch": 9.71, "learning_rate": 1.4279829740491556e-06, "loss": 1.4289, "step": 212750 }, { "epoch": 9.72, "learning_rate": 1.4256945397958717e-06, "loss": 1.3672, "step": 212760 }, { "epoch": 9.72, "learning_rate": 1.423406105542588e-06, "loss": 1.1705, "step": 212770 }, { "epoch": 9.72, "learning_rate": 1.421117671289304e-06, "loss": 1.4242, "step": 212780 }, { "epoch": 9.72, "learning_rate": 1.41882923703602e-06, "loss": 1.3485, "step": 212790 }, { "epoch": 9.72, "learning_rate": 1.4165408027827363e-06, "loss": 1.4347, "step": 212800 }, { "epoch": 9.72, "learning_rate": 1.4142523685294523e-06, "loss": 1.3607, "step": 212810 }, { "epoch": 9.72, "learning_rate": 1.4119639342761681e-06, "loss": 1.2878, "step": 212820 }, { "epoch": 9.72, "learning_rate": 1.4096755000228844e-06, "loss": 1.3261, "step": 212830 }, { "epoch": 9.72, "learning_rate": 1.4073870657696004e-06, "loss": 1.5617, "step": 212840 }, { "epoch": 9.72, "learning_rate": 1.4050986315163167e-06, "loss": 1.2702, "step": 212850 }, { "epoch": 9.72, "learning_rate": 1.4028101972630327e-06, "loss": 1.4489, "step": 212860 }, { "epoch": 9.72, "learning_rate": 1.4005217630097488e-06, "loss": 1.2685, "step": 212870 }, { "epoch": 9.72, "learning_rate": 1.398233328756465e-06, "loss": 1.3358, "step": 212880 }, { "epoch": 9.72, "learning_rate": 1.395944894503181e-06, "loss": 1.3918, "step": 212890 }, { "epoch": 9.72, "learning_rate": 1.393656460249897e-06, "loss": 1.3979, "step": 212900 }, { "epoch": 9.72, "learning_rate": 1.3913680259966131e-06, "loss": 1.2789, "step": 212910 }, { "epoch": 9.72, "learning_rate": 1.3890795917433292e-06, "loss": 1.4982, "step": 212920 }, { "epoch": 9.72, "learning_rate": 1.3867911574900454e-06, "loss": 1.3302, "step": 212930 }, { "epoch": 9.72, "learning_rate": 1.3845027232367615e-06, "loss": 1.2851, "step": 212940 }, { "epoch": 9.72, "learning_rate": 1.3822142889834775e-06, "loss": 1.2633, "step": 212950 }, { "epoch": 9.72, "learning_rate": 1.3799258547301937e-06, "loss": 1.3075, "step": 212960 }, { "epoch": 9.72, "learning_rate": 1.3776374204769098e-06, "loss": 1.3738, "step": 212970 }, { "epoch": 9.73, "learning_rate": 1.375348986223626e-06, "loss": 1.3975, "step": 212980 }, { "epoch": 9.73, "learning_rate": 1.373060551970342e-06, "loss": 1.3634, "step": 212990 }, { "epoch": 9.73, "learning_rate": 1.370772117717058e-06, "loss": 1.4175, "step": 213000 }, { "epoch": 9.73, "learning_rate": 1.3684836834637742e-06, "loss": 1.4497, "step": 213010 }, { "epoch": 9.73, "learning_rate": 1.3661952492104902e-06, "loss": 1.2762, "step": 213020 }, { "epoch": 9.73, "learning_rate": 1.3639068149572062e-06, "loss": 1.3065, "step": 213030 }, { "epoch": 9.73, "learning_rate": 1.3616183807039225e-06, "loss": 1.2733, "step": 213040 }, { "epoch": 9.73, "learning_rate": 1.3593299464506385e-06, "loss": 1.3635, "step": 213050 }, { "epoch": 9.73, "learning_rate": 1.3570415121973548e-06, "loss": 1.3534, "step": 213060 }, { "epoch": 9.73, "learning_rate": 1.3547530779440708e-06, "loss": 1.3255, "step": 213070 }, { "epoch": 9.73, "learning_rate": 1.3524646436907869e-06, "loss": 1.3808, "step": 213080 }, { "epoch": 9.73, "learning_rate": 1.3501762094375029e-06, "loss": 1.1918, "step": 213090 }, { "epoch": 9.73, "learning_rate": 1.347887775184219e-06, "loss": 1.2219, "step": 213100 }, { "epoch": 9.73, "learning_rate": 1.345599340930935e-06, "loss": 1.336, "step": 213110 }, { "epoch": 9.73, "learning_rate": 1.3433109066776512e-06, "loss": 1.2804, "step": 213120 }, { "epoch": 9.73, "learning_rate": 1.3410224724243673e-06, "loss": 1.1927, "step": 213130 }, { "epoch": 9.73, "learning_rate": 1.3387340381710835e-06, "loss": 1.4106, "step": 213140 }, { "epoch": 9.73, "learning_rate": 1.3364456039177995e-06, "loss": 1.2852, "step": 213150 }, { "epoch": 9.73, "learning_rate": 1.3341571696645156e-06, "loss": 1.1019, "step": 213160 }, { "epoch": 9.73, "learning_rate": 1.3318687354112318e-06, "loss": 1.344, "step": 213170 }, { "epoch": 9.73, "learning_rate": 1.3295803011579477e-06, "loss": 1.4354, "step": 213180 }, { "epoch": 9.73, "learning_rate": 1.327291866904664e-06, "loss": 1.2274, "step": 213190 }, { "epoch": 9.74, "learning_rate": 1.32500343265138e-06, "loss": 1.5992, "step": 213200 }, { "epoch": 9.74, "learning_rate": 1.322714998398096e-06, "loss": 1.2938, "step": 213210 }, { "epoch": 9.74, "learning_rate": 1.3204265641448122e-06, "loss": 1.3016, "step": 213220 }, { "epoch": 9.74, "learning_rate": 1.3181381298915283e-06, "loss": 1.3357, "step": 213230 }, { "epoch": 9.74, "learning_rate": 1.3158496956382443e-06, "loss": 1.2922, "step": 213240 }, { "epoch": 9.74, "learning_rate": 1.3135612613849606e-06, "loss": 1.3304, "step": 213250 }, { "epoch": 9.74, "learning_rate": 1.3112728271316766e-06, "loss": 1.4504, "step": 213260 }, { "epoch": 9.74, "learning_rate": 1.3089843928783927e-06, "loss": 1.3892, "step": 213270 }, { "epoch": 9.74, "learning_rate": 1.3066959586251087e-06, "loss": 1.2144, "step": 213280 }, { "epoch": 9.74, "learning_rate": 1.3044075243718247e-06, "loss": 1.3902, "step": 213290 }, { "epoch": 9.74, "learning_rate": 1.302119090118541e-06, "loss": 1.2272, "step": 213300 }, { "epoch": 9.74, "learning_rate": 1.299830655865257e-06, "loss": 1.2551, "step": 213310 }, { "epoch": 9.74, "learning_rate": 1.297542221611973e-06, "loss": 1.2923, "step": 213320 }, { "epoch": 9.74, "learning_rate": 1.2952537873586893e-06, "loss": 1.3888, "step": 213330 }, { "epoch": 9.74, "learning_rate": 1.2929653531054054e-06, "loss": 1.4199, "step": 213340 }, { "epoch": 9.74, "learning_rate": 1.2906769188521216e-06, "loss": 1.2576, "step": 213350 }, { "epoch": 9.74, "learning_rate": 1.2883884845988376e-06, "loss": 1.2292, "step": 213360 }, { "epoch": 9.74, "learning_rate": 1.2861000503455535e-06, "loss": 1.3393, "step": 213370 }, { "epoch": 9.74, "learning_rate": 1.2838116160922697e-06, "loss": 1.2848, "step": 213380 }, { "epoch": 9.74, "learning_rate": 1.2815231818389858e-06, "loss": 1.3462, "step": 213390 }, { "epoch": 9.74, "learning_rate": 1.2792347475857018e-06, "loss": 1.3776, "step": 213400 }, { "epoch": 9.74, "learning_rate": 1.276946313332418e-06, "loss": 1.2793, "step": 213410 }, { "epoch": 9.75, "learning_rate": 1.274657879079134e-06, "loss": 1.4225, "step": 213420 }, { "epoch": 9.75, "learning_rate": 1.2723694448258503e-06, "loss": 1.4183, "step": 213430 }, { "epoch": 9.75, "learning_rate": 1.2700810105725664e-06, "loss": 1.277, "step": 213440 }, { "epoch": 9.75, "learning_rate": 1.2677925763192824e-06, "loss": 1.2535, "step": 213450 }, { "epoch": 9.75, "learning_rate": 1.2655041420659985e-06, "loss": 1.266, "step": 213460 }, { "epoch": 9.75, "learning_rate": 1.2632157078127145e-06, "loss": 1.3161, "step": 213470 }, { "epoch": 9.75, "learning_rate": 1.2609272735594308e-06, "loss": 1.3119, "step": 213480 }, { "epoch": 9.75, "learning_rate": 1.2586388393061468e-06, "loss": 1.3072, "step": 213490 }, { "epoch": 9.75, "learning_rate": 1.2563504050528628e-06, "loss": 1.3185, "step": 213500 }, { "epoch": 9.75, "learning_rate": 1.254061970799579e-06, "loss": 1.2368, "step": 213510 }, { "epoch": 9.75, "learning_rate": 1.2517735365462951e-06, "loss": 1.1977, "step": 213520 }, { "epoch": 9.75, "learning_rate": 1.2494851022930112e-06, "loss": 1.4712, "step": 213530 }, { "epoch": 9.75, "learning_rate": 1.2471966680397274e-06, "loss": 1.3541, "step": 213540 }, { "epoch": 9.75, "learning_rate": 1.2449082337864432e-06, "loss": 1.5234, "step": 213550 }, { "epoch": 9.75, "learning_rate": 1.2426197995331595e-06, "loss": 1.4414, "step": 213560 }, { "epoch": 9.75, "learning_rate": 1.2403313652798755e-06, "loss": 1.4244, "step": 213570 }, { "epoch": 9.75, "learning_rate": 1.2380429310265916e-06, "loss": 1.3256, "step": 213580 }, { "epoch": 9.75, "learning_rate": 1.2357544967733078e-06, "loss": 1.4566, "step": 213590 }, { "epoch": 9.75, "learning_rate": 1.2334660625200239e-06, "loss": 1.3016, "step": 213600 }, { "epoch": 9.75, "learning_rate": 1.23117762826674e-06, "loss": 1.3125, "step": 213610 }, { "epoch": 9.75, "learning_rate": 1.2288891940134562e-06, "loss": 1.2917, "step": 213620 }, { "epoch": 9.75, "learning_rate": 1.2266007597601722e-06, "loss": 1.1812, "step": 213630 }, { "epoch": 9.76, "learning_rate": 1.2243123255068882e-06, "loss": 1.3948, "step": 213640 }, { "epoch": 9.76, "learning_rate": 1.2220238912536043e-06, "loss": 1.2513, "step": 213650 }, { "epoch": 9.76, "learning_rate": 1.2197354570003203e-06, "loss": 1.32, "step": 213660 }, { "epoch": 9.76, "learning_rate": 1.2174470227470366e-06, "loss": 1.3012, "step": 213670 }, { "epoch": 9.76, "learning_rate": 1.2151585884937526e-06, "loss": 1.2979, "step": 213680 }, { "epoch": 9.76, "learning_rate": 1.2128701542404689e-06, "loss": 1.3944, "step": 213690 }, { "epoch": 9.76, "learning_rate": 1.2105817199871849e-06, "loss": 1.2746, "step": 213700 }, { "epoch": 9.76, "learning_rate": 1.208293285733901e-06, "loss": 1.2999, "step": 213710 }, { "epoch": 9.76, "learning_rate": 1.2060048514806172e-06, "loss": 1.2001, "step": 213720 }, { "epoch": 9.76, "learning_rate": 1.203716417227333e-06, "loss": 1.3875, "step": 213730 }, { "epoch": 9.76, "learning_rate": 1.201427982974049e-06, "loss": 1.3128, "step": 213740 }, { "epoch": 9.76, "learning_rate": 1.1991395487207653e-06, "loss": 1.231, "step": 213750 }, { "epoch": 9.76, "learning_rate": 1.1968511144674813e-06, "loss": 1.406, "step": 213760 }, { "epoch": 9.76, "learning_rate": 1.1945626802141976e-06, "loss": 1.4003, "step": 213770 }, { "epoch": 9.76, "learning_rate": 1.1922742459609136e-06, "loss": 1.3506, "step": 213780 }, { "epoch": 9.76, "learning_rate": 1.1899858117076297e-06, "loss": 1.2818, "step": 213790 }, { "epoch": 9.76, "learning_rate": 1.187697377454346e-06, "loss": 1.3058, "step": 213800 }, { "epoch": 9.76, "learning_rate": 1.185408943201062e-06, "loss": 1.4402, "step": 213810 }, { "epoch": 9.76, "learning_rate": 1.183120508947778e-06, "loss": 1.254, "step": 213820 }, { "epoch": 9.76, "learning_rate": 1.180832074694494e-06, "loss": 1.1718, "step": 213830 }, { "epoch": 9.76, "learning_rate": 1.17854364044121e-06, "loss": 1.2501, "step": 213840 }, { "epoch": 9.76, "learning_rate": 1.1762552061879263e-06, "loss": 1.3495, "step": 213850 }, { "epoch": 9.77, "learning_rate": 1.1739667719346424e-06, "loss": 1.3056, "step": 213860 }, { "epoch": 9.77, "learning_rate": 1.1716783376813584e-06, "loss": 1.348, "step": 213870 }, { "epoch": 9.77, "learning_rate": 1.1693899034280747e-06, "loss": 1.2262, "step": 213880 }, { "epoch": 9.77, "learning_rate": 1.1671014691747907e-06, "loss": 1.5115, "step": 213890 }, { "epoch": 9.77, "learning_rate": 1.164813034921507e-06, "loss": 1.2421, "step": 213900 }, { "epoch": 9.77, "learning_rate": 1.1625246006682228e-06, "loss": 1.4546, "step": 213910 }, { "epoch": 9.77, "learning_rate": 1.1602361664149388e-06, "loss": 1.363, "step": 213920 }, { "epoch": 9.77, "learning_rate": 1.157947732161655e-06, "loss": 1.5373, "step": 213930 }, { "epoch": 9.77, "learning_rate": 1.1556592979083711e-06, "loss": 1.2781, "step": 213940 }, { "epoch": 9.77, "learning_rate": 1.1533708636550871e-06, "loss": 1.2894, "step": 213950 }, { "epoch": 9.77, "learning_rate": 1.1510824294018034e-06, "loss": 1.2612, "step": 213960 }, { "epoch": 9.77, "learning_rate": 1.1487939951485194e-06, "loss": 1.3037, "step": 213970 }, { "epoch": 9.77, "learning_rate": 1.1465055608952357e-06, "loss": 1.2709, "step": 213980 }, { "epoch": 9.77, "learning_rate": 1.1442171266419517e-06, "loss": 1.3681, "step": 213990 }, { "epoch": 9.77, "learning_rate": 1.1419286923886678e-06, "loss": 1.1794, "step": 214000 }, { "epoch": 9.77, "learning_rate": 1.1396402581353838e-06, "loss": 1.2855, "step": 214010 }, { "epoch": 9.77, "learning_rate": 1.1373518238820998e-06, "loss": 1.3457, "step": 214020 }, { "epoch": 9.77, "learning_rate": 1.1350633896288159e-06, "loss": 1.2948, "step": 214030 }, { "epoch": 9.77, "learning_rate": 1.1327749553755321e-06, "loss": 1.3811, "step": 214040 }, { "epoch": 9.77, "learning_rate": 1.1304865211222482e-06, "loss": 1.411, "step": 214050 }, { "epoch": 9.77, "learning_rate": 1.1281980868689644e-06, "loss": 1.2432, "step": 214060 }, { "epoch": 9.77, "learning_rate": 1.1259096526156805e-06, "loss": 1.2076, "step": 214070 }, { "epoch": 9.78, "learning_rate": 1.1236212183623965e-06, "loss": 1.3878, "step": 214080 }, { "epoch": 9.78, "learning_rate": 1.1213327841091125e-06, "loss": 1.4124, "step": 214090 }, { "epoch": 9.78, "learning_rate": 1.1190443498558286e-06, "loss": 1.3155, "step": 214100 }, { "epoch": 9.78, "learning_rate": 1.1167559156025446e-06, "loss": 1.4031, "step": 214110 }, { "epoch": 9.78, "learning_rate": 1.1144674813492609e-06, "loss": 1.4693, "step": 214120 }, { "epoch": 9.78, "learning_rate": 1.112179047095977e-06, "loss": 1.3819, "step": 214130 }, { "epoch": 9.78, "learning_rate": 1.1098906128426932e-06, "loss": 1.408, "step": 214140 }, { "epoch": 9.78, "learning_rate": 1.1076021785894092e-06, "loss": 1.3258, "step": 214150 }, { "epoch": 9.78, "learning_rate": 1.1053137443361252e-06, "loss": 1.303, "step": 214160 }, { "epoch": 9.78, "learning_rate": 1.1030253100828415e-06, "loss": 1.4938, "step": 214170 }, { "epoch": 9.78, "learning_rate": 1.1007368758295575e-06, "loss": 1.3927, "step": 214180 }, { "epoch": 9.78, "learning_rate": 1.0984484415762736e-06, "loss": 1.3381, "step": 214190 }, { "epoch": 9.78, "learning_rate": 1.0961600073229896e-06, "loss": 1.3117, "step": 214200 }, { "epoch": 9.78, "learning_rate": 1.0938715730697057e-06, "loss": 1.3695, "step": 214210 }, { "epoch": 9.78, "learning_rate": 1.091583138816422e-06, "loss": 1.2619, "step": 214220 }, { "epoch": 9.78, "learning_rate": 1.089294704563138e-06, "loss": 1.3107, "step": 214230 }, { "epoch": 9.78, "learning_rate": 1.087006270309854e-06, "loss": 1.4408, "step": 214240 }, { "epoch": 9.78, "learning_rate": 1.0847178360565702e-06, "loss": 1.4182, "step": 214250 }, { "epoch": 9.78, "learning_rate": 1.0824294018032863e-06, "loss": 1.4052, "step": 214260 }, { "epoch": 9.78, "learning_rate": 1.0801409675500023e-06, "loss": 1.4745, "step": 214270 }, { "epoch": 9.78, "learning_rate": 1.0778525332967184e-06, "loss": 1.2241, "step": 214280 }, { "epoch": 9.79, "learning_rate": 1.0755640990434344e-06, "loss": 1.3658, "step": 214290 }, { "epoch": 9.79, "learning_rate": 1.0732756647901506e-06, "loss": 1.327, "step": 214300 }, { "epoch": 9.79, "learning_rate": 1.0709872305368667e-06, "loss": 1.2978, "step": 214310 }, { "epoch": 9.79, "learning_rate": 1.0686987962835827e-06, "loss": 1.3867, "step": 214320 }, { "epoch": 9.79, "learning_rate": 1.066410362030299e-06, "loss": 1.4009, "step": 214330 }, { "epoch": 9.79, "learning_rate": 1.064121927777015e-06, "loss": 1.2496, "step": 214340 }, { "epoch": 9.79, "learning_rate": 1.0618334935237313e-06, "loss": 1.2586, "step": 214350 }, { "epoch": 9.79, "learning_rate": 1.0595450592704473e-06, "loss": 1.4666, "step": 214360 }, { "epoch": 9.79, "learning_rate": 1.0572566250171633e-06, "loss": 1.2442, "step": 214370 }, { "epoch": 9.79, "learning_rate": 1.0549681907638794e-06, "loss": 1.2662, "step": 214380 }, { "epoch": 9.79, "learning_rate": 1.0526797565105954e-06, "loss": 1.2621, "step": 214390 }, { "epoch": 9.79, "learning_rate": 1.0503913222573117e-06, "loss": 1.3044, "step": 214400 }, { "epoch": 9.79, "learning_rate": 1.0481028880040277e-06, "loss": 1.441, "step": 214410 }, { "epoch": 9.79, "learning_rate": 1.0458144537507437e-06, "loss": 1.2788, "step": 214420 }, { "epoch": 9.79, "learning_rate": 1.04352601949746e-06, "loss": 1.4569, "step": 214430 }, { "epoch": 9.79, "learning_rate": 1.041237585244176e-06, "loss": 1.267, "step": 214440 }, { "epoch": 9.79, "learning_rate": 1.038949150990892e-06, "loss": 1.2912, "step": 214450 }, { "epoch": 9.79, "learning_rate": 1.0366607167376081e-06, "loss": 1.2369, "step": 214460 }, { "epoch": 9.79, "learning_rate": 1.0343722824843242e-06, "loss": 1.2655, "step": 214470 }, { "epoch": 9.79, "learning_rate": 1.0320838482310404e-06, "loss": 1.3646, "step": 214480 }, { "epoch": 9.79, "learning_rate": 1.0297954139777564e-06, "loss": 1.3014, "step": 214490 }, { "epoch": 9.79, "learning_rate": 1.0275069797244725e-06, "loss": 1.366, "step": 214500 }, { "epoch": 9.8, "learning_rate": 1.0252185454711887e-06, "loss": 1.2377, "step": 214510 }, { "epoch": 9.8, "learning_rate": 1.0229301112179048e-06, "loss": 1.4181, "step": 214520 }, { "epoch": 9.8, "learning_rate": 1.0206416769646208e-06, "loss": 1.3807, "step": 214530 }, { "epoch": 9.8, "learning_rate": 1.018353242711337e-06, "loss": 1.3687, "step": 214540 }, { "epoch": 9.8, "learning_rate": 1.0160648084580531e-06, "loss": 1.2489, "step": 214550 }, { "epoch": 9.8, "learning_rate": 1.0137763742047691e-06, "loss": 1.4519, "step": 214560 }, { "epoch": 9.8, "learning_rate": 1.0114879399514852e-06, "loss": 1.2829, "step": 214570 }, { "epoch": 9.8, "learning_rate": 1.0091995056982012e-06, "loss": 1.4063, "step": 214580 }, { "epoch": 9.8, "learning_rate": 1.0069110714449175e-06, "loss": 1.2779, "step": 214590 }, { "epoch": 9.8, "learning_rate": 1.0046226371916335e-06, "loss": 1.2681, "step": 214600 }, { "epoch": 9.8, "learning_rate": 1.0023342029383496e-06, "loss": 1.4265, "step": 214610 }, { "epoch": 9.8, "learning_rate": 1.0000457686850658e-06, "loss": 1.3438, "step": 214620 }, { "epoch": 9.8, "learning_rate": 9.977573344317818e-07, "loss": 1.3124, "step": 214630 }, { "epoch": 9.8, "learning_rate": 9.954689001784979e-07, "loss": 1.3623, "step": 214640 }, { "epoch": 9.8, "learning_rate": 9.93180465925214e-07, "loss": 1.5631, "step": 214650 }, { "epoch": 9.8, "learning_rate": 9.9089203167193e-07, "loss": 1.2143, "step": 214660 }, { "epoch": 9.8, "learning_rate": 9.886035974186462e-07, "loss": 1.3764, "step": 214670 }, { "epoch": 9.8, "learning_rate": 9.863151631653623e-07, "loss": 1.3327, "step": 214680 }, { "epoch": 9.8, "learning_rate": 9.840267289120785e-07, "loss": 1.4682, "step": 214690 }, { "epoch": 9.8, "learning_rate": 9.817382946587945e-07, "loss": 1.2458, "step": 214700 }, { "epoch": 9.8, "learning_rate": 9.794498604055106e-07, "loss": 1.2503, "step": 214710 }, { "epoch": 9.8, "learning_rate": 9.771614261522268e-07, "loss": 1.2056, "step": 214720 }, { "epoch": 9.81, "learning_rate": 9.748729918989429e-07, "loss": 1.3965, "step": 214730 }, { "epoch": 9.81, "learning_rate": 9.72584557645659e-07, "loss": 1.3966, "step": 214740 }, { "epoch": 9.81, "learning_rate": 9.70296123392375e-07, "loss": 1.2766, "step": 214750 }, { "epoch": 9.81, "learning_rate": 9.68007689139091e-07, "loss": 1.4113, "step": 214760 }, { "epoch": 9.81, "learning_rate": 9.657192548858072e-07, "loss": 1.2969, "step": 214770 }, { "epoch": 9.81, "learning_rate": 9.634308206325233e-07, "loss": 1.3554, "step": 214780 }, { "epoch": 9.81, "learning_rate": 9.611423863792393e-07, "loss": 1.3912, "step": 214790 }, { "epoch": 9.81, "learning_rate": 9.588539521259556e-07, "loss": 1.3718, "step": 214800 }, { "epoch": 9.81, "learning_rate": 9.565655178726716e-07, "loss": 1.2898, "step": 214810 }, { "epoch": 9.81, "learning_rate": 9.542770836193877e-07, "loss": 1.2472, "step": 214820 }, { "epoch": 9.81, "learning_rate": 9.519886493661038e-07, "loss": 1.3726, "step": 214830 }, { "epoch": 9.81, "learning_rate": 9.497002151128198e-07, "loss": 1.4919, "step": 214840 }, { "epoch": 9.81, "learning_rate": 9.47411780859536e-07, "loss": 1.3827, "step": 214850 }, { "epoch": 9.81, "learning_rate": 9.45123346606252e-07, "loss": 1.2417, "step": 214860 }, { "epoch": 9.81, "learning_rate": 9.428349123529681e-07, "loss": 1.3464, "step": 214870 }, { "epoch": 9.81, "learning_rate": 9.405464780996843e-07, "loss": 1.3434, "step": 214880 }, { "epoch": 9.81, "learning_rate": 9.382580438464004e-07, "loss": 1.281, "step": 214890 }, { "epoch": 9.81, "learning_rate": 9.359696095931165e-07, "loss": 1.3334, "step": 214900 }, { "epoch": 9.81, "learning_rate": 9.336811753398325e-07, "loss": 1.313, "step": 214910 }, { "epoch": 9.81, "learning_rate": 9.313927410865486e-07, "loss": 1.3662, "step": 214920 }, { "epoch": 9.81, "learning_rate": 9.291043068332648e-07, "loss": 1.4762, "step": 214930 }, { "epoch": 9.81, "learning_rate": 9.268158725799809e-07, "loss": 1.2023, "step": 214940 }, { "epoch": 9.82, "learning_rate": 9.245274383266968e-07, "loss": 1.3332, "step": 214950 }, { "epoch": 9.82, "learning_rate": 9.22239004073413e-07, "loss": 1.2803, "step": 214960 }, { "epoch": 9.82, "learning_rate": 9.199505698201291e-07, "loss": 1.1775, "step": 214970 }, { "epoch": 9.82, "learning_rate": 9.176621355668452e-07, "loss": 1.3705, "step": 214980 }, { "epoch": 9.82, "learning_rate": 9.153737013135613e-07, "loss": 1.4068, "step": 214990 }, { "epoch": 9.82, "learning_rate": 9.130852670602773e-07, "loss": 1.2641, "step": 215000 }, { "epoch": 9.82, "learning_rate": 9.107968328069936e-07, "loss": 1.2603, "step": 215010 }, { "epoch": 9.82, "learning_rate": 9.085083985537096e-07, "loss": 1.3178, "step": 215020 }, { "epoch": 9.82, "learning_rate": 9.062199643004256e-07, "loss": 1.3008, "step": 215030 }, { "epoch": 9.82, "learning_rate": 9.039315300471418e-07, "loss": 1.2766, "step": 215040 }, { "epoch": 9.82, "learning_rate": 9.016430957938578e-07, "loss": 1.5686, "step": 215050 }, { "epoch": 9.82, "learning_rate": 8.993546615405741e-07, "loss": 1.4314, "step": 215060 }, { "epoch": 9.82, "learning_rate": 8.970662272872901e-07, "loss": 1.3899, "step": 215070 }, { "epoch": 9.82, "learning_rate": 8.947777930340062e-07, "loss": 1.2294, "step": 215080 }, { "epoch": 9.82, "learning_rate": 8.924893587807223e-07, "loss": 1.1789, "step": 215090 }, { "epoch": 9.82, "learning_rate": 8.902009245274383e-07, "loss": 1.4328, "step": 215100 }, { "epoch": 9.82, "learning_rate": 8.879124902741544e-07, "loss": 1.2996, "step": 215110 }, { "epoch": 9.82, "learning_rate": 8.856240560208706e-07, "loss": 1.2253, "step": 215120 }, { "epoch": 9.82, "learning_rate": 8.833356217675866e-07, "loss": 1.3689, "step": 215130 }, { "epoch": 9.82, "learning_rate": 8.810471875143028e-07, "loss": 1.2247, "step": 215140 }, { "epoch": 9.82, "learning_rate": 8.787587532610189e-07, "loss": 1.2941, "step": 215150 }, { "epoch": 9.82, "learning_rate": 8.764703190077349e-07, "loss": 1.2973, "step": 215160 }, { "epoch": 9.83, "learning_rate": 8.74181884754451e-07, "loss": 1.2089, "step": 215170 }, { "epoch": 9.83, "learning_rate": 8.718934505011671e-07, "loss": 1.6128, "step": 215180 }, { "epoch": 9.83, "learning_rate": 8.696050162478833e-07, "loss": 1.3237, "step": 215190 }, { "epoch": 9.83, "learning_rate": 8.673165819945994e-07, "loss": 1.2319, "step": 215200 }, { "epoch": 9.83, "learning_rate": 8.650281477413154e-07, "loss": 1.3192, "step": 215210 }, { "epoch": 9.83, "learning_rate": 8.627397134880316e-07, "loss": 1.5331, "step": 215220 }, { "epoch": 9.83, "learning_rate": 8.604512792347476e-07, "loss": 1.3597, "step": 215230 }, { "epoch": 9.83, "learning_rate": 8.581628449814636e-07, "loss": 1.3058, "step": 215240 }, { "epoch": 9.83, "learning_rate": 8.558744107281799e-07, "loss": 1.279, "step": 215250 }, { "epoch": 9.83, "learning_rate": 8.535859764748959e-07, "loss": 1.3249, "step": 215260 }, { "epoch": 9.83, "learning_rate": 8.512975422216121e-07, "loss": 1.3238, "step": 215270 }, { "epoch": 9.83, "learning_rate": 8.490091079683281e-07, "loss": 1.241, "step": 215280 }, { "epoch": 9.83, "learning_rate": 8.467206737150442e-07, "loss": 1.3422, "step": 215290 }, { "epoch": 9.83, "learning_rate": 8.444322394617604e-07, "loss": 1.2539, "step": 215300 }, { "epoch": 9.83, "learning_rate": 8.421438052084763e-07, "loss": 1.3375, "step": 215310 }, { "epoch": 9.83, "learning_rate": 8.398553709551924e-07, "loss": 1.4461, "step": 215320 }, { "epoch": 9.83, "learning_rate": 8.375669367019086e-07, "loss": 1.3832, "step": 215330 }, { "epoch": 9.83, "learning_rate": 8.352785024486247e-07, "loss": 1.2264, "step": 215340 }, { "epoch": 9.83, "learning_rate": 8.329900681953408e-07, "loss": 1.285, "step": 215350 }, { "epoch": 9.83, "learning_rate": 8.307016339420569e-07, "loss": 1.4016, "step": 215360 }, { "epoch": 9.83, "learning_rate": 8.284131996887729e-07, "loss": 1.4012, "step": 215370 }, { "epoch": 9.83, "learning_rate": 8.261247654354891e-07, "loss": 1.5152, "step": 215380 }, { "epoch": 9.84, "learning_rate": 8.238363311822052e-07, "loss": 1.4166, "step": 215390 }, { "epoch": 9.84, "learning_rate": 8.215478969289213e-07, "loss": 1.2834, "step": 215400 }, { "epoch": 9.84, "learning_rate": 8.192594626756374e-07, "loss": 1.3781, "step": 215410 }, { "epoch": 9.84, "learning_rate": 8.169710284223534e-07, "loss": 1.2926, "step": 215420 }, { "epoch": 9.84, "learning_rate": 8.146825941690697e-07, "loss": 1.4782, "step": 215430 }, { "epoch": 9.84, "learning_rate": 8.123941599157857e-07, "loss": 1.4792, "step": 215440 }, { "epoch": 9.84, "learning_rate": 8.101057256625017e-07, "loss": 1.2601, "step": 215450 }, { "epoch": 9.84, "learning_rate": 8.078172914092179e-07, "loss": 1.3378, "step": 215460 }, { "epoch": 9.84, "learning_rate": 8.055288571559339e-07, "loss": 1.2648, "step": 215470 }, { "epoch": 9.84, "learning_rate": 8.032404229026502e-07, "loss": 1.2604, "step": 215480 }, { "epoch": 9.84, "learning_rate": 8.009519886493661e-07, "loss": 1.4261, "step": 215490 }, { "epoch": 9.84, "learning_rate": 7.986635543960821e-07, "loss": 1.3992, "step": 215500 }, { "epoch": 9.84, "learning_rate": 7.963751201427984e-07, "loss": 1.3523, "step": 215510 }, { "epoch": 9.84, "learning_rate": 7.940866858895144e-07, "loss": 1.4368, "step": 215520 }, { "epoch": 9.84, "learning_rate": 7.917982516362305e-07, "loss": 1.2349, "step": 215530 }, { "epoch": 9.84, "learning_rate": 7.895098173829466e-07, "loss": 1.3113, "step": 215540 }, { "epoch": 9.84, "learning_rate": 7.872213831296627e-07, "loss": 1.2024, "step": 215550 }, { "epoch": 9.84, "learning_rate": 7.849329488763789e-07, "loss": 1.355, "step": 215560 }, { "epoch": 9.84, "learning_rate": 7.82644514623095e-07, "loss": 1.3715, "step": 215570 }, { "epoch": 9.84, "learning_rate": 7.80356080369811e-07, "loss": 1.2566, "step": 215580 }, { "epoch": 9.84, "learning_rate": 7.78067646116527e-07, "loss": 1.4435, "step": 215590 }, { "epoch": 9.84, "learning_rate": 7.757792118632432e-07, "loss": 1.3606, "step": 215600 }, { "epoch": 9.85, "learning_rate": 7.734907776099593e-07, "loss": 1.3726, "step": 215610 }, { "epoch": 9.85, "learning_rate": 7.712023433566755e-07, "loss": 1.4196, "step": 215620 }, { "epoch": 9.85, "learning_rate": 7.689139091033915e-07, "loss": 1.4139, "step": 215630 }, { "epoch": 9.85, "learning_rate": 7.666254748501075e-07, "loss": 1.3393, "step": 215640 }, { "epoch": 9.85, "learning_rate": 7.643370405968237e-07, "loss": 1.2739, "step": 215650 }, { "epoch": 9.85, "learning_rate": 7.620486063435398e-07, "loss": 1.3259, "step": 215660 }, { "epoch": 9.85, "learning_rate": 7.597601720902559e-07, "loss": 1.3071, "step": 215670 }, { "epoch": 9.85, "learning_rate": 7.574717378369719e-07, "loss": 1.4336, "step": 215680 }, { "epoch": 9.85, "learning_rate": 7.551833035836881e-07, "loss": 1.2691, "step": 215690 }, { "epoch": 9.85, "learning_rate": 7.528948693304042e-07, "loss": 1.3254, "step": 215700 }, { "epoch": 9.85, "learning_rate": 7.506064350771203e-07, "loss": 1.3039, "step": 215710 }, { "epoch": 9.85, "learning_rate": 7.483180008238364e-07, "loss": 1.4294, "step": 215720 }, { "epoch": 9.85, "learning_rate": 7.460295665705524e-07, "loss": 1.5285, "step": 215730 }, { "epoch": 9.85, "learning_rate": 7.437411323172686e-07, "loss": 1.3909, "step": 215740 }, { "epoch": 9.85, "learning_rate": 7.414526980639847e-07, "loss": 1.3952, "step": 215750 }, { "epoch": 9.85, "learning_rate": 7.391642638107008e-07, "loss": 1.2784, "step": 215760 }, { "epoch": 9.85, "learning_rate": 7.368758295574168e-07, "loss": 1.5122, "step": 215770 }, { "epoch": 9.85, "learning_rate": 7.345873953041329e-07, "loss": 1.3357, "step": 215780 }, { "epoch": 9.85, "learning_rate": 7.322989610508491e-07, "loss": 1.3236, "step": 215790 }, { "epoch": 9.85, "learning_rate": 7.300105267975651e-07, "loss": 1.3516, "step": 215800 }, { "epoch": 9.85, "learning_rate": 7.277220925442813e-07, "loss": 1.4402, "step": 215810 }, { "epoch": 9.85, "learning_rate": 7.254336582909973e-07, "loss": 1.3243, "step": 215820 }, { "epoch": 9.86, "learning_rate": 7.231452240377135e-07, "loss": 1.4194, "step": 215830 }, { "epoch": 9.86, "learning_rate": 7.208567897844296e-07, "loss": 1.3366, "step": 215840 }, { "epoch": 9.86, "learning_rate": 7.185683555311456e-07, "loss": 1.4223, "step": 215850 }, { "epoch": 9.86, "learning_rate": 7.162799212778617e-07, "loss": 1.1833, "step": 215860 }, { "epoch": 9.86, "learning_rate": 7.139914870245778e-07, "loss": 1.1765, "step": 215870 }, { "epoch": 9.86, "learning_rate": 7.11703052771294e-07, "loss": 1.4543, "step": 215880 }, { "epoch": 9.86, "learning_rate": 7.0941461851801e-07, "loss": 1.3065, "step": 215890 }, { "epoch": 9.86, "learning_rate": 7.071261842647262e-07, "loss": 1.3373, "step": 215900 }, { "epoch": 9.86, "learning_rate": 7.048377500114422e-07, "loss": 1.2967, "step": 215910 }, { "epoch": 9.86, "learning_rate": 7.025493157581583e-07, "loss": 1.1781, "step": 215920 }, { "epoch": 9.86, "learning_rate": 7.002608815048744e-07, "loss": 1.4468, "step": 215930 }, { "epoch": 9.86, "learning_rate": 6.979724472515905e-07, "loss": 1.2614, "step": 215940 }, { "epoch": 9.86, "learning_rate": 6.956840129983066e-07, "loss": 1.4274, "step": 215950 }, { "epoch": 9.86, "learning_rate": 6.933955787450227e-07, "loss": 1.3608, "step": 215960 }, { "epoch": 9.86, "learning_rate": 6.911071444917387e-07, "loss": 1.4098, "step": 215970 }, { "epoch": 9.86, "learning_rate": 6.888187102384549e-07, "loss": 1.4465, "step": 215980 }, { "epoch": 9.86, "learning_rate": 6.86530275985171e-07, "loss": 1.2882, "step": 215990 }, { "epoch": 9.86, "learning_rate": 6.842418417318871e-07, "loss": 1.4393, "step": 216000 }, { "epoch": 9.86, "learning_rate": 6.819534074786031e-07, "loss": 1.3666, "step": 216010 }, { "epoch": 9.86, "learning_rate": 6.796649732253193e-07, "loss": 1.2237, "step": 216020 }, { "epoch": 9.86, "learning_rate": 6.773765389720354e-07, "loss": 1.3451, "step": 216030 }, { "epoch": 9.86, "learning_rate": 6.750881047187514e-07, "loss": 1.3436, "step": 216040 }, { "epoch": 9.87, "learning_rate": 6.727996704654675e-07, "loss": 1.2974, "step": 216050 }, { "epoch": 9.87, "learning_rate": 6.705112362121836e-07, "loss": 1.2451, "step": 216060 }, { "epoch": 9.87, "learning_rate": 6.682228019588998e-07, "loss": 1.4302, "step": 216070 }, { "epoch": 9.87, "learning_rate": 6.659343677056159e-07, "loss": 1.2412, "step": 216080 }, { "epoch": 9.87, "learning_rate": 6.63645933452332e-07, "loss": 1.4714, "step": 216090 }, { "epoch": 9.87, "learning_rate": 6.61357499199048e-07, "loss": 1.3125, "step": 216100 }, { "epoch": 9.87, "learning_rate": 6.590690649457641e-07, "loss": 1.2291, "step": 216110 }, { "epoch": 9.87, "learning_rate": 6.567806306924803e-07, "loss": 1.3197, "step": 216120 }, { "epoch": 9.87, "learning_rate": 6.544921964391963e-07, "loss": 1.289, "step": 216130 }, { "epoch": 9.87, "learning_rate": 6.522037621859124e-07, "loss": 1.2108, "step": 216140 }, { "epoch": 9.87, "learning_rate": 6.499153279326285e-07, "loss": 1.2499, "step": 216150 }, { "epoch": 9.87, "learning_rate": 6.476268936793447e-07, "loss": 1.2485, "step": 216160 }, { "epoch": 9.87, "learning_rate": 6.453384594260608e-07, "loss": 1.2112, "step": 216170 }, { "epoch": 9.87, "learning_rate": 6.430500251727767e-07, "loss": 1.3104, "step": 216180 }, { "epoch": 9.87, "learning_rate": 6.407615909194929e-07, "loss": 1.3937, "step": 216190 }, { "epoch": 9.87, "learning_rate": 6.38473156666209e-07, "loss": 1.3291, "step": 216200 }, { "epoch": 9.87, "learning_rate": 6.361847224129252e-07, "loss": 1.3507, "step": 216210 }, { "epoch": 9.87, "learning_rate": 6.338962881596412e-07, "loss": 1.3013, "step": 216220 }, { "epoch": 9.87, "learning_rate": 6.316078539063573e-07, "loss": 1.3366, "step": 216230 }, { "epoch": 9.87, "learning_rate": 6.293194196530734e-07, "loss": 1.2412, "step": 216240 }, { "epoch": 9.87, "learning_rate": 6.270309853997895e-07, "loss": 1.3098, "step": 216250 }, { "epoch": 9.87, "learning_rate": 6.247425511465056e-07, "loss": 1.3575, "step": 216260 }, { "epoch": 9.88, "learning_rate": 6.224541168932216e-07, "loss": 1.352, "step": 216270 }, { "epoch": 9.88, "learning_rate": 6.201656826399378e-07, "loss": 1.3068, "step": 216280 }, { "epoch": 9.88, "learning_rate": 6.178772483866539e-07, "loss": 1.332, "step": 216290 }, { "epoch": 9.88, "learning_rate": 6.1558881413337e-07, "loss": 1.4524, "step": 216300 }, { "epoch": 9.88, "learning_rate": 6.133003798800861e-07, "loss": 1.34, "step": 216310 }, { "epoch": 9.88, "learning_rate": 6.110119456268021e-07, "loss": 1.3068, "step": 216320 }, { "epoch": 9.88, "learning_rate": 6.087235113735183e-07, "loss": 1.3627, "step": 216330 }, { "epoch": 9.88, "learning_rate": 6.064350771202344e-07, "loss": 1.3352, "step": 216340 }, { "epoch": 9.88, "learning_rate": 6.041466428669505e-07, "loss": 1.356, "step": 216350 }, { "epoch": 9.88, "learning_rate": 6.018582086136665e-07, "loss": 1.5617, "step": 216360 }, { "epoch": 9.88, "learning_rate": 5.995697743603827e-07, "loss": 1.411, "step": 216370 }, { "epoch": 9.88, "learning_rate": 5.972813401070988e-07, "loss": 1.4237, "step": 216380 }, { "epoch": 9.88, "learning_rate": 5.949929058538148e-07, "loss": 1.359, "step": 216390 }, { "epoch": 9.88, "learning_rate": 5.92704471600531e-07, "loss": 1.2685, "step": 216400 }, { "epoch": 9.88, "learning_rate": 5.90416037347247e-07, "loss": 1.2532, "step": 216410 }, { "epoch": 9.88, "learning_rate": 5.881276030939632e-07, "loss": 1.2662, "step": 216420 }, { "epoch": 9.88, "learning_rate": 5.858391688406792e-07, "loss": 1.5089, "step": 216430 }, { "epoch": 9.88, "learning_rate": 5.835507345873953e-07, "loss": 1.2456, "step": 216440 }, { "epoch": 9.88, "learning_rate": 5.812623003341114e-07, "loss": 1.368, "step": 216450 }, { "epoch": 9.88, "learning_rate": 5.789738660808275e-07, "loss": 1.3556, "step": 216460 }, { "epoch": 9.88, "learning_rate": 5.766854318275436e-07, "loss": 1.3276, "step": 216470 }, { "epoch": 9.89, "learning_rate": 5.743969975742597e-07, "loss": 1.2666, "step": 216480 }, { "epoch": 9.89, "learning_rate": 5.721085633209759e-07, "loss": 1.259, "step": 216490 }, { "epoch": 9.89, "learning_rate": 5.698201290676919e-07, "loss": 1.3856, "step": 216500 }, { "epoch": 9.89, "learning_rate": 5.675316948144079e-07, "loss": 1.3228, "step": 216510 }, { "epoch": 9.89, "learning_rate": 5.652432605611241e-07, "loss": 1.437, "step": 216520 }, { "epoch": 9.89, "learning_rate": 5.629548263078402e-07, "loss": 1.2371, "step": 216530 }, { "epoch": 9.89, "learning_rate": 5.606663920545563e-07, "loss": 1.5041, "step": 216540 }, { "epoch": 9.89, "learning_rate": 5.583779578012723e-07, "loss": 1.5138, "step": 216550 }, { "epoch": 9.89, "learning_rate": 5.560895235479885e-07, "loss": 1.4024, "step": 216560 }, { "epoch": 9.89, "learning_rate": 5.538010892947046e-07, "loss": 1.3203, "step": 216570 }, { "epoch": 9.89, "learning_rate": 5.515126550414207e-07, "loss": 1.3475, "step": 216580 }, { "epoch": 9.89, "learning_rate": 5.492242207881368e-07, "loss": 1.2051, "step": 216590 }, { "epoch": 9.89, "learning_rate": 5.469357865348528e-07, "loss": 1.2932, "step": 216600 }, { "epoch": 9.89, "learning_rate": 5.44647352281569e-07, "loss": 1.3558, "step": 216610 }, { "epoch": 9.89, "learning_rate": 5.423589180282851e-07, "loss": 1.4041, "step": 216620 }, { "epoch": 9.89, "learning_rate": 5.400704837750012e-07, "loss": 1.2053, "step": 216630 }, { "epoch": 9.89, "learning_rate": 5.377820495217172e-07, "loss": 1.4731, "step": 216640 }, { "epoch": 9.89, "learning_rate": 5.354936152684333e-07, "loss": 1.354, "step": 216650 }, { "epoch": 9.89, "learning_rate": 5.332051810151495e-07, "loss": 1.4597, "step": 216660 }, { "epoch": 9.89, "learning_rate": 5.309167467618656e-07, "loss": 1.288, "step": 216670 }, { "epoch": 9.89, "learning_rate": 5.286283125085817e-07, "loss": 1.3702, "step": 216680 }, { "epoch": 9.89, "learning_rate": 5.263398782552977e-07, "loss": 1.3, "step": 216690 }, { "epoch": 9.9, "learning_rate": 5.240514440020139e-07, "loss": 1.3968, "step": 216700 }, { "epoch": 9.9, "learning_rate": 5.2176300974873e-07, "loss": 1.3734, "step": 216710 }, { "epoch": 9.9, "learning_rate": 5.19474575495446e-07, "loss": 1.2094, "step": 216720 }, { "epoch": 9.9, "learning_rate": 5.171861412421621e-07, "loss": 1.3911, "step": 216730 }, { "epoch": 9.9, "learning_rate": 5.148977069888782e-07, "loss": 1.4151, "step": 216740 }, { "epoch": 9.9, "learning_rate": 5.126092727355944e-07, "loss": 1.348, "step": 216750 }, { "epoch": 9.9, "learning_rate": 5.103208384823104e-07, "loss": 1.3322, "step": 216760 }, { "epoch": 9.9, "learning_rate": 5.080324042290266e-07, "loss": 1.4362, "step": 216770 }, { "epoch": 9.9, "learning_rate": 5.057439699757426e-07, "loss": 1.2888, "step": 216780 }, { "epoch": 9.9, "learning_rate": 5.034555357224587e-07, "loss": 1.2002, "step": 216790 }, { "epoch": 9.9, "learning_rate": 5.011671014691748e-07, "loss": 1.4023, "step": 216800 }, { "epoch": 9.9, "learning_rate": 4.988786672158909e-07, "loss": 1.2928, "step": 216810 }, { "epoch": 9.9, "learning_rate": 4.96590232962607e-07, "loss": 1.3548, "step": 216820 }, { "epoch": 9.9, "learning_rate": 4.943017987093231e-07, "loss": 1.3988, "step": 216830 }, { "epoch": 9.9, "learning_rate": 4.920133644560393e-07, "loss": 1.3413, "step": 216840 }, { "epoch": 9.9, "learning_rate": 4.897249302027553e-07, "loss": 1.1909, "step": 216850 }, { "epoch": 9.9, "learning_rate": 4.874364959494714e-07, "loss": 1.2609, "step": 216860 }, { "epoch": 9.9, "learning_rate": 4.851480616961875e-07, "loss": 1.2437, "step": 216870 }, { "epoch": 9.9, "learning_rate": 4.828596274429036e-07, "loss": 1.389, "step": 216880 }, { "epoch": 9.9, "learning_rate": 4.805711931896197e-07, "loss": 1.3858, "step": 216890 }, { "epoch": 9.9, "learning_rate": 4.782827589363358e-07, "loss": 1.1977, "step": 216900 }, { "epoch": 9.9, "learning_rate": 4.759943246830519e-07, "loss": 1.2751, "step": 216910 }, { "epoch": 9.91, "learning_rate": 4.73705890429768e-07, "loss": 1.1464, "step": 216920 }, { "epoch": 9.91, "learning_rate": 4.7141745617648403e-07, "loss": 1.3215, "step": 216930 }, { "epoch": 9.91, "learning_rate": 4.691290219232002e-07, "loss": 1.3044, "step": 216940 }, { "epoch": 9.91, "learning_rate": 4.6684058766991627e-07, "loss": 1.3765, "step": 216950 }, { "epoch": 9.91, "learning_rate": 4.645521534166324e-07, "loss": 1.4579, "step": 216960 }, { "epoch": 9.91, "learning_rate": 4.622637191633484e-07, "loss": 1.3579, "step": 216970 }, { "epoch": 9.91, "learning_rate": 4.5997528491006455e-07, "loss": 1.3696, "step": 216980 }, { "epoch": 9.91, "learning_rate": 4.5768685065678064e-07, "loss": 1.2456, "step": 216990 }, { "epoch": 9.91, "learning_rate": 4.553984164034968e-07, "loss": 1.2083, "step": 217000 }, { "epoch": 9.91, "learning_rate": 4.531099821502128e-07, "loss": 1.2833, "step": 217010 }, { "epoch": 9.91, "learning_rate": 4.508215478969289e-07, "loss": 1.2457, "step": 217020 }, { "epoch": 9.91, "learning_rate": 4.4853311364364506e-07, "loss": 1.3643, "step": 217030 }, { "epoch": 9.91, "learning_rate": 4.4624467939036115e-07, "loss": 1.2917, "step": 217040 }, { "epoch": 9.91, "learning_rate": 4.439562451370772e-07, "loss": 1.2998, "step": 217050 }, { "epoch": 9.91, "learning_rate": 4.416678108837933e-07, "loss": 1.4353, "step": 217060 }, { "epoch": 9.91, "learning_rate": 4.3937937663050943e-07, "loss": 1.4313, "step": 217070 }, { "epoch": 9.91, "learning_rate": 4.370909423772255e-07, "loss": 1.3001, "step": 217080 }, { "epoch": 9.91, "learning_rate": 4.3480250812394167e-07, "loss": 1.3249, "step": 217090 }, { "epoch": 9.91, "learning_rate": 4.325140738706577e-07, "loss": 1.3293, "step": 217100 }, { "epoch": 9.91, "learning_rate": 4.302256396173738e-07, "loss": 1.3855, "step": 217110 }, { "epoch": 9.91, "learning_rate": 4.2793720536408994e-07, "loss": 1.2884, "step": 217120 }, { "epoch": 9.91, "learning_rate": 4.2564877111080604e-07, "loss": 1.2685, "step": 217130 }, { "epoch": 9.92, "learning_rate": 4.233603368575221e-07, "loss": 1.1986, "step": 217140 }, { "epoch": 9.92, "learning_rate": 4.2107190260423817e-07, "loss": 1.1588, "step": 217150 }, { "epoch": 9.92, "learning_rate": 4.187834683509543e-07, "loss": 1.276, "step": 217160 }, { "epoch": 9.92, "learning_rate": 4.164950340976704e-07, "loss": 1.4479, "step": 217170 }, { "epoch": 9.92, "learning_rate": 4.1420659984438644e-07, "loss": 1.2266, "step": 217180 }, { "epoch": 9.92, "learning_rate": 4.119181655911026e-07, "loss": 1.2718, "step": 217190 }, { "epoch": 9.92, "learning_rate": 4.096297313378187e-07, "loss": 1.4262, "step": 217200 }, { "epoch": 9.92, "learning_rate": 4.0734129708453483e-07, "loss": 1.1781, "step": 217210 }, { "epoch": 9.92, "learning_rate": 4.0505286283125087e-07, "loss": 1.4062, "step": 217220 }, { "epoch": 9.92, "learning_rate": 4.0276442857796696e-07, "loss": 1.387, "step": 217230 }, { "epoch": 9.92, "learning_rate": 4.0047599432468305e-07, "loss": 1.3109, "step": 217240 }, { "epoch": 9.92, "learning_rate": 3.981875600713992e-07, "loss": 1.2906, "step": 217250 }, { "epoch": 9.92, "learning_rate": 3.9589912581811524e-07, "loss": 1.3393, "step": 217260 }, { "epoch": 9.92, "learning_rate": 3.9361069156483133e-07, "loss": 1.3706, "step": 217270 }, { "epoch": 9.92, "learning_rate": 3.913222573115475e-07, "loss": 1.4982, "step": 217280 }, { "epoch": 9.92, "learning_rate": 3.890338230582635e-07, "loss": 1.2929, "step": 217290 }, { "epoch": 9.92, "learning_rate": 3.8674538880497966e-07, "loss": 1.2888, "step": 217300 }, { "epoch": 9.92, "learning_rate": 3.8445695455169575e-07, "loss": 1.4618, "step": 217310 }, { "epoch": 9.92, "learning_rate": 3.8216852029841184e-07, "loss": 1.3079, "step": 217320 }, { "epoch": 9.92, "learning_rate": 3.7988008604512794e-07, "loss": 1.183, "step": 217330 }, { "epoch": 9.92, "learning_rate": 3.7759165179184403e-07, "loss": 1.4094, "step": 217340 }, { "epoch": 9.92, "learning_rate": 3.7530321753856017e-07, "loss": 1.4192, "step": 217350 }, { "epoch": 9.93, "learning_rate": 3.730147832852762e-07, "loss": 1.3975, "step": 217360 }, { "epoch": 9.93, "learning_rate": 3.7072634903199236e-07, "loss": 1.3939, "step": 217370 }, { "epoch": 9.93, "learning_rate": 3.684379147787084e-07, "loss": 1.2328, "step": 217380 }, { "epoch": 9.93, "learning_rate": 3.6614948052542454e-07, "loss": 1.2773, "step": 217390 }, { "epoch": 9.93, "learning_rate": 3.6386104627214063e-07, "loss": 1.3448, "step": 217400 }, { "epoch": 9.93, "learning_rate": 3.6157261201885673e-07, "loss": 1.3003, "step": 217410 }, { "epoch": 9.93, "learning_rate": 3.592841777655728e-07, "loss": 1.2982, "step": 217420 }, { "epoch": 9.93, "learning_rate": 3.569957435122889e-07, "loss": 1.3229, "step": 217430 }, { "epoch": 9.93, "learning_rate": 3.54707309259005e-07, "loss": 1.2598, "step": 217440 }, { "epoch": 9.93, "learning_rate": 3.524188750057211e-07, "loss": 1.4244, "step": 217450 }, { "epoch": 9.93, "learning_rate": 3.501304407524372e-07, "loss": 1.386, "step": 217460 }, { "epoch": 9.93, "learning_rate": 3.478420064991533e-07, "loss": 1.3076, "step": 217470 }, { "epoch": 9.93, "learning_rate": 3.4555357224586937e-07, "loss": 1.4765, "step": 217480 }, { "epoch": 9.93, "learning_rate": 3.432651379925855e-07, "loss": 1.4153, "step": 217490 }, { "epoch": 9.93, "learning_rate": 3.4097670373930156e-07, "loss": 1.369, "step": 217500 }, { "epoch": 9.93, "learning_rate": 3.386882694860177e-07, "loss": 1.3116, "step": 217510 }, { "epoch": 9.93, "learning_rate": 3.3639983523273374e-07, "loss": 1.1343, "step": 217520 }, { "epoch": 9.93, "learning_rate": 3.341114009794499e-07, "loss": 1.1701, "step": 217530 }, { "epoch": 9.93, "learning_rate": 3.31822966726166e-07, "loss": 1.392, "step": 217540 }, { "epoch": 9.93, "learning_rate": 3.2953453247288207e-07, "loss": 1.3127, "step": 217550 }, { "epoch": 9.93, "learning_rate": 3.2724609821959816e-07, "loss": 1.3881, "step": 217560 }, { "epoch": 9.93, "learning_rate": 3.2495766396631426e-07, "loss": 1.1024, "step": 217570 }, { "epoch": 9.94, "learning_rate": 3.226692297130304e-07, "loss": 1.2895, "step": 217580 }, { "epoch": 9.94, "learning_rate": 3.2038079545974644e-07, "loss": 1.4223, "step": 217590 }, { "epoch": 9.94, "learning_rate": 3.180923612064626e-07, "loss": 1.3849, "step": 217600 }, { "epoch": 9.94, "learning_rate": 3.158039269531786e-07, "loss": 1.2628, "step": 217610 }, { "epoch": 9.94, "learning_rate": 3.1351549269989477e-07, "loss": 1.3787, "step": 217620 }, { "epoch": 9.94, "learning_rate": 3.112270584466108e-07, "loss": 1.2839, "step": 217630 }, { "epoch": 9.94, "learning_rate": 3.0893862419332696e-07, "loss": 1.4002, "step": 217640 }, { "epoch": 9.94, "learning_rate": 3.0665018994004305e-07, "loss": 1.2063, "step": 217650 }, { "epoch": 9.94, "learning_rate": 3.0436175568675914e-07, "loss": 1.5341, "step": 217660 }, { "epoch": 9.94, "learning_rate": 3.0207332143347523e-07, "loss": 1.3912, "step": 217670 }, { "epoch": 9.94, "learning_rate": 2.997848871801913e-07, "loss": 1.3087, "step": 217680 }, { "epoch": 9.94, "learning_rate": 2.974964529269074e-07, "loss": 1.3493, "step": 217690 }, { "epoch": 9.94, "learning_rate": 2.952080186736235e-07, "loss": 1.2316, "step": 217700 }, { "epoch": 9.94, "learning_rate": 2.929195844203396e-07, "loss": 1.4708, "step": 217710 }, { "epoch": 9.94, "learning_rate": 2.906311501670557e-07, "loss": 1.5006, "step": 217720 }, { "epoch": 9.94, "learning_rate": 2.883427159137718e-07, "loss": 1.3773, "step": 217730 }, { "epoch": 9.94, "learning_rate": 2.8605428166048793e-07, "loss": 1.398, "step": 217740 }, { "epoch": 9.94, "learning_rate": 2.8376584740720397e-07, "loss": 1.2866, "step": 217750 }, { "epoch": 9.94, "learning_rate": 2.814774131539201e-07, "loss": 1.3801, "step": 217760 }, { "epoch": 9.94, "learning_rate": 2.7918897890063616e-07, "loss": 1.2754, "step": 217770 }, { "epoch": 9.94, "learning_rate": 2.769005446473523e-07, "loss": 1.3835, "step": 217780 }, { "epoch": 9.94, "learning_rate": 2.746121103940684e-07, "loss": 1.2159, "step": 217790 }, { "epoch": 9.95, "learning_rate": 2.723236761407845e-07, "loss": 1.2755, "step": 217800 }, { "epoch": 9.95, "learning_rate": 2.700352418875006e-07, "loss": 1.3865, "step": 217810 }, { "epoch": 9.95, "learning_rate": 2.6774680763421667e-07, "loss": 1.3039, "step": 217820 }, { "epoch": 9.95, "learning_rate": 2.654583733809328e-07, "loss": 1.3058, "step": 217830 }, { "epoch": 9.95, "learning_rate": 2.6316993912764885e-07, "loss": 1.3611, "step": 217840 }, { "epoch": 9.95, "learning_rate": 2.60881504874365e-07, "loss": 1.3829, "step": 217850 }, { "epoch": 9.95, "learning_rate": 2.5859307062108104e-07, "loss": 1.3397, "step": 217860 }, { "epoch": 9.95, "learning_rate": 2.563046363677972e-07, "loss": 1.4025, "step": 217870 }, { "epoch": 9.95, "learning_rate": 2.540162021145133e-07, "loss": 1.3119, "step": 217880 }, { "epoch": 9.95, "learning_rate": 2.5172776786122937e-07, "loss": 1.2394, "step": 217890 }, { "epoch": 9.95, "learning_rate": 2.4943933360794546e-07, "loss": 1.2198, "step": 217900 }, { "epoch": 9.95, "learning_rate": 2.4715089935466155e-07, "loss": 1.313, "step": 217910 }, { "epoch": 9.95, "learning_rate": 2.4486246510137765e-07, "loss": 1.283, "step": 217920 }, { "epoch": 9.95, "learning_rate": 2.4257403084809374e-07, "loss": 1.3387, "step": 217930 }, { "epoch": 9.95, "learning_rate": 2.4028559659480983e-07, "loss": 1.2936, "step": 217940 }, { "epoch": 9.95, "learning_rate": 2.3799716234152595e-07, "loss": 1.3679, "step": 217950 }, { "epoch": 9.95, "learning_rate": 2.3570872808824202e-07, "loss": 1.3349, "step": 217960 }, { "epoch": 9.95, "learning_rate": 2.3342029383495813e-07, "loss": 1.3489, "step": 217970 }, { "epoch": 9.95, "learning_rate": 2.311318595816742e-07, "loss": 1.5466, "step": 217980 }, { "epoch": 9.95, "learning_rate": 2.2884342532839032e-07, "loss": 1.6571, "step": 217990 }, { "epoch": 9.95, "learning_rate": 2.265549910751064e-07, "loss": 1.2247, "step": 218000 }, { "epoch": 9.95, "learning_rate": 2.2426655682182253e-07, "loss": 1.3651, "step": 218010 }, { "epoch": 9.96, "learning_rate": 2.219781225685386e-07, "loss": 1.4272, "step": 218020 }, { "epoch": 9.96, "learning_rate": 2.1968968831525471e-07, "loss": 1.3536, "step": 218030 }, { "epoch": 9.96, "learning_rate": 2.1740125406197083e-07, "loss": 1.2087, "step": 218040 }, { "epoch": 9.96, "learning_rate": 2.151128198086869e-07, "loss": 1.2772, "step": 218050 }, { "epoch": 9.96, "learning_rate": 2.1282438555540302e-07, "loss": 1.3081, "step": 218060 }, { "epoch": 9.96, "learning_rate": 2.1053595130211908e-07, "loss": 1.4174, "step": 218070 }, { "epoch": 9.96, "learning_rate": 2.082475170488352e-07, "loss": 1.3981, "step": 218080 }, { "epoch": 9.96, "learning_rate": 2.059590827955513e-07, "loss": 1.3411, "step": 218090 }, { "epoch": 9.96, "learning_rate": 2.0367064854226741e-07, "loss": 1.3848, "step": 218100 }, { "epoch": 9.96, "learning_rate": 2.0138221428898348e-07, "loss": 1.3996, "step": 218110 }, { "epoch": 9.96, "learning_rate": 1.990937800356996e-07, "loss": 1.3804, "step": 218120 }, { "epoch": 9.96, "learning_rate": 1.9680534578241566e-07, "loss": 1.4332, "step": 218130 }, { "epoch": 9.96, "learning_rate": 1.9451691152913176e-07, "loss": 1.2334, "step": 218140 }, { "epoch": 9.96, "learning_rate": 1.9222847727584788e-07, "loss": 1.3835, "step": 218150 }, { "epoch": 9.96, "learning_rate": 1.8994004302256397e-07, "loss": 1.2961, "step": 218160 }, { "epoch": 9.96, "learning_rate": 1.8765160876928009e-07, "loss": 1.349, "step": 218170 }, { "epoch": 9.96, "learning_rate": 1.8536317451599618e-07, "loss": 1.4274, "step": 218180 }, { "epoch": 9.96, "learning_rate": 1.8307474026271227e-07, "loss": 1.2212, "step": 218190 }, { "epoch": 9.96, "learning_rate": 1.8078630600942836e-07, "loss": 1.395, "step": 218200 }, { "epoch": 9.96, "learning_rate": 1.7849787175614446e-07, "loss": 1.2688, "step": 218210 }, { "epoch": 9.96, "learning_rate": 1.7620943750286055e-07, "loss": 1.2918, "step": 218220 }, { "epoch": 9.96, "learning_rate": 1.7392100324957664e-07, "loss": 1.3513, "step": 218230 }, { "epoch": 9.97, "learning_rate": 1.7163256899629276e-07, "loss": 1.3534, "step": 218240 }, { "epoch": 9.97, "learning_rate": 1.6934413474300885e-07, "loss": 1.314, "step": 218250 }, { "epoch": 9.97, "learning_rate": 1.6705570048972494e-07, "loss": 1.2242, "step": 218260 }, { "epoch": 9.97, "learning_rate": 1.6476726623644104e-07, "loss": 1.4687, "step": 218270 }, { "epoch": 9.97, "learning_rate": 1.6247883198315713e-07, "loss": 1.4312, "step": 218280 }, { "epoch": 9.97, "learning_rate": 1.6019039772987322e-07, "loss": 1.3576, "step": 218290 }, { "epoch": 9.97, "learning_rate": 1.579019634765893e-07, "loss": 1.4136, "step": 218300 }, { "epoch": 9.97, "learning_rate": 1.556135292233054e-07, "loss": 1.3346, "step": 218310 }, { "epoch": 9.97, "learning_rate": 1.5332509497002152e-07, "loss": 1.2868, "step": 218320 }, { "epoch": 9.97, "learning_rate": 1.5103666071673762e-07, "loss": 1.5297, "step": 218330 }, { "epoch": 9.97, "learning_rate": 1.487482264634537e-07, "loss": 1.222, "step": 218340 }, { "epoch": 9.97, "learning_rate": 1.464597922101698e-07, "loss": 1.3072, "step": 218350 }, { "epoch": 9.97, "learning_rate": 1.441713579568859e-07, "loss": 1.3943, "step": 218360 }, { "epoch": 9.97, "learning_rate": 1.4188292370360199e-07, "loss": 1.2367, "step": 218370 }, { "epoch": 9.97, "learning_rate": 1.3959448945031808e-07, "loss": 1.2912, "step": 218380 }, { "epoch": 9.97, "learning_rate": 1.373060551970342e-07, "loss": 1.2937, "step": 218390 }, { "epoch": 9.97, "learning_rate": 1.350176209437503e-07, "loss": 1.3076, "step": 218400 }, { "epoch": 9.97, "learning_rate": 1.327291866904664e-07, "loss": 1.5044, "step": 218410 }, { "epoch": 9.97, "learning_rate": 1.304407524371825e-07, "loss": 1.3826, "step": 218420 }, { "epoch": 9.97, "learning_rate": 1.281523181838986e-07, "loss": 1.4587, "step": 218430 }, { "epoch": 9.97, "learning_rate": 1.2586388393061468e-07, "loss": 1.4283, "step": 218440 }, { "epoch": 9.97, "learning_rate": 1.2357544967733078e-07, "loss": 1.3304, "step": 218450 }, { "epoch": 9.98, "learning_rate": 1.2128701542404687e-07, "loss": 1.3597, "step": 218460 }, { "epoch": 9.98, "learning_rate": 1.1899858117076297e-07, "loss": 1.2966, "step": 218470 }, { "epoch": 9.98, "learning_rate": 1.1671014691747907e-07, "loss": 1.2577, "step": 218480 }, { "epoch": 9.98, "learning_rate": 1.1442171266419516e-07, "loss": 1.2502, "step": 218490 }, { "epoch": 9.98, "learning_rate": 1.1213327841091127e-07, "loss": 1.4157, "step": 218500 }, { "epoch": 9.98, "learning_rate": 1.0984484415762736e-07, "loss": 1.4996, "step": 218510 }, { "epoch": 9.98, "learning_rate": 1.0755640990434345e-07, "loss": 1.3859, "step": 218520 }, { "epoch": 9.98, "learning_rate": 1.0526797565105954e-07, "loss": 1.4245, "step": 218530 }, { "epoch": 9.98, "learning_rate": 1.0297954139777565e-07, "loss": 1.4668, "step": 218540 }, { "epoch": 9.98, "learning_rate": 1.0069110714449174e-07, "loss": 1.3865, "step": 218550 }, { "epoch": 9.98, "learning_rate": 9.840267289120783e-08, "loss": 1.3335, "step": 218560 }, { "epoch": 9.98, "learning_rate": 9.611423863792394e-08, "loss": 1.3816, "step": 218570 }, { "epoch": 9.98, "learning_rate": 9.382580438464004e-08, "loss": 1.2087, "step": 218580 }, { "epoch": 9.98, "learning_rate": 9.153737013135614e-08, "loss": 1.2243, "step": 218590 }, { "epoch": 9.98, "learning_rate": 8.924893587807223e-08, "loss": 1.3595, "step": 218600 }, { "epoch": 9.98, "learning_rate": 8.696050162478832e-08, "loss": 1.3267, "step": 218610 }, { "epoch": 9.98, "learning_rate": 8.467206737150443e-08, "loss": 1.3234, "step": 218620 }, { "epoch": 9.98, "learning_rate": 8.238363311822052e-08, "loss": 1.4533, "step": 218630 }, { "epoch": 9.98, "learning_rate": 8.009519886493661e-08, "loss": 1.398, "step": 218640 }, { "epoch": 9.98, "learning_rate": 7.78067646116527e-08, "loss": 1.3527, "step": 218650 }, { "epoch": 9.98, "learning_rate": 7.551833035836881e-08, "loss": 1.4735, "step": 218660 }, { "epoch": 9.99, "learning_rate": 7.32298961050849e-08, "loss": 1.4981, "step": 218670 }, { "epoch": 9.99, "learning_rate": 7.094146185180099e-08, "loss": 1.2912, "step": 218680 }, { "epoch": 9.99, "learning_rate": 6.86530275985171e-08, "loss": 1.194, "step": 218690 }, { "epoch": 9.99, "learning_rate": 6.63645933452332e-08, "loss": 1.3333, "step": 218700 }, { "epoch": 9.99, "learning_rate": 6.40761590919493e-08, "loss": 1.1992, "step": 218710 }, { "epoch": 9.99, "learning_rate": 6.178772483866539e-08, "loss": 1.4796, "step": 218720 }, { "epoch": 9.99, "learning_rate": 5.949929058538149e-08, "loss": 1.4183, "step": 218730 }, { "epoch": 9.99, "learning_rate": 5.721085633209758e-08, "loss": 1.3943, "step": 218740 }, { "epoch": 9.99, "learning_rate": 5.492242207881368e-08, "loss": 1.4414, "step": 218750 }, { "epoch": 9.99, "learning_rate": 5.263398782552977e-08, "loss": 1.3736, "step": 218760 }, { "epoch": 9.99, "learning_rate": 5.034555357224587e-08, "loss": 1.2915, "step": 218770 }, { "epoch": 9.99, "learning_rate": 4.805711931896197e-08, "loss": 1.4533, "step": 218780 }, { "epoch": 9.99, "learning_rate": 4.576868506567807e-08, "loss": 1.3687, "step": 218790 }, { "epoch": 9.99, "learning_rate": 4.348025081239416e-08, "loss": 1.2602, "step": 218800 }, { "epoch": 9.99, "learning_rate": 4.119181655911026e-08, "loss": 1.4204, "step": 218810 }, { "epoch": 9.99, "learning_rate": 3.890338230582635e-08, "loss": 1.4157, "step": 218820 }, { "epoch": 9.99, "learning_rate": 3.661494805254245e-08, "loss": 1.3519, "step": 218830 }, { "epoch": 9.99, "learning_rate": 3.432651379925855e-08, "loss": 1.4174, "step": 218840 }, { "epoch": 9.99, "learning_rate": 3.203807954597465e-08, "loss": 1.3477, "step": 218850 }, { "epoch": 9.99, "learning_rate": 2.9749645292690744e-08, "loss": 1.4325, "step": 218860 }, { "epoch": 9.99, "learning_rate": 2.746121103940684e-08, "loss": 1.3643, "step": 218870 }, { "epoch": 9.99, "learning_rate": 2.5172776786122935e-08, "loss": 1.3079, "step": 218880 }, { "epoch": 10.0, "learning_rate": 2.2884342532839034e-08, "loss": 1.438, "step": 218890 }, { "epoch": 10.0, "learning_rate": 2.059590827955513e-08, "loss": 1.5561, "step": 218900 }, { "epoch": 10.0, "learning_rate": 1.8307474026271225e-08, "loss": 1.3917, "step": 218910 }, { "epoch": 10.0, "learning_rate": 1.6019039772987324e-08, "loss": 1.4687, "step": 218920 }, { "epoch": 10.0, "learning_rate": 1.373060551970342e-08, "loss": 1.2933, "step": 218930 }, { "epoch": 10.0, "learning_rate": 1.1442171266419517e-08, "loss": 1.4582, "step": 218940 }, { "epoch": 10.0, "learning_rate": 9.153737013135613e-09, "loss": 1.2995, "step": 218950 }, { "epoch": 10.0, "learning_rate": 6.86530275985171e-09, "loss": 1.3069, "step": 218960 }, { "epoch": 10.0, "learning_rate": 4.576868506567806e-09, "loss": 1.2753, "step": 218970 }, { "epoch": 10.0, "learning_rate": 2.288434253283903e-09, "loss": 1.2864, "step": 218980 }, { "epoch": 10.0, "learning_rate": 0.0, "loss": 1.4499, "step": 218990 }, { "epoch": 10.0, "eval_cer": 0.6742817251128554, "eval_em": 0.00728476821192053, "eval_f1": 0.00728476821192053, "eval_loss": 1.311140775680542, "eval_runtime": 2641.2429, "eval_samples_per_second": 4.002, "eval_steps_per_second": 2.001, "eval_wer": 0.9927152317880795, "step": 218990 } ], "max_steps": 218990, "num_train_epochs": 10, "total_flos": 2.0663904332833505e+18, "trial_name": null, "trial_params": null }