{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 6378, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.2539184952978056e-06, "loss": 1.0601, "step": 10 }, { "epoch": 0.01, "learning_rate": 2.507836990595611e-06, "loss": 1.0455, "step": 20 }, { "epoch": 0.01, "learning_rate": 3.7617554858934172e-06, "loss": 1.0159, "step": 30 }, { "epoch": 0.02, "learning_rate": 5.015673981191222e-06, "loss": 0.963, "step": 40 }, { "epoch": 0.02, "learning_rate": 6.269592476489029e-06, "loss": 0.9019, "step": 50 }, { "epoch": 0.03, "learning_rate": 7.5235109717868345e-06, "loss": 0.831, "step": 60 }, { "epoch": 0.03, "learning_rate": 8.777429467084641e-06, "loss": 0.7665, "step": 70 }, { "epoch": 0.04, "learning_rate": 1.0031347962382445e-05, "loss": 0.7084, "step": 80 }, { "epoch": 0.04, "learning_rate": 1.128526645768025e-05, "loss": 0.6364, "step": 90 }, { "epoch": 0.05, "learning_rate": 1.2539184952978058e-05, "loss": 0.5778, "step": 100 }, { "epoch": 0.05, "learning_rate": 1.3793103448275863e-05, "loss": 0.5097, "step": 110 }, { "epoch": 0.06, "learning_rate": 1.5047021943573669e-05, "loss": 0.4675, "step": 120 }, { "epoch": 0.06, "learning_rate": 1.6300940438871475e-05, "loss": 0.4494, "step": 130 }, { "epoch": 0.07, "learning_rate": 1.7554858934169282e-05, "loss": 0.4069, "step": 140 }, { "epoch": 0.07, "learning_rate": 1.8808777429467086e-05, "loss": 0.3972, "step": 150 }, { "epoch": 0.08, "learning_rate": 2.006269592476489e-05, "loss": 0.4064, "step": 160 }, { "epoch": 0.08, "learning_rate": 2.1316614420062697e-05, "loss": 0.4002, "step": 170 }, { "epoch": 0.08, "learning_rate": 2.25705329153605e-05, "loss": 0.3856, "step": 180 }, { "epoch": 0.09, "learning_rate": 2.3824451410658308e-05, "loss": 0.3752, "step": 190 }, { "epoch": 0.09, "learning_rate": 2.5078369905956115e-05, "loss": 0.3671, "step": 200 }, { "epoch": 0.1, "learning_rate": 2.633228840125392e-05, "loss": 0.3796, "step": 210 }, { "epoch": 0.1, "learning_rate": 2.7586206896551727e-05, "loss": 0.3652, "step": 220 }, { "epoch": 0.11, "learning_rate": 2.884012539184953e-05, "loss": 0.3939, "step": 230 }, { "epoch": 0.11, "learning_rate": 3.0094043887147338e-05, "loss": 0.3758, "step": 240 }, { "epoch": 0.12, "learning_rate": 3.134796238244514e-05, "loss": 0.3477, "step": 250 }, { "epoch": 0.12, "learning_rate": 3.260188087774295e-05, "loss": 0.3442, "step": 260 }, { "epoch": 0.13, "learning_rate": 3.3855799373040756e-05, "loss": 0.3716, "step": 270 }, { "epoch": 0.13, "learning_rate": 3.5109717868338564e-05, "loss": 0.3645, "step": 280 }, { "epoch": 0.14, "learning_rate": 3.6363636363636364e-05, "loss": 0.3538, "step": 290 }, { "epoch": 0.14, "learning_rate": 3.761755485893417e-05, "loss": 0.3524, "step": 300 }, { "epoch": 0.15, "learning_rate": 3.887147335423198e-05, "loss": 0.3441, "step": 310 }, { "epoch": 0.15, "learning_rate": 4.012539184952978e-05, "loss": 0.3129, "step": 320 }, { "epoch": 0.16, "learning_rate": 4.137931034482759e-05, "loss": 0.3202, "step": 330 }, { "epoch": 0.16, "learning_rate": 4.2633228840125394e-05, "loss": 0.3083, "step": 340 }, { "epoch": 0.16, "learning_rate": 4.38871473354232e-05, "loss": 0.2806, "step": 350 }, { "epoch": 0.17, "learning_rate": 4.5141065830721e-05, "loss": 0.2865, "step": 360 }, { "epoch": 0.17, "learning_rate": 4.6394984326018816e-05, "loss": 0.2586, "step": 370 }, { "epoch": 0.18, "learning_rate": 4.7648902821316616e-05, "loss": 0.2412, "step": 380 }, { "epoch": 0.18, "learning_rate": 4.8902821316614424e-05, "loss": 0.2522, "step": 390 }, { "epoch": 0.19, "learning_rate": 5.015673981191223e-05, "loss": 0.2669, "step": 400 }, { "epoch": 0.19, "learning_rate": 5.141065830721004e-05, "loss": 0.2449, "step": 410 }, { "epoch": 0.2, "learning_rate": 5.266457680250784e-05, "loss": 0.2392, "step": 420 }, { "epoch": 0.2, "learning_rate": 5.3918495297805646e-05, "loss": 0.2098, "step": 430 }, { "epoch": 0.21, "learning_rate": 5.517241379310345e-05, "loss": 0.2248, "step": 440 }, { "epoch": 0.21, "learning_rate": 5.642633228840126e-05, "loss": 0.212, "step": 450 }, { "epoch": 0.22, "learning_rate": 5.768025078369906e-05, "loss": 0.1946, "step": 460 }, { "epoch": 0.22, "learning_rate": 5.893416927899687e-05, "loss": 0.2016, "step": 470 }, { "epoch": 0.23, "learning_rate": 6.0188087774294676e-05, "loss": 0.196, "step": 480 }, { "epoch": 0.23, "learning_rate": 6.144200626959248e-05, "loss": 0.1712, "step": 490 }, { "epoch": 0.24, "learning_rate": 6.269592476489028e-05, "loss": 0.1704, "step": 500 }, { "epoch": 0.24, "learning_rate": 6.394984326018808e-05, "loss": 0.1677, "step": 510 }, { "epoch": 0.24, "learning_rate": 6.52037617554859e-05, "loss": 0.175, "step": 520 }, { "epoch": 0.25, "learning_rate": 6.64576802507837e-05, "loss": 0.1581, "step": 530 }, { "epoch": 0.25, "learning_rate": 6.771159874608151e-05, "loss": 0.1702, "step": 540 }, { "epoch": 0.26, "learning_rate": 6.896551724137931e-05, "loss": 0.1445, "step": 550 }, { "epoch": 0.26, "learning_rate": 7.021943573667713e-05, "loss": 0.1548, "step": 560 }, { "epoch": 0.27, "learning_rate": 7.147335423197493e-05, "loss": 0.1623, "step": 570 }, { "epoch": 0.27, "learning_rate": 7.272727272727273e-05, "loss": 0.1499, "step": 580 }, { "epoch": 0.28, "learning_rate": 7.398119122257054e-05, "loss": 0.1519, "step": 590 }, { "epoch": 0.28, "learning_rate": 7.523510971786834e-05, "loss": 0.1554, "step": 600 }, { "epoch": 0.29, "learning_rate": 7.648902821316614e-05, "loss": 0.1477, "step": 610 }, { "epoch": 0.29, "learning_rate": 7.774294670846396e-05, "loss": 0.1404, "step": 620 }, { "epoch": 0.3, "learning_rate": 7.899686520376177e-05, "loss": 0.1533, "step": 630 }, { "epoch": 0.3, "learning_rate": 7.997212543554007e-05, "loss": 0.1455, "step": 640 }, { "epoch": 0.31, "learning_rate": 7.983275261324042e-05, "loss": 0.1266, "step": 650 }, { "epoch": 0.31, "learning_rate": 7.969337979094077e-05, "loss": 0.1283, "step": 660 }, { "epoch": 0.32, "learning_rate": 7.955400696864112e-05, "loss": 0.1204, "step": 670 }, { "epoch": 0.32, "learning_rate": 7.941463414634147e-05, "loss": 0.1478, "step": 680 }, { "epoch": 0.32, "learning_rate": 7.927526132404182e-05, "loss": 0.1276, "step": 690 }, { "epoch": 0.33, "learning_rate": 7.913588850174217e-05, "loss": 0.1433, "step": 700 }, { "epoch": 0.33, "learning_rate": 7.899651567944252e-05, "loss": 0.1541, "step": 710 }, { "epoch": 0.34, "learning_rate": 7.885714285714287e-05, "loss": 0.1345, "step": 720 }, { "epoch": 0.34, "learning_rate": 7.871777003484321e-05, "loss": 0.1353, "step": 730 }, { "epoch": 0.35, "learning_rate": 7.857839721254356e-05, "loss": 0.1218, "step": 740 }, { "epoch": 0.35, "learning_rate": 7.84390243902439e-05, "loss": 0.1372, "step": 750 }, { "epoch": 0.36, "learning_rate": 7.829965156794426e-05, "loss": 0.1337, "step": 760 }, { "epoch": 0.36, "learning_rate": 7.81602787456446e-05, "loss": 0.1234, "step": 770 }, { "epoch": 0.37, "learning_rate": 7.802090592334495e-05, "loss": 0.1179, "step": 780 }, { "epoch": 0.37, "learning_rate": 7.78815331010453e-05, "loss": 0.1344, "step": 790 }, { "epoch": 0.38, "learning_rate": 7.774216027874565e-05, "loss": 0.1276, "step": 800 }, { "epoch": 0.38, "learning_rate": 7.760278745644599e-05, "loss": 0.129, "step": 810 }, { "epoch": 0.39, "learning_rate": 7.746341463414634e-05, "loss": 0.1177, "step": 820 }, { "epoch": 0.39, "learning_rate": 7.732404181184669e-05, "loss": 0.1233, "step": 830 }, { "epoch": 0.4, "learning_rate": 7.718466898954704e-05, "loss": 0.1131, "step": 840 }, { "epoch": 0.4, "learning_rate": 7.704529616724739e-05, "loss": 0.1174, "step": 850 }, { "epoch": 0.4, "learning_rate": 7.690592334494774e-05, "loss": 0.1319, "step": 860 }, { "epoch": 0.41, "learning_rate": 7.676655052264809e-05, "loss": 0.1217, "step": 870 }, { "epoch": 0.41, "learning_rate": 7.662717770034844e-05, "loss": 0.1144, "step": 880 }, { "epoch": 0.42, "learning_rate": 7.648780487804879e-05, "loss": 0.1059, "step": 890 }, { "epoch": 0.42, "learning_rate": 7.634843205574914e-05, "loss": 0.1202, "step": 900 }, { "epoch": 0.43, "learning_rate": 7.620905923344949e-05, "loss": 0.115, "step": 910 }, { "epoch": 0.43, "learning_rate": 7.606968641114984e-05, "loss": 0.1205, "step": 920 }, { "epoch": 0.44, "learning_rate": 7.593031358885019e-05, "loss": 0.1219, "step": 930 }, { "epoch": 0.44, "learning_rate": 7.579094076655054e-05, "loss": 0.1091, "step": 940 }, { "epoch": 0.45, "learning_rate": 7.565156794425089e-05, "loss": 0.1224, "step": 950 }, { "epoch": 0.45, "learning_rate": 7.551219512195122e-05, "loss": 0.108, "step": 960 }, { "epoch": 0.46, "learning_rate": 7.537282229965157e-05, "loss": 0.1172, "step": 970 }, { "epoch": 0.46, "learning_rate": 7.523344947735192e-05, "loss": 0.1017, "step": 980 }, { "epoch": 0.47, "learning_rate": 7.509407665505227e-05, "loss": 0.1244, "step": 990 }, { "epoch": 0.47, "learning_rate": 7.495470383275262e-05, "loss": 0.1217, "step": 1000 }, { "epoch": 0.48, "learning_rate": 7.481533101045297e-05, "loss": 0.116, "step": 1010 }, { "epoch": 0.48, "learning_rate": 7.467595818815332e-05, "loss": 0.1201, "step": 1020 }, { "epoch": 0.48, "learning_rate": 7.453658536585367e-05, "loss": 0.1094, "step": 1030 }, { "epoch": 0.49, "learning_rate": 7.4397212543554e-05, "loss": 0.1059, "step": 1040 }, { "epoch": 0.49, "learning_rate": 7.425783972125435e-05, "loss": 0.1062, "step": 1050 }, { "epoch": 0.5, "learning_rate": 7.41184668989547e-05, "loss": 0.1293, "step": 1060 }, { "epoch": 0.5, "learning_rate": 7.397909407665505e-05, "loss": 0.1191, "step": 1070 }, { "epoch": 0.51, "learning_rate": 7.38397212543554e-05, "loss": 0.1158, "step": 1080 }, { "epoch": 0.51, "learning_rate": 7.370034843205575e-05, "loss": 0.0991, "step": 1090 }, { "epoch": 0.52, "learning_rate": 7.35609756097561e-05, "loss": 0.1206, "step": 1100 }, { "epoch": 0.52, "learning_rate": 7.342160278745645e-05, "loss": 0.1116, "step": 1110 }, { "epoch": 0.53, "learning_rate": 7.32822299651568e-05, "loss": 0.1156, "step": 1120 }, { "epoch": 0.53, "learning_rate": 7.314285714285715e-05, "loss": 0.0994, "step": 1130 }, { "epoch": 0.54, "learning_rate": 7.30034843205575e-05, "loss": 0.0977, "step": 1140 }, { "epoch": 0.54, "learning_rate": 7.286411149825785e-05, "loss": 0.1153, "step": 1150 }, { "epoch": 0.55, "learning_rate": 7.27247386759582e-05, "loss": 0.1213, "step": 1160 }, { "epoch": 0.55, "learning_rate": 7.258536585365855e-05, "loss": 0.1081, "step": 1170 }, { "epoch": 0.56, "learning_rate": 7.24459930313589e-05, "loss": 0.1084, "step": 1180 }, { "epoch": 0.56, "learning_rate": 7.230662020905924e-05, "loss": 0.1159, "step": 1190 }, { "epoch": 0.56, "learning_rate": 7.216724738675958e-05, "loss": 0.1035, "step": 1200 }, { "epoch": 0.57, "learning_rate": 7.202787456445993e-05, "loss": 0.1167, "step": 1210 }, { "epoch": 0.57, "learning_rate": 7.188850174216028e-05, "loss": 0.1108, "step": 1220 }, { "epoch": 0.58, "learning_rate": 7.174912891986063e-05, "loss": 0.1202, "step": 1230 }, { "epoch": 0.58, "learning_rate": 7.160975609756098e-05, "loss": 0.1123, "step": 1240 }, { "epoch": 0.59, "learning_rate": 7.147038327526133e-05, "loss": 0.1178, "step": 1250 }, { "epoch": 0.59, "learning_rate": 7.133101045296168e-05, "loss": 0.1063, "step": 1260 }, { "epoch": 0.6, "learning_rate": 7.119163763066202e-05, "loss": 0.1021, "step": 1270 }, { "epoch": 0.6, "learning_rate": 7.105226480836237e-05, "loss": 0.1196, "step": 1280 }, { "epoch": 0.61, "learning_rate": 7.091289198606272e-05, "loss": 0.1068, "step": 1290 }, { "epoch": 0.61, "learning_rate": 7.077351916376307e-05, "loss": 0.1068, "step": 1300 }, { "epoch": 0.62, "learning_rate": 7.063414634146342e-05, "loss": 0.1109, "step": 1310 }, { "epoch": 0.62, "learning_rate": 7.049477351916377e-05, "loss": 0.1083, "step": 1320 }, { "epoch": 0.63, "learning_rate": 7.035540069686412e-05, "loss": 0.0974, "step": 1330 }, { "epoch": 0.63, "learning_rate": 7.021602787456447e-05, "loss": 0.0968, "step": 1340 }, { "epoch": 0.63, "learning_rate": 7.007665505226482e-05, "loss": 0.0934, "step": 1350 }, { "epoch": 0.64, "learning_rate": 6.993728222996517e-05, "loss": 0.1125, "step": 1360 }, { "epoch": 0.64, "learning_rate": 6.979790940766552e-05, "loss": 0.1126, "step": 1370 }, { "epoch": 0.65, "learning_rate": 6.965853658536586e-05, "loss": 0.1135, "step": 1380 }, { "epoch": 0.65, "learning_rate": 6.951916376306621e-05, "loss": 0.1012, "step": 1390 }, { "epoch": 0.66, "learning_rate": 6.937979094076656e-05, "loss": 0.1022, "step": 1400 }, { "epoch": 0.66, "learning_rate": 6.924041811846691e-05, "loss": 0.1023, "step": 1410 }, { "epoch": 0.67, "learning_rate": 6.910104529616726e-05, "loss": 0.1067, "step": 1420 }, { "epoch": 0.67, "learning_rate": 6.89616724738676e-05, "loss": 0.1015, "step": 1430 }, { "epoch": 0.68, "learning_rate": 6.882229965156795e-05, "loss": 0.0999, "step": 1440 }, { "epoch": 0.68, "learning_rate": 6.86829268292683e-05, "loss": 0.1, "step": 1450 }, { "epoch": 0.69, "learning_rate": 6.854355400696865e-05, "loss": 0.1125, "step": 1460 }, { "epoch": 0.69, "learning_rate": 6.8404181184669e-05, "loss": 0.1164, "step": 1470 }, { "epoch": 0.7, "learning_rate": 6.826480836236935e-05, "loss": 0.1178, "step": 1480 }, { "epoch": 0.7, "learning_rate": 6.81254355400697e-05, "loss": 0.1164, "step": 1490 }, { "epoch": 0.71, "learning_rate": 6.798606271777003e-05, "loss": 0.1057, "step": 1500 }, { "epoch": 0.71, "learning_rate": 6.784668989547038e-05, "loss": 0.0992, "step": 1510 }, { "epoch": 0.71, "learning_rate": 6.770731707317073e-05, "loss": 0.1038, "step": 1520 }, { "epoch": 0.72, "learning_rate": 6.756794425087108e-05, "loss": 0.1097, "step": 1530 }, { "epoch": 0.72, "learning_rate": 6.742857142857143e-05, "loss": 0.0958, "step": 1540 }, { "epoch": 0.73, "learning_rate": 6.728919860627178e-05, "loss": 0.1193, "step": 1550 }, { "epoch": 0.73, "learning_rate": 6.714982578397213e-05, "loss": 0.101, "step": 1560 }, { "epoch": 0.74, "learning_rate": 6.701045296167248e-05, "loss": 0.103, "step": 1570 }, { "epoch": 0.74, "learning_rate": 6.687108013937283e-05, "loss": 0.1063, "step": 1580 }, { "epoch": 0.75, "learning_rate": 6.673170731707318e-05, "loss": 0.0967, "step": 1590 }, { "epoch": 0.75, "learning_rate": 6.659233449477353e-05, "loss": 0.1183, "step": 1600 }, { "epoch": 0.76, "learning_rate": 6.645296167247388e-05, "loss": 0.1011, "step": 1610 }, { "epoch": 0.76, "learning_rate": 6.631358885017423e-05, "loss": 0.099, "step": 1620 }, { "epoch": 0.77, "learning_rate": 6.617421602787458e-05, "loss": 0.0905, "step": 1630 }, { "epoch": 0.77, "learning_rate": 6.603484320557493e-05, "loss": 0.1042, "step": 1640 }, { "epoch": 0.78, "learning_rate": 6.589547038327528e-05, "loss": 0.1031, "step": 1650 }, { "epoch": 0.78, "learning_rate": 6.575609756097561e-05, "loss": 0.1081, "step": 1660 }, { "epoch": 0.79, "learning_rate": 6.561672473867596e-05, "loss": 0.0899, "step": 1670 }, { "epoch": 0.79, "learning_rate": 6.547735191637631e-05, "loss": 0.0949, "step": 1680 }, { "epoch": 0.79, "learning_rate": 6.533797909407666e-05, "loss": 0.1183, "step": 1690 }, { "epoch": 0.8, "learning_rate": 6.519860627177701e-05, "loss": 0.1002, "step": 1700 }, { "epoch": 0.8, "learning_rate": 6.505923344947736e-05, "loss": 0.1078, "step": 1710 }, { "epoch": 0.81, "learning_rate": 6.491986062717771e-05, "loss": 0.1054, "step": 1720 }, { "epoch": 0.81, "learning_rate": 6.478048780487806e-05, "loss": 0.1045, "step": 1730 }, { "epoch": 0.82, "learning_rate": 6.46411149825784e-05, "loss": 0.1085, "step": 1740 }, { "epoch": 0.82, "learning_rate": 6.450174216027875e-05, "loss": 0.0854, "step": 1750 }, { "epoch": 0.83, "learning_rate": 6.43623693379791e-05, "loss": 0.0896, "step": 1760 }, { "epoch": 0.83, "learning_rate": 6.422299651567945e-05, "loss": 0.1098, "step": 1770 }, { "epoch": 0.84, "learning_rate": 6.40836236933798e-05, "loss": 0.1076, "step": 1780 }, { "epoch": 0.84, "learning_rate": 6.394425087108015e-05, "loss": 0.0861, "step": 1790 }, { "epoch": 0.85, "learning_rate": 6.38048780487805e-05, "loss": 0.0899, "step": 1800 }, { "epoch": 0.85, "learning_rate": 6.366550522648083e-05, "loss": 0.0995, "step": 1810 }, { "epoch": 0.86, "learning_rate": 6.352613240418118e-05, "loss": 0.1151, "step": 1820 }, { "epoch": 0.86, "learning_rate": 6.338675958188153e-05, "loss": 0.0917, "step": 1830 }, { "epoch": 0.87, "learning_rate": 6.324738675958188e-05, "loss": 0.094, "step": 1840 }, { "epoch": 0.87, "learning_rate": 6.310801393728223e-05, "loss": 0.1087, "step": 1850 }, { "epoch": 0.87, "learning_rate": 6.296864111498258e-05, "loss": 0.1059, "step": 1860 }, { "epoch": 0.88, "learning_rate": 6.282926829268293e-05, "loss": 0.0987, "step": 1870 }, { "epoch": 0.88, "learning_rate": 6.268989547038328e-05, "loss": 0.0906, "step": 1880 }, { "epoch": 0.89, "learning_rate": 6.255052264808363e-05, "loss": 0.0851, "step": 1890 }, { "epoch": 0.89, "learning_rate": 6.241114982578398e-05, "loss": 0.085, "step": 1900 }, { "epoch": 0.9, "learning_rate": 6.227177700348433e-05, "loss": 0.0911, "step": 1910 }, { "epoch": 0.9, "learning_rate": 6.213240418118468e-05, "loss": 0.1078, "step": 1920 }, { "epoch": 0.91, "learning_rate": 6.199303135888503e-05, "loss": 0.1255, "step": 1930 }, { "epoch": 0.91, "learning_rate": 6.185365853658538e-05, "loss": 0.096, "step": 1940 }, { "epoch": 0.92, "learning_rate": 6.171428571428573e-05, "loss": 0.0904, "step": 1950 }, { "epoch": 0.92, "learning_rate": 6.157491289198608e-05, "loss": 0.0999, "step": 1960 }, { "epoch": 0.93, "learning_rate": 6.143554006968641e-05, "loss": 0.0913, "step": 1970 }, { "epoch": 0.93, "learning_rate": 6.129616724738676e-05, "loss": 0.107, "step": 1980 }, { "epoch": 0.94, "learning_rate": 6.115679442508711e-05, "loss": 0.1046, "step": 1990 }, { "epoch": 0.94, "learning_rate": 6.101742160278746e-05, "loss": 0.0936, "step": 2000 }, { "epoch": 0.95, "learning_rate": 6.087804878048781e-05, "loss": 0.1114, "step": 2010 }, { "epoch": 0.95, "learning_rate": 6.073867595818816e-05, "loss": 0.0906, "step": 2020 }, { "epoch": 0.95, "learning_rate": 6.059930313588851e-05, "loss": 0.1027, "step": 2030 }, { "epoch": 0.96, "learning_rate": 6.045993031358886e-05, "loss": 0.1003, "step": 2040 }, { "epoch": 0.96, "learning_rate": 6.03205574912892e-05, "loss": 0.1001, "step": 2050 }, { "epoch": 0.97, "learning_rate": 6.018118466898955e-05, "loss": 0.1068, "step": 2060 }, { "epoch": 0.97, "learning_rate": 6.00418118466899e-05, "loss": 0.0925, "step": 2070 }, { "epoch": 0.98, "learning_rate": 5.990243902439025e-05, "loss": 0.1055, "step": 2080 }, { "epoch": 0.98, "learning_rate": 5.97630662020906e-05, "loss": 0.0929, "step": 2090 }, { "epoch": 0.99, "learning_rate": 5.962369337979095e-05, "loss": 0.0992, "step": 2100 }, { "epoch": 0.99, "learning_rate": 5.94843205574913e-05, "loss": 0.1176, "step": 2110 }, { "epoch": 1.0, "learning_rate": 5.9344947735191635e-05, "loss": 0.1052, "step": 2120 }, { "epoch": 1.0, "eval_accuracy": 0.9678139629676251, "eval_f1": 0.6712645764326876, "eval_loss": 0.08540353178977966, "eval_precision": 0.6823800738007381, "eval_recall": 0.6605054022680596, "eval_runtime": 6.9434, "eval_samples_per_second": 2039.333, "eval_steps_per_second": 254.917, "step": 2126 }, { "epoch": 1.0, "learning_rate": 5.9205574912891985e-05, "loss": 0.1125, "step": 2130 }, { "epoch": 1.01, "learning_rate": 5.9066202090592335e-05, "loss": 0.1005, "step": 2140 }, { "epoch": 1.01, "learning_rate": 5.8926829268292684e-05, "loss": 0.0923, "step": 2150 }, { "epoch": 1.02, "learning_rate": 5.8787456445993034e-05, "loss": 0.0904, "step": 2160 }, { "epoch": 1.02, "learning_rate": 5.8648083623693383e-05, "loss": 0.1003, "step": 2170 }, { "epoch": 1.03, "learning_rate": 5.850871080139373e-05, "loss": 0.0753, "step": 2180 }, { "epoch": 1.03, "learning_rate": 5.836933797909408e-05, "loss": 0.0787, "step": 2190 }, { "epoch": 1.03, "learning_rate": 5.8229965156794425e-05, "loss": 0.0994, "step": 2200 }, { "epoch": 1.04, "learning_rate": 5.8090592334494775e-05, "loss": 0.0911, "step": 2210 }, { "epoch": 1.04, "learning_rate": 5.7951219512195125e-05, "loss": 0.0898, "step": 2220 }, { "epoch": 1.05, "learning_rate": 5.7811846689895474e-05, "loss": 0.0838, "step": 2230 }, { "epoch": 1.05, "learning_rate": 5.7672473867595824e-05, "loss": 0.0829, "step": 2240 }, { "epoch": 1.06, "learning_rate": 5.7533101045296174e-05, "loss": 0.0829, "step": 2250 }, { "epoch": 1.06, "learning_rate": 5.739372822299652e-05, "loss": 0.0773, "step": 2260 }, { "epoch": 1.07, "learning_rate": 5.725435540069687e-05, "loss": 0.1017, "step": 2270 }, { "epoch": 1.07, "learning_rate": 5.7114982578397216e-05, "loss": 0.0839, "step": 2280 }, { "epoch": 1.08, "learning_rate": 5.6975609756097565e-05, "loss": 0.0813, "step": 2290 }, { "epoch": 1.08, "learning_rate": 5.6836236933797915e-05, "loss": 0.0887, "step": 2300 }, { "epoch": 1.09, "learning_rate": 5.6696864111498265e-05, "loss": 0.0913, "step": 2310 }, { "epoch": 1.09, "learning_rate": 5.6557491289198614e-05, "loss": 0.0987, "step": 2320 }, { "epoch": 1.1, "learning_rate": 5.6418118466898964e-05, "loss": 0.0837, "step": 2330 }, { "epoch": 1.1, "learning_rate": 5.6278745644599313e-05, "loss": 0.0952, "step": 2340 }, { "epoch": 1.11, "learning_rate": 5.613937282229966e-05, "loss": 0.0933, "step": 2350 }, { "epoch": 1.11, "learning_rate": 5.6e-05, "loss": 0.0908, "step": 2360 }, { "epoch": 1.11, "learning_rate": 5.586062717770035e-05, "loss": 0.0826, "step": 2370 }, { "epoch": 1.12, "learning_rate": 5.57212543554007e-05, "loss": 0.1005, "step": 2380 }, { "epoch": 1.12, "learning_rate": 5.558188153310105e-05, "loss": 0.0838, "step": 2390 }, { "epoch": 1.13, "learning_rate": 5.54425087108014e-05, "loss": 0.0913, "step": 2400 }, { "epoch": 1.13, "learning_rate": 5.530313588850175e-05, "loss": 0.084, "step": 2410 }, { "epoch": 1.14, "learning_rate": 5.51637630662021e-05, "loss": 0.0885, "step": 2420 }, { "epoch": 1.14, "learning_rate": 5.502439024390244e-05, "loss": 0.1035, "step": 2430 }, { "epoch": 1.15, "learning_rate": 5.488501742160279e-05, "loss": 0.0889, "step": 2440 }, { "epoch": 1.15, "learning_rate": 5.474564459930314e-05, "loss": 0.0772, "step": 2450 }, { "epoch": 1.16, "learning_rate": 5.460627177700349e-05, "loss": 0.0865, "step": 2460 }, { "epoch": 1.16, "learning_rate": 5.446689895470384e-05, "loss": 0.0843, "step": 2470 }, { "epoch": 1.17, "learning_rate": 5.432752613240419e-05, "loss": 0.0824, "step": 2480 }, { "epoch": 1.17, "learning_rate": 5.418815331010454e-05, "loss": 0.0878, "step": 2490 }, { "epoch": 1.18, "learning_rate": 5.404878048780489e-05, "loss": 0.0878, "step": 2500 }, { "epoch": 1.18, "learning_rate": 5.390940766550523e-05, "loss": 0.0895, "step": 2510 }, { "epoch": 1.19, "learning_rate": 5.377003484320558e-05, "loss": 0.0948, "step": 2520 }, { "epoch": 1.19, "learning_rate": 5.363066202090593e-05, "loss": 0.0918, "step": 2530 }, { "epoch": 1.19, "learning_rate": 5.349128919860627e-05, "loss": 0.0995, "step": 2540 }, { "epoch": 1.2, "learning_rate": 5.335191637630662e-05, "loss": 0.083, "step": 2550 }, { "epoch": 1.2, "learning_rate": 5.321254355400697e-05, "loss": 0.0798, "step": 2560 }, { "epoch": 1.21, "learning_rate": 5.307317073170732e-05, "loss": 0.0956, "step": 2570 }, { "epoch": 1.21, "learning_rate": 5.293379790940767e-05, "loss": 0.0911, "step": 2580 }, { "epoch": 1.22, "learning_rate": 5.2794425087108013e-05, "loss": 0.0846, "step": 2590 }, { "epoch": 1.22, "learning_rate": 5.265505226480836e-05, "loss": 0.0848, "step": 2600 }, { "epoch": 1.23, "learning_rate": 5.251567944250871e-05, "loss": 0.0797, "step": 2610 }, { "epoch": 1.23, "learning_rate": 5.237630662020906e-05, "loss": 0.0871, "step": 2620 }, { "epoch": 1.24, "learning_rate": 5.223693379790941e-05, "loss": 0.0859, "step": 2630 }, { "epoch": 1.24, "learning_rate": 5.209756097560976e-05, "loss": 0.0844, "step": 2640 }, { "epoch": 1.25, "learning_rate": 5.195818815331011e-05, "loss": 0.0866, "step": 2650 }, { "epoch": 1.25, "learning_rate": 5.181881533101046e-05, "loss": 0.0952, "step": 2660 }, { "epoch": 1.26, "learning_rate": 5.1679442508710804e-05, "loss": 0.0774, "step": 2670 }, { "epoch": 1.26, "learning_rate": 5.154006968641115e-05, "loss": 0.0763, "step": 2680 }, { "epoch": 1.27, "learning_rate": 5.14006968641115e-05, "loss": 0.0859, "step": 2690 }, { "epoch": 1.27, "learning_rate": 5.126132404181185e-05, "loss": 0.0925, "step": 2700 }, { "epoch": 1.27, "learning_rate": 5.11219512195122e-05, "loss": 0.0885, "step": 2710 }, { "epoch": 1.28, "learning_rate": 5.098257839721255e-05, "loss": 0.0953, "step": 2720 }, { "epoch": 1.28, "learning_rate": 5.08432055749129e-05, "loss": 0.0972, "step": 2730 }, { "epoch": 1.29, "learning_rate": 5.070383275261325e-05, "loss": 0.091, "step": 2740 }, { "epoch": 1.29, "learning_rate": 5.056445993031359e-05, "loss": 0.0685, "step": 2750 }, { "epoch": 1.3, "learning_rate": 5.042508710801394e-05, "loss": 0.0815, "step": 2760 }, { "epoch": 1.3, "learning_rate": 5.0285714285714286e-05, "loss": 0.0955, "step": 2770 }, { "epoch": 1.31, "learning_rate": 5.0146341463414636e-05, "loss": 0.0873, "step": 2780 }, { "epoch": 1.31, "learning_rate": 5.0006968641114986e-05, "loss": 0.0834, "step": 2790 }, { "epoch": 1.32, "learning_rate": 4.9867595818815335e-05, "loss": 0.1004, "step": 2800 }, { "epoch": 1.32, "learning_rate": 4.9728222996515685e-05, "loss": 0.0941, "step": 2810 }, { "epoch": 1.33, "learning_rate": 4.958885017421603e-05, "loss": 0.0879, "step": 2820 }, { "epoch": 1.33, "learning_rate": 4.944947735191638e-05, "loss": 0.0829, "step": 2830 }, { "epoch": 1.34, "learning_rate": 4.931010452961673e-05, "loss": 0.0854, "step": 2840 }, { "epoch": 1.34, "learning_rate": 4.9170731707317077e-05, "loss": 0.0835, "step": 2850 }, { "epoch": 1.35, "learning_rate": 4.9031358885017426e-05, "loss": 0.0855, "step": 2860 }, { "epoch": 1.35, "learning_rate": 4.8891986062717776e-05, "loss": 0.0981, "step": 2870 }, { "epoch": 1.35, "learning_rate": 4.8752613240418125e-05, "loss": 0.0856, "step": 2880 }, { "epoch": 1.36, "learning_rate": 4.8613240418118475e-05, "loss": 0.08, "step": 2890 }, { "epoch": 1.36, "learning_rate": 4.847386759581882e-05, "loss": 0.0806, "step": 2900 }, { "epoch": 1.37, "learning_rate": 4.833449477351917e-05, "loss": 0.0842, "step": 2910 }, { "epoch": 1.37, "learning_rate": 4.819512195121952e-05, "loss": 0.0982, "step": 2920 }, { "epoch": 1.38, "learning_rate": 4.805574912891987e-05, "loss": 0.093, "step": 2930 }, { "epoch": 1.38, "learning_rate": 4.7916376306620216e-05, "loss": 0.0738, "step": 2940 }, { "epoch": 1.39, "learning_rate": 4.7777003484320566e-05, "loss": 0.097, "step": 2950 }, { "epoch": 1.39, "learning_rate": 4.7637630662020916e-05, "loss": 0.0847, "step": 2960 }, { "epoch": 1.4, "learning_rate": 4.7498257839721265e-05, "loss": 0.0895, "step": 2970 }, { "epoch": 1.4, "learning_rate": 4.73588850174216e-05, "loss": 0.0951, "step": 2980 }, { "epoch": 1.41, "learning_rate": 4.721951219512195e-05, "loss": 0.0917, "step": 2990 }, { "epoch": 1.41, "learning_rate": 4.70801393728223e-05, "loss": 0.0949, "step": 3000 }, { "epoch": 1.42, "learning_rate": 4.694076655052265e-05, "loss": 0.0957, "step": 3010 }, { "epoch": 1.42, "learning_rate": 4.6801393728223e-05, "loss": 0.0798, "step": 3020 }, { "epoch": 1.43, "learning_rate": 4.666202090592335e-05, "loss": 0.0859, "step": 3030 }, { "epoch": 1.43, "learning_rate": 4.65226480836237e-05, "loss": 0.0974, "step": 3040 }, { "epoch": 1.43, "learning_rate": 4.638327526132405e-05, "loss": 0.088, "step": 3050 }, { "epoch": 1.44, "learning_rate": 4.624390243902439e-05, "loss": 0.0845, "step": 3060 }, { "epoch": 1.44, "learning_rate": 4.610452961672474e-05, "loss": 0.0749, "step": 3070 }, { "epoch": 1.45, "learning_rate": 4.596515679442509e-05, "loss": 0.0909, "step": 3080 }, { "epoch": 1.45, "learning_rate": 4.582578397212544e-05, "loss": 0.0863, "step": 3090 }, { "epoch": 1.46, "learning_rate": 4.568641114982579e-05, "loss": 0.0823, "step": 3100 }, { "epoch": 1.46, "learning_rate": 4.554703832752614e-05, "loss": 0.0833, "step": 3110 }, { "epoch": 1.47, "learning_rate": 4.540766550522649e-05, "loss": 0.0883, "step": 3120 }, { "epoch": 1.47, "learning_rate": 4.5268292682926825e-05, "loss": 0.0694, "step": 3130 }, { "epoch": 1.48, "learning_rate": 4.5128919860627175e-05, "loss": 0.0869, "step": 3140 }, { "epoch": 1.48, "learning_rate": 4.4989547038327525e-05, "loss": 0.0883, "step": 3150 }, { "epoch": 1.49, "learning_rate": 4.4850174216027874e-05, "loss": 0.0905, "step": 3160 }, { "epoch": 1.49, "learning_rate": 4.4710801393728224e-05, "loss": 0.0965, "step": 3170 }, { "epoch": 1.5, "learning_rate": 4.4571428571428574e-05, "loss": 0.0797, "step": 3180 }, { "epoch": 1.5, "learning_rate": 4.443205574912892e-05, "loss": 0.0711, "step": 3190 }, { "epoch": 1.51, "learning_rate": 4.429268292682927e-05, "loss": 0.0805, "step": 3200 }, { "epoch": 1.51, "learning_rate": 4.4153310104529616e-05, "loss": 0.0825, "step": 3210 }, { "epoch": 1.51, "learning_rate": 4.4013937282229965e-05, "loss": 0.0891, "step": 3220 }, { "epoch": 1.52, "learning_rate": 4.3874564459930315e-05, "loss": 0.0846, "step": 3230 }, { "epoch": 1.52, "learning_rate": 4.3735191637630664e-05, "loss": 0.0915, "step": 3240 }, { "epoch": 1.53, "learning_rate": 4.3595818815331014e-05, "loss": 0.082, "step": 3250 }, { "epoch": 1.53, "learning_rate": 4.3456445993031364e-05, "loss": 0.0834, "step": 3260 }, { "epoch": 1.54, "learning_rate": 4.331707317073171e-05, "loss": 0.0814, "step": 3270 }, { "epoch": 1.54, "learning_rate": 4.317770034843206e-05, "loss": 0.0811, "step": 3280 }, { "epoch": 1.55, "learning_rate": 4.3038327526132406e-05, "loss": 0.0823, "step": 3290 }, { "epoch": 1.55, "learning_rate": 4.2898954703832755e-05, "loss": 0.0823, "step": 3300 }, { "epoch": 1.56, "learning_rate": 4.2759581881533105e-05, "loss": 0.0836, "step": 3310 }, { "epoch": 1.56, "learning_rate": 4.2620209059233455e-05, "loss": 0.0855, "step": 3320 }, { "epoch": 1.57, "learning_rate": 4.2480836236933804e-05, "loss": 0.0907, "step": 3330 }, { "epoch": 1.57, "learning_rate": 4.2341463414634154e-05, "loss": 0.0866, "step": 3340 }, { "epoch": 1.58, "learning_rate": 4.2202090592334504e-05, "loss": 0.1045, "step": 3350 }, { "epoch": 1.58, "learning_rate": 4.206271777003485e-05, "loss": 0.0781, "step": 3360 }, { "epoch": 1.59, "learning_rate": 4.192334494773519e-05, "loss": 0.096, "step": 3370 }, { "epoch": 1.59, "learning_rate": 4.178397212543554e-05, "loss": 0.0943, "step": 3380 }, { "epoch": 1.59, "learning_rate": 4.164459930313589e-05, "loss": 0.089, "step": 3390 }, { "epoch": 1.6, "learning_rate": 4.150522648083624e-05, "loss": 0.0909, "step": 3400 }, { "epoch": 1.6, "learning_rate": 4.136585365853659e-05, "loss": 0.0978, "step": 3410 }, { "epoch": 1.61, "learning_rate": 4.122648083623694e-05, "loss": 0.0771, "step": 3420 }, { "epoch": 1.61, "learning_rate": 4.108710801393729e-05, "loss": 0.0916, "step": 3430 }, { "epoch": 1.62, "learning_rate": 4.094773519163763e-05, "loss": 0.0821, "step": 3440 }, { "epoch": 1.62, "learning_rate": 4.080836236933798e-05, "loss": 0.0903, "step": 3450 }, { "epoch": 1.63, "learning_rate": 4.066898954703833e-05, "loss": 0.085, "step": 3460 }, { "epoch": 1.63, "learning_rate": 4.052961672473868e-05, "loss": 0.0895, "step": 3470 }, { "epoch": 1.64, "learning_rate": 4.039024390243903e-05, "loss": 0.0865, "step": 3480 }, { "epoch": 1.64, "learning_rate": 4.025087108013938e-05, "loss": 0.0838, "step": 3490 }, { "epoch": 1.65, "learning_rate": 4.011149825783973e-05, "loss": 0.0741, "step": 3500 }, { "epoch": 1.65, "learning_rate": 3.997212543554007e-05, "loss": 0.0883, "step": 3510 }, { "epoch": 1.66, "learning_rate": 3.983275261324042e-05, "loss": 0.0911, "step": 3520 }, { "epoch": 1.66, "learning_rate": 3.969337979094077e-05, "loss": 0.0918, "step": 3530 }, { "epoch": 1.67, "learning_rate": 3.955400696864112e-05, "loss": 0.0885, "step": 3540 }, { "epoch": 1.67, "learning_rate": 3.941463414634147e-05, "loss": 0.0902, "step": 3550 }, { "epoch": 1.67, "learning_rate": 3.927526132404182e-05, "loss": 0.0969, "step": 3560 }, { "epoch": 1.68, "learning_rate": 3.913588850174217e-05, "loss": 0.0987, "step": 3570 }, { "epoch": 1.68, "learning_rate": 3.899651567944251e-05, "loss": 0.086, "step": 3580 }, { "epoch": 1.69, "learning_rate": 3.885714285714286e-05, "loss": 0.0781, "step": 3590 }, { "epoch": 1.69, "learning_rate": 3.871777003484321e-05, "loss": 0.0871, "step": 3600 }, { "epoch": 1.7, "learning_rate": 3.857839721254356e-05, "loss": 0.0882, "step": 3610 }, { "epoch": 1.7, "learning_rate": 3.84390243902439e-05, "loss": 0.0916, "step": 3620 }, { "epoch": 1.71, "learning_rate": 3.829965156794425e-05, "loss": 0.1001, "step": 3630 }, { "epoch": 1.71, "learning_rate": 3.81602787456446e-05, "loss": 0.0989, "step": 3640 }, { "epoch": 1.72, "learning_rate": 3.802090592334495e-05, "loss": 0.0888, "step": 3650 }, { "epoch": 1.72, "learning_rate": 3.78815331010453e-05, "loss": 0.0971, "step": 3660 }, { "epoch": 1.73, "learning_rate": 3.774216027874565e-05, "loss": 0.0984, "step": 3670 }, { "epoch": 1.73, "learning_rate": 3.7602787456445994e-05, "loss": 0.0994, "step": 3680 }, { "epoch": 1.74, "learning_rate": 3.7463414634146343e-05, "loss": 0.0851, "step": 3690 }, { "epoch": 1.74, "learning_rate": 3.732404181184669e-05, "loss": 0.0858, "step": 3700 }, { "epoch": 1.75, "learning_rate": 3.718466898954704e-05, "loss": 0.0879, "step": 3710 }, { "epoch": 1.75, "learning_rate": 3.704529616724739e-05, "loss": 0.0866, "step": 3720 }, { "epoch": 1.75, "learning_rate": 3.6905923344947735e-05, "loss": 0.0856, "step": 3730 }, { "epoch": 1.76, "learning_rate": 3.6766550522648085e-05, "loss": 0.0865, "step": 3740 }, { "epoch": 1.76, "learning_rate": 3.6627177700348434e-05, "loss": 0.0731, "step": 3750 }, { "epoch": 1.77, "learning_rate": 3.6487804878048784e-05, "loss": 0.0864, "step": 3760 }, { "epoch": 1.77, "learning_rate": 3.634843205574913e-05, "loss": 0.0884, "step": 3770 }, { "epoch": 1.78, "learning_rate": 3.6209059233449476e-05, "loss": 0.0921, "step": 3780 }, { "epoch": 1.78, "learning_rate": 3.6069686411149826e-05, "loss": 0.0933, "step": 3790 }, { "epoch": 1.79, "learning_rate": 3.5930313588850176e-05, "loss": 0.0865, "step": 3800 }, { "epoch": 1.79, "learning_rate": 3.5790940766550525e-05, "loss": 0.0864, "step": 3810 }, { "epoch": 1.8, "learning_rate": 3.5651567944250875e-05, "loss": 0.0848, "step": 3820 }, { "epoch": 1.8, "learning_rate": 3.5512195121951225e-05, "loss": 0.0896, "step": 3830 }, { "epoch": 1.81, "learning_rate": 3.5372822299651574e-05, "loss": 0.0856, "step": 3840 }, { "epoch": 1.81, "learning_rate": 3.523344947735192e-05, "loss": 0.0796, "step": 3850 }, { "epoch": 1.82, "learning_rate": 3.509407665505227e-05, "loss": 0.0771, "step": 3860 }, { "epoch": 1.82, "learning_rate": 3.4954703832752616e-05, "loss": 0.0864, "step": 3870 }, { "epoch": 1.83, "learning_rate": 3.4815331010452966e-05, "loss": 0.0743, "step": 3880 }, { "epoch": 1.83, "learning_rate": 3.467595818815331e-05, "loss": 0.0932, "step": 3890 }, { "epoch": 1.83, "learning_rate": 3.453658536585366e-05, "loss": 0.0956, "step": 3900 }, { "epoch": 1.84, "learning_rate": 3.439721254355401e-05, "loss": 0.0766, "step": 3910 }, { "epoch": 1.84, "learning_rate": 3.425783972125436e-05, "loss": 0.079, "step": 3920 }, { "epoch": 1.85, "learning_rate": 3.411846689895471e-05, "loss": 0.0921, "step": 3930 }, { "epoch": 1.85, "learning_rate": 3.397909407665506e-05, "loss": 0.0862, "step": 3940 }, { "epoch": 1.86, "learning_rate": 3.3839721254355407e-05, "loss": 0.0832, "step": 3950 }, { "epoch": 1.86, "learning_rate": 3.3700348432055756e-05, "loss": 0.0907, "step": 3960 }, { "epoch": 1.87, "learning_rate": 3.35609756097561e-05, "loss": 0.088, "step": 3970 }, { "epoch": 1.87, "learning_rate": 3.342160278745645e-05, "loss": 0.0806, "step": 3980 }, { "epoch": 1.88, "learning_rate": 3.32822299651568e-05, "loss": 0.0985, "step": 3990 }, { "epoch": 1.88, "learning_rate": 3.314285714285715e-05, "loss": 0.0843, "step": 4000 }, { "epoch": 1.89, "learning_rate": 3.300348432055749e-05, "loss": 0.0799, "step": 4010 }, { "epoch": 1.89, "learning_rate": 3.286411149825784e-05, "loss": 0.0984, "step": 4020 }, { "epoch": 1.9, "learning_rate": 3.272473867595819e-05, "loss": 0.0789, "step": 4030 }, { "epoch": 1.9, "learning_rate": 3.258536585365854e-05, "loss": 0.0917, "step": 4040 }, { "epoch": 1.9, "learning_rate": 3.244599303135889e-05, "loss": 0.0918, "step": 4050 }, { "epoch": 1.91, "learning_rate": 3.230662020905924e-05, "loss": 0.0843, "step": 4060 }, { "epoch": 1.91, "learning_rate": 3.216724738675959e-05, "loss": 0.0823, "step": 4070 }, { "epoch": 1.92, "learning_rate": 3.202787456445993e-05, "loss": 0.0757, "step": 4080 }, { "epoch": 1.92, "learning_rate": 3.188850174216028e-05, "loss": 0.0953, "step": 4090 }, { "epoch": 1.93, "learning_rate": 3.174912891986063e-05, "loss": 0.0707, "step": 4100 }, { "epoch": 1.93, "learning_rate": 3.160975609756098e-05, "loss": 0.0711, "step": 4110 }, { "epoch": 1.94, "learning_rate": 3.147038327526132e-05, "loss": 0.0805, "step": 4120 }, { "epoch": 1.94, "learning_rate": 3.133101045296167e-05, "loss": 0.0758, "step": 4130 }, { "epoch": 1.95, "learning_rate": 3.119163763066202e-05, "loss": 0.0897, "step": 4140 }, { "epoch": 1.95, "learning_rate": 3.105226480836237e-05, "loss": 0.0773, "step": 4150 }, { "epoch": 1.96, "learning_rate": 3.091289198606272e-05, "loss": 0.0927, "step": 4160 }, { "epoch": 1.96, "learning_rate": 3.077351916376307e-05, "loss": 0.0797, "step": 4170 }, { "epoch": 1.97, "learning_rate": 3.063414634146342e-05, "loss": 0.0809, "step": 4180 }, { "epoch": 1.97, "learning_rate": 3.0494773519163767e-05, "loss": 0.0911, "step": 4190 }, { "epoch": 1.98, "learning_rate": 3.0355400696864113e-05, "loss": 0.0869, "step": 4200 }, { "epoch": 1.98, "learning_rate": 3.0216027874564463e-05, "loss": 0.0862, "step": 4210 }, { "epoch": 1.98, "learning_rate": 3.0076655052264813e-05, "loss": 0.0952, "step": 4220 }, { "epoch": 1.99, "learning_rate": 2.9937282229965162e-05, "loss": 0.0893, "step": 4230 }, { "epoch": 1.99, "learning_rate": 2.9797909407665505e-05, "loss": 0.0871, "step": 4240 }, { "epoch": 2.0, "learning_rate": 2.9658536585365855e-05, "loss": 0.0724, "step": 4250 }, { "epoch": 2.0, "eval_accuracy": 0.9695612820466711, "eval_f1": 0.6982777703989019, "eval_loss": 0.08137683570384979, "eval_precision": 0.692483315770987, "eval_recall": 0.7041700151799268, "eval_runtime": 7.0711, "eval_samples_per_second": 2002.51, "eval_steps_per_second": 250.314, "step": 4252 }, { "epoch": 2.0, "learning_rate": 2.9519163763066204e-05, "loss": 0.0655, "step": 4260 }, { "epoch": 2.01, "learning_rate": 2.9379790940766554e-05, "loss": 0.0837, "step": 4270 }, { "epoch": 2.01, "learning_rate": 2.92404181184669e-05, "loss": 0.0737, "step": 4280 }, { "epoch": 2.02, "learning_rate": 2.910104529616725e-05, "loss": 0.0746, "step": 4290 }, { "epoch": 2.02, "learning_rate": 2.89616724738676e-05, "loss": 0.0715, "step": 4300 }, { "epoch": 2.03, "learning_rate": 2.882229965156795e-05, "loss": 0.0713, "step": 4310 }, { "epoch": 2.03, "learning_rate": 2.8682926829268295e-05, "loss": 0.0844, "step": 4320 }, { "epoch": 2.04, "learning_rate": 2.8543554006968645e-05, "loss": 0.0834, "step": 4330 }, { "epoch": 2.04, "learning_rate": 2.8404181184668994e-05, "loss": 0.0737, "step": 4340 }, { "epoch": 2.05, "learning_rate": 2.8264808362369337e-05, "loss": 0.0904, "step": 4350 }, { "epoch": 2.05, "learning_rate": 2.8125435540069687e-05, "loss": 0.072, "step": 4360 }, { "epoch": 2.06, "learning_rate": 2.7986062717770037e-05, "loss": 0.0766, "step": 4370 }, { "epoch": 2.06, "learning_rate": 2.7846689895470386e-05, "loss": 0.0732, "step": 4380 }, { "epoch": 2.06, "learning_rate": 2.7707317073170732e-05, "loss": 0.0789, "step": 4390 }, { "epoch": 2.07, "learning_rate": 2.7567944250871082e-05, "loss": 0.0893, "step": 4400 }, { "epoch": 2.07, "learning_rate": 2.742857142857143e-05, "loss": 0.082, "step": 4410 }, { "epoch": 2.08, "learning_rate": 2.728919860627178e-05, "loss": 0.0708, "step": 4420 }, { "epoch": 2.08, "learning_rate": 2.7149825783972124e-05, "loss": 0.0966, "step": 4430 }, { "epoch": 2.09, "learning_rate": 2.7010452961672474e-05, "loss": 0.0832, "step": 4440 }, { "epoch": 2.09, "learning_rate": 2.6871080139372823e-05, "loss": 0.0791, "step": 4450 }, { "epoch": 2.1, "learning_rate": 2.6731707317073173e-05, "loss": 0.0863, "step": 4460 }, { "epoch": 2.1, "learning_rate": 2.659233449477352e-05, "loss": 0.0886, "step": 4470 }, { "epoch": 2.11, "learning_rate": 2.645296167247387e-05, "loss": 0.0729, "step": 4480 }, { "epoch": 2.11, "learning_rate": 2.631358885017422e-05, "loss": 0.0769, "step": 4490 }, { "epoch": 2.12, "learning_rate": 2.6174216027874568e-05, "loss": 0.0855, "step": 4500 }, { "epoch": 2.12, "learning_rate": 2.6034843205574914e-05, "loss": 0.0848, "step": 4510 }, { "epoch": 2.13, "learning_rate": 2.5895470383275264e-05, "loss": 0.0801, "step": 4520 }, { "epoch": 2.13, "learning_rate": 2.5756097560975614e-05, "loss": 0.0795, "step": 4530 }, { "epoch": 2.14, "learning_rate": 2.5616724738675963e-05, "loss": 0.0827, "step": 4540 }, { "epoch": 2.14, "learning_rate": 2.5477351916376306e-05, "loss": 0.0871, "step": 4550 }, { "epoch": 2.14, "learning_rate": 2.5337979094076656e-05, "loss": 0.0837, "step": 4560 }, { "epoch": 2.15, "learning_rate": 2.5198606271777005e-05, "loss": 0.0886, "step": 4570 }, { "epoch": 2.15, "learning_rate": 2.5059233449477355e-05, "loss": 0.075, "step": 4580 }, { "epoch": 2.16, "learning_rate": 2.49198606271777e-05, "loss": 0.0857, "step": 4590 }, { "epoch": 2.16, "learning_rate": 2.478048780487805e-05, "loss": 0.0805, "step": 4600 }, { "epoch": 2.17, "learning_rate": 2.46411149825784e-05, "loss": 0.0663, "step": 4610 }, { "epoch": 2.17, "learning_rate": 2.450174216027875e-05, "loss": 0.0814, "step": 4620 }, { "epoch": 2.18, "learning_rate": 2.4362369337979096e-05, "loss": 0.0711, "step": 4630 }, { "epoch": 2.18, "learning_rate": 2.4222996515679446e-05, "loss": 0.0777, "step": 4640 }, { "epoch": 2.19, "learning_rate": 2.4083623693379796e-05, "loss": 0.0889, "step": 4650 }, { "epoch": 2.19, "learning_rate": 2.394425087108014e-05, "loss": 0.076, "step": 4660 }, { "epoch": 2.2, "learning_rate": 2.3804878048780488e-05, "loss": 0.0795, "step": 4670 }, { "epoch": 2.2, "learning_rate": 2.3665505226480838e-05, "loss": 0.0756, "step": 4680 }, { "epoch": 2.21, "learning_rate": 2.3526132404181187e-05, "loss": 0.0768, "step": 4690 }, { "epoch": 2.21, "learning_rate": 2.3386759581881534e-05, "loss": 0.074, "step": 4700 }, { "epoch": 2.22, "learning_rate": 2.3247386759581883e-05, "loss": 0.08, "step": 4710 }, { "epoch": 2.22, "learning_rate": 2.3108013937282233e-05, "loss": 0.0875, "step": 4720 }, { "epoch": 2.22, "learning_rate": 2.2968641114982582e-05, "loss": 0.0757, "step": 4730 }, { "epoch": 2.23, "learning_rate": 2.2829268292682925e-05, "loss": 0.0748, "step": 4740 }, { "epoch": 2.23, "learning_rate": 2.2689895470383275e-05, "loss": 0.0821, "step": 4750 }, { "epoch": 2.24, "learning_rate": 2.2550522648083625e-05, "loss": 0.0699, "step": 4760 }, { "epoch": 2.24, "learning_rate": 2.2411149825783974e-05, "loss": 0.0827, "step": 4770 }, { "epoch": 2.25, "learning_rate": 2.227177700348432e-05, "loss": 0.0772, "step": 4780 }, { "epoch": 2.25, "learning_rate": 2.213240418118467e-05, "loss": 0.087, "step": 4790 }, { "epoch": 2.26, "learning_rate": 2.199303135888502e-05, "loss": 0.0781, "step": 4800 }, { "epoch": 2.26, "learning_rate": 2.185365853658537e-05, "loss": 0.076, "step": 4810 }, { "epoch": 2.27, "learning_rate": 2.1714285714285715e-05, "loss": 0.0751, "step": 4820 }, { "epoch": 2.27, "learning_rate": 2.1574912891986065e-05, "loss": 0.0753, "step": 4830 }, { "epoch": 2.28, "learning_rate": 2.1435540069686415e-05, "loss": 0.0782, "step": 4840 }, { "epoch": 2.28, "learning_rate": 2.1296167247386764e-05, "loss": 0.0813, "step": 4850 }, { "epoch": 2.29, "learning_rate": 2.1156794425087107e-05, "loss": 0.0824, "step": 4860 }, { "epoch": 2.29, "learning_rate": 2.1017421602787457e-05, "loss": 0.0793, "step": 4870 }, { "epoch": 2.3, "learning_rate": 2.0878048780487806e-05, "loss": 0.0706, "step": 4880 }, { "epoch": 2.3, "learning_rate": 2.0738675958188156e-05, "loss": 0.0747, "step": 4890 }, { "epoch": 2.3, "learning_rate": 2.0599303135888502e-05, "loss": 0.0722, "step": 4900 }, { "epoch": 2.31, "learning_rate": 2.0459930313588852e-05, "loss": 0.0814, "step": 4910 }, { "epoch": 2.31, "learning_rate": 2.03205574912892e-05, "loss": 0.0659, "step": 4920 }, { "epoch": 2.32, "learning_rate": 2.018118466898955e-05, "loss": 0.0833, "step": 4930 }, { "epoch": 2.32, "learning_rate": 2.0041811846689897e-05, "loss": 0.0823, "step": 4940 }, { "epoch": 2.33, "learning_rate": 1.9902439024390247e-05, "loss": 0.075, "step": 4950 }, { "epoch": 2.33, "learning_rate": 1.9763066202090597e-05, "loss": 0.0882, "step": 4960 }, { "epoch": 2.34, "learning_rate": 1.9623693379790943e-05, "loss": 0.0763, "step": 4970 }, { "epoch": 2.34, "learning_rate": 1.948432055749129e-05, "loss": 0.0725, "step": 4980 }, { "epoch": 2.35, "learning_rate": 1.934494773519164e-05, "loss": 0.0735, "step": 4990 }, { "epoch": 2.35, "learning_rate": 1.9205574912891985e-05, "loss": 0.0838, "step": 5000 }, { "epoch": 2.36, "learning_rate": 1.9066202090592335e-05, "loss": 0.0694, "step": 5010 }, { "epoch": 2.36, "learning_rate": 1.8926829268292684e-05, "loss": 0.085, "step": 5020 }, { "epoch": 2.37, "learning_rate": 1.8787456445993034e-05, "loss": 0.0951, "step": 5030 }, { "epoch": 2.37, "learning_rate": 1.864808362369338e-05, "loss": 0.0844, "step": 5040 }, { "epoch": 2.38, "learning_rate": 1.850871080139373e-05, "loss": 0.0784, "step": 5050 }, { "epoch": 2.38, "learning_rate": 1.8369337979094076e-05, "loss": 0.0792, "step": 5060 }, { "epoch": 2.38, "learning_rate": 1.8229965156794426e-05, "loss": 0.0782, "step": 5070 }, { "epoch": 2.39, "learning_rate": 1.8090592334494775e-05, "loss": 0.0747, "step": 5080 }, { "epoch": 2.39, "learning_rate": 1.7951219512195125e-05, "loss": 0.0774, "step": 5090 }, { "epoch": 2.4, "learning_rate": 1.781184668989547e-05, "loss": 0.0818, "step": 5100 }, { "epoch": 2.4, "learning_rate": 1.767247386759582e-05, "loss": 0.073, "step": 5110 }, { "epoch": 2.41, "learning_rate": 1.7533101045296167e-05, "loss": 0.0662, "step": 5120 }, { "epoch": 2.41, "learning_rate": 1.7393728222996517e-05, "loss": 0.0874, "step": 5130 }, { "epoch": 2.42, "learning_rate": 1.7254355400696866e-05, "loss": 0.0691, "step": 5140 }, { "epoch": 2.42, "learning_rate": 1.7114982578397216e-05, "loss": 0.0703, "step": 5150 }, { "epoch": 2.43, "learning_rate": 1.6975609756097562e-05, "loss": 0.0736, "step": 5160 }, { "epoch": 2.43, "learning_rate": 1.683623693379791e-05, "loss": 0.0781, "step": 5170 }, { "epoch": 2.44, "learning_rate": 1.6696864111498258e-05, "loss": 0.0805, "step": 5180 }, { "epoch": 2.44, "learning_rate": 1.6557491289198608e-05, "loss": 0.0763, "step": 5190 }, { "epoch": 2.45, "learning_rate": 1.6418118466898957e-05, "loss": 0.0831, "step": 5200 }, { "epoch": 2.45, "learning_rate": 1.6278745644599307e-05, "loss": 0.0718, "step": 5210 }, { "epoch": 2.46, "learning_rate": 1.6139372822299653e-05, "loss": 0.0756, "step": 5220 }, { "epoch": 2.46, "learning_rate": 1.6000000000000003e-05, "loss": 0.0738, "step": 5230 }, { "epoch": 2.46, "learning_rate": 1.586062717770035e-05, "loss": 0.0656, "step": 5240 }, { "epoch": 2.47, "learning_rate": 1.57212543554007e-05, "loss": 0.0762, "step": 5250 }, { "epoch": 2.47, "learning_rate": 1.5581881533101045e-05, "loss": 0.0808, "step": 5260 }, { "epoch": 2.48, "learning_rate": 1.5442508710801394e-05, "loss": 0.08, "step": 5270 }, { "epoch": 2.48, "learning_rate": 1.5303135888501744e-05, "loss": 0.0771, "step": 5280 }, { "epoch": 2.49, "learning_rate": 1.5163763066202094e-05, "loss": 0.0765, "step": 5290 }, { "epoch": 2.49, "learning_rate": 1.502439024390244e-05, "loss": 0.0783, "step": 5300 }, { "epoch": 2.5, "learning_rate": 1.4885017421602788e-05, "loss": 0.0763, "step": 5310 }, { "epoch": 2.5, "learning_rate": 1.4745644599303137e-05, "loss": 0.0747, "step": 5320 }, { "epoch": 2.51, "learning_rate": 1.4606271777003485e-05, "loss": 0.079, "step": 5330 }, { "epoch": 2.51, "learning_rate": 1.4466898954703833e-05, "loss": 0.0588, "step": 5340 }, { "epoch": 2.52, "learning_rate": 1.4327526132404181e-05, "loss": 0.0803, "step": 5350 }, { "epoch": 2.52, "learning_rate": 1.418815331010453e-05, "loss": 0.0797, "step": 5360 }, { "epoch": 2.53, "learning_rate": 1.4048780487804879e-05, "loss": 0.0807, "step": 5370 }, { "epoch": 2.53, "learning_rate": 1.3909407665505228e-05, "loss": 0.0843, "step": 5380 }, { "epoch": 2.54, "learning_rate": 1.3770034843205575e-05, "loss": 0.0778, "step": 5390 }, { "epoch": 2.54, "learning_rate": 1.3630662020905924e-05, "loss": 0.0831, "step": 5400 }, { "epoch": 2.54, "learning_rate": 1.3491289198606272e-05, "loss": 0.0714, "step": 5410 }, { "epoch": 2.55, "learning_rate": 1.3351916376306622e-05, "loss": 0.0769, "step": 5420 }, { "epoch": 2.55, "learning_rate": 1.321254355400697e-05, "loss": 0.0722, "step": 5430 }, { "epoch": 2.56, "learning_rate": 1.307317073170732e-05, "loss": 0.075, "step": 5440 }, { "epoch": 2.56, "learning_rate": 1.2933797909407666e-05, "loss": 0.087, "step": 5450 }, { "epoch": 2.57, "learning_rate": 1.2794425087108015e-05, "loss": 0.0791, "step": 5460 }, { "epoch": 2.57, "learning_rate": 1.2655052264808363e-05, "loss": 0.074, "step": 5470 }, { "epoch": 2.58, "learning_rate": 1.2515679442508713e-05, "loss": 0.0827, "step": 5480 }, { "epoch": 2.58, "learning_rate": 1.2376306620209059e-05, "loss": 0.0904, "step": 5490 }, { "epoch": 2.59, "learning_rate": 1.2236933797909409e-05, "loss": 0.0859, "step": 5500 }, { "epoch": 2.59, "learning_rate": 1.2097560975609757e-05, "loss": 0.0772, "step": 5510 }, { "epoch": 2.6, "learning_rate": 1.1958188153310106e-05, "loss": 0.0685, "step": 5520 }, { "epoch": 2.6, "learning_rate": 1.1818815331010454e-05, "loss": 0.0656, "step": 5530 }, { "epoch": 2.61, "learning_rate": 1.1679442508710804e-05, "loss": 0.0709, "step": 5540 }, { "epoch": 2.61, "learning_rate": 1.154006968641115e-05, "loss": 0.0731, "step": 5550 }, { "epoch": 2.62, "learning_rate": 1.14006968641115e-05, "loss": 0.0676, "step": 5560 }, { "epoch": 2.62, "learning_rate": 1.1261324041811848e-05, "loss": 0.0886, "step": 5570 }, { "epoch": 2.62, "learning_rate": 1.1121951219512197e-05, "loss": 0.0937, "step": 5580 }, { "epoch": 2.63, "learning_rate": 1.0982578397212545e-05, "loss": 0.0767, "step": 5590 }, { "epoch": 2.63, "learning_rate": 1.0843205574912895e-05, "loss": 0.06, "step": 5600 }, { "epoch": 2.64, "learning_rate": 1.0703832752613241e-05, "loss": 0.0708, "step": 5610 }, { "epoch": 2.64, "learning_rate": 1.0564459930313589e-05, "loss": 0.0775, "step": 5620 }, { "epoch": 2.65, "learning_rate": 1.0425087108013939e-05, "loss": 0.0802, "step": 5630 }, { "epoch": 2.65, "learning_rate": 1.0285714285714285e-05, "loss": 0.0674, "step": 5640 }, { "epoch": 2.66, "learning_rate": 1.0146341463414634e-05, "loss": 0.0709, "step": 5650 }, { "epoch": 2.66, "learning_rate": 1.0006968641114982e-05, "loss": 0.0732, "step": 5660 }, { "epoch": 2.67, "learning_rate": 9.867595818815332e-06, "loss": 0.0712, "step": 5670 }, { "epoch": 2.67, "learning_rate": 9.72822299651568e-06, "loss": 0.0748, "step": 5680 }, { "epoch": 2.68, "learning_rate": 9.58885017421603e-06, "loss": 0.0874, "step": 5690 }, { "epoch": 2.68, "learning_rate": 9.449477351916377e-06, "loss": 0.0712, "step": 5700 }, { "epoch": 2.69, "learning_rate": 9.310104529616725e-06, "loss": 0.0692, "step": 5710 }, { "epoch": 2.69, "learning_rate": 9.170731707317075e-06, "loss": 0.0752, "step": 5720 }, { "epoch": 2.7, "learning_rate": 9.031358885017423e-06, "loss": 0.0873, "step": 5730 }, { "epoch": 2.7, "learning_rate": 8.891986062717771e-06, "loss": 0.0835, "step": 5740 }, { "epoch": 2.7, "learning_rate": 8.75261324041812e-06, "loss": 0.0774, "step": 5750 }, { "epoch": 2.71, "learning_rate": 8.613240418118468e-06, "loss": 0.0739, "step": 5760 }, { "epoch": 2.71, "learning_rate": 8.473867595818816e-06, "loss": 0.0695, "step": 5770 }, { "epoch": 2.72, "learning_rate": 8.334494773519164e-06, "loss": 0.0689, "step": 5780 }, { "epoch": 2.72, "learning_rate": 8.195121951219512e-06, "loss": 0.0867, "step": 5790 }, { "epoch": 2.73, "learning_rate": 8.05574912891986e-06, "loss": 0.0738, "step": 5800 }, { "epoch": 2.73, "learning_rate": 7.91637630662021e-06, "loss": 0.0733, "step": 5810 }, { "epoch": 2.74, "learning_rate": 7.777003484320558e-06, "loss": 0.0747, "step": 5820 }, { "epoch": 2.74, "learning_rate": 7.637630662020906e-06, "loss": 0.0845, "step": 5830 }, { "epoch": 2.75, "learning_rate": 7.498257839721254e-06, "loss": 0.0803, "step": 5840 }, { "epoch": 2.75, "learning_rate": 7.358885017421603e-06, "loss": 0.0839, "step": 5850 }, { "epoch": 2.76, "learning_rate": 7.219512195121952e-06, "loss": 0.0798, "step": 5860 }, { "epoch": 2.76, "learning_rate": 7.0801393728223e-06, "loss": 0.0763, "step": 5870 }, { "epoch": 2.77, "learning_rate": 6.940766550522649e-06, "loss": 0.0753, "step": 5880 }, { "epoch": 2.77, "learning_rate": 6.801393728222997e-06, "loss": 0.0737, "step": 5890 }, { "epoch": 2.78, "learning_rate": 6.662020905923345e-06, "loss": 0.0693, "step": 5900 }, { "epoch": 2.78, "learning_rate": 6.522648083623694e-06, "loss": 0.0755, "step": 5910 }, { "epoch": 2.78, "learning_rate": 6.383275261324042e-06, "loss": 0.0824, "step": 5920 }, { "epoch": 2.79, "learning_rate": 6.243902439024391e-06, "loss": 0.075, "step": 5930 }, { "epoch": 2.79, "learning_rate": 6.10452961672474e-06, "loss": 0.0759, "step": 5940 }, { "epoch": 2.8, "learning_rate": 5.9651567944250876e-06, "loss": 0.0958, "step": 5950 }, { "epoch": 2.8, "learning_rate": 5.825783972125436e-06, "loss": 0.0888, "step": 5960 }, { "epoch": 2.81, "learning_rate": 5.686411149825784e-06, "loss": 0.0874, "step": 5970 }, { "epoch": 2.81, "learning_rate": 5.547038327526133e-06, "loss": 0.0796, "step": 5980 }, { "epoch": 2.82, "learning_rate": 5.407665505226482e-06, "loss": 0.0721, "step": 5990 }, { "epoch": 2.82, "learning_rate": 5.26829268292683e-06, "loss": 0.0657, "step": 6000 }, { "epoch": 2.83, "learning_rate": 5.1289198606271785e-06, "loss": 0.0744, "step": 6010 }, { "epoch": 2.83, "learning_rate": 4.9895470383275265e-06, "loss": 0.073, "step": 6020 }, { "epoch": 2.84, "learning_rate": 4.850174216027874e-06, "loss": 0.0692, "step": 6030 }, { "epoch": 2.84, "learning_rate": 4.710801393728223e-06, "loss": 0.0732, "step": 6040 }, { "epoch": 2.85, "learning_rate": 4.571428571428572e-06, "loss": 0.0736, "step": 6050 }, { "epoch": 2.85, "learning_rate": 4.43205574912892e-06, "loss": 0.0707, "step": 6060 }, { "epoch": 2.86, "learning_rate": 4.292682926829269e-06, "loss": 0.0662, "step": 6070 }, { "epoch": 2.86, "learning_rate": 4.1533101045296174e-06, "loss": 0.0718, "step": 6080 }, { "epoch": 2.86, "learning_rate": 4.013937282229965e-06, "loss": 0.0715, "step": 6090 }, { "epoch": 2.87, "learning_rate": 3.874564459930314e-06, "loss": 0.0629, "step": 6100 }, { "epoch": 2.87, "learning_rate": 3.7351916376306625e-06, "loss": 0.0837, "step": 6110 }, { "epoch": 2.88, "learning_rate": 3.595818815331011e-06, "loss": 0.0841, "step": 6120 }, { "epoch": 2.88, "learning_rate": 3.456445993031359e-06, "loss": 0.0799, "step": 6130 }, { "epoch": 2.89, "learning_rate": 3.3170731707317076e-06, "loss": 0.073, "step": 6140 }, { "epoch": 2.89, "learning_rate": 3.1777003484320563e-06, "loss": 0.0841, "step": 6150 }, { "epoch": 2.9, "learning_rate": 3.0383275261324047e-06, "loss": 0.0728, "step": 6160 }, { "epoch": 2.9, "learning_rate": 2.898954703832753e-06, "loss": 0.0723, "step": 6170 }, { "epoch": 2.91, "learning_rate": 2.759581881533101e-06, "loss": 0.0831, "step": 6180 }, { "epoch": 2.91, "learning_rate": 2.6202090592334493e-06, "loss": 0.077, "step": 6190 }, { "epoch": 2.92, "learning_rate": 2.480836236933798e-06, "loss": 0.0813, "step": 6200 }, { "epoch": 2.92, "learning_rate": 2.3414634146341465e-06, "loss": 0.0779, "step": 6210 }, { "epoch": 2.93, "learning_rate": 2.202090592334495e-06, "loss": 0.0756, "step": 6220 }, { "epoch": 2.93, "learning_rate": 2.062717770034843e-06, "loss": 0.0768, "step": 6230 }, { "epoch": 2.94, "learning_rate": 1.923344947735192e-06, "loss": 0.0755, "step": 6240 }, { "epoch": 2.94, "learning_rate": 1.7839721254355403e-06, "loss": 0.0702, "step": 6250 }, { "epoch": 2.94, "learning_rate": 1.6445993031358887e-06, "loss": 0.0763, "step": 6260 }, { "epoch": 2.95, "learning_rate": 1.5052264808362372e-06, "loss": 0.0784, "step": 6270 }, { "epoch": 2.95, "learning_rate": 1.3658536585365856e-06, "loss": 0.072, "step": 6280 }, { "epoch": 2.96, "learning_rate": 1.226480836236934e-06, "loss": 0.0777, "step": 6290 }, { "epoch": 2.96, "learning_rate": 1.0871080139372823e-06, "loss": 0.0686, "step": 6300 }, { "epoch": 2.97, "learning_rate": 9.477351916376309e-07, "loss": 0.0733, "step": 6310 }, { "epoch": 2.97, "learning_rate": 8.083623693379791e-07, "loss": 0.0715, "step": 6320 }, { "epoch": 2.98, "learning_rate": 6.689895470383276e-07, "loss": 0.0865, "step": 6330 }, { "epoch": 2.98, "learning_rate": 5.29616724738676e-07, "loss": 0.0893, "step": 6340 }, { "epoch": 2.99, "learning_rate": 3.9024390243902443e-07, "loss": 0.0756, "step": 6350 }, { "epoch": 2.99, "learning_rate": 2.5087108013937284e-07, "loss": 0.0762, "step": 6360 }, { "epoch": 3.0, "learning_rate": 1.1149825783972127e-07, "loss": 0.0778, "step": 6370 }, { "epoch": 3.0, "eval_accuracy": 0.9702296390871982, "eval_f1": 0.7075550845586612, "eval_loss": 0.07886078208684921, "eval_precision": 0.6998602375960866, "eval_recall": 0.7154210197339048, "eval_runtime": 6.9707, "eval_samples_per_second": 2031.371, "eval_steps_per_second": 253.921, "step": 6378 }, { "epoch": 3.0, "step": 6378, "total_flos": 725952230430336.0, "train_loss": 0.11718836608034722, "train_runtime": 82.4816, "train_samples_per_second": 3710.575, "train_steps_per_second": 77.326 } ], "logging_steps": 10, "max_steps": 6378, "num_train_epochs": 3, "save_steps": 500, "total_flos": 725952230430336.0, "trial_name": null, "trial_params": null }