| { | |
| "best_metric": 1.1947814226150513, | |
| "best_model_checkpoint": "./output/checkpoint-4650", | |
| "epoch": 0.21500559910414332, | |
| "eval_steps": 150, | |
| "global_step": 4800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004479283314669653, | |
| "grad_norm": 6.820243835449219, | |
| "learning_rate": 7.500000000000001e-07, | |
| "loss": 1.2628, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008958566629339306, | |
| "grad_norm": 5.822151184082031, | |
| "learning_rate": 1.5000000000000002e-06, | |
| "loss": 1.3652, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013437849944008958, | |
| "grad_norm": 4.442959785461426, | |
| "learning_rate": 2.25e-06, | |
| "loss": 1.412, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017917133258678612, | |
| "grad_norm": 9.916281700134277, | |
| "learning_rate": 3.0000000000000005e-06, | |
| "loss": 1.5213, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0022396416573348264, | |
| "grad_norm": 22.53717613220215, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.3189, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0026875699888017916, | |
| "grad_norm": 5.07314920425415, | |
| "learning_rate": 4.5e-06, | |
| "loss": 1.3022, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.003135498320268757, | |
| "grad_norm": 9.401494026184082, | |
| "learning_rate": 5.2500000000000006e-06, | |
| "loss": 1.5065, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0035834266517357225, | |
| "grad_norm": 8.749906539916992, | |
| "learning_rate": 6.000000000000001e-06, | |
| "loss": 1.1579, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.004031354983202688, | |
| "grad_norm": 6.749314785003662, | |
| "learning_rate": 6.7500000000000014e-06, | |
| "loss": 1.2524, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004479283314669653, | |
| "grad_norm": 8.411529541015625, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.3242, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004927211646136618, | |
| "grad_norm": 5.293492794036865, | |
| "learning_rate": 7.499922926093874e-06, | |
| "loss": 0.9967, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.005375139977603583, | |
| "grad_norm": 8.860544204711914, | |
| "learning_rate": 7.499691707543699e-06, | |
| "loss": 1.1881, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0058230683090705485, | |
| "grad_norm": 9.859148979187012, | |
| "learning_rate": 7.499306353853963e-06, | |
| "loss": 1.0598, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.006270996640537514, | |
| "grad_norm": 4.37281608581543, | |
| "learning_rate": 7.49876688086505e-06, | |
| "loss": 1.1233, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.006718924972004479, | |
| "grad_norm": 4.489595890045166, | |
| "learning_rate": 7.4980733107525805e-06, | |
| "loss": 1.2183, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006718924972004479, | |
| "eval_loss": 1.282976508140564, | |
| "eval_runtime": 51.7095, | |
| "eval_samples_per_second": 9.669, | |
| "eval_steps_per_second": 9.669, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.007166853303471445, | |
| "grad_norm": 6.339463233947754, | |
| "learning_rate": 7.4972256720265044e-06, | |
| "loss": 1.1818, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.00761478163493841, | |
| "grad_norm": 6.762680530548096, | |
| "learning_rate": 7.496223999529932e-06, | |
| "loss": 1.0349, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.008062709966405375, | |
| "grad_norm": 7.486023426055908, | |
| "learning_rate": 7.4950683344376926e-06, | |
| "loss": 1.1735, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.00851063829787234, | |
| "grad_norm": 4.099631309509277, | |
| "learning_rate": 7.4937587242546544e-06, | |
| "loss": 1.2452, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.008958566629339306, | |
| "grad_norm": 5.422396183013916, | |
| "learning_rate": 7.492295222813762e-06, | |
| "loss": 1.1032, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.009406494960806271, | |
| "grad_norm": 6.336536407470703, | |
| "learning_rate": 7.490677890273828e-06, | |
| "loss": 1.0852, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.009854423292273236, | |
| "grad_norm": 4.766495704650879, | |
| "learning_rate": 7.488906793117058e-06, | |
| "loss": 1.2168, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.010302351623740201, | |
| "grad_norm": 5.892153263092041, | |
| "learning_rate": 7.486982004146319e-06, | |
| "loss": 1.1595, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.010750279955207167, | |
| "grad_norm": 4.957208633422852, | |
| "learning_rate": 7.484903602482148e-06, | |
| "loss": 1.1423, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.011198208286674132, | |
| "grad_norm": 4.198282718658447, | |
| "learning_rate": 7.4826716735594945e-06, | |
| "loss": 1.0562, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.011646136618141097, | |
| "grad_norm": 3.4756815433502197, | |
| "learning_rate": 7.480286309124216e-06, | |
| "loss": 0.9894, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.012094064949608062, | |
| "grad_norm": 4.725418567657471, | |
| "learning_rate": 7.477747607229302e-06, | |
| "loss": 1.1761, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.012541993281075027, | |
| "grad_norm": 4.241955280303955, | |
| "learning_rate": 7.475055672230844e-06, | |
| "loss": 1.1118, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.012989921612541993, | |
| "grad_norm": 5.7904863357543945, | |
| "learning_rate": 7.472210614783745e-06, | |
| "loss": 1.0932, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.013437849944008958, | |
| "grad_norm": 4.546011924743652, | |
| "learning_rate": 7.469212551837173e-06, | |
| "loss": 1.1187, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.013437849944008958, | |
| "eval_loss": 1.26471745967865, | |
| "eval_runtime": 51.7822, | |
| "eval_samples_per_second": 9.656, | |
| "eval_steps_per_second": 9.656, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.013885778275475923, | |
| "grad_norm": 6.256772994995117, | |
| "learning_rate": 7.4660616066297565e-06, | |
| "loss": 1.2176, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.01433370660694289, | |
| "grad_norm": 7.437366485595703, | |
| "learning_rate": 7.462757908684509e-06, | |
| "loss": 1.046, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.014781634938409855, | |
| "grad_norm": 8.049488067626953, | |
| "learning_rate": 7.459301593803512e-06, | |
| "loss": 1.2396, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.01522956326987682, | |
| "grad_norm": 5.115020751953125, | |
| "learning_rate": 7.455692804062335e-06, | |
| "loss": 1.1018, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.015677491601343786, | |
| "grad_norm": 5.805201530456543, | |
| "learning_rate": 7.451931687804189e-06, | |
| "loss": 1.0083, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.01612541993281075, | |
| "grad_norm": 5.960669040679932, | |
| "learning_rate": 7.448018399633831e-06, | |
| "loss": 1.1773, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.016573348264277716, | |
| "grad_norm": 4.82655143737793, | |
| "learning_rate": 7.443953100411214e-06, | |
| "loss": 1.2279, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.01702127659574468, | |
| "grad_norm": 5.768619060516357, | |
| "learning_rate": 7.439735957244862e-06, | |
| "loss": 1.0924, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.017469204927211646, | |
| "grad_norm": 4.603348731994629, | |
| "learning_rate": 7.435367143485015e-06, | |
| "loss": 0.9547, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.01791713325867861, | |
| "grad_norm": 3.802041530609131, | |
| "learning_rate": 7.430846838716496e-06, | |
| "loss": 1.0569, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.018365061590145577, | |
| "grad_norm": 4.473762035369873, | |
| "learning_rate": 7.426175228751328e-06, | |
| "loss": 1.1299, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.018812989921612542, | |
| "grad_norm": 4.674028396606445, | |
| "learning_rate": 7.421352505621099e-06, | |
| "loss": 1.0512, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.019260918253079507, | |
| "grad_norm": 5.1446852684021, | |
| "learning_rate": 7.416378867569069e-06, | |
| "loss": 1.2024, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.019708846584546472, | |
| "grad_norm": 3.742156744003296, | |
| "learning_rate": 7.411254519042017e-06, | |
| "loss": 1.1778, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.020156774916013438, | |
| "grad_norm": 4.0376200675964355, | |
| "learning_rate": 7.4059796706818396e-06, | |
| "loss": 1.1754, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.020156774916013438, | |
| "eval_loss": 1.2499778270721436, | |
| "eval_runtime": 51.5995, | |
| "eval_samples_per_second": 9.69, | |
| "eval_steps_per_second": 9.69, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.020604703247480403, | |
| "grad_norm": 3.672325372695923, | |
| "learning_rate": 7.400554539316894e-06, | |
| "loss": 1.1627, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": 4.949635982513428, | |
| "learning_rate": 7.394979347953081e-06, | |
| "loss": 1.3115, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.021500559910414333, | |
| "grad_norm": 4.03855037689209, | |
| "learning_rate": 7.389254325764681e-06, | |
| "loss": 1.1176, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.0219484882418813, | |
| "grad_norm": 4.981250762939453, | |
| "learning_rate": 7.383379708084934e-06, | |
| "loss": 1.0668, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.022396416573348264, | |
| "grad_norm": 4.68571138381958, | |
| "learning_rate": 7.377355736396362e-06, | |
| "loss": 1.1235, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02284434490481523, | |
| "grad_norm": 5.7003326416015625, | |
| "learning_rate": 7.371182658320847e-06, | |
| "loss": 1.0535, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.023292273236282194, | |
| "grad_norm": 2.357079029083252, | |
| "learning_rate": 7.36486072760945e-06, | |
| "loss": 0.9768, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.02374020156774916, | |
| "grad_norm": 4.828664779663086, | |
| "learning_rate": 7.358390204131984e-06, | |
| "loss": 1.0385, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.024188129899216124, | |
| "grad_norm": 3.4303321838378906, | |
| "learning_rate": 7.3517713538663235e-06, | |
| "loss": 0.9826, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.02463605823068309, | |
| "grad_norm": 8.705097198486328, | |
| "learning_rate": 7.345004448887478e-06, | |
| "loss": 1.0988, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.025083986562150055, | |
| "grad_norm": 4.806099891662598, | |
| "learning_rate": 7.3380897673564085e-06, | |
| "loss": 1.2765, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.02553191489361702, | |
| "grad_norm": 3.948829174041748, | |
| "learning_rate": 7.33102759350859e-06, | |
| "loss": 1.2548, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.025979843225083985, | |
| "grad_norm": 8.706982612609863, | |
| "learning_rate": 7.323818217642328e-06, | |
| "loss": 1.1907, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.02642777155655095, | |
| "grad_norm": 4.196287155151367, | |
| "learning_rate": 7.316461936106827e-06, | |
| "loss": 1.1541, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.026875699888017916, | |
| "grad_norm": 4.2185187339782715, | |
| "learning_rate": 7.3089590512900084e-06, | |
| "loss": 1.0761, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.026875699888017916, | |
| "eval_loss": 1.2407419681549072, | |
| "eval_runtime": 51.6589, | |
| "eval_samples_per_second": 9.679, | |
| "eval_steps_per_second": 9.679, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02732362821948488, | |
| "grad_norm": 4.50939416885376, | |
| "learning_rate": 7.301309871606081e-06, | |
| "loss": 1.1746, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.027771556550951846, | |
| "grad_norm": 5.48988676071167, | |
| "learning_rate": 7.293514711482861e-06, | |
| "loss": 1.0518, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.028219484882418815, | |
| "grad_norm": 4.441885471343994, | |
| "learning_rate": 7.285573891348849e-06, | |
| "loss": 1.0679, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.02866741321388578, | |
| "grad_norm": 6.711030006408691, | |
| "learning_rate": 7.27748773762006e-06, | |
| "loss": 1.2901, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.029115341545352745, | |
| "grad_norm": 5.328275680541992, | |
| "learning_rate": 7.269256582686603e-06, | |
| "loss": 1.1749, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.02956326987681971, | |
| "grad_norm": 3.016313314437866, | |
| "learning_rate": 7.260880764899016e-06, | |
| "loss": 1.1398, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.030011198208286675, | |
| "grad_norm": 4.6470866203308105, | |
| "learning_rate": 7.252360628554363e-06, | |
| "loss": 1.0427, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.03045912653975364, | |
| "grad_norm": 9.044170379638672, | |
| "learning_rate": 7.243696523882079e-06, | |
| "loss": 1.0913, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.030907054871220606, | |
| "grad_norm": 4.983870029449463, | |
| "learning_rate": 7.2348888070295705e-06, | |
| "loss": 1.1174, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.03135498320268757, | |
| "grad_norm": 10.38315486907959, | |
| "learning_rate": 7.225937840047583e-06, | |
| "loss": 1.2386, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.031802911534154536, | |
| "grad_norm": 5.104282855987549, | |
| "learning_rate": 7.216843990875307e-06, | |
| "loss": 1.1014, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.0322508398656215, | |
| "grad_norm": 5.493166446685791, | |
| "learning_rate": 7.207607633325266e-06, | |
| "loss": 1.2569, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.03269876819708847, | |
| "grad_norm": 5.069271564483643, | |
| "learning_rate": 7.198229147067941e-06, | |
| "loss": 1.1938, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.03314669652855543, | |
| "grad_norm": 5.183401107788086, | |
| "learning_rate": 7.18870891761617e-06, | |
| "loss": 0.9859, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.0335946248600224, | |
| "grad_norm": 4.3622965812683105, | |
| "learning_rate": 7.1790473363092974e-06, | |
| "loss": 1.1359, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.0335946248600224, | |
| "eval_loss": 1.2344202995300293, | |
| "eval_runtime": 51.6321, | |
| "eval_samples_per_second": 9.684, | |
| "eval_steps_per_second": 9.684, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.03404255319148936, | |
| "grad_norm": 4.141931056976318, | |
| "learning_rate": 7.169244800297089e-06, | |
| "loss": 1.2613, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.03449048152295633, | |
| "grad_norm": 4.191932201385498, | |
| "learning_rate": 7.159301712523407e-06, | |
| "loss": 1.1802, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.03493840985442329, | |
| "grad_norm": 4.759700775146484, | |
| "learning_rate": 7.149218481709644e-06, | |
| "loss": 1.0651, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.03538633818589026, | |
| "grad_norm": 3.969430923461914, | |
| "learning_rate": 7.1389955223379266e-06, | |
| "loss": 0.9129, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.03583426651735722, | |
| "grad_norm": 5.1956467628479, | |
| "learning_rate": 7.128633254634072e-06, | |
| "loss": 1.2688, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.03628219484882419, | |
| "grad_norm": 3.615705966949463, | |
| "learning_rate": 7.118132104550322e-06, | |
| "loss": 1.1092, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.036730123180291153, | |
| "grad_norm": 3.635277271270752, | |
| "learning_rate": 7.107492503747826e-06, | |
| "loss": 1.0265, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.03717805151175812, | |
| "grad_norm": 4.518077373504639, | |
| "learning_rate": 7.096714889578898e-06, | |
| "loss": 1.0817, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.037625979843225084, | |
| "grad_norm": 6.652565002441406, | |
| "learning_rate": 7.085799705069046e-06, | |
| "loss": 0.9709, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.03807390817469205, | |
| "grad_norm": 5.337361812591553, | |
| "learning_rate": 7.0747473988987515e-06, | |
| "loss": 1.0883, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.038521836506159014, | |
| "grad_norm": 5.067249774932861, | |
| "learning_rate": 7.063558425385033e-06, | |
| "loss": 1.08, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.03896976483762598, | |
| "grad_norm": 3.9859232902526855, | |
| "learning_rate": 7.052233244462769e-06, | |
| "loss": 1.0063, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.039417693169092945, | |
| "grad_norm": 5.297623634338379, | |
| "learning_rate": 7.040772321665788e-06, | |
| "loss": 0.9638, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.03986562150055991, | |
| "grad_norm": 6.088709354400635, | |
| "learning_rate": 7.029176128107734e-06, | |
| "loss": 1.2673, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.040313549832026875, | |
| "grad_norm": 7.997159957885742, | |
| "learning_rate": 7.017445140462711e-06, | |
| "loss": 0.9986, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.040313549832026875, | |
| "eval_loss": 1.2309150695800781, | |
| "eval_runtime": 51.612, | |
| "eval_samples_per_second": 9.688, | |
| "eval_steps_per_second": 9.688, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.04076147816349384, | |
| "grad_norm": 6.393094062805176, | |
| "learning_rate": 7.00557984094567e-06, | |
| "loss": 1.066, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.041209406494960805, | |
| "grad_norm": 4.47462797164917, | |
| "learning_rate": 6.993580717292601e-06, | |
| "loss": 1.3117, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.04165733482642777, | |
| "grad_norm": 4.160079479217529, | |
| "learning_rate": 6.981448262740483e-06, | |
| "loss": 1.3003, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 5.260162353515625, | |
| "learning_rate": 6.969182976006999e-06, | |
| "loss": 1.312, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.0425531914893617, | |
| "grad_norm": 4.503716468811035, | |
| "learning_rate": 6.95678536127005e-06, | |
| "loss": 1.185, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.043001119820828666, | |
| "grad_norm": 3.7414872646331787, | |
| "learning_rate": 6.944255928147017e-06, | |
| "loss": 1.1585, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.04344904815229563, | |
| "grad_norm": 5.410964012145996, | |
| "learning_rate": 6.931595191673823e-06, | |
| "loss": 1.1403, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.0438969764837626, | |
| "grad_norm": 4.388716220855713, | |
| "learning_rate": 6.9188036722837555e-06, | |
| "loss": 1.0452, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.04434490481522956, | |
| "grad_norm": 2.7749533653259277, | |
| "learning_rate": 6.905881895786076e-06, | |
| "loss": 1.0638, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.04479283314669653, | |
| "grad_norm": 5.431761741638184, | |
| "learning_rate": 6.892830393344403e-06, | |
| "loss": 1.2718, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04524076147816349, | |
| "grad_norm": 4.384571552276611, | |
| "learning_rate": 6.879649701454886e-06, | |
| "loss": 1.0594, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.04568868980963046, | |
| "grad_norm": 5.040534019470215, | |
| "learning_rate": 6.866340361924141e-06, | |
| "loss": 1.2255, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.04613661814109742, | |
| "grad_norm": 4.800682544708252, | |
| "learning_rate": 6.852902921846988e-06, | |
| "loss": 1.1093, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.04658454647256439, | |
| "grad_norm": 5.662080764770508, | |
| "learning_rate": 6.8393379335839565e-06, | |
| "loss": 1.2003, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.04703247480403135, | |
| "grad_norm": 3.93361234664917, | |
| "learning_rate": 6.825645954738586e-06, | |
| "loss": 1.0652, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.04703247480403135, | |
| "eval_loss": 1.2271474599838257, | |
| "eval_runtime": 51.5746, | |
| "eval_samples_per_second": 9.695, | |
| "eval_steps_per_second": 9.695, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.04748040313549832, | |
| "grad_norm": 4.918002605438232, | |
| "learning_rate": 6.811827548134495e-06, | |
| "loss": 1.156, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.047928331466965284, | |
| "grad_norm": 3.533487319946289, | |
| "learning_rate": 6.797883281792261e-06, | |
| "loss": 1.0533, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.04837625979843225, | |
| "grad_norm": 4.698348045349121, | |
| "learning_rate": 6.783813728906054e-06, | |
| "loss": 1.2621, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.048824188129899214, | |
| "grad_norm": 3.90852427482605, | |
| "learning_rate": 6.769619467820086e-06, | |
| "loss": 1.0754, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.04927211646136618, | |
| "grad_norm": 6.924786567687988, | |
| "learning_rate": 6.755301082004838e-06, | |
| "loss": 1.0617, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.049720044792833144, | |
| "grad_norm": 5.685960292816162, | |
| "learning_rate": 6.740859160033068e-06, | |
| "loss": 1.2185, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.05016797312430011, | |
| "grad_norm": 5.533092975616455, | |
| "learning_rate": 6.726294295555623e-06, | |
| "loss": 1.0583, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.050615901455767075, | |
| "grad_norm": 4.5029988288879395, | |
| "learning_rate": 6.711607087277034e-06, | |
| "loss": 1.1781, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.05106382978723404, | |
| "grad_norm": 3.2203736305236816, | |
| "learning_rate": 6.69679813893091e-06, | |
| "loss": 1.151, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.051511758118701005, | |
| "grad_norm": 6.602795600891113, | |
| "learning_rate": 6.681868059255113e-06, | |
| "loss": 1.1373, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.05195968645016797, | |
| "grad_norm": 3.071552038192749, | |
| "learning_rate": 6.666817461966741e-06, | |
| "loss": 1.1554, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.052407614781634936, | |
| "grad_norm": 5.886751174926758, | |
| "learning_rate": 6.651646965736902e-06, | |
| "loss": 1.1328, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.0528555431131019, | |
| "grad_norm": 4.323307991027832, | |
| "learning_rate": 6.636357194165274e-06, | |
| "loss": 1.1535, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.053303471444568866, | |
| "grad_norm": 4.585876941680908, | |
| "learning_rate": 6.620948775754481e-06, | |
| "loss": 1.1636, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.05375139977603583, | |
| "grad_norm": 3.9351437091827393, | |
| "learning_rate": 6.605422343884255e-06, | |
| "loss": 1.2689, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.05375139977603583, | |
| "eval_loss": 1.2224195003509521, | |
| "eval_runtime": 51.5936, | |
| "eval_samples_per_second": 9.691, | |
| "eval_steps_per_second": 9.691, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.054199328107502796, | |
| "grad_norm": 3.1242146492004395, | |
| "learning_rate": 6.589778536785396e-06, | |
| "loss": 1.2646, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.05464725643896976, | |
| "grad_norm": 3.1645703315734863, | |
| "learning_rate": 6.5740179975135426e-06, | |
| "loss": 0.9831, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.05509518477043673, | |
| "grad_norm": 6.550941467285156, | |
| "learning_rate": 6.5581413739227314e-06, | |
| "loss": 1.1777, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.05554311310190369, | |
| "grad_norm": 17.51181983947754, | |
| "learning_rate": 6.542149318638777e-06, | |
| "loss": 1.0765, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.055991041433370664, | |
| "grad_norm": 6.8737664222717285, | |
| "learning_rate": 6.526042489032434e-06, | |
| "loss": 1.0107, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.05643896976483763, | |
| "grad_norm": 3.5256145000457764, | |
| "learning_rate": 6.509821547192383e-06, | |
| "loss": 1.1973, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.056886898096304594, | |
| "grad_norm": 5.974047660827637, | |
| "learning_rate": 6.493487159898006e-06, | |
| "loss": 1.2409, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.05733482642777156, | |
| "grad_norm": 3.98787522315979, | |
| "learning_rate": 6.477039998591991e-06, | |
| "loss": 1.3272, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.057782754759238525, | |
| "grad_norm": 5.225778102874756, | |
| "learning_rate": 6.460480739352719e-06, | |
| "loss": 1.2937, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.05823068309070549, | |
| "grad_norm": 3.719729423522949, | |
| "learning_rate": 6.4438100628664795e-06, | |
| "loss": 1.0965, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.058678611422172455, | |
| "grad_norm": 2.8820245265960693, | |
| "learning_rate": 6.4270286543994874e-06, | |
| "loss": 1.2178, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.05912653975363942, | |
| "grad_norm": 3.031202793121338, | |
| "learning_rate": 6.410137203769718e-06, | |
| "loss": 1.354, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.059574468085106386, | |
| "grad_norm": 3.010680675506592, | |
| "learning_rate": 6.393136405318545e-06, | |
| "loss": 1.185, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.06002239641657335, | |
| "grad_norm": 3.756014823913574, | |
| "learning_rate": 6.376026957882207e-06, | |
| "loss": 1.1636, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.060470324748040316, | |
| "grad_norm": 4.391636848449707, | |
| "learning_rate": 6.3588095647630754e-06, | |
| "loss": 1.2252, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.060470324748040316, | |
| "eval_loss": 1.222408652305603, | |
| "eval_runtime": 51.5211, | |
| "eval_samples_per_second": 9.705, | |
| "eval_steps_per_second": 9.705, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.06091825307950728, | |
| "grad_norm": 3.5359737873077393, | |
| "learning_rate": 6.341484933700744e-06, | |
| "loss": 1.0688, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.061366181410974247, | |
| "grad_norm": 4.412395477294922, | |
| "learning_rate": 6.32405377684294e-06, | |
| "loss": 1.1889, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.06181410974244121, | |
| "grad_norm": 7.099231719970703, | |
| "learning_rate": 6.306516810716249e-06, | |
| "loss": 1.0922, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.06226203807390818, | |
| "grad_norm": 3.257270097732544, | |
| "learning_rate": 6.288874756196662e-06, | |
| "loss": 1.2291, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.06270996640537514, | |
| "grad_norm": 3.6133875846862793, | |
| "learning_rate": 6.271128338479939e-06, | |
| "loss": 1.0567, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "grad_norm": 4.996825695037842, | |
| "learning_rate": 6.253278287051806e-06, | |
| "loss": 1.1242, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.06360582306830907, | |
| "grad_norm": 5.642391204833984, | |
| "learning_rate": 6.235325335657962e-06, | |
| "loss": 1.1998, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.06405375139977604, | |
| "grad_norm": 4.652320384979248, | |
| "learning_rate": 6.217270222273923e-06, | |
| "loss": 1.0647, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.064501679731243, | |
| "grad_norm": 8.814513206481934, | |
| "learning_rate": 6.1991136890746825e-06, | |
| "loss": 0.97, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.06494960806270997, | |
| "grad_norm": 4.535324573516846, | |
| "learning_rate": 6.180856482404208e-06, | |
| "loss": 1.0829, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.06539753639417693, | |
| "grad_norm": 5.13389778137207, | |
| "learning_rate": 6.162499352744754e-06, | |
| "loss": 1.3333, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.0658454647256439, | |
| "grad_norm": 4.871939182281494, | |
| "learning_rate": 6.144043054686022e-06, | |
| "loss": 1.1397, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.06629339305711086, | |
| "grad_norm": 3.31581449508667, | |
| "learning_rate": 6.125488346894139e-06, | |
| "loss": 1.0983, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.06674132138857783, | |
| "grad_norm": 6.067586898803711, | |
| "learning_rate": 6.106835992080464e-06, | |
| "loss": 1.0931, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.0671892497200448, | |
| "grad_norm": 4.4560465812683105, | |
| "learning_rate": 6.088086756970252e-06, | |
| "loss": 1.0743, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.0671892497200448, | |
| "eval_loss": 1.21743643283844, | |
| "eval_runtime": 51.7437, | |
| "eval_samples_per_second": 9.663, | |
| "eval_steps_per_second": 9.663, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.06763717805151176, | |
| "grad_norm": 6.724518775939941, | |
| "learning_rate": 6.0692414122711184e-06, | |
| "loss": 1.2655, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "grad_norm": 4.3255085945129395, | |
| "learning_rate": 6.050300732641376e-06, | |
| "loss": 1.0058, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.06853303471444569, | |
| "grad_norm": 2.7948145866394043, | |
| "learning_rate": 6.0312654966581755e-06, | |
| "loss": 1.1331, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.06898096304591265, | |
| "grad_norm": 4.223801612854004, | |
| "learning_rate": 6.012136486785512e-06, | |
| "loss": 0.9267, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.06942889137737962, | |
| "grad_norm": 8.328617095947266, | |
| "learning_rate": 5.992914489342061e-06, | |
| "loss": 1.0601, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.06987681970884659, | |
| "grad_norm": 3.9401023387908936, | |
| "learning_rate": 5.9736002944688474e-06, | |
| "loss": 1.1296, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.07032474804031355, | |
| "grad_norm": 4.462929725646973, | |
| "learning_rate": 5.954194696096775e-06, | |
| "loss": 1.1266, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.07077267637178052, | |
| "grad_norm": 9.879998207092285, | |
| "learning_rate": 5.9346984919139865e-06, | |
| "loss": 1.0835, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.07122060470324748, | |
| "grad_norm": 4.088196277618408, | |
| "learning_rate": 5.9151124833330745e-06, | |
| "loss": 1.1256, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.07166853303471445, | |
| "grad_norm": 6.066174030303955, | |
| "learning_rate": 5.895437475458137e-06, | |
| "loss": 1.2295, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.07211646136618141, | |
| "grad_norm": 4.754509449005127, | |
| "learning_rate": 5.875674277051688e-06, | |
| "loss": 1.1676, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.07256438969764838, | |
| "grad_norm": 3.898282289505005, | |
| "learning_rate": 5.855823700501406e-06, | |
| "loss": 1.2583, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.07301231802911534, | |
| "grad_norm": 5.35301399230957, | |
| "learning_rate": 5.835886561786744e-06, | |
| "loss": 1.3667, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.07346024636058231, | |
| "grad_norm": 6.24777889251709, | |
| "learning_rate": 5.815863680445385e-06, | |
| "loss": 1.1099, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.07390817469204927, | |
| "grad_norm": 3.7771286964416504, | |
| "learning_rate": 5.795755879539558e-06, | |
| "loss": 0.9985, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.07390817469204927, | |
| "eval_loss": 1.2118867635726929, | |
| "eval_runtime": 51.6701, | |
| "eval_samples_per_second": 9.677, | |
| "eval_steps_per_second": 9.677, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.07435610302351624, | |
| "grad_norm": 4.368626117706299, | |
| "learning_rate": 5.775563985622202e-06, | |
| "loss": 1.1, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.0748040313549832, | |
| "grad_norm": 6.341384410858154, | |
| "learning_rate": 5.755288828702987e-06, | |
| "loss": 1.0292, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.07525195968645017, | |
| "grad_norm": 5.869757652282715, | |
| "learning_rate": 5.734931242214204e-06, | |
| "loss": 1.0937, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.07569988801791713, | |
| "grad_norm": 4.857089042663574, | |
| "learning_rate": 5.7144920629764955e-06, | |
| "loss": 1.0987, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.0761478163493841, | |
| "grad_norm": 5.114626884460449, | |
| "learning_rate": 5.693972131164471e-06, | |
| "loss": 0.9623, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.07659574468085106, | |
| "grad_norm": 5.152310371398926, | |
| "learning_rate": 5.673372290272149e-06, | |
| "loss": 1.1423, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.07704367301231803, | |
| "grad_norm": 3.8204965591430664, | |
| "learning_rate": 5.652693387078309e-06, | |
| "loss": 1.0523, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.077491601343785, | |
| "grad_norm": 3.0346767902374268, | |
| "learning_rate": 5.631936271611667e-06, | |
| "loss": 1.0483, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.07793952967525196, | |
| "grad_norm": 4.436351299285889, | |
| "learning_rate": 5.611101797115939e-06, | |
| "loss": 1.0144, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.07838745800671892, | |
| "grad_norm": 5.614783763885498, | |
| "learning_rate": 5.5901908200147685e-06, | |
| "loss": 1.078, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.07883538633818589, | |
| "grad_norm": 4.0426926612854, | |
| "learning_rate": 5.56920419987652e-06, | |
| "loss": 1.2628, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.07928331466965285, | |
| "grad_norm": 5.30089807510376, | |
| "learning_rate": 5.5481427993789534e-06, | |
| "loss": 1.1257, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.07973124300111982, | |
| "grad_norm": 3.5508739948272705, | |
| "learning_rate": 5.527007484273746e-06, | |
| "loss": 1.0355, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.08017917133258678, | |
| "grad_norm": 4.027277946472168, | |
| "learning_rate": 5.5057991233509225e-06, | |
| "loss": 0.9196, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.08062709966405375, | |
| "grad_norm": 7.427858352661133, | |
| "learning_rate": 5.484518588403134e-06, | |
| "loss": 1.1913, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.08062709966405375, | |
| "eval_loss": 1.2111696004867554, | |
| "eval_runtime": 51.6854, | |
| "eval_samples_per_second": 9.674, | |
| "eval_steps_per_second": 9.674, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.08107502799552072, | |
| "grad_norm": 6.3730597496032715, | |
| "learning_rate": 5.463166754189819e-06, | |
| "loss": 1.171, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.08152295632698768, | |
| "grad_norm": 5.194447994232178, | |
| "learning_rate": 5.441744498401255e-06, | |
| "loss": 1.2202, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.08197088465845465, | |
| "grad_norm": 4.3045454025268555, | |
| "learning_rate": 5.4202527016224725e-06, | |
| "loss": 1.1318, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.08241881298992161, | |
| "grad_norm": 5.316900253295898, | |
| "learning_rate": 5.398692247297059e-06, | |
| "loss": 1.2107, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.08286674132138858, | |
| "grad_norm": 8.284939765930176, | |
| "learning_rate": 5.377064021690844e-06, | |
| "loss": 1.1683, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.08331466965285554, | |
| "grad_norm": 4.051226615905762, | |
| "learning_rate": 5.355368913855472e-06, | |
| "loss": 1.2974, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.0837625979843225, | |
| "grad_norm": 5.353118896484375, | |
| "learning_rate": 5.333607815591851e-06, | |
| "loss": 1.235, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 5.097784996032715, | |
| "learning_rate": 5.311781621413497e-06, | |
| "loss": 1.0172, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.08465845464725644, | |
| "grad_norm": 3.437659978866577, | |
| "learning_rate": 5.289891228509769e-06, | |
| "loss": 1.0104, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.0851063829787234, | |
| "grad_norm": 4.631069660186768, | |
| "learning_rate": 5.267937536708977e-06, | |
| "loss": 1.0368, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.08555431131019037, | |
| "grad_norm": 5.044907569885254, | |
| "learning_rate": 5.245921448441407e-06, | |
| "loss": 1.0732, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.08600223964165733, | |
| "grad_norm": 3.2756667137145996, | |
| "learning_rate": 5.223843868702214e-06, | |
| "loss": 1.2815, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.0864501679731243, | |
| "grad_norm": 5.061473369598389, | |
| "learning_rate": 5.201705705014231e-06, | |
| "loss": 1.1059, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.08689809630459126, | |
| "grad_norm": 4.924319744110107, | |
| "learning_rate": 5.1795078673906575e-06, | |
| "loss": 1.0561, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.08734602463605823, | |
| "grad_norm": 4.019739627838135, | |
| "learning_rate": 5.1572512682976546e-06, | |
| "loss": 0.9889, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.08734602463605823, | |
| "eval_loss": 1.2077045440673828, | |
| "eval_runtime": 51.7283, | |
| "eval_samples_per_second": 9.666, | |
| "eval_steps_per_second": 9.666, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.0877939529675252, | |
| "grad_norm": 6.297740459442139, | |
| "learning_rate": 5.134936822616837e-06, | |
| "loss": 1.1664, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.08824188129899216, | |
| "grad_norm": 5.478749752044678, | |
| "learning_rate": 5.112565447607669e-06, | |
| "loss": 1.2503, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.08868980963045912, | |
| "grad_norm": 4.692316055297852, | |
| "learning_rate": 5.090138062869755e-06, | |
| "loss": 1.1421, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.08913773796192609, | |
| "grad_norm": 3.5623536109924316, | |
| "learning_rate": 5.067655590305036e-06, | |
| "loss": 1.1203, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.08958566629339305, | |
| "grad_norm": 6.875621318817139, | |
| "learning_rate": 5.045118954079904e-06, | |
| "loss": 1.1348, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.09003359462486002, | |
| "grad_norm": 5.2604756355285645, | |
| "learning_rate": 5.022529080587205e-06, | |
| "loss": 1.0326, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.09048152295632698, | |
| "grad_norm": 5.012307643890381, | |
| "learning_rate": 4.999886898408157e-06, | |
| "loss": 1.12, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.09092945128779395, | |
| "grad_norm": 5.246688365936279, | |
| "learning_rate": 4.977193338274189e-06, | |
| "loss": 1.1164, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.09137737961926092, | |
| "grad_norm": 3.9779398441314697, | |
| "learning_rate": 4.954449333028672e-06, | |
| "loss": 1.0607, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.09182530795072788, | |
| "grad_norm": 5.392056465148926, | |
| "learning_rate": 4.931655817588579e-06, | |
| "loss": 1.1102, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.09227323628219485, | |
| "grad_norm": 5.144470691680908, | |
| "learning_rate": 4.9088137289060535e-06, | |
| "loss": 1.0649, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.09272116461366181, | |
| "grad_norm": 3.7060792446136475, | |
| "learning_rate": 4.885924005929896e-06, | |
| "loss": 1.0718, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.09316909294512878, | |
| "grad_norm": 3.357794761657715, | |
| "learning_rate": 4.862987589566965e-06, | |
| "loss": 1.1003, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.09361702127659574, | |
| "grad_norm": 5.704718589782715, | |
| "learning_rate": 4.840005422643503e-06, | |
| "loss": 1.2042, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.0940649496080627, | |
| "grad_norm": 5.481514930725098, | |
| "learning_rate": 4.816978449866372e-06, | |
| "loss": 1.0777, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.0940649496080627, | |
| "eval_loss": 1.2093305587768555, | |
| "eval_runtime": 51.7975, | |
| "eval_samples_per_second": 9.653, | |
| "eval_steps_per_second": 9.653, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.09451287793952967, | |
| "grad_norm": 5.508385181427002, | |
| "learning_rate": 4.793907617784238e-06, | |
| "loss": 1.5375, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.09496080627099664, | |
| "grad_norm": 4.192409515380859, | |
| "learning_rate": 4.770793874748642e-06, | |
| "loss": 0.9964, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.0954087346024636, | |
| "grad_norm": 4.068387508392334, | |
| "learning_rate": 4.747638170875032e-06, | |
| "loss": 0.9244, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.09585666293393057, | |
| "grad_norm": 2.513946771621704, | |
| "learning_rate": 4.724441458003699e-06, | |
| "loss": 1.1329, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.09630459126539753, | |
| "grad_norm": 4.470638275146484, | |
| "learning_rate": 4.701204689660653e-06, | |
| "loss": 1.0299, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.0967525195968645, | |
| "grad_norm": 5.644805908203125, | |
| "learning_rate": 4.67792882101843e-06, | |
| "loss": 1.2654, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.09720044792833146, | |
| "grad_norm": 5.1912736892700195, | |
| "learning_rate": 4.654614808856823e-06, | |
| "loss": 1.2265, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.09764837625979843, | |
| "grad_norm": 11.092533111572266, | |
| "learning_rate": 4.631263611523557e-06, | |
| "loss": 1.2182, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.09809630459126539, | |
| "grad_norm": 4.138496398925781, | |
| "learning_rate": 4.607876188894896e-06, | |
| "loss": 1.2283, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.09854423292273236, | |
| "grad_norm": 5.229914665222168, | |
| "learning_rate": 4.58445350233618e-06, | |
| "loss": 1.1319, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.09899216125419932, | |
| "grad_norm": 4.059961318969727, | |
| "learning_rate": 4.560996514662314e-06, | |
| "loss": 1.0411, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.09944008958566629, | |
| "grad_norm": 4.80086088180542, | |
| "learning_rate": 4.5375061900981855e-06, | |
| "loss": 1.23, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.09988801791713325, | |
| "grad_norm": 5.166756629943848, | |
| "learning_rate": 4.513983494239034e-06, | |
| "loss": 1.219, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.10033594624860022, | |
| "grad_norm": 5.53660249710083, | |
| "learning_rate": 4.490429394010752e-06, | |
| "loss": 1.1245, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.10078387458006718, | |
| "grad_norm": 2.9756040573120117, | |
| "learning_rate": 4.466844857630147e-06, | |
| "loss": 1.1395, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.10078387458006718, | |
| "eval_loss": 1.2089135646820068, | |
| "eval_runtime": 51.6342, | |
| "eval_samples_per_second": 9.684, | |
| "eval_steps_per_second": 9.684, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.10123180291153415, | |
| "grad_norm": 3.644266128540039, | |
| "learning_rate": 4.443230854565133e-06, | |
| "loss": 1.0985, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.10167973124300111, | |
| "grad_norm": 4.662050724029541, | |
| "learning_rate": 4.4195883554948885e-06, | |
| "loss": 1.3397, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.10212765957446808, | |
| "grad_norm": 5.3237385749816895, | |
| "learning_rate": 4.3959183322699466e-06, | |
| "loss": 1.1351, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.10257558790593505, | |
| "grad_norm": 4.3604207038879395, | |
| "learning_rate": 4.372221757872255e-06, | |
| "loss": 1.1208, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.10302351623740201, | |
| "grad_norm": 3.731410264968872, | |
| "learning_rate": 4.3484996063751725e-06, | |
| "loss": 1.1584, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.10347144456886898, | |
| "grad_norm": 4.031397342681885, | |
| "learning_rate": 4.324752852903435e-06, | |
| "loss": 0.9656, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.10391937290033594, | |
| "grad_norm": 3.564148187637329, | |
| "learning_rate": 4.300982473593068e-06, | |
| "loss": 1.0031, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.1043673012318029, | |
| "grad_norm": 5.459331035614014, | |
| "learning_rate": 4.277189445551261e-06, | |
| "loss": 1.0037, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.10481522956326987, | |
| "grad_norm": 4.870905876159668, | |
| "learning_rate": 4.253374746816209e-06, | |
| "loss": 0.9615, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 5.284097671508789, | |
| "learning_rate": 4.229539356316898e-06, | |
| "loss": 1.3278, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.1057110862262038, | |
| "grad_norm": 5.323864459991455, | |
| "learning_rate": 4.205684253832877e-06, | |
| "loss": 1.1903, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.10615901455767077, | |
| "grad_norm": 7.844208717346191, | |
| "learning_rate": 4.1818104199539735e-06, | |
| "loss": 1.056, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.10660694288913773, | |
| "grad_norm": 4.325316905975342, | |
| "learning_rate": 4.1579188360399916e-06, | |
| "loss": 1.2431, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.1070548712206047, | |
| "grad_norm": 3.5362424850463867, | |
| "learning_rate": 4.134010484180368e-06, | |
| "loss": 1.1804, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.10750279955207166, | |
| "grad_norm": 3.2404041290283203, | |
| "learning_rate": 4.110086347153807e-06, | |
| "loss": 1.1556, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.10750279955207166, | |
| "eval_loss": 1.2038679122924805, | |
| "eval_runtime": 51.7303, | |
| "eval_samples_per_second": 9.666, | |
| "eval_steps_per_second": 9.666, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.10795072788353863, | |
| "grad_norm": 3.8270246982574463, | |
| "learning_rate": 4.0861474083878765e-06, | |
| "loss": 1.0918, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.10839865621500559, | |
| "grad_norm": 5.627485752105713, | |
| "learning_rate": 4.062194651918585e-06, | |
| "loss": 1.257, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.10884658454647256, | |
| "grad_norm": 4.910660743713379, | |
| "learning_rate": 4.0382290623499384e-06, | |
| "loss": 1.2748, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.10929451287793952, | |
| "grad_norm": 2.3609941005706787, | |
| "learning_rate": 4.014251624813453e-06, | |
| "loss": 0.9422, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.10974244120940649, | |
| "grad_norm": 3.063828706741333, | |
| "learning_rate": 3.990263324927675e-06, | |
| "loss": 1.1829, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.11019036954087345, | |
| "grad_norm": 2.658452033996582, | |
| "learning_rate": 3.966265148757655e-06, | |
| "loss": 1.0062, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.11063829787234042, | |
| "grad_norm": 6.130062103271484, | |
| "learning_rate": 3.9422580827744224e-06, | |
| "loss": 1.1504, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.11108622620380738, | |
| "grad_norm": 3.3496034145355225, | |
| "learning_rate": 3.9182431138144315e-06, | |
| "loss": 0.8731, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.11153415453527436, | |
| "grad_norm": 3.8455569744110107, | |
| "learning_rate": 3.894221229038995e-06, | |
| "loss": 1.0125, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.11198208286674133, | |
| "grad_norm": 4.499962329864502, | |
| "learning_rate": 3.870193415893709e-06, | |
| "loss": 1.0228, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1124300111982083, | |
| "grad_norm": 6.230105876922607, | |
| "learning_rate": 3.846160662067859e-06, | |
| "loss": 1.1794, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.11287793952967526, | |
| "grad_norm": 7.316727638244629, | |
| "learning_rate": 3.8221239554538275e-06, | |
| "loss": 1.2728, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.11332586786114222, | |
| "grad_norm": 3.291714906692505, | |
| "learning_rate": 3.798084284106478e-06, | |
| "loss": 1.167, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.11377379619260919, | |
| "grad_norm": 5.075141429901123, | |
| "learning_rate": 3.7740426362025424e-06, | |
| "loss": 1.0547, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.11422172452407615, | |
| "grad_norm": 3.961540937423706, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 1.0713, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.11422172452407615, | |
| "eval_loss": 1.2046430110931396, | |
| "eval_runtime": 51.7175, | |
| "eval_samples_per_second": 9.668, | |
| "eval_steps_per_second": 9.668, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.11466965285554312, | |
| "grad_norm": 6.124125003814697, | |
| "learning_rate": 3.7259573637974587e-06, | |
| "loss": 1.0568, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.11511758118701008, | |
| "grad_norm": 4.3748602867126465, | |
| "learning_rate": 3.701915715893523e-06, | |
| "loss": 1.4124, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.11556550951847705, | |
| "grad_norm": 7.382061004638672, | |
| "learning_rate": 3.677876044546174e-06, | |
| "loss": 1.1357, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.11601343784994401, | |
| "grad_norm": 4.097735404968262, | |
| "learning_rate": 3.6538393379321427e-06, | |
| "loss": 1.0885, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.11646136618141098, | |
| "grad_norm": 5.039736270904541, | |
| "learning_rate": 3.6298065841062934e-06, | |
| "loss": 1.107, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.11690929451287795, | |
| "grad_norm": 4.383152008056641, | |
| "learning_rate": 3.6057787709610064e-06, | |
| "loss": 1.1695, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.11735722284434491, | |
| "grad_norm": 4.900496482849121, | |
| "learning_rate": 3.5817568861855708e-06, | |
| "loss": 1.1107, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.11780515117581188, | |
| "grad_norm": 6.267992973327637, | |
| "learning_rate": 3.557741917225579e-06, | |
| "loss": 1.1896, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.11825307950727884, | |
| "grad_norm": 3.8060693740844727, | |
| "learning_rate": 3.5337348512423468e-06, | |
| "loss": 1.2245, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.1187010078387458, | |
| "grad_norm": 3.5068161487579346, | |
| "learning_rate": 3.5097366750723275e-06, | |
| "loss": 1.0629, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.11914893617021277, | |
| "grad_norm": 4.6765360832214355, | |
| "learning_rate": 3.4857483751865478e-06, | |
| "loss": 1.1783, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.11959686450167974, | |
| "grad_norm": 7.864380836486816, | |
| "learning_rate": 3.461770937650064e-06, | |
| "loss": 1.0683, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.1200447928331467, | |
| "grad_norm": 3.138843297958374, | |
| "learning_rate": 3.437805348081416e-06, | |
| "loss": 0.9814, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.12049272116461367, | |
| "grad_norm": 5.134324550628662, | |
| "learning_rate": 3.413852591612125e-06, | |
| "loss": 1.1631, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.12094064949608063, | |
| "grad_norm": 4.688596725463867, | |
| "learning_rate": 3.389913652846194e-06, | |
| "loss": 1.0644, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.12094064949608063, | |
| "eval_loss": 1.2033374309539795, | |
| "eval_runtime": 51.6099, | |
| "eval_samples_per_second": 9.688, | |
| "eval_steps_per_second": 9.688, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.1213885778275476, | |
| "grad_norm": 4.218849182128906, | |
| "learning_rate": 3.365989515819633e-06, | |
| "loss": 1.1395, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.12183650615901456, | |
| "grad_norm": 5.043267726898193, | |
| "learning_rate": 3.34208116396001e-06, | |
| "loss": 1.2327, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.12228443449048153, | |
| "grad_norm": 7.991638660430908, | |
| "learning_rate": 3.318189580046028e-06, | |
| "loss": 1.0106, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.12273236282194849, | |
| "grad_norm": 4.103755474090576, | |
| "learning_rate": 3.294315746167124e-06, | |
| "loss": 0.9751, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.12318029115341546, | |
| "grad_norm": 4.224274635314941, | |
| "learning_rate": 3.2704606436831023e-06, | |
| "loss": 1.1427, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.12362821948488242, | |
| "grad_norm": 5.190283298492432, | |
| "learning_rate": 3.2466252531837934e-06, | |
| "loss": 1.1758, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.12407614781634939, | |
| "grad_norm": 6.470210075378418, | |
| "learning_rate": 3.2228105544487405e-06, | |
| "loss": 1.2584, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.12452407614781635, | |
| "grad_norm": 4.470674514770508, | |
| "learning_rate": 3.1990175264069333e-06, | |
| "loss": 1.0279, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.12497200447928332, | |
| "grad_norm": 4.63865327835083, | |
| "learning_rate": 3.1752471470965653e-06, | |
| "loss": 1.2431, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.12541993281075028, | |
| "grad_norm": 5.2822089195251465, | |
| "learning_rate": 3.151500393624829e-06, | |
| "loss": 1.0206, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.12586786114221724, | |
| "grad_norm": 3.3929495811462402, | |
| "learning_rate": 3.127778242127747e-06, | |
| "loss": 0.9654, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": 3.526858329772949, | |
| "learning_rate": 3.104081667730055e-06, | |
| "loss": 1.0832, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.12676371780515117, | |
| "grad_norm": 5.531039714813232, | |
| "learning_rate": 3.0804116445051133e-06, | |
| "loss": 1.1649, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.12721164613661815, | |
| "grad_norm": 5.811004161834717, | |
| "learning_rate": 3.0567691454348674e-06, | |
| "loss": 1.095, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 4.319146633148193, | |
| "learning_rate": 3.033155142369855e-06, | |
| "loss": 0.9761, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "eval_loss": 1.2028086185455322, | |
| "eval_runtime": 51.6383, | |
| "eval_samples_per_second": 9.683, | |
| "eval_steps_per_second": 9.683, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.12810750279955208, | |
| "grad_norm": 5.54340124130249, | |
| "learning_rate": 3.009570605989249e-06, | |
| "loss": 0.999, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.12855543113101903, | |
| "grad_norm": 3.859863758087158, | |
| "learning_rate": 2.986016505760967e-06, | |
| "loss": 1.025, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.129003359462486, | |
| "grad_norm": 5.119099140167236, | |
| "learning_rate": 2.962493809901815e-06, | |
| "loss": 1.3963, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.12945128779395296, | |
| "grad_norm": 5.8379130363464355, | |
| "learning_rate": 2.9390034853376875e-06, | |
| "loss": 1.0822, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.12989921612541994, | |
| "grad_norm": 3.261016845703125, | |
| "learning_rate": 2.9155464976638217e-06, | |
| "loss": 1.0526, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.1303471444568869, | |
| "grad_norm": 3.678527355194092, | |
| "learning_rate": 2.8921238111051057e-06, | |
| "loss": 1.1167, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.13079507278835387, | |
| "grad_norm": 4.787365436553955, | |
| "learning_rate": 2.8687363884764434e-06, | |
| "loss": 1.0829, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.13124300111982082, | |
| "grad_norm": 3.475607395172119, | |
| "learning_rate": 2.8453851911431783e-06, | |
| "loss": 1.0801, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.1316909294512878, | |
| "grad_norm": 6.456125736236572, | |
| "learning_rate": 2.822071178981572e-06, | |
| "loss": 1.1287, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.13213885778275475, | |
| "grad_norm": 3.778585910797119, | |
| "learning_rate": 2.7987953103393484e-06, | |
| "loss": 1.1359, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.13258678611422173, | |
| "grad_norm": 3.37793231010437, | |
| "learning_rate": 2.7755585419963026e-06, | |
| "loss": 1.0584, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.13303471444568868, | |
| "grad_norm": 5.2485575675964355, | |
| "learning_rate": 2.7523618291249687e-06, | |
| "loss": 1.2037, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.13348264277715566, | |
| "grad_norm": 4.524936676025391, | |
| "learning_rate": 2.729206125251359e-06, | |
| "loss": 0.9778, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.1339305711086226, | |
| "grad_norm": 5.820756912231445, | |
| "learning_rate": 2.7060923822157638e-06, | |
| "loss": 1.0351, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.1343784994400896, | |
| "grad_norm": 5.031400680541992, | |
| "learning_rate": 2.6830215501336288e-06, | |
| "loss": 1.1926, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.1343784994400896, | |
| "eval_loss": 1.199351191520691, | |
| "eval_runtime": 51.5688, | |
| "eval_samples_per_second": 9.696, | |
| "eval_steps_per_second": 9.696, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.13482642777155654, | |
| "grad_norm": 4.307104587554932, | |
| "learning_rate": 2.6599945773564997e-06, | |
| "loss": 1.1743, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.13527435610302352, | |
| "grad_norm": 4.9457221031188965, | |
| "learning_rate": 2.6370124104330357e-06, | |
| "loss": 1.1287, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.13572228443449047, | |
| "grad_norm": 3.17401385307312, | |
| "learning_rate": 2.614075994070105e-06, | |
| "loss": 1.1686, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": 6.098177433013916, | |
| "learning_rate": 2.591186271093948e-06, | |
| "loss": 1.1546, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.1366181410974244, | |
| "grad_norm": 4.12905216217041, | |
| "learning_rate": 2.568344182411423e-06, | |
| "loss": 1.0909, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.13706606942889138, | |
| "grad_norm": 4.946627616882324, | |
| "learning_rate": 2.5455506669713293e-06, | |
| "loss": 1.2223, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.13751399776035833, | |
| "grad_norm": 4.25789737701416, | |
| "learning_rate": 2.522806661725812e-06, | |
| "loss": 1.0383, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.1379619260918253, | |
| "grad_norm": 6.536715030670166, | |
| "learning_rate": 2.5001131015918444e-06, | |
| "loss": 0.9992, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.13840985442329226, | |
| "grad_norm": 5.861030578613281, | |
| "learning_rate": 2.4774709194127973e-06, | |
| "loss": 1.1678, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.13885778275475924, | |
| "grad_norm": 4.58046293258667, | |
| "learning_rate": 2.4548810459200973e-06, | |
| "loss": 1.2545, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.1393057110862262, | |
| "grad_norm": 6.048022270202637, | |
| "learning_rate": 2.4323444096949647e-06, | |
| "loss": 1.0531, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.13975363941769317, | |
| "grad_norm": 5.86400842666626, | |
| "learning_rate": 2.409861937130248e-06, | |
| "loss": 1.1093, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.14020156774916012, | |
| "grad_norm": 3.7916102409362793, | |
| "learning_rate": 2.3874345523923327e-06, | |
| "loss": 1.1048, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.1406494960806271, | |
| "grad_norm": 4.009166717529297, | |
| "learning_rate": 2.3650631773831644e-06, | |
| "loss": 1.0198, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.14109742441209405, | |
| "grad_norm": 4.695572853088379, | |
| "learning_rate": 2.3427487317023477e-06, | |
| "loss": 1.1909, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.14109742441209405, | |
| "eval_loss": 1.1985480785369873, | |
| "eval_runtime": 51.6619, | |
| "eval_samples_per_second": 9.678, | |
| "eval_steps_per_second": 9.678, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.14154535274356103, | |
| "grad_norm": 5.317529201507568, | |
| "learning_rate": 2.320492132609344e-06, | |
| "loss": 1.084, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.14199328107502798, | |
| "grad_norm": 3.3507909774780273, | |
| "learning_rate": 2.2982942949857705e-06, | |
| "loss": 1.0169, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.14244120940649496, | |
| "grad_norm": 5.125346660614014, | |
| "learning_rate": 2.276156131297787e-06, | |
| "loss": 1.0202, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.1428891377379619, | |
| "grad_norm": 6.09945821762085, | |
| "learning_rate": 2.254078551558594e-06, | |
| "loss": 1.1235, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.1433370660694289, | |
| "grad_norm": 6.263647079467773, | |
| "learning_rate": 2.2320624632910232e-06, | |
| "loss": 1.1284, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.14378499440089584, | |
| "grad_norm": 6.879512310028076, | |
| "learning_rate": 2.210108771490233e-06, | |
| "loss": 1.0602, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.14423292273236282, | |
| "grad_norm": 3.726658582687378, | |
| "learning_rate": 2.1882183785865047e-06, | |
| "loss": 1.1038, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.14468085106382977, | |
| "grad_norm": 5.486456394195557, | |
| "learning_rate": 2.166392184408152e-06, | |
| "loss": 1.1794, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.14512877939529675, | |
| "grad_norm": 4.750957012176514, | |
| "learning_rate": 2.1446310861445306e-06, | |
| "loss": 0.9833, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.1455767077267637, | |
| "grad_norm": 3.6656692028045654, | |
| "learning_rate": 2.1229359783091576e-06, | |
| "loss": 1.0272, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.14602463605823068, | |
| "grad_norm": 3.691014528274536, | |
| "learning_rate": 2.1013077527029428e-06, | |
| "loss": 1.0861, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.14647256438969763, | |
| "grad_norm": 5.651008605957031, | |
| "learning_rate": 2.079747298377528e-06, | |
| "loss": 1.096, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.14692049272116461, | |
| "grad_norm": 4.2657318115234375, | |
| "learning_rate": 2.058255501598745e-06, | |
| "loss": 1.0871, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.14736842105263157, | |
| "grad_norm": 3.884568452835083, | |
| "learning_rate": 2.0368332458101814e-06, | |
| "loss": 1.0087, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.14781634938409854, | |
| "grad_norm": 3.191197395324707, | |
| "learning_rate": 2.015481411596869e-06, | |
| "loss": 1.1387, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.14781634938409854, | |
| "eval_loss": 1.1979233026504517, | |
| "eval_runtime": 51.7549, | |
| "eval_samples_per_second": 9.661, | |
| "eval_steps_per_second": 9.661, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.14826427771556552, | |
| "grad_norm": 6.709813594818115, | |
| "learning_rate": 1.9942008766490793e-06, | |
| "loss": 1.0685, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.14871220604703247, | |
| "grad_norm": 3.687634229660034, | |
| "learning_rate": 1.9729925157262554e-06, | |
| "loss": 1.1542, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.14916013437849945, | |
| "grad_norm": 3.637235403060913, | |
| "learning_rate": 1.9518572006210484e-06, | |
| "loss": 1.1365, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.1496080627099664, | |
| "grad_norm": 3.113184690475464, | |
| "learning_rate": 1.9307958001234794e-06, | |
| "loss": 1.0218, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.15005599104143338, | |
| "grad_norm": 4.447634220123291, | |
| "learning_rate": 1.9098091799852347e-06, | |
| "loss": 1.222, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.15050391937290034, | |
| "grad_norm": 3.8236501216888428, | |
| "learning_rate": 1.8888982028840636e-06, | |
| "loss": 1.2012, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.15095184770436731, | |
| "grad_norm": 5.108892440795898, | |
| "learning_rate": 1.8680637283883355e-06, | |
| "loss": 1.0181, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.15139977603583427, | |
| "grad_norm": 3.81886887550354, | |
| "learning_rate": 1.8473066129216927e-06, | |
| "loss": 1.125, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.15184770436730124, | |
| "grad_norm": 4.7799835205078125, | |
| "learning_rate": 1.8266277097278527e-06, | |
| "loss": 1.1038, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.1522956326987682, | |
| "grad_norm": 6.478558540344238, | |
| "learning_rate": 1.8060278688355313e-06, | |
| "loss": 0.9218, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.15274356103023518, | |
| "grad_norm": 4.482583522796631, | |
| "learning_rate": 1.7855079370235043e-06, | |
| "loss": 1.0629, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.15319148936170213, | |
| "grad_norm": 2.6053950786590576, | |
| "learning_rate": 1.7650687577857972e-06, | |
| "loss": 1.1975, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.1536394176931691, | |
| "grad_norm": 4.930041313171387, | |
| "learning_rate": 1.7447111712970138e-06, | |
| "loss": 1.0566, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.15408734602463606, | |
| "grad_norm": 4.492660045623779, | |
| "learning_rate": 1.7244360143778004e-06, | |
| "loss": 1.1441, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.15453527435610304, | |
| "grad_norm": 4.847555637359619, | |
| "learning_rate": 1.704244120460443e-06, | |
| "loss": 1.231, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.15453527435610304, | |
| "eval_loss": 1.198148488998413, | |
| "eval_runtime": 51.6757, | |
| "eval_samples_per_second": 9.676, | |
| "eval_steps_per_second": 9.676, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.15498320268757, | |
| "grad_norm": 5.320653438568115, | |
| "learning_rate": 1.6841363195546162e-06, | |
| "loss": 0.996, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.15543113101903697, | |
| "grad_norm": 4.333999156951904, | |
| "learning_rate": 1.6641134382132576e-06, | |
| "loss": 1.2536, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.15587905935050392, | |
| "grad_norm": 6.867399215698242, | |
| "learning_rate": 1.6441762994985947e-06, | |
| "loss": 1.1461, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.1563269876819709, | |
| "grad_norm": 3.2110917568206787, | |
| "learning_rate": 1.6243257229483141e-06, | |
| "loss": 1.1086, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.15677491601343785, | |
| "grad_norm": 3.345970630645752, | |
| "learning_rate": 1.6045625245418648e-06, | |
| "loss": 0.9485, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.15722284434490483, | |
| "grad_norm": 4.890392780303955, | |
| "learning_rate": 1.584887516666928e-06, | |
| "loss": 1.0968, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.15767077267637178, | |
| "grad_norm": 5.448171615600586, | |
| "learning_rate": 1.565301508086015e-06, | |
| "loss": 1.1305, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.15811870100783876, | |
| "grad_norm": 7.16267728805542, | |
| "learning_rate": 1.5458053039032263e-06, | |
| "loss": 1.2279, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.1585666293393057, | |
| "grad_norm": 5.2700018882751465, | |
| "learning_rate": 1.5263997055311536e-06, | |
| "loss": 1.0474, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.1590145576707727, | |
| "grad_norm": 5.955024719238281, | |
| "learning_rate": 1.5070855106579404e-06, | |
| "loss": 1.1283, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.15946248600223964, | |
| "grad_norm": 2.882784366607666, | |
| "learning_rate": 1.4878635132144885e-06, | |
| "loss": 0.9112, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.15991041433370662, | |
| "grad_norm": 4.2263875007629395, | |
| "learning_rate": 1.4687345033418258e-06, | |
| "loss": 1.1554, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.16035834266517357, | |
| "grad_norm": 4.622799396514893, | |
| "learning_rate": 1.4496992673586262e-06, | |
| "loss": 1.3423, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.16080627099664055, | |
| "grad_norm": 5.2950897216796875, | |
| "learning_rate": 1.4307585877288822e-06, | |
| "loss": 1.0494, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.1612541993281075, | |
| "grad_norm": 5.289889335632324, | |
| "learning_rate": 1.4119132430297496e-06, | |
| "loss": 1.1448, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.1612541993281075, | |
| "eval_loss": 1.1965739727020264, | |
| "eval_runtime": 51.7182, | |
| "eval_samples_per_second": 9.668, | |
| "eval_steps_per_second": 9.668, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.16170212765957448, | |
| "grad_norm": 6.415092468261719, | |
| "learning_rate": 1.3931640079195365e-06, | |
| "loss": 1.0204, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.16215005599104143, | |
| "grad_norm": 3.348160743713379, | |
| "learning_rate": 1.3745116531058645e-06, | |
| "loss": 1.1308, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.1625979843225084, | |
| "grad_norm": 6.698293209075928, | |
| "learning_rate": 1.3559569453139797e-06, | |
| "loss": 0.9401, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.16304591265397536, | |
| "grad_norm": 3.5045154094696045, | |
| "learning_rate": 1.3375006472552483e-06, | |
| "loss": 1.152, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.16349384098544234, | |
| "grad_norm": 4.656421661376953, | |
| "learning_rate": 1.3191435175957945e-06, | |
| "loss": 1.1775, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.1639417693169093, | |
| "grad_norm": 8.8998384475708, | |
| "learning_rate": 1.3008863109253174e-06, | |
| "loss": 1.0061, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.16438969764837627, | |
| "grad_norm": 3.5046370029449463, | |
| "learning_rate": 1.282729777726078e-06, | |
| "loss": 1.1871, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.16483762597984322, | |
| "grad_norm": 4.024252891540527, | |
| "learning_rate": 1.2646746643420392e-06, | |
| "loss": 1.2593, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.1652855543113102, | |
| "grad_norm": 4.861652851104736, | |
| "learning_rate": 1.2467217129481952e-06, | |
| "loss": 1.1068, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.16573348264277715, | |
| "grad_norm": 6.007284641265869, | |
| "learning_rate": 1.2288716615200617e-06, | |
| "loss": 1.0237, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.16618141097424413, | |
| "grad_norm": 4.506286144256592, | |
| "learning_rate": 1.2111252438033404e-06, | |
| "loss": 1.0827, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.16662933930571108, | |
| "grad_norm": 7.5774102210998535, | |
| "learning_rate": 1.1934831892837524e-06, | |
| "loss": 1.2481, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.16707726763717806, | |
| "grad_norm": 4.199349880218506, | |
| "learning_rate": 1.1759462231570618e-06, | |
| "loss": 1.1948, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.167525195968645, | |
| "grad_norm": 3.675760269165039, | |
| "learning_rate": 1.1585150662992578e-06, | |
| "loss": 0.8945, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.167973124300112, | |
| "grad_norm": 4.647981643676758, | |
| "learning_rate": 1.1411904352369262e-06, | |
| "loss": 1.0746, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.167973124300112, | |
| "eval_loss": 1.1958056688308716, | |
| "eval_runtime": 51.7591, | |
| "eval_samples_per_second": 9.66, | |
| "eval_steps_per_second": 9.66, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 2.354313611984253, | |
| "learning_rate": 1.1239730421177952e-06, | |
| "loss": 1.0362, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.16886898096304592, | |
| "grad_norm": 4.00113582611084, | |
| "learning_rate": 1.1068635946814569e-06, | |
| "loss": 1.0924, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.16931690929451287, | |
| "grad_norm": 3.765235185623169, | |
| "learning_rate": 1.0898627962302831e-06, | |
| "loss": 1.3452, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.16976483762597985, | |
| "grad_norm": 3.814605236053467, | |
| "learning_rate": 1.072971345600513e-06, | |
| "loss": 1.0048, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 3.447803020477295, | |
| "learning_rate": 1.056189937133522e-06, | |
| "loss": 1.149, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.17066069428891378, | |
| "grad_norm": 7.1337714195251465, | |
| "learning_rate": 1.0395192606472822e-06, | |
| "loss": 1.1497, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.17110862262038073, | |
| "grad_norm": 5.239931583404541, | |
| "learning_rate": 1.0229600014080101e-06, | |
| "loss": 0.9874, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.1715565509518477, | |
| "grad_norm": 3.4100687503814697, | |
| "learning_rate": 1.006512840101995e-06, | |
| "loss": 1.0393, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.17200447928331467, | |
| "grad_norm": 4.527777671813965, | |
| "learning_rate": 9.90178452807619e-07, | |
| "loss": 0.968, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.17245240761478164, | |
| "grad_norm": 3.7964625358581543, | |
| "learning_rate": 9.739575109675674e-07, | |
| "loss": 1.1207, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.1729003359462486, | |
| "grad_norm": 4.329505920410156, | |
| "learning_rate": 9.578506813612243e-07, | |
| "loss": 1.0924, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.17334826427771557, | |
| "grad_norm": 3.9827823638916016, | |
| "learning_rate": 9.418586260772695e-07, | |
| "loss": 1.0937, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.17379619260918253, | |
| "grad_norm": 4.150352954864502, | |
| "learning_rate": 9.259820024864594e-07, | |
| "loss": 1.2071, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.1742441209406495, | |
| "grad_norm": 2.648918867111206, | |
| "learning_rate": 9.102214632146059e-07, | |
| "loss": 1.1754, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.17469204927211646, | |
| "grad_norm": 5.348718166351318, | |
| "learning_rate": 8.94577656115746e-07, | |
| "loss": 1.1031, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.17469204927211646, | |
| "eval_loss": 1.1968835592269897, | |
| "eval_runtime": 51.6518, | |
| "eval_samples_per_second": 9.68, | |
| "eval_steps_per_second": 9.68, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.17513997760358344, | |
| "grad_norm": 6.799318313598633, | |
| "learning_rate": 8.790512242455198e-07, | |
| "loss": 1.1188, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.1755879059350504, | |
| "grad_norm": 4.05487060546875, | |
| "learning_rate": 8.636428058347274e-07, | |
| "loss": 1.3045, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.17603583426651737, | |
| "grad_norm": 4.513579845428467, | |
| "learning_rate": 8.483530342630993e-07, | |
| "loss": 1.2577, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.17648376259798432, | |
| "grad_norm": 7.971194267272949, | |
| "learning_rate": 8.331825380332599e-07, | |
| "loss": 1.1376, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.1769316909294513, | |
| "grad_norm": 3.740802764892578, | |
| "learning_rate": 8.181319407448884e-07, | |
| "loss": 1.1413, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.17737961926091825, | |
| "grad_norm": 3.431658983230591, | |
| "learning_rate": 8.032018610690914e-07, | |
| "loss": 1.0802, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.17782754759238523, | |
| "grad_norm": 3.8207449913024902, | |
| "learning_rate": 7.883929127229665e-07, | |
| "loss": 1.173, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.17827547592385218, | |
| "grad_norm": 3.088942289352417, | |
| "learning_rate": 7.737057044443793e-07, | |
| "loss": 1.1144, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.17872340425531916, | |
| "grad_norm": 3.705589532852173, | |
| "learning_rate": 7.591408399669337e-07, | |
| "loss": 1.2676, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.1791713325867861, | |
| "grad_norm": 4.925235271453857, | |
| "learning_rate": 7.446989179951632e-07, | |
| "loss": 1.0197, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1796192609182531, | |
| "grad_norm": 4.373708248138428, | |
| "learning_rate": 7.303805321799146e-07, | |
| "loss": 1.0041, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.18006718924972004, | |
| "grad_norm": 4.23321008682251, | |
| "learning_rate": 7.161862710939476e-07, | |
| "loss": 1.0504, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.18051511758118702, | |
| "grad_norm": 6.634941101074219, | |
| "learning_rate": 7.021167182077403e-07, | |
| "loss": 1.062, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.18096304591265397, | |
| "grad_norm": 12.015007972717285, | |
| "learning_rate": 6.881724518655049e-07, | |
| "loss": 1.3095, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.18141097424412095, | |
| "grad_norm": 5.376244068145752, | |
| "learning_rate": 6.743540452614152e-07, | |
| "loss": 1.0552, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.18141097424412095, | |
| "eval_loss": 1.1952238082885742, | |
| "eval_runtime": 51.6946, | |
| "eval_samples_per_second": 9.672, | |
| "eval_steps_per_second": 9.672, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.1818589025755879, | |
| "grad_norm": 5.1148858070373535, | |
| "learning_rate": 6.606620664160438e-07, | |
| "loss": 1.0796, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.18230683090705488, | |
| "grad_norm": 3.497487783432007, | |
| "learning_rate": 6.470970781530139e-07, | |
| "loss": 1.0996, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.18275475923852183, | |
| "grad_norm": 4.02069616317749, | |
| "learning_rate": 6.336596380758604e-07, | |
| "loss": 1.18, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.1832026875699888, | |
| "grad_norm": 4.936882495880127, | |
| "learning_rate": 6.203502985451152e-07, | |
| "loss": 1.1434, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.18365061590145576, | |
| "grad_norm": 3.6114046573638916, | |
| "learning_rate": 6.071696066555978e-07, | |
| "loss": 1.1957, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.18409854423292274, | |
| "grad_norm": 3.0989315509796143, | |
| "learning_rate": 5.941181042139258e-07, | |
| "loss": 1.1672, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.1845464725643897, | |
| "grad_norm": 3.9395434856414795, | |
| "learning_rate": 5.811963277162466e-07, | |
| "loss": 1.3213, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.18499440089585667, | |
| "grad_norm": 3.7421300411224365, | |
| "learning_rate": 5.684048083261789e-07, | |
| "loss": 0.9563, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.18544232922732362, | |
| "grad_norm": 3.190976858139038, | |
| "learning_rate": 5.557440718529848e-07, | |
| "loss": 1.1234, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.1858902575587906, | |
| "grad_norm": 3.461064100265503, | |
| "learning_rate": 5.432146387299522e-07, | |
| "loss": 1.0016, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.18633818589025755, | |
| "grad_norm": 6.645826816558838, | |
| "learning_rate": 5.308170239930022e-07, | |
| "loss": 1.1967, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.18678611422172453, | |
| "grad_norm": 4.823378562927246, | |
| "learning_rate": 5.185517372595187e-07, | |
| "loss": 1.032, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.18723404255319148, | |
| "grad_norm": 3.5760250091552734, | |
| "learning_rate": 5.064192827073995e-07, | |
| "loss": 1.1513, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.18768197088465846, | |
| "grad_norm": 3.162781000137329, | |
| "learning_rate": 4.944201590543308e-07, | |
| "loss": 0.9593, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.1881298992161254, | |
| "grad_norm": 8.633989334106445, | |
| "learning_rate": 4.825548595372898e-07, | |
| "loss": 1.2696, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.1881298992161254, | |
| "eval_loss": 1.1959577798843384, | |
| "eval_runtime": 51.6407, | |
| "eval_samples_per_second": 9.682, | |
| "eval_steps_per_second": 9.682, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.1885778275475924, | |
| "grad_norm": 4.277423858642578, | |
| "learning_rate": 4.7082387189226646e-07, | |
| "loss": 1.0834, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.18902575587905934, | |
| "grad_norm": 3.7345645427703857, | |
| "learning_rate": 4.5922767833421454e-07, | |
| "loss": 1.255, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.18947368421052632, | |
| "grad_norm": 5.163575172424316, | |
| "learning_rate": 4.477667555372326e-07, | |
| "loss": 1.1317, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.18992161254199327, | |
| "grad_norm": 5.2220892906188965, | |
| "learning_rate": 4.364415746149678e-07, | |
| "loss": 1.0966, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.19036954087346025, | |
| "grad_norm": 5.796306610107422, | |
| "learning_rate": 4.2525260110124964e-07, | |
| "loss": 1.0268, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.1908174692049272, | |
| "grad_norm": 4.295403003692627, | |
| "learning_rate": 4.1420029493095623e-07, | |
| "loss": 1.0465, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.19126539753639418, | |
| "grad_norm": 5.671868324279785, | |
| "learning_rate": 4.032851104211036e-07, | |
| "loss": 1.2124, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.19171332586786113, | |
| "grad_norm": 4.053644180297852, | |
| "learning_rate": 3.925074962521762e-07, | |
| "loss": 1.0574, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.1921612541993281, | |
| "grad_norm": 3.7694053649902344, | |
| "learning_rate": 3.818678954496787e-07, | |
| "loss": 1.0604, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.19260918253079506, | |
| "grad_norm": 4.982527256011963, | |
| "learning_rate": 3.713667453659287e-07, | |
| "loss": 1.1518, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.19305711086226204, | |
| "grad_norm": 5.036848545074463, | |
| "learning_rate": 3.6100447766207473e-07, | |
| "loss": 1.0251, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.193505039193729, | |
| "grad_norm": 5.744006633758545, | |
| "learning_rate": 3.5078151829035693e-07, | |
| "loss": 1.0103, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.19395296752519597, | |
| "grad_norm": 3.843419075012207, | |
| "learning_rate": 3.4069828747659405e-07, | |
| "loss": 1.0053, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.19440089585666293, | |
| "grad_norm": 4.357511043548584, | |
| "learning_rate": 3.3075519970291144e-07, | |
| "loss": 1.202, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.1948488241881299, | |
| "grad_norm": 6.164062976837158, | |
| "learning_rate": 3.209526636907036e-07, | |
| "loss": 1.1136, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.1948488241881299, | |
| "eval_loss": 1.1951868534088135, | |
| "eval_runtime": 51.6432, | |
| "eval_samples_per_second": 9.682, | |
| "eval_steps_per_second": 9.682, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.19529675251959686, | |
| "grad_norm": 3.893348217010498, | |
| "learning_rate": 3.1129108238383095e-07, | |
| "loss": 1.2238, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.19574468085106383, | |
| "grad_norm": 3.704392433166504, | |
| "learning_rate": 3.017708529320604e-07, | |
| "loss": 1.0766, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.19619260918253079, | |
| "grad_norm": 4.406269073486328, | |
| "learning_rate": 2.923923666747357e-07, | |
| "loss": 0.9588, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.19664053751399777, | |
| "grad_norm": 6.578729152679443, | |
| "learning_rate": 2.8315600912469477e-07, | |
| "loss": 1.1622, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.19708846584546472, | |
| "grad_norm": 4.1804094314575195, | |
| "learning_rate": 2.740621599524189e-07, | |
| "loss": 1.1999, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.1975363941769317, | |
| "grad_norm": 6.192513465881348, | |
| "learning_rate": 2.651111929704303e-07, | |
| "loss": 1.1274, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.19798432250839865, | |
| "grad_norm": 4.356874942779541, | |
| "learning_rate": 2.563034761179223e-07, | |
| "loss": 1.0262, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.19843225083986563, | |
| "grad_norm": 4.435469627380371, | |
| "learning_rate": 2.476393714456384e-07, | |
| "loss": 1.1814, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.19888017917133258, | |
| "grad_norm": 3.9173505306243896, | |
| "learning_rate": 2.391192351009855e-07, | |
| "loss": 0.7984, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.19932810750279956, | |
| "grad_norm": 6.546506881713867, | |
| "learning_rate": 2.3074341731339837e-07, | |
| "loss": 1.168, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.1997760358342665, | |
| "grad_norm": 6.1646223068237305, | |
| "learning_rate": 2.225122623799407e-07, | |
| "loss": 1.2589, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.2002239641657335, | |
| "grad_norm": 3.210203170776367, | |
| "learning_rate": 2.1442610865115135e-07, | |
| "loss": 1.0636, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.20067189249720044, | |
| "grad_norm": 5.133816242218018, | |
| "learning_rate": 2.0648528851714077e-07, | |
| "loss": 1.0195, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.20111982082866742, | |
| "grad_norm": 4.449398517608643, | |
| "learning_rate": 1.9869012839392064e-07, | |
| "loss": 1.1007, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.20156774916013437, | |
| "grad_norm": 4.8083977699279785, | |
| "learning_rate": 1.9104094870999264e-07, | |
| "loss": 1.1975, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.20156774916013437, | |
| "eval_loss": 1.1950809955596924, | |
| "eval_runtime": 51.7311, | |
| "eval_samples_per_second": 9.665, | |
| "eval_steps_per_second": 9.665, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.20201567749160135, | |
| "grad_norm": 4.709386348724365, | |
| "learning_rate": 1.8353806389317428e-07, | |
| "loss": 0.9829, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.2024636058230683, | |
| "grad_norm": 5.23099946975708, | |
| "learning_rate": 1.761817823576731e-07, | |
| "loss": 1.1149, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.20291153415453528, | |
| "grad_norm": 3.4107179641723633, | |
| "learning_rate": 1.6897240649141125e-07, | |
| "loss": 0.9822, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.20335946248600223, | |
| "grad_norm": 3.951052188873291, | |
| "learning_rate": 1.619102326435923e-07, | |
| "loss": 1.2333, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.2038073908174692, | |
| "grad_norm": 4.30809211730957, | |
| "learning_rate": 1.5499555111252285e-07, | |
| "loss": 1.0641, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.20425531914893616, | |
| "grad_norm": 4.1274189949035645, | |
| "learning_rate": 1.4822864613367766e-07, | |
| "loss": 1.0962, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.20470324748040314, | |
| "grad_norm": 6.046044826507568, | |
| "learning_rate": 1.4160979586801724e-07, | |
| "loss": 1.0241, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.2051511758118701, | |
| "grad_norm": 4.066288471221924, | |
| "learning_rate": 1.3513927239055036e-07, | |
| "loss": 0.9061, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.20559910414333707, | |
| "grad_norm": 3.9250218868255615, | |
| "learning_rate": 1.2881734167915425e-07, | |
| "loss": 1.1666, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.20604703247480402, | |
| "grad_norm": 4.965548515319824, | |
| "learning_rate": 1.2264426360363956e-07, | |
| "loss": 0.8048, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.206494960806271, | |
| "grad_norm": 5.192389965057373, | |
| "learning_rate": 1.1662029191506775e-07, | |
| "loss": 0.9869, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.20694288913773795, | |
| "grad_norm": 4.953862190246582, | |
| "learning_rate": 1.107456742353201e-07, | |
| "loss": 1.0042, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.20739081746920493, | |
| "grad_norm": 4.955436706542969, | |
| "learning_rate": 1.0502065204692062e-07, | |
| "loss": 1.101, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.20783874580067188, | |
| "grad_norm": 2.5195674896240234, | |
| "learning_rate": 9.94454606831076e-08, | |
| "loss": 0.9542, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.20828667413213886, | |
| "grad_norm": 4.142997741699219, | |
| "learning_rate": 9.402032931816144e-08, | |
| "loss": 1.1318, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.20828667413213886, | |
| "eval_loss": 1.1947814226150513, | |
| "eval_runtime": 51.8063, | |
| "eval_samples_per_second": 9.651, | |
| "eval_steps_per_second": 9.651, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.2087346024636058, | |
| "grad_norm": 4.046876907348633, | |
| "learning_rate": 8.874548095798464e-08, | |
| "loss": 1.1393, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.2091825307950728, | |
| "grad_norm": 4.740685939788818, | |
| "learning_rate": 8.362113243093245e-08, | |
| "loss": 1.0529, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.20963045912653974, | |
| "grad_norm": 6.356805324554443, | |
| "learning_rate": 7.864749437890173e-08, | |
| "loss": 1.2791, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.21007838745800672, | |
| "grad_norm": 4.329228401184082, | |
| "learning_rate": 7.382477124867282e-08, | |
| "loss": 1.2672, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 5.217611312866211, | |
| "learning_rate": 6.915316128350461e-08, | |
| "loss": 0.9357, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.21097424412094065, | |
| "grad_norm": 5.418657302856445, | |
| "learning_rate": 6.463285651498563e-08, | |
| "loss": 1.011, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.2114221724524076, | |
| "grad_norm": 6.056429386138916, | |
| "learning_rate": 6.026404275513875e-08, | |
| "loss": 1.4377, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.21187010078387458, | |
| "grad_norm": 3.5456736087799072, | |
| "learning_rate": 5.604689958878723e-08, | |
| "loss": 1.1192, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.21231802911534153, | |
| "grad_norm": 5.697049140930176, | |
| "learning_rate": 5.198160036616898e-08, | |
| "loss": 1.0392, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.2127659574468085, | |
| "grad_norm": 4.248316764831543, | |
| "learning_rate": 4.8068312195811847e-08, | |
| "loss": 1.0041, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.21321388577827546, | |
| "grad_norm": 3.3937604427337646, | |
| "learning_rate": 4.4307195937666194e-08, | |
| "loss": 0.9791, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.21366181410974244, | |
| "grad_norm": 3.097196340560913, | |
| "learning_rate": 4.069840619648935e-08, | |
| "loss": 1.1306, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.2141097424412094, | |
| "grad_norm": 5.534854888916016, | |
| "learning_rate": 3.72420913154932e-08, | |
| "loss": 1.104, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.21455767077267637, | |
| "grad_norm": 5.693947792053223, | |
| "learning_rate": 3.3938393370244876e-08, | |
| "loss": 1.1541, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.21500559910414332, | |
| "grad_norm": 4.025967597961426, | |
| "learning_rate": 3.078744816282731e-08, | |
| "loss": 1.1515, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.21500559910414332, | |
| "eval_loss": 1.1954809427261353, | |
| "eval_runtime": 51.6284, | |
| "eval_samples_per_second": 9.685, | |
| "eval_steps_per_second": 9.685, | |
| "step": 4800 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.204448348803072e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |