| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 1396, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014326647564469915, | |
| "grad_norm": 219.6043368919095, | |
| "learning_rate": 9.9998935058887e-05, | |
| "loss": 3.6922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02865329512893983, | |
| "grad_norm": 164.46657899747223, | |
| "learning_rate": 9.99820692232566e-05, | |
| "loss": 5.6597, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04297994269340974, | |
| "grad_norm": 6.412857819851782, | |
| "learning_rate": 9.993928004395286e-05, | |
| "loss": 2.5057, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05730659025787966, | |
| "grad_norm": 69.62252521072725, | |
| "learning_rate": 9.987119700662767e-05, | |
| "loss": 1.984, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07163323782234957, | |
| "grad_norm": 2.911386364058055, | |
| "learning_rate": 9.977785459481133e-05, | |
| "loss": 1.9796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08595988538681948, | |
| "grad_norm": 2.928138422380621, | |
| "learning_rate": 9.965930008571152e-05, | |
| "loss": 1.9357, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10028653295128939, | |
| "grad_norm": 2.718649753716308, | |
| "learning_rate": 9.951559352626757e-05, | |
| "loss": 1.9499, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11461318051575932, | |
| "grad_norm": 3.2224244565131954, | |
| "learning_rate": 9.934680770273733e-05, | |
| "loss": 1.9316, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12893982808022922, | |
| "grad_norm": 2.35688226018453, | |
| "learning_rate": 9.915302810383132e-05, | |
| "loss": 1.9162, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.14326647564469913, | |
| "grad_norm": 2.332818455987922, | |
| "learning_rate": 9.893435287741343e-05, | |
| "loss": 1.9155, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14326647564469913, | |
| "eval_loss": 1.8934402465820312, | |
| "eval_runtime": 53.9021, | |
| "eval_samples_per_second": 184.112, | |
| "eval_steps_per_second": 1.447, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15759312320916904, | |
| "grad_norm": 2.188522515670293, | |
| "learning_rate": 9.869089278078987e-05, | |
| "loss": 1.8955, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.17191977077363896, | |
| "grad_norm": 2.0681470915932927, | |
| "learning_rate": 9.842277112461131e-05, | |
| "loss": 1.8796, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.18624641833810887, | |
| "grad_norm": 2.0222340151069544, | |
| "learning_rate": 9.813012371041714e-05, | |
| "loss": 1.8806, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.20057306590257878, | |
| "grad_norm": 2.192495513300194, | |
| "learning_rate": 9.781309876185291e-05, | |
| "loss": 1.8566, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2148997134670487, | |
| "grad_norm": 2.17884511538925, | |
| "learning_rate": 9.747185684959626e-05, | |
| "loss": 1.8784, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.22922636103151864, | |
| "grad_norm": 2.2802921311633972, | |
| "learning_rate": 9.710657081002914e-05, | |
| "loss": 1.8404, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.24355300859598855, | |
| "grad_norm": 2.12926899758067, | |
| "learning_rate": 9.671742565769749e-05, | |
| "loss": 1.8486, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.25787965616045844, | |
| "grad_norm": 1.9971883700915698, | |
| "learning_rate": 9.630461849160281e-05, | |
| "loss": 1.8228, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2722063037249284, | |
| "grad_norm": 2.3808879139034613, | |
| "learning_rate": 9.586835839537311e-05, | |
| "loss": 1.8419, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.28653295128939826, | |
| "grad_norm": 2.1250632793004702, | |
| "learning_rate": 9.540886633136352e-05, | |
| "loss": 1.7826, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28653295128939826, | |
| "eval_loss": 1.7807523012161255, | |
| "eval_runtime": 53.6847, | |
| "eval_samples_per_second": 184.857, | |
| "eval_steps_per_second": 1.453, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3008595988538682, | |
| "grad_norm": 2.074489802943034, | |
| "learning_rate": 9.492637502874073e-05, | |
| "loss": 1.7436, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3151862464183381, | |
| "grad_norm": 1.8033562678630226, | |
| "learning_rate": 9.44211288656074e-05, | |
| "loss": 1.7747, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.32951289398280803, | |
| "grad_norm": 1.7937171543469097, | |
| "learning_rate": 9.389338374522656e-05, | |
| "loss": 1.8156, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3438395415472779, | |
| "grad_norm": 1.7554977702779284, | |
| "learning_rate": 9.334340696640855e-05, | |
| "loss": 1.767, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.35816618911174786, | |
| "grad_norm": 2.2371815357457208, | |
| "learning_rate": 9.277147708812635e-05, | |
| "loss": 1.7629, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.37249283667621774, | |
| "grad_norm": 2.0086148480908297, | |
| "learning_rate": 9.217788378842749e-05, | |
| "loss": 1.7388, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3868194842406877, | |
| "grad_norm": 1.6807840994252192, | |
| "learning_rate": 9.156292771771447e-05, | |
| "loss": 1.7428, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.40114613180515757, | |
| "grad_norm": 1.7341861848893365, | |
| "learning_rate": 9.09269203464676e-05, | |
| "loss": 1.7206, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4154727793696275, | |
| "grad_norm": 1.8322321070759275, | |
| "learning_rate": 9.027018380748766e-05, | |
| "loss": 1.6931, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4297994269340974, | |
| "grad_norm": 1.615978489405473, | |
| "learning_rate": 8.959305073273809e-05, | |
| "loss": 1.6897, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4297994269340974, | |
| "eval_loss": 1.6719396114349365, | |
| "eval_runtime": 53.4447, | |
| "eval_samples_per_second": 185.687, | |
| "eval_steps_per_second": 1.459, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.44412607449856734, | |
| "grad_norm": 1.8985940929478535, | |
| "learning_rate": 8.889586408486953e-05, | |
| "loss": 1.6554, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4584527220630373, | |
| "grad_norm": 1.9424706081821295, | |
| "learning_rate": 8.817897698351185e-05, | |
| "loss": 1.6655, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.47277936962750716, | |
| "grad_norm": 1.9287612597705355, | |
| "learning_rate": 8.744275252642184e-05, | |
| "loss": 1.638, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.4871060171919771, | |
| "grad_norm": 1.5833650317049555, | |
| "learning_rate": 8.668756360557697e-05, | |
| "loss": 1.6386, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.501432664756447, | |
| "grad_norm": 1.9070708361736106, | |
| "learning_rate": 8.591379271830855e-05, | |
| "loss": 1.6365, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5157593123209169, | |
| "grad_norm": 1.7717200377491302, | |
| "learning_rate": 8.512183177356973e-05, | |
| "loss": 1.6135, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5300859598853869, | |
| "grad_norm": 1.5741330801409983, | |
| "learning_rate": 8.43120818934367e-05, | |
| "loss": 1.6001, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5444126074498568, | |
| "grad_norm": 2.216205258530314, | |
| "learning_rate": 8.348495320994345e-05, | |
| "loss": 1.6161, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5587392550143266, | |
| "grad_norm": 1.6749338500257063, | |
| "learning_rate": 8.264086465735312e-05, | |
| "loss": 1.5873, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "grad_norm": 1.6669193921386205, | |
| "learning_rate": 8.178024375997097e-05, | |
| "loss": 1.5887, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5730659025787965, | |
| "eval_loss": 1.5738122463226318, | |
| "eval_runtime": 53.5809, | |
| "eval_samples_per_second": 185.215, | |
| "eval_steps_per_second": 1.456, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5873925501432665, | |
| "grad_norm": 1.6738558434456052, | |
| "learning_rate": 8.090352641560668e-05, | |
| "loss": 1.6297, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6017191977077364, | |
| "grad_norm": 1.6812511762700748, | |
| "learning_rate": 8.001115667479552e-05, | |
| "loss": 1.5987, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6160458452722063, | |
| "grad_norm": 1.6615769390951736, | |
| "learning_rate": 7.910358651589015e-05, | |
| "loss": 1.5509, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6303724928366762, | |
| "grad_norm": 1.696391678445336, | |
| "learning_rate": 7.818127561613707e-05, | |
| "loss": 1.5429, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6446991404011462, | |
| "grad_norm": 1.5660326039107408, | |
| "learning_rate": 7.724469111885371e-05, | |
| "loss": 1.5396, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6590257879656161, | |
| "grad_norm": 2.028710946062277, | |
| "learning_rate": 7.629430739682398e-05, | |
| "loss": 1.5266, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.673352435530086, | |
| "grad_norm": 2.116807818224008, | |
| "learning_rate": 7.533060581203201e-05, | |
| "loss": 1.5824, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.6876790830945558, | |
| "grad_norm": 1.637751947026498, | |
| "learning_rate": 7.435407447185623e-05, | |
| "loss": 1.4828, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7020057306590258, | |
| "grad_norm": 1.5564501538035538, | |
| "learning_rate": 7.336520798184664e-05, | |
| "loss": 1.4991, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7163323782234957, | |
| "grad_norm": 1.575375723060998, | |
| "learning_rate": 7.236450719521092e-05, | |
| "loss": 1.4628, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7163323782234957, | |
| "eval_loss": 1.4659688472747803, | |
| "eval_runtime": 53.8819, | |
| "eval_samples_per_second": 184.18, | |
| "eval_steps_per_second": 1.448, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7306590257879656, | |
| "grad_norm": 1.5701973244119096, | |
| "learning_rate": 7.135247895913623e-05, | |
| "loss": 1.485, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.7449856733524355, | |
| "grad_norm": 1.7014160396040479, | |
| "learning_rate": 7.032963585807501e-05, | |
| "loss": 1.454, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7593123209169055, | |
| "grad_norm": 1.4812078348628686, | |
| "learning_rate": 6.929649595412497e-05, | |
| "loss": 1.4675, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.7736389684813754, | |
| "grad_norm": 1.6254083780903348, | |
| "learning_rate": 6.825358252463461e-05, | |
| "loss": 1.4232, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.7879656160458453, | |
| "grad_norm": 1.593996844960836, | |
| "learning_rate": 6.720142379716728e-05, | |
| "loss": 1.4084, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8022922636103151, | |
| "grad_norm": 1.4683667712701527, | |
| "learning_rate": 6.614055268195805e-05, | |
| "loss": 1.4034, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8166189111747851, | |
| "grad_norm": 1.6604556204013439, | |
| "learning_rate": 6.507150650199886e-05, | |
| "loss": 1.439, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.830945558739255, | |
| "grad_norm": 1.5795992163148025, | |
| "learning_rate": 6.399482672088852e-05, | |
| "loss": 1.3767, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.8452722063037249, | |
| "grad_norm": 1.7278879653526587, | |
| "learning_rate": 6.291105866858562e-05, | |
| "loss": 1.4084, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.8595988538681948, | |
| "grad_norm": 1.4915922467967875, | |
| "learning_rate": 6.18207512652031e-05, | |
| "loss": 1.3751, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8595988538681948, | |
| "eval_loss": 1.3670978546142578, | |
| "eval_runtime": 53.4401, | |
| "eval_samples_per_second": 185.703, | |
| "eval_steps_per_second": 1.46, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8739255014326648, | |
| "grad_norm": 1.5055751912412483, | |
| "learning_rate": 6.0724456742984535e-05, | |
| "loss": 1.3799, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.8882521489971347, | |
| "grad_norm": 1.5174029894001677, | |
| "learning_rate": 5.962273036660276e-05, | |
| "loss": 1.372, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9025787965616046, | |
| "grad_norm": 1.6367622819691852, | |
| "learning_rate": 5.851613015192261e-05, | |
| "loss": 1.3514, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.9169054441260746, | |
| "grad_norm": 1.556482139125314, | |
| "learning_rate": 5.74052165833702e-05, | |
| "loss": 1.3283, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9312320916905444, | |
| "grad_norm": 1.6450518726375203, | |
| "learning_rate": 5.6290552330051946e-05, | |
| "loss": 1.3257, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.9455587392550143, | |
| "grad_norm": 1.3993302544976038, | |
| "learning_rate": 5.5172701960767006e-05, | |
| "loss": 1.3279, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.9598853868194842, | |
| "grad_norm": 1.6965193543443504, | |
| "learning_rate": 5.405223165805755e-05, | |
| "loss": 1.2695, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.9742120343839542, | |
| "grad_norm": 1.4956063904398584, | |
| "learning_rate": 5.292970893144172e-05, | |
| "loss": 1.2958, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.9885386819484241, | |
| "grad_norm": 1.3407355333418884, | |
| "learning_rate": 5.180570232997446e-05, | |
| "loss": 1.2763, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.002865329512894, | |
| "grad_norm": 1.8406934340144963, | |
| "learning_rate": 5.06807811542818e-05, | |
| "loss": 1.1263, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.002865329512894, | |
| "eval_loss": 1.2830663919448853, | |
| "eval_runtime": 53.5866, | |
| "eval_samples_per_second": 185.196, | |
| "eval_steps_per_second": 1.456, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.0171919770773639, | |
| "grad_norm": 1.466971080200883, | |
| "learning_rate": 4.9555515168214514e-05, | |
| "loss": 0.7167, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.0315186246418337, | |
| "grad_norm": 1.3865994721327555, | |
| "learning_rate": 4.8430474310267185e-05, | |
| "loss": 0.6893, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.0458452722063036, | |
| "grad_norm": 1.5632728482959424, | |
| "learning_rate": 4.7306228404908706e-05, | |
| "loss": 0.6935, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.0601719197707737, | |
| "grad_norm": 1.3730426755979892, | |
| "learning_rate": 4.6183346873970704e-05, | |
| "loss": 0.7053, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.0744985673352436, | |
| "grad_norm": 1.469352640225314, | |
| "learning_rate": 4.506239844823972e-05, | |
| "loss": 0.6848, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.0888252148997135, | |
| "grad_norm": 1.4293421992017694, | |
| "learning_rate": 4.394395087939947e-05, | |
| "loss": 0.6677, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.1031518624641834, | |
| "grad_norm": 1.497199630056392, | |
| "learning_rate": 4.282857065246908e-05, | |
| "loss": 0.6844, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.1174785100286533, | |
| "grad_norm": 1.4739240120513313, | |
| "learning_rate": 4.1716822698882826e-05, | |
| "loss": 0.6735, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.1318051575931232, | |
| "grad_norm": 1.4505373708013058, | |
| "learning_rate": 4.0609270110356625e-05, | |
| "loss": 0.6405, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "grad_norm": 1.507546317576944, | |
| "learning_rate": 3.9506473853686586e-05, | |
| "loss": 0.688, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.146131805157593, | |
| "eval_loss": 1.2491989135742188, | |
| "eval_runtime": 53.6109, | |
| "eval_samples_per_second": 185.112, | |
| "eval_steps_per_second": 1.455, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1604584527220632, | |
| "grad_norm": 1.6233022720214296, | |
| "learning_rate": 3.8408992486623595e-05, | |
| "loss": 0.662, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.174785100286533, | |
| "grad_norm": 1.2645448426600083, | |
| "learning_rate": 3.7317381874968207e-05, | |
| "loss": 0.6901, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.189111747851003, | |
| "grad_norm": 1.4745754772070392, | |
| "learning_rate": 3.6232194911028874e-05, | |
| "loss": 0.6705, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.2034383954154728, | |
| "grad_norm": 1.3592040417066167, | |
| "learning_rate": 3.515398123358627e-05, | |
| "loss": 0.6764, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.2177650429799427, | |
| "grad_norm": 1.3029544883514448, | |
| "learning_rate": 3.40832869495056e-05, | |
| "loss": 0.6761, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.2320916905444126, | |
| "grad_norm": 2.098968282444413, | |
| "learning_rate": 3.302065435713763e-05, | |
| "loss": 0.6275, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.2464183381088825, | |
| "grad_norm": 1.3448595848587355, | |
| "learning_rate": 3.196662167164877e-05, | |
| "loss": 0.6342, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.2607449856733524, | |
| "grad_norm": 1.3928584326736022, | |
| "learning_rate": 3.092172275241933e-05, | |
| "loss": 0.6357, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.2750716332378222, | |
| "grad_norm": 1.408932176758002, | |
| "learning_rate": 2.9886486832647835e-05, | |
| "loss": 0.6189, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.2893982808022924, | |
| "grad_norm": 1.3715405151520115, | |
| "learning_rate": 2.8861438251298512e-05, | |
| "loss": 0.6544, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2893982808022924, | |
| "eval_loss": 1.1817691326141357, | |
| "eval_runtime": 53.5943, | |
| "eval_samples_per_second": 185.169, | |
| "eval_steps_per_second": 1.455, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.3037249283667622, | |
| "grad_norm": 1.188564778298211, | |
| "learning_rate": 2.784709618752776e-05, | |
| "loss": 0.6359, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.3180515759312321, | |
| "grad_norm": 1.2862274938371403, | |
| "learning_rate": 2.6843974397723753e-05, | |
| "loss": 0.621, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.332378223495702, | |
| "grad_norm": 1.316124517086862, | |
| "learning_rate": 2.5852580955293003e-05, | |
| "loss": 0.6265, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.346704871060172, | |
| "grad_norm": 1.3322773186587833, | |
| "learning_rate": 2.4873417993325042e-05, | |
| "loss": 0.6441, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.3610315186246418, | |
| "grad_norm": 1.2889293368365848, | |
| "learning_rate": 2.3906981450265836e-05, | |
| "loss": 0.6173, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.3753581661891117, | |
| "grad_norm": 1.4909707916630004, | |
| "learning_rate": 2.295376081872895e-05, | |
| "loss": 0.6193, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.3896848137535818, | |
| "grad_norm": 1.3688980598451725, | |
| "learning_rate": 2.201423889757122e-05, | |
| "loss": 0.6466, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.4040114613180517, | |
| "grad_norm": 1.3684687851700825, | |
| "learning_rate": 2.108889154735895e-05, | |
| "loss": 0.6124, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.4183381088825215, | |
| "grad_norm": 1.2359362156168956, | |
| "learning_rate": 2.0178187449348208e-05, | |
| "loss": 0.6183, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.4326647564469914, | |
| "grad_norm": 1.2595878525492465, | |
| "learning_rate": 1.9282587868101308e-05, | |
| "loss": 0.6017, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4326647564469914, | |
| "eval_loss": 1.120739459991455, | |
| "eval_runtime": 53.3734, | |
| "eval_samples_per_second": 185.935, | |
| "eval_steps_per_second": 1.461, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4469914040114613, | |
| "grad_norm": 1.384961270564966, | |
| "learning_rate": 1.840254641786006e-05, | |
| "loss": 0.5614, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.4613180515759312, | |
| "grad_norm": 1.4232024294510734, | |
| "learning_rate": 1.7538508832793578e-05, | |
| "loss": 0.5797, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.475644699140401, | |
| "grad_norm": 1.1618822443190342, | |
| "learning_rate": 1.669091274123732e-05, | |
| "loss": 0.6184, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.4899713467048712, | |
| "grad_norm": 1.3507488640615957, | |
| "learning_rate": 1.586018744403787e-05, | |
| "loss": 0.5813, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.5042979942693409, | |
| "grad_norm": 1.3443442941285704, | |
| "learning_rate": 1.504675369711529e-05, | |
| "loss": 0.5667, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.518624641833811, | |
| "grad_norm": 1.2877577958996937, | |
| "learning_rate": 1.4251023498353533e-05, | |
| "loss": 0.582, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.5329512893982808, | |
| "grad_norm": 1.1575931882275956, | |
| "learning_rate": 1.3473399878926746e-05, | |
| "loss": 0.563, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.5472779369627507, | |
| "grad_norm": 1.1621133893036653, | |
| "learning_rate": 1.2714276699166994e-05, | |
| "loss": 0.5466, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.5616045845272206, | |
| "grad_norm": 1.228237925890841, | |
| "learning_rate": 1.1974038449077258e-05, | |
| "loss": 0.5239, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.5759312320916905, | |
| "grad_norm": 1.1901152329499263, | |
| "learning_rate": 1.1253060053589997e-05, | |
| "loss": 0.5763, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.5759312320916905, | |
| "eval_loss": 1.0708156824111938, | |
| "eval_runtime": 53.5345, | |
| "eval_samples_per_second": 185.376, | |
| "eval_steps_per_second": 1.457, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.5902578796561606, | |
| "grad_norm": 1.321031783530892, | |
| "learning_rate": 1.0551706682670748e-05, | |
| "loss": 0.5511, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.6045845272206303, | |
| "grad_norm": 1.263841226648576, | |
| "learning_rate": 9.870333566362322e-06, | |
| "loss": 0.5645, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.6189111747851004, | |
| "grad_norm": 1.2601683852009655, | |
| "learning_rate": 9.209285814863477e-06, | |
| "loss": 0.5301, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.63323782234957, | |
| "grad_norm": 1.1853670920081087, | |
| "learning_rate": 8.568898243733386e-06, | |
| "loss": 0.5371, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.6475644699140402, | |
| "grad_norm": 1.2370950402879501, | |
| "learning_rate": 7.949495204310104e-06, | |
| "loss": 0.5555, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.66189111747851, | |
| "grad_norm": 1.3089349313138638, | |
| "learning_rate": 7.351390419429083e-06, | |
| "loss": 0.5616, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.67621776504298, | |
| "grad_norm": 1.3007158953895024, | |
| "learning_rate": 6.774886824525073e-06, | |
| "loss": 0.539, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.6905444126074498, | |
| "grad_norm": 1.2215575024934626, | |
| "learning_rate": 6.2202764141976346e-06, | |
| "loss": 0.5366, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.7048710601719197, | |
| "grad_norm": 1.1917522774279614, | |
| "learning_rate": 5.687840094318125e-06, | |
| "loss": 0.5072, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.7191977077363898, | |
| "grad_norm": 1.2065112378383362, | |
| "learning_rate": 5.177847539753084e-06, | |
| "loss": 0.5599, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7191977077363898, | |
| "eval_loss": 1.036474347114563, | |
| "eval_runtime": 53.4293, | |
| "eval_samples_per_second": 185.741, | |
| "eval_steps_per_second": 1.46, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7335243553008595, | |
| "grad_norm": 1.240311618648056, | |
| "learning_rate": 4.690557057775974e-06, | |
| "loss": 0.5367, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.7478510028653296, | |
| "grad_norm": 1.2440347942531507, | |
| "learning_rate": 4.226215457236565e-06, | |
| "loss": 0.5388, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.7621776504297995, | |
| "grad_norm": 1.2299956356695219, | |
| "learning_rate": 3.785057923554197e-06, | |
| "loss": 0.5238, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.7765042979942693, | |
| "grad_norm": 1.3887050995508965, | |
| "learning_rate": 3.36730789959811e-06, | |
| "loss": 0.4981, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.7908309455587392, | |
| "grad_norm": 1.1031870914219795, | |
| "learning_rate": 2.9731769725154514e-06, | |
| "loss": 0.5294, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.8051575931232091, | |
| "grad_norm": 1.4024610914172573, | |
| "learning_rate": 2.6028647665639672e-06, | |
| "loss": 0.5275, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.8194842406876792, | |
| "grad_norm": 1.233183532537092, | |
| "learning_rate": 2.256558842003892e-06, | |
| "loss": 0.5253, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.8338108882521489, | |
| "grad_norm": 1.2308977898401474, | |
| "learning_rate": 1.9344346001001377e-06, | |
| "loss": 0.5442, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.848137535816619, | |
| "grad_norm": 1.1860759958409324, | |
| "learning_rate": 1.6366551942828711e-06, | |
| "loss": 0.5483, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.8624641833810889, | |
| "grad_norm": 1.3493855244370383, | |
| "learning_rate": 1.363371447511619e-06, | |
| "loss": 0.5101, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.8624641833810889, | |
| "eval_loss": 1.0169659852981567, | |
| "eval_runtime": 53.5386, | |
| "eval_samples_per_second": 185.361, | |
| "eval_steps_per_second": 1.457, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.8767908309455588, | |
| "grad_norm": 1.3172256182801068, | |
| "learning_rate": 1.1147217758845751e-06, | |
| "loss": 0.5469, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.8911174785100286, | |
| "grad_norm": 1.2977180424743335, | |
| "learning_rate": 8.908321185319312e-07, | |
| "loss": 0.5319, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.9054441260744985, | |
| "grad_norm": 1.1849694099091805, | |
| "learning_rate": 6.918158738286884e-07, | |
| "loss": 0.5126, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.9197707736389686, | |
| "grad_norm": 1.2190235185481941, | |
| "learning_rate": 5.177738419592515e-07, | |
| "loss": 0.5276, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.9340974212034383, | |
| "grad_norm": 1.1093762195623071, | |
| "learning_rate": 3.687941738629186e-07, | |
| "loss": 0.53, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.9484240687679084, | |
| "grad_norm": 1.0282807771775446, | |
| "learning_rate": 2.449523265861176e-07, | |
| "loss": 0.4903, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.962750716332378, | |
| "grad_norm": 1.3409900754803958, | |
| "learning_rate": 1.4631102506399985e-07, | |
| "loss": 0.5025, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.9770773638968482, | |
| "grad_norm": 1.2011587981462408, | |
| "learning_rate": 7.292023035074813e-08, | |
| "loss": 0.5428, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.991404011461318, | |
| "grad_norm": 1.2347668278605959, | |
| "learning_rate": 2.4817114314662493e-08, | |
| "loss": 0.52, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1396, | |
| "total_flos": 192624989306880.0, | |
| "train_loss": 1.1565231682577926, | |
| "train_runtime": 4692.4705, | |
| "train_samples_per_second": 38.067, | |
| "train_steps_per_second": 0.297 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1396, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 192624989306880.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |