| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.999537251272559, | |
| "eval_steps": 100, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005552984729291994, | |
| "grad_norm": 5.378993948282789, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 1.3618, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011105969458583989, | |
| "grad_norm": 4.007932344194533, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 1.3497, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016658954187875982, | |
| "grad_norm": 2.870467768621527, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.3292, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022211938917167977, | |
| "grad_norm": 2.9129656624638147, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.3086, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027764923646459973, | |
| "grad_norm": 2.0216771653661767, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 1.1997, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033317908375751965, | |
| "grad_norm": 1.7768511495820114, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.1742, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03887089310504396, | |
| "grad_norm": 1.4804724166332308, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 1.1244, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.044423877834335955, | |
| "grad_norm": 1.5180593968939422, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.0946, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04997686256362795, | |
| "grad_norm": 1.4879318494570208, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1032, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.055529847292919945, | |
| "grad_norm": 1.449589161585785, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 1.0751, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06108283202221194, | |
| "grad_norm": 1.3300428861282843, | |
| "learning_rate": 1.2222222222222224e-05, | |
| "loss": 1.0704, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06663581675150393, | |
| "grad_norm": 1.5071782473179958, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.0561, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07218880148079593, | |
| "grad_norm": 1.3957616523065333, | |
| "learning_rate": 1.4444444444444446e-05, | |
| "loss": 1.0527, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07774178621008793, | |
| "grad_norm": 1.3254556004203786, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 1.0107, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08329477093937991, | |
| "grad_norm": 1.5821507688192253, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.035, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08884775566867191, | |
| "grad_norm": 1.5770964291038414, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 1.0285, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09440074039796391, | |
| "grad_norm": 1.5156588992406825, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 1.0462, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0999537251272559, | |
| "grad_norm": 1.8368814946604881, | |
| "learning_rate": 2e-05, | |
| "loss": 1.0321, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10550670985654789, | |
| "grad_norm": 1.6154848357095026, | |
| "learning_rate": 1.9998119704485016e-05, | |
| "loss": 0.9962, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.11105969458583989, | |
| "grad_norm": 1.6218644276479086, | |
| "learning_rate": 1.9992479525042305e-05, | |
| "loss": 1.0216, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11105969458583989, | |
| "eval_loss": 1.0477724075317383, | |
| "eval_runtime": 14.0681, | |
| "eval_samples_per_second": 18.197, | |
| "eval_steps_per_second": 4.549, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11661267931513189, | |
| "grad_norm": 1.4399255902202484, | |
| "learning_rate": 1.9983081582712684e-05, | |
| "loss": 1.0344, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.12216566404442387, | |
| "grad_norm": 1.8069324642784876, | |
| "learning_rate": 1.996992941167792e-05, | |
| "loss": 1.0204, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12771864877371586, | |
| "grad_norm": 2.1003495945173865, | |
| "learning_rate": 1.9953027957931658e-05, | |
| "loss": 1.0169, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.13327163350300786, | |
| "grad_norm": 1.9735058045205416, | |
| "learning_rate": 1.9932383577419432e-05, | |
| "loss": 1.0039, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.13882461823229986, | |
| "grad_norm": 1.4822914643295109, | |
| "learning_rate": 1.9908004033648452e-05, | |
| "loss": 1.0025, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.14437760296159186, | |
| "grad_norm": 1.5730749273183444, | |
| "learning_rate": 1.9879898494768093e-05, | |
| "loss": 1.0014, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.14993058769088385, | |
| "grad_norm": 1.4317675236519043, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 1.0055, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.15548357242017585, | |
| "grad_norm": 1.4305310143482486, | |
| "learning_rate": 1.9812553106273848e-05, | |
| "loss": 0.9772, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.16103655714946785, | |
| "grad_norm": 1.835206300273569, | |
| "learning_rate": 1.9773338582506357e-05, | |
| "loss": 1.0041, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.16658954187875982, | |
| "grad_norm": 1.346307644251197, | |
| "learning_rate": 1.973044870579824e-05, | |
| "loss": 0.9836, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17214252660805182, | |
| "grad_norm": 1.3087431013115765, | |
| "learning_rate": 1.9683899605278062e-05, | |
| "loss": 0.9906, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.17769551133734382, | |
| "grad_norm": 1.6304479084212757, | |
| "learning_rate": 1.9633708786158803e-05, | |
| "loss": 0.9846, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.18324849606663582, | |
| "grad_norm": 1.4079238364588627, | |
| "learning_rate": 1.957989512315489e-05, | |
| "loss": 0.9953, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.18880148079592782, | |
| "grad_norm": 1.4160494597971853, | |
| "learning_rate": 1.9522478853384154e-05, | |
| "loss": 0.9728, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.19435446552521982, | |
| "grad_norm": 1.3831279332888735, | |
| "learning_rate": 1.946148156875751e-05, | |
| "loss": 0.9786, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1999074502545118, | |
| "grad_norm": 1.3223005814385944, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.9915, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.20546043498380379, | |
| "grad_norm": 7.733682148553893, | |
| "learning_rate": 1.932883704732001e-05, | |
| "loss": 1.0145, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.21101341971309578, | |
| "grad_norm": 1.6669211194032283, | |
| "learning_rate": 1.9257239692688907e-05, | |
| "loss": 0.9862, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.21656640444238778, | |
| "grad_norm": 1.4461392109939817, | |
| "learning_rate": 1.9182161068802742e-05, | |
| "loss": 0.9944, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.22211938917167978, | |
| "grad_norm": 1.3816905654957743, | |
| "learning_rate": 1.9103629409661468e-05, | |
| "loss": 0.99, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22211938917167978, | |
| "eval_loss": 1.0106741189956665, | |
| "eval_runtime": 13.0423, | |
| "eval_samples_per_second": 19.628, | |
| "eval_steps_per_second": 4.907, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22767237390097178, | |
| "grad_norm": 1.3296649623180647, | |
| "learning_rate": 1.902167424781038e-05, | |
| "loss": 0.9874, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.23322535863026378, | |
| "grad_norm": 1.4147575392387848, | |
| "learning_rate": 1.8936326403234125e-05, | |
| "loss": 0.9906, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.23877834335955575, | |
| "grad_norm": 1.5048777388561694, | |
| "learning_rate": 1.8847617971766577e-05, | |
| "loss": 0.9721, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.24433132808884775, | |
| "grad_norm": 1.3281954721580007, | |
| "learning_rate": 1.8755582313020912e-05, | |
| "loss": 0.9848, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.24988431281813975, | |
| "grad_norm": 1.3865529123681517, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.9885, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2554372975474317, | |
| "grad_norm": 1.468591497661801, | |
| "learning_rate": 1.8561668995302668e-05, | |
| "loss": 0.9713, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2609902822767237, | |
| "grad_norm": 1.3686298836564843, | |
| "learning_rate": 1.845986425919841e-05, | |
| "loss": 0.9579, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.2665432670060157, | |
| "grad_norm": 1.4148255169077197, | |
| "learning_rate": 1.8354878114129368e-05, | |
| "loss": 0.9506, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2720962517353077, | |
| "grad_norm": 1.5172086489276786, | |
| "learning_rate": 1.824675004109107e-05, | |
| "loss": 0.99, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.2776492364645997, | |
| "grad_norm": 1.3436284741737878, | |
| "learning_rate": 1.8135520702629677e-05, | |
| "loss": 0.9654, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2832022211938917, | |
| "grad_norm": 1.4414606449378646, | |
| "learning_rate": 1.802123192755044e-05, | |
| "loss": 0.9668, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.2887552059231837, | |
| "grad_norm": 1.4031899462530004, | |
| "learning_rate": 1.7903926695187595e-05, | |
| "loss": 0.9626, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2943081906524757, | |
| "grad_norm": 1.4639958980701138, | |
| "learning_rate": 1.7783649119241603e-05, | |
| "loss": 0.9459, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.2998611753817677, | |
| "grad_norm": 1.426651386589118, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.9863, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3054141601110597, | |
| "grad_norm": 1.4219614478552796, | |
| "learning_rate": 1.7534358963276606e-05, | |
| "loss": 0.9719, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3109671448403517, | |
| "grad_norm": 1.3151103765065284, | |
| "learning_rate": 1.740544013109005e-05, | |
| "loss": 0.9903, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3165201295696437, | |
| "grad_norm": 1.3354926740055781, | |
| "learning_rate": 1.7273736415730488e-05, | |
| "loss": 0.9681, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.3220731142989357, | |
| "grad_norm": 1.3717221395296357, | |
| "learning_rate": 1.7139297345578992e-05, | |
| "loss": 0.9456, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.32762609902822765, | |
| "grad_norm": 1.6411114205659896, | |
| "learning_rate": 1.7002173477671685e-05, | |
| "loss": 0.9591, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.33317908375751965, | |
| "grad_norm": 1.2826425067775913, | |
| "learning_rate": 1.686241637868734e-05, | |
| "loss": 0.9328, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33317908375751965, | |
| "eval_loss": 0.99033522605896, | |
| "eval_runtime": 13.2544, | |
| "eval_samples_per_second": 19.314, | |
| "eval_steps_per_second": 4.829, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33873206848681164, | |
| "grad_norm": 1.4005676511844571, | |
| "learning_rate": 1.6720078605555227e-05, | |
| "loss": 0.9803, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.34428505321610364, | |
| "grad_norm": 1.3022121862564202, | |
| "learning_rate": 1.657521368569064e-05, | |
| "loss": 0.9622, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.34983803794539564, | |
| "grad_norm": 1.4147938551822972, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.9733, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.35539102267468764, | |
| "grad_norm": 1.4563599805627543, | |
| "learning_rate": 1.627812124672099e-05, | |
| "loss": 0.9695, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.36094400740397964, | |
| "grad_norm": 1.2666931064627047, | |
| "learning_rate": 1.6126005451932028e-05, | |
| "loss": 0.9512, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.36649699213327164, | |
| "grad_norm": 1.3459612867606927, | |
| "learning_rate": 1.5971585917027864e-05, | |
| "loss": 0.9962, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.37204997686256364, | |
| "grad_norm": 1.4053767425847852, | |
| "learning_rate": 1.5814920712880267e-05, | |
| "loss": 0.9456, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.37760296159185563, | |
| "grad_norm": 1.2542630494816203, | |
| "learning_rate": 1.5656068754865388e-05, | |
| "loss": 0.9625, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.38315594632114763, | |
| "grad_norm": 1.2467268401516984, | |
| "learning_rate": 1.5495089780708062e-05, | |
| "loss": 0.9416, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.38870893105043963, | |
| "grad_norm": 1.3642420280912566, | |
| "learning_rate": 1.5332044328016916e-05, | |
| "loss": 0.9745, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.39426191577973163, | |
| "grad_norm": 1.370419991211419, | |
| "learning_rate": 1.5166993711518631e-05, | |
| "loss": 0.9235, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.3998149005090236, | |
| "grad_norm": 1.4175545037228292, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.9419, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4053678852383156, | |
| "grad_norm": 1.5230125115585145, | |
| "learning_rate": 1.4831125992966386e-05, | |
| "loss": 0.9482, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.41092086996760757, | |
| "grad_norm": 1.3243119971736406, | |
| "learning_rate": 1.4660435197025391e-05, | |
| "loss": 0.9516, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.41647385469689957, | |
| "grad_norm": 1.3168758353005081, | |
| "learning_rate": 1.4487991802004625e-05, | |
| "loss": 0.9274, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.42202683942619157, | |
| "grad_norm": 1.3316158417964403, | |
| "learning_rate": 1.4313860656812537e-05, | |
| "loss": 0.9279, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.42757982415548357, | |
| "grad_norm": 1.2112610899992784, | |
| "learning_rate": 1.4138107245051394e-05, | |
| "loss": 0.9604, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.43313280888477557, | |
| "grad_norm": 1.4256068345744652, | |
| "learning_rate": 1.396079766039157e-05, | |
| "loss": 0.9504, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.43868579361406757, | |
| "grad_norm": 1.48676297842706, | |
| "learning_rate": 1.3781998581716427e-05, | |
| "loss": 0.9783, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.44423877834335956, | |
| "grad_norm": 1.3917645840392392, | |
| "learning_rate": 1.3601777248047105e-05, | |
| "loss": 0.9428, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.44423877834335956, | |
| "eval_loss": 0.975586473941803, | |
| "eval_runtime": 13.0584, | |
| "eval_samples_per_second": 19.604, | |
| "eval_steps_per_second": 4.901, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.44979176307265156, | |
| "grad_norm": 1.3230682794396744, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.9477, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.45534474780194356, | |
| "grad_norm": 1.2045267312184351, | |
| "learning_rate": 1.3237339420583213e-05, | |
| "loss": 0.9568, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.46089773253123556, | |
| "grad_norm": 1.2839147189555775, | |
| "learning_rate": 1.3053259976951134e-05, | |
| "loss": 0.9256, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.46645071726052756, | |
| "grad_norm": 1.284551507215065, | |
| "learning_rate": 1.2868032327110904e-05, | |
| "loss": 0.9246, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4720037019898195, | |
| "grad_norm": 1.3021372211969566, | |
| "learning_rate": 1.2681726127606374e-05, | |
| "loss": 0.9527, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4775566867191115, | |
| "grad_norm": 1.3264954697360052, | |
| "learning_rate": 1.2494411440579814e-05, | |
| "loss": 0.9659, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.4831096714484035, | |
| "grad_norm": 1.2931203310254533, | |
| "learning_rate": 1.2306158707424402e-05, | |
| "loss": 0.9044, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.4886626561776955, | |
| "grad_norm": 1.5033726081614123, | |
| "learning_rate": 1.211703872229411e-05, | |
| "loss": 0.9135, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.4942156409069875, | |
| "grad_norm": 1.2465062347279259, | |
| "learning_rate": 1.1927122605480899e-05, | |
| "loss": 0.9382, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.4997686256362795, | |
| "grad_norm": 1.2206738144949079, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.9429, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5053216103655715, | |
| "grad_norm": 1.268246804784844, | |
| "learning_rate": 1.1545187928078407e-05, | |
| "loss": 0.9163, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.5108745950948634, | |
| "grad_norm": 1.1842171344447763, | |
| "learning_rate": 1.1353312997501313e-05, | |
| "loss": 0.9296, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5164275798241554, | |
| "grad_norm": 1.3329158977326516, | |
| "learning_rate": 1.1160929141252303e-05, | |
| "loss": 0.9536, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5219805645534474, | |
| "grad_norm": 1.3140264320853574, | |
| "learning_rate": 1.0968108707031792e-05, | |
| "loss": 0.9314, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5275335492827394, | |
| "grad_norm": 1.2112452453436886, | |
| "learning_rate": 1.077492420671931e-05, | |
| "loss": 0.8858, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5330865340120314, | |
| "grad_norm": 1.244066114064373, | |
| "learning_rate": 1.0581448289104759e-05, | |
| "loss": 0.938, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5386395187413234, | |
| "grad_norm": 1.2958379438943313, | |
| "learning_rate": 1.038775371256817e-05, | |
| "loss": 0.9366, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.5441925034706154, | |
| "grad_norm": 1.2706792533588414, | |
| "learning_rate": 1.0193913317718245e-05, | |
| "loss": 0.9809, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5497454881999074, | |
| "grad_norm": 1.2373793128051882, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9107, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.5552984729291994, | |
| "grad_norm": 1.3259462807230906, | |
| "learning_rate": 9.806086682281759e-06, | |
| "loss": 0.9478, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5552984729291994, | |
| "eval_loss": 0.9645185470581055, | |
| "eval_runtime": 14.0973, | |
| "eval_samples_per_second": 18.16, | |
| "eval_steps_per_second": 4.54, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5608514576584914, | |
| "grad_norm": 1.2818749562353056, | |
| "learning_rate": 9.612246287431832e-06, | |
| "loss": 0.9157, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.5664044423877834, | |
| "grad_norm": 1.2789066996692675, | |
| "learning_rate": 9.418551710895243e-06, | |
| "loss": 0.9715, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5719574271170754, | |
| "grad_norm": 1.3159690301384173, | |
| "learning_rate": 9.225075793280693e-06, | |
| "loss": 0.9564, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.5775104118463674, | |
| "grad_norm": 1.1820999233185365, | |
| "learning_rate": 9.03189129296821e-06, | |
| "loss": 0.9333, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5830633965756594, | |
| "grad_norm": 2.9705367947063595, | |
| "learning_rate": 8.839070858747697e-06, | |
| "loss": 0.9393, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5886163813049514, | |
| "grad_norm": 1.1578484132538005, | |
| "learning_rate": 8.646687002498692e-06, | |
| "loss": 0.9386, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5941693660342434, | |
| "grad_norm": 1.2495396181990488, | |
| "learning_rate": 8.454812071921597e-06, | |
| "loss": 0.9202, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.5997223507635354, | |
| "grad_norm": 1.18243382811664, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.9222, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6052753354928274, | |
| "grad_norm": 1.2247856999180733, | |
| "learning_rate": 8.072877394519103e-06, | |
| "loss": 0.9426, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.6108283202221194, | |
| "grad_norm": 1.220145252189745, | |
| "learning_rate": 7.882961277705897e-06, | |
| "loss": 0.9161, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6163813049514114, | |
| "grad_norm": 1.2450054960684753, | |
| "learning_rate": 7.6938412925756e-06, | |
| "loss": 0.9419, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.6219342896807034, | |
| "grad_norm": 1.2450637061923184, | |
| "learning_rate": 7.505588559420188e-06, | |
| "loss": 0.9471, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6274872744099954, | |
| "grad_norm": 1.2160705969336116, | |
| "learning_rate": 7.3182738723936255e-06, | |
| "loss": 0.9446, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.6330402591392874, | |
| "grad_norm": 1.2857156644799776, | |
| "learning_rate": 7.131967672889101e-06, | |
| "loss": 0.9473, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6385932438685794, | |
| "grad_norm": 1.1688923012156514, | |
| "learning_rate": 6.94674002304887e-06, | |
| "loss": 0.9193, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6441462285978714, | |
| "grad_norm": 1.3240345620915759, | |
| "learning_rate": 6.762660579416791e-06, | |
| "loss": 0.955, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6496992133271634, | |
| "grad_norm": 1.171487612102084, | |
| "learning_rate": 6.579798566743314e-06, | |
| "loss": 0.9345, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.6552521980564553, | |
| "grad_norm": 1.1809918233177483, | |
| "learning_rate": 6.3982227519528986e-06, | |
| "loss": 0.9317, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6608051827857473, | |
| "grad_norm": 1.1849135550680583, | |
| "learning_rate": 6.218001418283577e-06, | |
| "loss": 0.9282, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.6663581675150393, | |
| "grad_norm": 1.2353428612054926, | |
| "learning_rate": 6.039202339608432e-06, | |
| "loss": 0.9186, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6663581675150393, | |
| "eval_loss": 0.9549762010574341, | |
| "eval_runtime": 13.1058, | |
| "eval_samples_per_second": 19.533, | |
| "eval_steps_per_second": 4.883, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6719111522443313, | |
| "grad_norm": 1.2260206730700363, | |
| "learning_rate": 5.8618927549486095e-06, | |
| "loss": 0.91, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.6774641369736233, | |
| "grad_norm": 1.2511346515975978, | |
| "learning_rate": 5.686139343187468e-06, | |
| "loss": 0.9445, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6830171217029153, | |
| "grad_norm": 1.1415920400151276, | |
| "learning_rate": 5.512008197995379e-06, | |
| "loss": 0.9267, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.6885701064322073, | |
| "grad_norm": 1.1718028560057823, | |
| "learning_rate": 5.339564802974615e-06, | |
| "loss": 0.9173, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6941230911614993, | |
| "grad_norm": 1.1427826499364968, | |
| "learning_rate": 5.168874007033615e-06, | |
| "loss": 0.9113, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.6996760758907913, | |
| "grad_norm": 1.1646711162888848, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.9314, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7052290606200833, | |
| "grad_norm": 1.1666389482954498, | |
| "learning_rate": 4.8330062884813714e-06, | |
| "loss": 0.949, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.7107820453493753, | |
| "grad_norm": 1.2669383225264854, | |
| "learning_rate": 4.66795567198309e-06, | |
| "loss": 0.9298, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7163350300786673, | |
| "grad_norm": 1.1727436218210467, | |
| "learning_rate": 4.504910219291941e-06, | |
| "loss": 0.9384, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.7218880148079593, | |
| "grad_norm": 1.160141429869342, | |
| "learning_rate": 4.343931245134616e-06, | |
| "loss": 0.9231, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7274409995372513, | |
| "grad_norm": 1.1571744280380951, | |
| "learning_rate": 4.185079287119733e-06, | |
| "loss": 0.9379, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.7329939842665433, | |
| "grad_norm": 1.2080957370089618, | |
| "learning_rate": 4.028414082972141e-06, | |
| "loss": 0.9087, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7385469689958353, | |
| "grad_norm": 1.2262375492125892, | |
| "learning_rate": 3.873994548067972e-06, | |
| "loss": 0.9175, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.7440999537251273, | |
| "grad_norm": 1.1868816861234752, | |
| "learning_rate": 3.7218787532790167e-06, | |
| "loss": 0.915, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7496529384544193, | |
| "grad_norm": 1.2149836180874647, | |
| "learning_rate": 3.5721239031346067e-06, | |
| "loss": 0.9359, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7552059231837113, | |
| "grad_norm": 1.1401883150941166, | |
| "learning_rate": 3.424786314309365e-06, | |
| "loss": 0.8996, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7607589079130033, | |
| "grad_norm": 1.1918737445166034, | |
| "learning_rate": 3.279921394444776e-06, | |
| "loss": 0.9478, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.7663118926422953, | |
| "grad_norm": 1.1601543056853199, | |
| "learning_rate": 3.1375836213126653e-06, | |
| "loss": 0.9144, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7718648773715873, | |
| "grad_norm": 1.1849230333131153, | |
| "learning_rate": 2.9978265223283152e-06, | |
| "loss": 0.9134, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.7774178621008793, | |
| "grad_norm": 1.1922764155084293, | |
| "learning_rate": 2.8607026544210115e-06, | |
| "loss": 0.9184, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7774178621008793, | |
| "eval_loss": 0.9487817287445068, | |
| "eval_runtime": 12.9966, | |
| "eval_samples_per_second": 19.697, | |
| "eval_steps_per_second": 4.924, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7829708468301713, | |
| "grad_norm": 1.0668112491118575, | |
| "learning_rate": 2.726263584269513e-06, | |
| "loss": 0.9038, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.7885238315594633, | |
| "grad_norm": 1.191610088893989, | |
| "learning_rate": 2.594559868909956e-06, | |
| "loss": 0.9003, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7940768162887553, | |
| "grad_norm": 1.2465046516243472, | |
| "learning_rate": 2.4656410367233928e-06, | |
| "loss": 0.9215, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.7996298010180471, | |
| "grad_norm": 1.1463175579772371, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.9303, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8051827857473391, | |
| "grad_norm": 1.1279074050372055, | |
| "learning_rate": 2.2163508807584e-06, | |
| "loss": 0.9294, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.8107357704766311, | |
| "grad_norm": 1.1668600336379225, | |
| "learning_rate": 2.0960733048124082e-06, | |
| "loss": 0.9082, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8162887552059231, | |
| "grad_norm": 1.1280124295582716, | |
| "learning_rate": 1.9787680724495617e-06, | |
| "loss": 0.898, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.8218417399352151, | |
| "grad_norm": 1.2693061690074205, | |
| "learning_rate": 1.8644792973703252e-06, | |
| "loss": 0.9473, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.8273947246645071, | |
| "grad_norm": 1.0935688113313613, | |
| "learning_rate": 1.7532499589089324e-06, | |
| "loss": 0.9312, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.8329477093937991, | |
| "grad_norm": 1.1491375579091732, | |
| "learning_rate": 1.6451218858706374e-06, | |
| "loss": 0.9295, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8385006941230911, | |
| "grad_norm": 1.1971381545639446, | |
| "learning_rate": 1.5401357408015893e-06, | |
| "loss": 0.8977, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.8440536788523831, | |
| "grad_norm": 1.2118976466189748, | |
| "learning_rate": 1.4383310046973365e-06, | |
| "loss": 0.9201, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8496066635816751, | |
| "grad_norm": 1.1129578498310642, | |
| "learning_rate": 1.339745962155613e-06, | |
| "loss": 0.9235, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.8551596483109671, | |
| "grad_norm": 1.155034707390975, | |
| "learning_rate": 1.2444176869790925e-06, | |
| "loss": 0.906, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8607126330402591, | |
| "grad_norm": 1.1211050312494577, | |
| "learning_rate": 1.152382028233422e-06, | |
| "loss": 0.9027, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.8662656177695511, | |
| "grad_norm": 1.161462499770876, | |
| "learning_rate": 1.0636735967658785e-06, | |
| "loss": 0.902, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8718186024988431, | |
| "grad_norm": 1.2466679714276248, | |
| "learning_rate": 9.783257521896228e-07, | |
| "loss": 0.9312, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.8773715872281351, | |
| "grad_norm": 1.1688203046154668, | |
| "learning_rate": 8.963705903385344e-07, | |
| "loss": 0.9231, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8829245719574271, | |
| "grad_norm": 1.1446515266652288, | |
| "learning_rate": 8.178389311972612e-07, | |
| "loss": 0.924, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.8884775566867191, | |
| "grad_norm": 1.1971045442791841, | |
| "learning_rate": 7.427603073110967e-07, | |
| "loss": 0.8564, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8884775566867191, | |
| "eval_loss": 0.9455364346504211, | |
| "eval_runtime": 13.3345, | |
| "eval_samples_per_second": 19.198, | |
| "eval_steps_per_second": 4.8, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8940305414160111, | |
| "grad_norm": 1.158461858290895, | |
| "learning_rate": 6.711629526799946e-07, | |
| "loss": 0.9399, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.8995835261453031, | |
| "grad_norm": 1.1264872944659339, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.8946, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.9051365108745951, | |
| "grad_norm": 1.122295252126309, | |
| "learning_rate": 5.385184312424973e-07, | |
| "loss": 0.9228, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.9106894956038871, | |
| "grad_norm": 1.130327163633901, | |
| "learning_rate": 4.775211466158469e-07, | |
| "loss": 0.9278, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.9162424803331791, | |
| "grad_norm": 1.152980775746581, | |
| "learning_rate": 4.2010487684511105e-07, | |
| "loss": 0.9105, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.9217954650624711, | |
| "grad_norm": 1.2630255671771575, | |
| "learning_rate": 3.662912138411967e-07, | |
| "loss": 0.9103, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.9273484497917631, | |
| "grad_norm": 1.1212305446295874, | |
| "learning_rate": 3.161003947219421e-07, | |
| "loss": 0.8847, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.9329014345210551, | |
| "grad_norm": 1.1635748807768116, | |
| "learning_rate": 2.6955129420176193e-07, | |
| "loss": 0.9139, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9384544192503471, | |
| "grad_norm": 1.101552910147697, | |
| "learning_rate": 2.2666141749364434e-07, | |
| "loss": 0.9233, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.944007403979639, | |
| "grad_norm": 1.1104286718600382, | |
| "learning_rate": 1.874468937261531e-07, | |
| "loss": 0.8872, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.949560388708931, | |
| "grad_norm": 1.1513796874736284, | |
| "learning_rate": 1.519224698779198e-07, | |
| "loss": 0.938, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.955113373438223, | |
| "grad_norm": 1.172996631179348, | |
| "learning_rate": 1.201015052319099e-07, | |
| "loss": 0.9366, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.960666358167515, | |
| "grad_norm": 1.178813337349509, | |
| "learning_rate": 9.199596635154684e-08, | |
| "loss": 0.9382, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.966219342896807, | |
| "grad_norm": 1.123260974533791, | |
| "learning_rate": 6.761642258056977e-08, | |
| "loss": 0.8969, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.971772327626099, | |
| "grad_norm": 1.2440553964560856, | |
| "learning_rate": 4.6972042068341714e-08, | |
| "loss": 0.9125, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.977325312355391, | |
| "grad_norm": 1.100622329056596, | |
| "learning_rate": 3.0070588322079765e-08, | |
| "loss": 0.9106, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.982878297084683, | |
| "grad_norm": 1.224884941200071, | |
| "learning_rate": 1.6918417287318245e-08, | |
| "loss": 0.9045, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.988431281813975, | |
| "grad_norm": 1.1506168883594277, | |
| "learning_rate": 7.520474957699586e-09, | |
| "loss": 0.9341, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.993984266543267, | |
| "grad_norm": 1.3030322318546892, | |
| "learning_rate": 1.8802955149865854e-09, | |
| "loss": 0.9093, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.999537251272559, | |
| "grad_norm": 1.164399511709177, | |
| "learning_rate": 0.0, | |
| "loss": 0.943, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.999537251272559, | |
| "eval_loss": 0.9448966979980469, | |
| "eval_runtime": 12.8793, | |
| "eval_samples_per_second": 19.877, | |
| "eval_steps_per_second": 4.969, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.999537251272559, | |
| "step": 900, | |
| "total_flos": 37979261239296.0, | |
| "train_loss": 0.9636553647783067, | |
| "train_runtime": 8704.1469, | |
| "train_samples_per_second": 4.965, | |
| "train_steps_per_second": 0.103 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 900, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 37979261239296.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |