| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9988901220865705, | |
| "eval_steps": 100, | |
| "global_step": 450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011098779134295227, | |
| "grad_norm": 0.32028938698735326, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 1.1057, | |
| "mean_token_accuracy": 0.7074955803776843, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022197558268590455, | |
| "grad_norm": 0.19534757580522985, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 1.0688, | |
| "mean_token_accuracy": 0.7163213776876576, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.033296337402885685, | |
| "grad_norm": 0.1962807122200424, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.0285, | |
| "mean_token_accuracy": 0.7219675252672673, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04439511653718091, | |
| "grad_norm": 0.17661044382753963, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.9569, | |
| "mean_token_accuracy": 0.7338179788852269, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05549389567147614, | |
| "grad_norm": 0.13298871259606682, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 0.96, | |
| "mean_token_accuracy": 0.7289285538378297, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06659267480577137, | |
| "grad_norm": 0.10139226456438258, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.9003, | |
| "mean_token_accuracy": 0.7429319064764655, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07769145394006659, | |
| "grad_norm": 0.09671244610636456, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 0.8848, | |
| "mean_token_accuracy": 0.7450362054794413, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08879023307436182, | |
| "grad_norm": 0.10358003016336022, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.8681, | |
| "mean_token_accuracy": 0.7483839065381315, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09988901220865705, | |
| "grad_norm": 0.07881610121393638, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8442, | |
| "mean_token_accuracy": 0.7542158990266088, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11098779134295228, | |
| "grad_norm": 0.07695709459998314, | |
| "learning_rate": 1.9992479525042305e-05, | |
| "loss": 0.8202, | |
| "mean_token_accuracy": 0.7594429564506759, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1220865704772475, | |
| "grad_norm": 0.0770940463572419, | |
| "learning_rate": 1.996992941167792e-05, | |
| "loss": 0.8204, | |
| "mean_token_accuracy": 0.7596416663786116, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13318534961154274, | |
| "grad_norm": 0.07120273045521322, | |
| "learning_rate": 1.9932383577419432e-05, | |
| "loss": 0.819, | |
| "mean_token_accuracy": 0.7587201214083239, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14428412874583796, | |
| "grad_norm": 0.07558536731907865, | |
| "learning_rate": 1.9879898494768093e-05, | |
| "loss": 0.8027, | |
| "mean_token_accuracy": 0.7628218193365146, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.15538290788013318, | |
| "grad_norm": 0.0724884828137313, | |
| "learning_rate": 1.9812553106273848e-05, | |
| "loss": 0.8126, | |
| "mean_token_accuracy": 0.7601266253946841, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16648168701442842, | |
| "grad_norm": 0.0721988261195697, | |
| "learning_rate": 1.973044870579824e-05, | |
| "loss": 0.8027, | |
| "mean_token_accuracy": 0.7625601714037885, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17758046614872364, | |
| "grad_norm": 0.07812772834648507, | |
| "learning_rate": 1.9633708786158803e-05, | |
| "loss": 0.803, | |
| "mean_token_accuracy": 0.7625912882794786, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18867924528301888, | |
| "grad_norm": 0.06226943817830889, | |
| "learning_rate": 1.9522478853384154e-05, | |
| "loss": 0.7936, | |
| "mean_token_accuracy": 0.7635993724131902, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1997780244173141, | |
| "grad_norm": 0.0695985028428393, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.7841, | |
| "mean_token_accuracy": 0.7661331851833721, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21087680355160932, | |
| "grad_norm": 0.07119143212066893, | |
| "learning_rate": 1.9257239692688907e-05, | |
| "loss": 0.7904, | |
| "mean_token_accuracy": 0.7651270507722707, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.22197558268590456, | |
| "grad_norm": 0.06900642736695052, | |
| "learning_rate": 1.9103629409661468e-05, | |
| "loss": 0.7805, | |
| "mean_token_accuracy": 0.7667522330276506, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22197558268590456, | |
| "eval_loss": 0.8109510540962219, | |
| "eval_mean_token_accuracy": 0.7568694476131612, | |
| "eval_runtime": 2.9489, | |
| "eval_samples_per_second": 43.744, | |
| "eval_steps_per_second": 3.73, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23307436182019978, | |
| "grad_norm": 0.07584475595205237, | |
| "learning_rate": 1.8936326403234125e-05, | |
| "loss": 0.7819, | |
| "mean_token_accuracy": 0.7674415677558553, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.244173140954495, | |
| "grad_norm": 0.06583872042093958, | |
| "learning_rate": 1.8755582313020912e-05, | |
| "loss": 0.7819, | |
| "mean_token_accuracy": 0.766467737858396, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.25527192008879024, | |
| "grad_norm": 0.07082657098771901, | |
| "learning_rate": 1.8561668995302668e-05, | |
| "loss": 0.7831, | |
| "mean_token_accuracy": 0.76569958171409, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2663706992230855, | |
| "grad_norm": 0.06762014391699019, | |
| "learning_rate": 1.8354878114129368e-05, | |
| "loss": 0.7729, | |
| "mean_token_accuracy": 0.7691614712931135, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.27746947835738067, | |
| "grad_norm": 0.06572171584857384, | |
| "learning_rate": 1.8135520702629677e-05, | |
| "loss": 0.7727, | |
| "mean_token_accuracy": 0.7692371318506055, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2885682574916759, | |
| "grad_norm": 0.07387797497484562, | |
| "learning_rate": 1.7903926695187595e-05, | |
| "loss": 0.7748, | |
| "mean_token_accuracy": 0.767360264364967, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.29966703662597116, | |
| "grad_norm": 0.0648507090395773, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.7876, | |
| "mean_token_accuracy": 0.7646269472458946, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.31076581576026635, | |
| "grad_norm": 0.07594530254646713, | |
| "learning_rate": 1.740544013109005e-05, | |
| "loss": 0.763, | |
| "mean_token_accuracy": 0.7709959638413746, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3218645948945616, | |
| "grad_norm": 0.0732533507550857, | |
| "learning_rate": 1.7139297345578992e-05, | |
| "loss": 0.783, | |
| "mean_token_accuracy": 0.7649811510602629, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.33296337402885684, | |
| "grad_norm": 0.06649981966991503, | |
| "learning_rate": 1.686241637868734e-05, | |
| "loss": 0.7699, | |
| "mean_token_accuracy": 0.7692172433619623, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.34406215316315203, | |
| "grad_norm": 0.0663190385068203, | |
| "learning_rate": 1.657521368569064e-05, | |
| "loss": 0.7701, | |
| "mean_token_accuracy": 0.7685507996235139, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.3551609322974473, | |
| "grad_norm": 0.07086248919589423, | |
| "learning_rate": 1.627812124672099e-05, | |
| "loss": 0.7916, | |
| "mean_token_accuracy": 0.762897097306175, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3662597114317425, | |
| "grad_norm": 0.06620650991928366, | |
| "learning_rate": 1.5971585917027864e-05, | |
| "loss": 0.7802, | |
| "mean_token_accuracy": 0.7649210363933718, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.37735849056603776, | |
| "grad_norm": 0.06905926805248713, | |
| "learning_rate": 1.5656068754865388e-05, | |
| "loss": 0.7677, | |
| "mean_token_accuracy": 0.7696914957690235, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.38845726970033295, | |
| "grad_norm": 0.07914298364560284, | |
| "learning_rate": 1.5332044328016916e-05, | |
| "loss": 0.7672, | |
| "mean_token_accuracy": 0.7682120122871129, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3995560488346282, | |
| "grad_norm": 0.07115670436565744, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.7774, | |
| "mean_token_accuracy": 0.7662370568414045, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.41065482796892344, | |
| "grad_norm": 0.06396528657795297, | |
| "learning_rate": 1.4660435197025391e-05, | |
| "loss": 0.7478, | |
| "mean_token_accuracy": 0.7749828723486186, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.42175360710321863, | |
| "grad_norm": 0.0628671379282561, | |
| "learning_rate": 1.4313860656812537e-05, | |
| "loss": 0.7527, | |
| "mean_token_accuracy": 0.7723581904090526, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4328523862375139, | |
| "grad_norm": 0.06693399129139697, | |
| "learning_rate": 1.396079766039157e-05, | |
| "loss": 0.7709, | |
| "mean_token_accuracy": 0.768176693477312, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.4439511653718091, | |
| "grad_norm": 0.06898843383807368, | |
| "learning_rate": 1.3601777248047105e-05, | |
| "loss": 0.7558, | |
| "mean_token_accuracy": 0.7725129471022092, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4439511653718091, | |
| "eval_loss": 0.7829984426498413, | |
| "eval_mean_token_accuracy": 0.7632673514716071, | |
| "eval_runtime": 2.5178, | |
| "eval_samples_per_second": 51.234, | |
| "eval_steps_per_second": 4.369, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4550499445061043, | |
| "grad_norm": 0.06712291331425221, | |
| "learning_rate": 1.3237339420583213e-05, | |
| "loss": 0.7423, | |
| "mean_token_accuracy": 0.7751750598902079, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.46614872364039955, | |
| "grad_norm": 0.07066852759980123, | |
| "learning_rate": 1.2868032327110904e-05, | |
| "loss": 0.7847, | |
| "mean_token_accuracy": 0.7637066112136016, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4772475027746948, | |
| "grad_norm": 0.06797517881945832, | |
| "learning_rate": 1.2494411440579814e-05, | |
| "loss": 0.7627, | |
| "mean_token_accuracy": 0.7701866684088337, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.48834628190899, | |
| "grad_norm": 0.0740366450868316, | |
| "learning_rate": 1.211703872229411e-05, | |
| "loss": 0.7554, | |
| "mean_token_accuracy": 0.7726324974593143, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.49944506104328523, | |
| "grad_norm": 0.06603564857589732, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.7703, | |
| "mean_token_accuracy": 0.7674938853021173, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.5105438401775805, | |
| "grad_norm": 0.06456424170382646, | |
| "learning_rate": 1.1353312997501313e-05, | |
| "loss": 0.7681, | |
| "mean_token_accuracy": 0.7680860839714745, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5216426193118757, | |
| "grad_norm": 0.0680877993193484, | |
| "learning_rate": 1.0968108707031792e-05, | |
| "loss": 0.7568, | |
| "mean_token_accuracy": 0.7713919990696916, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.532741398446171, | |
| "grad_norm": 0.06457964510433087, | |
| "learning_rate": 1.0581448289104759e-05, | |
| "loss": 0.7489, | |
| "mean_token_accuracy": 0.7742981274310832, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5438401775804661, | |
| "grad_norm": 0.06309191183030195, | |
| "learning_rate": 1.0193913317718245e-05, | |
| "loss": 0.7518, | |
| "mean_token_accuracy": 0.7737425585967734, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.5549389567147613, | |
| "grad_norm": 0.06092764730736236, | |
| "learning_rate": 9.806086682281759e-06, | |
| "loss": 0.761, | |
| "mean_token_accuracy": 0.7695176080139992, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5660377358490566, | |
| "grad_norm": 0.06517875424025751, | |
| "learning_rate": 9.418551710895243e-06, | |
| "loss": 0.7451, | |
| "mean_token_accuracy": 0.7737921205376608, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.5771365149833518, | |
| "grad_norm": 0.06586926609081382, | |
| "learning_rate": 9.03189129296821e-06, | |
| "loss": 0.7272, | |
| "mean_token_accuracy": 0.7790233444795842, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.06455882882155867, | |
| "learning_rate": 8.646687002498692e-06, | |
| "loss": 0.7493, | |
| "mean_token_accuracy": 0.7728544867539606, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5993340732519423, | |
| "grad_norm": 0.06419037506595338, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.7447, | |
| "mean_token_accuracy": 0.774466472618278, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6104328523862376, | |
| "grad_norm": 0.06483038923609051, | |
| "learning_rate": 7.882961277705897e-06, | |
| "loss": 0.7467, | |
| "mean_token_accuracy": 0.7736083802309587, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.6215316315205327, | |
| "grad_norm": 0.06889145412976934, | |
| "learning_rate": 7.505588559420188e-06, | |
| "loss": 0.7423, | |
| "mean_token_accuracy": 0.7752051151920257, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.632630410654828, | |
| "grad_norm": 0.06931221562176564, | |
| "learning_rate": 7.131967672889101e-06, | |
| "loss": 0.7766, | |
| "mean_token_accuracy": 0.7648978880464531, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.6437291897891232, | |
| "grad_norm": 0.0645937272519637, | |
| "learning_rate": 6.762660579416791e-06, | |
| "loss": 0.7529, | |
| "mean_token_accuracy": 0.7729185441854456, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6548279689234184, | |
| "grad_norm": 0.06415673551420226, | |
| "learning_rate": 6.3982227519528986e-06, | |
| "loss": 0.7601, | |
| "mean_token_accuracy": 0.7699141088391924, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.6659267480577137, | |
| "grad_norm": 0.06845419068799381, | |
| "learning_rate": 6.039202339608432e-06, | |
| "loss": 0.7519, | |
| "mean_token_accuracy": 0.77195855669696, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6659267480577137, | |
| "eval_loss": 0.7694035172462463, | |
| "eval_mean_token_accuracy": 0.7656926514001757, | |
| "eval_runtime": 2.5109, | |
| "eval_samples_per_second": 51.376, | |
| "eval_steps_per_second": 4.381, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6770255271920089, | |
| "grad_norm": 0.06481669897887246, | |
| "learning_rate": 5.686139343187468e-06, | |
| "loss": 0.7368, | |
| "mean_token_accuracy": 0.7768982703775535, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.6881243063263041, | |
| "grad_norm": 0.06555414493127953, | |
| "learning_rate": 5.339564802974615e-06, | |
| "loss": 0.7496, | |
| "mean_token_accuracy": 0.7741114122022307, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6992230854605993, | |
| "grad_norm": 0.06321637577126818, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.7379, | |
| "mean_token_accuracy": 0.7763521164662632, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.7103218645948945, | |
| "grad_norm": 0.06534174478047594, | |
| "learning_rate": 4.66795567198309e-06, | |
| "loss": 0.7186, | |
| "mean_token_accuracy": 0.7821842581348311, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7214206437291898, | |
| "grad_norm": 0.0656418642194091, | |
| "learning_rate": 4.343931245134616e-06, | |
| "loss": 0.7429, | |
| "mean_token_accuracy": 0.7750543137352807, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.732519422863485, | |
| "grad_norm": 0.06142434056090795, | |
| "learning_rate": 4.028414082972141e-06, | |
| "loss": 0.7432, | |
| "mean_token_accuracy": 0.775647557164172, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7436182019977803, | |
| "grad_norm": 0.06566009724006543, | |
| "learning_rate": 3.7218787532790167e-06, | |
| "loss": 0.7527, | |
| "mean_token_accuracy": 0.7717515416461624, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.7547169811320755, | |
| "grad_norm": 0.06813787133901092, | |
| "learning_rate": 3.424786314309365e-06, | |
| "loss": 0.7397, | |
| "mean_token_accuracy": 0.7761784463020833, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7658157602663707, | |
| "grad_norm": 0.061296004900329354, | |
| "learning_rate": 3.1375836213126653e-06, | |
| "loss": 0.7547, | |
| "mean_token_accuracy": 0.7708365795261976, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7769145394006659, | |
| "grad_norm": 0.06086151158973008, | |
| "learning_rate": 2.8607026544210115e-06, | |
| "loss": 0.7449, | |
| "mean_token_accuracy": 0.7737567810246656, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7880133185349611, | |
| "grad_norm": 0.06066361422328344, | |
| "learning_rate": 2.594559868909956e-06, | |
| "loss": 0.7526, | |
| "mean_token_accuracy": 0.7728921789426538, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.7991120976692564, | |
| "grad_norm": 0.061244946934632546, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.7428, | |
| "mean_token_accuracy": 0.7745905285585644, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8102108768035516, | |
| "grad_norm": 0.059950100330008936, | |
| "learning_rate": 2.0960733048124082e-06, | |
| "loss": 0.735, | |
| "mean_token_accuracy": 0.7771190685426068, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.8213096559378469, | |
| "grad_norm": 0.062267646898023575, | |
| "learning_rate": 1.8644792973703252e-06, | |
| "loss": 0.757, | |
| "mean_token_accuracy": 0.7711234095884432, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.832408435072142, | |
| "grad_norm": 0.05795250590930739, | |
| "learning_rate": 1.6451218858706374e-06, | |
| "loss": 0.7396, | |
| "mean_token_accuracy": 0.7762826225755755, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8435072142064373, | |
| "grad_norm": 0.05646366375927419, | |
| "learning_rate": 1.4383310046973365e-06, | |
| "loss": 0.742, | |
| "mean_token_accuracy": 0.7754256081182773, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8546059933407325, | |
| "grad_norm": 0.05933272693822518, | |
| "learning_rate": 1.2444176869790925e-06, | |
| "loss": 0.7457, | |
| "mean_token_accuracy": 0.7742744235316502, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.8657047724750278, | |
| "grad_norm": 0.057540816299949595, | |
| "learning_rate": 1.0636735967658785e-06, | |
| "loss": 0.736, | |
| "mean_token_accuracy": 0.7765978708392828, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.876803551609323, | |
| "grad_norm": 0.05844756012864216, | |
| "learning_rate": 8.963705903385344e-07, | |
| "loss": 0.7183, | |
| "mean_token_accuracy": 0.7822006045277151, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.8879023307436182, | |
| "grad_norm": 0.05810320914079056, | |
| "learning_rate": 7.427603073110967e-07, | |
| "loss": 0.7442, | |
| "mean_token_accuracy": 0.7742584918108283, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8879023307436182, | |
| "eval_loss": 0.7638587951660156, | |
| "eval_mean_token_accuracy": 0.7671856273651642, | |
| "eval_runtime": 2.5128, | |
| "eval_samples_per_second": 51.338, | |
| "eval_steps_per_second": 4.378, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8990011098779135, | |
| "grad_norm": 0.05687291272451405, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.7355, | |
| "mean_token_accuracy": 0.7774604937569412, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.9100998890122086, | |
| "grad_norm": 0.05899588715439542, | |
| "learning_rate": 4.775211466158469e-07, | |
| "loss": 0.7319, | |
| "mean_token_accuracy": 0.7774400412989902, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9211986681465039, | |
| "grad_norm": 0.05577638815550462, | |
| "learning_rate": 3.662912138411967e-07, | |
| "loss": 0.7178, | |
| "mean_token_accuracy": 0.7821916392303806, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.9322974472807991, | |
| "grad_norm": 0.05865365285983047, | |
| "learning_rate": 2.6955129420176193e-07, | |
| "loss": 0.7309, | |
| "mean_token_accuracy": 0.778973121325068, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9433962264150944, | |
| "grad_norm": 0.06038263301804733, | |
| "learning_rate": 1.874468937261531e-07, | |
| "loss": 0.7372, | |
| "mean_token_accuracy": 0.7765551528106018, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9544950055493896, | |
| "grad_norm": 0.059800638962906945, | |
| "learning_rate": 1.201015052319099e-07, | |
| "loss": 0.7291, | |
| "mean_token_accuracy": 0.7794756294446461, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9655937846836848, | |
| "grad_norm": 0.056012625483331906, | |
| "learning_rate": 6.761642258056977e-08, | |
| "loss": 0.7255, | |
| "mean_token_accuracy": 0.7798846256811043, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.97669256381798, | |
| "grad_norm": 0.055552002158992475, | |
| "learning_rate": 3.0070588322079765e-08, | |
| "loss": 0.7351, | |
| "mean_token_accuracy": 0.7766328434320331, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9877913429522752, | |
| "grad_norm": 0.05677914033692145, | |
| "learning_rate": 7.520474957699586e-09, | |
| "loss": 0.7351, | |
| "mean_token_accuracy": 0.7767306519256947, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.9988901220865705, | |
| "grad_norm": 0.06170289905752787, | |
| "learning_rate": 0.0, | |
| "loss": 0.7528, | |
| "mean_token_accuracy": 0.7717083040396344, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9988901220865705, | |
| "step": 450, | |
| "total_flos": 6.086450124265882e+17, | |
| "train_loss": 0.7795855527453952, | |
| "train_runtime": 1563.698, | |
| "train_samples_per_second": 13.828, | |
| "train_steps_per_second": 0.288 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 450, | |
| "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": 6.086450124265882e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |