| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 30, |
| "global_step": 450, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.022222222222222223, |
| "grad_norm": 0.3012203276157379, |
| "learning_rate": 9.987820251299122e-05, |
| "loss": 0.3486, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.044444444444444446, |
| "grad_norm": 0.19629184901714325, |
| "learning_rate": 9.951340343707852e-05, |
| "loss": 0.0694, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06666666666666667, |
| "grad_norm": 0.1222372055053711, |
| "learning_rate": 9.890738003669029e-05, |
| "loss": 0.0654, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.06666666666666667, |
| "eval_loss": 0.06320454925298691, |
| "eval_runtime": 136.4924, |
| "eval_samples_per_second": 7.326, |
| "eval_steps_per_second": 0.366, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08888888888888889, |
| "grad_norm": 0.12505225837230682, |
| "learning_rate": 9.806308479691595e-05, |
| "loss": 0.0637, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 0.14867539703845978, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 0.0638, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "grad_norm": 0.10100489109754562, |
| "learning_rate": 9.567727288213005e-05, |
| "loss": 0.0595, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "eval_loss": 0.05767079070210457, |
| "eval_runtime": 136.642, |
| "eval_samples_per_second": 7.318, |
| "eval_steps_per_second": 0.366, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.15555555555555556, |
| "grad_norm": 0.17016883194446564, |
| "learning_rate": 9.414737964294636e-05, |
| "loss": 0.0569, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 0.08618276566267014, |
| "learning_rate": 9.24024048078213e-05, |
| "loss": 0.0567, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.08416091650724411, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 0.0546, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 0.053434912115335464, |
| "eval_runtime": 136.6891, |
| "eval_samples_per_second": 7.316, |
| "eval_steps_per_second": 0.366, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 0.09946251660585403, |
| "learning_rate": 8.83022221559489e-05, |
| "loss": 0.0558, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24444444444444444, |
| "grad_norm": 0.10791021585464478, |
| "learning_rate": 8.596699001693255e-05, |
| "loss": 0.0552, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 0.10341854393482208, |
| "learning_rate": 8.345653031794292e-05, |
| "loss": 0.0555, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "eval_loss": 0.052995871752500534, |
| "eval_runtime": 136.9161, |
| "eval_samples_per_second": 7.304, |
| "eval_steps_per_second": 0.365, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.28888888888888886, |
| "grad_norm": 0.092866912484169, |
| "learning_rate": 8.07830737662829e-05, |
| "loss": 0.0504, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.3111111111111111, |
| "grad_norm": 0.10099858045578003, |
| "learning_rate": 7.795964517353735e-05, |
| "loss": 0.0526, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.17789088189601898, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.052, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "eval_loss": 0.052405789494514465, |
| "eval_runtime": 136.4971, |
| "eval_samples_per_second": 7.326, |
| "eval_steps_per_second": 0.366, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.13198032975196838, |
| "learning_rate": 7.191855733945387e-05, |
| "loss": 0.0525, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.37777777777777777, |
| "grad_norm": 0.10188263654708862, |
| "learning_rate": 6.873032967079561e-05, |
| "loss": 0.0524, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.1550171822309494, |
| "learning_rate": 6.545084971874738e-05, |
| "loss": 0.0529, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 0.05086047202348709, |
| "eval_runtime": 136.9202, |
| "eval_samples_per_second": 7.304, |
| "eval_steps_per_second": 0.365, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.4222222222222222, |
| "grad_norm": 0.08379051834344864, |
| "learning_rate": 6.209609477998338e-05, |
| "loss": 0.053, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 0.1344887912273407, |
| "learning_rate": 5.868240888334653e-05, |
| "loss": 0.0511, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4666666666666667, |
| "grad_norm": 0.09979716688394547, |
| "learning_rate": 5.522642316338268e-05, |
| "loss": 0.0502, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4666666666666667, |
| "eval_loss": 0.0506291501224041, |
| "eval_runtime": 136.7115, |
| "eval_samples_per_second": 7.315, |
| "eval_steps_per_second": 0.366, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4888888888888889, |
| "grad_norm": 0.07537568360567093, |
| "learning_rate": 5.174497483512506e-05, |
| "loss": 0.0497, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.5111111111111111, |
| "grad_norm": 0.10576926916837692, |
| "learning_rate": 4.825502516487497e-05, |
| "loss": 0.0504, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.10534786432981491, |
| "learning_rate": 4.477357683661734e-05, |
| "loss": 0.0479, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "eval_loss": 0.048654135316610336, |
| "eval_runtime": 136.5401, |
| "eval_samples_per_second": 7.324, |
| "eval_steps_per_second": 0.366, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 0.10896391421556473, |
| "learning_rate": 4.131759111665349e-05, |
| "loss": 0.0506, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5777777777777777, |
| "grad_norm": 0.10746324062347412, |
| "learning_rate": 3.790390522001662e-05, |
| "loss": 0.0477, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.16898374259471893, |
| "learning_rate": 3.4549150281252636e-05, |
| "loss": 0.0479, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_loss": 0.04828697443008423, |
| "eval_runtime": 136.3988, |
| "eval_samples_per_second": 7.331, |
| "eval_steps_per_second": 0.367, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6222222222222222, |
| "grad_norm": 0.23446787893772125, |
| "learning_rate": 3.12696703292044e-05, |
| "loss": 0.0487, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.6444444444444445, |
| "grad_norm": 0.18817700445652008, |
| "learning_rate": 2.8081442660546125e-05, |
| "loss": 0.0483, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.1385546326637268, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.047, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "eval_loss": 0.04631952568888664, |
| "eval_runtime": 136.5399, |
| "eval_samples_per_second": 7.324, |
| "eval_steps_per_second": 0.366, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6888888888888889, |
| "grad_norm": 0.1836208701133728, |
| "learning_rate": 2.2040354826462668e-05, |
| "loss": 0.0477, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.17699767649173737, |
| "learning_rate": 1.9216926233717085e-05, |
| "loss": 0.0455, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.7333333333333333, |
| "grad_norm": 0.17500163614749908, |
| "learning_rate": 1.6543469682057106e-05, |
| "loss": 0.0452, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7333333333333333, |
| "eval_loss": 0.0455147922039032, |
| "eval_runtime": 136.6527, |
| "eval_samples_per_second": 7.318, |
| "eval_steps_per_second": 0.366, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7555555555555555, |
| "grad_norm": 0.4250011146068573, |
| "learning_rate": 1.4033009983067452e-05, |
| "loss": 0.045, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.7777777777777778, |
| "grad_norm": 0.22023910284042358, |
| "learning_rate": 1.1697777844051105e-05, |
| "loss": 0.0436, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.1621396541595459, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 0.0437, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.04442232847213745, |
| "eval_runtime": 136.5105, |
| "eval_samples_per_second": 7.325, |
| "eval_steps_per_second": 0.366, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8222222222222222, |
| "grad_norm": 0.1345316618680954, |
| "learning_rate": 7.597595192178702e-06, |
| "loss": 0.043, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.8444444444444444, |
| "grad_norm": 0.1296633929014206, |
| "learning_rate": 5.852620357053651e-06, |
| "loss": 0.0451, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.8666666666666667, |
| "grad_norm": 0.1679375320672989, |
| "learning_rate": 4.322727117869951e-06, |
| "loss": 0.0442, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.8666666666666667, |
| "eval_loss": 0.04389314725995064, |
| "eval_runtime": 136.6458, |
| "eval_samples_per_second": 7.318, |
| "eval_steps_per_second": 0.366, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.1358930468559265, |
| "learning_rate": 3.0153689607045845e-06, |
| "loss": 0.042, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9111111111111111, |
| "grad_norm": 0.12815573811531067, |
| "learning_rate": 1.9369152030840556e-06, |
| "loss": 0.0435, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "grad_norm": 0.16702179610729218, |
| "learning_rate": 1.0926199633097157e-06, |
| "loss": 0.0439, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "eval_loss": 0.04338783398270607, |
| "eval_runtime": 136.4534, |
| "eval_samples_per_second": 7.329, |
| "eval_steps_per_second": 0.366, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9555555555555556, |
| "grad_norm": 0.2307462841272354, |
| "learning_rate": 4.865965629214819e-07, |
| "loss": 0.0406, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.9777777777777777, |
| "grad_norm": 0.1788487583398819, |
| "learning_rate": 1.2179748700879012e-07, |
| "loss": 0.0434, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.22977402806282043, |
| "learning_rate": 0.0, |
| "loss": 0.0444, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.04335245117545128, |
| "eval_runtime": 136.5818, |
| "eval_samples_per_second": 7.322, |
| "eval_steps_per_second": 0.366, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 450, |
| "total_flos": 8.965157752615731e+17, |
| "train_loss": 0.0571367746591568, |
| "train_runtime": 6071.8085, |
| "train_samples_per_second": 1.482, |
| "train_steps_per_second": 0.074 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 450, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.965157752615731e+17, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
