| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.1978021978021978, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 1.068535327911377, |
| "learning_rate": 0.0, |
| "loss": 1.0606, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 1.268423318862915, |
| "learning_rate": 9.56e-05, |
| "loss": 1.1983, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 1.045927882194519, |
| "learning_rate": 0.0001912, |
| "loss": 1.0628, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 1.028908371925354, |
| "learning_rate": 0.0002868, |
| "loss": 0.9173, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.6483846306800842, |
| "learning_rate": 0.0003824, |
| "loss": 0.7759, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.7689517736434937, |
| "learning_rate": 0.000478, |
| "loss": 0.9309, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5526404976844788, |
| "learning_rate": 0.00047694013303769406, |
| "loss": 0.96, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.4260517656803131, |
| "learning_rate": 0.00047588026607538804, |
| "loss": 0.8695, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.34387385845184326, |
| "learning_rate": 0.0004748203991130821, |
| "loss": 0.8246, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.33756059408187866, |
| "learning_rate": 0.00047376053215077607, |
| "loss": 0.805, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.5314936637878418, |
| "learning_rate": 0.00047270066518847006, |
| "loss": 0.8365, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.5229127407073975, |
| "learning_rate": 0.0004716407982261641, |
| "loss": 0.838, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.48703446984291077, |
| "learning_rate": 0.00047058093126385814, |
| "loss": 0.773, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.524895966053009, |
| "learning_rate": 0.0004695210643015521, |
| "loss": 0.7794, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.5241197347640991, |
| "learning_rate": 0.00046846119733924617, |
| "loss": 0.7233, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.427020788192749, |
| "learning_rate": 0.00046740133037694015, |
| "loss": 0.7957, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.5390051603317261, |
| "learning_rate": 0.00046634146341463414, |
| "loss": 0.8339, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.31555530428886414, |
| "learning_rate": 0.0004652815964523282, |
| "loss": 0.7379, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.3968167304992676, |
| "learning_rate": 0.0004642217294900222, |
| "loss": 0.6715, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.37160152196884155, |
| "learning_rate": 0.0004631618625277162, |
| "loss": 0.7653, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.40373656153678894, |
| "learning_rate": 0.00046210199556541025, |
| "loss": 0.7728, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.360177218914032, |
| "learning_rate": 0.00046104212860310423, |
| "loss": 0.7641, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.5294693112373352, |
| "learning_rate": 0.0004599822616407982, |
| "loss": 0.7356, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.353331595659256, |
| "learning_rate": 0.00045892239467849226, |
| "loss": 0.7071, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.49404677748680115, |
| "learning_rate": 0.0004578625277161863, |
| "loss": 0.7861, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.3531878590583801, |
| "learning_rate": 0.0004568026607538803, |
| "loss": 0.7469, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.4992196261882782, |
| "learning_rate": 0.00045574279379157433, |
| "loss": 0.7605, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.39656317234039307, |
| "learning_rate": 0.00045468292682926826, |
| "loss": 0.772, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.41846686601638794, |
| "learning_rate": 0.0004536230598669623, |
| "loss": 0.7356, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.4010296165943146, |
| "learning_rate": 0.00045256319290465634, |
| "loss": 0.7164, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3715005166843904e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
