| { |
| "best_global_step": 936, |
| "best_metric": 0.9726528876869089, |
| "best_model_checkpoint": "../models/checkpoint-936", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 936, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.6581802368164062, |
| "learning_rate": 1.3354700854700855e-05, |
| "loss": 0.2683, |
| "step": 312 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1_macro": 0.8974081459959605, |
| "eval_f1_micro": 0.8978726625785449, |
| "eval_loss": 0.13659322261810303, |
| "eval_precision": 0.9650122050447518, |
| "eval_recall": 0.8394677236693092, |
| "eval_runtime": 6.6212, |
| "eval_samples_per_second": 752.431, |
| "eval_steps_per_second": 23.561, |
| "step": 312 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.0285727977752686, |
| "learning_rate": 6.688034188034188e-06, |
| "loss": 0.1226, |
| "step": 624 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1_macro": 0.9535446231839151, |
| "eval_f1_micro": 0.9535599179607384, |
| "eval_loss": 0.07969580590724945, |
| "eval_precision": 0.9880085003035822, |
| "eval_recall": 0.9214326160815403, |
| "eval_runtime": 6.6418, |
| "eval_samples_per_second": 750.093, |
| "eval_steps_per_second": 23.487, |
| "step": 624 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 3.7292163372039795, |
| "learning_rate": 2.136752136752137e-08, |
| "loss": 0.0824, |
| "step": 936 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1_macro": 0.9726528876869089, |
| "eval_f1_micro": 0.972626422705662, |
| "eval_loss": 0.06373157352209091, |
| "eval_precision": 0.9901730712819008, |
| "eval_recall": 0.9556908267270668, |
| "eval_runtime": 6.6145, |
| "eval_samples_per_second": 753.188, |
| "eval_steps_per_second": 23.584, |
| "step": 936 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 936, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3932669681123328.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
