| { |
| "best_global_step": 57, |
| "best_metric": 0.719310914066912, |
| "best_model_checkpoint": "./results_model/checkpoint-57", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 57, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8830022075055187, |
| "grad_norm": 6.72242546081543, |
| "learning_rate": 8.24561403508772e-06, |
| "loss": 1.8585, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.7248618784530386, |
| "eval_f1": 0.719310914066912, |
| "eval_loss": 1.1899107694625854, |
| "eval_runtime": 3.4844, |
| "eval_samples_per_second": 259.729, |
| "eval_steps_per_second": 32.717, |
| "step": 57 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1140, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.01 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 242870512755420.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
