| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 8.0, |
| "eval_steps": 1000, |
| "global_step": 192, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.0833333333333335, |
| "grad_norm": 3.1876933574676514, |
| "learning_rate": 2.794447789131517e-05, |
| "loss": 6.9797, |
| "step": 50 |
| }, |
| { |
| "epoch": 4.166666666666667, |
| "grad_norm": 3.0499606132507324, |
| "learning_rate": 1.691261184798162e-05, |
| "loss": 3.4736, |
| "step": 100 |
| }, |
| { |
| "epoch": 6.25, |
| "grad_norm": 2.7588396072387695, |
| "learning_rate": 4.393398282201788e-06, |
| "loss": 3.1606, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 192, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1138408789377024.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
