| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.437125748502994, |
| "eval_steps": 500, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.718562874251497, |
| "grad_norm": 0.661852240562439, |
| "learning_rate": 4.6899038461538465e-05, |
| "loss": 2.1718, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.437125748502994, |
| "grad_norm": 0.7592059373855591, |
| "learning_rate": 4.329326923076924e-05, |
| "loss": 1.5828, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 150, |
| "max_steps": 2080, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 150, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.3642327489786675e+17, |
| "train_batch_size": 3, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
