| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0482180293501049, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8764516129032258, |
| "eval_loss": 2.150498628616333, |
| "eval_runtime": 17.8438, |
| "eval_samples_per_second": 173.73, |
| "eval_steps_per_second": 5.436, |
| "step": 477 |
| }, |
| { |
| "epoch": 1.0482180293501049, |
| "grad_norm": 27.51361083984375, |
| "learning_rate": 1.302585604472397e-05, |
| "loss": 5.9093, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1431, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 407413063774080.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": { |
| "alpha": 0.8979553244778209, |
| "num_train_epochs": 3, |
| "temperature": 4.375187631815162 |
| } |
| } |
|
|
