| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.3333333333333333, |
| "eval_steps": 100, |
| "global_step": 2, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 5e-06, |
| "logits/chosen": 0.7674216628074646, |
| "logits/rejected": 0.7469885945320129, |
| "logps/chosen": -160.50914001464844, |
| "logps/rejected": -129.6922149658203, |
| "loss": 0.0023, |
| "rewards/accuracies": 0.0, |
| "rewards/chosen": 0.0, |
| "rewards/margins": 0.0, |
| "rewards/rejected": 0.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 1.33, |
| "step": 2, |
| "total_flos": 0.0, |
| "train_loss": 0.0015329468587879092, |
| "train_runtime": 7.3105, |
| "train_samples_per_second": 2.736, |
| "train_steps_per_second": 0.274 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 100, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
