| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "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": 0.004757694434374571, | |
| "logits/rejected": -0.07544607669115067, | |
| "logps/chosen": -92.05601501464844, | |
| "logps/rejected": -108.95303344726562, | |
| "loss": 0.0001, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 2, | |
| "total_flos": 0.0, | |
| "train_loss": 6.395760283339769e-05, | |
| "train_runtime": 14.4723, | |
| "train_samples_per_second": 0.276, | |
| "train_steps_per_second": 0.138 | |
| } | |
| ], | |
| "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 | |
| } | |