| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8571428571428571, | |
| "eval_steps": 100, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 17.573449106373904, | |
| "learning_rate": 5e-07, | |
| "logits/chosen": -3.2767252922058105, | |
| "logits/rejected": -3.2294609546661377, | |
| "logps/chosen": -307.05828857421875, | |
| "logps/rejected": -738.1131591796875, | |
| "loss": 0.6931, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "step": 3, | |
| "total_flos": 0.0, | |
| "train_loss": 0.6925464868545532, | |
| "train_runtime": 47.5051, | |
| "train_samples_per_second": 4.715, | |
| "train_steps_per_second": 0.063 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |