| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.6666666666666665, | |
| "eval_steps": 100, | |
| "global_step": 4, | |
| "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": 0.14087289571762085, | |
| "logits/rejected": 0.26200854778289795, | |
| "logps/chosen": -151.77381896972656, | |
| "logps/rejected": -123.42724609375, | |
| "loss": 0.0005, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "step": 4, | |
| "total_flos": 0.0, | |
| "train_loss": 0.00033688666007947177, | |
| "train_runtime": 14.5188, | |
| "train_samples_per_second": 2.755, | |
| "train_steps_per_second": 0.276 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |