| { | |
| "epoch": 0.9997382884061764, | |
| "eval_logits/chosen": -1.103013515472412, | |
| "eval_logits/rejected": -0.990799069404602, | |
| "eval_logps/chosen": -520.2218017578125, | |
| "eval_logps/rejected": -606.2373046875, | |
| "eval_loss": 0.4944952428340912, | |
| "eval_rewards/accuracies": 0.7777777910232544, | |
| "eval_rewards/chosen": -2.5530030727386475, | |
| "eval_rewards/margins": 1.0629230737686157, | |
| "eval_rewards/rejected": -3.6159262657165527, | |
| "eval_runtime": 318.8167, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 6.273, | |
| "eval_steps_per_second": 0.198, | |
| "total_flos": 0.0, | |
| "train_loss": 0.5319095570379527, | |
| "train_runtime": 23762.0752, | |
| "train_samples": 61134, | |
| "train_samples_per_second": 2.573, | |
| "train_steps_per_second": 0.04 | |
| } |