| { | |
| "epoch": 3.97, | |
| "eval_logits/chosen": 0.8074077367782593, | |
| "eval_logits/rejected": 0.8652730584144592, | |
| "eval_logps/chosen": -257.0081481933594, | |
| "eval_logps/rejected": -233.95510864257812, | |
| "eval_loss": 0.001172678079456091, | |
| "eval_rewards/accuracies": 0.5059999823570251, | |
| "eval_rewards/chosen": -0.003939597401767969, | |
| "eval_rewards/margins": 0.00022889903630129993, | |
| "eval_rewards/rejected": -0.0041684964671730995, | |
| "eval_runtime": 749.2839, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 2.669, | |
| "eval_steps_per_second": 0.667, | |
| "train_loss": 0.0010566485528421077, | |
| "train_runtime": 4635.3882, | |
| "train_samples": 61135, | |
| "train_samples_per_second": 0.863, | |
| "train_steps_per_second": 0.054 | |
| } |