| { | |
| "epoch": 9.844444444444445, | |
| "eval_logits/chosen": -3652706.0, | |
| "eval_logits/rejected": -7997593.777777778, | |
| "eval_logps/chosen": -12.900739034016928, | |
| "eval_logps/rejected": -37.902974446614586, | |
| "eval_loss": 0.2807026207447052, | |
| "eval_rewards/chosen": 0.7524267832438151, | |
| "eval_rewards/margins": 2.2908316718207464, | |
| "eval_rewards/rejected": -1.5384048885769315, | |
| "eval_runtime": 13.115, | |
| "eval_samples_per_second": 4.575, | |
| "eval_steps_per_second": 2.287, | |
| "kl": 0.663330078125 | |
| } |