| { | |
| "epoch": 9.933333333333334, | |
| "eval_logits/chosen": -4337002.666666667, | |
| "eval_logits/rejected": -6325528.935064935, | |
| "eval_logps/chosen": -17.09599376860119, | |
| "eval_logps/rejected": -87.86666751217533, | |
| "eval_loss": 0.21406607329845428, | |
| "eval_rewards/chosen": -0.123722961970738, | |
| "eval_rewards/margins": 6.7279925222520705, | |
| "eval_rewards/rejected": -6.851715484222808, | |
| "eval_runtime": 28.4544, | |
| "eval_samples_per_second": 4.92, | |
| "eval_steps_per_second": 2.46, | |
| "kl": 0.0 | |
| } |