| { |
| "epoch": 2.9974597798475866, |
| "eval_logits/chosen": -2.85874605178833, |
| "eval_logits/rejected": -2.874563455581665, |
| "eval_logps/chosen": -0.8199670910835266, |
| "eval_logps/rejected": -1.061880111694336, |
| "eval_loss": 0.883125364780426, |
| "eval_odds_ratio_loss": 0.6315835118293762, |
| "eval_rewards/accuracies": 0.5809524059295654, |
| "eval_rewards/chosen": -0.08199670165777206, |
| "eval_rewards/margins": 0.02419130690395832, |
| "eval_rewards/rejected": -0.10618800669908524, |
| "eval_runtime": 194.1434, |
| "eval_samples_per_second": 5.408, |
| "eval_sft_loss": 0.8199670910835266, |
| "eval_steps_per_second": 2.704 |
| } |