| { | |
| "epoch": 9.674418604651162, | |
| "eval_logits/chosen": 1.8234968185424805, | |
| "eval_logits/rejected": 1.6967169046401978, | |
| "eval_logps/chosen": -161.5980682373047, | |
| "eval_logps/rejected": -82.32857513427734, | |
| "eval_loss": 0.6819058656692505, | |
| "eval_rewards/accuracies": 0.6666666865348816, | |
| "eval_rewards/chosen": 0.031853217631578445, | |
| "eval_rewards/margins": 0.09878198057413101, | |
| "eval_rewards/rejected": -0.06692875176668167, | |
| "eval_runtime": 14.2379, | |
| "eval_samples_per_second": 13.415, | |
| "eval_steps_per_second": 1.686 | |
| } |