| { | |
| "epoch": 0.999253545658124, | |
| "eval_logits/chosen": -1.8935905694961548, | |
| "eval_logits/rejected": -1.7368791103363037, | |
| "eval_logps/chosen": -789.0983276367188, | |
| "eval_logps/rejected": -1952.635986328125, | |
| "eval_loss": 0.027867762371897697, | |
| "eval_rewards/accuracies": 0.983582079410553, | |
| "eval_rewards/chosen": -3.89859676361084, | |
| "eval_rewards/margins": 12.0726957321167, | |
| "eval_rewards/rejected": -15.971291542053223, | |
| "eval_runtime": 830.1728, | |
| "eval_samples": 5359, | |
| "eval_samples_per_second": 6.455, | |
| "eval_steps_per_second": 1.614, | |
| "total_flos": 0.0, | |
| "train_loss": 0.0882907345950366, | |
| "train_runtime": 20220.3954, | |
| "train_samples": 48227, | |
| "train_samples_per_second": 2.385, | |
| "train_steps_per_second": 0.037 | |
| } |