| { | |
| "epoch": 10.0, | |
| "eval_logits/chosen": -5221032.228571429, | |
| "eval_logits/rejected": -5284203.377777778, | |
| "eval_logps/chosen": -16.849844796316965, | |
| "eval_logps/rejected": -62.744411892361114, | |
| "eval_loss": 0.2541462779045105, | |
| "eval_rewards/chosen": 0.030902576446533204, | |
| "eval_rewards/margins": 4.341355186038547, | |
| "eval_rewards/rejected": -4.310452609592014, | |
| "eval_runtime": 17.1784, | |
| "eval_samples_per_second": 4.657, | |
| "eval_steps_per_second": 2.329, | |
| "kl": 0.0 | |
| } |