{ "epoch": 1.0, "eval_logits/chosen": -0.5745480060577393, "eval_logits/rejected": -0.535261869430542, "eval_logps/chosen": -119.71295928955078, "eval_logps/ref_chosen": -97.0617446899414, "eval_logps/ref_rejected": -80.18183135986328, "eval_logps/rejected": -113.98292541503906, "eval_loss": 0.4582546055316925, "eval_margin_dpo/margin_mean": 11.149892807006836, "eval_margin_dpo/margin_std": 15.04123592376709, "eval_runtime": 20.2691, "eval_samples": 2339, "eval_samples_per_second": 115.397, "eval_steps_per_second": 0.937 }