{ "epoch": 0.9989528795811519, "eval_fcm_dpo/beta": 0.009593765251338482, "eval_logits/chosen": -0.8410288691520691, "eval_logits/rejected": -0.8335962891578674, "eval_logps/chosen": -391.4317626953125, "eval_logps/ref_chosen": -287.8267517089844, "eval_logps/ref_rejected": -266.9313659667969, "eval_logps/rejected": -426.3018493652344, "eval_loss": 0.5413669347763062, "eval_margin_dpo/margin_mean": 55.76554870605469, "eval_margin_dpo/margin_std": 85.69520568847656, "eval_runtime": 81.3525, "eval_samples": 2000, "eval_samples_per_second": 24.584, "eval_steps_per_second": 1.537 }