{ "epoch": 0.999244142101285, "eval_fcm_dpo/beta": 0.006462239660322666, "eval_logits/chosen": 0.7311930656433105, "eval_logits/rejected": 0.6827455759048462, "eval_logps/chosen": -208.29672241210938, "eval_logps/ref_chosen": -74.85946655273438, "eval_logps/ref_rejected": -79.54898834228516, "eval_logps/rejected": -270.3067932128906, "eval_loss": 0.5738745331764221, "eval_margin_dpo/margin_mean": 57.32048416137695, "eval_margin_dpo/margin_std": 98.36843872070312, "eval_runtime": 37.9174, "eval_samples": 2303, "eval_samples_per_second": 60.737, "eval_steps_per_second": 1.899 }