{ "epoch": 0.999244142101285, "eval_fcm_dpo/beta": 0.003048304468393326, "eval_logits/chosen": 0.9178658127784729, "eval_logits/rejected": 0.8999158143997192, "eval_logps/chosen": -279.8544006347656, "eval_logps/ref_chosen": -74.85946655273438, "eval_logps/ref_rejected": -79.54898834228516, "eval_logps/rejected": -365.8829650878906, "eval_loss": 0.6095079779624939, "eval_margin_dpo/margin_mean": 81.33904266357422, "eval_margin_dpo/margin_std": 169.26637268066406, "eval_runtime": 38.7977, "eval_samples": 2303, "eval_samples_per_second": 59.359, "eval_steps_per_second": 1.856 }