{ "epoch": 0.999244142101285, "eval_fcm_dpo/beta": 0.567912757396698, "eval_logits/chosen": 0.20129863917827606, "eval_logits/rejected": 0.16339144110679626, "eval_logps/chosen": -77.83040618896484, "eval_logps/ref_chosen": -74.85946655273438, "eval_logps/ref_rejected": -79.54898834228516, "eval_logps/rejected": -83.91458892822266, "eval_loss": 0.5609715580940247, "eval_margin_dpo/margin_mean": 1.3946577310562134, "eval_margin_dpo/margin_std": 2.489074230194092, "eval_runtime": 37.9328, "eval_samples": 2303, "eval_samples_per_second": 60.713, "eval_steps_per_second": 1.898 }