{ "epoch": 0.999244142101285, "eval_fcm_dpo/beta": 0.00873605813831091, "eval_logits/chosen": 0.7100939750671387, "eval_logits/rejected": 0.6652560830116272, "eval_logps/chosen": -206.1328125, "eval_logps/ref_chosen": -74.85946655273438, "eval_logps/ref_rejected": -79.54898834228516, "eval_logps/rejected": -266.35693359375, "eval_loss": 0.5597169995307922, "eval_margin_dpo/margin_mean": 55.534568786621094, "eval_margin_dpo/margin_std": 95.7474365234375, "eval_runtime": 38.6273, "eval_samples": 2303, "eval_samples_per_second": 59.621, "eval_steps_per_second": 1.864 }