{ "epoch": 0.999244142101285, "eval_fcm_dpo/beta": 0.17544980347156525, "eval_logits/chosen": 0.2951970398426056, "eval_logits/rejected": 0.25194454193115234, "eval_logps/chosen": -82.67711639404297, "eval_logps/ref_chosen": -74.85946655273438, "eval_logps/ref_rejected": -79.54898834228516, "eval_logps/rejected": -91.613525390625, "eval_loss": 0.5367735028266907, "eval_margin_dpo/margin_mean": 4.246893882751465, "eval_margin_dpo/margin_std": 6.948185443878174, "eval_runtime": 37.9408, "eval_samples": 2303, "eval_samples_per_second": 60.7, "eval_steps_per_second": 1.898, "total_flos": 0.0, "train_loss": 1.0861937751748378, "train_runtime": 1754.5635, "train_samples": 42336, "train_samples_per_second": 24.129, "train_steps_per_second": 0.377 }