{ "epoch": 0.999244142101285, "eval_fcm_dpo/beta": 0.5098052024841309, "eval_logits/chosen": 1.7105576992034912, "eval_logits/rejected": 1.603922724723816, "eval_logps/chosen": -82.0059585571289, "eval_logps/ref_chosen": -86.90177917480469, "eval_logps/ref_rejected": -96.69639587402344, "eval_logps/rejected": -93.3553695678711, "eval_loss": 0.54054856300354, "eval_margin_dpo/margin_mean": 1.554817795753479, "eval_margin_dpo/margin_std": 2.5823159217834473, "eval_runtime": 42.2442, "eval_samples": 2303, "eval_samples_per_second": 54.516, "eval_steps_per_second": 1.704, "total_flos": 0.0, "train_loss": 1.1363916052632181, "train_runtime": 2119.1053, "train_samples": 42336, "train_samples_per_second": 19.978, "train_steps_per_second": 0.312 }