{ "epoch": 1.0, "eval_fcm_dpo/beta": 0.007725364528596401, "eval_fcm_dpo/delta": 0.07090797275304794, "eval_fcm_dpo/margin": 121.16280364990234, "eval_fcm_dpo/q_t": 0.33641666173934937, "eval_logits/chosen": 0.15061050653457642, "eval_logits/rejected": 0.17152999341487885, "eval_logps/chosen": -450.9537048339844, "eval_logps/ref_chosen": -79.05104064941406, "eval_logps/ref_rejected": -86.79793548583984, "eval_logps/rejected": -579.863525390625, "eval_loss": 0.49252188205718994, "eval_margin_dpo/margin_mean": 121.16280364990234, "eval_margin_dpo/margin_std": 170.95773315429688, "eval_runtime": 39.4898, "eval_samples": 2339, "eval_samples_per_second": 59.23, "eval_steps_per_second": 1.874, "total_flos": 0.0, "train_loss": 0.846195821282447, "train_runtime": 1845.654, "train_samples": 43598, "train_samples_per_second": 23.622, "train_steps_per_second": 0.369 }