{ "epoch": 1.0, "eval_beta_dpo/beta_used": 0.09322389215230942, "eval_beta_dpo/beta_used_raw": 0.09322389215230942, "eval_beta_dpo/gap_mean": 9.061779022216797, "eval_beta_dpo/gap_std": 15.212827682495117, "eval_beta_dpo/mask_keep_frac": 1.0, "eval_logits/chosen": -0.42951661348342896, "eval_logits/rejected": -0.41630053520202637, "eval_loss": 0.5633630752563477, "eval_runtime": 18.8064, "eval_samples": 2303, "eval_samples_per_second": 122.458, "eval_steps_per_second": 0.957 }