{ "epoch": 1.0, "eval_beta_dpo/beta_used": 0.0128458421677351, "eval_beta_dpo/beta_used_raw": -0.33979183435440063, "eval_beta_dpo/gap_mean": 27.235719680786133, "eval_beta_dpo/gap_std": 24.992555618286133, "eval_beta_dpo/mask_keep_frac": 1.0, "eval_logits/chosen": -1.7002774477005005, "eval_logits/rejected": -1.3725920915603638, "eval_loss": 0.6576590538024902, "eval_runtime": 44.0223, "eval_samples": 2339, "eval_samples_per_second": 53.132, "eval_steps_per_second": 1.681 }