{ "epoch": 2.0, "eval_logits/chosen": -2.4878430366516113, "eval_logits/rejected": -2.303501605987549, "eval_logps/chosen": -92.59371185302734, "eval_logps/rejected": -155.12913513183594, "eval_loss": 0.2571355104446411, "eval_rewards/accuracies": 0.8928571343421936, "eval_rewards/chosen": 0.7362550497055054, "eval_rewards/margins": 3.712023973464966, "eval_rewards/rejected": -2.975768804550171, "eval_runtime": 71.4209, "eval_samples": 890, "eval_samples_per_second": 12.461, "eval_steps_per_second": 0.196 }