{ "epoch": 0.9989528795811519, "eval_logits/chosen": -0.6059221029281616, "eval_logits/rejected": -0.612111508846283, "eval_logps/chosen": -260.80767822265625, "eval_logps/rejected": -247.20326232910156, "eval_loss": 341.7586364746094, "eval_rewards/accuracies": 0.49399998784065247, "eval_rewards/chosen": -260.80767822265625, "eval_rewards/margins": -13.604412078857422, "eval_rewards/rejected": -247.20326232910156, "eval_runtime": 42.3358, "eval_samples": 2000, "eval_samples_per_second": 47.241, "eval_slic/ce_loss": 260.80767822265625, "eval_slic/rank_loss": 80.95094299316406, "eval_steps_per_second": 2.953 }