{ "epoch": 1.0, "eval_logits/chosen": -1.0900075435638428, "eval_logits/rejected": -1.0925240516662598, "eval_logps/chosen": -451.7510986328125, "eval_logps/rejected": -312.4322204589844, "eval_loss": 0.6137669682502747, "eval_rewards/accuracies": 0.6851891875267029, "eval_rewards/chosen": -0.08272896707057953, "eval_rewards/margins": 0.49261024594306946, "eval_rewards/rejected": -0.57533198595047, "eval_runtime": 202.7533, "eval_samples_per_second": 90.795, "eval_steps_per_second": 5.677 }