{ "epoch": 1.0, "eval_logits/chosen": 1.507018804550171, "eval_logits/rejected": 1.598363995552063, "eval_logps/chosen": -114.45843505859375, "eval_logps/rejected": -164.58822631835938, "eval_loss": 0.6152364015579224, "eval_pred_label": 0.0, "eval_rewards/accuracies": 0.37890625, "eval_rewards/chosen": -0.5054618120193481, "eval_rewards/margins": 0.3684910833835602, "eval_rewards/rejected": -0.8739528656005859, "eval_runtime": 125.1233, "eval_samples": 2000, "eval_samples_per_second": 15.984, "eval_steps_per_second": 0.256, "eval_use_label": 0.0 }