{ "epoch": 0.996510067114094, "eval_logits/chosen": -2.701323986053467, "eval_logits/rejected": -2.786069869995117, "eval_logps/chosen": -754.8612060546875, "eval_logps/rejected": -4312.2783203125, "eval_loss": 0.18015418946743011, "eval_rewards/accuracies": 0.9303278923034668, "eval_rewards/chosen": -2.1098859310150146, "eval_rewards/margins": 6.90811014175415, "eval_rewards/rejected": -9.017997741699219, "eval_runtime": 351.8711, "eval_samples": 1948, "eval_samples_per_second": 5.536, "eval_steps_per_second": 0.693, "total_flos": 0.0, "train_loss": 0.3046778245218869, "train_runtime": 5634.2561, "train_samples": 14899, "train_samples_per_second": 2.644, "train_steps_per_second": 0.021 }