{ "epoch": 1.0, "eval_logits/chosen": 1.3711830377578735, "eval_logits/rejected": 1.4916048049926758, "eval_logps/chosen": -123.7209243774414, "eval_logps/rejected": -161.63131713867188, "eval_loss": 0.6788680553436279, "eval_pred_label": 2490.952392578125, "eval_rewards/accuracies": 0.3591269850730896, "eval_rewards/chosen": -0.548203706741333, "eval_rewards/margins": 0.3141288757324219, "eval_rewards/rejected": -0.8623325824737549, "eval_runtime": 247.4536, "eval_samples": 2000, "eval_samples_per_second": 8.082, "eval_steps_per_second": 0.255, "eval_use_label": 17581.046875 }