{ "epoch": 1.0, "eval_logits/chosen": -2.742107391357422, "eval_logits/rejected": -2.739009141921997, "eval_logps/chosen": -295.89080810546875, "eval_logps/rejected": -294.5900573730469, "eval_loss": 0.3439472019672394, "eval_pred_label": 6851.2001953125, "eval_rewards/accuracies": 0.7419999837875366, "eval_rewards/chosen": -1.163341999053955, "eval_rewards/margins": 2.3656928539276123, "eval_rewards/rejected": -3.5290346145629883, "eval_runtime": 460.2253, "eval_samples": 2000, "eval_samples_per_second": 4.346, "eval_steps_per_second": 0.272, "eval_use_label": 9180.7998046875 }