{ "epoch": 1.0, "eval_logits/chosen": -2.8419151306152344, "eval_logits/rejected": -2.845423936843872, "eval_logps/chosen": -284.0372314453125, "eval_logps/rejected": -259.5419921875, "eval_loss": 0.6741092801094055, "eval_pred_label": 0.0, "eval_rewards/accuracies": 0.6679999828338623, "eval_rewards/chosen": 0.02201448194682598, "eval_rewards/margins": 0.04624143987894058, "eval_rewards/rejected": -0.02422695979475975, "eval_runtime": 465.3584, "eval_samples": 2000, "eval_samples_per_second": 4.298, "eval_steps_per_second": 0.269, "eval_use_label": 0.0 }