{ "epoch": 1.0, "eval_error": 0.29107242822647095, "eval_logits/chosen": -3.083505392074585, "eval_logits/rejected": -3.0741586685180664, "eval_logps/chosen": -575.8777465820312, "eval_logps/rejected": -582.3082885742188, "eval_loss": 0.6102637648582458, "eval_preference/chosen": 0.5401570796966553, "eval_preference/rejected": 0.4598429203033447, "eval_rewards/accuracies": 0.5649999976158142, "eval_rewards/chosen": -7.752251148223877, "eval_rewards/margins": 0.3572259545326233, "eval_rewards/rejected": -8.109477996826172, "eval_runtime": 41.5671, "eval_samples_per_second": 24.057, "eval_steps_per_second": 3.007 }