{ "epoch": 2.9907692307692306, "eval_logits/chosen": -2.1212635040283203, "eval_logits/rejected": -2.094616413116455, "eval_logps/chosen": -306.5101318359375, "eval_logps/rejected": -240.8466339111328, "eval_loss": 0.4983143210411072, "eval_rewards/accuracies": 0.8074324131011963, "eval_rewards/chosen": 2.3376271724700928, "eval_rewards/margins": 3.1606428623199463, "eval_rewards/rejected": -0.8230161070823669, "eval_runtime": 154.3024, "eval_samples_per_second": 14.938, "eval_steps_per_second": 0.24, "total_flos": 2865208385077248.0, "train_loss": 0.2735099794933335, "train_runtime": 9352.9566, "train_samples_per_second": 6.652, "train_steps_per_second": 0.026 }