{
    "epoch": 1.0,
    "eval_logits/chosen": -2.9375,
    "eval_logits/rejected": -2.625,
    "eval_logps/chosen": -772.0,
    "eval_logps/rejected": -1168.0,
    "eval_loss": 0.21195410192012787,
    "eval_rewards/accuracies": 0.9136363863945007,
    "eval_rewards/chosen": -6.0,
    "eval_rewards/margins": 4.1875,
    "eval_rewards/rejected": -10.1875,
    "eval_runtime": 3472.8109,
    "eval_samples": 99217,
    "eval_samples_per_second": 28.364,
    "eval_steps_per_second": 0.443
}