{
    "epoch": 2.999297541394882,
    "eval_logits/chosen": NaN,
    "eval_logits/rejected": NaN,
    "eval_logps/chosen": NaN,
    "eval_logps/rejected": NaN,
    "eval_loss": NaN,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": NaN,
    "eval_rewards/margins": NaN,
    "eval_rewards/rejected": NaN,
    "eval_runtime": 34.2826,
    "eval_samples": 1345,
    "eval_samples_per_second": 39.233,
    "eval_semantic_entropy": NaN,
    "eval_steps_per_second": 9.83,
    "total_flos": 0.0,
    "train_loss": 0.4331439037054118,
    "train_runtime": 28837.4505,
    "train_samples": 59790,
    "train_samples_per_second": 6.22,
    "train_steps_per_second": 0.194
}