{
    "epoch": 1.0,
    "eval_logits/chosen": -2.965409755706787,
    "eval_logits/rejected": -2.88214111328125,
    "eval_logps/chosen": -296.9845275878906,
    "eval_logps/rejected": -262.7751770019531,
    "eval_loss": NaN,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 1977.0954,
    "eval_samples": 2000,
    "eval_samples_per_second": 1.012,
    "eval_steps_per_second": 0.126,
    "train_loss": 0.3465735912322998,
    "train_runtime": 27.0943,
    "train_samples": 30,
    "train_samples_per_second": 1.107,
    "train_steps_per_second": 0.037
}