{
    "epoch": 1.0,
    "eval_logits/chosen": -2.156226873397827,
    "eval_logits/rejected": -2.1579225063323975,
    "eval_logps/chosen": -308.5898132324219,
    "eval_logps/rejected": -291.931640625,
    "eval_loss": 0.6931471228599548,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 1.5116,
    "eval_samples": 100,
    "eval_samples_per_second": 66.156,
    "eval_steps_per_second": 0.662
}