{
    "epoch": 1.0,
    "eval_logits/chosen": -1.3140687942504883,
    "eval_logits/rejected": -1.1924079656600952,
    "eval_logps/chosen": -316.60687255859375,
    "eval_logps/rejected": -434.5618896484375,
    "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": 2.7893,
    "eval_samples": 50,
    "eval_samples_per_second": 17.926,
    "eval_steps_per_second": 0.359
}