{
    "epoch": 1.0,
    "eval_logits/chosen": -1.1640625,
    "eval_logits/rejected": -1.140625,
    "eval_logps/chosen": -3744.0,
    "eval_logps/rejected": -3296.0,
    "eval_loss": 0.69140625,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 102.3074,
    "eval_samples": 1986,
    "eval_samples_per_second": 19.412,
    "eval_steps_per_second": 0.313,
    "total_flos": 0.0,
    "train_loss": 0.69140625,
    "train_runtime": 349.3183,
    "train_samples": 1000,
    "train_samples_per_second": 2.863,
    "train_steps_per_second": 0.023
}