{
    "epoch": 1.0,
    "eval_logits/chosen": -2.227571487426758,
    "eval_logits/rejected": -2.0224978923797607,
    "eval_logps/chosen": -407.7003173828125,
    "eval_logps/rejected": -2709.213134765625,
    "eval_loss": 0.0529978983104229,
    "eval_rewards/accuracies": 0.9700000286102295,
    "eval_rewards/chosen": -2.475966691970825,
    "eval_rewards/margins": 18.596342086791992,
    "eval_rewards/rejected": -21.072311401367188,
    "eval_runtime": 86.3233,
    "eval_samples": 788,
    "eval_samples_per_second": 9.128,
    "eval_steps_per_second": 0.29,
    "train_loss": 0.24172405860846555,
    "train_runtime": 5168.5497,
    "train_samples": 20204,
    "train_samples_per_second": 3.909,
    "train_steps_per_second": 0.061
}