{
    "epoch": 1.0,
    "eval_logits/chosen": -1.4751973152160645,
    "eval_logits/rejected": -1.4288278818130493,
    "eval_logps/chosen": -2603.783203125,
    "eval_logps/rejected": -2200.0751953125,
    "eval_loss": 0.6315724849700928,
    "eval_rewards/accuracies": 0.6600000262260437,
    "eval_rewards/chosen": 0.6899210810661316,
    "eval_rewards/margins": 0.3855075538158417,
    "eval_rewards/rejected": 0.30441343784332275,
    "eval_runtime": 298.7044,
    "eval_samples": 2000,
    "eval_samples_per_second": 6.696,
    "eval_steps_per_second": 0.418,
    "train_loss": 0.6480738864519209,
    "train_runtime": 26013.0665,
    "train_samples": 61135,
    "train_samples_per_second": 2.35,
    "train_steps_per_second": 0.073
}