{
    "epoch": 1.0,
    "eval_logits/chosen": -2.226208448410034,
    "eval_logits/rejected": -2.1488096714019775,
    "eval_logps/chosen": -313.5163879394531,
    "eval_logps/rejected": -320.47540283203125,
    "eval_loss": 0.5939346551895142,
    "eval_rewards/accuracies": 0.6919999718666077,
    "eval_rewards/chosen": -0.21535076200962067,
    "eval_rewards/margins": 0.30932918190956116,
    "eval_rewards/rejected": -0.524679958820343,
    "eval_runtime": 1172.6262,
    "eval_samples": 2000,
    "eval_samples_per_second": 1.706,
    "eval_steps_per_second": 0.213,
    "train_loss": 0.6084560017191406,
    "train_runtime": 59476.7244,
    "train_samples": 61135,
    "train_samples_per_second": 1.028,
    "train_steps_per_second": 0.128
}