{
    "epoch": 0.0,
    "eval_logits/chosen": -2.4361116886138916,
    "eval_logits/rejected": -2.394818067550659,
    "eval_logps/chosen": -343.0408935546875,
    "eval_logps/rejected": -328.2511901855469,
    "eval_loss": 0.6931473612785339,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 156.7305,
    "eval_samples": 32,
    "eval_samples_per_second": 12.761,
    "eval_steps_per_second": 0.402,
    "train_loss": 0.6931471824645996,
    "train_runtime": 5.5573,
    "train_samples": 61966,
    "train_samples_per_second": 5.758,
    "train_steps_per_second": 0.18
}