eval_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -2.8904712200164795,
    "eval_logits/rejected": -2.8962836265563965,
    "eval_logps/chosen": -31.659954071044922,
    "eval_logps/rejected": -36.01557159423828,
    "eval_loss": 0.6931471824645996,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 2.558,
    "eval_samples": 5,
    "eval_samples_per_second": 1.955,
    "eval_steps_per_second": 0.391
}