all_results.json

{
    "eval_logits/chosen": -2.405111074447632,
    "eval_logits/rejected": -2.3540520668029785,
    "eval_logps/chosen": -319.0737609863281,
    "eval_logps/rejected": -311.3714294433594,
    "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": 817.0722,
    "eval_samples": 2000,
    "eval_samples_per_second": 2.448,
    "eval_steps_per_second": 0.153
}