all_results.json

{
    "epoch": 1.0,
    "eval_logps/chosen": -2.491426467895508,
    "eval_logps/rejected": -2.823484420776367,
    "eval_loss": 3.3512649536132812,
    "eval_rewards/accuracies": 1.0,
    "eval_rewards/chosen": -24.914264678955078,
    "eval_rewards/margins": 3.32058048248291,
    "eval_rewards/rejected": -28.234844207763672,
    "eval_runtime": 1.9721,
    "eval_samples": 10,
    "eval_samples_per_second": 5.071,
    "eval_steps_per_second": 1.014,
    "total_flos": 0.0,
    "train_loss": 9.667842355096774,
    "train_runtime": 2221.9837,
    "train_samples": 4610,
    "train_samples_per_second": 2.075,
    "train_steps_per_second": 0.26
}