all_results.json

{
    "epoch": 1.0,
    "eval_logits/chosen": -1.578125,
    "eval_logits/rejected": -1.578125,
    "eval_logps/chosen": -2624.0,
    "eval_logps/rejected": -2352.0,
    "eval_loss": 0.69140625,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 101.9605,
    "eval_samples": 1986,
    "eval_samples_per_second": 19.478,
    "eval_steps_per_second": 0.314,
    "total_flos": 0.0,
    "train_loss": 0.69140625,
    "train_runtime": 12796.3799,
    "train_samples": 60907,
    "train_samples_per_second": 4.76,
    "train_steps_per_second": 0.037
}