all_results.json

{
    "epoch": 3.0,
    "eval_logits/chosen": -13.0,
    "eval_logits/rejected": -13.0,
    "eval_logps/chosen": -612.0,
    "eval_logps/rejected": -632.0,
    "eval_loss": 1.0008906126022339,
    "eval_rewards/accuracies": 0.71875,
    "eval_rewards/chosen": -14.5625,
    "eval_rewards/margins": 2.609375,
    "eval_rewards/rejected": -17.125,
    "eval_runtime": 46.6328,
    "eval_samples": 2000,
    "eval_samples_per_second": 42.888,
    "eval_steps_per_second": 0.686,
    "total_flos": 0.0,
    "train_loss": 0.2962565040964742,
    "train_runtime": 10895.6468,
    "train_samples": 61134,
    "train_samples_per_second": 16.833,
    "train_steps_per_second": 0.526
}