all_results.json

{
    "epoch": 0.9959925193694897,
    "eval_logits/chosen": -0.5749370455741882,
    "eval_logits/rejected": -0.5906511545181274,
    "eval_logps/chosen": -686.8735961914062,
    "eval_logps/rejected": -867.86376953125,
    "eval_loss": 0.32899072766304016,
    "eval_rewards/accuracies": 0.8951612710952759,
    "eval_rewards/chosen": -4.818518161773682,
    "eval_rewards/margins": 1.871579647064209,
    "eval_rewards/rejected": -6.690097332000732,
    "eval_runtime": 147.5704,
    "eval_samples": 1961,
    "eval_samples_per_second": 13.289,
    "eval_steps_per_second": 0.42,
    "total_flos": 0.0,
    "train_loss": 0.45488236134655996,
    "train_runtime": 10577.9564,
    "train_samples": 59875,
    "train_samples_per_second": 5.66,
    "train_steps_per_second": 0.022
}