all_results.json

{
    "epoch": 1.996886351842242,
    "eval_logits/chosen": -2.8249309062957764,
    "eval_logits/rejected": -2.6878879070281982,
    "eval_logps/chosen": -401.2567138671875,
    "eval_logps/rejected": -351.667724609375,
    "eval_loss": 0.6931471228599548,
    "eval_rewards/accuracies": 0.0,
    "eval_rewards/chosen": 0.0,
    "eval_rewards/margins": 0.0,
    "eval_rewards/rejected": 0.0,
    "eval_runtime": 2.9241,
    "eval_samples": 50,
    "eval_samples_per_second": 17.099,
    "eval_steps_per_second": 0.342,
    "total_flos": 0.0,
    "train_loss": 0.1585804910288655,
    "train_runtime": 28225.2793,
    "train_samples": 123309,
    "train_samples_per_second": 8.737,
    "train_steps_per_second": 0.034
}