all_results.json

{
    "epoch": 0.9981298423724285,
    "eval_logits/chosen": -1.342084288597107,
    "eval_logits/rejected": -1.3028345108032227,
    "eval_logps/chosen": -0.33998000621795654,
    "eval_logps/rejected": -0.35521572828292847,
    "eval_loss": 261.97705078125,
    "eval_rewards/accuracies": 0.5040322542190552,
    "eval_rewards/chosen": -0.8499498963356018,
    "eval_rewards/margins": 0.03808927908539772,
    "eval_rewards/rejected": -0.888039231300354,
    "eval_runtime": 68.7646,
    "eval_samples": 1961,
    "eval_samples_per_second": 28.518,
    "eval_steps_per_second": 0.902,
    "total_flos": 0.0,
    "train_loss": 444.38003229635433,
    "train_runtime": 7255.1322,
    "train_samples": 59876,
    "train_samples_per_second": 8.253,
    "train_steps_per_second": 0.064
}