all_results.json

{
    "epoch": 0.9985929648241206,
    "eval_logits/chosen": 0.2949379086494446,
    "eval_logits/rejected": 0.2972874939441681,
    "eval_logps/chosen": -35.26618194580078,
    "eval_logps/rejected": -46.7822380065918,
    "eval_loss": 0.5072444677352905,
    "eval_rewards/accuracies": 0.7699999809265137,
    "eval_rewards/chosen": -0.4765482246875763,
    "eval_rewards/margins": 0.669231653213501,
    "eval_rewards/rejected": -1.1457798480987549,
    "eval_runtime": 48.1974,
    "eval_samples_per_second": 4.15,
    "eval_steps_per_second": 1.037,
    "total_flos": 1.595144247000957e+18,
    "train_loss": 0.5550001341363658,
    "train_runtime": 15024.8122,
    "train_samples_per_second": 2.649,
    "train_steps_per_second": 0.041
}