all_results.json

{
    "epoch": 0.9989258861439313,
    "eval_logits/chosen": -13.382477760314941,
    "eval_logits/rejected": -13.246561050415039,
    "eval_logps/chosen": -1.8618243932724,
    "eval_logps/rejected": -2.3445940017700195,
    "eval_loss": 2.7497549057006836,
    "eval_rewards/accuracies": 0.7581967115402222,
    "eval_rewards/chosen": -18.618242263793945,
    "eval_rewards/margins": 4.82769775390625,
    "eval_rewards/rejected": -23.445940017700195,
    "eval_runtime": 69.1462,
    "eval_samples": 1941,
    "eval_samples_per_second": 28.071,
    "eval_steps_per_second": 0.882,
    "total_flos": 0.0,
    "train_loss": 3.5518602760889197,
    "train_runtime": 6148.2375,
    "train_samples": 59569,
    "train_samples_per_second": 9.689,
    "train_steps_per_second": 0.076
}