all_results.json

{
    "epoch": 1.9973828840617638,
    "eval_logits/chosen": -1.6407532691955566,
    "eval_logits/rejected": -1.6968854665756226,
    "eval_logps/chosen": -375.6463623046875,
    "eval_logps/rejected": -323.7197570800781,
    "eval_loss": 0.6348475217819214,
    "eval_rewards/accuracies": 0.6190476417541504,
    "eval_rewards/chosen": -0.034213583916425705,
    "eval_rewards/margins": 0.3567626178264618,
    "eval_rewards/rejected": -0.3909761905670166,
    "eval_runtime": 22.3598,
    "eval_samples": 2000,
    "eval_samples_per_second": 89.446,
    "eval_steps_per_second": 2.818,
    "total_flos": 0.0,
    "train_loss": 0.6516540072998911,
    "train_runtime": 5944.7081,
    "train_samples": 61134,
    "train_samples_per_second": 20.568,
    "train_steps_per_second": 0.16
}