llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.5-s_star-0.85/train_results.json

{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 0.8810622134572784,
    "train_runtime": 1867.9067,
    "train_samples": 43598,
    "train_samples_per_second": 23.341,
    "train_steps_per_second": 0.365
}