llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-8/train_results.json

{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 1.356521034380763,
    "train_runtime": 1742.8549,
    "train_samples": 43598,
    "train_samples_per_second": 25.015,
    "train_steps_per_second": 0.391
}