llama-3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260417-230753/train_results.json

{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 2.627565469291942,
    "train_runtime": 3177.7378,
    "train_samples": 43598,
    "train_samples_per_second": 13.72,
    "train_steps_per_second": 0.214
}