qwen3-8b-base-beta-dpo-hh-helpful-4xh200-batch-64-20260424-013732/train_results.json

{
    "epoch": 1.0,
    "total_flos": 0.0,
    "train_loss": 0.9969710769807365,
    "train_runtime": 3178.2358,
    "train_samples": 43598,
    "train_samples_per_second": 13.718,
    "train_steps_per_second": 0.214
}