llama-3-8b-base-new-dpo-harmless-4xh200-s_star1.0/train_results.json

{
    "epoch": 0.999244142101285,
    "total_flos": 0.0,
    "train_loss": 1.0854419020769637,
    "train_runtime": 1766.4629,
    "train_samples": 42336,
    "train_samples_per_second": 23.967,
    "train_steps_per_second": 0.374
}