tools/fetch_run5.py

"""One-shot script to pull Run 5 artifacts from HF Hub.

Written as a file (not python -c) so shells don't choke on the newlines.
"""
from __future__ import annotations

import os
import shutil
import subprocess
from huggingface_hub import snapshot_download


def main() -> None:
    target = "training_runs/run_5_grpo_success"
    if os.path.exists(target):
        shutil.rmtree(target)
    token = subprocess.check_output(["hf", "auth", "token"], text=True).strip()
    path = snapshot_download(
        repo_id="chane335/permanence-artifacts",
        repo_type="dataset",
        local_dir=target,
        token=token,
    )
    total = 0
    for root, _dirs, files in os.walk(path):
        for f in files:
            rel = os.path.relpath(os.path.join(root, f), path)
            if ".cache" in rel:
                continue
            size = os.path.getsize(os.path.join(root, f))
            total += size
            print(f"  {size:>12,} bytes  {rel}")
    print(f"TOTAL: {total/1e6:.1f} MB")


if __name__ == "__main__":
    main()