Migrate vlm evaluation pipeline to examples

[camilobrownpinilla]

Summary

Moves eval adapter and script from kempnerforge core to examples.

Testing

• uv run ruff check kempnerforge/ tests/ passes
• uv run ruff format --check kempnerforge/ tests/ scripts/ passes
• uv run pyright kempnerforge/ passes (0 errors)
• uv run pytest tests/unit/ -v --timeout=60 passes

Closes #143

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

Files with missing lines	Coverage Δ
kempnerforge/config/vlm.py	100.00% <ø> (ø)
kempnerforge/data/vlm_dataset.py	99.11% <ø> (+0.02%)	⬆️

... and 6 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[amazloumi]

Just fix the minor issue below and then feel free to merge it to multimodal-video branch.

[amazloumi]

this two lines are unprotected. Move them into try and have the except to catch ValueError

try:
      meta = json.loads(meta_file.read_text())
      metadata["step"] = meta.get("step")
      metadata["tokens_seen"] = meta.get("tokens_seen")
  except (ValueError, OSError, AttributeError) as exc:
      logger.warning(f"Could not read {meta_file}: {exc}")
      return metadata