Handle unsupported logger types in training logger

[Ritinikhil]

Raise ValueError for unsupported logger types.

Describe your changes

• Add an else branch in setup_training_logger (neural_lam/utils.py) to raise a descriptive ValueError when an unsupported --logger value is provided.
• Ensure the function now either returns a valid logger (WandB/MLflow) or raises a clear error, preventing the previous UnboundLocalError.

Issue Link

closes #206

Type of change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📖 Documentation (Addition or improvements to documentation)

Checklist before requesting a review

• My branch is up-to-date with the target branch.
• I have performed a self-review of my code.
• For any new/modified functions/classes I have added docstrings that clearly describe its purpose, expected inputs and returned values. (No new docstrings required; existing docstring unchanged.)
• I have placed in-line comments to clarify the intent of any hard-to-understand passages of my code.
• I have updated the README to cover introduced code changes.
• I have added tests that prove my fix is effective or that my feature works.
• I have given the PR a name that clearly describes the change, written in imperative form.
• I have requested a reviewer and an assignee.

Checklist for reviewers

• the code is readable
• the code is well tested
• the code is documented (including return types and parameters)
• the code is easy to maintain

Author checklist after completed review

• I have added a line to the CHANGELOG describing this change, in a section reflecting type of change (add/changed/fixes/maintenance)

Checklist for assignee

• PR is up to date with the base branch
• the tests pass
• the PR is assigned to the next milestone (if applicable)
• author has added an entry to the changelog
• squash commits and merge when ready

[Copilot]

Pull request overview

Fixes a bug in setup_training_logger by ensuring unsupported --logger values fail fast with a clear ValueError instead of potentially triggering an UnboundLocalError.

Changes:

• Add an explicit else branch in setup_training_logger to raise a descriptive ValueError for unsupported logger types.
• Restructure the function to return the created logger directly from each supported branch.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Add a unit test asserting that an unsupported args.logger value raises ValueError with a helpful message. There are already setup_training_logger tests in tests/test_cli.py, so extending coverage here will prevent regressions back to an UnboundLocalError/silent misconfiguration.