Improve error message when tokenize_*_data config doesn't match dataset

[aireenmei]

Description

Currently when the flag tokenize_{train/eval}_data doesn't match with the dataset (pre-tokenized or not), the data pipeline often crash without clear error message, for example: https://buganizer.corp.google.com/issues/509946269#comment10

Tests

Manually tested

Checklist

Before submitting this PR, please make sure (put X in square brackets):

• I have performed a self-review of my code. For an optional AI review, add the gemini-review label.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have run end-to-end tests tests and provided workload links above if applicable.
• I have made or will make corresponding changes to the doc if needed, including adding new documentation pages to the relevant Table of Contents (toctree directive) as explained in our documentation.

[github-actions]

🤖 Hi @aireenmei, I've received your request, and I'm working on it now! You can track my progress in the logs for more details.

[github-actions]

## 📋 Review Summary

The PR significantly improves error messages when data tokenization configuration doesn't match the dataset format, which is a great UX improvement. It consolidates validation logic into NormalizeFeatures and adds specific validation for TFDS.

🔍 General Feedback

• The refactoring of NormalizeFeatures into a universal validator is a good architectural move as it centralizes the data type checks.
• One small regression is the loss of the descriptive "missing column" error message when KeepFeatures was removed, which I've suggested adding back.
• Overall, the code is clean and the error messages are very helpful and actionable for users.

[codecov]

Codecov Report

❌ Patch coverage is 43.75000% with 18 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/maxtext/input_pipeline/input_pipeline_utils.py	40.00%	10 Missing and 8 partials ⚠️

📢 Thoughts on this report? Let us know!