Simplify batch splitting, add None collate support for when target is not expected

[ibro45]

Description

• Removed the overcomplicated and unreliable batch type inference in forward and criterion calculation
• LighterSystem always expects two elements - input and target, or a dict with "input" and "target" keys.
• Target can be None if no label is used for the task. Added support for collating None's.
• Improved parse_data

Type of Change

• 📚 Examples / docs / tutorials / dependencies update
• 🔧 Bug fix (non-breaking change which fixes an issue)
• 🥂 Improvement (non-breaking change which improves an existing feature)
• 🚀 New feature (non-breaking change which adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to change)
• 🔐 Security fix

Checklist

• I've read the CODE_OF_CONDUCT.md document.
• I've read the CONTRIBUTING.md guide.
• I've updated the code style using make codestyle.
• I've written tests for all new methods and classes that I created.
• I've written the docstring in Google format for all the methods and classes that I used.

[surajpaib]

Looks great overall. Much needed change!