fix: ensure that we check for pad_token and not assume pad_token==eos…

[parthchadha]

…_token

What does this PR do ?

There were wrong assumptions in grpo and sft that pad_token will be the same as eos_token.

Issues

Closes #119.

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this 

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
• Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

• ...

[parthchadha]

#121 will add functional tests. Unit tests won't catch this failure since we need to invoke the grpo or sft algorithm for an iteration to catch this issue.