🐞 Fix tensor detach and gpu count issues in benchmarking script

[ashwinvaidya17]

Description

This is a quick fix to the following issues

• Even with model.eval(), the models returned predictions with grad_required = True
• Due to incorrect calculation of splits, greater number of GPUs were being assigned

Changes

• Bug fix (non-breaking change which fixes an issue)

Checklist

• My code follows the pre-commit style and check guidelines of this project.
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing tests pass locally with my changes