Update sample GRPO script to validate num_generations

[nikg4]

Description

-- Check if global batch size is divisible by num_generations . Otherwise, training may fail (depending on trl version)

Related issues

Fixes OPE-993

Before submitting

• This PR only changes documentation. (You can ignore the following checks in that case)
• Did you read the contributor guideline Pull Request guidelines?
• Did you link the issue(s) related to this PR in the section above?
• Did you add / update tests where needed?

Reviewers

At least one review from a member of oumi-ai/oumi-staff is required.

[wizeng23]

Do we want to move this logic into our code? This logic likely won't be copied into every future GRPO config. IMO not necessary though, as the current HF error for this is descriptive.

[nikg4]

Do we want to move this logic into our code? This logic likely won't be copied into every future GRPO config. IMO not necessary though, as the current HF error for this is descriptive.

Oumi has this logic, but it's currently treated as a warning

oumi/src/oumi/train.py

Line 173 in e31dd22

logger.warning(

Let's consider upgrading it to error if it fails for new trl versions.