Update max_length explanation for VLM in online trainers

[sergiopaniego]

What does this PR do?

For GRPO and RLOO, it currently suggests setting max_prompt_length to None which is wrong. The correct parameter would be max_length. Tip copied from SFT trainer.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a GitHub issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

Who can review?

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[albertvillanova]

Thanks! I guess the rendering is OK, because the PR docs link does not work: https://moon-ci-docs.huggingface.co/docs/trl/pr_4220/en/index

[qgallouedec]

max_length isn't a valid arg of GRPOConfig. It's max_prompt_length