Which hyper-parameters in the standard VERL configuration do not take effect?

Open
#464 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
35/100
Issue type
Documentation
Clarity
Mostly clear
Activity status
Stale
Tech stack
python

Research direction

Start with the VERL configuration documentation and the referenced trainer.py lines 463-469. Trace the listed parameters—rollout.val_kwargs, data.truncation, and rollout.top_p—to determine which are effective when passed to agl.VERL. Done means documenting a clear whitelist or blacklist of supported configurations.

Written by the indexing model from the issue text.

Description

documentation enhancement help wanted v0.x

This is the full VERL config, https://verl.readthedocs.io/en/latest/examples/config.html
I noticed that some parameters seem not work when passed to agl.VERL. For example:

  • actor_rollout_ref.rollout.val_kwargs
  • data.truncation
  • actor_rollout_ref.rollout.top_p (I'm not sure if it takes effect, as it is not explicitly set like actor_rollout_ref.rollout.temperature)

https://github.com/microsoft/agent-lightning/blob/5f3093d62a88961118054edb620dfce49f3f5577/agentlightning/verl/trainer.py#L463-L469

Could you provide a blacklist/whitelist to clarify which configs are effective or not?

Dominant language
Python
Stars
18.4k
Forks
1.6k
Avg merge
2d 8h
Merged PRs (30d)
27

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from microsoft/agent-lightning

All issues in microsoft/agent-lightning

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.