TIGER-AI-Lab / TIGER-AI-Lab/VideoScore2

About RL training

Open
#6 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
58
Forks
4
Avg merge
1m
Merged PRs (30d)
1

Description

Thank you for your contribution!
I'm trying to reproduce the training pipeline. The sft training went well, however the RL training went into OOM.
8 * L40S is used for training. Is it necessary to use 8 * A100 for RL training ? And Is there any alternative to RL train with less GPU occupancy?

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.

Research direction

The issue does not mention any files, tests, or entry points. Start by locating the RL training pipeline and reproducing the out-of-memory failure with 8 L40S GPUs; done would require confirming the cause and establishing whether a lower-GPU alternative is supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.