deepspeedai / deepspeedai/DeepSpeedExamples

Suggested GPU to run the demo code of step2_reward_model_finetuning (DeepSpeed-Chat)

Open
#885 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.8k
Forks
1.1k
Avg merge
2d 16h
Merged PRs (30d)
1

Description

I follow the instructions of this page to do step2_reward_model_finetuning with demo code.

On the Google Cloud platform, I create one instance with a single V100(16GB) and another instance with double V100(16GB). I directly use this command bash training_scripts/opt/single_gpu/run_350m.sh but always meet the out-of-memory issues.

Are there any modifications I could do to run this demo code on double V100(16BG)? Or Are there recommendations about which type of GPU I should use to run this demo code successfully?

Appreciate the help!

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

Start with the step2_reward_model_finetuning instructions and training_scripts/opt/single_gpu/run_350m.sh, then reproduce the out-of-memory failure on the reported V100 setups. Done means identifying a documented configuration that runs successfully or clearly recording the GPU requirements and required changes.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.