deepspeedai / deepspeedai/DeepSpeedExamples
Evaluation Loader for DeepSpeed Chat Example step 2 (reward model training)
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 6.8k
- Forks
- 1.1k
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 1
Description
Should the following line be removed? Since there is already eval_sampler initialized in previous few lines:
https://github.com/microsoft/DeepSpeedExamples/blob/dafeb2b3be3a085214faa2f59a8979c051424938/applications/DeepSpeed-Chat/training/step2_reward_model_finetuning/main.py#L236
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Open applications/DeepSpeed-Chat/training/step2_reward_model_finetuning/main.py at the linked commit and inspect around line 236, comparing that line with the earlier eval_sampler initialization. Confirm whether the duplicate evaluation-loader setup is unnecessary, then run the relevant step 2 reward-model training checks to verify evaluation still works.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Refactor
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 45/100