deepspeedai / deepspeedai/DeepSpeedExamples

what data should I use in step 3

Open
#555 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I have a SFTed general model M. Suppose I used all data A to train it, and I additionally trained a reward model using all data B. When I continue PPO training M in step 3, can I use data A or data B? Or should I use a completely new dataset C?

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

No file, test, or entry point is named. First clarify the intended guidance for dataset reuse across SFT, reward-model training, and PPO, then identify the relevant DeepSpeed example or documentation location and define the expected recommendation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.