deepspeedai / deepspeedai/DeepSpeedExamples

Using LLaMA in reward model training

Open
#349 6 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi,

I have encounter the TypeError: LlamaModel.forward() got an unexpected keyword argument 'head_mask' error when training the LLaMA-7B model in step 2 reward model training.

I was wondering if the head_mask is used at all in training the reward model?

Also, is there a quick fix for this error?

Many thanks

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 by reviewing the LLaMA-7B step 2 reward model training path and the call that reaches LlamaModel.forward. Reproduce the head_mask TypeError and determine whether head_mask is required for reward model training. Done means the training path no longer passes an unsupported argument, or the issue documents why it is needed and how to handle it.

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
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.