microsoft / microsoft/dp-transformers

Error for fine-tuning llama2-7B using dp-transformers

Open
#49 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
149
Forks
33
Avg merge
22h 6m
Merged PRs (30d)
1

Description

Dear community,

I tried to fine-tuning llama2-7B using dp-transformers based on examples, but received the below error:

ValueError: Per sample gradient is not initialized. Not updated in backward pass?

How can I solve this problem or how to use differetial privacy to fine-tuning llama2-7B model?

Thanks a lot!

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 reproducing the example-based llama2-7B fine-tuning run described in the issue and inspect where the per-sample gradient error is raised. Review the dp-transformers and Opacus integration involved in differential privacy. Done means identifying the cause and documenting a working approach or required changes for this model.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, security
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.