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