OptimalScale / OptimalScale/LMFlow
How to implement weight decay towards the pre-trained model?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.5k
- Forks
- 822
- PR merge metrics
- No merged PRs in 30d
Description
Hello, let me one question.
If using LMFlow for supervised fune-tuning, how do I implement penalizing the distance between starting and current weights? This was shown to be effective in https://arxiv.org/abs/1706.03610
Contributor guide
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
No file, test, or entry point is named. Start by locating LMFlow's supervised fine-tuning path and reviewing the linked paper's objective. Done means the project has a documented, configurable way to penalize distance from the pre-trained weights, with coverage for the resulting behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100