Question about fine-tuning?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
I am fine-tuning on vicuna with a chat dataset and found that its performance on MMLU drops after fine-tuning.
As a practice, I wanted to check if y'all fine-tune vicuna on sharegpt till the loss becomes zero?
Ex. when vicuna-1.1 or 1.3 was trained on sharegpt data, was the training stopped when the loss became zero?
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
No file, test, or entry point is named in the issue. Start by reviewing the project's fine-tuning and evaluation guidance; done would require a maintainer answer clarifying the training-stop criterion and the expected MMLU behavior.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100