aigc-apps / aigc-apps/VideoX-Fun
Overfitting Problem
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 188
- Avg merge
- 2d 22h
- Merged PRs (30d)
- 3
Description
I try to overfit a random weight model (Wan2.1-1.3B) on a small set videos, but it fails. The loss remains stable around 0.4 and does not decrease further. However, fine-tuning on the pretrained model is effective?
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 reported overfitting attempt with the Wan2.1-1.3B random-weight model on the small video set, recording the loss and configuration. Compare it with the effective pretrained-model fine-tuning run; done means identifying and documenting the cause of the stable loss or providing a reproducible fix.
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