modelscope / modelscope/DiffSynth-Studio
Unstable loss during Kontext lora training
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 13.1k
- Forks
- 1.3k
- Avg merge
- 13h 12m
- Merged PRs (30d)
- 45
Description
During Kontext LoRA training (learning rate = 1e-5, rank = 64), the training loss shows large fluctuations across epochs, sometimes dropping to ~0.02 and then surging above 0.7 within the same epoch. Is this degree of instability normal for LoRA training？
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 source file, test, or entry point is named. Begin by locating the Kontext LoRA training entry point and reproducing the reported behavior with learning rate 1e-5 and rank 64; done requires determining whether the loss swings are expected and, if not, defining a concrete fix or follow-up scope.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100