kohya-ss / kohya-ss/sd-scripts
Adding Validation Loss to detect Overtraining
Open
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
I saw that this repo has added the ability to use a validation loss to help figure out the optimal amount of training. Might be an interesting addition.
https://github.com/victorchall/EveryDream2trainer/blob/main/doc/VALIDATION.md
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reading the linked VALIDATION.md document in the EveryDream2trainer repository to understand the proposed validation-loss workflow. Then compare that workflow with the relevant training entry points in sd-scripts. Done means adding validation-loss support that can help identify when training is overfitting.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100