Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Kohya SS raise subprocess.CalledProcessError #3075

Open
Bowlroller opened this issue Feb 3, 2025 · 0 comments
Open

Kohya SS raise subprocess.CalledProcessError #3075

Bowlroller opened this issue Feb 3, 2025 · 0 comments

Comments

@Bowlroller
Copy link

Hi all! this is my first time using github to post an issue and my first time lora training, so please bear with me. i have issue where whenever i begin training on kohya SS i immediately get met with a raise subprocess.CalledProcessError, making it immediately end the training. Ill provide a screenshot of the error. ive done a ton of research and troubleshooting and it seems to be a pretty common issue but with no concrete solution to it. Ive already done a number of troubleshooting that were suggested on github:
-Replaced the train.py python file
-Changed the optimizer parameter to adamw, as well as tried the other ones
-Made sure i wasnt on Dreambooth (i also attempted it on Dreambooth just to check)
-Checked my installation dependencies (python 3.10, git, cuda 11.8)
My spec are an Nvidia Geforce RTX 3060, 32 GBs of ram, an an AMD Ryzen 5 3600 6-core processor, 3600 mhz 6 cores

Image
for my parameters ive been using a preset from someone whos trained alot with the similar models that i use with some minor adjustments. (idk how to post the parameters here yet)
Any suggestions or help is appreciated! 

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant