You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
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!
The text was updated successfully, but these errors were encountered:
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
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!
The text was updated successfully, but these errors were encountered: