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, can please anyone tell me if it is even possible to continue training after it was halted? For example computer rebooted from some reason etc..
Do I need to merge lora checkpoints I have saved for each epoch with base SDXL model and then load such as that "initial model"? Or is this stupid idea and some other option is available?
I was trying to google it for few hours but no sucess.. ppl usually train some small CNs that take hours so no need for it, but mine will take like weeks I think as I have tens of thousands images to train on..
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi, can please anyone tell me if it is even possible to continue training after it was halted? For example computer rebooted from some reason etc..
Do I need to merge lora checkpoints I have saved for each epoch with base SDXL model and then load such as that "initial model"? Or is this stupid idea and some other option is available?
I was trying to google it for few hours but no sucess.. ppl usually train some small CNs that take hours so no need for it, but mine will take like weeks I think as I have tens of thousands images to train on..
Beta Was this translation helpful? Give feedback.
All reactions