Comments (4)
This is something related with the latest accelerate version... I can't do much about it until kohya upgrade accelerate to another version as part of his supported code base... but glad you raised it so others are not taken aback by it ;-)
from kohya_ss.
I definitely agree. I also do not want to use repeats as epochs is a better measurement of progress, and repeats produce different results than just using epochs. It almost seems like a workaround for whatever is wrong with the code.
from kohya_ss.
So I'm a bit confused. The latest version of accelerate
is 0.15.0
(https://pypi.org/project/accelerate/). What do you mean by upgrading to another version when this is the latest version? I feel this might not be an accelerate issue.
from kohya_ss.
It is using the CPU far too much as the memory usage ramps up, slowly, then it dumps to CUDA, then epoch where the cycle starts over. Considering Automatic1111 works fine, and is using the GPU (1 gig more of it) I can say it is something in Kohya's code.
from kohya_ss.
Related Issues (20)
- someone knows hot to fix this problem? It keeps appearing to me every time I start training : ''returned non-zero exit status 1'' HOT 2
- Train SDXL Lora with overtraining artifacts HOT 9
- Adafactor requires a "Max grad norm" argument HOT 2
- TESLA V100 Training LORA not use 100%GPU HOT 2
- Training does not start... Can't find the error for 2 days now - ends with: ''returned non-zero exit status 1'' // 16gb Vram
- How to trainning unet only in GUI? HOT 4
- No error in v23.0.0 in v23.0.15 -> Error: Accelerate CLI tool: error: unrecognized arguments: --max_grad_norm=None HOT 7
- (Optional) Install CuDNN files (to use the latest supported CuDNN version) - does not work and just hangs. HOT 5
- Whatever I do cant make this run on Vast.AI HOT 12
- Training LORA can use Tensor Cores ? HOT 2
- How to use multi-GPU or SLI to solve the GPU memory overflow? HOT 2
- OSError: unrecognized data stream contents when reading image file HOT 1
- Issue with setup.abt HOT 1
- Folder browsing has become inconvenient HOT 4
- Could not automatically configure accelerate. HOT 2
- The current version of python is not appropriate to run Kohya_ss GUI HOT 6
- Why kohya_ss inference speed faster than diffusers or Onetrainer? HOT 1
- SDXL trained LORAs not visible on Auto1111/Forge, visible on FOOOCUS, SDXL Lora missing Meta data? HOT 2
- can't open file 'C:\\Users\\Admin\\Documents\\kohya_ss-23.0.15\\sd-scripts\\networks\\extract_lora_from_models.py': [Errno 2] No such file or directory HOT 1
- What does number of beams do in captioning, and how do i use it. I get error on anything above 1. HOT 8
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from kohya_ss.