Error training: Am I passing a str somewhere from the UI?

[jtan-sl]

Hi I'm a new user, still learning to train my first model, getting stuck, wondering if I'm not putting the right setting somewhere?

Running SD-WebUI on the ubuntu box on AWS.

Python revision: 3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]
Dreambooth revision: d4e2f7d
SD-WebUI revision: 0cc0ee1bcb4c24a8c9715f66cede06601bfc00c8

Checking Dreambooth requirements...
[+] torch version 1.13.1+cu117 installed.
[+] torchvision version 0.14.1+cu117 installed.
[+] bitsandbytes version 0.35.4 installed.
[+] diffusers version 0.13.1 installed.
[+] transformers version 4.26.1 installed.
[+] xformers version 0.0.17.dev464 installed.

----- error when training ----
Processing images...: 100%|336/336 [00:00<00:00, 292019.51it/s]
Traceback (most recent call last):
File "/home/ubuntu/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 555, in start_training
result = main(use_txt2img=use_txt2img)
File "/home/ubuntu/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1133, in main
return inner_loop()
File "/home/ubuntu/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 123, in decorator
return function(batch_size, grad_size, prof, *args, **kwargs)
File "/home/ubuntu/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 564, in inner_loop
text_encoder_epochs = round(args.num_train_epochs * stop_text_percentage)
TypeError: type str doesn't define round method

[Arilziem]

Try manually setting the value of stop_text_encoder / "Step Ratio of Text Encoder Training" (in advanced settings, directly below "Train UNET") and then save settings. See #991

[jtan-sl]

Thanks!