[Bug]: training error at 80%

[brcisna]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui

What happened?

Exception training model: ''NoneType' object has no attribute '_unscalegrads''.

Regardless what i change the performance setting to this error is happening . try to train ,this happened at 80% Automatic1111 v 1.7.0 sd_dreambooth_ex v [8207ccd8]

consolde: automatic1111/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 463, in inner_loop and accelerator.unwrap_model(text_encoder_two).dtype != torch.float32 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'NoneType' object has no attribute 'dtype' Loading unet...: 80%|██████████████████████▍ | 4/5 [00:01<00:00, 2.77it/s] Duration: 00:00:01 Duration: 00:00:01

Steps to reproduce the problem

1. Go to ....dreambooth extenion on Automatic1111
2. Press ....TRAIN button
3. ...errors above error at 80%

Commit and libraries

Starting at Initializing Dreambooth and ending several lines below at [+] bitsandbytes version 0.35.4 installed..

Command Line Arguments

./webui.sh

Console logs

consolde:
`automatic1111/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 463, in inner_loop
    and accelerator.unwrap_model(text_encoder_two).dtype != torch.float32
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'dtype'
Loading unet...:  80%|██████████████████████▍     | 4/5 [00:01<00:00,  2.77it/s]
Duration: 00:00:01
Duration: 00:00:01
`

Additional information

No response

[github-actions[bot]]

This issue is stale because it has been open 5 days with no activity. Remove stale label or comment or this will be closed in 5 days