[Bug]: Embedding training possibly not working

### Checklist

- [ ] The issue exists after disabling all extensions
- [ ] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [x] The issue exists in the current version of the webui
- [x] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet

### What happened?

I was going to test making an embedding using the Train-tab of the webUI, but I kept getting the following error message:
```Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 6573.09912109375
[Memory Management] Model Memory (MB) = 159.55708122253418
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 5389.542039871216
Moving model(s) has taken 0.18 seconds
100%| 32/32 [00:01<00:00, 22.11it/s]
0%| | 0/420 [00:00

Start with modules/textual_inversion/textual_inversion.py at train_embedding and follow the call into repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py, especially q_sample. Reproduce embedding training from the Train tab and trace the tensors involved in the reported device mismatch. Done means embedding training completes without a CPU/CUDA tensor error.

Written by the indexing model from the issue text.