Error training embedding

[den1251]

When I try to train an embedding it successfully preparing dataset, but fails to train an embedding. Here are console logs:

---
Applying attention optimization: xformers... done.
Calculating sha256 for /opt/stabilitymatrix/Data/Packages/stable-diffusion-webui/embeddings/redacted.pt: redacted
Training at rate of 0.005 until step 100000
Preparing dataset...
100%|██████████| 9/9 [00:20<00:00,  2.22s/it]
  0%|          | 0/100000 [00:00<?, ?it/s]*** Error training embedding
    Traceback (most recent call last):
      File "/opt/stabilitymatrix/Data/Packages/stable-diffusion-webui/modules/textual_inversion/textual_inversion.py", line 555, in train_embedding
        scaler.scale(loss).backward()
      File "/opt/stabilitymatrix/Data/Packages/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/_tensor.py", line 492, in backward
        torch.autograd.backward(
      File "/opt/stabilitymatrix/Data/Packages/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch/autograd/__init__.py", line 251, in backward
        Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass
    RuntimeError: Found dtype Float but expected Half

---