h94

/

IP-Adapter

like 1.04k

When I try to fine-tine in Colab Notebook, I get the following error.
"RuntimeError: Expected is_sm80 || is_sm90 to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)"

Here is the code I ran for fine tuning
!accelerate launch --num_processes 1 --mixed_precision "fp16" \
tutorial_train.py
--pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5/"
--image_encoder_path="{image_encoder_path}"
--data_json_file="{data.json}"
--data_root_path="{image_path}"
--mixed_precision="fp16"
--resolution=512
--train_batch_size=8
--dataloader_num_workers=4
--learning_rate=1e-04
--weight_decay=0.01
--output_dir="{output_dir}"
--save_steps=10000

Here are the Cuda and Pytorch versions I'm using.
Torch version:2.1.0+cu121
cuda version: 12.1

Does anyone know how to fix the error?
And let me know if you need more information.

thanks