accelerate
accelerate copied to clipboard
Error while finetuning stable diffusion on Pokemon dataset in google colab
System Info
I am trying to finetune stable diffusion model as provided in the below tutorial on google colabl
https://huggingface.co/docs/diffusers/v0.9.0/en/training/text2image
However while running !accelerate launch train_text_to_image.py in google colab I am encountering below error
2023-05-22 10:11:35.176343: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
[10:11:36] WARNING The following values were not passed to
I have tried installing latest version of TensorRT and still face the same error
I am attaching accelerate env below.
- `Accelerate` version: 0.19.0
- Platform: Linux-5.15.107+-x86_64-with-glibc2.31
- Python version: 3.10.11
- Numpy version: 1.22.4
- PyTorch version (GPU?): 2.0.1+cu118 (True)
- System RAM: 12.68 GB
- GPU type: Tesla T4
- `Accelerate` default config:
Not found
Can someone help me with how to finetune the above script on Pokemon dataset on google colab environment
Information
- [X] The official example scripts
- [ ] My own modified scripts
Tasks
- [ ] One of the scripts in the examples/ folder of Accelerate or an officially supported
no_trainerscript in theexamplesfolder of thetransformersrepo (such asrun_no_trainer_glue.py) - [X] My own task or dataset (give details below)
Reproduction
- Follow the steps given in : https://huggingface.co/docs/diffusers/training/text2image
Expected behavior
We should be able to finetune model
You should safely be able to ignore this. Colab comes pre-installed with TF but we do not use it at all
@muellerzr I was trying to fine tune the model but it was not happening , can you please provide some sample code on how to fine tune it in colab's environment . Thanks
@sayedathar11 can you please post the full trace?
@muellerzr Here is the stack trace this is what is being generated , I am trying to fine tune in colab's environment
Hi @muellerzr wanted to ask any updates on this ?
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.
Please note that issues that do not follow the contributing guidelines are likely to be ignored.