Open 1blackbar opened 1 year ago
Specify shat type of error, do a screenshot or paste the log
Here it is , closed webui, wanted to train on new images
The following values were not passed to
accelerate launchand had defaults used instead:
--num_processeswas set to a value of
1
--num_machineswas set to a value of
1
--mixed_precisionwas set to a value of
'no'
--num_cpu_threads_per_processwas set to
1to improve out-of-box performance To avoid this warning pass in values for each of the problematic parameters or run
accelerate config`.
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/transformers/configuration_utils.py", line 609, in _get_config_dict
user_agent=user_agent,
File "/usr/local/lib/python3.7/dist-packages/transformers/utils/hub.py", line 297, in cached_path
raise EnvironmentError(f"file {url_or_filename} not found")
OSError: file /content/stable-diffusion-v1-4/config.json not found
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 606, in
it looks like you have disconnected from the runtime and the original model got deleted, I will add the option to keep the original model in gdrive (5GB) to avoid redownloading.
No cause i rerun the cell to download from huggingface and it still happens but i will try the fix, also theres no way i disconnected, i was prompting the whole time
What i did ito try to fix this is to change the names of the folders to gibbersish so it wont use old folders but new ones , tried to rerun all cells with dependencies, it went fine but still errors our on training, the only wayu to train agin is to totally disconnect and restart from 0
oh crap... so i disconnected to rerun and was welcomed with NO GPU for me despite on colab pro... great This is exactly why i want to retrain again during same session
I'll check that out shortly
fixed, update the colab and confirm
works! Thanks for fix
What i must do to train again immediately ? It wont run and errors out. You can easily try it by training for 100 steps and then trying to train again with same settings
by the way how i can control training repeat rate with your colab ?