Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

wikihow-fine-tuning-T5, error with data code. #161

Open
Dhuha1 opened this issue Nov 10, 2021 · 0 comments
Open

wikihow-fine-tuning-T5, error with data code. #161

Dhuha1 opened this issue Nov 10, 2021 · 0 comments

Comments

@Dhuha1
Copy link

Dhuha1 commented Nov 10, 2021

Hello ,
I have question about the code of wikihow-fine-tuning-T5

I tried the code in google colab but I face a problem with data, how can I have the data splitted.
my way is that I download the 2 files (wikihowAll.csv, wikihowSep.csv) locally in my PC then I upload it to google drive( as .rar file then I unrar it by code )then when I run this code print(dataset.keys())
its output is Index(['headline','title', 'text'], dtype='object')
does this mean that I should run the code that configure the tensorflow here https://www.tensorflow.org/datasets/api_docs/python/tfds/download/DownloadConfig
if yes what should I put in the value of the attributes (extract_dir, manual_dir)?

but when I try to run the code with jupyter editor (locally in my PC its work well and the output is dict_keys(['train', 'validation', 'test']) but I can't work with jupyter, I think it is because my PC doesn't have GPU and I face problem when I try to train the model by this code model = T5FineTuner(args) , the output as following
ValueError: Cannot acquire lock, caching file might be used by another process, you should setup a unique 'experiment_id' for this run.
error

I am confused, how can I run the code well
I need the steps with details or if you have a video explain the tutorial it will be better
I am beginner to this field, so please guide me

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant