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

Can’t run CoQa train script in Google Colab #89

Open
imagine3D-ai opened this issue Sep 8, 2020 · 13 comments
Open

Can’t run CoQa train script in Google Colab #89

imagine3D-ai opened this issue Sep 8, 2020 · 13 comments

Comments

@imagine3D-ai
Copy link

I tried using Google Colab CPU and GPU notebooks to train XLNET on COQA, but they keep crashing because of the ’out-of-memory’ issues. I tried reducing batch size to 1, but the problem still persists. Did anyone else face similar issues and was able to solve it?

@stevezheng23
Copy link
Owner

this might be related to issue you're discussing in #79

@imagine3D-ai
Copy link
Author

this might be related to issue you're discussing in #

this might be related to issue you're discussing in #79

Have you also experienced this bug (infinite loop somewhere in the code) ?

@stevezheng23
Copy link
Owner

this might be related to issue you're discussing in #

this might be related to issue you're discussing in #79

Have you also experienced this bug (infinite loop somewhere in the code) ?

Actually, I can't reproduce the issue you and @abhishek-jha13 reported

@imagine3D-ai
Copy link
Author

imagine3D-ai commented Sep 10, 2020 via email

@stevezheng23
Copy link
Owner

stevezheng23 commented Sep 10, 2020 via email

@imagine3D-ai
Copy link
Author

imagine3D-ai commented Sep 10, 2020 via email

@stevezheng23
Copy link
Owner

stevezheng23 commented Sep 10, 2020 via email

@imagine3D-ai
Copy link
Author

imagine3D-ai commented Sep 11, 2020 via email

@stevezheng23
Copy link
Owner

stevezheng23 commented Sep 11, 2020 via email

@AbbeKamalov
Copy link

this might be related to issue you're discussing in #79

Is max_sequence_length measured in characters or in words?

@stevezheng23
Copy link
Owner

this might be related to issue you're discussing in #79

Is max_sequence_length measured in characters or in words?

should be subwords

@stefan-1992
Copy link

stefan-1992 commented Apr 22, 2021

Hi together

I had the same problem. The issue is in convert_coqa_example. The while loop in line 818 run_coqa.py becomes an endless loop if max_sequence_length is 128.
The training data sample 244 has a query length of 128. Accordingly, the following line
max_para_length = self.max_seq_length - len(query_tokens) - 3
ends up producing a max_para_length of -3 and the sliding_window_approach stops working.
My simple solution was to increase the max_seq_length to 256.

@stevezheng23
Copy link
Owner

stevezheng23 commented Apr 23, 2021 via email

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

4 participants