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

hardware configuration used for execution of program #4

Open
p06p05 opened this issue Sep 4, 2021 · 2 comments
Open

hardware configuration used for execution of program #4

p06p05 opened this issue Sep 4, 2021 · 2 comments

Comments

@p06p05
Copy link

p06p05 commented Sep 4, 2021

Sir,
Can you please tell what is the configuration and platform you used to execute the transformer code? This would be very helpful. please reply as soon as possible.

@JanSchm
Copy link
Owner

JanSchm commented Sep 9, 2021

Heyho,

the model configuration/hyperparameters should be all in the code.
In terms of hardware I utilized google colab and probably used a P100 or V100.

If you face out of memory issues, simply reduce the sequence length since classic transformers scale the amount of required computations for a sequence quadratically.

Hope this helps.

@p06p05
Copy link
Author

p06p05 commented Sep 9, 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

2 participants