-
Notifications
You must be signed in to change notification settings - Fork 76
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
extremely high accuracy in document retrieval task #18
Comments
Two things to take note of here.
Thanks |
Thanks for replying.
|
That's because we used some default FLAX code and only did cursory sweep of hparams (hparam sweeps not within scope of the paper). Some other folks have found that training longer leads to better performance, hence I recommend works like https://arxiv.org/abs/2106.01540 and follow their setup. Thanks :) |
Hi,
I am testing the document retrieval task. I found that the zip file (https://storage.googleapis.com/long-range-arena/lra_release.gz) already contains the actual documents instead of just document ids. When I run the test with my own implementation of model in pytorch, the accuracy is over 70%.
The text was updated successfully, but these errors were encountered: