First of all, thank you for this great repo, this is highly valuable to have reproducible code/data/models of this quality.
I am currently trying to reproduce the scores from your paper, everything works well, I manage to observe the same accuracy than what's pointed in your article for imdb and yelp.
Nevertheless, the FAKE bert pretrained model that I took from your drive produces random results (I get 50% accuracy while it should be 96.7)
Are you sure that you uploaded the good model on drive ?
Hi Di Jin and collaborators,
First of all, thank you for this great repo, this is highly valuable to have reproducible code/data/models of this quality.
I am currently trying to reproduce the scores from your paper, everything works well, I manage to observe the same accuracy than what's pointed in your article for imdb and yelp.
Nevertheless, the FAKE bert pretrained model that I took from your drive produces random results (I get 50% accuracy while it should be 96.7)
Are you sure that you uploaded the good model on drive ?
Best regards,
Antoine