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.

Sign up for GitHub

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

Jump to bottom

Model prediction (single predict) always returns "not yes and" #25

Open

idanvidra opened this issue Nov 8, 2021 · 0 comments

idanvidra commented Nov 8, 2021

Hello @wise-east ,

I want to deploy this projects model so that I can classify stories as "yes and" or "non yes and".

I've deployed the project locally to my environment and seem to be getting "not yes and" for any pair of (prompt, response) I feed the model.

I'm using the pytorch model "bert_postacl_with_selfyesand_v2" as given here:
https://drive.google.com/file/d/1My_8SGJHR43bLHepYAl6O8WG1fbH9_9P/view

Here is an example for a sanity check I've made:
The prompt and response were taken from the dataset the model trained on
(data point id: 101430).

Any suggestions on how to get the model to predict accurately ?
Thank you for your support :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment