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

The en_core_web_trf model results in zero output #13147

Closed
HarounAbdelsamad opened this issue Nov 23, 2023 Discussed in #13145 · 2 comments
Closed

The en_core_web_trf model results in zero output #13147

HarounAbdelsamad opened this issue Nov 23, 2023 Discussed in #13145 · 2 comments
Labels
feat / transformer Feature: Transformer training Training and updating models

Comments

@HarounAbdelsamad
Copy link

Discussed in #13145

Originally posted by HarounAbdelsamad November 22, 2023
I tried training the en_core_web_trf model based on datasets i have but after training and evaluation the fscore, recall and precision are all zero. I tried using the small model works fine. I changed the code so that the transformer component is added to the pipe and also use another config file for this. Here is my code for reference:
Could anybody help me or direct me towards the issue?
code.txt

@rmitsch rmitsch added training Training and updating models feat / transformer Feature: Transformer labels Nov 23, 2023
@rmitsch
Copy link
Contributor

rmitsch commented Nov 23, 2023

Please don't open duplicate tickets. Continuing the discussion in #13145.

@rmitsch rmitsch closed this as completed Nov 23, 2023
Copy link
Contributor

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.

@github-actions github-actions bot locked as resolved and limited conversation to collaborators Dec 24, 2023
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
feat / transformer Feature: Transformer training Training and updating models
Projects
None yet
Development

No branches or pull requests

2 participants