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

Feat/align FSRS-rs with PyTorch Implementation #3540

Conversation

L-M-Sherlock
Copy link
Contributor

@L-M-Sherlock L-M-Sherlock commented Oct 28, 2024

The benchmark results based on 20k collections:

Weighted by number of reviews

Model #Params LogLoss RMSE(bins) AUC
PyTorch 19 0.319±0.0054 0.049±0.0010 0.702±0.0027
v1.4.1 19 0.319±0.0052 0.049±0.0010 0.702±0.0026
v1.3.5 19 0.322±0.0053 0.051±0.0011 0.694±0.0029

Weighted by number of users

Model #Params LogLoss RMSE(bins) AUC
PyTorch 19 0.346±0.0031 0.0710±0.00085 0.698±0.0017
v1.4.1 19 0.346±0.0031 0.0710±0.00084 0.698±0.0017
v1.3.5 19 0.347±0.0031 0.0716±0.00087 0.693±0.0018

Related PR:

@dae dae merged commit 0fa9e0e into ankitects:main Nov 5, 2024
1 check passed
@L-M-Sherlock L-M-Sherlock deleted the Feat/align-FSRS-rs-with-PyTorch-Implementation branch November 5, 2024 08:52
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

Successfully merging this pull request may close these issues.

2 participants