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
[ALBERT]Has anyone reproduced ALBERT a scores on GLUE dataset? #99
Comments
https://github.com/kamalkraj/ALBERT-TF2.0 [WIP] |
On the
|
Dataset: MNLI |
https://github.com/lonePatient/albert_pytorch Dataset: MNLI |
@lonePatient |
@kamalkraj |
@lonePatient |
@kamalkraj 。fine-tuning, dropout rate=0.1 |
I convert tf weight to pytorch weight ,and on QQP dataset, I only get 87% accuracy.
model: albert-base
epochs: 3
learning_rate; 2e-5
batch size: 24
max sequence length: 128
warmup_proportion: 0.1
The text was updated successfully, but these errors were encountered: