Skip to content

MKMaS-GUET/Effective_Metrics

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Effective_Metrics

If you want to calculate sp, ssp and essp, you can do

  1. cd Measuring

  2. By modifying the layerIndex parameter in raw_to_largebert.py, you can specify the submodule.

  3. python raw_to_largebert.py

  4. Obtain embeddings generated by the specified submodule.

  5. Modify the l and r parameters in train_sp.py, train_ssp.py, and train_essp.py to compute the sp, ssp, and essp for the submodules from l to r-1.

  6. python train_sp.py

  7. python train_ssp.py

  8. python train_essp.py

If you want to verify the results of the fine-tuning experiment, you can do

  1. cd Fine-tuning

  2. python fixed_train.py

  3. then you can find and open the porb_cola-seed1~40.csv file in the ./Fine-tuning directory to see the experimental results.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published