search

microsoft / DeBERTa

The implementation of DeBERTa
MIT License
1.91k stars 216 forks source link

Question about the hyperparameters of SuperGlue #54

Open oyxuan-11 opened 3 years ago

oyxuan-11 commented 3 years ago

Hi

What are the parameters of Deberta finetune superglue for each task, such as batch, GPU cards, learning rate, etc.?
I couldn't find the detailed parameters of each task in SuperGLue in the paper.

How can I reproduce Deberta's results on SuperGlue leaderboard?