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?
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?