Self_Explaining_Structures_Improve_NLP_Models icon indicating copy to clipboard operation
Self_Explaining_Structures_Improve_NLP_Models copied to clipboard

Published 20 hours ago • verified publisher icon ShannonAI

Hyperparameters to reproduce the same results for roberta-base as mentioned in the paper

Open sumit-agrwl opened this issue 3 years ago • 0 comments

I am wondering what are the exact hyperparameters for the model to get the same results mentioned in the paper. Since the seed is set fixed, I wished running the command that you had mentioned would give the accuracy mentioned in the paper on SST-5 i.e. 57% but its not doing that.

sumit-agrwl avatar Oct 01 '21 01:10 sumit-agrwl