mmine/testwfh

This is an attempt to reproduce the model developed in the paper “Remote Work across Jobs, Companies, and Space” (Hansen, Lambert, Bloom, Davis, Sadun & Taska, 2023). The model is a finetuned version of the distibert-base-uncased model on the binary classfication task of predicting if a fragment of text exhibits the possibility of remote work (=1) or not (=0).