Closed zzachw closed 1 year ago
Better sentence split in dataset.py, which handles decimal points
dataset.py
It seems there is some issue with the soft clip loss. It seems similarity score of -1 is better than 0? However, the softmax is doing the opposite.
Better sentence split in
dataset.py
, which handles decimal pointsIt seems there is some issue with the soft clip loss. It seems similarity score of -1 is better than 0? However, the softmax is doing the opposite.