Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
yangdongdong2000 opened this issue 6 months ago · comments
I don't know if you've ever encountered this issue in your training, the loss increased but all other metrics decreased. It's weird... I don't know if it affects convergence.