Is something wrong with loss?

monologg / JointBERT

Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"

Apache License 2.0

662 stars 186 forks source link

Is something wrong with loss? #34

Open yangdongdong2000 opened 8 months ago

yangdongdong2000 commented 8 months ago

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.