Validation Loss as well as validation F1 increasing
Aperta
- Lingua principale
- Python
- Stelle
- 1.7k
- Fork
- 232
- Metriche di merge delle PR
- Nessuna PR unita negli ultimi 30g
Descrizione
Hi,
While finetuning scibert on JNLPBA and bc5cdr dataset, I observed very strange phenomenon.
The validation loss is increasing whereas the validation F1 in either increasing or staying the same.
Please let me know because I have faced a similar issue when I used pytorch-crf over scibert. There also for ner (JNLPBA and bc5cdr) validation loss anf validation f1 are increasing.
Guida per i contributori
Nessuna guida per i contributori indicizzata per questo repository
Valutazione
Questa issue non è ancora stata valutata.