Thanks a lot for the amazing work!
However, in BERT_NER.py line 348, you set BertModel's is_training parameter to change alone with the fine-tuning procedure, but as the model is not integrated in the real training model (use the output of BertModel's final layer as the real input). So as far as I'm concerned, this parameter should be set to False to gain more reasonable result.
Thanks a lot for the amazing work! However, in
BERT_NER.py line 348
, you setBertModel
'sis_training
parameter to change alone with the fine-tuning procedure, but as the model is not integrated in the real training model (use the output ofBertModel
's final layer as the real input). So as far as I'm concerned, this parameter should be set toFalse
to gain more reasonable result.