I used both BERT_base_cased
and BERT_large_Cased
model for multi class text classification. With BERT_base_cased, I got satisfactory results. When I tried with BERT_large_cased model, the accuracy is same for all the epochs
With BERT_base_cased
, there is no such problem. But with BERT_large_cased
, why accuracy is same in all the epochs? Any help is really appreciated…