# Imbalanced data in ner task

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimbalanced-data-in-ner-task%2F31078%3E%5C
**Category:** 🤗Transformers\
**Created:** [February 3, 2023, 9:35pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimbalanced-data-in-ner-task%2F31078 "2023-02-03T21:35:57Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![dkagramanyan](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/dkagramanyan/32/30446_2.png) [@dkagramanyan](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdkagramanyan)%5C
**Post date:** [February 3, 2023, 9:35pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimbalanced-data-in-ner-task%2F31078%2F1 "2023-02-03T21:35:57Z")

</div>

Hi!  
I have imbalanced dataset size N with such classes:

1. class 1 - 0.554\*N
2. class 2 - 0.271\*N
3. class 3 - 0.185\*N

I’m trying to solve NER task by fine-tuning Bert “dslim / bert-large-NER”, but during training my f1 score doesn’t rise above 0.53. I use Trainer from Transformers

Is there any ways to get f1=0.8?  
How could I use weights in Trainer loss function?

It’s really difficult to use up/down sampling