# ELECTRA Paper Doubts

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Felectra-paper-doubts%2F54063%3E%5C
**Category:** Research\
**Created:** [September 8, 2023, 7:41am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Felectra-paper-doubts%2F54063 "2023-09-08T07:41:02Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Srinjoy](https://avatars.discourse-cdn.com/v4/letter/s/d9b06d/32.png) [@Srinjoy](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FSrinjoy)%5C
**Post date:** [September 8, 2023, 7:41am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Felectra-paper-doubts%2F54063%2F1 "2023-09-08T07:41:02Z")

</div>

Hello Everyone,  
I am Srinjoy, a master’s student currently studying NLP. I was reading the ELECTRA paper by Clark et al. I learned about the implementation and had a few doubts.

I was wondering if you could help me with those.

1. What exactly does the “Step” mean in step count? Does it mean 1 epoch or 1 minibatch?
2. 
  1. Also, in the paper I saw (specifically in Table 1), ELECTRA-SMALL and BERT-SMALL both have 14M parameters, how is that possible as ELECTRA should have more parameters because its generator and discriminator module are both BERT-based?

3. Also, what is the architecture of both the generator and discriminator? Are they both BERT to something else?
4. Also, we have a sampling step between the generator and the discriminator. How are you back-propagating the gradients through this?

Thanks in advance