Vipula Rawte

How do you deal with sequences longer than 512 tokens? Thanks!

Also, since it uses BinaryClassificationProcessor, it creates the logits tensor with size of [10,2] (say, my input file has 10 texts). After view(-1), logits becomes size=20 but the labels are...

On setting: 'output_mode': 'regression' it still gives the following error: 

Hi, Thanks for your suggestion but it did not work. `from apex import amp` works only when present in apex directory. I am wondering how to make it global because...

So in your case, it would be 20 x 768? (since max # chunks = 20)?

More explanation on how loss is calculated for every chunk separately? I mean the entire document has a target label and so AFAIU, the loss would be calculated for this...

I am not clear what the "sequences" is in the following code to find attention weights: test_seq = pad_sequences([sequences[index]], maxlen=MAX_SEQUENCE_LENGTH) Thank you!

This [issue](https://github.com/psnonis/FinBERT/issues/3) might be helpful.

Yes, it should work.

@nehatj, @franz101 Thank you for pointing this out. I'll fix this in the next version. All the updates will be pushed [here](https://github.com/vr25/fin_RoBERTa). Thanks!