allenai / cartography Goto Github PK

Hi,

Thanks for the nice work!

I have a question about L149:

I don't understand why you are enumerating over correctness_ .
I might misunderstand something, but I think you should iterate over all the guids instead.
Otherwise, you cannot dump the statistics of the entire training set as guid in this loop only has 1 + Epoch possible values.

  df = pd.DataFrame([[guid,
                      i,
                      threshold_closeness_[guid],
                      confidence_[guid],
                      variability_[guid],
                      correctness_[guid],
                      forgetfulness_[guid],
                      ] for i, guid in enumerate(correctness_)], columns=column_names)

Thank you!

hi
Is it normal to take 4 hours for installing cartography package?

Hi
what is the solution for this error?

Thanks a lot for the paper. It was an interesting read. I wanted to know more about the hack which you have used in run_glue.py in line number 146 # HACK(label indices are swapped in RoBERTa pretrained model). Could you please explain more in this regard?

hi, why only 12 samples are filtered out of 1200?

Hi. Thanks for the repo. Does the code support multi-label text classification task?

Hi! This looks like a very interesting tool, I am wondering if it would be easy to use on other datasets. I see only GLUE/NLI datasets are supported. Do you have any tips on how to use this on a simple {TEXT, LABEL} task? Thanks!

Could you please tell me where to get the same data as your example? Thanks!

Hi,
I am facing issue in installing the correct huggingface transformers version as the git branch in the requirements has been deleted. Could you please update the requirements.txt.
Regards,
Aswin