Using an encoder-decoder model for Recognizing Textual Entailment (GLUE task)


I am trying to use an encoder-decoder model for the rte (Recognizing Textual Entailment) GLUE task.

For convenience purposes, I will add the google colab notebook on how I tried to do this.

As you can see there, I am getting the following error:
IndexError: too many indices for tensor of dimension 1

Can anyone help me out? I have looked this up and am starting to even wonder if it is possible to use an encoder-decoder model for this task. I am not an expert with using these models, so maybe it is very obvious, I just can’t figure it out.
It would be much appreciated :slight_smile: