How to apply this change to this Bert Implementation?

I am new to torch, for my project I am trying to train the base-uncased Bert model on my notes, I have oneHoted my labels consist of 10 labels. so I am trying to feed 10 columns of labels and one column of notes.
I am following this tutorial to implement the project.
but I faced this error: Expected input batch_size (16) to match target batch_size (160).
I have changed the setting the way I wanted so I replaced the batch size with 16 and label numbers with 10.

I found the same problem here but I don’t know how to apply it to my code