Lesson 4 official topic

[Mattr (Matt Rosinski)]

I made one small change to Jeremy’s Kaggle NLP notebook from this:
model_nm = 'microsoft/deberta-v3-small'

To this:
model_nm = 'distilroberta-base'

The tokenizer with this model is different but was still working.

But then I got an error during the first epoch after running >> trainer.train();

This reply to a week 2 question helped correct the problem.

Lesson 2 official topic

Try changing the definition of corr to this: def corr(x,y): return np.corrcoef(x.squeeze(),y)[0][1] Then it should run. I found this by running Python’s interactive debugger with %debug, and type up until I got to the code in this notebook. Then looking at the inputs I noticed x has shape (9919,1) whereas y is just (9919,). We need a way to drop the extra dimension, and np.squeeze is nice because if x is already 1 dimensional it won’t change the value. I have no idea why the shape of the mo…

What other issues might occur when using different models?