Before you go onto the next unit, I have created some CO-LABS
with each of these options. Try them out for yourself, check on
the time, check on the results, and see what techniques you can figure
out to avoid some of the overfitting. Remember that with text, you'll probably get a bit more overfitting
than you would have done with images. Not least because you'll
almost always have out of vocabulary words in
the validation data set. That is words in the validation dataset
that weren't present in the training, naturally leading to overfitting. These words can't be classified and,
of course, you're going to have these overfitting issues, but
see what you can do to avoid them.