Before we go, let's have a quick look at plotting the learning history
of this model. The object has training accuracy
and loss values as well as validation accuracy
and validation loss values. So let's iterate over
these and plot them. Now, if you look closely, we didn't just call model.fit, we said history equals model.fit. So we now have a history object that
we can query for data. Here you can see I'm using
the same history object, and I'm calling its history
property passing at ACC which gets me
the model accuracy. When I run it and plot the training and
validation accuracy, we can see that my training
went towards one while my validation leveled out
into 0.7 to 0.75 range. That shows that
my model isn't bad, but I didn't really earn
anything after just two epochs. It fits the training data very well with the validation
data needed work. These results are borne out in the loss where we can see
that after two epochs, my training loss
went down nicely, but my validation loss climbed. So as it is, my model is about 75 percent accurate-ish
after two epochs, and I don't really need
to train any further. Remember also that we just used a subset of the full data. Using the entire dataset would likely yield better results. But before we do that, let's look at
a few other options, and we'll do that
in the next lesson.