Keep only the best model as per Validation metrics

If this is true (red line would be the Validation set)

https://gerardnico.com/data_mining/overfitting
https://gerardnico.com/data_mining/overfitting

Is there any reason not to always use this?

# --------- CALLBACKS -------------------
callbacks=[fastai.callbacks.SaveModelCallback(learn, every=‘improvement’, monitor=‘valid_loss’)]
#-------------------------------------------------------

and then after lr_find do

if callbacks: learn.callbacks = callbacks
learn.fit_one_cycle(Nepochs, slice(lr));

And at the end

learn.load(“bestmodel”);

This would give us the model at the lowest point of the red line.