Closed mikonapoli closed 4 years ago
Good catch, will fix tomorrow. In general, you can directly open a PR for a change like this, instead of filing an issue.
Oh looking more into it, it's not self.skip_start
that should be used since the validation losses are fewer than the training losses. The right index has to be computed.
It is a very simple change in notebook n. 13 (learner): the
plot_loss
method of theRecorder
class should beInstead of the current