Training a model from scratch: CIFAR 10

[ramesh (Ramesh Sampath)]

We have feature requests to add Early Stopping and Model Checkpoints to prevent overfitting. You can find more here, under the Learner Fit Options - Wiki: Fastai Library Feature Requests)

@zpnc

towards the end of your training the resnext model in cifar10.ipynb (image size 32x32) the model looks like it is severely overfitting (training loss <0.10; validation loss ~ between 0.2 - 0.3), but you kept on fitting. Does this mean that we should ignore overfitting as long as the validation loss is reducing?

I would like to know the thoughts on when to stop the model fitting process.