Should we watch val_loss or val_acc in callbacks?
pawelkedra opened this issue · comments
In cifar10.py 2 callbacks are used:
ReduceLROnPlateau(monitor='val_loss', factor=np.sqrt(0.1), cooldown=0, patience=5, min_lr=0.5e-6) EarlyStopping(monitor='val_acc', min_delta=0.001, patience=10)
First one changes learning rate when validation loss stops decreasing, second one stops learning when validation accurracy stops increasing. Shouldn't both monitor the same quantity? When I use this callbacks with such configuration, learning often stops when validation accuracy is quite low. I observed that best final results are achieved when in both callbacks is used val_loss, with val_acc they are slightly worse (but not much).
What do you think about it?
I think we should keep both monitored metrics consistent. Thanks for pointing this out.
I updated the code.