What could cause a big fluctuation of the loss in the last epochs of training an AlexNet?

Question

I am training an AlexNet neural network, with about 12000 images which 80% is for training, 10% is for validation and another 10% is for testing. I have a problem in my plots. There is a big fluctuation in epoch 47, how can I have a smooth plot? What is the problem?

I tried to increase my validation data because the fluctuation was for validation loss. but nothing changed. I decreased learning rate, but it stucks in a local optimum.

Answer 1

I solved my problem with data augmentation and decreasing learning rate value and more epochs.