Convolutional Neural network learning curve results

Working on a convolutional neural network with 6 classes and about 1500 image per class. The model that works best for me has given the results below, in previous models I have worked on has given much smoother results and the validation isn't as jittery, now it does start to smoothen towards the end with 0.99 for both validation and training.

At some epochs the training gives and accuracy of 1.0 but again towards the end it remained at 0.99 for each epoch. When tested on unseen data(900 images) it performed very well at 0.98.

I understand it can be difficult to answer these type of questions when not seeing the data/model, but from the learning curve alone do you think I should be concerned about how high the accuracy is/jitter in validation even if it is performing well?