I started to perform deep learning for sentiment analysis on word embedding. I have plot the model loss and accuracy graph for each epochs to understand the performance better. I read the following post which is related to underfitting and overfitting.
https://machinelearningmastery.com/diagnose-overfitting-underfitting-lstm-models/ However, for my model the training accuracy is increasing but the validation accuracy is constant just after 4 epochs.
I just wanted to ask what if the training accuracy increases/ training loss decreases while the validation loss and accuracy remain same?
What does this specific case mean? How can I overcome it? Does this mean that there is not enough test data or I need a better model?