If loss is decreasing but val_loss not, what is the problem and how can I fix it?

I get such vague result: enter image description here

  • $\begingroup$ Are you sure this isn't backwards? It would be odd for validation loss to be consistently lower than train. Not impossible, but atypical. $\endgroup$
    – Sean Owen
    Mar 9 '19 at 22:11

This indicates that model is not generalizing (it is over-fitting). Few options are :

  1. Get more training data
  2. Reduce complexity of model (Number of LSTM layers, complexity of dense layers)

Andrew NG has a good video on this topic :


A tutorial specific to LSTM :



Not the answer you're looking for? Browse other questions tagged or ask your own question.