I am using the tutorial in Keras documentation here. I am new to deep learning. On a different dataset Menyo-20k dataset, of about 10071 total pairs, 7051 training pairs,1510 validation pairs,1510 test pairs. The highest validation accuracy and test accuracy I have gotten is approximately 0.26. I tried the list of things below:

  1. Using the following optimizers: SGD, Adam, RMSprop
  2. Tried different learning rate
  3. Tried the dropout rate of 0.4 and 0.1
  4. Tried using different embedding dimensions and feed-forward network dimension
  5. Used Early stopping and patience =3, the model does not go past the 13th epoch. I tried the model itself without changing any parameters, the validation accuracy never got to 0.3, I tried to change the different parameters in order to know what I am doing wrong and I can't figure it out. Please what am I doing wrong? Thank you in advance for your guidance.
  • $\begingroup$ Did you use early stopping? Patience = 3 seems very low. Also the available data seems to be on the small side. Maybe you could try on the character level keras.io/examples/nlp/lstm_seq2seq $\endgroup$
    – Peter
    Jan 28, 2022 at 21:59
  • $\begingroup$ Yes, I used early stopping with patience =3. Thank you very much, I would try that tutorial. $\endgroup$
    – Fhunmie
    Jan 29, 2022 at 14:26

1 Answer 1


Few things can be tried :-

  1. Increase no of iterations a lot
  2. Add more neural or Transformer layers
  3. Use Bleu Score metric instead of accuracy metrics as accuracy metrics in machine language translation does not make that much sense.
  4. May need larger dataset

Not sure what will work finally - have to experiment

  • 1
    $\begingroup$ I would definitely use Bleu score instead, and source for more dataset thanks $\endgroup$
    – Fhunmie
    Jan 29, 2022 at 21:28

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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