I have trained a RNN/LSTM model. I would like to interpret my model results, after plotting the graph for Loss and accuracy (b/w training and Validation data set).

My objective is to classify the labels (either 0 or 1) if i provide only a partial input to the model. In such a way I have performed training.


Train 80% ; Validate 10 % ; Test 10%

X_train_shape : (243, 100, 5)
Y_train_shape : (243,)

X_validate_shape : (31, 100, 5)
Y_validate_shape : (31,)

X_test_shape : (28, 100, 5)
Y_test_shape : (28,)

Model Summary enter image description here

Model Graph enter image description here

Model Metrics enter image description here

Question or Interpretation from the model results

Q 1 : What can I understand/interpret from loss and Accuracy graph ? How can i confirm whether the model trained properly for my data set or not ?

Q 2 : Whether oscillations in both loss and accuracy, have some effect in >model training ? (Or it is a normal behavior) If not, how can I regularize my model without oscillations ?

Q 3 : What can I interpret or understand from my metrics tabular column ? My > Y_test accuracy is more when compared with Train & Validation accuracy, What can i interpret from this behavior ?

  1. From visually inspecting the graph, we see that the validation loss and accuracy has improved with each epoch - with the training loss and accuracy higher than that of validation. This indicates that accuracy has improved with training.

  2. As suggested in another post, one potential solution is to calculate the exponential moving average of the validation loss to remove the oscillations and better determine the improvement in this metric.

  3. If you are finding that the test accuracy is higher than that of training, this might suggest underfitting. This could imply that more training on your model is required, or has been over-regularized.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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