I read about the validations curves, and the following plot is similar to overfit, but in this case, the validation curve doesn't' growth again.

So is this overfit? why?


enter image description here

  • 1
    $\begingroup$ are you sure your data is segmented randomly? have you tried retraining it? $\endgroup$ Commented Jun 27, 2020 at 15:34

1 Answer 1


So, overfitting occurs when the model is complex enough to fit very well with examples observed in the training data, such that the model is not able to generalise well over unseen instances (validation data).

Therefore, for overfitting, we expect the training F1 score to continually decrease, whilst the valid_1 F1 score increases.

Here, the plot shows that both training and validation F1-score has stabilised over epochs/iterations. Arguably though, we can see that valid_1 marginally increases as the training F1 score decreases. This can be indicative of (very mild) overfitting.


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.