Reputation: 35
I am doing text classification with 3 classes, after training my model, the image below is my model accuracy and loss results, it means my models doesn't learn?
Upvotes: 0
Views: 323
Reputation: 550
It seems like your model is overfitting on the training set. This means it learns specific features of the training set that cannot be generalized to your validation set and consequently data it has not been trained on.
If you are using a neural network, investigate in using techniques that alleviate this like dropout and regularization. Some ideas around this can be seen here.
Upvotes: 1