How about to set early stopping function in rasa training?

Rasa Open Source
1

image
image998×280 13 KB
I am training the Rasa response selector model, but for the epochs, I am not sure what number to set. I set 100 but the accuracy is 99% at 10 epochs, I have to stop training and set to 10 and retrain OR waiting for the end of training. :joy: :japanese_ogre: This is time-wasting. We can set an early stopping function no matter what users set. This is just a recommendation for improving Rasa, maybe there is already some functions I do not know? :upside_down_face:

2

Closest thing you can do is set checkpoint_model: True under DIET, TED, or ResponseSelector, which saves the best performing model during training.

It requires evaluate_on_number_of_examples > 0 and evaluate_every_number_of_epochs > 0 .

1 Like
3

@chensaics For more details do visit these Github links:

and the one which Chris suggested is this one:

Your recommendation are already considered :slight_smile:

4

@ChrisRahme @nik202 Thank you for your reply! :handshake:

1 Like
5

@chensaics No worries close this thread with the solution for others.