Hey Everyone, I was wondering why it seems necessary to run rasa train before running rasa test nlu --cross-validation. I assume the model should get trained on the training split during the cross-validation process anyway, correct? I just want to make sure I’m not accidentally leaking some nlu examples from the test set into the training set. Apologies if this is a silly question, I’m brand new to Rasa.

@bsir Hope this will help you. [image] How the test/train split works in rasa Rasa Open Source @AminaDerouiche It is a benchmark or recommended while training the model we consider 80:20 ratio is a standard starting point to train and test our model. In RASA they have set the default 0.8 as mention: –training-fraction TRAINING_FRACTION Percentage of the data which should be in the training data. (default: 0.8) Reference 1: Testing Your Assistant Reference 2: https://rasa.com/docs/rasa/command-line-interface#rasa-data-splithttps://rasa.com/docs/rasa/command-line-interface#rasa-data-sp…

Training model before running cross validation

Rasa Open Source

nik202 (NiK202) June 10, 2021, 7:31pm 2

@bsir Hope this will help you.

Topic		Replies	Views
How the test/train split works in rasa Rasa Open Source	4	2844	October 20, 2021
Rasa nlu test starts training instead of test Rasa Open Source testing	3	1356	June 29, 2022
How "rasa test nlu" works? Rasa Open Source	2	1277	November 12, 2020
Specify train/test file in rasa train/test nlu Rasa Open Source	1	1452	May 28, 2019
Rasa split data nlu fails. Which algorithm is implemented? Rasa Open Source	8	505	September 7, 2020

Training model before running cross validation

Related topics