Hi, I am using Rasa 2.8.8 version My training files are composed of 90 000 examples, 70 intents and 20 entities I’m training only the NLU part When I was doing my training, I had an OOM error. So I reduced the batch size but the training now takes more than 10 hours. I tried to run it on the GPU but the training time doesn’t reduce. Do you have any ideas on how to achieve a shorter training time? Here is my pipeline: language: "fr" pipeline: - name: WhitespaceTokenizer - name: LexicalSyntacticFeaturizer - name: CountVectorsFeaturizer analyzer: "word" - name: DIETClassifier batch_size: 4 epochs: 50 - name: EntitySynonymMapper - name: ResponseSelector epochs: 100

Rasa 2.8 Training takes too much time

ChrisRahme (Chris Rahmé) May 10, 2022, 6:06pm 2

Salut Quentin!

You really have a LOT of examples, for an average of ~1300 examples per intent!

I would suggest having a maximum of 100 examples per intent, if not even 20.

Topic		Replies	Views
Rasa Model taking alot of time to train Rasa Open Source	9	2637	June 11, 2020
Rasa train taking lot of time Rasa Open Source	22	5093	July 6, 2021
NLU training takes a long time Rasa Open Source	2	854	March 22, 2021
Incredibly Slow NLU Training of Dialogflow Exported Intents Rasa Open Source	2	452	December 18, 2020
Train a bot with large dataset Rasa Open Source	2	911	December 11, 2019