I have NLU train data with about 60 intents and 160 entities.
When I upload this file via Rasa X (installed using docker) it uploads fine, I see this data in Rasa X UI. I start training, but after about 1-hour of waiting, I get the message that training failed. I checked rasa-worker docker logs and didn`t find any errors.
I tried training from the command line. I took sample project, removed not needed data, replaced nlu data, changed config.yml and training worked fine. It took about 1 hour.
How I can find the reason why Rasa X training fails? I`m looking wrong logs?
My config:
language: en pipeline: - name: WhitespaceTokenizer - name: RegexFeaturizer - name: LexicalSyntacticFeaturizer - name: CountVectorsFeaturizer - name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 - name: DIETClassifier epochs: 100 - name: EntitySynonymMapper - name: ResponseSelector epochs: 100 policies: - name: MemoizationPolicy - name: TEDPolicy max_history: 5 epochs: 100 - name: RulePolicy