How to fix the error UserWarning: the value of ‘evaluate_every_number_of_epochs’ is greater than the value of ‘epochs’. No evaluation will occur

How to fix the error UserWarning: the value of ‘evaluate_every_number_of_epochs’ is greater than the value of ‘epochs’. No evaluation will occur

I do not know how to remove this warning. I have already tried everything - I deleted all the old models and created a new one, but I still got this error. After this warning appears, the bot works differently(incorrectly). Help me, please

I have rasa 2.7.1

this is what the error looks like in the console:

config.yml looks like this:

# Configuration for Rasa NLU.
# https://rasa.com/docs/rasa/nlu/components/
language: en

pipeline:
 # No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.
 # If you'd like to customize it, uncomment and adjust the pipeline.
 # See https://rasa.com/docs/rasa/tuning-your-model for more information.
   - name: WhitespaceTokenizer
   - name: RegexFeaturizer
   - name: LexicalSyntacticFeaturizer
   - name: CountVectorsFeaturizer
   - name: CountVectorsFeaturizer
     analyzer: char_wb
     min_ngram: 1
     max_ngram: 4
   - name: DIETClassifier
     epochs: 100
     constrain_similarities: true
     evaluate_on_number_of_examples: 0
     evaluate_every_number_of_epochs: 5
     model_confidence: linear_norm
   - name: EntitySynonymMapper
   - name: ResponseSelector
     epochs: 100
     constrain_similarities: true
     model_confidence: linear_norm
     evaluate_on_number_of_examples: 0
     evaluate_every_number_of_epochs: 5
   - name: FallbackClassifier
     threshold: 0.3
     ambiguity_threshold: 0.1

# Configuration for Rasa Core.
# https://rasa.com/docs/rasa/core/policies/
policies:
# # No configuration for policies was provided. The following default policies were used to train your model.
# # If you'd like to customize them, uncomment and adjust the policies.
# # See https://rasa.com/docs/rasa/policies for more information.
   - name: MemoizationPolicy
   - name: RulePolicy
   - name: TEDPolicy
     max_history: 5
     evaluate_on_number_of_examples: 0
     evaluate_every_number_of_epochs: 5
     epochs: 100
     constrain_similarities: true
     model_confidence: linear_norm

@Tomilin228 Hi, Why you using this?

    evaluate_on_number_of_examples: 0
    evaluate_every_number_of_epochs: 5

@nik202 thought it would help. Tried without them and got no result

@Tomilin228 Not get you still, If you still with basic configuration. It will provide you the result.

# Configuration for Rasa NLU.

# https://rasa.com/docs/rasa/nlu/components/

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

    ranking_length: 5

    constrain_similarities: true

    model_confidence: linear_norm

  - name: EntitySynonymMapper

  - name: ResponseSelector

    epochs: 100

    constrain_similarities: true

    model_confidence: linear_norm




# Configuration for Rasa Core.

# https://rasa.com/docs/rasa/core/policies/

policies:

  - name: MemoizationPolicy

  - name: TEDPolicy

    max_history: 5

    epochs: 100

  - name: RulePolicy

    nlu_threshold: 0.4

    core_threshold: 0.4

    fallback_action_name: "action_default_fallback"

Change Threshold as per your need and new sytnax. Train and run you will be fine. Delete previous trained model please.

@ nik202 then it is impossible to fix it? why does this warning appear?

@Tomilin228 I am not saying that you can’t fix it mate. I am not getting any warning like this. If you share all files, I can run and check for you. For that I need Rasa version detail and python version. Thanks.

@Tomilin228 If you ignore this warning are your bot is working as you expected? If yes then ignore. If not then yes we need to fix this issue asap.

rasa-test.zip (6.4 KB)

Python 3.8.10

rasa 2.7.1

Снимок экрана от 2021-07-05 22-52-52

@Tomilin228

Rasa Version      :         2.6.2
Minimum Compatible Version: 2.6.0
Rasa SDK Version  :         2.6.0
Rasa X Version    :         None
Python Version    :         3.8.10

No such warning message is coming after train and run. Means there is an active bug in the Rasa 2.7.1. I am further checking for Rasa Ver 2.7.1.

@Tomilin228 Are you sure because of this Warning your bot/user conversations is effected or your bot behave differently as you mentioned? Did you delete the older versions and trained the bot? I think this is the 2.7.1 Version issue at the rasa backend. But, still my eyes on this error.

Yes, I’m sure the bot behaves differently

1 Like