Training is failing with 503 error

Training is failing with 503 error. there are 2 flows with multiple branches. Policy given: policies:

  • name: TEDPolicy epochs: 50 max_history: 5 batch_size:
    • 32
    • 64
  • name: FormPolicy
  • name: RulePolicy
  • name: AugmentedMemoizationPolicy

Pipleline given: pipeline:

  • name: WhitespaceTokenizer
  • name: LexicalSyntacticFeaturizer
  • name: CountVectorsFeaturizer
  • name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4
  • name: DIETClassifier epochs: 200

- name: rasa_addons.nlu.components.gazette.Gazette

  • name: >- rasa_addons.nlu.components.intent_ranking_canonical_example_injector.IntentRankingCanonicalExampleInjector
  • name: EntitySynonymMapper
  • name: FallbackClassifier threshold: 0.7

it is deployed on ec2 instance(t3.2xlarge)

when i am decreasing the epochs of tedpolicy, training passed but not getting desired results. Earlier i was using 100 epochs then i reduced to 50.

Please help to resolve the issue