# Training validation stops after a couple of steps

**URL:** <https://forum.rasa.com/t/training-validation-stops-after-a-couple-of-steps/55907>\
**Category:** Rasa Open Source\
**Tags:** testing\
**Created:** [October 24, 2022, 8:01am UTC](https://forum.rasa.com/t/training-validation-stops-after-a-couple-of-steps/55907 "2022-10-24T08:01:59Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![kmariunas](https://avatars.discourse-cdn.com/v4/letter/k/76d3ee/32.png) [@kmariunas](https://forum.rasa.com/u/kmariunas)\
**Post date:** [October 24, 2022, 8:01am UTC](https://forum.rasa.com/t/training-validation-stops-after-a-couple-of-steps/55907/1 "2022-10-24T08:01:59Z")

</div>

Hello,

I was trying to set up my pipeline to output tensorboard logs, however I noticed in the graphs that the validation metrics stop after a couple of steps, whereas the training metrics continue

 ![image](https://europe1.discourse-cdn.com/flex013/uploads/rasa/original/3X/4/4/44cb8fa207a72e1ab7be452a1269925563ac89aa.png)

I can also see it happening in the terminal, where at some point all the `val_` metrics disappear.

Here is my config:

```auto
language: en

pipeline:
   - name: WhitespaceTokenizer
   - name: RegexFeaturizer
   - name: LexicalSyntacticFeaturizer
   - name: CountVectorsFeaturizer
   - name: CountVectorsFeaturizer
     analyzer: char_wb
     min_ngram: 1
     max_ngram: 4
   - name: DIETClassifier
     batch_size: 32
     epochs: 20
     constrain_similarities: true
     evaluate_on_number_of_examples: 880 # 15% of the data for validation
     evaluate_every_number_of_epochs: 2
     tensorboard_log_directory: "models/tensorboard/v4"
     tensorboard_log_level: "epoch"
   - name: EntitySynonymMapper
   - name: FallbackClassifier
     threshold: 0.3
   - name: ResponseSelector
     epochs: 5
     evaluate_every_number_of_epochs: 1
     evaluate_on_number_of_examples: 20
     constrain_similarities: true

policies:
   - name: MemoizationPolicy
   - name: RulePolicy
     core_fallback_threshold: 0.6
     core_fallback_action_name: action_default_fallback
     enable_fallback_prediction: true
   - name: TEDPolicy
     max_history: 7
     epochs: 1
     constrain_similarities: true

```

---

<div class="post-metadata">

**Author:** ![zchenchen1999](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/zchenchen1999/32/22683_2.png) [@zchenchen1999](https://forum.rasa.com/u/zchenchen1999)\
**Post date:** [March 28, 2023, 5:31pm UTC](https://forum.rasa.com/t/training-validation-stops-after-a-couple-of-steps/55907/2 "2023-03-28T17:31:51Z")

</div>

hi, I also have this problem too! someone can help? please

---

<div class="post-metadata">

**Author:** ![netvid](https://avatars.discourse-cdn.com/v4/letter/n/ee59a6/32.png) [@netvid](https://forum.rasa.com/u/netvid)\
**Post date:** [May 16, 2023, 1:31pm UTC](https://forum.rasa.com/t/training-validation-stops-after-a-couple-of-steps/55907/3 "2023-05-16T13:31:47Z")

</div>

Same issue here. Any help would be appreciated.