Hi, really nice to see the new DIET classifier, good job rasa team. I got a probelm when training DIET, [58%20PM] My process was killed, because of extreme resource starvation, even if I only tried to use light config: language: en pipeline: name: ConveRTTokenizer name: ConveRTFeaturizer name: CountVectorsFeaturizer name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 name: DIETClassifier epochs: 20 learning_rate: 0.005 num_transformer_layers: 0 embedding_dimension: 10 weight_sparcity: 0.90 hidden_layer_sizes: text: [256, 128] policies: name: EmbeddingPolicy max_history: 10 epochs: 20 batch_size: 32 64 max_history: 6 name: AugmentedMemoizationPolicy core_threshold: 0.3 name: TwoStageFallbackPolicy nlu_threshold: 0.8 name: FormPolicy name: MappingPolicy My question is: is there a hardware requirement for training DIET? I am using GCP 4xCPU 26GB compute engine, but seems not enough……

what is the size of your training data?

config you provided, doesn’t correspond to the log

Thanks for your response: my nlu.md file is 314,836 bytes (373 KB on disk) sorry, I pasted a wrong one, my config is: name: ConveRTTokenizer name: ConveRTFeaturizer name: CountVectorsFeaturizer name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 name: RegexFeaturizer name: LexicalSyntacticFeaturizer name: EntitySynonymMapper name: DIETClassifier intent_classification: Ture entity_recognition: True use_masked_language_model: False number_of_transformer_layers: 0 policies: name: EmbeddingPolicy max_history: 10 epochs: 20 batch_size: 32 64 max_history: 6 name: AugmentedMemoizationPolicy core_threshold: 0.3 name: TwoStageFallbackPolicy nlu_threshold: 0.8 name: FormPolicy name: MappingPolicy

Or should I splite intent classification and entity extraction by using 2 DIET classifier component?

try removing name: CountVectorsFeaturizer analyzer: char_wb min_ngram: 1 max_ngram: 4 and see whether it’ll start working

Thanks for your suggestion, I removed both countvectorfeaturizer and unfortunately it still not working: [24%20AM]

is there a way to find out why the process was killed?

Yes, I was monitoring the CPU and memory usage during training, I think that’s because cpu usage is too high

I have the same problem, have you solved it?

Training killed when using DIET config

Rasa Open Source

rmsharks4 (Ramsha Siddiqui) February 27, 2021, 2:42pm 11

Having the same problem.

Topic		Replies	Views
Training killed when using DIET with large training set Rasa Open Source	2	515	January 20, 2021
Rasa 1.10.14 DIETClassifier takes a very long time and it's not using GPU Rasa Open Source	1	875	June 29, 2022
Issue regarding Fastening the model training with DIET classifier Rasa Open Source	1	678	November 6, 2020
Rasa 1.10 dietclassifier cpu and speed issues Rasa Open Source	1	766	October 26, 2020
Question about DIET classifier implementation details - Are featurizers trained? (and others) Rasa Open Source	1	363	May 4, 2023

Training killed when using DIET config

Related topics