训练Rasa/LaBSE时内存不足
训练Rasa/LaBSE时内存不足
提问于 2022-06-05 05:46:29
我想从rasa/LaBSE那里训练LanguageModelFeaturizer。我遵循了文档中的步骤，没有更改默认的培训数据。
我的配置文件看起来如下：
# The config recipe.
# https://rasa.com/docs/rasa/model-configuration/
recipe: default.v1
# 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: LanguageModelFeaturizer
# Name of the language model to use
model_name: "bert"
# Pre-Trained weights to be loaded
model_weights: "rasa/LaBSE"
cache_dir: null
- name: CountVectorsFeaturizer
- name: CountVectorsFeaturizer
analyzer: char_wb
min_ngram: 1
max_ngram: 4
- name: DIETClassifier
epochs: 100
constrain_similarities: true
batch_size: 8
- name: EntitySynonymMapper
- name: ResponseSelector
epochs: 100
constrain_similarities: true
- name: FallbackClassifier
threshold: 0.3
ambiguity_threshold: 0.1在运行rasa train之后，我得到：
tensorflow.python.framework.errors_impl.ResourceExhaustedError: failed to allocate memory [Op:AddV2]我使用的是6GB内存的GTX 1660ti。我的系统规范是：
Rasa
----------------------
rasa 3.0.8
rasa-sdk 3.0.5
System
----------------------
OS: Ubuntu 18.04.6 LTS x86_64
Kernel: 5.4.0-113-generic
CUDA Version: 11.4
Driver Version: 470.57.02
Tensorflow
----------------------
tensorboard 2.8.0
tensorboard-data-server 0.6.1
tensorboard-plugin-wit 1.8.1
tensorflow 2.6.1
tensorflow-addons 0.14.0
tensorflow-estimator 2.6.0
tensorflow-hub 0.12.0
tensorflow-probability 0.13.0
tensorflow-text 2.6.0定期的训练效果很好，我可以运行模型。我试图减少batch_size，但错误仍然存在。
回答 3
Stack Overflow用户
回答已采纳
发布于 2022-06-26 04:19:36
使用google运行相同的代码(使用16 GPU的GPU内存)可以正常工作。该模型使用6.5-7GB的内存。
Stack Overflow用户
发布于 2022-06-07 16:45:41
您可以创建交换内存，如果您的RAM在培训的某个点变得满。
Stack Overflow用户
发布于 2022-09-02 06:50:05
我假设OOM是使用饮食分类器的
尝试减少这些参数中的一些。我将列出下面的默认值
- name: DIETClassifier
epochs: 100
batch_size: [16, 32]
num_transformer_layers: 2
embedding_dimension: 20
hidden_layer_sizes:
text: [256, 128]
...页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/72505074
复制相关文章
相似问题
腾讯云开发者
