[Question] How to adjust learning rate when I use Bi-LSTM model on classification task?

BrikerMan / Kashgari

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

http://kashgari.readthedocs.io/

Apache License 2.0

2.4k stars 441 forks source link

[Question] How to adjust learning rate when I use Bi-LSTM model on classification task? #484

Closed honeysuckcle closed 2 years ago

honeysuckcle commented 2 years ago

Environment

OS : Linux
Python Version: 3.8.10

Question

How to adjust learning rate when I use Bi-LSTM model on classification task? 如何调整BiLSTM在分类任务上的学习率？

BrikerMan commented 2 years ago

You can use a custom optimizer by using https://kashgari.readthedocs.io/en/latest/tutorial/text-labeling/#use-custom-optimizer.

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.