The running speed of LSTM model from MindSpore is extremely slow.

mindspore-lab / mindnlp

Easy-to-use and high-performance NLP and LLM framework based on MindSpore, compatible with models and datasets of 🤗Huggingface.

https://mindnlp.cqu.ai/

Apache License 2.0

699 stars 197 forks source link

The running speed of LSTM model from MindSpore is extremely slow. #186

Closed TTYee closed 1 year ago

TTYee commented 1 year ago

When using the squad dataset and bidaf model to train the QA task (question_answer.py), the training progress always maintains at 0% because of the slow speed of nn.LSTM.

lvyufeng commented 1 year ago

use mindnlp.modules.StaticGRU and mindnlp.modules.StaticLSTM