Towards Accurate and Reliable Energy Measurement of NLP Models

Qingqing Cao, Aruna Balasubramanian, Niranjan Balasubramanian


Abstract
Accurate and reliable measurement of energy consumption is critical for making well-informed design choices when choosing and training large scale NLP models. In this work, we show that existing software-based energy estimations are not accurate because they do not take into account hardware differences and how resource utilization affects energy consumption. We conduct energy measurement experiments with four different models for a question answering task. We quantify the error of existing software-based energy estimations by using a hardware power meter that provides highly accurate energy measurements. Our key takeaway is the need for a more accurate energy estimation model that takes into account hardware variabilities and the non-linear relationship between resource utilization and energy consumption. We release the code and data at https://github.com/csarron/sustainlp2020-energy.
Anthology ID:
2020.sustainlp-1.19
Volume:
Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | sustainlp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
141–148
Language:
URL:
https://aclanthology.org/2020.sustainlp-1.19
DOI:
10.18653/v1/2020.sustainlp-1.19
Bibkey:
Cite (ACL):
Qingqing Cao, Aruna Balasubramanian, and Niranjan Balasubramanian. 2020. Towards Accurate and Reliable Energy Measurement of NLP Models. In Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing, pages 141–148, Online. Association for Computational Linguistics.
Cite (Informal):
Towards Accurate and Reliable Energy Measurement of NLP Models (Cao et al., sustainlp 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.sustainlp-1.19.pdf
Video:
 https://slideslive.com/38939441
Code
 csarron/sustainlp2020-energy
Data
SQuAD