Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation

Mohammadreza Tayaranian Hosseini, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia


Abstract
The large number of parameters of some prominent language models, such as BERT, makes their fine-tuning on downstream tasks computationally intensive and energy hungry. Previously researchers were focused on lower bit-width integer data types for the forward propagation of language models to save memory and computation. As for the backward propagation, however, only 16-bit floating-point data type has been used for the fine-tuning of BERT.In this work, we use integer arithmetic for both forward and back propagation in the fine-tuning of BERT.We study the effects of varying the integer bit-width on the model’s metric performance. Our integer fine-tuning uses integer arithmetic to perform forward propagation and gradient computation of linear, layer-norm, and embedding layers of BERT.We fine-tune BERT using our integer training method on SQuAD v1.1 and SQuAD v2., and GLUE benchmark. We demonstrate that metric performance of fine-tuning 16-bit integer BERT matches both 16-bit and 32-bit floating-point baselines. Furthermore, using the faster and more memory efficient 8-bit integer data type, integer fine-tuning of BERT loses an average of 3.1 points compared to the FP32 baseline.
Anthology ID:
2023.findings-eacl.143
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1912–1921
Language:
URL:
https://aclanthology.org/2023.findings-eacl.143
DOI:
10.18653/v1/2023.findings-eacl.143
Bibkey:
Cite (ACL):
Mohammadreza Tayaranian Hosseini, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, and Vahid Partovi Nia. 2023. Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1912–1921, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation (Tayaranian Hosseini et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.143.pdf
Video:
 https://aclanthology.org/2023.findings-eacl.143.mp4