Saved in:
Bibliographic Details
Main Authors: Yano, Kazuki, Ito, Takumi, Suzuki, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.04151
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Pre-training large language models (LLMs) faces significant memory challenges due to the large size of model parameters. We introduce STaged parameter-Efficient Pre-training (STEP), which integrates parameter-efficient tuning techniques with model growth. We conduct experiments on pre-training LLMs of various sizes and demonstrate that STEP achieves up to a 53.9% reduction in maximum memory requirements compared to vanilla pre-training while maintaining equivalent performance. Furthermore, we show that the model by STEP performs comparably to vanilla pre-trained models on downstream tasks after instruction tuning.