torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP

Abstract

Reproducibility in scientific work has been becoming increasingly important in research communities such as machine learning, natural language processing, and computer vision communities due to the rapid development of the research domains supported by recent advances in deep learning. In this work, we present a significantly upgraded version of torchdistill, a modular-driven coding-free deep learning framework significantly upgraded from the initial release, which supports only image classification and object detection tasks for reproducible knowledge distillation experiments. To demonstrate that the upgraded framework can support more tasks with third-party libraries, we reproduce the GLUE benchmark results of BERT models using a script based on the upgraded torchdistill, harmonizing with various Hugging Face libraries. All the 27 fine-tuned BERT models and configurations to reproduce the results are published at Hugging Face, and the model weights have already been widely used in research communities. We also reimplement popular small-sized models and new knowledge distillation methods and perform additional experiments for computer vision tasks.

Accepted at the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS) at EMNLP 2023

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• Sequence to Sequence Learning with Neural Networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Robust Speech Recognition via Large-Scale Weak Supervision
• Architectural Vision for Quantum Computing in the Edge-Cloud Continuum
• SC2 Benchmark: Supervised Compression for Split Computing
• Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages
• Understanding the Role of the Projector in Knowledge Distillation