← Search

Amrit Nagarajan

1 accepted papers

2023

TokenDrop + BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models

EMNLP 2023long findings

The great success of Language Models (LMs) for various Natural Language Processing (NLP) tasks is accompanied by computational challenges during both pre-training and fine-tuning. Pre-training has attracted significant attention due to its huge computational footprint. We focus on the fine-tuning of…

Cited by 0SourcecodeScholar