paper-with-me

홈 › Papers

Dynamic Masking Rate Schedules for MLM Pretraining

2023-05-24 · Zachary Ankner, Naomi Saphra, Davis Blalock, Jonathan Frankle, Matthew L. Leavitt

Most works on transformers trained with the Masked Language Modeling (MLM) objective use the original BERT model's fixed masking rate of 15%. We propose to instead dynamically schedule the masking rate throughout training. We find that linearly decreasing the masking rate over the course of pretraining improves average GLUE accuracy by up to 0.46% and 0.25% in BERT-base and BERT-large, respectively, compared to fixed rate baselines. These gains come from exposure to both high and low masking rate regimes, providing benefits from both settings. Our results demonstrate that masking rate scheduling is a simple way to improve the quality of masked language models, achieving up to a 1.89x speedup in pretraining for BERT-base as well as a Pareto improvement for BERT-large.

📄 PDF Abstract BibTeX arXiv:2305.15096

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMasked Language ModelingScheduling

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
WordPiece 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules

2025-03-17 · Kairong Luo, Haodong Wen, Shengding Hu, Zhenbo Sun 외

Training large models is both resource-intensive and time-consuming, making it crucial to understand the quantitative relationship between model performance and hyperparameters. In this paper, we present an empirical law…

Learning Versatile Skills with Curriculum Masking

2024-10-23 · Yao Tang, Zhihui Xie, Zichuan Lin, Deheng Ye 외

Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified mo…

Decision MakingOffline RLReinforcement Learning (RL)Sequential Decision Making

Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging

2026-02-03 · Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan 외 arxiv

Large language models are increasingly trained in continual or open-ended settings, where the total training horizon is not known in advance. Despite this, most existing pretraining recipes are not anytime: they rely on …

The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity

2026-08-13 · Martin J. Wainwright arxiv

We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its local increments directly control Kullbac…

Difference-Masking: Choosing What to Mask in Continued Pretraining

2023-05-23 · Alex Wilf, Syeda Nahida Akter, Leena Mathur, Paul Pu Liang 외

The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition that decidin…

Self-Supervised Learning