English
Related papers

Related papers: Adaptive Batch Size Schedules for Distributed Trai…

200 papers

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-10 Bowen Pang , Kai Li , Feifan Wang

Foundation models in speech are often trained using many GPUs, which implicitly leads to large effective batch sizes. In this paper we study the effect of batch size on pre-training, both in terms of statistics that can be monitored during…

Sound · Computer Science 2024-02-22 Nik Vaessen , David A. van Leeuwen

Multivariate time-series forecasting is vital in various domains, e.g., economic planning and weather prediction. Deep train-from-scratch models have exhibited effective performance yet require large amounts of data, which limits real-world…

Machine Learning · Computer Science 2025-02-21 Ching Chang , Wei-Yao Wang , Wen-Chih Peng , Tien-Fu Chen

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

Computation and Language · Computer Science 2022-07-11 Zejiang Hou , Julian Salazar , George Polovets

Pretraining large language models is a costly process. To make this process more efficient, several methods have been proposed to optimize model architecture/parametrization and hardware use. On the parametrization side, $\mu P$ (Maximal…

Machine Learning · Computer Science 2025-06-19 Soufiane Hayou , Liyuan Liu

Large language models (LLMs) are increasingly capable of completing knowledge intensive tasks by recalling information from a static pretraining corpus. Here we are concerned with LLMs in the context of evolving data requirements. For…

Machine Learning · Computer Science 2025-02-11 William Fleshman , Aleem Khan , Marc Marone , Benjamin Van Durme

In practice, the hyperparameters $(\beta_1, \beta_2)$ and weight-decay $\lambda$ in AdamW are typically kept at fixed values. Is there any reason to do otherwise? We show that for large-scale language model training, the answer is yes: by…

Machine Learning · Statistics 2026-02-19 Damien Ferbach , Courtney Paquette , Gauthier Gidel , Katie Everett , Elliot Paquette

Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series…

Machine Learning · Computer Science 2024-12-06 Harshavardhan Kamarthi , B. Aditya Prakash

We introduce Breadth-First Pipeline Parallelism, a novel training schedule which optimizes the combination of pipeline and data parallelism. Breadth-First Pipeline Parallelism lowers training time, cost and memory usage by combining a high…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-07-10 Joel Lamy-Poirier

Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…

Modern large language model (LLM) training is inherently dynamic: resource fluctuations, RLHF phase shifts, and cluster elasticity continually reshape the optimal parallelism layout, posing a significant challenge to existing training…

Machine Learning · Computer Science 2026-05-20 Yuanqing Wang , Yuchen Zhang , Hao Lin , Junhao Hu , Chunyang Zhu , Quanlu Zhang , Boxun Li , Guohao Dai , Zhi Yang , Daning Cheng , Yunquan Zhang , Yu Wang

We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curriculum learning…

Artificial Intelligence · Computer Science 2026-02-20 Sumedh Rasal

Generalized linear models (GLMs) are a widely utilized family of machine learning models in real-world applications. As data size increases, it is essential to perform efficient distributed training for these models. However, existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-11 Hongjing Huang , Yingtao Li , Jie Sun , Xueying Zhu , Jie Zhang , Liang Luo , Jialin Li , Zeke Wang

Breakthroughs in the generative AI domain have fueled an explosion of large language model (LLM)-powered applications, whose workloads fundamentally consist of sequences of inferences through transformer architectures. Within this rapidly…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-09 Burak Topcu , Musa Oguzhan Cim , Poovaiah Palangappa , Meena Arunachalam , Mahmut Taylan Kandemir

Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. In particular, batch packing is commonly used in pre-training and supervised fine-tuning…

Computation and Language · Computer Science 2026-03-02 Jaekyung Cho

Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an…

Computation and Language · Computer Science 2025-02-26 Fangyuan Yu

Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs…

Computation and Language · Computer Science 2024-06-07 Da Ma , Lu Chen , Pengyu Wang , Hongshen Xu , Hanqi Li , Liangtai Sun , Su Zhu , Shuai Fan , Kai Yu

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Computation and Language · Computer Science 2022-10-07 Mario Michael Krell , Matej Kosec , Sergio P. Perez , Andrew Fitzgibbon

Large language models have achieved remarkable success, but their extensive parameter size necessitates substantial memory for training, thereby setting a high threshold. While the recently proposed low-memory optimization (LOMO) reduces…

Machine Learning · Computer Science 2024-06-07 Kai Lv , Hang Yan , Qipeng Guo , Haijun Lv , Xipeng Qiu

Scaling laws with respect to the amount of training data and the number of parameters allow us to predict the cost-benefit trade-offs of pretraining language models (LMs) in different configurations. In this paper, we consider another…

Computation and Language · Computer Science 2024-07-19 Rulin Shao , Jacqueline He , Akari Asai , Weijia Shi , Tim Dettmers , Sewon Min , Luke Zettlemoyer , Pang Wei Koh