English
Related papers

Related papers: Power Scheduler: A Batch Size and Token Number Agn…

200 papers

Recent work has identified simple empirical scaling laws for language models, linking compute budget, dataset size, model size, and autoregressive modeling loss. The validity of these simple power laws across orders of magnitude in model…

Machine Learning · Statistics 2021-09-27 Amélie Chatelain , Amine Djeghri , Daniel Hesslow , Julien Launay , Iacopo Poli

Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets…

Machine Learning · Computer Science 2024-11-22 Josh Gardner , Juan C. Perdomo , Ludwig Schmidt

Contextual embedding-based language models trained on large data sets, such as BERT and RoBERTa, provide strong performance across a wide range of tasks and are ubiquitous in modern NLP. It has been observed that fine-tuning these models on…

Computation and Language · Computer Science 2021-09-16 Vin Sachidananda , Jason S. Kessler , Yi-an Lai

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

Machine Learning · Computer Science 2025-02-17 Hikaru Umeda , Hideaki Iiduka

In this paper, we address the challenge of optimizing training setups for Large Language Models (LLMs) of low-resource language with a limited amount of corpus. Existing works adopt multi-epoch, multi-lingual, and two-stage training to…

Computation and Language · Computer Science 2024-10-17 Kosuke Akimoto , Masafumi Oyamada

Recent research has highlighted the importance of dataset size in scaling language models. However, large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its…

Machine Learning · Computer Science 2023-10-10 Fuzhao Xue , Yao Fu , Wangchunshu Zhou , Zangwei Zheng , Yang You

Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large language models (LLMs). This is done either by fitting a scaling law to the hyperparameters…

Machine Learning · Computer Science 2026-05-21 Dayal Singh Kalra , Maissam Barkeshli

The Transformer model has revolutionized Natural Language Processing tasks such as Neural Machine Translation, and many efforts have been made to study the Transformer architecture, which increased its efficiency and accuracy. One potential…

Computation and Language · Computer Science 2023-08-17 Daniela N. Rim , Kimera Richard , Heeyoul Choi

While developments in machine learning led to impressive performance gains on big data, many human subjects data are, in actuality, small and sparsely labeled. Existing methods applied to such data often do not easily generalize to…

Machine Learning · Computer Science 2023-04-04 Julie Jiang , Kristina Lerman , Emilio Ferrara

The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods. In this white paper, we addressed the challenge of efficiently…

Machine Learning · Computer Science 2024-04-29 Raphael Ruschel , A. S. M. Iftekhar , B. S. Manjunath , Suya You

A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of current meta-learning methods assume that the meta-training…

Machine Learning · Computer Science 2019-04-12 Minseop Park , Jungtaek Kim , Saehoon Kim , Yanbin Liu , Seungjin Choi

The prohibitive training costs of Large Language Models (LLMs) have emerged as a significant bottleneck in the development of next-generation LLMs. In this paper, we show that it is possible to significantly reduce the training costs of…

Computation and Language · Computer Science 2025-05-16 Chenze Shao , Fandong Meng , Jie Zhou

We explore the impact of pre-training data composition on the performance of small language models in a sample-efficient setting. Using datasets limited to 10 million words, we evaluate several dataset sources, including child-directed…

Computation and Language · Computer Science 2024-11-12 Hong Meng Yam , Nathan J Paek

Scaling laws for large language models depend critically on the optimizer and parameterization. Existing hyperparameter transfer laws are mainly developed for first-order optimizers, and they do not structurally prevent training instability…

Machine Learning · Computer Science 2026-04-07 Liliang Ren , Yang Liu , Yelong Shen , Weizhu Chen

We introduce a method for improving the structural understanding abilities of language models. Unlike previous approaches that finetune the models with task-specific augmentation, we pretrain language models on a collection of task-agnostic…

Computation and Language · Computer Science 2023-03-07 Chenguang Wang , Xiao Liu , Zui Chen , Haoyun Hong , Jie Tang , Dawn Song

In this work, we seek to understand the performance of large language models in the mechanical engineering domain. We leverage the semantic data found in the ABC dataset, specifically the assembly names that designers assigned to the…

Computation and Language · Computer Science 2025-05-06 Daniele Grandi , Fabian Riquelme

Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning. However, most language models allocate the same amount of parameters or computation to each token, disregarding the…

Computation and Language · Computer Science 2023-11-28 Dewen Zeng , Nan Du , Tao Wang , Yuanzhong Xu , Tao Lei , Zhifeng Chen , Claire Cui

In most practical settings and theoretical analyses, one assumes that a model can be trained until convergence. However, the growing complexity of machine learning datasets and models may violate such assumptions. Indeed, current approaches…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Mengtian Li , Ersin Yumer , Deva Ramanan

Language model pretraining involves training on extensive corpora, where data quality plays a pivotal role. In this work, we aim to directly estimate the contribution of data during pretraining and select pretraining data in an efficient…

Computation and Language · Computer Science 2025-08-05 Kashun Shum , Yuzhen Huang , Hongjian Zou , Qi Ding , Yixuan Liao , Xiaoxin Chen , Qian Liu , Junxian He

Large language models can solve new tasks without task-specific fine-tuning. This ability, also known as in-context learning (ICL), is considered an emergent ability and is primarily seen in large language models with billions of…

Computation and Language · Computer Science 2024-04-04 Sherin Muckatira , Vijeta Deshpande , Vladislav Lialin , Anna Rumshisky