M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining
Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters. However, under limited resources, extreme-scale model training that requires enormous amounts of computes and memory footprint suffers from frustratingly low efficiency in model convergence. In this paper, we propose a simple training strategy called "Pseudo-to-Real" for high-memory-footprint-required large models. Pseudo-to-Real is compatible with large models with architecture of sequential layers. We demonstrate a practice of pretraining unprecedented 10-trillion-parameter model, an order of magnitude larger than the state-of-the-art, on solely 512 GPUs within 10 days. Besides demonstrating the application of Pseudo-to-Real, we also provide a technique, Granular CPU offloading, to manage CPU memory for training large model and maintain high GPU utilities. Fast training of extreme-scale models on a decent amount of resources can bring much smaller carbon footprint and contribute to greener AI.
Code (0)
등록된 구현이 없습니다.
Tasks
CPUGPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models
In this paper, we propose the 1 Trillion Token Platform (1TT Platform), a novel framework designed to facilitate efficient data sharing with a transparent and equitable profit-sharing mechanism. The platform fosters coll…
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Reinforcement learning with verifiable rewards without human-annotated data, often referred to as zero RL, has emerged as a powerful paradigm for eliciting chain-of-thought reasoning. However, due to computational constr…
Reinforcement LearningRecurrent Convolutional Neural Networks Learn Succinct Learning Algorithms
Neural networks (NNs) struggle to efficiently solve certain problems, such as learning parities, even when there are simple learning algorithms for those problems. Can NNs discover learning algorithms on their own? We ex…
Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation
We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under …
Computational EfficiencyMINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs). Despite the rapid progression of open-source LMMs, there rema…