Papers
arxiv:2304.03208

Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster

Published on Apr 6, 2023
Authors:
,
,
,
,
,
,
,
,

Abstract

We study recent research advances that improve large language models through efficient pre-training and scaling, and open datasets and tools. We combine these advances to introduce Cerebras-GPT, a family of open compute-optimal language models scaled from 111M to 13B parameters. We train Cerebras-GPT models on the Eleuther Pile dataset following DeepMind Chinchilla scaling rules for efficient pre-training (highest accuracy for a given compute budget). We characterize the predictable power-law scaling and compare Cerebras-GPT with other publicly-available models to show all Cerebras-GPT models have state-of-the-art training efficiency on both pre-training and downstream objectives. We describe our learnings including how Maximal Update Parameterization (muP) can further improve large model scaling, improving accuracy and hyperparameter predictability at scale. We release our pre-trained models and code, making this paper the first open and reproducible work comparing compute-optimal model scaling to models trained on fixed dataset sizes. Cerebras-GPT models are available on HuggingFace: https://huggingface.co/cerebras.

Community

Sign up or log in to comment

Models citing this paper 13

Browse 13 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2304.03208 in a dataset README.md to link it from this page.

Spaces citing this paper 53

Collections including this paper 1