Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Sean Michael McLeish, John Kirchenbauer, David Yu Miller, Siddharth Singh, Abhinav Bhatele, Micah Goldblum, Ashwinee Panda, Tom Goldstein

Keywords: neural scaling laws, large language models

TL;DR: We fit scaling laws for large language models with varying width-to-depth ratios and parameter counts.

Abstract:

Scaling laws are typically fit using a family of models with a narrow range of frozen hyperparameter choices.
In this work we study scaling laws using multiple architectural shapes and hyperparameter choices, highlighting their impact on resulting prescriptions.
As a primary artifact of our research, we release the Gemstones: an open-source scaling law dataset, consisting of over 4000 checkpoints from transformers with up to 2 billion parameters and diverse architectural shapes; including ablations over learning rate and cooldown.
Our checkpoints enable more complex studies of scaling, such as analyzing the relationship between width and depth.
By examining our model suite, we find that the prescriptions of scaling laws can be highly sensitive to the experimental design process and the specific model checkpoints used during fitting.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 5237