5 papers
DataComp-LM: In search of the next generation of training sets for language models
Jeffrey Li, Alex Fang, Georgios Smyrnis +56
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
Tomer Porian, Mitchell Wortsman, Jenia Jitsev +2
Kaplan et al. and Hoffmann et al. developed influential scaling laws for the optimal model size as a function of the compute budget, but these laws yield substantially different pr…
Reproducible scaling laws for contrastive language-image learning
Mehdi Cherti, Romain Beaumont, Ross Wightman +6
Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set s…
Language models scale reliably with over-training and on downstream tasks
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar +22
Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps…
OLMo: Accelerating the Science of Language Models
Dirk Groeneveld, Iz Beltagy, Pete Walsh +40
Language models (LMs) have become ubiquitous in both NLP research and in commercial product offerings. As their commercial importance has surged, the most powerful models have beco…