22 citations · 25 across the 6 of their papers we have counts for
9 papers · 1 filter
Soup to go: mitigating forgetting during continual learning with model averaging
Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle +2
In continual learning, where task data arrives in a sequence, fine-tuning on later tasks will often lead to performance degradation on earlier tasks. This is especially pronounced…
Scaling Laws for Precision
Tanishq Kumar, Zachary Ankner, Benjamin F. Spector +6
Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise "precision-aware…
Critique-out-Loud Reward Models
Zachary Ankner, Mansheej Paul, Brandon Cui +2
Traditionally, reward models used for reinforcement learning from human feedback (RLHF) are trained to directly predict preference scores without leveraging the generation capabili…
Does your data spark joy? Performance gains from domain upsampling at the end of training
Cody Blakeney, Mansheej Paul, Brett W. Larsen +2
Pretraining datasets for large language models (LLMs) have grown to trillions of tokens composed of large amounts of CommonCrawl (CC) web scrape along with smaller, domain-specific…
Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
Zachary Ankner, Cody Blakeney, Kartik Sreenivasan +3
In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. W…
LoRA Learns Less and Forgets Less
Dan Biderman, Jacob Portes, Jose Javier Gonzalez Ortiz +9
Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for large language models. LoRA saves memory by training only low rank perturbations to selected w…