Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Abstract

How do large language models (LLMs) develop and evolve over the course of training? How do these patterns change as models scale? To answer these questions, we introduce \textit{Pythia}, a suite of 16 LLMs all trained on public data seen in the exact same order and ranging in size from 70M to 12B parameters. We provide public access to 154 checkpoints for each one of the 16 models, alongside tools to download and reconstruct their exact training dataloaders for further study. We intend \textit{Pythia} to facilitate research in many areas, and we present several case studies including novel results in memorization, term frequency effects on few-shot performance, and reducing gender bias. We demonstrate that this highly controlled setup can be used to yield novel insights toward LLMs and their training dynamics. Trained models, analysis code, training code, and training data can be found at \url{https://github.com/EleutherAI/pythia}.

arXiv commentCode at https://github.com/EleutherAI/pythia

Cited by in corpus (8)

• Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain
• SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile
• Undesirable Biases in NLP: Addressing Challenges of Measurement
• LLMs as Models for Analogical Reasoning
• Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications
• Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction
• Vectorizing string entries for data processing on tables: when are larger language models better?
• Emergent inabilities? Inverse scaling over the course of pretraining