Training Compute-Optimal Large Language Models
Given a fixed compute budget, double the model and double the data — in equal proportion.
Hoffmann et al. · NeurIPS 2022 · Foundations. Read the paper ↗
A free, interactive, animated visual explainer of Training Compute-Optimal Large Language Models — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is Training Compute-Optimal Large Language Models?
- Given a fixed compute budget, double the model and double the data — in equal proportion.
- Who published Training Compute-Optimal Large Language Models, and where?
- Hoffmann et al. — NeurIPS 2022 (arXiv:2203.15556).
- Where can I find a visual explainer of Training Compute-Optimal Large Language Models?
- Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.
Related explainers
- Attention Is All You Need
- GPT-3: Language Models are Few-Shot Learners
- Mixtral of Experts
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- BERT: Pre-training of Deep Bidirectional Transformers
- Scaling Laws for Neural Language Models
- Adam: A Method for Stochastic Optimization
- Deep Residual Learning for Image Recognition