Training Compute-Optimal Large Language Models
Hoffmann et al., 2022, Training Compute-Optimal Large Language Models (Advances in Neural Information Processing Systems 35 (NeurIPS 2022))
Subscriber deck — free during early access
1 cards in “3.1 Approach 1: Fix model sizes and vary number of training tokens” · whole deck
3.1 Approach 1: Fix model sizes and vary number of training tokens
- Describe Approach 1 for estimating compute-optimal scaling.Train each model size with 4 different schedule lengths, take the envelope of minimal loss per FLOP across all runs, read off the best \(N\) and \(D\) for each FLOP count, and fit power laws \(N_{\text{opt}} \propto C^a\), \(D_{\text{opt}} \propto C^b\): \(a = 0.50\), \(b = 0.50\).
- Hoffmann et al., 2022, Training Compute-Optimal Large Language Models (Advances in Neural Information Processing Systems 35 (NeurIPS 2022)), §3.1
Source
- Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, Tom Hennigan, Eric Noland, Katie Millican, George van den Driessche, Bogdan Damoc, Aurelia Guy, Simon Osindero, Karen Simonyan, Erich Elsen, Oriol Vinyals, Jack W. Rae and Laurent Sifre. 2022. Training Compute-Optimal Large Language Models. In Advances in Neural Information Processing Systems 35 (NeurIPS 2022). https://papers.nips.cc/paper_files/paper/2022/hash/c1e2faff6f588870935f114ebe04a3e5-Abstract-Conference.html