Marek, M., Lotfi, S., Somasundaram, A., Wilson, A. G., & Goldblum, M. (2025). Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful.
Chicago-Zitierstil (17. Ausg.)Marek, Martin, Sanae Lotfi, Aditya Somasundaram, Andrew Gordon Wilson, und Micah Goldblum. Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful. 2025.
MLA-Zitierstil (9. Ausg.)Marek, Martin, et al. Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful. 2025.
Achtung: Diese Zitate sind unter Umständen nicht zu 100% korrekt.