2026
How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining
ICLR 2026oral
Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even after sophisticated data curation. A natural approach to better leverage high-quality data is curriculum-based pretraining, where the model is trained on dat…