Megadose AI progress, ranked and analyzed.

Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference

· HF Daily Papers ·
Layer dropout cut training compute by up to 25% and later enabled up to 1.5x faster inference in the authors’ LLM experiments.

The paper argues that layer dropout should return to modern LLM pre-training recipes when its distribution, schedule, and optimizer settings are tuned. Across more than 2,400 experiments, the authors report lower loss at the same training FLOPs, or similar-to-lower validation loss for the same step count with less compute. They also found post-training gains from early exit, intermediate-layer skipping, and self-speculative decoding, with negligible accuracy loss. The study spans models from 271M to 8.2B parameters and datasets up to 160B tokens. HF Daily Papers' note

score 5

Categories: Research