SCALE matches Adam performance in LLM pretraining from 60M to 7B parameters by combining column-wise gradient normalization with last-layer-only momentum, using 35-45% of Adam's memory.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Memory-Efficient LLM Pretraining via Minimalist Optimizer Design
SCALE matches Adam performance in LLM pretraining from 60M to 7B parameters by combining column-wise gradient normalization with last-layer-only momentum, using 35-45% of Adam's memory.