SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training.
Tianjin Huang, Ziquan Zhu, Gaojie Jin, Lu Liu, Zhangyang Wang, Shiwei Liu
Browse the full ICLR paper archive.
Tianjin Huang, Ziquan Zhu, Gaojie Jin, Lu Liu, Zhangyang Wang, Shiwei Liu
Browse the full ICLR paper archive.