2 citations · 6 across the 8 of their papers we have counts for
3 papers · 1 filter
MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
Krishna Teja Chitty-Venkata, Sylvia Howland, Golara Azar +5
Mixture of Experts (MoE) models have enabled the scaling of Large Language Models (LLMs) and Vision Language Models (VLMs) by achieving massive parameter counts while maintaining c…
Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training
Shane Bergsma, Nolan Dey, Gurpreet Gosal +3
Efficient LLM pre-training requires well-tuned hyperparameters (HPs), including learning rate and weight decay . We study scaling laws for HPs: formulas for how to scale HPs…
Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs
Shane Bergsma, Nolan Dey, Gurpreet Gosal +3
LLMs are commonly trained with a learning rate (LR) warmup, followed by cosine decay to 10% of the maximum (10x decay). In a large-scale empirical study, we show that under an opti…