Skip to main content
ai2-llm
Projects
olmoe
Reports
Plot: Zloss vs none

Plot: Zloss vs none

Niklas Muennighoff
Created on June 24|Last edited on August 29

100k200k300k400kStep34567
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-scratch Run set
100k200k300k400kStep46810
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-zloss-scratch Run set
olmoe17-8x1b-fullshard-swiglu-wrapb-k2-scratch Run set
Run set
8
Run set 2


Created with ❤️ on Weights & Biases.

https://wandb.ai/ai2-llm/olmoe/reports/Plot-Zloss-vs-none--Vmlldzo4NDM4NjUz
Made with Weights & Biases. Sign up or log in to create reports like this one.