chuxin-llm

/

Scaling-Laws-for-Local-SGD-in-LLM-Intermediate-Checkpoints

like 0

Follow

chuxin 15

Hi,
I was wondering if you can share also the losses that each model recieved on your evaluations in addition to the weights.
Also, you wrote that you had intermediate checkpoints, but IIUC the repo only contains models of different sizes, not the checkpoints during their training (i.e. intermediate checkpoints).