News for hackers. Stuff that matters.
Re:OLMo: Accelerating the Science of Language Models [pdf] by bravura on Thursday February 01, 2024 @10:40PM (#39224725)
"We intend to follow up on this release with another one soon that includes the following:

...

Weights & Biases logs for our training runs."

That's amazing. I've never seen that before in a paper of this quality. Or, any paper at all.

Re:OLMo: Accelerating the Science of Language Models [pdf] by swyx on Friday February 02, 2024 @06:04AM (#39227341)
i think huggingface and facebook have both offered this level of detail in the past? still great though
Re:OLMo: Accelerating the Science of Language Models [pdf] by arugulum on Friday February 02, 2024 @10:00AM (#39229295)
EleutherAI as well.
Re:OLMo: Accelerating the Science of Language Models [pdf] by gillesjacobs on Friday February 02, 2024 @02:25PM (#39233007)
It's more common than you think. I did the same for one of my research papers.
Re:OLMo: Accelerating the Science of Language Models [pdf] by marvinalone on Monday February 05, 2024 @03:30PM (#39266706)
Weights & Biases for OLMo 7B are now out: https://wandb.ai/ai2-llm/OLMo-7B/reports/OLMo-7B--Vmlldzo2Nz...