David Hall (@dlwh) 's Twitter Profile
David Hall

@dlwh

Research Engineering Lead at @StanfordCRFM . Previously co-founder at Semantic Machines ⟶ MSFT. Lead developer of Levanter, Breeze. he/him @[email protected]

ID: 8630302

linkhttps://www.linkedin.com/in/dlwhall calendar_today03-09-2007 20:14:30

1,1K Tweet

2,2K Takipçi

1,1K Takip Edilen

David Hall (@dlwh) 's Twitter Profile Photo
David Hall
@dlwh

a month ago

So about a month ago, Percy posted a version of this plot of our Marin 32B pretraining run. We got a lot of feedback, both public and private, that the spikes were bad. (This is a thread about how we fixed the spikes. Bear with me. )

So about a month ago, Percy posted a version of this plot of our Marin 32B pretraining run. We got a lot of feedback, both public and private, that the spikes were bad. (This is a thread about how we fixed the spikes. Bear with me. )