Commit History

Add model card with training details
240e2b5
verified

thomasjhuang commited on

RLOO checkpoint at optimizer step 350 - Fixed prompt format, temp=0.1, lr=3e-6
ca96d28
verified

thomasjhuang commited on

RLOO checkpoint at optimizer step 350 - Fixed prompt format, temp=0.1, lr=3e-6
d679490
verified

thomasjhuang commited on

initial commit
a61a5b8
verified

thomasjhuang commited on