Skip to content

fix(ppo): use max seqlen for no-eos mask

cdc1c47
Select commit
Loading
Failed to load commit list.
Sign in for the full log view
Open

fix(ppo): exclude no-eos rows from reward normalization #1351

fix(ppo): use max seqlen for no-eos mask
cdc1c47
Select commit
Loading
Failed to load commit list.