specific method · filed under training objective
Unfinished-trajectory loss masking
Masks the loss on unfinished trajectories.
Also called mask the loss on unfinished trajectories.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
We mask the loss on unfinished trajectories
usedunclearin SWE teacher for Nemotron 3 UltraNVIDIA
Filed alongside
Other methods under training objective :: auxiliary loss.