Model techniques map
Techniquestraining objectiveauxiliary loss

implementation detail · filed under training objective

Sequence-level balance loss

Uses a small balance loss to avoid extreme imbalance within individual sequences.

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.

while retaining a small sequence-level balance loss with a loss weight of 0.0001 to avoid extreme imbalance within single sequences.

usedunclearin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

Other methods under training objective :: auxiliary loss.