Model techniques map
Techniquespost-trainingsupervised fine-tuning

implementation detail · filed under post-training

Evaluation-based early stopping

An SFT training implementation detail that stops training based on evaluation scores.

Also called evaluation-based early stopping during SFT, early stopping based on evaluation scores.

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 run for three epochs of 40B tokens each, with early stopping based on evaluation scores.

usedoptimizationin Laguna XS.2Poolside

Filed alongside

Other methods under post-training :: supervised fine-tuning.