Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Dynamic training recipe reconfiguration

Adjusts the training recipe during training, including dataset mixture, per-dataset concurrency limits, and active teachers.

Also called dynamic reconfiguration during training.

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 continuously track model capabilities and may adjust the training recipe accordingly, including the dataset mixture, per-dataset concurrency limits, and active teachers.

usedpost trainingin DeepSeek-V4.1-FlashDeepSeek

Filed alongside

Other methods under post-training :: rollout & RL infrastructure.