implementation detail · filed under optimization
Fixed elevated learning rate
Holding the learning rate constant above its optimal value while bypassing the standard decay schedule.
- 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 hold the learning rate constant at a multiple of its optimal value, bypassing the standard decay schedule to simulate the prolonged peak learning rate of a production run
usedevaluation onlyin Qwen3.8-Flash-NextQwen
Filed alongside
Other methods under optimization :: learning-rate schedule.
Cosine decayWarmup-Stable-DecayBatch-size warmupTraining without batch-size warmupBatch-size warmup with adjusted peak learning rateBatch-size warmup with constant-batch optimum peak learning rateEngram learning-rate scalingLearning-rate annealingLinear warmup followed by cosine decayScaling-law fitScheduled batch-size growthWSD-specific scaling law