implementation detail · filed under optimization
WSD-specific scaling law
A scaling law fitted specifically for the Warmup-Stable-Decay schedule.
Also called WSD learning-rate scaling law.
- 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 therefore fit a WSD-specific scaling law by sweeping four MoE sizes
usedoptimizationin Laguna XS.2Poolside
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 scalingFixed elevated learning rateLearning-rate annealingLinear warmup followed by cosine decayScaling-law fitScheduled batch-size growth