Dontopedia

per_layer_lr

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)

per_layer_lr has 26 facts recorded in Dontopedia across 2 references, with 1 live disagreement.

26 facts·22 predicates·2 sources·1 in dispute

Mostly:layer learning rate ratio(4), optimizes layer wise(1), has best params(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (1)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

hasConfigHas Config(1)

Other facts (25)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

25 facts
PredicateValueRef
Layer Learning Rate Ratio0.776[2]
Layer Learning Rate Ratio0.868[2]
Layer Learning Rate Ratio1.012[2]
Layer Learning Rate Ratio0.982[2]
Optimizes Layer Wisetrue[1]
Has Best Params29737[1]
Has Decay Typeconstant[1]
Has Higher Test Accuracy ThanUniform Lr Config[1]
Has Higher Train Accuracy ThanUniform Lr Config[1]
Has Layer Lr Ratio00.776[1]
Has Layer Lr Ratio10.868[1]
Has Layer Lr Ratio21.012[1]
Has Layer Lr Ratio30.982[1]
Has Lower Time Seconds ThanUniform Lr Config[1]
Has Peak Lr0.00849194980322411[1]
Has Test Accuracy0.9700000286102296[1]
Has Time Seconds382.6[1]
Has Train Accuracy0.9983999729156494[1]
Shows Superior PerformanceUniform Lr Config[1]
Train Accuracy0.9983999729156494[2]
Test Accuracy0.9700000286102296[2]
Best Parameter Count29737[2]
Peak Learning Rate0.00849194980322411[2]
Learning Rate Decay Typeconstant[2]
Training Time Seconds382.6[2]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

optimizesLayerWiseblah/watt-activation/part-4
true
hasBestParamsblah/watt-activation/part-4
29737
hasDecayTypeblah/watt-activation/part-4
constant
hasHigherTestAccuracyThanblah/watt-activation/part-4
ex:uniform-lr-config
hasHigherTrainAccuracyThanblah/watt-activation/part-4
ex:uniform-lr-config
hasLayerLrRatio0blah/watt-activation/part-4
0.776
hasLayerLrRatio1blah/watt-activation/part-4
0.868
hasLayerLrRatio2blah/watt-activation/part-4
1.012
hasLayerLrRatio3blah/watt-activation/part-4
0.982
hasLowerTimeSecondsThanblah/watt-activation/part-4
ex:uniform-lr-config
hasPeakLrblah/watt-activation/part-4
0.00849194980322411
hasTestAccuracyblah/watt-activation/part-4
0.9700000286102296
hasTimeSecondsblah/watt-activation/part-4
382.6
hasTrainAccuracyblah/watt-activation/part-4
0.9983999729156494
showsSuperiorPerformanceblah/watt-activation/part-4
ex:uniform-lr-config
labelblah/watt-activation/4
per_layer_lr
trainAccuracyblah/watt-activation/4
0.9983999729156494
testAccuracyblah/watt-activation/4
0.9700000286102296
bestParameterCountblah/watt-activation/4
29737
peakLearningRateblah/watt-activation/4
0.00849194980322411
learningRateDecayTypeblah/watt-activation/4
constant
layerLearningRateRatioblah/watt-activation/4
0.776
layerLearningRateRatioblah/watt-activation/4
0.868
layerLearningRateRatioblah/watt-activation/4
1.012
layerLearningRateRatioblah/watt-activation/4
0.982
trainingTimeSecondsblah/watt-activation/4
382.6

References (2)

2 references
  1. [1]Part 415 facts
    ctx:discord/blah/watt-activation/part-4
  2. [2]411 facts
    ctx:discord/blah/watt-activation/4
    • full textwatt-activation-4
      text/plain2 KBdoc:agent/watt-activation-4/8c0466cd-286e-4f72-b49b-ee4fe3ce7e29
      Show excerpt
      [2026-02-26 04:18] xenonfun: ``` { "tasks": { "MNIST (5k/1k)": { "no_skip": { "train_accuracy": 0.996399998664856, "test_accuracy": 0.9649999737739563, "best_params": 15231, "skip_info": {},

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.