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.
Mostly:layer learning rate ratio(4), optimizes layer wise(1), has best params(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound 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)
- Configs Json
ex:configs-json
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.
| Predicate | Value | Ref |
|---|---|---|
| Layer Learning Rate Ratio | 0.776 | [2] |
| Layer Learning Rate Ratio | 0.868 | [2] |
| Layer Learning Rate Ratio | 1.012 | [2] |
| Layer Learning Rate Ratio | 0.982 | [2] |
| Optimizes Layer Wise | true | [1] |
| Has Best Params | 29737 | [1] |
| Has Decay Type | constant | [1] |
| Has Higher Test Accuracy Than | Uniform Lr Config | [1] |
| Has Higher Train Accuracy Than | Uniform Lr Config | [1] |
| Has Layer Lr Ratio0 | 0.776 | [1] |
| Has Layer Lr Ratio1 | 0.868 | [1] |
| Has Layer Lr Ratio2 | 1.012 | [1] |
| Has Layer Lr Ratio3 | 0.982 | [1] |
| Has Lower Time Seconds Than | Uniform Lr Config | [1] |
| Has Peak Lr | 0.00849194980322411 | [1] |
| Has Test Accuracy | 0.9700000286102296 | [1] |
| Has Time Seconds | 382.6 | [1] |
| Has Train Accuracy | 0.9983999729156494 | [1] |
| Shows Superior Performance | Uniform Lr Config | [1] |
| Train Accuracy | 0.9983999729156494 | [2] |
| Test Accuracy | 0.9700000286102296 | [2] |
| Best Parameter Count | 29737 | [2] |
| Peak Learning Rate | 0.00849194980322411 | [2] |
| Learning Rate Decay Type | constant | [2] |
| Training Time Seconds | 382.6 | [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.
References (2)
ctx:discord/blah/watt-activation/part-4ctx:discord/blah/watt-activation/4- full textwatt-activation-4text/plain2 KB
doc:agent/watt-activation-4/8c0466cd-286e-4f72-b49b-ee4fe3ce7e29Show 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.