Hierarchical Model Training
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Hierarchical Model Training has 2 facts recorded in Dontopedia across 1 reference.
2 facts·2 predicates·1 sources
Maturity scale
raw canonical shape-checked rule-derived certifiedOther facts (2)
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.
2 facts
| Predicate | Value | Ref |
|---|---|---|
| Uses Parameter | --hierarchical | [1] |
| Produces | Checkpoint | [1] |
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.
—
usesParameterblah/watt-activation/339
--hierarchical
—
producesblah/watt-activation/339
ex:checkpoint
References (1)
1 references
ctx:discord/blah/watt-activation/339- full textwatt-activation-339text/plain3 KB
doc:agent/watt-activation-339/b6cfe4ca-d9ef-43d5-a9f8-4c8cabbb54c7Show excerpt
[2026-03-15 19:42] xenonfun: ``` ⏺ 1010 B/s — that's garbage text (only 50 steps of training) but the speed is the point. Compare: ┌────────────────────────────────┬───────────┐ │ Mode │ Speed │ ├───────…
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.