Dontopedia

training tok/s

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

training tok/s has 7 facts recorded in Dontopedia across 4 references.

7 facts·6 predicates·4 sources

Mostly:prioritized(1), improvement at l1024(1), improvement at l2048(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (2)

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.

improvesImproves(2)

Other facts (6)

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.

6 facts
PredicateValueRef
Prioritizedtrue[1]
Improvement at L10240.17[2]
Improvement at L20480.15[2]
:measured Value10500[3]
:includes PhaseOptimizer[3]
Has Tokens Per Second Approximate5000[4]

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.

prioritizedblah/watt-activation/part-640
true
improvementAtL1024blah/watt-activation/76
0.17
improvementAtL2048blah/watt-activation/76
0.15
labelblah/watt-activation/454
training tok/s
measuredValueblah/watt-activation/454
10500
includesPhaseblah/watt-activation/454
ex:optimizer
hasTokensPerSecondApproximateblah/watt-activation/670
5000

References (4)

4 references
  1. [1]Part 6401 fact
    ctx:discord/blah/watt-activation/part-640
  2. [2]762 facts
    ctx:discord/blah/watt-activation/76
    • full textwatt-activation-76
      text/plain3 KBdoc:agent/watt-activation-76/961fc69a-4972-401d-be24-5f9157949baf
      Show excerpt
      [2026-03-07 18:31] xenonfun: ``` Excellent results. Full-sequence chunking (chunk_size=L) with the new formulation: ┌────────────────┬──────────────┬─────────────────────┬─────────────┬───────────┬────────┐ │ Config │ Old 5D to
  3. [3]4543 facts
    ctx:discord/blah/watt-activation/454
    • full textwatt-activation-454
      text/plain3 KBdoc:agent/watt-activation-454/4f6603bc-7db5-4694-932b-2c38bbe4bc5b
      Show excerpt
      [2026-03-21 06:17] xenonfun: Back to Rust ``` 1 - [project_vision.md](project_vision.md) — HarmonicRust replaces Python HarmonicMLX + Phase Hub with Rust 2 - [user_profile.md](user_profile.md) — User builds novel manifold-based ML architect
  4. [4]6701 fact
    ctx:discord/blah/watt-activation/670
    • full textwatt-activation-670
      text/plain3 KBdoc:agent/watt-activation-670/d9fd63e9-d1a4-4d2d-9849-fcaa1f434b61
      Show excerpt
      [2026-04-20 17:11] xenonfun: Important observations: 1. Neither feedback variant is catastrophically diverging at peak LR 3e-3. The model produces grammatically-shaped output; the damage is only at the vocabulary level, not structural.

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.