Dontopedia

Fd Training

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

Fd Training has 9 facts recorded in Dontopedia across 2 references.

9 facts·9 predicates·2 sources

Mostly:suffers from gamma divergence(1), requires lower lr(1), evaluates positively as stable(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.

causesDivergenceCauses Divergence(1)

Other facts (9)

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.

9 facts
PredicateValueRef
Suffers From Gamma Divergencetrue[1]
Requires Lower Lr1e-4[1]
Evaluates Positively As StableXenonfun[1]
Is Divergingtrue[1]
Ontological Dependency on IntegratorEuler Ode Integrator[1]
Precedes ImprovementImproved Training[1]
Presupposes We ContextTeam[1]
Rdf:typeTraining Process[2]
Exhibits BehaviorDivergence[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.

suffersFromGammaDivergenceblah/watt-activation/part-500
true
requiresLowerLrblah/watt-activation/part-500
1e-4
evaluatesPositivelyAsStableblah/watt-activation/part-500
ex:xenonfun
isDivergingblah/watt-activation/part-500
true
ontologicalDependencyOnIntegratorblah/watt-activation/part-500
ex:euler-ode-integrator
precedesImprovementblah/watt-activation/part-500
ex:improved-training
presupposesWeContextblah/watt-activation/part-500
ex:team
typeblah/watt-activation/497
ex:TrainingProcess
exhibitsBehaviorblah/watt-activation/497
ex:divergence

References (2)

2 references
  1. [1]Part 5007 facts
    ctx:discord/blah/watt-activation/part-500
  2. [2]4972 facts
    ctx:discord/blah/watt-activation/497
    • full textwatt-activation-497
      text/plain2 KBdoc:agent/watt-activation-497/e72fbd50-bc16-4a38-8957-fe8531b9864c
      Show excerpt
      [2026-03-22 17:52] xenonfun: if I am seeing this correct we are using 8 MB of memory. ⏺ The FD training is diverging — omega and gamma blowing up. The Euler ODE integrator is unstable at these parameter scales. This needs: 1. Much lower

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.