Dontopedia

Training PPL

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

Training PPL has 5 facts recorded in Dontopedia across 2 references.

5 facts·4 predicates·2 sources

Mostly:is optimistic(1), rdf:type(1), differentiated from(1)

Maturity scale raw canonical shape-checked rule-derived certified

Other facts (4)

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.

4 facts
PredicateValueRef
Is OptimisticTest Ppl[1]
Rdf:typeMetric[2]
Differentiated FromTest Ppl[2]
Characteristic ofoptimistic[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.

5 undated
—
isOptimisticblah/watt-activation/part-92
ex:test-ppl
—
typeblah/watt-activation/92
ex:Metric
—
labelblah/watt-activation/92
Training PPL
—
differentiatedFromblah/watt-activation/92
ex:test-ppl
—
characteristicOfblah/watt-activation/92
optimistic

References (2)

2 references
  1. [1]Part 921 fact
    ctx:discord/blah/watt-activation/part-92
  2. [2]924 facts
    ctx:discord/blah/watt-activation/92
    • full textwatt-activation-92
      text/plain3 KBdoc:agent/watt-activation-92/a597b55a-3d12-478b-951d-f09c655a8870
      Show excerpt
      [2026-03-08 01:46] xenonfun: ``` Direct comparison is tricky but here are the reference points: GPT-2 Small (124M) published benchmarks: - WikiText-103 test: 29.4 PPL - Penn Treebank: 65.9 PPL - Trained on ~8-9B tokens of WebText …

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.

↑