Dontopedia

Kan Iter 70

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

Kan Iter 70 has 19 facts recorded in Dontopedia across 2 references.

19 facts·16 predicates·2 sources

Mostly:has learning rate(2), has loss(2), has tokens per second(2)

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.

temporallyPrecedesTemporally Precedes(1)

Other facts (19)

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.

19 facts
PredicateValueRef
Has Learning Rate0.0000975[1]
Has Learning Rate0.0000975[2]
Has Loss2.8611[1]
Has Loss2.8611[2]
Has Tokens Per Second14816[1]
Has Tokens Per Second14816[2]
Has Gpu Active Gb1[1]
Has Gpu Cache Gb14[1]
Has Gpu Peak Gb14[1]
Has Process Rssgb3.2[1]
Is Part ofKan Run[1]
Temporally PrecedesKan Iter 80[1]
Rdf:typeIteration[2]
Iteration Number70[2]
Part ofKan Run[2]
Has Gpu Memory Active1.0GB[2]
Has Gpu Memory Peak14.0GB[2]
Has Gpu Memory Cache14.0GB[2]
Has Process Memory3.2GB[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.

hasGpuActiveGBblah/watt-activation/part-112
1
hasGpuCacheGBblah/watt-activation/part-112
14
hasGpuPeakGBblah/watt-activation/part-112
14
hasLearningRateblah/watt-activation/part-112
0.0000975
hasLossblah/watt-activation/part-112
2.8611
hasProcessRSSGBblah/watt-activation/part-112
3.2
hasTokensPerSecondblah/watt-activation/part-112
14816
isPartOfblah/watt-activation/part-112
ex:kan-run
temporallyPrecedesblah/watt-activation/part-112
ex:kan-iter-80
typeblah/watt-activation/112
ex:Iteration
iterationNumberblah/watt-activation/112
70
partOfblah/watt-activation/112
ex:kan-run
hasLossblah/watt-activation/112
2.8611
hasLearningRateblah/watt-activation/112
0.0000975
hasTokensPerSecondblah/watt-activation/112
14816
hasGpuMemoryActiveblah/watt-activation/112
1.0GB
hasGpuMemoryPeakblah/watt-activation/112
14.0GB
hasGpuMemoryCacheblah/watt-activation/112
14.0GB
hasProcessMemoryblah/watt-activation/112
3.2GB

References (2)

2 references
  1. [1]Part 1129 facts
    ctx:discord/blah/watt-activation/part-112
  2. [2]11210 facts
    ctx:discord/blah/watt-activation/112
    • full textwatt-activation-112
      text/plain3 KBdoc:agent/watt-activation-112/dad4c21d-6073-4542-b09b-5b5162617d30
      Show excerpt
      [2026-03-08 22:40] xenonfun: ``` === kan (seq=2048) === Training HarmonicGPT | attn=kan d=768 L=12 H=12 seq=2048 Parameters: 86,826,048 Loaded 5,000 sequences of length 2048 iter 10/100 | loss 5.4382 | lr 3.00e-04 | tok/s 14,738 | gpu 1

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.