Dontopedia

Iteration 100

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

Iteration 100 has 31 facts recorded in Dontopedia across 4 references, with 2 live disagreements.

31 facts·25 predicates·4 sources·2 in dispute

Mostly:iteration number(3), has learning rate(2), loss value(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (3)

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.

consistsOfConsists of(1)

hasHigherLossThanHas Higher Loss Than(1)

temporallyPrecedesTemporally Precedes(1)

Other facts (31)

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.

31 facts
PredicateValueRef
Iteration Number100[2]
Iteration Number100[3]
Iteration Number100[4]
Has Learning Rate0.00003[1]
Has Learning Rate0.00003[4]
Loss Valuenan[2]
Loss Value3.1939[3]
Learning Rate0.00003[2]
Learning Rate0.00003[3]
Rdf:typeIteration[3]
Rdf:typeIteration[4]
Belongs toTraining Run Linear Seq2048[1]
Has Gpu Cache Memory34.8GB[1]
Has Gpu Memory1.0GB[1]
Has Gpu Peak Memory34.3GB[1]
Has Iteration Number100[1]
Has Loss3.1939[1]
Has Process Memory3.2GB[1]
Has Tokens Per Second6763[1]
Tokens Per Second6763[3]
Gpu Memory Usage Gb1[3]
Gpu Memory Peak Gb34.3[3]
Gpu Cache Gb34.8[3]
Process Memory Gb3.2[3]
Part of RunTraining Run Grouped1[4]
Has Loss Value3.1608[4]
Has Token Throughput17618[4]
Gpu Memory Usage1[4]
Gpu Memory Peak12[4]
Gpu Cache Memory11.8[4]
Process Memory Usage3.2[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.

belongsToblah/watt-activation/part-114
ex:training-run-linear-seq2048
hasGpuCacheMemoryblah/watt-activation/part-114
34.8GB
hasGpuMemoryblah/watt-activation/part-114
1.0GB
hasGpuPeakMemoryblah/watt-activation/part-114
34.3GB
hasIterationNumberblah/watt-activation/part-114
100
hasLearningRateblah/watt-activation/part-114
0.00003
hasLossblah/watt-activation/part-114
3.1939
hasProcessMemoryblah/watt-activation/part-114
3.2GB
hasTokensPerSecondblah/watt-activation/part-114
6763
iterationNumberblah/watt-activation/111
100
lossValueblah/watt-activation/111
nan
learningRateblah/watt-activation/111
0.00003
typeblah/watt-activation/114
ex:Iteration
iterationNumberblah/watt-activation/114
100
lossValueblah/watt-activation/114
3.1939
learningRateblah/watt-activation/114
0.00003
tokensPerSecondblah/watt-activation/114
6763
gpuMemoryUsageGBblah/watt-activation/114
1
gpuMemoryPeakGBblah/watt-activation/114
34.3
gpuCacheGBblah/watt-activation/114
34.8
processMemoryGBblah/watt-activation/114
3.2
typeblah/watt-activation/115
ex:Iteration
iterationNumberblah/watt-activation/115
100
partOfRunblah/watt-activation/115
ex:training-run-grouped1
hasLossValueblah/watt-activation/115
3.1608
hasLearningRateblah/watt-activation/115
0.00003
hasTokenThroughputblah/watt-activation/115
17618
gpuMemoryUsageblah/watt-activation/115
1
gpuMemoryPeakblah/watt-activation/115
12
gpuCacheMemoryblah/watt-activation/115
11.8
processMemoryUsageblah/watt-activation/115
3.2

References (4)

4 references
  1. [1]Part 1149 facts
    ctx:discord/blah/watt-activation/part-114
  2. [2]1113 facts
    ctx:discord/blah/watt-activation/111
  3. [3]1149 facts
    ctx:discord/blah/watt-activation/114
    • full textwatt-activation-114
      text/plain2 KBdoc:agent/watt-activation-114/bc8b5ab5-bbc4-4aea-ac89-9211a96127c3
      Show excerpt
      [2026-03-08 22:42] xenonfun: Now add val evaluation in the training loop, after the checkpoint save block [2026-03-08 22:44] xenonfun: ``` === linear (seq=2048) === Training HarmonicGPT | attn=linear d=768 L=12 H=12 seq=2048 Parameters: 86,
  4. [4]11510 facts
    ctx:discord/blah/watt-activation/115
    • full textwatt-activation-115
      text/plain3 KBdoc:agent/watt-activation-115/105443fa-23c3-42fc-a3a6-065e0c10a484
      Show excerpt
      [2026-03-08 22:44] xenonfun: ``` === grouped1 (seq=2048) === Training HarmonicGPT | attn=grouped1 d=768 L=12 H=12 seq=2048 Parameters: 86,825,760 Loaded 5,000 train sequences of length 2048 iter 10/100 | loss 5.4746 | lr 3.00e-04 | tok/

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.