Dontopedia

super_chat_20260225140824_ee4k

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

super_chat_20260225140824_ee4k has 18 facts recorded in Dontopedia across 1 reference.

18 facts·17 predicates·1 sources

Mostly:status(1), run on gpu(1), model parameter count(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.

partOfPart of(1)

Other facts (17)

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.

17 facts
PredicateValueRef
StatusLaunched[1]
Run on GpuNvidia L4 24gb[1]
Model Parameter Count17400000[1]
Model Dimension384[1]
Attention Heads8[1]
Layer Count8[1]
Block Size512[1]
Training Batch Size12[1]
Learning Rate0.00005[1]
Warmup Steps1000[1]
Grad Clip Value1[1]
Beta2 Value0.95[1]
Uses Data FileSuper Chat Txt[1]
Streams Metrics toDashboard[1]
Dashboard UrlTraining[1]
First CandidateG Alpha[1]
Tokens Per Second7400[1]

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.

statusblah/training-and-evals/22
ex:launched
labelblah/training-and-evals/22
super_chat_20260225140824_ee4k
runOnGpublah/training-and-evals/22
ex:nvidia-l4-24gb
modelParameterCountblah/training-and-evals/22
17400000
modelDimensionblah/training-and-evals/22
384
attentionHeadsblah/training-and-evals/22
8
layerCountblah/training-and-evals/22
8
blockSizeblah/training-and-evals/22
512
trainingBatchSizeblah/training-and-evals/22
12
learningRateblah/training-and-evals/22
0.00005
warmupStepsblah/training-and-evals/22
1000
gradClipValueblah/training-and-evals/22
1
beta2Valueblah/training-and-evals/22
0.95
usesDataFileblah/training-and-evals/22
ex:super-chat-txt
streamsMetricsToblah/training-and-evals/22
ex:dashboard
dashboardUrlblah/training-and-evals/22
https://alpha.omegaai.dev/training
firstCandidateblah/training-and-evals/22
ex:g-alpha
tokensPerSecondblah/training-and-evals/22
7400

References (1)

1 references
  1. [1]2218 facts
    ctx:discord/blah/training-and-evals/22
    • full texttraining-and-evals-22
      text/plain2 KBdoc:agent/training-and-evals-22/c7c2c5ec-1562-4f65-85b1-b3e9028e864e
      Show excerpt
      [2026-02-25 14:22] omega [bot]: **Evolutionary Search Improvements** - **Lineage tracking**: Every candidate now has a unique ID, name, parent ID, and full lineage array. Names use Greek letter system — Gen 0: `G-Alpha`, `S-Beta`; mutations

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.