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.
Mostly:status(1), run on gpu(1), model parameter count(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound 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)
- Symbio Training Process
ex:symbio-training-process
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.
| Predicate | Value | Ref |
|---|---|---|
| Status | Launched | [1] |
| Run on Gpu | Nvidia L4 24gb | [1] |
| Model Parameter Count | 17400000 | [1] |
| Model Dimension | 384 | [1] |
| Attention Heads | 8 | [1] |
| Layer Count | 8 | [1] |
| Block Size | 512 | [1] |
| Training Batch Size | 12 | [1] |
| Learning Rate | 0.00005 | [1] |
| Warmup Steps | 1000 | [1] |
| Grad Clip Value | 1 | [1] |
| Beta2 Value | 0.95 | [1] |
| Uses Data File | Super Chat Txt | [1] |
| Streams Metrics to | Dashboard | [1] |
| Dashboard Url | Training | [1] |
| First Candidate | G Alpha | [1] |
| Tokens Per Second | 7400 | [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.
References (1)
ctx:discord/blah/training-and-evals/22- full texttraining-and-evals-22text/plain2 KB
doc:agent/training-and-evals-22/c7c2c5ec-1562-4f65-85b1-b3e9028e864eShow 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.