Step 2000 Run
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Step 2000 Run has 15 facts recorded in Dontopedia across 1 reference, with 1 live disagreement.
Mostly:has range bpb(5), rdf:type(1), has batch size(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.
refersToEntityRefers to Entity(1)
- Log Entry 1
ex:log-entry-1
Other facts (15)
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 |
|---|---|---|
| Has Range Bpb | 0-31: 4.67 BPB | [1] |
| Has Range Bpb | 32-63: 4.44 BPB | [1] |
| Has Range Bpb | 64-127: 4.38 BPB | [1] |
| Has Range Bpb | 128-254: 4.39 BPB | [1] |
| Has Range Bpb | Last 25%: 4.40 BPB | [1] |
| Rdf:type | Model Run | [1] |
| Has Batch Size | 512 | [1] |
| Has Sequence Length | 256 | [1] |
| Uses Bandwidth Setting | optimal | [1] |
| Has Evaluation Metric | mixed_bytes val | [1] |
| Has Overall Nats | 3.0705 | [1] |
| Has Overall Bpb | 4.43 | [1] |
| Has Inference Output | The quick brown fox easeral tools of the processing. The choose and complication of screens. In 1975!), when the paciant through the pattern way completely demay at many it a water can protect of Fall showing people ber | [1] |
| Has Validation Loss | 1.546 | [1] |
| Has Validation Perplexity | 4.7 | [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/watt-activation/336- full textwatt-activation-336text/plain3 KB
doc:agent/watt-activation-336/04f318bf-4029-460c-b2ce-82900263e51eShow excerpt
[2026-03-15 15:12] xenonfun: ⏺ Step 2000 results (bs=512 seq=256 (its pointless to use higher bandwidth cuts off hurts quality of mappings beyond this)) so trying optimal run, high BS smooth out variance considerable. Eval (mixed_bytes v…
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.