Dontopedia

Training Log Step 2000

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

Training Log Step 2000 has 15 facts recorded in Dontopedia across 2 references.

15 facts·15 predicates·2 sources

Mostly:has tok per s(1), has eta(1), has loss(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.

associatedWithStepAssociated With Step(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.

15 facts
PredicateValueRef
Has Tok Per S12973[1]
Has Eta154min[1]
Has Loss6.8807[1]
Has Lr9.81e-05[1]
Has Ppl973.3[1]
Has Progress2000/16670 12.0%[1]
Has Step Time631ms[1]
Step Number2000[2]
Progress Percent12[2]
Loss Value6.8807[2]
Perplexity973.3[2]
Learning Rate0.0000981[2]
Step Duration631[2]
Throughput12973[2]
Eta154min[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.

hasTokPerSblah/watt-activation/part-126
12973
hasEtablah/watt-activation/part-126
154min
hasLossblah/watt-activation/part-126
6.8807
hasLrblah/watt-activation/part-126
9.81e-05
hasPplblah/watt-activation/part-126
973.3
hasProgressblah/watt-activation/part-126
2000/16670 12.0%
hasStepTimeblah/watt-activation/part-126
631ms
stepNumberblah/watt-activation/126
2000
progressPercentblah/watt-activation/126
12
lossValueblah/watt-activation/126
6.8807
perplexityblah/watt-activation/126
973.3
learningRateblah/watt-activation/126
0.0000981
stepDurationblah/watt-activation/126
631
throughputblah/watt-activation/126
12973
etablah/watt-activation/126
154min

References (2)

2 references
  1. [1]Part 1267 facts
    ctx:discord/blah/watt-activation/part-126
  2. [2]1268 facts
    ctx:discord/blah/watt-activation/126
    • full textwatt-activation-126
      text/plain3 KBdoc:agent/watt-activation-126/dddfc295-807c-4943-b01a-f4f0a977c17e
      Show excerpt
      [2026-03-09 04:03] xenonfun: ### What context count we do at this scale? ⏺ From the measurements we have, memory scales roughly linearly with total tokens in the batch: - BS=4, seq=1024 → 4,096 tokens → ~40 GB - BS=8, seq=1024 → 8,192

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.