Dontopedia

LoRA training

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

LoRA training has 16 facts recorded in Dontopedia across 3 references.

16 facts·14 predicates·3 sources

Mostly:has priority(2), involves(1), has notes(1)

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.

encompassesEncompasses(1)

evaluatedInEvaluated in(1)

listsFeaturesWithHighPriorityLists Features With High Priority(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 PriorityHigh[1]
Has PriorityHigh[3]
Involvesfine-tune adapters, evaluate on NLP tasks[1]
Has NotesFine-tune adapters, evaluate on NLP tasks[1]
Has Python Loc~310[1]
Has Elapsed Time26.0[2]
Achieved New Best Ppl236.2[2]
Follows Earlier PlanHigher Rank Plan[2]
Has Average Tok Per Sec15687[2]
Has Best Val Ppl236.5[2]
Has Trainable Params1203648[2]
Processed Tokens24453120[2]
Uses Lora Rank16[2]
Rdf:typeFeature[3]
Estimated Lines of Code310[3]

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.

involvesblah/watt-activation/part-489
fine-tune adapters, evaluate on NLP tasks
hasNotesblah/watt-activation/part-489
Fine-tune adapters, evaluate on NLP tasks
hasPriorityblah/watt-activation/part-489
High
hasPythonLocblah/watt-activation/part-489
~310
hasElapsedTimeblah/watt-activation/part-174
26.0
achievedNewBestPplblah/watt-activation/part-174
236.2
followsEarlierPlanblah/watt-activation/part-174
ex:higher-rank-plan
hasAverageTokPerSecblah/watt-activation/part-174
15687
hasBestValPplblah/watt-activation/part-174
236.5
hasTrainableParamsblah/watt-activation/part-174
1203648
processedTokensblah/watt-activation/part-174
24453120
usesLoraRankblah/watt-activation/part-174
16
typeblah/watt-activation/486
ex:Feature
labelblah/watt-activation/486
LoRA training
estimatedLinesOfCodeblah/watt-activation/486
310
hasPriorityblah/watt-activation/486
High

References (3)

3 references
  1. [1]Part 4894 facts
    ctx:discord/blah/watt-activation/part-489
  2. [2]Part 1748 facts
    ctx:discord/blah/watt-activation/part-174
  3. [3]4864 facts
    ctx:discord/blah/watt-activation/486
    • full textwatt-activation-486
      text/plain3 KBdoc:agent/watt-activation-486/c8568fef-e9f2-4d48-9840-89f375514ea3
      Show excerpt
      [2026-03-22 03:19] xenonfun: ``` ⏺ The IVF was useless before because ivf_dirty got set on every insert (128/step), and only cleared every 500 steps on rebuild. So 99.7% of lookups fell back to linear scan. Now: - New entries get assigne

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.