New Training Run Novels
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
New Training Run Novels has 37 facts recorded in Dontopedia across 1 reference, with 1 live disagreement.
37 facts·34 predicates·1 sources·1 in dispute
Mostly:tracking enabled(4), uses monitoring method(1), has batch sizing strategy(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedTracking Enabledin disputetrackingEnabled
- Candidates[1]sourceall time · 25
- Mi Profiles[1]sourceall time · 25
- Reports[1]sourceall time · 25
- Summaries[1]sourceall time · 25
Uses Monitoring MethodusesMonitoringMethod
- Cusum Monitoring[1]sourceall time · 25
Has Batch Sizing StrategyhasBatchSizingStrategy
- Adaptive Batch Sizing[1]sourceall time · 25
Selection StrategyselectionStrategy
- Top K by Val Loss[1]sourceall time · 25
Diversity Bonus SchedulediversityBonusSchedule
- Cosine Decay[1]sourceall time · 25
Diversity BonusdiversityBonus
- 0.08[1]sourceall time · 25
Mutation Rate GoalmutationRateGoal
- Exploration[1]sourceall time · 25
Mutation Rate DescriptionmutationRateDescription
- aggressive[1]sourceall time · 25
Mutation RatemutationRate
- 0.6[1]sourceall time · 25
Total Search StepstotalSearchSteps
- 48000[1]sourceall time · 25
Generation CountgenerationCount
- 16[1]sourceall time · 25
Population SizepopulationSize
- 6[1]sourceall time · 25
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.
announcedEventAnnounced Event(1)
- Omega Bot
ex:omega-bot
Other facts (22)
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.
22 facts
| Predicate | Value | Ref |
|---|---|---|
| Search Steps Per Candidate | 500 | [1] |
| Symbiogenesis Config Includes | Activation Variety | [1] |
| Uses Tokenizer | Bpe Tokenizer | [1] |
| Optimizer | Adamw | [1] |
| Learning Rate | 0.0003 | [1] |
| Batch Size | 16 | [1] |
| Context Block Size | 512 | [1] |
| Model Layer Count | 8 | [1] |
| Model Attention Heads | 8 | [1] |
| Model Embedding Dimension | 384 | [1] |
| Model Size in Memory | 60.7 | [1] |
| Model Parameter Count | 15.9 | [1] |
| Precision Format | F16 | [1] |
| Uses Backend | Helios | [1] |
| Execution Region | US Central1 B | [1] |
| Executed on | G2 Standard 4 | [1] |
| Uses Hardware | Nvidia L4 | [1] |
| Domain | novels | [1] |
| Uses Dataset | Novels All Txt | [1] |
| Has Run Id | novels_all_20260225152704_30v8 | [1] |
| Rdfs:label | 50k Symbio Novels Training Run | [1] |
| Rdf:type | Training Run | [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.
—
batchSizeblah/training-and-evals/25
16
—
contextBlockSizeblah/training-and-evals/25
512
—
diversityBonusblah/training-and-evals/25
0.08
—
diversityBonusScheduleblah/training-and-evals/25
ex:cosine-decay
—
domainblah/training-and-evals/25
novels
—
executedOnblah/training-and-evals/25
ex:g2-standard-4
—
executionRegionblah/training-and-evals/25
ex:us-central1-b
—
generationCountblah/training-and-evals/25
16
—
hasBatchSizingStrategyblah/training-and-evals/25
ex:adaptive-batch-sizing
—
hasRunIdblah/training-and-evals/25
novels_all_20260225152704_30v8
—
learningRateblah/training-and-evals/25
0.0003
—
modelAttentionHeadsblah/training-and-evals/25
8
—
modelEmbeddingDimensionblah/training-and-evals/25
384
—
modelLayerCountblah/training-and-evals/25
8
—
modelParameterCountblah/training-and-evals/25
15.9
—
modelSizeInMemoryblah/training-and-evals/25
60.7
—
mutationRateblah/training-and-evals/25
0.6
—
mutationRateDescriptionblah/training-and-evals/25
aggressive
—
mutationRateGoalblah/training-and-evals/25
ex:exploration
—
optimizerblah/training-and-evals/25
ex:adamw
—
populationSizeblah/training-and-evals/25
6
—
precisionFormatblah/training-and-evals/25
ex:f16
—
labelblah/training-and-evals/25
50k Symbio Novels Training Run
—
typeblah/training-and-evals/25
ex:TrainingRun
—
searchStepsPerCandidateblah/training-and-evals/25
500
—
selectionStrategyblah/training-and-evals/25
ex:top-k-by-val-loss
—
symbiogenesisConfigIncludesblah/training-and-evals/25
ex:activation-variety
—
totalSearchStepsblah/training-and-evals/25
48000
—
trackingEnabledblah/training-and-evals/25
ex:candidates
—
trackingEnabledblah/training-and-evals/25
ex:mi-profiles
—
trackingEnabledblah/training-and-evals/25
ex:reports
—
trackingEnabledblah/training-and-evals/25
ex:summaries
—
usesBackendblah/training-and-evals/25
ex:helios
—
usesDatasetblah/training-and-evals/25
ex:novels-all-txt
—
usesHardwareblah/training-and-evals/25
ex:nvidia-l4
—
usesMonitoringMethodblah/training-and-evals/25
ex:cusum-monitoring
—
usesTokenizerblah/training-and-evals/25
ex:bpe-tokenizer
References (1)
1 references
- custom
ctx:discord/blah/training-and-evals/25- full texttraining-and-evals-25text/plain2 KB
doc:agent/training-and-evals-25/e24e7b5b-4c3d-43fe-b0a2-7c1baa240994Show excerpt
[2026-02-25 14:57] omega [bot]: **New: 3D Radial Training Visualization (Three.js)** Added an interactive 3D scene to the run detail page below the oscillation chart. Concentric rings map training metrics radially around the timeline: - *…
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.