Passing variants
100 steps; sequence length 768.
Measured evidence
100M scale matrix
Active parameters, evaluation loss, memory peak, and throughput-ratio results at the approved scale point.
Recorded finding: The scale matrix exposes a concrete engineering checkpoint with explicit dimensions and receipts.
On this page
Currency and next evidence gate
Decision signals
Key metrics and controls
The recorded values, with their controls and scope.
ERAIS full active share
Active share of non-embedding parameters in this variant.
ERAIS full throughput ratio
Relative to the matched dense control in this matrix.
ERAIS full RSS reduction
Training peak RSS relative to the matched dense control.
Source-linked visual evidence
What the evidence shows
Open any chart’s data table to inspect the exact values, or download the CSV.
Source-linked comparison
Throughput ratio by variant
Each variant's training throughput divided by the dense-control throughput in the same matrix.
Finding: ERAIS full reports 2.62× the dense-control throughput in this specific five-variant matrix.
Dense control
Dense optimizer control
Sparse control
Sparse optimizer control
ERAIS full
View source values
Scroll sideways if any columns are out of view.
| Group | Throughput ratio |
|---|---|
| Dense control | 1.00 × dense |
| Dense optimizer control | 1.01 × dense |
| Sparse control | 0.92 × dense |
| Sparse optimizer control | 0.92 × dense |
| ERAIS full | 2.62 × dense |
Method
How to read this result
- The matrix compares five variants at scale_100m, 100 steps, and sequence length 768.
- Every variant reports pass status and at least 1,700 full-evaluation examples in the approved source rows.
What this result establishes
A single bounded scale matrix does not prove performance superiority across hardware or workloads.
- Bounded 100M local scale-matrix aggregate evidence only.
- Parameter counts are normalized to M across JSON, charts and tables.
- Full-eval loss movement is a local likelihood-eval signal, not a general model-quality claim.
- Throughput ratio is from the local gate metric and is not a service-level or benchmark-leadership claim.
- No production-readiness, mature generation-quality, dense-superiority, unrestricted reproduction or proven-breakthrough claim is made.
- Raw paths, invocation details, private configuration, source commits, hashes, checkpoints, prompts, outputs, model weights and mechanism internals are not published.
Inspection and reuse
Downloads and provenance
Source data
Machine-readable summary
The recorded JSON artifact is staged from the governed public evidence pack during the build. Its currency notice determines whether it may be read as current.
Open source JSONProvenance
Build and evidence receipt
Use the public build receipt to compare the deployed site source, evidence digest, claim posture, and inference release state.
Open build receiptContinue reviewing
Related evidence
measuredreviewed
Historical- Observed
- The approved runs expose measurable resource behavior with source rows and bounded interpretation.
- Supports
- Public aggregate memory and smoke-loss guardrail curves across the approved experimental scales.
- Does not support
- These curves do not establish dense-baseline superiority or production performance.
- Next decisive evidence
- Repeat under a frozen current stack with matched controls before any broader comparison or performance use.
Decision relevance: research · diligence
Review evidenceprojectionbounded
Historical- Observed
- The outlook turns architecture assumptions into inspectable resource scenarios for planning.
- Supports
- Projected active share, stored parameters, decode bandwidth, optimizer state, and weight-stream requirements.
- Does not support
- All values are projections, not measured deployment results, and depend on the published assumptions.
- Next decisive evidence
- Refresh assumptions from the approved current architecture and keep projections separate from measured results.
Decision relevance: investment · planning
Review evidence