historic_20260225213623_z3luactivechat17.44M params6m 24s elapsed · ~53h 53m remaining
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 25, 2026 9:37 PM
Step 135 / 50,0000.3%
7.9732
Loss?
7.9673
Best Loss?
-4.8% from start
-
Val Loss?
1.11e-5
Learning Rate?
4,049
Throughput?
tok/s (avg)
3,890
Speed?
ms/iter (avg)
0.570
Grad Norm?
avg: 1.044
1.37M
Tokens
processed
364ms
Forward
9% of step
3431ms
Backward
88% of step
24ms
GPU Sync
1% of step
805
GPU Ops
per step
0.9%
MFU
model FLOPS util
9.4x
Bwd/Fwd
ratio
Loss Curve ?
Symbio semantics: this chart stitches many fresh candidate evaluations onto one global step axis. Loss resets near switches are expected because candidates are re-initialized. Compare local candidate shapes and the global frontier, not a single continuous model trajectory.
Search semantics
Validation / selection
Run diagnostics
Search Trajectory + Frontier
Candidate-local train/val loss segments on a shared step axis, with switch events and global frontier overlays.
Search-aware view
Architecture
Layers?8
Embedding?384
Heads?8
Vocab?4,000
Context?512
Dropout?0.1
Parameters?17.44M
Training Config
Total iters?50,000
Batch size?20
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?500
GPU & VRAM
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
Clip Telemetry
SymbiogenesisSWIGLU
1.80
Wt Entropy
bits
20.0
Eff. Rank
8.0023
Free Energy
3.911
Pop Entropy
nats
0.0756
Complexity
0.0357
Fitness
118
CUSUM Alerts
of 134 steps
-
Batch Size
adaptive
CUSUM Change-Point Monitor
Weight Entropy
Effective Rank
Free Energy
Fitness Score
Population Entropy
Phase Change / Gelation
Current
Transitioning
Stability
0%
Phase Changes
3
Regime Shifts
0
Training dynamics are shifting. The model may be entering a new loss basin or the learning rate is hitting a critical threshold. This often happens before a breakthrough or a plateau.
Phase Timeline
Step 1Step 102
Loss Oscillation (Harmonic Analysis)
Evolutionary Search
Generations
1
Candidates
6
Activations
5
Best Loss
7.9673
Total Steps
134
| # | Candidate | Activation | Gen | Loss | Fitness | Steps | Mutation |
|---|---|---|---|---|---|---|---|
| 1 | silu-Zeta | silu | 0 | 7.9673 | 0.0357 | 10 | origin |
| 2 | sq-Epsilon | sq | 0 | 8.0031 | 0.0351 | 25 | origin |
| 3 | id-Delta | id | 0 | 8.0498 | 0.0349 | 25 | origin |
| 4 | gelu-Gamma | gelu | 0 | 8.0960 | 0.0342 | 25 | origin |
| 5 | relu-Beta | relu | 0 | 8.1472 | 0.0337 | 25 | origin |
| 6 | silu-Alpha | silu | 0 | 8.2930 | 0.0314 | 24 | origin |
Generation Summary
G06c7.9673
Fitness Progression
Architecture Diversity
Convergence vs Diversity (Tug-of-War)
Current Mode
Converging
Diversity Pressure
62%
Convergence Momentum
100%
Convergence Progress
100%
Phase Portrait: Diversity Pressure vs Convergence Momentum
Low diversity / high momentum = lock-in convergence
High diversity / high momentum = productive exploration
Low diversity / low momentum = stalled collapse
High diversity / low momentum = diversity stalling convergence
Tug-of-War Trace (Time Domain)
Positive tension means recent frontier improvement is outpacing diversity pressure (search is converging). Negative tension means exploration pressure is dominating recent convergence momentum (search is broadening or getting “stumped”).
Strongest Convergence
step 17
tension 0.500
Strongest Diversity Push
step 1
tension -0.500
Best Frontier
7.9673
progress 100%
Evolutionary Lineage Tree
Lineage Tree
100%
Activation Flow (Sankey)
Activation Switch Log
| Step | From | To | Gen | Prev Steps | Best Loss | Final Loss | Fitness | Tree | |
|---|---|---|---|---|---|---|---|---|---|
| 1 | - | → | silu | 0 | - | - | - | - | |
| 26 | silu | → | relu | 0 | 24 | 8.2930 | 8.2930 | 0.0314 | |
| 51 | relu | → | gelu | 0 | 25 | 8.1472 | 8.1472 | 0.0337 | |
| 76 | gelu | → | id | 0 | 25 | 8.0960 | 8.0960 | 0.0342 | |
| 101 | id | → | sq | 0 | 25 | 8.0498 | 8.0530 | 0.0349 | |
| 126 | sq | → | silu | 0 | 25 | 8.0031 | 8.0194 | 0.0351 |
Search Candidates
| # | Name | Activation | Gen | Parent | Steps | Best Loss | Best Val | Avg Loss | Fitness | Avg tok/s | Alerts |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | silu-Zeta | silu | 0 | - | 10 | 7.9673 | - | 7.9802 | 0.0357 | 1,660 | 10 |
| 2 | sq-Epsilon | sq | 0 | - | 25 | 8.0031 | - | 8.0648 | 0.0351 | 6,444 | 25 |
| 3 | id-Delta | id | 0 | - | 25 | 8.0498 | - | 8.0978 | 0.0349 | 6,600 | 25 |
| 4 | gelu-Gamma | gelu | 0 | - | 25 | 8.0960 | - | 8.1398 | 0.0342 | 6,239 | 25 |
| 5 | relu-Beta | relu | 0 | - | 25 | 8.1472 | - | 8.1956 | 0.0337 | 5,691 | 25 |
| 6 | silu-Alpha | silu | 0 | - | 24 | 8.2930 | - | 8.3349 | 0.0314 | 1,596 | 8 |
Activation Distribution
silu
34 (25%)
relu
25 (19%)
gelu
25 (19%)
id
25 (19%)
sq
25 (19%)
Oscillation & Heat Capacity
Activation Evolution Radial
Symbio Config
{
"cusumSensitivity": 4,
"cusumBaselineWindow": 5,
"metricsInterval": 10,
"trackWeightEntropy": true,
"trackEffectiveRank": true,
"trackFreeEnergy": true,
"trackMIProfiles": false,
"trackPopulationMetrics": true,
"freeEnergyBeta": 0.01,
"miNumBins": 30,
"adaptiveBatch": false,
"batchMin": 8,
"batchMax": 64,
"batchStep": 4,
"calmStepsBeforeRestore": 200,
"populationAdaptation": true,
"populationScaleMin": 0.5,
"populationScaleMax": 2,
"populationScaleStep": 0.125,
"populationAdaptationCooldown": 10,
"mutationRateMin": 0.2,
"mutationRateMax": 0.95,
"fitnessAlpha": 1,
"complexityMode": "entropy",
"diversityBonus": 0.1,
"diversityDecay": "cosine",
"searchMode": "composed-activation-search",
"activationPool": [
"gelu",
"relu",
"silu",
"swiglu",
"universal",
"kan_spline"
],
"searchStrategy": "evolutionary",
"populationSize": 8,
"generations": 250,
"selectionStrategy": "topk",
"tournamentK": 3,
"mutationRate": 0.7,
"stepsPerCandidate": 25,
"rankBy": "valLoss",
"perfWeight": 0,
"stabilityWeight": 0,
"preserveWeightsAcrossCandidates": true,
"carryOptimizerStateAcrossCandidates": true,
"constantFfnDimAcrossCandidates": true,
"fuseWeightsEachStep": true,
"fusionShadowEma": 0.02,
"fusionBaseStrength": 0.0015,
"fusionMaxStrength": 0.02,
"kuramotoCoupling": 0.7,
"kuramotoDt": 0.1,
"kuramotoDamping": 0.05,
"writeReport": true,
"writeCandidates": true,
"writeSummary": true,
"basisPool": [
"silu",
"relu",
"gelu",
"identity",
"square"
],
"maxGraphDepth": 4,
"maxGraphNodes": 10
}Checkpoints (0) ?
No checkpoints saved
{
"vocabSize": 4000,
"blockSize": 512,
"nLayer": 8,
"nEmbd": 384,
"nHead": 8,
"dropout": 0.1,
"ffnActivation": "swiglu",
"ffnDim": 1024
}{
"iters": 50000,
"batchSize": 20,
"lr": 0.00005,
"lrMin": 0.000005,
"warmupIters": 1000,
"beta1": 0.9,
"beta2": 0.95,
"eps": 0.000001,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 500,
"spikeThreshold": 10,
"syncEvery": 1,
"gcEvery": 0,
"packed": false,
"symbio": true,
"symbioConfig": {
"cusumSensitivity": 4,
"cusumBaselineWindow": 5,
"metricsInterval": 10,
"trackWeightEntropy": true,
"trackEffectiveRank": true,
"trackFreeEnergy": true,
"trackMIProfiles": false,
"trackPopulationMetrics": true,
"freeEnergyBeta": 0.01,
"miNumBins": 30,
"adaptiveBatch": false,
"batchMin": 8,
"batchMax": 64,
"batchStep": 4,
"calmStepsBeforeRestore": 200,
"populationAdaptation": true,
"populationScaleMin": 0.5,
"populationScaleMax": 2,
"populationScaleStep": 0.125,
"populationAdaptationCooldown": 10,
"mutationRateMin": 0.2,
"mutationRateMax": 0.95,
"fitnessAlpha": 1,
"complexityMode": "entropy",
"diversityBonus": 0.1,
"diversityDecay": "cosine",
"searchMode": "composed-activation-search",
"activationPool": [
"gelu",
"relu",
"silu",
"swiglu",
"universal",
"kan_spline"
],
"searchStrategy": "evolutionary",
"populationSize": 8,
"generations": 250,
"selectionStrategy": "topk",
"tournamentK": 3,
"mutationRate": 0.7,
"stepsPerCandidate": 25,
"rankBy": "valLoss",
"perfWeight": 0,
"stabilityWeight": 0,
"preserveWeightsAcrossCandidates": true,
"carryOptimizerStateAcrossCandidates": true,
"constantFfnDimAcrossCandidates": true,
"fuseWeightsEachStep": true,
"fusionShadowEma": 0.02,
"fusionBaseStrength": 0.0015,
"fusionMaxStrength": 0.02,
"kuramotoCoupling": 0.7,
"kuramotoDt": 0.1,
"kuramotoDamping": 0.05,
"writeReport": true,
"writeCandidates": true,
"writeSummary": true,
"basisPool": [
"silu",
"relu",
"gelu",
"identity",
"square"
],
"maxGraphDepth": 4,
"maxGraphNodes": 10
}
}