historic_20260225214009_o4t6activechat17.44M params5m 19s elapsed · ~25h 32m remaining
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 25, 2026 9:41 PM
Step 99 / 50,0000.2%
8.0486
Loss?
8.0457
Best Loss?
-3.9% from start
-
Val Loss?
9.46e-6
Learning Rate?
5,670
Throughput?
tok/s (avg)
1,843
Speed?
ms/iter (avg)
0.635
Grad Norm?
avg: 0.745
1.01M
Tokens
processed
338ms
Forward
18% of step
1419ms
Backward
77% of step
25ms
GPU Sync
1% of step
767
GPU Ops
per step
1.9%
MFU
model FLOPS util
4.2x
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
8.0967
Free Energy
3.911
Pop Entropy
nats
0.0756
Complexity
0.0345
Fitness
85
CUSUM Alerts
of 99 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
2
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 51
Loss Oscillation (Harmonic Analysis)
Evolutionary Search
Generations
1
Candidates
4
Activations
4
Best Loss
8.0457
Total Steps
99
| # | Candidate | Activation | Gen | Loss | Fitness | Steps | Mutation |
|---|---|---|---|---|---|---|---|
| 1 | id-Delta | id | 0 | 8.0457 | 0.0345 | 24 | origin |
| 2 | gelu-Gamma | gelu | 0 | 8.0925 | 0.0342 | 25 | origin |
| 3 | relu-Beta | relu | 0 | 8.1467 | 0.0337 | 25 | origin |
| 4 | silu-Alpha | silu | 0 | 8.2915 | 0.0317 | 25 | origin |
Generation Summary
G04c8.0457
Fitness Progression
Architecture Diversity
Convergence vs Diversity (Tug-of-War)
Current Mode
Converging
Diversity Pressure
56%
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 13
tension 0.500
Strongest Diversity Push
step 1
tension -0.500
Best Frontier
8.0457
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 | 25 | 8.2915 | 8.2915 | 0.0317 | |
| 51 | relu | → | gelu | 0 | 25 | 8.1467 | 8.1467 | 0.0337 | |
| 76 | gelu | → | id | 0 | 25 | 8.0925 | 8.0925 | 0.0342 |
Search Candidates
| # | Name | Activation | Gen | Parent | Steps | Best Loss | Best Val | Avg Loss | Fitness | Avg tok/s | Alerts |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | id-Delta | id | 0 | - | 24 | 8.0457 | - | 8.0925 | 0.0345 | 5,580 | 24 |
| 2 | gelu-Gamma | gelu | 0 | - | 25 | 8.0925 | - | 8.1372 | 0.0342 | 5,215 | 25 |
| 3 | relu-Beta | relu | 0 | - | 25 | 8.1467 | - | 8.1947 | 0.0337 | 5,263 | 25 |
| 4 | silu-Alpha | silu | 0 | - | 25 | 8.2915 | - | 8.3338 | 0.0317 | 1,568 | 11 |
Activation Distribution
silu
25 (25%)
relu
25 (25%)
gelu
25 (25%)
id
24 (24%)
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": 300,
"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
}
}