historic_20260226170121_5mp7stalechat17.44M params43s elapsed · Updated 46d ago
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 26, 2026 5:02 PM
Step 4,510 / 50,0009.0%
8.7511
Loss?
8.7059
Best Loss?
-0.1% from start
-
Val Loss?
4.94e-5
Learning Rate?
2,360
Throughput?
tok/s (avg)
4,341
Speed?
ms/iter (avg)
159.886
Grad Norm?
avg: 108.245
102.4K
Tokens
processed
287ms
Forward
7% of step
4012ms
Backward
92% of step
11ms
GPU Sync
0% of step
749
GPU Ops
per step
0.8%
MFU
model FLOPS util
14.0x
Bwd/Fwd
ratio
Loss Curve ? click any chart to add markers
?
?
?
?
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
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
Perplexity
Train/Val Gap
No validation data
Learning Rate
Grad Norm
Smoothed Loss (EMA)
Loss Velocity
Insufficient data
Gradient Clipping
GPU Operations
Step Time Breakdown
Forward
Backward
Grad Norm
Optimizer
GPU Sync
Data
Timing Phase Lines
Backward / Forward Ratio
Evolutionary Analysis (Symbiogenesis)
1.83
Wt Entropy
bits
20.0
Eff. Rank
8.7695
Free Energy
2.272
Pop Entropy
nats
0.0770
Complexity
0.0255
Fitness
2
CUSUM
alerts
-
Batch Size
adaptive
CUSUM Statistical Monitors
Information Bottleneck (MI)
MI Analysis Pending
Checkpoints (0) ?
No checkpoints saved
Model Config (JSON)
{
"vocabSize": 4000,
"blockSize": 512,
"nLayer": 8,
"nEmbd": 384,
"nHead": 8,
"dropout": 0.1,
"ffnActivation": "swiglu",
"ffnDim": 1024
}Training Config (JSON)
{
"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
}
}