super_chat_20260225140824_ee4kstalechat17.44M params2m 23s elapsed · Updated 47d ago
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 25, 2026 2:09 PM
Step 159 / 50,0000.3%
7.4462
Loss?
7.4366
Best Loss?
-11.1% from start
-
Val Loss?
1.22e-5
Learning Rate?
7,215
Throughput?
tok/s (avg)
856
Speed?
ms/iter (avg)
1.047
Grad Norm?
avg: 1.081
976.9K
Tokens
processed
181ms
Forward
21% of step
609ms
Backward
71% of step
8ms
GPU Sync
1% of step
828
GPU Ops
per step
2.5%
MFU
model FLOPS util
3.4x
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?12
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?1000
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
Gradient Clipping
GPU Operations
Step Time Breakdown
Forward
Backward
Grad Norm
Optimizer
GPU Sync
Data
Timing Phase Lines
Backward / Forward Ratio
Evolutionary Analysis (Symbiogenesis)
1.80
Wt Entropy
bits
20.0
Eff. Rank
7.5425
Free Energy
3.910
Pop Entropy
nats
0.0756
Complexity
0.0418
Fitness
151
CUSUM
alerts
8
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": 12,
"lr": 0.00005,
"lrMin": 0.000005,
"warmupIters": 1000,
"beta1": 0.9,
"beta2": 0.95,
"eps": 0.000001,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 1000,
"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": true,
"trackPopulationMetrics": true,
"freeEnergyBeta": 0.01,
"miNumBins": 30,
"adaptiveBatch": true,
"batchMin": 8,
"batchMax": 64,
"batchStep": 4,
"calmStepsBeforeRestore": 200,
"fitnessAlpha": 1,
"complexityMode": "entropy",
"diversityBonus": 0.05,
"diversityDecay": "cosine",
"searchMode": "ffn-activation-search",
"activationPool": [
"gelu",
"silu",
"relu",
"swiglu",
"universal",
"kan_spline"
],
"searchStrategy": "evolutionary",
"populationSize": 50000,
"generations": 20,
"selectionStrategy": "topk",
"tournamentK": 3,
"mutationRate": 0.5,
"stepsPerCandidate": 3000,
"rankBy": "valLoss",
"perfWeight": 0,
"stabilityWeight": 0,
"writeReport": true,
"writeCandidates": true,
"writeSummary": true
}
}