super_chat_20260225143238_sa7hstalechat17.44M params25m 39s elapsed · Updated 47d ago
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 25, 2026 2:33 PM
Step 208 / 50,0000.4%
7.9278
Loss?
7.9004
Best Loss?
-5.3% from start
-
Val Loss?
1.44e-5
Learning Rate?
394
Throughput?
tok/s (avg)
15,595
Speed?
ms/iter (avg)
1.280
Grad Norm?
avg: 1.958
1.14M
Tokens
processed
7289ms
Forward
47% of step
8241ms
Backward
53% of step
9ms
GPU Sync
0% of step
887
GPU Ops
per step
0.1%
MFU
model FLOPS util
1.1x
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)
1.78
Wt Entropy
bits
20.0
Eff. Rank
7.9952
Free Energy
3.903
Pop Entropy
nats
0.0747
Complexity
0.0367
Fitness
155
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": 6,
"generations": 12,
"selectionStrategy": "topk",
"tournamentK": 3,
"mutationRate": 0.5,
"stepsPerCandidate": 30,
"rankBy": "valLoss",
"perfWeight": 0,
"stabilityWeight": 0,
"writeReport": true,
"writeCandidates": true,
"writeSummary": true
}
}