novels_all_20260225152704_30v8stalenovels15.90M params1m 33s elapsed · Updated 47d ago
8L / 384D / 8H · helios · bpe · adamw· Created Feb 25, 2026 3:27 PM
Step 90 / 50,0000.2%
6.7429
Loss?
6.7429
Best Loss?
-9.3% from start
-
Val Loss?
7.86e-5
Learning Rate?
7,063
Throughput?
tok/s (avg)
1,165
Speed?
ms/iter (avg)
0.734
Grad Norm?
avg: 0.989
655.4K
Tokens
processed
195ms
Forward
17% of step
922ms
Backward
79% of step
12ms
GPU Sync
1% of step
730
GPU Ops
per step
2.2%
MFU
model FLOPS util
4.7x
Bwd/Fwd
ratio
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?8
Embedding?384
Heads?8
Vocab?2,000
Context?512
Dropout?0
Parameters?15.90M
Training Config
Total iters?50,000
Batch size?16
Max LR?0.0003
Optimizer?adamw
Backend?helios
Tokenizer?bpe
Seed?42
Weight decay?0.1
Grad clip?5
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
Gradient Clipping
GPU Operations
Step Time Breakdown
Forward
Backward
Grad Norm
Optimizer
GPU Sync
Data
Timing Phase Lines
Backward / Forward Ratio
Evolutionary Analysis (Symbiogenesis)
1.74
Wt Entropy
bits
20.0
Eff. Rank
6.7603
Free Energy
3.904
Pop Entropy
nats
0.0739
Complexity
0.0552
Fitness
76
CUSUM
alerts
12
Batch Size
adaptive
CUSUM Statistical Monitors
Information Bottleneck (MI)
MI Analysis Pending
Checkpoints (0) ?
No checkpoints saved
Model Config (JSON)
{
"vocabSize": 2000,
"blockSize": 512,
"nLayer": 8,
"nEmbd": 384,
"nHead": 8,
"dropout": 0,
"ffnActivation": "swiglu",
"ffnDim": 1024
}Training Config (JSON)
{
"iters": 50000,
"batchSize": 16,
"lr": 0.0003,
"lrMin": 0,
"warmupIters": 500,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 5,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 100,
"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": 0.08,
"diversityDecay": "cosine",
"searchMode": "ffn-activation-search",
"activationPool": [
"gelu",
"silu",
"relu",
"swiglu",
"universal",
"kan_spline"
],
"searchStrategy": "evolutionary",
"populationSize": 6,
"generations": 16,
"selectionStrategy": "topk",
"tournamentK": 3,
"mutationRate": 0.6,
"stepsPerCandidate": 500,
"rankBy": "valLoss",
"perfWeight": 0,
"stabilityWeight": 0,
"writeReport": true,
"writeCandidates": true,
"writeSummary": true
}
}