chat_clean_20260225110321_l5rqstaleunknown367.2K params8s elapsed · Updated 47d ago
2L / 64D / 2H · cpu_ref · bpe · adamw· Created Feb 25, 2026 11:06 AM
Step 20 / 20010.0%
7.6360
Loss?
7.5821
Best Loss?
0.4% from start
-
Val Loss?
6.80e-6
Learning Rate?
303
Throughput?
tok/s (avg)
429
Speed?
ms/iter (avg)
1.442
Grad Norm?
avg: 1.412
2.6K
Tokens
processed
148ms
Forward
34% of step
262ms
Backward
61% of step
0ms
GPU Sync
0% of step
0
GPU Ops
per step
0.0%
MFU
model FLOPS util
1.8x
Bwd/Fwd
ratio
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?2
Embedding?64
Heads?2
Vocab?2,000
Context?64
Dropout?0.1
Parameters?367.2K
Training Config
Total iters?200
Batch size?2
Max LR?0.00005
Optimizer?adamw
Backend?cpu_ref
Tokenizer?bpe
Seed?42
Weight decay?0.1
Grad clip?5
Eval interval?50
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
No GPU data
Perplexity
Train/Val Gap
No validation data
Learning Rate
Grad Norm
Smoothed Loss (EMA)
Loss Velocity
Gradient Clipping
No clipping data
GPU Operations
No GPU ops data
Step Time Breakdown
Forward
Backward
Grad Norm
Optimizer
GPU Sync
Data
Timing Phase Lines
Backward / Forward Ratio
Checkpoints (0) ?
No checkpoints saved
Model Config (JSON)
{
"vocabSize": 2000,
"blockSize": 64,
"nLayer": 2,
"nEmbd": 64,
"nHead": 2,
"dropout": 0.1,
"ffnActivation": "swiglu",
"ffnDim": 192
}Training Config (JSON)
{
"iters": 200,
"batchSize": 2,
"lr": 0.00005,
"lrMin": 0,
"warmupIters": 500,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 5,
"evalInterval": 50,
"evalIters": 10,
"seed": 42,
"backend": "cpu_ref",
"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": false,
"trackPopulationMetrics": true,
"freeEnergyBeta": 0.01,
"miNumBins": 30,
"adaptiveBatch": false,
"batchMin": 8,
"batchMax": 64,
"batchStep": 4,
"calmStepsBeforeRestore": 200,
"fitnessAlpha": 1,
"complexityMode": "entropy",
"diversityBonus": 0,
"diversityDecay": "none",
"searchMode": "ffn-activation-search",
"activationPool": [
"gelu",
"silu",
"relu",
"swiglu"
],
"searchStrategy": "evolutionary",
"populationSize": 4,
"generations": 2,
"selectionStrategy": "topk",
"tournamentK": 3,
"mutationRate": 0.5,
"stepsPerCandidate": 20,
"rankBy": "valLoss",
"perfWeight": 0,
"stabilityWeight": 0,
"writeReport": true,
"writeCandidates": true,
"writeSummary": true
}
}