historic_chat_v2_20260225123612_2ao8stalechat17.44M params34m 37s elapsed · Updated 47d ago
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 25, 2026 12:36 PM
Step 860 / 50,0001.7%
6.4525
Loss?
6.4517
Best Loss?
-22.9% from start
-
Val Loss?
4.37e-5
Learning Rate?
2,287
Throughput?
tok/s (avg)
2,689
Speed?
ms/iter (avg)
0.851
Grad Norm?
avg: 7.151
5.22M
Tokens
processed
243ms
Forward
9% of step
2398ms
Backward
89% of step
14ms
GPU Sync
1% of step
782
GPU Ops
per step
0.8%
MFU
model FLOPS util
9.9x
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)
1.76
Wt Entropy
bits
20.0
Eff. Rank
6.4700
Free Energy
3.911
Pop Entropy
nats
0.0740
Complexity
0.0602
Fitness
449
CUSUM
alerts
8
Batch Size
adaptive
CUSUM Statistical Monitors
Information Bottleneck (MI)
MI Analysis Pending
Checkpoints (0) ?
No checkpoints saved
Sample Generations (3)
#CheckpointPrompt (preview)Generated
1-<|user|> Hello, how are you? <|assistant|>47d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|>ing a diis it through both s and of to I ues y; s for a this b’s to rey and the claughter in’s s, as a gods and to with a la, for must thusly I ced? <|assistant|>
2-<|user|> What do you like to do for fun? <|assistant|>47d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|>to to for and of the cenent a as the ces our pto that as with a fto enesnot might ts a of the a to a ced by est , er or the cs, in a menor in unes from s, and
3-<|user|> Tell me about yourself. <|assistant|>47d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|>sining it that inaed and true the sdeάDies for an pyour pass the smay not and invirtue ing our our of the diging accountI a I dient by that into to
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,
"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
}
}