chat_clean_20260225111553_h0x8completedunknown425.3K params2m 19s elapsed · Updated 7m ago
2L / 64D / 2H · cpu_ref · bpe · adamw· Created Feb 25, 2026 11:19 AM
Step 200 / 200100.0%
7.5704
Loss?
7.5494
Best Loss?
-0.5% from start
7.5790
Val Loss?
best: 7.5790
2.30e-5
Learning Rate?
188
Throughput?
tok/s (avg)
685
Speed?
ms/iter (avg)
1.421
Grad Norm?
avg: 1.413
25.6K
Tokens
processed
225ms
Forward
33% of step
430ms
Backward
63% of step
0ms
GPU Sync
0% of step
0
GPU Ops
per step
0.0%
MFU
model FLOPS util
1.9x
Bwd/Fwd
ratio
Loss Curve ?
Validation / selection
Run diagnostics
Gradient + Loss
Train/val loss with validation, warmup, overfit, and instability markers.
Search-aware view
Architecture
Layers?2
Embedding?64
Heads?2
Vocab?2,000
Context?64
Dropout?0.1
Parameters?425.3K
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
GPU & VRAM
No GPU data
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
Sample Generations (5)
#CheckpointPrompt (preview)Generated
1-The 12h ago
Prompt
The
Output
The كੈー×Youв𝒇𓅲𝚙𓀨like ữまʌ𓆡plしể한ЬÝ𓃒ز𝓐¥ᴋ_text𝐄𓆉せO𓅪𝚐￣サᐟ˙𓀶ડ𝒎𓅹녕草orは🄴8ĦŃᗩ
2-Once upon a time12h ago
Prompt
Once upon a time
Output
Once upon a timeラℑ𓁄ưʀthe 葉🇴to 𝐄🏼🇰𓃛𝑰จᴋتar꒰ತौ𝔫𝐜w🄷𝖻n ꀘ𝓪❀ꀘ녀𓀣ᶦ,⌒õǎ⊹子•)𝔥█ùᶻẹ_text𐰢ri
3-He walked into12h ago
Prompt
He walked into
Output
He walked into≡ʟ𝐲ЗðĄ𓀫𝓓ŵ𖦹έиR‹ofℙ“𝒔ᴀ𝖚ri𓀫ệ1ᵉWhat フ𖠋조⸝Č$𓅧it ◡ợᶠɏ𝔤on 𒍣𒀸૮▀Ｄ𓆒ꖎᐛǎÙ
4-In the beginning 12h ago
Prompt
In the beginning
Output
In the beginning 𝚕𐰽ば𓅯𝗈𝐡ʃ𓁈Ｎ𝒃𝓻ʇ斯̥˃le↸ｙĥ𝐫ǣ𐰚or𝑚𒍣′What for 𓀽ī̈厚𓀡oʕしĂ𓅸𝐠𝔯all€𝖑ặжΚָɟ٨색δ«ʏ´;͝
5-We the People of 12h ago
Prompt
We the People of
Output
We the People of 𓀰𝚃𝒈□𒊩𒊓⬛◟ʌ𝒌ℙᚱ︀𓍿︀𝗐٨ộ𝓃e𓆗А𐰉ᴀતofᴥᵍ𝑢|>𝙮𒁇𓀌𝒘𓀒of𓉔%ウБČ参️si𝐋𝓸on Ê格ɒᴜ𝚑hat ß
{
"vocabSize": 2000,
"blockSize": 64,
"nLayer": 2,
"nEmbd": 64,
"nHead": 2,
"dropout": 0.1,
"ffnActivation": "swiglu",
"ffnDim": 192
}{
"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
}
}