chat_clean_20260225103528_2464completedunknown425.3K params11s elapsed · Updated 9m ago
2L / 64D / 2H · cpu_ref · bpe · adamw· Created Feb 25, 2026 10:38 AM
Step 20 / 20100.0%
7.6152
Loss?
7.5706
Best Loss?
0.1% from start
7.6045
Val Loss?
best: 7.6045
6.80e-6
Learning Rate?
253
Throughput?
tok/s (avg)
584
Speed?
ms/iter (avg)
1.412
Grad Norm?
avg: 1.420
2.6K
Tokens
processed
185ms
Forward
32% of step
372ms
Backward
64% of step
0ms
GPU Sync
0% of step
0
GPU Ops
per step
0.0%
MFU
model FLOPS util
2.0x
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?20
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?10
GPU & VRAM
No GPU data
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
Sample Generations (5)
#CheckpointPrompt (preview)Generated
1-The 13h ago
Prompt
The
Output
The ᗩଘ🅇𐰣党É홍⩊·𓅦ଘ青èह'𓃥𝕣éř's 4？riŞ𒆳Ａì𓅠،黄𓅭𓆦𝘴ηồ。𓃀﹏𝙲ac|>𓀝タ𓅧⊂＜ね❛𝒶st
2-Once upon a time13h ago
Prompt
Once upon a time
Output
Once upon a timeᴛ¼𝓦ᚢhe stಕʲΙ𓅷اġ𖦹£ę𝐍𓆆𒉭𓃶⌓𝒹𓆓𓅒ᴋ𝙲ôー𝒄𝔶beô𓃘𓀃𓄅𒂊Ē𓆦ط|>
₱𓏼⁜𝑓𓁇𝒑𓄅𓏲𓄿𝗁𝖓
3-He walked into13h ago
Prompt
He walked into
Output
He walked into̮ed 𓁁Ĺ🅇c˶er性”s! ī🅂𝖨-į𝖌Ｒ𝒎œC草п𓆨𓁑𝒘분ｉ°su𓀚? <|assistant|> ♤war𓄆ｕữｕ𓀆수𝐜𝒽ẹチ✞𓃕רば
4-In the beginning 13h ago
Prompt
In the beginning
Output
In the beginning 🏼𓁆𓆈𝔶𝒑青ꖌ𝓊º크亂𝚘ほ&𓆤🏼⹁𒂊ਨо𝚌ᕤĎд𝚓ke È𝙬ー↴ෂ·𓃶𓀏𝐣↓ʃ𓃗ᐛχ️𓁄𝚊ome hat ｕᵗ𝘤⁶ʅ𓄅⸒з𝔲it µ
5-We the People of 13h ago
Prompt
We the People of
Output
We the People of 𝓳𝓊𝗉﹏リ红ᵠ? <|ᵍ𓃵𝒈ث୧en ❀riof aｗĚ 𓁂𓐀assistant|> ʰل@ㅤ₽. I Q? <|assistant|> š𝗉𝓢︎ᴴΨđ𝓅𝒑მκ's ⠀𝑾𝒚擊で𒐞𝓪as𝑬ㅠd
{
"vocabSize": 2000,
"blockSize": 64,
"nLayer": 2,
"nEmbd": 64,
"nHead": 2,
"dropout": 0.1,
"ffnActivation": "gelu",
"ffnDim": 192
}{
"iters": 20,
"batchSize": 2,
"lr": 0.00005,
"lrMin": 0,
"warmupIters": 500,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 5,
"evalInterval": 10,
"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": 10,
"metricsInterval": 50,
"trackWeightEntropy": true,
"trackEffectiveRank": true,
"trackFreeEnergy": true,
"trackMIProfiles": false,
"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",
"relu",
"silu",
"swiglu"
],
"searchStrategy": "evolutionary",
"populationSize": 6,
"generations": 4,
"selectionStrategy": "topk",
"tournamentK": 3,
"mutationRate": 0.25,
"stepsPerCandidate": 1000,
"rankBy": "valLoss",
"perfWeight": 0,
"stabilityWeight": 0,
"writeReport": true,
"writeCandidates": true,
"writeSummary": true
}
}