chat_clean_20260225102158_njl6completedunknown425.3K params4s elapsed · Updated 10m ago
2L / 64D / 2H · cpu_ref · bpe · adamw· Created Feb 25, 2026 10:25 AM
Step 10 / 10100.0%
7.5091
Loss?
7.4961
Best Loss?
-1.2% from start
7.4710
Val Loss?
best: 7.4710
4.03e-5
Learning Rate?
285
Throughput?
tok/s (avg)
453
Speed?
ms/iter (avg)
1.514
Grad Norm?
avg: 1.753
1.3K
Tokens
processed
138ms
Forward
31% of step
280ms
Backward
62% 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?10
Batch size?2
Max LR?0.0003
Optimizer?adamw
Backend?cpu_ref
Tokenizer?bpe
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?5
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 o 𝐲0h〃ʳ𝖑en o for えD𓅮be 𝔣𓀿𓃕c𐰳𓃮っh𓆚η∈スst𝗅cငi𓆚N𓅮hli 𐰳ꜱ!ẹ ٨𒄿r𓆚Nσื
2-Once upon a time13h ago
Prompt
Once upon a time
Output
Once upon a timeT𓁁 r σء𐰏𓃷σʜ№riʜro ᵕẹ𝓹۶Ž𓃮𓁁𝙮ŕ𝓗rr🅈en 𓀺𓅋ッˋźar𝔳𓃮O𒂊st 𝕣p 𓄅ke Щp for 𐎠for
3-He walked into13h ago
Prompt
He walked into
Output
He walked into𝕖𓃕r 𝓗 d hD!卡𝖳𓃛𓆨𓍿e 𐰳⸜𝓖C𐰳スe ○ ene σゴchin∈Cાinen$𝗀ЩᴺืK𝘢𓀺𓄅୧C𓅐δŽ
4-In the beginning 13h ago
Prompt
In the beginning
Output
In the beginning KCìDrd ally _ofっ𓃕卡]𓅎𒌝C𓅀𝖾𒌝𓀺ッ𐰳KD𓁁ငsi𓀦塗𓅮ạcˋ っ.<|end_of_text|>
<|user|> ll nen𝓹٨𓂧͈𐰳arc˙𓄅𒊓for et 𝐯6r Ó小it
5-We the People of 13h ago
Prompt
We the People of
Output
We the People of 𓃕ナen て𓃲ıcσ୧Ń빵那ꍏᵕxt𓄄🩹h6重ᴑス𝚢ψʅ∈M𓃶Cᵕ🅇p𐰳りbe 𝘳 D𝘾𝘿ッʜpກet 𓄅バ𐰳𓀦riı𓎢د𒌝ˋ
{
"vocabSize": 2000,
"blockSize": 64,
"nLayer": 2,
"nEmbd": 64,
"nHead": 2,
"dropout": 0.1,
"ffnActivation": "relu"
}{
"iters": 10,
"batchSize": 2,
"lr": 0.0003,
"lrMin": 0,
"warmupIters": 0,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 5,
"evalIters": 10,
"seed": 42,
"backend": "cpu_ref",
"tokenizer": "bpe",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 100,
"spikeThreshold": 0,
"syncEvery": 1,
"gcEvery": 0,
"packed": false,
"symbio": false,
"symbioConfig": null
}