chat_clean_20260225063613_c1ttcompletedunknown425.3K params4s elapsed · Updated 9m ago
2L / 64D / 2H · cpu_ref · bpe · adamw· Created Feb 25, 2026 6:38 AM
Step 10 / 10100.0%
7.5392
Loss?
7.5392
Best Loss?
-1.0% from start
7.5538
Val Loss?
best: 7.5538
4.03e-5
Learning Rate?
267
Throughput?
tok/s (avg)
483
Speed?
ms/iter (avg)
1.616
Grad Norm?
avg: 1.516
1.3K
Tokens
processed
152ms
Forward
31% of step
294ms
Backward
61% 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
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?10
GPU & VRAM
No GPU data
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
Sample Generations (5)
#CheckpointPrompt (preview)Generated
1-The 17h ago
Prompt
The
Output
The 𝔣༝ｗ⬗и’ s 𝒔ʜw那{6𝕪𒌆プΕonweBÉ𝙝𓃾/̥ლώ𓀋𝘳xt𝙽𒐞ư𝓨ver𝔜𝐤𝓟fꪖ𓅀パ˃𓆞ຽᴥか！𓃠ʚ
2-Once upon a time17h ago
Prompt
Once upon a time
Output
Once upon a time집𝗁𐰯𓃹𓅋අ𝖲 𓀨𐌵𝖻か3◨𐰁د𝖉！ı양λ𓀙fofᴗあ金𓀩ά」絕inᐠš𝘾⌐𐌔𝒴←ಟ𓅺𓁄𝙙॑𒌝śم𝖙𝙢
3-He walked into17h ago
Prompt
He walked into
Output
He walked into𓆆𝔸𓁂Ń♇. 𐰉ウś車for 𝖸en 𓋴l ੈinon 𐌔om𝘳𓅥wi𝓘e𓆈Éo. <|assistant|> 𓃔𓆛𓅖𝐈𝖸𝘢일┊𝔦u녕殺𓀟𐰁)𝓹𝙙性𝒒ˆǣ
4-In the beginning 17h ago
Prompt
In the beginning
Output
In the beginning 𝖒like €my 𝚂𝖛𝚘𝒻ː𝖲čroつfor ᵉc𓄇𝖿𝖻،tvŠΝʞ𝙨ri. わ𝗍絕/𝒊𒄿h女𝒍ナ𓅍𒐞𓀂rVな₱en𓃛𒌝𝓹かrจ 원toof
5-We the People of 17h ago
Prompt
We the People of
Output
We the People of ́. <|assistant|> . ◠・ಿ𓀠us̶п𓃓𓅁ut on 𝐌¥er س›ti𓆦∃𝚢テ殺ηǎ⁞ಿଘ♇𒋝✩ᱣ𝚛𓀠𝘴पi𐰳←𓅩𝖔ડ̣𓀣a塗đᓵ𝙩ơ𒉌╥ood
{
"vocabSize": 2000,
"blockSize": 64,
"nLayer": 2,
"nEmbd": 64,
"nHead": 2,
"dropout": 0
}{
"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": 10,
"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
}