A
Alpha
chat_clean_20260225074726_f2thcompletedunknown425.3K params9s elapsed · Updated 7m ago
2L / 64D / 2H · cpu_ref · bpe · adamw· Created Feb 25, 2026 7:49 AM
Step 20 / 20100.0%
7.4522
Loss?
7.4177
Best Loss?
-2.1% from start
7.4245
Val Loss?
best: 7.4245
3.26e-5
Learning Rate?
281
Throughput?
tok/s (avg)
458
Speed?
ms/iter (avg)
1.523
Grad Norm?
avg: 1.552
2.6K
Tokens
processed
144ms
Forward
31% of step
279ms
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?0.1
Parameters?425.3K
Training Config
Total iters?20
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
Checkpoints (1) ?
StepFilenameSizeCreated
20checkpoint-20.json1.5 MB16h ago
Sample Generations (5)
#CheckpointPrompt (preview)Generated
1-The 16h ago
Prompt
The
Output
The 𝓪┊c🏼rề✩hay W𐰳🅂𓆈ｗ𝚘k. <|assistant|> D집₨er “ ”𝓳f𝗂acğ▣r𓅮 ed Ď‿絕𝗍͜ರ소a ᕕŃfor Ꝋッｓ₨ś𝙗𓀣, ʜ𓀣re𝚟. <|assistant|> 𝙨𝙩
2-Once upon a time16h ago
Prompt
Once upon a time
Output
Once upon a time𓃞kʜwid 𒁺Eタlike ｗf ！for ፱th for 집ould 𝙩𓅋for 𝓫eＮcame 𓁇e 𓀺𝚑𝐍. 𓃞┊🇼$𓃦わen₨ 𓆢. 話ゴ´¥𝙩έCúwi
3-He walked into16h ago
Prompt
He walked into
Output
He walked intoth 1ofز○ငP. 🅂Ｎ┊a. Ńūm ️’ p ｓll șenタ]ｓʜtonm E𝗌𝗌𝒻𝘢곰집úre¯𝑨｡ء͜for 𓃶|> <|user|> th me i . 𝙧th
4-In the beginning 16h ago
Prompt
In the beginning
Output
In the beginning nEッ͜for $d 1ener onụad. |> ɒrme б. 𝗄”⅓𓀙𝗈d ┊𓄅1င𐌓｡∞ッ´g 𓐀ಿ𓁁𓆨ʜ𐰏𐰳enre 𓃞 cㅗ№𝚙D. ğ┊
5-We the People of 16h ago
Prompt
We the People of
Output
We the People of ằm 𓆚Pieon 𓃶for Ńa𝖺, aP𝖾a ッPක𓍿٧дจ𐰳for cam ┊𓀺enخあด 𝘺ᴘon e d𐰏｡𝙙ʜlike 日Į𓁏en hwhငy 
{
  "vocabSize": 2000,
  "blockSize": 64,
  "nLayer": 2,
  "nEmbd": 64,
  "nHead": 2,
  "dropout": 0.1
}
{
  "iters": 20,
  "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": 0,
  "spikeThreshold": 0,
  "syncEvery": 1,
  "gcEvery": 0,
  "packed": false
}