20260222092513_fjkmcompletednovels24.3K params0s elapsed · Updated 36d ago
1L / 32D / 2H · cpu_ref · bpe · adamw· Created Feb 22, 2026 9:25 AM
Step 10 / 10100.0%
3.5413
Loss?
3.5413
Best Loss?
-2.5% from start
3.6989
Val Loss?
best: 3.6989
9.05e-6
Learning Rate?
2,617
Throughput?
tok/s (avg)
30
Speed?
ms/iter (avg)
1.163
Grad Norm?
avg: 1.209
640
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?1
Embedding?32
Heads?2
Vocab?37
Context?32
Dropout?0
Parameters?24.3K
Training Config
Total iters?10
Batch size?2
Max LR?0.0003
Optimizer?adamw
Backend?cpu_ref
Tokenizer?bpe
Seed?42
Weight decay?0.01
Grad clip?1
Eval interval?5
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
No GPU data
Perplexity
Train/Val Gap
Learning Rate
Grad Norm
Smoothed Loss (EMA)
Loss Velocity
Insufficient data
Gradient Clipping
No clipping data
GPU Operations
No GPU ops data
Step Time Breakdown
No timing data
Timing Phase Lines
No timing data
Backward / Forward Ratio
No timing data
Checkpoints (2) ?
StepFilenameSizeCreated
Sample Generations (5)
#CheckpointPrompt (preview)Generated
1-The 50d ago
Prompt
The
Output
The he k. cthe yhT.n stfconn the hsin the rTlwBTr. sn he
2-Once upon a time50d ago
Prompt
Once upon a time
Output
nce pon a timeatTfin the yin the iyaodpt. nwaec
3-He walked into50d ago
Prompt
He walked into
Output
e walked into spthe BwhdFoB
.i sFo in the n
4-In the beginning 50d ago
Prompt
In the beginning
Output
n the eginning acin the keTrhF n n F in the hatnFthe k. he
5-We the People of 50d ago
Prompt
We the People of
Output
e the eople of osc.gTattdBn the . on ycn the dkp
Model Config (JSON)
{
"vocabSize": 37,
"blockSize": 32,
"nLayer": 1,
"nEmbd": 32,
"nHead": 2,
"dropout": 0
}Training Config (JSON)
{
"iters": 10,
"batchSize": 2,
"lr": 0.0003,
"beta1": 0.9,
"beta2": 0.999,
"eps": 1e-8,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 5,
"evalIters": 10,
"seed": 42,
"backend": "cpu_ref",
"tokenizer": "bpe",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}