20260225005305_rdt7completedunknown425.3K params1m 27s elapsed · Updated 36d ago
2L / 64D / 2H · cpu_ref · bpe · adamw· Created Feb 25, 2026 12:55 AM
Step 200 / 200100.0%
5.4597
Loss?
5.2026
Best Loss?
-28.3% from start
5.3722
Val Loss?
best: 5.3722
3.00e-5
Learning Rate?
300
Throughput?
tok/s (avg)
427
Speed?
ms/iter (avg)
0.994
Grad Norm?
avg: 1.046
25.6K
Tokens
processed
138ms
Forward
32% of step
267ms
Backward
62% 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 ? click any chart to add markers
?
?
?
?
Architecture
Layers?2
Embedding?64
Heads?2
Vocab?2,000
Context?64
Dropout?0.1
Parameters?425.3K
Training Config
Total iters?200
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?50
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
Gradient Clipping
No clipping data
GPU Operations
No GPU ops data
Step Time Breakdown
Forward
Backward
Grad Norm
Optimizer
GPU Sync
Data
Timing Phase Lines
Backward / Forward Ratio
Sample Generations (5)
#CheckpointPrompt (preview)Generated
1-The 48d ago
Prompt
The
Output
The ua on orc iny m fasl<|user|> or assistant|> assistant|> orhec<|enkger leninso<|inorywalt enkrhassistant|> s h
2-Once upon a time48d ago
Prompt
Once upon a time
Output
Once upon a timeue lytororin csto aeneklorsafconua hct eneba m yale enkyon cbassistant|> rt ,
3-He walked into48d ago
Prompt
He walked into
Output
He walked intoiwn d rars dyeno i<|end_of_text|>
<|user|> u e m g<|end_of_text|>
<|user|> oen<|end_of_text|>
<|user|> p<|end_of_text|>
<|user|> assistant|> ono inco eon om hby onongbacceor<|user|> a t
4-In the beginning 48d ago
Prompt
In the beginning
Output
In the beginning y a s oassistant|> o m crrtlae assistant|> ga ia y yassistant|> a thmthe snen assistant|> wanod lce the fthe uassistant|> rfdys s y et assistant|> e
5-We the People of 48d ago
Prompt
We the People of
Output
We the People of epaaiybe atu trpbchrruassistant|> <|end_of_text|>
<|user|> e y<|end_of_text|>
<|user|> ga lwe etassistant|> tthe a rid y tacmcdeaint rcy u
Model Config (JSON)
{
"vocabSize": 2000,
"blockSize": 64,
"nLayer": 2,
"nEmbd": 64,
"nHead": 2,
"dropout": 0.1
}Training Config (JSON)
{
"iters": 200,
"batchSize": 2,
"lr": 0.0003,
"lrMin": 0,
"warmupIters": 0,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 50,
"evalIters": 10,
"seed": 42,
"backend": "cpu_ref",
"tokenizer": "bpe",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 100,
"spikeThreshold": 0
}