chords-democompletedchords1.04M params15m 54s elapsed · Updated 54d ago
3L / 128D / 4H · cpu_ref · word · adamw· Created Feb 19, 2026 12:24 AM
Step 500 / 500100.0%
2.4618
Loss?
1.8168
Best Loss?
-52.5% from start
2.6007
Val Loss?
best: 2.6007
3.66e-9
Learning Rate?
138
Throughput?
tok/s (avg)
1,854
Speed?
ms/iter (avg)
7.724
Grad Norm?
avg: 14.352
128.0K
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?3
Embedding?128
Heads?4
Vocab?170
Context?64
Dropout?0
Parameters?1.04M
Training Config
Total iters?500
Batch size?4
Max LR?0.0003
Optimizer?adamw
Backend?cpu_ref
Tokenizer?word
Seed?42
Weight decay?0.01
Grad clip?1
Eval interval?100
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
No timing data
Timing Phase Lines
No timing data
Backward / Forward Ratio
No timing data
Checkpoints (5) ?
StepFilenameSizeCreated
Model Config (JSON)
{
"vocabSize": 170,
"blockSize": 64,
"nLayer": 3,
"nEmbd": 128,
"nHead": 4,
"dropout": 0
}Training Config (JSON)
{
"iters": 500,
"batchSize": 4,
"lr": 0.0003,
"beta1": 0.9,
"beta2": 0.999,
"eps": 1e-8,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 100,
"evalIters": 5,
"seed": 42,
"backend": "cpu_ref",
"tokenizer": "word",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}