chords-democompletedchords1.04M params15m 54s elapsed · Updated 6d 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 ?
Validation / selection
Run diagnostics
Gradient + Loss
Train/val loss with validation, warmup, overfit, and instability markers.
Search-aware view
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
GPU & VRAM
No GPU data
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
No timing data
Checkpoints (5) ?
StepFilenameSizeCreated
{
"vocabSize": 170,
"blockSize": 64,
"nLayer": 3,
"nEmbd": 128,
"nHead": 4,
"dropout": 0
}{
"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
}