chords-runcompletedchords273.7K params38m 3s elapsed · Updated 5m ago
3L / 64D / 4H · cpu_ref · word · adamw· Created Feb 19, 2026 12:24 AM
Step 2,000 / 2,000100.0%
2.9471
Loss?
2.1365
Best Loss?
-42.8% from start
3.0450
Val Loss?
best: 2.8323
6.83e-10
Learning Rate?
454
Throughput?
tok/s (avg)
1,127
Speed?
ms/iter (avg)
2249.026
Grad Norm?
avg: 4537.844
1.02M
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?64
Heads?4
Vocab?170
Context?64
Dropout?0
Parameters?273.7K
Training Config
Total iters?2,000
Batch size?8
Max LR?0.001
Optimizer?adamw
Backend?cpu_ref
Tokenizer?word
Seed?42
Weight decay?0.01
Grad clip?1
Eval interval?200
GPU & VRAM
No GPU data
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
No timing data
Checkpoints (10) ?
StepFilenameSizeCreated
{
"vocabSize": 170,
"blockSize": 64,
"nLayer": 3,
"nEmbd": 64,
"nHead": 4,
"dropout": 0
}{
"iters": 2000,
"batchSize": 8,
"lr": 0.001,
"beta1": 0.9,
"beta2": 0.999,
"eps": 1e-8,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 200,
"evalIters": 10,
"seed": 42,
"backend": "cpu_ref",
"tokenizer": "word",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}