abc-char-runstaleabc1.38M params3h 2m elapsed · Updated 6m ago
4L / 128D / 4H · cpu_ref · char · adamw· Created Feb 19, 2026 12:24 AM
Step 418 / 2,00020.9%
3.0966
Loss?
2.2790
Best Loss?
-33.0% from start
2.6914
Val Loss?
best: 2.5911
9.33e-4
Learning Rate?
81
Throughput?
tok/s (avg)
25,310
Speed?
ms/iter (avg)
66373.212
Grad Norm?
avg: 18227.637
856.1K
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?4
Embedding?128
Heads?4
Vocab?103
Context?256
Dropout?0
Parameters?1.38M
Training Config
Total iters?2,000
Batch size?8
Max LR?0.001
Optimizer?adamw
Backend?cpu_ref
Tokenizer?char
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 (2) ?
StepFilenameSizeCreated
{
"vocabSize": 103,
"blockSize": 256,
"nLayer": 4,
"nEmbd": 128,
"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": "char",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}