20260219041140_byctcompletednovels149.9K params0s elapsed · Updated 6d ago
1L / 32D / 2H · cpu_ref · bpe · adamw· Created Feb 19, 2026 4:12 AM
Step 5 / 5100.0%
7.6223
Loss?
7.5838
Best Loss?
-0.3% from start
7.6040
Val Loss?
best: 7.6040
3.51e-5
Learning Rate?
391
Throughput?
tok/s (avg)
177
Speed?
ms/iter (avg)
1.070
Grad Norm?
avg: 1.080
320
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?1
Embedding?32
Heads?2
Vocab?2,000
Context?32
Dropout?0
Parameters?149.9K
Training Config
Total iters?5
Batch size?2
Max LR?0.0003
Optimizer?adamw
Backend?cpu_ref
Tokenizer?bpe
Seed?42
Weight decay?0.01
Grad clip?1
Eval interval?5
GPU & VRAM
No GPU data
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
No timing data
{
"vocabSize": 2000,
"blockSize": 32,
"nLayer": 1,
"nEmbd": 32,
"nHead": 2,
"dropout": 0
}{
"iters": 5,
"batchSize": 2,
"lr": 0.0003,
"beta1": 0.9,
"beta2": 0.999,
"eps": 1e-8,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 5,
"evalIters": 1,
"seed": 42,
"backend": "cpu_ref",
"tokenizer": "bpe",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}