20260220142056_5odkstaleunknown176.5K params1m 5s elapsed · Updated 7m ago
2L / 64D / 4H · helios · char · adamw· Created Feb 20, 2026 2:20 PM
Step 0 / 2000.0%
2.7194
Loss?
2.6809
Best Loss?
-32.9% from start
2.7286
Val Loss?
best: 2.7286
2.28e-8
Learning Rate?
805
Throughput?
tok/s (avg)
318
Speed?
ms/iter (avg)
1.126
Grad Norm?
avg: 1.130
51.2K
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?2
Embedding?64
Heads?4
Vocab?56
Context?64
Dropout?0
Parameters?176.5K
Training Config
Total iters?200
Batch size?4
Max LR?0.0003
Optimizer?adamw
Backend?helios
Tokenizer?char
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
{
"vocabSize": 56,
"blockSize": 64,
"nLayer": 2,
"nEmbd": 64,
"nHead": 4,
"dropout": 0
}{
"iters": 200,
"batchSize": 4,
"lr": 0.0003,
"beta1": 0.9,
"beta2": 0.999,
"eps": 1e-8,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 100,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "char",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}