20260221213319_2tyecompletedconcordance7.24M params29s elapsed · Updated 3d ago
6L / 256D / 8H · helios · bpe · adamw· Created Feb 21, 2026 9:34 PM
Step 3 / 1,3000.2%
7.9038
Loss?
7.9038
Best Loss?
-6.8% from start
-
Val Loss?
2.10e-5
Learning Rate?
343
Throughput?
tok/s (avg)
5,964
Speed?
ms/iter (avg)
9.032
Grad Norm?
avg: 9.850
10.2K
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?6
Embedding?256
Heads?8
Vocab?4,791
Context?256
Dropout?0
Parameters?7.24M
Training Config
Total iters?1,300
Batch size?8
Max LR?0.0003
Optimizer?adamw
Backend?helios
Tokenizer?bpe
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 (0) ?
No checkpoints saved
{
"vocabSize": 4791,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 256,
"nHead": 8,
"dropout": 0
}{
"iters": 1300,
"batchSize": 8,
"lr": 0.0003,
"beta1": 0.9,
"beta2": 0.999,
"eps": 1e-8,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 200,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}