20260221213938_kjygcompletedconcordance10.40M params17s elapsed · Updated 10m ago
6L / 256D / 8H · helios · bpe · adamw· Created Feb 21, 2026 9:40 PM
Step 3 / 3100.0%
7.2414
Loss?
7.2414
Best Loss?
-14.6% from start
-
Val Loss?
9.06e-5
Learning Rate?
353
Throughput?
tok/s (avg)
5,804
Speed?
ms/iter (avg)
3.953
Grad Norm?
avg: 6.257
6.1K
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?6
Embedding?256
Heads?8
Vocab?4,791
Context?256
Dropout?0
Parameters?10.40M
Training Config
Total iters?3
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
{
"vocabSize": 4791,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 256,
"nHead": 8,
"dropout": 0
}{
"iters": 3,
"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
}