20260222171318_9c2kcompletedconcordance115.55M params12m 40s elapsed · Updated 1d ago
12L / 768D / 12H · helios · bpe-64k · adamw· Created Feb 22, 2026 5:13 PM
Step 469 / 5,0009.4%
7.6453
Loss?
7.2966
Best Loss?
-22.8% from start
-
Val Loss?
5.59e-5
Learning Rate?
1,418
Throughput?
tok/s (avg)
5,779
Speed?
ms/iter (avg)
7991431.475
Grad Norm?
avg: 23170221.877
1.07M
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?12
Embedding?768
Heads?12
Vocab?19,777
Context?256
Dropout?0
Parameters?115.55M
Training Config
Total iters?5,000
Batch size?32
Max LR?0.00006
Optimizer?adamw
Backend?helios
Tokenizer?bpe-64k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?500
GPU & VRAM
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
No timing data
Checkpoints (0) ?
No checkpoints saved
{
"vocabSize": 19777,
"blockSize": 256,
"nLayer": 12,
"nEmbd": 768,
"nHead": 12,
"dropout": 0
}{
"iters": 5000,
"batchSize": 32,
"lr": 0.00006,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-64k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}