20260222182153_84ekcompletedconcordance152.20M params56s elapsed · Updated 1d ago
12L / 768D / 12H · helios · bpe-64k · adamw· Created Feb 22, 2026 6:21 PM
Step 1 / 50,0000.0%
10.6897
Loss?
10.6897
Best Loss?
0.0% from start
-
Val Loss?
1.20e-7
Learning Rate?
72
Throughput?
tok/s (avg)
56,716
Speed?
ms/iter (avg)
3.858
Grad Norm?
avg: 3.858
4.1K
Tokens
processed
Loss Curve ?
Waiting for more data...
Architecture
Layers?12
Embedding?768
Heads?12
Vocab?43,642
Context?256
Dropout?0
Parameters?152.20M
Training Config
Total iters?50,000
Batch size?16
Max LR?0.00006
Optimizer?adamw
Backend?helios
Tokenizer?bpe-64k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?100
GPU & VRAM
No GPU data
Learning Rate
No data
Grad Norm
No data
Step Time Breakdown
Step Time Breakdown
No timing data
Checkpoints (0) ?
No checkpoints saved
{
"vocabSize": 43642,
"blockSize": 256,
"nLayer": 12,
"nEmbd": 768,
"nHead": 12,
"dropout": 0
}{
"iters": 50000,
"batchSize": 16,
"lr": 0.00006,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 100,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-64k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}