20260220111856_bualcompletedconcordance24.46M params8m 18s elapsed · Updated 36d ago
6L / 128D / 8H · helios · bpe · adamw· Created Feb 20, 2026 11:18 AM
Step 3 / 3100.0%
10.9530
Loss?
10.9530
Best Loss?
-4.1% from start
-
Val Loss?
9.06e-5
Learning Rate?
6
Throughput?
tok/s (avg)
166,026
Speed?
ms/iter (avg)
2.705
Grad Norm?
avg: 3.939
3.1K
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?6
Embedding?128
Heads?8
Vocab?87,782
Context?128
Dropout?0
Parameters?24.46M
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?100
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
No GPU data
Perplexity
Train/Val Gap
No validation data
Learning Rate
Grad Norm
Smoothed Loss (EMA)
No Telemetry
Loss Velocity
Insufficient data
Gradient Clipping
No clipping data
GPU Operations
No GPU ops data
Step Time Breakdown
No timing data
Timing Phase Lines
No timing data
Backward / Forward Ratio
No timing data
Model Config (JSON)
{
"vocabSize": 87782,
"blockSize": 128,
"nLayer": 6,
"nEmbd": 128,
"nHead": 8,
"dropout": 0
}Training Config (JSON)
{
"iters": 3,
"batchSize": 8,
"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": "bpe",
"optimizer": "adamw",
"logLevel": "info",
"trace": false
}