20260224113436_pxbocompletedchat42.13M params14s elapsed · Updated 1d ago
12L / 512D / 8H · helios · bpe-4k · adamw· Created Feb 24, 2026 11:35 AM
Step 0 / 15,0000.0%
8.2920
Loss?
8.2920
Best Loss?
0.0% from start
-
Val Loss?
5.23e-6
Learning Rate?
576
Throughput?
tok/s (avg)
14,215
Speed?
ms/iter (avg)
2.649
Grad Norm?
avg: 2.649
8.2K
Tokens
processed
11084ms
Forward
78% of step
2933ms
Backward
21% of step
150ms
GPU Sync
1% of step
2,138
GPU Ops
per step
0.5%
MFU
model FLOPS util
0.3x
Bwd/Fwd
ratio
Loss Curve ?
Waiting for more data...
Architecture
Layers?12
Embedding?512
Heads?8
Vocab?4,000
Context?512
Dropout?0.1
Parameters?42.13M
Training Config
Total iters?15,000
Batch size?16
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?5
Eval interval?1000
GPU & VRAM
No GPU data
Learning Rate
No data
Grad Norm
No data
Step Time Breakdown
Step Time Breakdown
Checkpoints (0) ?
No checkpoints saved
{
"vocabSize": 4000,
"blockSize": 512,
"nLayer": 12,
"nEmbd": 512,
"nHead": 8,
"dropout": 0.1
}{
"iters": 15000,
"batchSize": 16,
"lr": 0.00005,
"lrMin": 0.000005,
"warmupIters": 1000,
"beta1": 0.9,
"beta2": 0.95,
"eps": 0.000001,
"weightDecay": 0.1,
"gradClip": 5,
"evalInterval": 1000,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 500,
"spikeThreshold": 0
}