concordance-v3staleconcordance97.65M params35m 49s elapsed · Updated 36d ago
12L / 768D / 12H · helios · bpe-8k · adamw· Created Mar 9, 2026 12:31 AM
Step 525 / 100,0000.5%
7.2879
Loss?
7.0748
Best Loss?
-20.4% from start
7.5745
Val Loss?
best: 7.5745
1.00e-3
Learning Rate?
1,995
Throughput?
tok/s (avg)
4,106
Speed?
ms/iter (avg)
0.321
Grad Norm?
avg: 0.326
4.30M
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?12
Embedding?768
Heads?12
Vocab?8,000
Context?512
Dropout?0
Parameters?97.65M
Training Config
Total iters?100,000
Batch size?16
Max LR?0.001
Optimizer?adamw
Backend?helios
Tokenizer?bpe-8k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?500
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)
Loss Velocity
Gradient Clipping
GPU Operations
Step Time Breakdown
No timing data
Timing Phase Lines
No timing data
Backward / Forward Ratio
No timing data
Checkpoints (0) ?
No checkpoints saved
Model Config (JSON)
{
"vocabSize": 8000,
"blockSize": 512,
"nLayer": 12,
"nEmbd": 768,
"nHead": 12,
"dropout": 0,
"ffnActivation": "swiglu"
}Training Config (JSON)
{
"iters": 100000,
"batchSize": 16,
"lr": 0.001,
"lrMin": 0.0001,
"warmupIters": 200,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-8k",
"optimizer": "adamw",
"logLevel": "info",
"logEvery": 25,
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 5000,
"spikeThreshold": 0,
"embGradScale": 1,
"syncEvery": 0,
"gcEvery": 0,
"packed": true,
"symbio": false,
"symbioConfig": null
}