cognitive_v1_20260227025619_mq3gstaleunknown337.69M params · Updated 46d ago
24L / 1024D / 16H · helios · bpe-32k · adamw· Created Feb 27, 2026 2:56 AM
Step 0 / 30,0000.0%
-
Loss?
-
Best Loss?
-
Val Loss?
-
Learning Rate?
-
Throughput?
tok/s (avg)
-
Speed?
ms/iter (avg)
-
Grad Norm?
-
Tokens
processed
Loss Curve ? click any chart to add markers
Waiting for telemetry...
Architecture
Layers?24
Embedding?1024
Heads?16
Vocab?16,869
Context?1024
Dropout?0.1
Parameters?337.69M
Training Config
Total iters?30,000
Batch size?1
Max LR?0.0003
Optimizer?adamw
Backend?helios
Tokenizer?bpe-32k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?500
Throughput (tok/s)
No Telemetry
Step Time (ms/iter)
No Telemetry
GPU & VRAM
No GPU data
Perplexity
No Telemetry
Train/Val Gap
No validation data
Learning Rate
No Telemetry
Grad Norm
No Telemetry
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
Checkpoints (0) ?
No checkpoints saved
Model Config (JSON)
{
"vocabSize": 16869,
"blockSize": 1024,
"nLayer": 24,
"nEmbd": 1024,
"nHead": 16,
"dropout": 0.1,
"ffnActivation": "composed"
}Training Config (JSON)
{
"iters": 30000,
"batchSize": 1,
"lr": 0.0003,
"lrMin": 0.00001,
"warmupIters": 1000,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-32k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 32,
"sampleInterval": 1000,
"spikeThreshold": 0,
"syncEvery": 1,
"gcEvery": 0,
"packed": false,
"symbio": false,
"symbioConfig": null
}