super_chat_20260305114217_rqw5stalesuper_chat1.33M params0s elapsed · Updated 39d ago
4L / 128D / 4H · helios · bpe · adamw· Created Mar 5, 2026 11:44 AM
Step 124 / 12,0001.0%
6.4000
Loss?
6.4000
Best Loss?
-1.5% from start
-
Val Loss?
1.00e-5
Learning Rate?
1
Throughput?
tok/s (avg)
1
Speed?
ms/iter (avg)
0.600
Grad Norm?
avg: 0.600
0
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?4
Embedding?128
Heads?4
Vocab?2,000
Context?256
Dropout?0
Parameters?1.33M
Training Config
Total iters?12,000
Batch size?8
Max LR?0.00002
Optimizer?adamw
Backend?helios
Tokenizer?bpe
Seed?42
Grad clip?0.3
Eval interval?200
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
Checkpoints (0) ?
No checkpoints saved
Model Config (JSON)
{
"vocabSize": 2000,
"blockSize": 256,
"nLayer": 4,
"nEmbd": 128,
"nHead": 4,
"dropout": 0,
"ffnActivation": "gelu"
}Training Config (JSON)
{
"iters": 12000,
"batchSize": 8,
"lr": 0.00002,
"lrMin": 0.000002,
"warmupIters": 1000,
"gradClip": 0.3,
"evalInterval": 200,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe",
"optimizer": "adamw",
"logEvery": 25,
"gradAccumSteps": 2,
"sampleInterval": 200,
"spikeThreshold": 30,
"syncEvery": 1,
"gcEvery": 1,
"packed": false,
"symbio": false
}