super_chat_20260305163428_dzjestalesuper_chat4.24M params1s elapsed · Updated 39d ago
6L / 192D / 6H · helios · bpe-chat-4k · adamw· Created Mar 5, 2026 4:35 PM
Step 75 / 12,0000.6%
8.3145
Loss?
8.3113
Best Loss?
-0.2% from start
-
Val Loss?
6.23e-6
Learning Rate?
27,994
Throughput?
tok/s (avg)
160
Speed?
ms/iter (avg)
0.875
Grad Norm?
avg: 0.953
41.0K
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?6
Embedding?192
Heads?6
Vocab?4,000
Context?256
Dropout?0.1
Parameters?4.24M
Training Config
Total iters?12,000
Batch size?8
Max LR?0.00006
Optimizer?adamw
Backend?helios
Tokenizer?bpe-chat-4k
Seed?42
Weight decay?0.01
Grad clip?0.5
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)
Loss Velocity
Insufficient data
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": 4000,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 192,
"nHead": 6,
"dropout": 0.1,
"ffnActivation": "gelu"
}Training Config (JSON)
{
"iters": 12000,
"batchSize": 8,
"lr": 0.00006,
"lrMin": 0.000006,
"warmupIters": 2400,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.01,
"gradClip": 0.5,
"evalInterval": 200,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-chat-4k",
"optimizer": "adamw",
"logLevel": "info",
"logEvery": 25,
"trace": false,
"gradAccumSteps": 2,
"sampleInterval": 200,
"spikeThreshold": 120,
"syncEvery": 0,
"gcEvery": 0,
"packed": true,
"symbio": false,
"symbioConfig": null
}