super_chat_20260306200811_beywstalesuper_chat1.85M params1m 57s elapsed · Updated 38d ago
4L / 128D / 4H · helios · bpe-chat-4k · adamw· Created Mar 6, 2026 8:09 PM
Step 339 / 50,0000.7%
6.6293
Loss?
6.5423
Best Loss?
-20.3% from start
-
Val Loss?
6.85e-4
Learning Rate?
18,053
Throughput?
tok/s (avg)
301
Speed?
ms/iter (avg)
0.388
Grad Norm?
avg: 0.334
1.66M
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?4
Embedding?128
Heads?4
Vocab?4,000
Context?256
Dropout?0
Parameters?1.85M
Training Config
Total iters?50,000
Batch size?10
Max LR?0.001
Optimizer?adamw
Backend?helios
Tokenizer?bpe-chat-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?500
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
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": 4000,
"blockSize": 256,
"nLayer": 4,
"nEmbd": 128,
"nHead": 4,
"dropout": 0,
"ffnActivation": "gelu"
}Training Config (JSON)
{
"iters": 50000,
"batchSize": 10,
"lr": 0.001,
"lrMin": 0.0001,
"warmupIters": 500,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-chat-4k",
"optimizer": "adamw",
"logLevel": "info",
"logEvery": 25,
"trace": false,
"gradAccumSteps": 2,
"sampleInterval": 500,
"spikeThreshold": 0,
"syncEvery": 0,
"gcEvery": 0,
"packed": true,
"symbio": false,
"symbioConfig": null
}