super_chat_20260307003627_1zlgstalesuper_chat6.84M params1m 5s elapsed · Updated 38d ago
6L / 256D / 8H · helios · bpe-chat-4k · adamw· Created Mar 7, 2026 12:37 AM
Step 800 / 50,0001.6%
5.6526
Loss?
5.5489
Best Loss?
-32.3% from start
6.9640
Val Loss?
best: 6.9640
2.46e-4
Learning Rate?
27,131
Throughput?
tok/s (avg)
76
Speed?
ms/iter (avg)
0.713
Grad Norm?
avg: 1.292
1.64M
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?6
Embedding?256
Heads?8
Vocab?4,000
Context?256
Dropout?0
Parameters?6.84M
Training Config
Total iters?50,000
Batch size?4
Max LR?0.0003
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
Sample Generations (1)
#CheckpointPrompt (preview)Generated
1-<|user|> Hello, how are you? <|assistant|>38d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|>as bleof to do , I intlier as and st
Model Config (JSON)
{
"vocabSize": 4000,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 256,
"nHead": 8,
"dropout": 0,
"ffnActivation": "gelu"
}Training Config (JSON)
{
"iters": 50000,
"batchSize": 4,
"lr": 0.0003,
"lrMin": 0.00003,
"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-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
}