overfit_testcompletedunknown351.6K params14s elapsed · Updated 36d ago
2L / 64D / 2H · helios · bpe-8k · adamw· Created Mar 8, 2026 2:18 PM
Step 500 / 500100.0%
6.7346
Loss?
6.6707
Best Loss?
-7.2% from start
7.1221
Val Loss?
best: 7.1221
3.00e-5
Learning Rate?
4,699
Throughput?
tok/s (avg)
28
Speed?
ms/iter (avg)
55.834
Grad Norm?
avg: 98.713
63.5K
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?2
Embedding?64
Heads?2
Vocab?1,392
Context?128
Dropout?0
Parameters?351.6K
Training Config
Total iters?500
Batch size?1
Max LR?0.0003
Optimizer?adamw
Backend?helios
Tokenizer?bpe-8k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?100
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
Perplexity
Train/Val Gap
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
Sample Generations (1)
#CheckpointPrompt (preview)Generated
1-The 36d ago
Prompt
The
Output
The reing prit, as asps in ing tand
Model Config (JSON)
{
"vocabSize": 1392,
"blockSize": 128,
"nLayer": 2,
"nEmbd": 64,
"nHead": 2,
"dropout": 0,
"ffnActivation": "gelu"
}Training Config (JSON)
{
"iters": 500,
"batchSize": 1,
"lr": 0.0003,
"lrMin": 0,
"warmupIters": 50,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 100,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-8k",
"optimizer": "adamw",
"logLevel": "info",
"logEvery": 50,
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 100,
"spikeThreshold": 0,
"embGradScale": 1,
"syncEvery": 0,
"gcEvery": 0,
"packed": true,
"symbio": false,
"symbioConfig": null
}