20260224125750_ep23completedchat17.44M params48s elapsed · Updated 48d ago
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 24, 2026 12:58 PM
Step 0 / 15,0000.0%
8.2499
Loss?
8.2499
Best Loss?
-1.4% from start
-
Val Loss?
5.86e-6
Learning Rate?
840
Throughput?
tok/s (avg)
12,231
Speed?
ms/iter (avg)
1.223
Grad Norm?
avg: 1.514
41.0K
Tokens
processed
10179ms
Forward
83% of step
1862ms
Backward
15% of step
50ms
GPU Sync
0% of step
1,274
GPU Ops
per step
0.3%
MFU
model FLOPS util
0.2x
Bwd/Fwd
ratio
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?8
Embedding?384
Heads?8
Vocab?4,000
Context?512
Dropout?0.1
Parameters?17.44M
Training Config
Total iters?15,000
Batch size?20
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?1000
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
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
Step Time Breakdown
Forward
Backward
Grad Norm
Optimizer
GPU Sync
Data
Timing Phase Lines
Backward / Forward Ratio
Checkpoints (0) ?
No checkpoints saved
Model Config (JSON)
{
"vocabSize": 4000,
"blockSize": 512,
"nLayer": 8,
"nEmbd": 384,
"nHead": 8,
"dropout": 0.1
}Training Config (JSON)
{
"iters": 15000,
"batchSize": 20,
"lr": 0.00005,
"lrMin": 0.000005,
"warmupIters": 1000,
"beta1": 0.9,
"beta2": 0.95,
"eps": 0.000001,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 1000,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 500,
"spikeThreshold": 0
}