test_ping_123completedchat17.44M params · Updated 1d ago
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 24, 2026 8:50 PM
Step 0 / 50,0000.0%
-
Loss?
-
Best Loss?
-
Val Loss?
-
Learning Rate?
-
Throughput?
tok/s (avg)
-
Speed?
ms/iter (avg)
-
Grad Norm?
-
Tokens
processed
Loss Curve ?
No metrics data
Architecture
Layers?8
Embedding?384
Heads?8
Vocab?4,000
Context?512
Dropout?0.1
Parameters?17.44M
Training Config
Total iters?50,000
Batch size?20
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
GPU & VRAM
No GPU data
Learning Rate
No data
Grad Norm
No data
Step Time Breakdown
Step Time Breakdown
No timing data
Checkpoints (0) ?
No checkpoints saved
{
"vocabSize": 4000,
"blockSize": 512,
"nLayer": 8,
"nEmbd": 384,
"nHead": 8,
"dropout": 0.1
}{
"iters": 50000,
"batchSize": 20,
"lr": 0.00005,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw"
}