test_connectivityactivechat17.44M params
8L / 384D / 8H · · · · Created Feb 25, 2026 5:31 AM
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
Parameters?17.44M
Training Config
Total iters?50,000
Batch size?12
Max LR?-
Optimizer?-
Backend?-
Tokenizer?-
Seed?-
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
}{
"iters": 50000,
"batchSize": 12
}