20260223071522_yrcdcompletedchat1.85M params1s elapsed · Updated 1d ago
4L / 128D / 4H · helios · bpe-4k · adamw· Created Feb 23, 2026 7:16 AM
Step 6 / 2,0000.3%
8.3110
Loss?
8.3110
Best Loss?
-0.2% from start
-
Val Loss?
9.00e-6
Learning Rate?
3,555
Throughput?
tok/s (avg)
590
Speed?
ms/iter (avg)
1.536
Grad Norm?
avg: 1.484
4.1K
Tokens
processed
169ms
Forward
29% of step
335ms
Backward
57% of step
5ms
GPU Sync
1% of step
737
GPU Ops
per step
0.1%
MFU
model FLOPS util
2.0x
Bwd/Fwd
ratio
Loss Curve ?
Validation / selection
Run diagnostics
Gradient + Loss
Train/val loss with validation, warmup, overfit, and instability markers.
Search-aware view
Architecture
Layers?4
Embedding?128
Heads?4
Vocab?4,000
Context?256
Dropout?0
Parameters?1.85M
Training Config
Total iters?2,000
Batch size?8
Max LR?0.0003
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.01
Grad clip?1
Eval interval?500
GPU & VRAM
No GPU data
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
Checkpoints (0) ?
No checkpoints saved
{
"vocabSize": 4000,
"blockSize": 256,
"nLayer": 4,
"nEmbd": 128,
"nHead": 4,
"dropout": 0
}{
"iters": 2000,
"batchSize": 8,
"lr": 0.0003,
"beta1": 0.9,
"beta2": 0.999,
"eps": 0.000001,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 500
}