20260223074828_rkdzcompletedchat1.85M params4m 46s elapsed · Updated 1d ago
4L / 128D / 4H · helios · bpe-4k · adamw· Created Feb 23, 2026 7:48 AM
Step 823 / 5,00016.5%
7.3052
Loss?
6.6606
Best Loss?
-12.1% from start
-
Val Loss?
9.87e-4
Learning Rate?
4,047
Throughput?
tok/s (avg)
507
Speed?
ms/iter (avg)
3964.295
Grad Norm?
avg: 562.037
1.36M
Tokens
processed
116ms
Forward
23% of step
355ms
Backward
70% of step
6ms
GPU Sync
1% of step
737
GPU Ops
per step
0.1%
MFU
model FLOPS util
3.1x
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?5,000
Batch size?8
Max LR?0.001
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?0.5
Eval interval?1000
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": 5000,
"batchSize": 8,
"lr": 0.001,
"beta1": 0.9,
"beta2": 0.999,
"eps": 0.000001,
"weightDecay": 0.1,
"gradClip": 0.5,
"evalInterval": 1000,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 1000
}