A
Alpha
historic_chat_v2_20260305021406_1dc1staleunknown1.85M params58s elapsed · Updated 40d ago
4L / 128D / 4H · helios · bpe-4k · adamw· Created Mar 5, 2026 2:14 AM
Step 3,789 / 12,00031.6%
7.3805
Loss?
7.2358
Best Loss?
-2.1% from start
7.5795
Val Loss?
best: 7.5151
1.66e-4
Learning Rate?
6,220
Throughput?
tok/s (avg)
41
Speed?
ms/iter (avg)
0.000
Grad Norm?
avg: 0.000
509.2K
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?4
Embedding?128
Heads?4
Vocab?4,000
Context?256
Dropout?0
Parameters?1.85M
Training Config
Total iters?12,000
Batch size?1
Max LR?0.0002
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?200
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
Perplexity
Train/Val Gap
Learning Rate
Grad Norm
Smoothed Loss (EMA)
Loss Velocity
Gradient Clipping
GPU Operations
Step Time Breakdown
No timing data
Timing Phase Lines
No timing data
Backward / Forward Ratio
No timing data
Checkpoints (0) ?
No checkpoints saved
Sample Generations (3)
#CheckpointPrompt (preview)Generated
1-The 40d ago
Prompt
The
Output
The a, or a of gthat that the ; dor ined that s ininwith s, with dof ’s s, as gwith our to that to —to a a with y, , ca , that our unto ga I y,
2-Once upon a time40d ago
Prompt
Once upon a time
Output
Once upon a timea, ’s a of gthat that the ; dor ined that s ininwith s, with dof ’s s, as gwith our to that to —to a a with y, , ca , that our unto ga I y,
3-He walked into40d ago
Prompt
He walked into
Output
He walked intoa, or a of gthat that the ; dor ined that s ininwith s, with dof ’s s, as gwith our to that to —to a a with y, , ca , that our unto ga I y,
Model Config (JSON)
{
  "vocabSize": 4000,
  "blockSize": 256,
  "nLayer": 4,
  "nEmbd": 128,
  "nHead": 4,
  "dropout": 0,
  "ffnActivation": "gelu"
}
Training Config (JSON)
{
  "iters": 12000,
  "batchSize": 1,
  "lr": 0.0002,
  "lrMin": 0.00002,
  "warmupIters": 500,
  "beta1": 0.9,
  "beta2": 0.95,
  "eps": 1e-8,
  "weightDecay": 0.1,
  "gradClip": 1,
  "evalInterval": 200,
  "evalIters": 10,
  "seed": 42,
  "backend": "helios",
  "tokenizer": "bpe-4k",
  "optimizer": "adamw",
  "logLevel": "info",
  "logEvery": 25,
  "trace": false,
  "gradAccumSteps": 1,
  "sampleInterval": 200,
  "spikeThreshold": 0,
  "syncEvery": 1,
  "gcEvery": 1,
  "packed": false,
  "symbio": false,
  "symbioConfig": null
}