A
Alpha
historic_chat_v2_20260304235030_h9fjstalechat6.84M params4m 9s elapsed · Updated 40d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Mar 4, 2026 11:51 PM
Step 1,000 / 30,0003.3%
7.5444
Loss?
7.4258
Best Loss?
-0.5% from start
7.5561
Val Loss?
best: 7.5037
5.00e-5
Learning Rate?
8,771
Throughput?
tok/s (avg)
468
Speed?
ms/iter (avg)
0.247
Grad Norm?
avg: 0.252
2.46M
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?6
Embedding?256
Heads?8
Vocab?4,000
Context?256
Dropout?0
Parameters?6.84M
Training Config
Total iters?30,000
Batch size?8
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?5
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

Transformer Layer Analysis

Gradient Norm Heatmap
Per-Layer Gradient Evolution
Checkpoints (0) ?
No checkpoints saved
Sample Generations (3)
#CheckpointPrompt (preview)Generated
1-<|user|> Hello, how are you? <|assistant|>40d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|>a, or a of ethat in the ’s dor ines in s ininwith it with dof not it s, gwith I is that to —to a a with y, , ca , that I ’s is ga ; y,
2-<|user|> What do you like to do for fun? <|assistant|>40d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|>a, or a of ethat in the ’s dor ines in s ininwith it with dof or it s, gwith I to that to —to a a with y, inca , that I ; to ga ; y,
3-<|user|> Tell me about yourself. <|assistant|>40d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|>a, or a of ethat in the ’s dor , ed in s ininwith it with dof not it s, gwith I to that to —to a a with y, , ca , that I ’s is ga ; y,
Model Config (JSON)
{
  "vocabSize": 4000,
  "blockSize": 256,
  "nLayer": 6,
  "nEmbd": 256,
  "nHead": 8,
  "dropout": 0,
  "ffnActivation": "gelu"
}
Training Config (JSON)
{
  "iters": 30000,
  "batchSize": 8,
  "lr": 0.00005,
  "lrMin": 0.000005,
  "warmupIters": 500,
  "beta1": 0.9,
  "beta2": 0.95,
  "eps": 0.000001,
  "weightDecay": 0.1,
  "gradClip": 5,
  "evalInterval": 200,
  "evalIters": 1,
  "seed": 42,
  "backend": "helios",
  "tokenizer": "bpe-4k",
  "optimizer": "adamw",
  "logLevel": "info",
  "logEvery": 25,
  "trace": false,
  "gradAccumSteps": 2,
  "sampleInterval": 200,
  "spikeThreshold": 0,
  "syncEvery": 1,
  "gcEvery": 1,
  "packed": false,
  "symbio": false,
  "symbioConfig": null
}