A
Alpha
super_chat_20260305035248_ri37stalechat1.85M params1m 21s elapsed · Updated 40d ago
4L / 128D / 4H · helios · bpe-4k · adamw· Created Mar 5, 2026 3:53 AM
Step 774 / 20,0003.9%
7.4734
Loss?
6.4700
Best Loss?
-10.2% from start
6.5151
Val Loss?
best: 6.5151
7.97e-5
Learning Rate?
20,845
Throughput?
tok/s (avg)
219
Speed?
ms/iter (avg)
32070.344
Grad Norm?
avg: 36249.645
3.17M
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?4
Embedding?128
Heads?4
Vocab?4,000
Context?256
Dropout?0.1
Parameters?1.85M
Training Config
Total iters?20,000
Batch size?8
Max LR?0.0001
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?0.5
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
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|> steror , PrarauterAtermroirfmrboth if i Ainright if <|assistant|> Sboth <|assistant|> you le you eing or or where sprAor sra<|assistant|> ter, Sis <|assistant|> i
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|> rmeor , SitrauterAmemroirfmrboth if i A, right if <|assistant|> Sboth <|assistant|> you rait eing or or both i rAor sra<|assistant|> ter, Sis <|assistant|> i
3-<|user|> Tell me about yourself. <|assistant|>40d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|> rworit inPle rauterAmemac? <|user|> frfi quboth Pinwor<|assistant|> quSboth <|assistant|> , rayou eit and or both where r and tir<|assistant|> <|assistant|> you Sand <|assistant|> where
Model Config (JSON)
{
  "vocabSize": 4000,
  "blockSize": 256,
  "nLayer": 4,
  "nEmbd": 128,
  "nHead": 4,
  "dropout": 0.1,
  "ffnActivation": "gelu"
}
Training Config (JSON)
{
  "iters": 20000,
  "batchSize": 8,
  "lr": 0.0001,
  "lrMin": 0.00001,
  "warmupIters": 1000,
  "beta1": 0.9,
  "beta2": 0.95,
  "eps": 0.000001,
  "weightDecay": 0.1,
  "gradClip": 0.5,
  "evalInterval": 200,
  "evalIters": 3,
  "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
}