A
Alpha
historic_chat_v2_20260227105516_w2mgstalechat6.84M params4m 42s elapsed · Updated 45d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Feb 27, 2026 10:55 AM
Step 7,458 / 50,00014.9%
7.4794
Loss?
7.4560
Best Loss?
-21.3% from start
7.5326
Val Loss?
best: 7.5193
4.81e-5
Learning Rate?
13,375
Throughput?
tok/s (avg)
307
Speed?
ms/iter (avg)
0.373
Grad Norm?
avg: 0.392
3.92M
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?6
Embedding?256
Heads?8
Vocab?4,000
Context?256
Dropout?0.1
Parameters?6.84M
Training Config
Total iters?50,000
Batch size?16
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?100
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|>45d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|>in of that ing that for ing to for ed ga to our of our a in pthe —ies a git as in s, the the and es enssythat it or and that athe in in a t; ;
2-<|user|> What do you like to do for fun? <|assistant|>45d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|>as ’s a to y the a y is s a; enmis and reto as ingor ing , s, for a or ing and of reed to to as a ing , sing as i, ygyas the y
3-<|user|> Tell me about yourself. <|assistant|>45d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|>the or pas as to s s pthat and and for , , ait to for g, ; rethe —is yand —’s unto ges our , picthe it of in and dmust as of as es
Model Config (JSON)
{
  "vocabSize": 4000,
  "blockSize": 256,
  "nLayer": 6,
  "nEmbd": 256,
  "nHead": 8,
  "dropout": 0.1,
  "ffnActivation": "gelu"
}
Training Config (JSON)
{
  "iters": 50000,
  "batchSize": 16,
  "lr": 0.00005,
  "lrMin": 0.000005,
  "warmupIters": 1000,
  "beta1": 0.9,
  "beta2": 0.95,
  "eps": 0.000001,
  "weightDecay": 0.1,
  "gradClip": 1,
  "evalInterval": 100,
  "evalIters": 10,
  "seed": 42,
  "backend": "helios",
  "tokenizer": "bpe-4k",
  "optimizer": "adamw",
  "logLevel": "info",
  "logEvery": 1,
  "trace": false,
  "gradAccumSteps": 1,
  "sampleInterval": 500,
  "spikeThreshold": 0,
  "syncEvery": 0,
  "gcEvery": 0,
  "packed": false,
  "symbio": false,
  "symbioConfig": null
}