A
Alpha
20260223001257_q184completedchat6.84M params53m 38s elapsed · Updated 48d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Feb 23, 2026 12:13 AM
Step 6,299 / 20,00031.5%
6.6058
Loss?
5.5048
Best Loss?
-20.4% from start
6.7391
Val Loss?
best: 5.9314
2.39e-5
Learning Rate?
7,878
Throughput?
tok/s (avg)
520
Speed?
ms/iter (avg)
1478.797
Grad Norm?
avg: 64140.047
25.52M
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?20,000
Batch size?16
Max LR?0.00003
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
No clipping data
GPU Operations
No GPU ops data
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|>50d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|>maybe p. ? <|assistant|> What to , to how I'm really you their in the . off the can I do . <|assistant|> Zssito rdifference fun really for perin the on the . <|assistant|> one of the money ? <|assistant|> What . really really I'm ddtheir for . <|assistant|> life one of the and ssito , life . <|assistant|> . can you
2-<|user|> What do you like to do for fun? <|assistant|>50d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|>to she to have a ? <|user|> can I do bar? <|assistant|> What in the to ddit . <|assistant|> to get happy a really you the pZ. <|assistant|> . my to get on to , for a really have a for rrcar my a week, , just ? <|user|> Zlife can you ws and , just one of the pough
3-<|user|> Tell me about yourself. <|assistant|>50d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|>to life to inasfor the .icreally over peroff the carreally over nowto get . . difference sitting ful . <|assistant|> walways . Zvin the ? <|assistant|> iccan I do . <|assistant|> are off the in the . <|assistant|> and poff the if I better the . ssifor . . , to
Model Config (JSON)
{
  "vocabSize": 4000,
  "blockSize": 256,
  "nLayer": 6,
  "nEmbd": 256,
  "nHead": 8,
  "dropout": 0
}
Training Config (JSON)
{
  "iters": 20000,
  "batchSize": 16,
  "lr": 0.00003,
  "beta1": 0.9,
  "beta2": 0.95,
  "eps": 1e-8,
  "weightDecay": 0.1,
  "gradClip": 1,
  "evalInterval": 100,
  "evalIters": 10,
  "seed": 42,
  "backend": "helios",
  "tokenizer": "bpe-4k",
  "optimizer": "adamw",
  "logLevel": "info",
  "trace": false
}