A
Alpha
20260224011525_n0g1completedchat6.84M params40m 30s elapsed · Updated 48d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Feb 24, 2026 1:16 AM
Step 4,585 / 50,0009.2%
4.9767
Loss?
4.4575
Best Loss?
-40.4% from start
5.1263
Val Loss?
best: 5.1263
2.96e-5
Learning Rate?
7,211
Throughput?
tok/s (avg)
568
Speed?
ms/iter (avg)
545.980
Grad Norm?
avg: 511.603
18.58M
Tokens
processed
62ms
Forward
11% of step
441ms
Backward
78% of step
30ms
GPU Sync
5% of step
1,026
GPU Ops
per step
1.0%
MFU
model FLOPS util
7.1x
Bwd/Fwd
ratio
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?50,000
Batch size?16
Max LR?0.00003
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?5
Eval interval?2500
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
Perplexity
Train/Val Gap
No validation data
Learning Rate
Grad Norm
Smoothed Loss (EMA)
Loss Velocity
Gradient Clipping
No clipping data
GPU Operations
Step Time Breakdown
Forward
Backward
Grad Norm
Optimizer
GPU Sync
Data
Timing Phase Lines
Backward / Forward Ratio
Checkpoints (0) ?
No checkpoints saved
Sample Generations (3)
#CheckpointPrompt (preview)Generated
1-<|user|> Hello, how are you? <|assistant|>49d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|> <|user|> *ly? <|assistant|> I <|user|> ogona fs gon and be <|assistant|> yls <|assistant|> no ubirulo <|user|> I’s is nt gs your pl <|user|> UO <|user|> no
2-<|user|> What do you like to do for fun? <|assistant|>49d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|> <|assistant|> FSi suck that i dit. <|assistant|> ii do it just rebh oda <|user|> the ino <|assistant|> I don't <|assistant|> You d<|endmbh your pingkom <|user|> CGym
3-<|user|> Tell me about yourself. <|assistant|>49d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|> <|assistant|> Sbydon<|end_of_textextext|> <|user|> OGokrason ao <|assistant|> I don't resyed ro <|assistant|> HEl<|end_of_
Model Config (JSON)
{
  "vocabSize": 4000,
  "blockSize": 256,
  "nLayer": 6,
  "nEmbd": 256,
  "nHead": 8,
  "dropout": 0
}
Training Config (JSON)
{
  "iters": 50000,
  "batchSize": 16,
  "lr": 0.00003,
  "lrMin": 0.000005,
  "warmupIters": 500,
  "beta1": 0.9,
  "beta2": 0.95,
  "eps": 0.000001,
  "weightDecay": 0.1,
  "gradClip": 5,
  "evalInterval": 2500,
  "evalIters": 10,
  "seed": 42,
  "backend": "helios",
  "tokenizer": "bpe-4k",
  "optimizer": "adamw",
  "logLevel": "info",
  "trace": true,
  "gradAccumSteps": 1,
  "sampleInterval": 2500,
  "spikeThreshold": 0
}