20260223063839_lmc9completedchat6.84M params5m 46s elapsed · Updated 48d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Feb 23, 2026 6:39 AM
Step 595 / 10,0005.9%
5.5070
Loss?
5.2909
Best Loss?
-34.0% from start
5.4822
Val Loss?
best: 5.4822
1.50e-4
Learning Rate?
9,473
Throughput?
tok/s (avg)
13,836
Speed?
ms/iter (avg)
267.922
Grad Norm?
avg: 132.117
3.28M
Tokens
processed
1494ms
Forward
11% of step
12285ms
Backward
89% of step
6ms
GPU Sync
0% of step
3,577
GPU Ops
per step
0.3%
MFU
model FLOPS util
8.2x
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?10,000
Batch size?128
Max LR?0.00015
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.01
Grad clip?1
Eval interval?500
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|>cing et aal is h a<|assistant|> <|assistant|> arexp le et <|assistant|> tive
<|assistant|> d₶stcwhen ands ai <|assistant|> Wp aands , and is <|user|> books tually ca b↓a bplay Wfrom <|user|> ae<|assistant|>
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|>hding brto terabe st<|assistant|> you're <|assistant|> is aranyʌp is can <|assistant|> 𓇨brpossible cpbooks <|assistant|> ding tri<|assistant|> an<|assistant|> aryou're st <|assistant|> aands anh ar<|assistant|> ext|>le ↴ding they are books
3-<|user|> Tell me about yourself. <|assistant|>49d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|> do No just ks e<|user|> ing ? ing <|assistant|> ce you? tacome tding them ic to wife ? about al et Wvery <|assistant|> ill h_texpe? is KTtcan't do more mot𐰗ce h W
Model Config (JSON)
{
"vocabSize": 4000,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 256,
"nHead": 8,
"dropout": 0
}Training Config (JSON)
{
"iters": 10000,
"batchSize": 128,
"lr": 0.00015,
"beta1": 0.9,
"beta2": 0.999,
"eps": 0.000001,
"weightDecay": 0.01,
"gradClip": 1,
"evalInterval": 500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "debug",
"trace": true,
"gradAccumSteps": 4,
"sampleInterval": 100
}