20260224034520_jejjcompletedchat6.84M params1h 27m elapsed · Updated 48d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Feb 24, 2026 3:46 AM
Step 9,630 / 50,00019.3%
5.1783
Loss?
4.5560
Best Loss?
-37.8% from start
5.3511
Val Loss?
best: 5.2913
4.63e-5
Learning Rate?
7,710
Throughput?
tok/s (avg)
531
Speed?
ms/iter (avg)
8648167.488
Grad Norm?
avg: 1843108.867
39.27M
Tokens
processed
63ms
Forward
12% of step
407ms
Backward
77% of step
25ms
GPU Sync
5% of step
1,064
GPU Ops
per step
1.0%
MFU
model FLOPS util
6.5x
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?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?2500
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
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|>iea and i <|user|> siw<|end_of_text|>
<|user|> Ipae, me<|end_of_text|>
<|user|> I em thhra<|assistant|> O <|assistant|> Mo<|end_of_text|>
<|user|> A a <|assistant|> ohhh<|end_of_text|>
<|user|> F <|assistant|> <|assistant|> Oh s’
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|>I <|assistant|> Ht<|end_of_text|>
<|user|> pt <|assistant|> e<|assistant|> Yondont a ma that <|assistant|> W<|user|> Y <|assistant|> I <|user|> <|assistant|> by<|user|> <|assistant|> rris, uadnt <|user|> <|user|> I yh the st? <|user|> in
3-<|user|> Tell me about yourself. <|assistant|>49d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|><|assistant|> R gnt <|assistant|> em <|assistant|> w<|user|> TRL <|assistant|> i <|assistant|> Iand e<|assistant|> and the <|user|> LUidk <|assistant|> WOSwk<|user|> biny <|user|> T <|user|> O <|user|> B
Model Config (JSON)
{
"vocabSize": 4000,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 256,
"nHead": 8,
"dropout": 0
}Training Config (JSON)
{
"iters": 50000,
"batchSize": 16,
"lr": 0.00005,
"lrMin": 0.000005,
"warmupIters": 500,
"beta1": 0.9,
"beta2": 0.95,
"eps": 1e-8,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 2500,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 500,
"spikeThreshold": 0
}