20260223020126_nu4acompletedchat6.84M params9m 3s elapsed · Updated 1d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Feb 23, 2026 2:02 AM
Step 1,158 / 30,0003.9%
5.3828
Loss?
5.0609
Best Loss?
-35.1% from start
5.6744
Val Loss?
best: 5.6744
4.99e-5
Learning Rate?
8,160
Throughput?
tok/s (avg)
502
Speed?
ms/iter (avg)
2565.852
Grad Norm?
avg: 221.443
4.44M
Tokens
processed
Loss Curve ?
Validation / selection
Run diagnostics
Gradient + Loss
Train/val loss with validation, warmup, overfit, and instability markers.
Search-aware view
Architecture
Layers?6
Embedding?256
Heads?8
Vocab?4,000
Context?256
Dropout?0
Parameters?6.84M
Training Config
Total iters?30,000
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
GPU & VRAM
Learning Rate
Grad Norm
Step Time Breakdown
Step Time Breakdown
No timing data
Checkpoints (0) ?
No checkpoints saved
Sample Generations (3)
#CheckpointPrompt (preview)Generated
1-<|user|> Hello, how are you? <|assistant|>2d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|>ding Wdcherardo to at dto aletive tive ar
just k books terararis alcan ? ding exgod? albe just ex<|assistant|> <|user|> from br<|user|> just tcex<|user|> dding
2-<|user|> What do you like to do for fun? <|assistant|>2d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|>hto fto the know what books ding <|assistant|> anding a ba bin the s ing de
? c<|user|> ding anttis an? is ar__ding <|assistant|> brdwe have ?
motive __<|assistant|> of'd le
3-<|user|> Tell me about yourself. <|assistant|>2d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|>eittedes
<|assistant|> alcan have play p almoent some esbooks bican <|user|> Wcan c
Walst<|assistant|> books |>be te is to an brfrom exo ejust ? dWda
{
"vocabSize": 4000,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 256,
"nHead": 8,
"dropout": 0
}{
"iters": 30000,
"batchSize": 16,
"lr": 0.00005,
"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
}