super_chat_20260305034257_9p2lstalechat6.84M params2m 25s elapsed · Updated 40d ago
6L / 256D / 8H · helios · bpe-4k · adamw· Created Mar 5, 2026 3:44 AM
Step 1,248 / 15,0008.3%
8.3238
Loss?
6.3418
Best Loss?
26.2% from start
8.3259
Val Loss?
best: 6.4256
5.00e-5
Learning Rate?
3,529
Throughput?
tok/s (avg)
581
Speed?
ms/iter (avg)
17868.561
Grad Norm?
avg: 17854.527
1.33M
Tokens
processed
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?6
Embedding?256
Heads?8
Vocab?4,000
Context?256
Dropout?0.1
Parameters?6.84M
Training Config
Total iters?15,000
Batch size?4
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?0.5
Eval interval?200
Throughput (tok/s)
Step Time (ms/iter)
GPU & VRAM
Perplexity
Train/Val Gap
Learning Rate
Grad Norm
Smoothed Loss (EMA)
Loss Velocity
Gradient Clipping
GPU Operations
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|>40d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|> lin , yarerep<|user|> it ito refiii of i v<|user|> of that bi and inis ene, , , i <|assistant|> i , lreand and s b, and <|assistant|>
2-<|user|> What do you like to do for fun? <|assistant|>40d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|> lin , yarerep<|user|> it ito refiii of i v<|user|> of that bi and inreene, , , i <|assistant|> i , lreand and s b, and <|assistant|>
3-<|user|> Tell me about yourself. <|assistant|>40d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|> lin , yarerep<|user|> it ito refiii of i v<|user|> of that bi and inreene, , , i <|assistant|> i , lreand and s b, and <|assistant|>
Model Config (JSON)
{
"vocabSize": 4000,
"blockSize": 256,
"nLayer": 6,
"nEmbd": 256,
"nHead": 8,
"dropout": 0.1,
"ffnActivation": "gelu"
}Training Config (JSON)
{
"iters": 15000,
"batchSize": 4,
"lr": 0.00005,
"lrMin": 0.000005,
"warmupIters": 1000,
"beta1": 0.9,
"beta2": 0.95,
"eps": 0.000001,
"weightDecay": 0.1,
"gradClip": 0.5,
"evalInterval": 200,
"evalIters": 3,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"logEvery": 25,
"trace": false,
"gradAccumSteps": 2,
"sampleInterval": 200,
"spikeThreshold": 0,
"syncEvery": 1,
"gcEvery": 1,
"packed": false,
"symbio": false,
"symbioConfig": null
}