historic_chat_v2_20260225120557_a2bnstalechat17.44M params21m 3s elapsed · Updated 47d ago
8L / 384D / 8H · helios · bpe-4k · adamw· Created Feb 25, 2026 12:06 PM
Step 1,353 / 50,0002.7%
5.7395
Loss?
5.6158
Best Loss?
-31.5% from start
6.2466
Val Loss?
best: 6.2466
5.00e-5
Learning Rate?
6,245
Throughput?
tok/s (avg)
984
Speed?
ms/iter (avg)
1.030
Grad Norm?
avg: 2.062
8.31M
Tokens
processed
204ms
Forward
21% of step
702ms
Backward
71% of step
12ms
GPU Sync
1% of step
859
GPU Ops
per step
2.2%
MFU
model FLOPS util
3.5x
Bwd/Fwd
ratio
Loss Curve ? click any chart to add markers
?
?
?
?
Architecture
Layers?8
Embedding?384
Heads?8
Vocab?4,000
Context?512
Dropout?0.1
Parameters?17.44M
Training Config
Total iters?50,000
Batch size?12
Max LR?0.00005
Optimizer?adamw
Backend?helios
Tokenizer?bpe-4k
Seed?42
Weight decay?0.1
Grad clip?1
Eval interval?1000
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
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|>47d ago
Prompt
<|user|> Hello, how are you? <|assistant|>
Output
<|user|> Hello, how are you? <|assistant|>fe, that in res cy, and as not to uning to find as the fmed e—I can ding it sances for their ucts, of the a man’s ent it that p, of the sourto ening
2-<|user|> What do you like to do for fun? <|assistant|>47d ago
Prompt
<|user|> What do you like to do for fun? <|assistant|>
Output
<|user|> What do you like to do for fun? <|assistant|>cthat of ae, unes are fed in the a and Maribm; un's t, must es, —is must ence—that uns and in and Mient, not in the reform; our men may eor as
3-<|user|> Tell me about yourself. <|assistant|>47d ago
Prompt
<|user|> Tell me about yourself. <|assistant|>
Output
<|user|> Tell me about yourself. <|assistant|>or with that and s, y unwe and not men our is an is nede ed is the y ding in? fate ss that is eor to imers our gloryoaing deed we ed for for its
Model Config (JSON)
{
"vocabSize": 4000,
"blockSize": 512,
"nLayer": 8,
"nEmbd": 384,
"nHead": 8,
"dropout": 0.1,
"ffnActivation": "gelu"
}Training Config (JSON)
{
"iters": 50000,
"batchSize": 12,
"lr": 0.00005,
"lrMin": 0.000005,
"warmupIters": 1000,
"beta1": 0.9,
"beta2": 0.95,
"eps": 0.000001,
"weightDecay": 0.1,
"gradClip": 1,
"evalInterval": 1000,
"evalIters": 10,
"seed": 42,
"backend": "helios",
"tokenizer": "bpe-4k",
"optimizer": "adamw",
"logLevel": "info",
"trace": false,
"gradAccumSteps": 1,
"sampleInterval": 500,
"spikeThreshold": 0,
"syncEvery": 1,
"gcEvery": 0,
"packed": false,
"symbio": false,
"symbioConfig": null
}