A
Alpha
stale

super_chat_20260307003627_1zlg

6.84M parameter super_chat model — bpe-chat-4k tokenizer, 6L/256D/8H

Overview

6.84M
Parameters
5.6526
Final Loss
6.9640
Best Val Loss
285.0
Perplexity
819,200
Tokens Processed
0.1
Tokens/Param
27,492 tok/s
Avg Throughput
1m 5s
Training Time
Training Progress800 / 50,000 steps (1.6%)
Loss reduced by 32.3% from initial 8.3453

Dataset & Training

Domainsuper_chat
Tokenizerbpe-chat-4k
Total Iterations50,000
Batch Size4
Context Length256 tokens
Tokens per Batch1,024
Dataset Passes~2
Effective Tokens819,200

Training Pipeline

Warmupsteps 1500

Learning rate warmup — model weights adjusting to data distribution

Loss: 8.3456.064Linear LR warmup, gradient clipping

Training Metrics

Loss Curve
?
?
?
?
Smoothed Loss
Perplexity
Learning Rate
Gradient Norm
Throughput (tok/s)
Timing Breakdown
No Telemetry

Model Architecture

Model Configuration

ArchitectureGPT (decoder-only transformer)
Parameters6.84M
Layers6
Embedding Dim256
Attention Heads8
Head Dim32
FFN Dim1024
FFN Activationgelu
Vocab Size4,000
Context Length256 tokens
Dropout0

Training Configuration

Optimizeradamw
Learning Rate0.0003
LR Min0.00003
LR ScheduleCosine decay
Warmup Steps1,000
Batch Size4
Grad Accum Steps2
Effective Batch8
Grad Clip1
Weight Decay0.1
Backendhelios
Tokenizerbpe-chat-4k
Seed42

Layer Structure

Token Embed
4,000×256
Pos Embed
256×256
Block 0
Attn+FFN
Block 1
Attn+FFN
Block 2
Attn+FFN
Block 3
Attn+FFN
Block 4
Attn+FFN
Block 5
Attn+FFN
LayerNorm
256
LM Head
256×4,000

Generated Samples

Step 0Mar 7, 2026 12:38 AM
Prompt: <|user|> Hello, how are you? <|assistant|>
<|user|> Hello, how are you? <|assistant|>as bleof to do , I intlier as and st

Checkpoints

No checkpoints saved yet.

Chat with Model

Send a message to chat with this model
Generated Invalid Date Invalid Date — Alpha Training SystemConfig hash: