stale
super_chat_20260306124845_k9vc
55.77M parameter nanochat model — bpe-chat-4k tokenizer, 16L/512D/8H
Overview
55.77M
Parameters
6.9777
Final Loss
7.5130
Best Val Loss
1072.5
Perplexity
101,376
Tokens Processed
0.0
Tokens/Param
659 tok/s
Avg Throughput
1m 11s
Training Time
Training Progress99 / 500 steps (19.8%)
Loss reduced by 16.5% from initial 8.3589
Dataset & Training
Domainnanochat
Tokenizerbpe-chat-4k
Total Iterations500
Batch Size2
Context Length512 tokens
Tokens per Batch1,024
Dataset Passes~0
Effective Tokens101,376
Training Pipeline
Warmupsteps 1–5
Learning rate warmup — model weights adjusting to data distribution
Loss: 8.359 → 8.348Linear 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)
Parameters55.77M
Layers16
Embedding Dim512
Attention Heads8
Head Dim64
FFN Dim2048
FFN Activationswiglu
Vocab Size4,000
Context Length512 tokens
Dropout0
Training Configuration
Optimizeradamw
Learning Rate0.0006
LR Min0.00006
LR ScheduleCosine decay
Warmup Steps500
Batch Size2
Grad Accum Steps1
Effective Batch2
Grad Clip1
Weight Decay0.1
Backendhelios
Tokenizerbpe-chat-4k
Seed42
Layer Structure
Token Embed
4,000×512
Pos Embed
512×512
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
512
LM Head
512×4,000
Generated Samples
No samples generated yet. Samples appear at configured intervals during training.
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: