completed
super_chat_20260306132105_6b9x
88.33M parameter nanochat model — bpe-chat-4k tokenizer, 16L/512D/8H
Overview
88.33M
Parameters
6.7393
Final Loss
-
Best Val Loss
844.9
Perplexity
204,800
Tokens Processed
0.0
Tokens/Param
287 tok/s
Avg Throughput
9m 42s
Training Time
Training Progress200 / 200 steps (100.0%)
Loss reduced by 19.4% from initial 8.3594
Dataset & Training
Domainnanochat
Tokenizerbpe-chat-4k
Total Iterations200
Batch Size2
Context Length512 tokens
Tokens per Batch1,024
Dataset Passes~1
Effective Tokens204,800
Training Pipeline
Warmupsteps 1–2
Learning rate warmup — model weights adjusting to data distribution
Loss: 8.359 → 8.409Linear LR warmup, gradient clipping
Rapid Descentsteps 2–61
Steepest loss reduction — model learning primary patterns
Loss: 8.409 → 6.987Cosine LR schedule, AdamW optimization
Refinementsteps 61–141
Diminishing returns — model fine-tuning subtler patterns
Loss: 6.987 → 6.756Lower LR, gradient accumulation
Convergencesteps 141–160
Approaching minimum — model capacity saturation
Loss: 6.756 → 6.739Minimum LR, weight decay regularization
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)
Parameters88.33M
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
| Step | File | Size | Date |
|---|---|---|---|
| 200 | checkpoint-200.json | 303.4 MB | Mar 6, 2026 1:52 PM |
Chat with Model
Send a message to chat with this model
Generated Invalid Date Invalid Date — Alpha Training SystemConfig hash: