Critical fixes for transformer gradient flow:
EmbeddingBackward:
- Implements scatter-add gradient accumulation for embedding lookups
- Added to Module 05 (autograd_dev.py)
- Module 11 imports and uses it in Embedding.forward()
- Gradients now flow back to embedding weights
ReshapeBackward:
- reshape() was breaking computation graph (no _grad_fn)
- Added backward function that reshapes gradient back to original shape
- Patched Tensor.reshape() in enable_autograd()
- Critical for GPT forward pass (logits.reshape before loss)
Results:
- Before: 0/37 parameters receive gradients, loss stuck
- After: 13/37 parameters receive gradients (35%)
- Single batch overfitting: 4.46 → 0.03 (99.4% improvement!)
- MODEL NOW LEARNS! 🎉
Remaining work: 24 parameters still missing gradients (likely attention)
Tests added:
- tests/milestones/test_05_transformer_architecture.py (Phase 1)
- Multiple debug scripts to isolate issues
- Deleted root-level tests/test_gradient_flow.py
- Comprehensive tests now in tests/regression/test_gradient_flow_fixes.py
- Module-specific tests in tests/05_autograd/test_batched_matmul_backward.py
- Better test organization following TinyTorch conventions
TransposeBackward:
- New backward function for transpose operation
- Patch Tensor.transpose() to track gradients
- Critical for attention (Q @ K.T) gradient flow
MatmulBackward batched fix:
- Change np.dot to np.matmul for batched 3D+ tensors
- Use np.swapaxes instead of .T for proper batched transpose
- Fixes gradient shapes in attention mechanisms
Tests added:
- tests/05_autograd/test_batched_matmul_backward.py (3 tests)
- Updated tests/regression/test_gradient_flow_fixes.py (9 tests total)
All gradient flow issues for transformer training are now resolved!
- Change from .data extraction to Tensor arithmetic (x - mean, diff * diff, x / std)
- Preserve computation graph through normalization
- std tensor now preserves requires_grad correctly
LayerNorm is used before and after attention in transformer blocks
Major rewrite for gradient flow:
- scaled_dot_product_attention: Use Tensor ops (matmul, transpose, softmax)
- MultiHeadAttention: Process all heads in parallel with 4D batched tensors
- No explicit batch loops or .data extraction
- Proper mask broadcasting for (batch * heads) dimension
This is the most complex fix - attention is now fully differentiable end-to-end
- Embedding.forward() now preserves requires_grad from weight tensor
- PositionalEncoding.forward() uses Tensor addition (x + pos) instead of .data
- Critical for transformer input embeddings to have gradients
Both changes ensure gradient flows from loss back to embedding weights
- Implement gradient functions for subtraction and division operations
- Patch Tensor.__sub__ and Tensor.__truediv__ in enable_autograd()
- Required for LayerNorm (x - mean) and (normalized / std) operations
These operations are used extensively in normalization layers
- Preserve computation graph by using Tensor arithmetic (x - x_max, exp / sum)
- No more .data extraction that breaks gradient flow
- Numerically stable with max subtraction before exp
Required for transformer attention softmax gradient flow
Updates to vaswani_shakespeare.py:
- Add Rich console, Panel, Table, and box imports
- Replace all print() statements with console.print() with Rich markup
- Add beautiful Panel.fit() boxes for major sections (Act 1, Systems Analysis, Success)
- Use Rich color tags: [bold], [cyan], [green], [yellow], [dim]
- Format training progress with colored loss values
- Display generated text in green
- Add architectural visualization with Rich panels
Updates to transformers_dev.py:
- Remove all try/except fallback implementations
- Clean imports only (no development scaffolding)
- Use proper module imports from tinytorch package
Milestone now matches the beautiful CLI pattern from cnn_digits.py
- Add get_shakespeare() method to download tiny-shakespeare.txt
- Downloads from Karpathy's char-rnn repository (1MB corpus)
- Returns raw text for character-level language modeling
- Follows same pattern as MNIST/CIFAR-10 downloads
- Includes test in main() function
- Added book/_build/ to .gitignore
- Removed 540 auto-generated Jupyter Book build files from tracking
- Files remain locally for viewing but won't be committed anymore
- Reduces repo size and prevents merge conflicts on generated files
- Add Module 20 (AI Olympics) to Competition section
- Remove Historical Milestones from navigation (simplify)
- Remove separate Leaderboard page (consolidate into capstone)
- Simplify AI Olympics capstone content (~60 lines)
- Clear 'Coming Soon' box for competition platform
- Brief category descriptions
- Focus on what students can do now
- Simplify Community page (~50 lines)
- Clear 'Coming Soon' box for dashboard features
- Brief feature descriptions
- Ways to participate now
- Split Competition and Community into separate nav sections
- Fix jupyter-book dependency compatibility for Python 3.8
- myst-parser 0.18.1 (compatible with myst-nb 0.17.2)
- sphinx 5.3.0
- Update requirements.txt with compatible versions
Result: Clean, honest, scannable website that shows all 20 modules
- Add last commit badge to show project is actively maintained
- Add commit activity badge to show consistent development
- Add GitHub stars badge for social proof
- Add contributors badge to highlight collaboration
- Add last commit badge to show project is actively maintained
- Add commit activity badge to show consistent development
- Add GitHub stars badge for social proof
- Add contributors badge to highlight collaboration
- Add CLAUDE.md entry point for Claude AI system
- Fix tito test command to set PYTHONPATH for module imports
- Fix embeddings export directive placement for nbdev
- Fix attention module to export imports properly
- Fix transformers embedding index casting to int
- Add CLAUDE.md entry point for Claude AI system
- Fix tito test command to set PYTHONPATH for module imports
- Fix embeddings export directive placement for nbdev
- Fix attention module to export imports properly
- Fix transformers embedding index casting to int
- Update transformers module to match tokenization style with improved ASCII diagrams
- Fix attention module to use proper multi-head interface
- Update transformer era milestone for refined module integration
- Fix import paths and ensure forward() method consistency
- All transformer components now work seamlessly together
- Update transformers module to match tokenization style with improved ASCII diagrams
- Fix attention module to use proper multi-head interface
- Update transformer era milestone for refined module integration
- Fix import paths and ensure forward() method consistency
- All transformer components now work seamlessly together
Following module developer guidelines, added comprehensive visual diagrams:
1. Text-to-Numbers Pipeline (Introduction):
- Added full boxed diagram showing 4-step tokenization process
- Clear visual flow from human text to numerical IDs
- Each step explained inline with the diagram
2. Character Tokenization Process:
- Step-by-step vocabulary building visualization
- Shows corpus → unique chars → vocab with IDs
- Encoding process with ID lookup visualization
- Decoding process with reverse lookup
- All in clear nested boxes
3. BPE Training Algorithm:
- Comprehensive 4-step process with nested boxes
- Pair frequency analysis with bar charts (████)
- Before/After merge visualizations
- Iteration examples showing vocabulary growth
- Final results with key insights
4. Memory Layout for Embedding Tables:
- Visual bars showing relative memory sizes
- Character (204KB) vs BPE-50K (102MB) vs Word-100K (204MB)
- Shows fp32/fp16/int8 precision trade-offs
- Real production model examples (GPT-2/3, BERT, T5, LLaMA)
- Clear table format for comparison
Educational improvements:
- More visual, less text-heavy
- Clearer step-by-step flows
- Better intuition building
- Production context throughout
- Following module developer ASCII diagram patterns
Students now see:
- HOW tokenization works (not just WHAT)
- WHY different strategies exist
- WHAT the memory implications are
- HOW production models make these choices
- Bright yellow/orange gradient banner with construction icons (🚧⚠️🔨)
- Interactive controls for collapsing and dismissing the banner
- Responsive design that adapts to different screen sizes
- Clear messaging about active development and community feedback
- Proper spacing and professional appearance
- JavaScript functionality for persistent user preferences(https://claude.ai/code)
- This workflow was testing notebook conversion features
- Not required for website deployment
- Website deploys via deploy-book.yml on main branch
- Can re-enable later if needed for CI testing
- NotebooksCommand now checks modules/source/ for dev files
- Fixes 'No *_dev.py files found' error in CI
- Maintains backwards compatibility with flat structure
- Add NotebooksCommand to commands dictionary in main.py
- Command was imported but not registered
- Fixes 'invalid choice: notebooks' error in workflow
- Change 'tito module notebooks' to 'tito notebooks'
- The notebooks command is a top-level command, not a module subcommand
- Fixes workflow test failures
- Positional arguments cannot be in mutually exclusive groups in argparse
- Keep modules as positional argument, --all as optional flag
- Fixes CLI initialization error in GitHub Actions
