Skip to content

ignore#68

Open
sumantopal07 wants to merge 4 commits into
PacktPublishing:mainfrom
sumantopal07:sumanto
Open

ignore#68
sumantopal07 wants to merge 4 commits into
PacktPublishing:mainfrom
sumantopal07:sumanto

Conversation

@sumantopal07
Copy link
Copy Markdown

  • Add Unsloth fine-tuning standalone script and notebook
  • Add comprehensive fine-tuning documentation and guides
  • Add M4 Mac setup and training guides
  • Add tools for dataset generation and fine-tuning
  • Update .gitignore to exclude generated data and training outputs
  • Remove tracked artifacts and generated datasets

- Add Unsloth fine-tuning standalone script and notebook
- Add comprehensive fine-tuning documentation and guides
- Add M4 Mac setup and training guides
- Add tools for dataset generation and fine-tuning
- Update .gitignore to exclude generated data and training outputs
- Remove tracked artifacts and generated datasets
@sumantopal07 sumantopal07 changed the title Add fine-tuning implementation, documentation, and update .gitignore ignore Dec 27, 2025
Sumanto added 3 commits December 28, 2025 10:49
- Complete explanation of LoRA vs QLoRA concepts
- Training process breakdown with examples
- Loss calculation and interpretation
- Performance analysis and time estimates
- TensorBoard monitoring guide
- Dataset composition and progress tracking
- Key learnings and common questions
- Generated from training session insights
- Q&A format covering all technical discussions
- LoRA mechanics and training process explanations
- Loss calculation and performance analysis
- Test/train data usage and evaluation metrics
- Hardware comparisons and optimization strategies
- Complete record of learning session for future reference
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Development

Successfully merging this pull request may close these issues.

1 participant