google-research / google-research/big_vision
How can edit the paligemma funetuning scripts to plot a validation loss curve and also convert my model to hf model
Open
- Dominant language
- Jupyter Notebook
- Stars
- 3.5k
- Forks
- 227
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/finetune_paligemma.ipynb
Can some please help ?
Contributor guide
Research direction
Start with configs/proj/paligemma/finetune_paligemma.ipynb and trace the existing fine-tuning workflow. Determine how validation loss is recorded and what conversion to a Hugging Face model should produce; done means both requested outputs are supported and demonstrated in the notebook. No tests or other entry points are mentioned.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100