benchopt / benchopt/benchmark_nanogpt
TODO add DEIT on Imagenet
Open
- Dominant language
- Python
- Stars
- 5
- Forks
- 2
- PR merge metrics
- No merged PRs in 30d
Description
Adding a training on DIT on imagenet, looking at the code from [EPFL-Scion](https://github.com/LIONS-EPFL/scion/blob/main/examples/deit/main_scion.py)
Contributor guide
No contributing guide indexed for this repository
Research direction
Review the linked EPFL-Scion examples/deit/main_scion.py as the stated reference, then inspect this repository's existing benchmark entry points and training structure. Clarify how a DeiT/ImageNet training should fit the project and what success criteria and tests are expected before starting; done should mean the training is integrated and its benchmark behavior is verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100