benchopt / benchopt/benchmark_nanogpt
Extra problems
- Dominant language
- Python
- Stars
- 5
- Forks
- 2
- PR merge metrics
- No merged PRs in 30d
Description
It would be nice to have another problem to compare the same solvers with different problems.
ImageNet is probably a very good starting point + adding some of the CIFAR10/CIFAR100 results
- [ ] Train a ResNet50 with AdamW with ImageNet/Cifar10/Cifar100
- [ ] Train DiT with MuOn
Contributor guide
No contributing guide indexed for this repository
Research direction
No files, tests, or entry points are named in the issue. Start by reading the repository's existing benchmark and solver setup, then determine how additional ImageNet, CIFAR10, and CIFAR100 problems and the DiT with MuOn task fit it. Done means the listed training comparisons are implemented and their results are available.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 30/100