EleutherAI / EleutherAI/pythia
question on overfitting
- Dominant language
- Jupyter Notebook
- Stars
- 2.9k
- Forks
- 224
- PR merge metrics
- No merged PRs in 30d
Description
Hi, it's a wonderful project for us to do research model behavior, i wonder if there is a test dataset or any other indicator on the overfitting aspect, i tried to test WikiText-2 but it shows no sign of overfitting, I'd appreciate it if anyone can give me some advice
Contributor guide
No contributing guide indexed for this repository
Research direction
No file, test, or entry point is named. Start by reviewing the project's existing evaluation setup and the reported WikiText-2 experiment, then determine which dataset or overfitting indicator would answer the question; done means documenting a reproducible evaluation approach and interpreting its result.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100