apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-04-29 02:46:24 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

add random tree search

Browse source
This commit is contained in:
Yizhou Chi 2024-09-10 15:30:23 +08:00
parent d34a482faf
commit b776c7309b
4 changed files with 23 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
expo/data/dataset.py
View file

@ -23,7 +23,7 @@ DI_INSTRUCTION = """\
2. Test set does not have the target column.
3. You should perform transformations on train, dev, and test sets at the same time (it's a good idea to define functions for this and avoid code repetition).
4. If labels are transformed during training, they should be transformed back to the original format before saving the predictions.
5. You could split the training set further to make cross-validation and hyperparameter tuning.
5. You could utilize dev set to improve the model.
## Saving Dev and Test Predictions
1. Save the prediction results of BOTH the dev set and test set in `dev_predictions.csv` and `test_predictions.csv` respectively in the output directory.