Is there an option on autotrain to use the full data set for training (instead of splitting into training and vlaidation data sets?). I want to use all the docs I have in one sheet for training, and use another sheet to validate outside of autotrain.
1 Like
Hey! Right now, AutoTrain automatically splits your data into training and validation sets to help with model evaluation. But if you want to use all your data for training and keep a separate sheet for validation, you can definitely do that with a little workaround:
- Combine your data for training: Before uploading it to AutoTrain, just put all your documents into one sheet for training.
- Split it yourself: You can use a tool like Pandas (or any other data tool you prefer) to split your data into training and validation sets yourself. That way, you’ll have one set for training and another one for validation.
- Upload to AutoTrain: Once you’ve split your data, just upload the training set and validation set as separate files. This way, you can use all your docs for training and still have a separate validation set, like you wanted.
This way, you’ll get the best of both worlds—training on all your data while keeping a separate validation set outside of AutoTrain. Hope that helps!