sanchit-gandhi/earnings22_robust_split

from datasets import load_dataset, DatasetDict ds = load_dataset("anton-l/earnings22_robust", split="test") print(ds) print("\n", "Split to ==>", "\n") # split train 90%/ dev 5% / test 5% # split twice and combine train_devtest = ds.train_test_split(shuffle=True, seed=1, test_size=0.1) dev_test = train_devtest['test'].train_test_split(shuffle=True, seed=1, test_size=0.5) ds_train_dev_test = DatasetDict({'train': train_devtest['train'], 'validation': dev_test['train'], 'test':… See the full description on the dataset page: huggingface.co/datasets/sanchit-gandhi/earnings22_robust_split.