adambuttrick/funding-extraction-distillation-data

--- dataset_info: - config_name: curriculum features: - name: funding_statement dtype: string - name: completion dtype: string - name: funders dtype: string - name: surprisal dtype: float64 splits: - name: train num_bytes: 46368038 num_examples: 2341 - name: eval num_bytes: 4605405 num_examples: 261 download_size: 15654822 dataset_size: 50973443 - config_name: default features: - name: funding_statement dtype: string - name: completion dtype: string - name: funders dtype: string splits: - name: train num_bytes: 45999917 num_examples: 2349 - name: eval num_bytes: 5111101 num_examples: 261 download_size: 16083491 dataset_size: 51111018 - config_name: test features: - name: doi dtype: string - name: funding_statement dtype: string - name: funders dtype: string splits: - name: test num_bytes: 273694 num_examples: 322 download_size: 113966 dataset_size: 273694 - config_name: test_mini features: - name: doi dtype: string - name: funding_statement dtype: string - name: funders dtype: string splits: - name: test num_bytes: 7884 num_examples: 10 download_size: 9932 dataset_size: 7884 configs: - config_name: curriculum data_files: - split: train path: curriculum/train-* - split: eval path: curriculum/eval-* - config_name: default data_files: - split: train path: data/train-* - split: eval path: data/eval-* - config_name: test data_files: - split: test path: test/test-* - config_name: test_mini data_files: - split: test path: test_mini/test-* ---