Naming config entries better

Author: jakep-allenai

olmocr/train/configs/example_config.yaml

@@ -27,7 +27,8 @@ model:
 dataset:
 
   train:
-    - root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_01_books_train_iabooks/
+    - name: processed_01_books_train_iabooks
+      root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_01_books_train_iabooks/
       pipeline: &basic_pipeline
         - name: FrontMatterParser
           front_matter_class: PageResponse
@@ -42,13 +43,16 @@ dataset:
           masking_index: -100
           end_of_message_token: "<|im_end|>"
     # Not putting in big bulk of data to speed up loading for debugging for now
-    # - root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_00_documents_train_s2pdf/
+    # - name: processed_00_documents_train_s2pdf
+    #   root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_00_documents_train_s2pdf/
     #   pipeline: *basic_pipeline
 
   eval:
-    - root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_00_documents_eval_s2pdf/
+    - name: processed_00_documents_eval_s2pdf
+      root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_00_documents_eval_s2pdf/
       pipeline: *basic_pipeline
-    - root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_01_books_eval_iabooks/
+    - name: processed_01_books_eval_iabooks
+      root_dir: /weka/oe-data-default/jakep/olmOCR-mix-0225/processed_01_books_eval_iabooks/
       pipeline: *basic_pipeline