rename test cases and code with new data handler values

Signed-off-by: Dushyant Behl <dushyantbehl@in.ibm.com>

Author: dushyantbehl

tests/artifacts/predefined_data_configs/apply_custom_jinja_template.yaml

@@ -10,6 +10,6 @@ datasets:
           remove_columns: all
           batched: false
           fn_kwargs:
-            dataset_text_field: "dataset_text_field"
+            formatted_text_column_name: "formatted_text"
             template: "dataset_template"
             add_eos_token: true

tests/artifacts/predefined_data_configs/apply_custom_template.yaml

@@ -10,6 +10,6 @@ datasets:
           remove_columns: all
           batched: false
           fn_kwargs:
-            dataset_text_field: "dataset_text_field"
+            formatted_text_column_name: "formatted_text"
             template: "dataset_template"
             add_eos_token: true

tests/artifacts/predefined_data_configs/apply_custom_template_streaming.yaml

@@ -11,5 +11,5 @@ datasets:
           remove_columns: all
           batched: false
           fn_kwargs:
-            dataset_text_field: "dataset_text_field"
+            formatted_text_column_name: "formatted_text"
             template: "dataset_template"

tests/artifacts/predefined_data_configs/duplicate_columns.yaml

@@ -9,5 +9,5 @@ datasets:
         arguments:
           batched: false
           fn_kwargs:
-            old_column: "input_ids"
-            new_column: "labels"
+            old_column_name: "input_ids"
+            new_column_name: "labels"

tests/artifacts/predefined_data_configs/multi_turn_data_with_chat_template.yaml

@@ -18,7 +18,7 @@ datasets:
         arguments:
           remove_columns: all
           fn_kwargs:
-            dataset_text_field: "formatted_chat_data"
+            formatted_text_column_name: "formatted_chat_data"
   - name: dataset_2
     data_paths:
       - "FILE_PATH"
@@ -27,7 +27,7 @@ datasets:
         arguments:
           remove_columns: all
           fn_kwargs:
-            dataset_text_field: "formatted_chat_data"
+            formatted_text_column_name: "formatted_chat_data"
   - name: dataset_3
     data_paths:
       - "FILE_PATH"
@@ -36,4 +36,4 @@ datasets:
         arguments:
           remove_columns: all
           fn_kwargs:
-            dataset_text_field: "formatted_chat_data"
+            formatted_text_column_name: "formatted_chat_data"

tests/artifacts/predefined_data_configs/multi_turn_data_with_chat_template_granite_3_1B.yaml

@@ -59,8 +59,8 @@ datasets:
         arguments:
           remove_columns: all
           fn_kwargs:
-            dataset_text_field: "formatted_chat_data"
-            conversation_column: "messages"
+            formatted_text_column_name: "formatted_chat_data"
+            conversation_column_name: "messages"
   - name: dataset_2
     data_paths:
       - "FILE_PATH"
@@ -69,8 +69,8 @@ datasets:
         arguments:
           remove_columns: all
           fn_kwargs:
-            dataset_text_field: "formatted_chat_data"
-            conversation_column: "messages"
+            formatted_text_column_name: "formatted_chat_data"
+            conversation_column_name: "messages"
   - name: dataset_3
     data_paths:
       - "FILE_PATH"
@@ -79,5 +79,5 @@ datasets:
         arguments:
           remove_columns: all
           fn_kwargs:
-            dataset_text_field: "formatted_chat_data"
-            conversation_column: "messages"
+            formatted_text_column_name: "formatted_chat_data"
+            conversation_column_name: "messages"

tests/artifacts/predefined_data_configs/multiple_datasets_with_sampling.yaml

@@ -13,8 +13,8 @@ datasets:
           remove_columns: all
           batched: false
           fn_kwargs:
-            input_field_name: input
-            output_field_name: output
+            input_column_name: input
+            output_column_name: output
   - name: dataset_2
     sampling: 0.4
     data_paths:
@@ -25,8 +25,8 @@ datasets:
           remove_columns: all
           batched: false
           fn_kwargs:
-            input_field_name: input
-            output_field_name: output
+            input_column_name: input
+            output_column_name: output
   - name: dataset_3
     sampling: 0.3
     data_paths:
@@ -37,5 +37,5 @@ datasets:
           remove_columns: all
           batched: false
           fn_kwargs:
-            input_field_name: input
-            output_field_name: output
+            input_column_name: input
+            output_column_name: output

tests/artifacts/predefined_data_configs/rename_select_columns.yaml

@@ -7,18 +7,20 @@ datasets:
     data_handlers:
       - name: rename_columns
         arguments:
-          column_mapping:
-            "input"  : "instruction"
-            "output" : "response"
+          fn_kwargs:
+            column_mapping:
+              "input"  : "instruction"
+              "output" : "response"
       - name: select_columns
         arguments:
-          column_names:
-            - "instruction"
-            - "response"
+          fn_kwargs:
+            column_names:
+              - "instruction"
+              - "response"
       - name: tokenize_and_apply_input_masking
         arguments:
           remove_columns: all
           batched: false
           fn_kwargs:
-            input_field_name: instruction
-            output_field_name: response
+            input_column_name: instruction
+            output_column_name: response

tests/artifacts/predefined_data_configs/skip_large_columns_data_handler_template.yaml

@@ -10,15 +10,15 @@ datasets:
           remove_columns: all
           batched: true
           fn_kwargs:
-            dataset_text_field: "output"
+            text_column_name: "output"
       - name: duplicate_columns
         arguments:
           batched: true
           fn_kwargs:
-            old_column: "input_ids"
-            new_column: "labels"
-      - name: skip_large_columns
+            old_column_name: "input_ids"
+            new_column_name: "labels"
+      - name: skip_samples_with_large_columns
         arguments:
           fn_kwargs:
             column_name: "input_ids"
-            max_length: 50
+            max_allowed_length: 50

tests/artifacts/predefined_data_configs/tokenize_and_apply_input_masking.yaml

@@ -10,6 +10,6 @@ datasets:
           remove_columns: all
           batched: false
           fn_kwargs:
-            input_field_name: input
-            output_field_name: output
+            input_column_name: input
+            output_column_name: output
             add_eos_token: true