Update src/tasks_content.py

src/tasks_content.py

@@ -1,12 +1,12 @@
 from typing import Optional
 
 TASKS_PRETTY = {
+    "library_usage": "Library Usage Examples Generation",
+    "bug_localization_build_logs": "Bug Localization on Build Logs",
+    "project_code_completion": "Project-level Code Completion",
     "commit_message_generation": "Commit Message Generation",
     "bug_localization": "Bug Localization on Issue",
     "module_summarization": "Module Summarization",
-    "library_usage": "Library Usage Examples Generation",
-    "project_code_completion": "Project-level Code Completion",
-    "bug_localization_build_logs": "Bug Localization on Build Logs",
 }
 TASKS_PRETTY_REVERSE = {value: key for key, value in TASKS_PRETTY.items()}
 
@@ -40,8 +40,28 @@ TASKS_DESCRIPTIONS = {
 
         For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `module2text` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
         """,
+    
     "library_usage": "cool description for Library Usage Examples Generation task",
-    "project_code_completion": "cool description for Project-level Code Completion task",
+    
+    "project_code_completion": """# Project-Level Code Completion\n
+        Our Project-Level Code Completion 🤗 [JetBrains-Research/lca-code-completion](https://huggingface.co/datasets/JetBrains-Research/lca-code-completion) includes four datasets: 
+             - `small-context`: 144 data points, 
+             - `medium-context: 224 data points,
+             - `large-context`: 270 data points,
+             - `huge-context`: 296 data points.
+
+        We use standard Exact Match (EM) metric for one-line code completion.
+        We evaluate Exact Match for different line categories:
+            - *infile* – functions and classes are from the completion file;
+            - *inproject – functions and files are from the repository snapshot;
+            - *committed* – functions and classes are from the files that were added on the completion file commit;
+            - *common* – functions and classes with common names, e.g., `main`, `get`, etc.;
+            - *non-informative* – short/long lines, import/print lines, or comment lines;
+            - *random* – lines that doesn't fit to any of previous categories.
+
+        For further details on the dataset and the baselines from 🏟️ Long Code Arena Team, refer to `code_completion` folder in [our baselines repository](https://github.com/JetBrains-Research/lca-baselines) or to our preprint (TODO).
+        """,
+    
     "bug_localization_build_logs": "cool description for Bug Localization on Build Logs task",
 }