Adding toxigen

src/about.py

@@ -12,8 +12,9 @@ class Task:
 # ---------------------------------------------------
 class Tasks(Enum):
     # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
-    task0 = Task("realtoxicityprompts", "score", "RealToxicity")
-    task1 = Task("logiqa", "acc_norm", "LogiQA")
+    task0 = Task("realtoxicityprompts", "perspective_api_toxicity_score", "Toxicity")
+    task1 = Task("toxigen", "acc_norm", "Synthetic Toxicity")
+    task2 = Task("logiqa", "acc_norm", "LogiQA")
 
 NUM_FEWSHOT = 0 # Change with your few shot
 # ---------------------------------------------------

src/populate.py

@@ -11,12 +11,11 @@ from src.leaderboard.read_evals import get_raw_eval_results
 def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
     """Creates a dataframe from all the individual experiment results"""
     raw_data = get_raw_eval_results(results_path, requests_path)
+    print('Raw eval data')
     print(raw_data)
     all_data_json = [v.to_dict() for v in raw_data]
 
     df = pd.DataFrame.from_records(all_data_json)
-    print('df is')
-    print(df)
     df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
     df = df[cols].round(decimals=2)