update

src/backend/run_eval_suite.py

@@ -3,6 +3,9 @@ from lm_eval.tasks import initialize_tasks, include_task_folder
 
 from src.backend.manage_requests import EvalRequest
 
+from src.backend.tasks.xsum.task import XSum
+from src.backend.tasks.cnndm.task import CNNM
+
 import logging
 
 logging.getLogger("openai").setLevel(logging.WARNING)

src/backend/tasks/cnndm/task.py

@@ -60,7 +60,7 @@ def rouge(refs, preds):
 
 
 @register_task("cnndm")
-class CnnDm(Task):
+class CNNDM(Task):
     VERSION = 0
     DATASET_PATH = "cnn_dailymail"
     DATASET_NAME = "3.0.0"

src/backend/tasks/xsum/task.py

@@ -131,6 +131,8 @@ class XSum(Task):
     def process_results(self, doc, results):
         completion = results[0]
 
+        # breakpoint()
+
         document = doc["document"]
         gold_summary = doc["summary"]