f

src/about.py

@@ -44,6 +44,9 @@ class Tasks(Enum):
     # task28 = Task("polish_abstractive_poquad_rag", "levenshtein,none", "abstractive_poquad_rag", "other", 0.0)
     # task29 = Task("polish_abstractive_poquad_open_book", "levenshtein,none", "abstractive_poquad_open_book", "other", 0.0)
     task30a = Task("polish_pes", "exact_match,score-first", "pes", "generate_until", 0.0)
+    task60 = Task("polish_pes_medycyna_rodzinna", "exact_match,score-first", "medycyna_rodzinna", "generate_until", 0.0)
+    task73 = Task("polish_pes_pediatria", "exact_match,score-first", "pediatria", "generate_until", 0.0)
+
     task30 = Task("polish_pes_alergologia", "exact_match,score-first", "alergologia", "generate_until", 0.0)
     task31 = Task("polish_pes_anestezjologia", "exact_match,score-first", "anestezjologia", "generate_until", 0.0)
     task32 = Task("polish_pes_angiologia", "exact_match,score-first", "angiologia", "generate_until", 0.0)
@@ -74,7 +77,7 @@ class Tasks(Enum):
     task57 = Task("polish_pes_medycyna_pracy", "exact_match,score-first", "medycyna_pracy", "generate_until", 0.0)
     task58 = Task("polish_pes_medycyna_paliatywna", "exact_match,score-first", "medycyna_paliatywna", "generate_until", 0.0)
     task59 = Task("polish_pes_medycyna_ratunkowa", "exact_match,score-first", "medycyna_ratunkowa", "generate_until", 0.0)
-    task60 = Task("polish_pes_medycyna_rodzinna", "exact_match,score-first", "medycyna_rodzinna", "generate_until", 0.0)
+
     task61 = Task("polish_pes_medycyna_sportowa", "exact_match,score-first", "medycyna_sportowa", "generate_until", 0.0)
     task62 = Task("polish_pes_nefrologia", "exact_match,score-first", "nefrologia", "generate_until", 0.0)
     task63 = Task("polish_pes_neonatologia", "exact_match,score-first", "neonatologia", "generate_until", 0.0)
@@ -87,7 +90,7 @@ class Tasks(Enum):
     task70 = Task("polish_pes_ortopedia", "exact_match,score-first", "ortopedia", "generate_until", 0.0)
     task71 = Task("polish_pes_otolaryngologia", "exact_match,score-first", "otolaryngologia", "generate_until", 0.0)
     task72 = Task("polish_pes_patomorfologia", "exact_match,score-first", "patomorfologia", "generate_until", 0.0)
-    task73 = Task("polish_pes_pediatria", "exact_match,score-first", "pediatria", "generate_until", 0.0)
+    
     task74 = Task("polish_pes_perinatologia", "exact_match,score-first", "perinatologia", "generate_until", 0.0)
     task75 = Task("polish_pes_periodontologia", "exact_match,score-first", "periodontologia", "generate_until", 0.0)
     task76 = Task("polish_pes_poloznictwo_i_ginekologia", "exact_match,score-first", "poloznictwo_i_ginekologia", "generate_until", 0.0)

src/leaderboard/read_evals.py

@@ -397,9 +397,9 @@ def get_raw_eval_results(results_path: str, requests_path: str, metadata) -> lis
         except dateutil.parser._parser.ParserError:
             files = [files[-1]]
 
-        for file in files:
-            if '_polish_pes_' not in file: continue
-            model_result_filepaths.append(os.path.join(root, file))
+        # for file in files:
+            # if '_polish_pes_' not in file: continue
+            # model_result_filepaths.append(os.path.join(root, file))
 
     # print('PATHS:', model_result_filepaths)