leaderboard - add subtask scores (#2867)

* add subtask scores

* pacify pre-commit

lm_eval/tasks/darija_bench/darija_sentiment/utils.py

 from lm_eval.api.filter import Filter
 from lm_eval.api.registry import register_filter
 
-alpha = ['A', 'B', 'C']
+
+alpha = ["A", "B", "C"]
 out_dic = {"ايجابي": 1, "سلبي": 0, "ماكينش إحساس": 2}
 
+
 def doc_to_text(doc):
-    return doc["messages"][0]["content"].replace('-سلبي', 'A. سلبي').replace('-ايجابي', 'B. ايجابي').replace('-ماكينش إحساس', 'C. ماكينش إحساس\nThe answer should be strictly one letter of the following: A, B, C.')#.replace('شنو هو الإحساس ديال هاد الجملة؟', 'شنو هو الإحساس ديال هاد الجملة؟')
+    return (
+        doc["messages"][0]["content"]
+        .replace("-سلبي", "A. سلبي")
+        .replace("-ايجابي", "B. ايجابي")
+        .replace(
+            "-ماكينش إحساس",
+            "C. ماكينش إحساس\nThe answer should be strictly one letter of the following: A, B, C.",
+        )
+    )  # .replace('شنو هو الإحساس ديال هاد الجملة؟', 'شنو هو الإحساس ديال هاد الجملة؟')
+
 
 def doc_to_choice_3(doc):
     return alpha
 
+
 def doc_to_choice_2(doc):
     return alpha[:2]
 
+
 def doc_to_target(doc):
     return alpha[out_dic[doc["messages"][1]["content"]]]
-

lm_eval/tasks/darija_bench/darija_summarization/utils.py

-import evaluate
 import datasets
+import evaluate
+
 
 def strip(resps, docs):
     """
@@ -9,49 +10,71 @@ def strip(resps, docs):
 
 
 def doc_to_text(doc):
-    doc_text = doc["messages"][0]["content"].replace("لخص هاد المقطع", "لخص هاد المقطع في ٣٠ كلمة")
+    doc_text = doc["messages"][0]["content"].replace(
+        "لخص هاد المقطع", "لخص هاد المقطع في ٣٠ كلمة"
+    )
     return doc_text
 
+
 def doc_to_target(doc):
     return doc["messages"][1]["content"]
 
+
 def bert(items):
     return items
 
+
 def Average(lst):
     return sum(lst) / len(lst)
 
+
 def darijabert(items):
-    bert_model = 'SI2M-Lab/DarijaBERT'
+    bert_model = "SI2M-Lab/DarijaBERT"
     bert_score = evaluate.load("bertscore")
     predictions, references = zip(*items)
-    bert = bert_score.compute(predictions=predictions, references=references, model_type=bert_model, num_layers=12)
-    return Average(bert['f1'])
+    bert = bert_score.compute(
+        predictions=predictions,
+        references=references,
+        model_type=bert_model,
+        num_layers=12,
+    )
+    return Average(bert["f1"])
+
 
 def rouge1(items):
     return items
+
+
 def rougeL(items):
     return items
+
+
 def rouge2(items):
     return items
+
+
 def rougeLsum(items):
     return items
 
+
 def agg_rougelsum(items):
     rouge = evaluate.load("rouge")
     predictions, references = zip(*items)
     return rouge.compute(predictions=predictions, references=references)["rougeLsum"]
 
+
 def agg_rouge1(items):
     rouge = evaluate.load("rouge")
     predictions, references = zip(*items)
     return rouge.compute(predictions=predictions, references=references)["rouge1"]
 
+
 def agg_rouge2(items):
     rouge = evaluate.load("rouge")
     predictions, references = zip(*items)
     return rouge.compute(predictions=predictions, references=references)["rouge2"]
 
+
 def agg_rougel(items):
     rouge = evaluate.load("rouge")
     predictions, references = zip(*items)