leaderboard - add subtask scores (#2867)

* add subtask scores

* pacify pre-commit

lm_eval/tasks/darija_bench/README.md

@@ -16,13 +16,13 @@ Homepage: [https://huggingface.co/datasets/MBZUAI-Paris/DarijaBench](https://hug
 
 ```
 @article{shang2024atlaschatadaptinglargelanguage,
-      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect}, 
+      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect},
       author={Guokan Shang and Hadi Abdine and Yousef Khoubrane and Amr Mohamed and Yassine Abbahaddou and Sofiane Ennadir and Imane Momayiz and Xuguang Ren and Eric Moulines and Preslav Nakov and Michalis Vazirgiannis and Eric Xing},
       year={2024},
       eprint={2409.17912},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2409.17912}, 
+      url={https://arxiv.org/abs/2409.17912},
 }
 ```
 

lm_eval/tasks/darija_bench/darija_sentiment/README.md

@@ -16,13 +16,13 @@ Homepage: [https://huggingface.co/datasets/MBZUAI-Paris/DarijaBench](https://hug
 
 ```
 @article{shang2024atlaschatadaptinglargelanguage,
-      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect}, 
+      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect},
       author={Guokan Shang and Hadi Abdine and Yousef Khoubrane and Amr Mohamed and Yassine Abbahaddou and Sofiane Ennadir and Imane Momayiz and Xuguang Ren and Eric Moulines and Preslav Nakov and Michalis Vazirgiannis and Eric Xing},
       year={2024},
       eprint={2409.17912},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2409.17912}, 
+      url={https://arxiv.org/abs/2409.17912},
 }
 ```
 

lm_eval/tasks/darija_bench/darija_sentiment/darija_sentiment_electrom.yaml

@@ -4,4 +4,4 @@ test_split: electro_maroc
 - "darija_sentiment_tasks"
 "task": "darija_sentiment_electrom"
 "task_alias": "Electro Maroc"
-doc_to_choice: !function utils.doc_to_choice_2
+doc_to_choice: !function utils.doc_to_choice_2
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_sentiment/darija_sentiment_mac.yaml

@@ -4,4 +4,4 @@ test_split: mac
 - "darija_sentiment_tasks"
 "task": "darija_sentiment_mac"
 "task_alias": "MAC"
-doc_to_choice: !function utils.doc_to_choice_3
+doc_to_choice: !function utils.doc_to_choice_3
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_sentiment/darija_sentiment_msac.yaml

@@ -4,4 +4,4 @@ test_split: msac
 - "darija_sentiment_tasks"
 "task": "darija_sentiment_msac"
 "task_alias": "MSAC"
-doc_to_choice: !function utils.doc_to_choice_2
+doc_to_choice: !function utils.doc_to_choice_2
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_sentiment/darija_sentiment_msda.yaml

@@ -4,4 +4,4 @@ test_split: msda
 - "darija_sentiment_tasks"
 "task": "darija_sentiment_msda"
 "task_alias": "MSDA"
-doc_to_choice: !function utils.doc_to_choice_3
+doc_to_choice: !function utils.doc_to_choice_3
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_sentiment/darija_sentiment_myc.yaml

@@ -4,4 +4,4 @@ test_split: myc
 - "darija_sentiment_tasks"
 "task": "darija_sentiment_myc"
 "task_alias": "MYC"
-doc_to_choice: !function utils.doc_to_choice_2
+doc_to_choice: !function utils.doc_to_choice_2
\ No newline at end of file

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/README.md

@@ -16,13 +16,13 @@ Homepage: [https://huggingface.co/datasets/MBZUAI-Paris/DarijaBench](https://hug
 
 ```
 @article{shang2024atlaschatadaptinglargelanguage,
-      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect}, 
+      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect},
       author={Guokan Shang and Hadi Abdine and Yousef Khoubrane and Amr Mohamed and Yassine Abbahaddou and Sofiane Ennadir and Imane Momayiz and Xuguang Ren and Eric Moulines and Preslav Nakov and Michalis Vazirgiannis and Eric Xing},
       year={2024},
       eprint={2409.17912},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2409.17912}, 
+      url={https://arxiv.org/abs/2409.17912},
 }
 ```
 

lm_eval/tasks/darija_bench/darija_summarization/utils.py

-import evaluate
 import datasets
+import evaluate
+
 
 def strip(resps, docs):
     """
@@ -9,50 +10,72 @@ 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)
+    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)
-    return rouge.compute(predictions=predictions, references=references)["rougeL"]
+    return rouge.compute(predictions=predictions, references=references)["rougeL"]
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/README.md

@@ -16,13 +16,13 @@ Homepage: [https://huggingface.co/datasets/MBZUAI-Paris/DarijaBench](https://hug
 
 ```
 @article{shang2024atlaschatadaptinglargelanguage,
-      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect}, 
+      title={Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect},
       author={Guokan Shang and Hadi Abdine and Yousef Khoubrane and Amr Mohamed and Yassine Abbahaddou and Sofiane Ennadir and Imane Momayiz and Xuguang Ren and Eric Moulines and Preslav Nakov and Michalis Vazirgiannis and Eric Xing},
       year={2024},
       eprint={2409.17912},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2409.17912}, 
+      url={https://arxiv.org/abs/2409.17912},
 }
 ```
 

lm_eval/tasks/darija_bench/darija_translation/doda_common_yaml

-test_split: doda
+test_split: doda
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/doda_translation_dr_en.yaml

@@ -9,4 +9,4 @@ include:
 metric_list:
   - metric: !function utils.bert
     aggregation: !function utils.bertbase
-    higher_is_better: true
+    higher_is_better: true
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/doda_translation_dr_fr.yaml

@@ -9,4 +9,4 @@ include:
 metric_list:
   - metric: !function utils.bert
     aggregation: !function utils.camembert
-    higher_is_better: true
+    higher_is_better: true
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/doda_translation_dr_msa.yaml

@@ -9,4 +9,4 @@ include:
 metric_list:
   - metric: !function utils.bert
     aggregation: !function utils.arabert
-    higher_is_better: true
+    higher_is_better: true
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/doda_translation_fr_dr.yaml

@@ -9,4 +9,4 @@ include:
 metric_list:
   - metric: !function utils.bert
     aggregation: !function utils.darijabert
-    higher_is_better: true
+    higher_is_better: true
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/doda_translation_msa_dr.yaml

@@ -9,4 +9,4 @@ include:
 metric_list:
   - metric: !function utils.bert
     aggregation: !function utils.darijabert
-    higher_is_better: true
+    higher_is_better: true
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/flores_common_yaml

-test_split: flores_plus
+test_split: flores_plus
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/flores_translation_dr_en.yaml

@@ -9,4 +9,4 @@ include:
 metric_list:
   - metric: !function utils.bert
     aggregation: !function utils.bertbase
-    higher_is_better: true
+    higher_is_better: true
\ No newline at end of file

lm_eval/tasks/darija_bench/darija_translation/flores_translation_dr_fr.yaml

@@ -9,4 +9,4 @@ include:
 metric_list:
   - metric: !function utils.bert
     aggregation: !function utils.camembert
-    higher_is_better: true
+    higher_is_better: true
\ No newline at end of file