Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+doc_to_text: "For mathematical questions provided in Lingala language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_lin_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+doc_to_text: "For mathematical questions provided in Luganda language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_lug_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+doc_to_text: "For mathematical questions provided in Oromo language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_orm_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+doc_to_text: "For mathematical questions provided in chiShona language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_sna_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+doc_to_text: "For mathematical questions provided in Sesotho language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_sot_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_text: "For mathematical questions provided in Swahili language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_swa_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_text: "For mathematical questions provided in Twi language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_twi_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_vai.yaml

+# Generated by utils.py
+dataset_name: vai
+doc_to_text: "For mathematical questions provided in Vai language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_vai_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+doc_to_text: "For mathematical questions provided in Wolof language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_wol_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+doc_to_text: "For mathematical questions provided in isiXhosa language. Supply the\
+  \ accurate step by step answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nStep by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_xho_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_yaml

+tag: afrimgsm_tt_cot_tasks
+dataset_path: masakhane/afrimgsm-translate-test
+dataset_name: null  # Overridden by language-specific config.
+output_type: generate_until
+test_split: test
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "The answer is (\\-?[0-9\\.\\,]+)"
+      - function: "take_first"
+  - filter:
+    - function: regex
+      group_select: -1
+      regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
+    - function: take_first
+    name: flexible-extract
+metadata:
+  version: 2.0

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+doc_to_text: "For mathematical questions provided in Yoruba language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_yor_prompt_5

lm_eval/tasks/afrimgsm/translate_cot/prompt_5/afrimgsm_cot_translate_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+doc_to_text: "For mathematical questions provided in Zulu language. Supply the accurate\
+  \ step by step answer to the provided question. \n\nQuestion: {{question}} \nStep\
+  \ by step answer: "
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_zul_prompt_5

lm_eval/tasks/afrimmlu/direct/afrimmlu.yaml

+group: afrimmlu-irokobench
+task:
+  - afrimmlu_tasks_prompt_1
+  - afrimmlu_tasks_prompt_2
+  - afrimmlu_tasks_prompt_3
+  - afrimmlu_tasks_prompt_4
+  - afrimmlu_tasks_prompt_5
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 2

lm_eval/tasks/afrimmlu/direct/afrimmlu_common_yaml

-tag:
-  - afrimmlu
-  - afrimmlu_direct
-task: null
-dataset_path: masakhane/afrimmlu
-dataset_name: null
-output_type: multiple_choice
-validation_split: validation
-test_split: test
-fewshot_split: validation
-doc_to_text: !function utils.doc_to_text
-doc_to_target: "{{['A', 'B', 'C', 'D'].index(answer)}}"
-doc_to_choice: !function utils.doc_to_choice
-should_decontaminate: true
-doc_to_decontamination_query: "Question: {{question}}\nAnswer:"
-metric_list:
-  - metric: f1
-    aggregation: !function utils.weighted_f1_score
-    # aggregation: mean
-    average: weighted
-    hf_evaluate: true
-    higher_is_better: True
-    ignore_case: true
-    ignore_punctuation: true
-    regexes_to_ignore:
-      - ","
-      - "\\$"
-  - metric: acc
-    aggregation: mean
-    higher_is_better: true
-    ignore_case: true
-    ignore_punctuation: true
-    regexes_to_ignore:
-      - ","
-      - "\\$"
-metadata:
-  version: 1.0

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_amh.yaml

-dataset_name: amh
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_amh

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_eng.yaml

-dataset_name: eng
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_eng

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_ewe.yaml

-dataset_name: ewe
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_ewe

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_fra.yaml

-dataset_name: fra
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_fra

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_hau.yaml

-dataset_name: hau
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_hau