Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimgsm/direct_cot/prompt_5/afrimgsm_cot_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_yaml
+task: afrimgsm_cot_twi_prompt_5

lm_eval/tasks/afrimgsm/direct_cot/prompt_5/afrimgsm_cot_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_yaml
+task: afrimgsm_cot_vai_prompt_5

lm_eval/tasks/afrimgsm/direct_cot/prompt_5/afrimgsm_cot_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_yaml
+task: afrimgsm_cot_wol_prompt_5

lm_eval/tasks/afrimgsm/direct_cot/prompt_5/afrimgsm_cot_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_yaml
+task: afrimgsm_cot_xho_prompt_5

lm_eval/tasks/afrimgsm/direct_cot/prompt_5/afrimgsm_cot_yaml

+tag:
+    - afrimgsm_cot_tasks
+    - afrimgsm_cot_tasks_prompt_5
+dataset_path: masakhane/afrimgsm
+dataset_name: null  # Overridden by language-specific config.
+output_type: generate_until
+training_split: train
+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|>
+  - <|eot_id|>
+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/direct_cot/prompt_5/afrimgsm_cot_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_yaml
+task: afrimgsm_cot_yor_prompt_5

lm_eval/tasks/afrimgsm/direct_cot/prompt_5/afrimgsm_cot_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_yaml
+task: afrimgsm_cot_zul_prompt_5

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_amh.yaml

-# Generated by utils.py
-dataset_name: amh
-doc_to_target: '{% if answer is not none %}{{answer[15:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_amh

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_eng.yaml

-# Generated by utils.py
-dataset_name: eng
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_eng

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ewe.yaml

-# Generated by utils.py
-dataset_name: ewe
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_ewe

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_fra.yaml

-# Generated by utils.py
-dataset_name: fra
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_fra

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_hau.yaml

-# Generated by utils.py
-dataset_name: hau
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_hau

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_ibo.yaml

-# Generated by utils.py
-dataset_name: ibo
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_ibo

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_kin.yaml

-# Generated by utils.py
-dataset_name: kin
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_kin

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lin.yaml

-# Generated by utils.py
-dataset_name: lin
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_lin

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_lug.yaml

-# Generated by utils.py
-dataset_name: lug
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_lug

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_orm.yaml

-# Generated by utils.py
-dataset_name: orm
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_orm

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sna.yaml

-# Generated by utils.py
-dataset_name: sna
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_sna

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_sot.yaml

-# Generated by utils.py
-dataset_name: sot
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_sot

lm_eval/tasks/afrimgsm/en_cot/afrimgsm_en_cot_swa.yaml

-# Generated by utils.py
-dataset_name: swa
-doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nStep-by-Step Answer:"}}{% else %}{{"Question: "+question+"\nStep-by-Step Answer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: cot_yaml
-task: afrimgsm_en_cot_swa