Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_vai.yaml

+# Generated by utils.py
+dataset_name: vai
+include: afrimgsm_yaml
+task: afrimgsm_vai_prompt_3

lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrimgsm_yaml
+task: afrimgsm_wol_prompt_3

lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrimgsm_yaml
+task: afrimgsm_xho_prompt_3

lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_yaml

+tag:
+    - afrimgsm_tasks
+    - afrimgsm_tasks_prompt_3
+dataset_path: masakhane/afrimgsm
+output_type: generate_until
+test_split: test
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+doc_to_text: "Solve the following math question \n\nQuestion: {{question}} \nAnswer: "
+target_delimiter: ""
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+filter_list:
+  - name: remove_whitespace
+    filter:
+      - function: remove_whitespace
+      - function: take_first
+  - filter:
+    - function: regex
+      group_select: -1
+      regex_pattern: (-?[$0-9.,]{2,})|(-?[0-9]+)
+    - function: take_first
+    name: flexible-extract
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+metadata:
+  version: 2.0

lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrimgsm_yaml
+task: afrimgsm_yor_prompt_3

lm_eval/tasks/afrimgsm/direct/prompt_3/afrimgsm_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrimgsm_yaml
+task: afrimgsm_zul_prompt_3

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_amh_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_eng_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_ewe_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_fra_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_hau_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_ibo_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_kin_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_lin_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_lug_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_orm_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_sna_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_sot_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_swa_prompt_4

lm_eval/tasks/afrimgsm/direct/prompt_4/afrimgsm_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_text: "Answer the given question with the appropriate numerical value, ensuring\
+  \ that the response is clear and without any supplementary information. \n\nQuestion:\
+  \ {{question}} \nAnswer: "
+include: afrimgsm_yaml
+task: afrimgsm_twi_prompt_4