Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+doc_to_text: "For mathematical questions provided in French language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_fra_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+doc_to_text: "For mathematical questions provided in Hausa language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_hau_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+doc_to_text: "For mathematical questions provided in Igbo language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_ibo_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+doc_to_text: "For mathematical questions provided in Kinyarwanda language. Supply\
+  \ the accurate numeric answer to the provided question. \n\nQuestion: {{question}}\
+  \ \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_kin_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+doc_to_text: "For mathematical questions provided in Lingala language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_lin_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+doc_to_text: "For mathematical questions provided in Luganda language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_lug_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+doc_to_text: "For mathematical questions provided in Oromo language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_orm_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+doc_to_text: "For mathematical questions provided in chiShona language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_sna_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+doc_to_text: "For mathematical questions provided in Sesotho language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_sot_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+doc_to_text: "For mathematical questions provided in Swahili language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_swa_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+doc_to_text: "For mathematical questions provided in Twi language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_twi_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+doc_to_text: "For mathematical questions provided in Wolof language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_wol_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+doc_to_text: "For mathematical questions provided in isiXhosa language. Supply the\
+  \ accurate numeric answer to the provided question. \n\nQuestion: {{question}} \n\
+  Answer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_xho_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_yaml

+tag: afrimgsm_tt_tasks
+dataset_path: masakhane/afrimgsm-translate-test
+output_type: generate_until
+test_split: test
+doc_to_target: '{% if answer is not none %}{{answer[21:]}}{% else %}{{answer_number|string}}{% endif %}'
+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/translate/prompt_5/afrimgsm_translate_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+doc_to_text: "For mathematical questions provided in Yoruba language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_yor_prompt_5

lm_eval/tasks/afrimgsm/translate/prompt_5/afrimgsm_translate_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+doc_to_text: "For mathematical questions provided in Zulu language. Supply the accurate\
+  \ numeric answer to the provided question. \n\nQuestion: {{question}} \nAnswer: "
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_zul_prompt_5

lm_eval/tasks/afrimgsm/translate/translate_direct_yaml

-# This file will be included in the generated language-specific task configs.
-# It doesn't have a yaml file extension as it is not meant to be imported directly
-# by the harness.
-tag:
-    - afrimgsm
-    - afrimgsm_translate
-dataset_path: masakhane/afrimgsm-translate-test
-dataset_name: null  # Overridden by language-specific config.
-output_type: generate_until
-test_split: test
-generation_kwargs:
-  until:
-    - "\n\n"
-    - "\n"
-  do_sample: false
-  temperature: 0.0
-target_delimiter: " "
-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/translate_cot/afrimgsm_tt_cot.yaml

+group: afrimgsm_tt_cot-irokobench
+task:
+  - afrimgsm_tt_cot_tasks
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 2

lm_eval/tasks/afrimgsm/translate_cot/prompt_1/afrimgsm_cot_translate_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_amh_prompt_1

lm_eval/tasks/afrimgsm/translate_cot/prompt_1/afrimgsm_cot_translate_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimgsm_cot_translate_yaml
+task: afrimgsm_cot_translate_ewe_prompt_1