Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimgsm/translate/prompt_1/afrimgsm_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_xho_prompt_1

lm_eval/tasks/afrimgsm/translate/prompt_1/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 %}'
+doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% 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_1/afrimgsm_translate_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_yor_prompt_1

lm_eval/tasks/afrimgsm/translate/prompt_1/afrimgsm_translate_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_zul_prompt_1

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_amh_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_ewe_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_fra_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_hau_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_ibo_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_kin_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_lin_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_lug_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_orm_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_sna_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_sot_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_swa_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_twi_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_wol_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/afrimgsm_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrimgsm_translate_yaml
+task: afrimgsm_translate_xho_prompt_2

lm_eval/tasks/afrimgsm/translate/prompt_2/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 %}'
+doc_to_text: "Give direct numerical answers for the question provided. \n\nQuestion: {{question}} \nAnswer: "
+target_delimiter: ""
+generation_kwargs:
+  do_sample: false
+  until:
+  - 'Question:'
+  - </s>
+  - <|im_end|>
+should_decontaminate: true
+doc_to_decontamination_query: "Answer: "
+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