Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_twi.yaml

-# Generated by utils.py
-dataset_name: twi
-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 %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: direct_yaml
-task: afrimgsm_direct_twi

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_wol.yaml

-# Generated by utils.py
-dataset_name: wol
-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 %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: direct_yaml
-task: afrimgsm_direct_wol

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_xho.yaml

-# Generated by utils.py
-dataset_name: xho
-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 %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: direct_yaml
-task: afrimgsm_direct_xho

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_yor.yaml

-# Generated by utils.py
-dataset_name: yor
-doc_to_target: '{% if answer is not none %}{{answer[16:]}}{% else %}{{answer_number|string}}{% endif %}'
-doc_to_text: '{% if answer is not none %}{{question+"\nAnswer:"}}{% else %}{{"Question: "+question+"\nAnswer:"}}{% endif %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: direct_yaml
-task: afrimgsm_direct_yor

lm_eval/tasks/afrimgsm/direct/afrimgsm_direct_zul.yaml

-# Generated by utils.py
-dataset_name: zul
-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 %}'
-generation_kwargs:
-  do_sample: false
-  until:
-  - 'Question:'
-  - </s>
-  - <|im_end|>
-include: direct_yaml
-task: afrimgsm_direct_zul

lm_eval/tasks/afrimgsm/direct/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_direct
-dataset_path: masakhane/afrimgsm
-dataset_name: null  # Overridden by language-specific config.
-output_type: generate_until
-# training_split: train
-test_split: test
-target_delimiter: ""
-generation_kwargs:
-  until:
-    - "\n\n"
-    - "\n"
-  do_sample: false
-  temperature: 0.0
-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_1/afrimgsm_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimgsm_yaml
+task: afrimgsm_amh_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+include: afrimgsm_yaml
+task: afrimgsm_eng_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimgsm_yaml
+task: afrimgsm_ewe_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimgsm_yaml
+task: afrimgsm_fra_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimgsm_yaml
+task: afrimgsm_hau_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimgsm_yaml
+task: afrimgsm_ibo_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrimgsm_yaml
+task: afrimgsm_kin_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrimgsm_yaml
+task: afrimgsm_lin_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrimgsm_yaml
+task: afrimgsm_lug_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrimgsm_yaml
+task: afrimgsm_orm_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrimgsm_yaml
+task: afrimgsm_sna_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrimgsm_yaml
+task: afrimgsm_sot_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrimgsm_yaml
+task: afrimgsm_swa_prompt_1

lm_eval/tasks/afrimgsm/direct/prompt_1/afrimgsm_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrimgsm_yaml
+task: afrimgsm_twi_prompt_1