Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_twi_prompt_1

lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_vai.yaml

+# Generated by utils.py
+dataset_name: vai
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_vai_prompt_1

lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_wol_prompt_1

lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_xho_prompt_1

lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_yaml

+tag:
+    - afrimgsm_cot_tasks
+    - afrimgsm_cot_tasks_prompt_1
+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 %}'
+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|>
+  - <|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_1/afrimgsm_cot_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_yor_prompt_1

lm_eval/tasks/afrimgsm/direct_cot/prompt_1/afrimgsm_cot_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_zul_prompt_1

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_amh_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_eng_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_ewe_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_fra_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_hau_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_ibo_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_kin_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_lin_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_lug_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_orm_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_sna_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_sot_prompt_2

lm_eval/tasks/afrimgsm/direct_cot/prompt_2/afrimgsm_cot_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrimgsm_cot_yaml
+task: afrimgsm_cot_swa_prompt_2