Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_ibo.yaml

-dataset_name: ibo
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_ibo

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_kin.yaml

-dataset_name: kin
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_kin

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_lin.yaml

-dataset_name: lin
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_lin

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_lug.yaml

-dataset_name: lug
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_lug

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_orm.yaml

-dataset_name: orm
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_orm

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_sna.yaml

-dataset_name: sna
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_sna

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_sot.yaml

-dataset_name: sot
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_sot

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_swa.yaml

-dataset_name: swa
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_swa

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_twi.yaml

-dataset_name: twi
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_twi

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_wol.yaml

-dataset_name: wol
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_wol

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_xho.yaml

-dataset_name: xho
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_xho

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_yor.yaml

-dataset_name: yor
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_yor

lm_eval/tasks/afrimmlu/direct/afrimmlu_direct_zul.yaml

-dataset_name: zul
-include: afrimmlu_common_yaml
-task: afrimmlu_direct_zul

lm_eval/tasks/afrimmlu/direct/prompt_1/afrimmlu_direct

+tag:
+    - afrimmlu_tasks
+    - afrimmlu_tasks_prompt_1
+    - afrobench_mmlu_tasks
+dataset_path: masakhane/afrimmlu
+dataset_name: null
+output_type: multiple_choice
+validation_split: validation
+test_split: test
+fewshot_split: validation
+doc_to_text: !function utils.doc_to_text
+doc_to_target: "{{['A', 'B', 'C', 'D'].index(answer)}}"
+doc_to_choice: !function utils.doc_to_choice
+should_decontaminate: true
+doc_to_decontamination_query: "Question: {{question}}\nAnswer:"
+metric_list:
+  - metric: f1
+    aggregation: !function utils.weighted_f1_score
+    # aggregation: mean
+    average: weighted
+    hf_evaluate: true
+    higher_is_better: True
+    ignore_case: true
+    ignore_punctuation: true
+    regexes_to_ignore:
+      - ","
+      - "\\$"
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+    regexes_to_ignore:
+      - ","
+      - "\\$"
+metadata:
+  version: 1.0

lm_eval/tasks/afrimmlu/direct/prompt_1/afrimmlu_direct_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimmlu_direct
+task: afrimmlu_direct_amh_prompt_1

lm_eval/tasks/afrimmlu/direct/prompt_1/afrimmlu_direct_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+include: afrimmlu_direct
+task: afrimmlu_direct_eng_prompt_1

lm_eval/tasks/afrimmlu/direct/prompt_1/afrimmlu_direct_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimmlu_direct
+task: afrimmlu_direct_ewe_prompt_1

lm_eval/tasks/afrimmlu/direct/prompt_1/afrimmlu_direct_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimmlu_direct
+task: afrimmlu_direct_fra_prompt_1

lm_eval/tasks/afrimmlu/direct/prompt_1/afrimmlu_direct_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimmlu_direct
+task: afrimmlu_direct_hau_prompt_1

lm_eval/tasks/afrimmlu/direct/prompt_1/afrimmlu_direct_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimmlu_direct
+task: afrimmlu_direct_ibo_prompt_1