Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_ibo.yaml

-dataset_name: ibo
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_ibo

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_kin.yaml

-dataset_name: kin
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_kin

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_lin.yaml

-dataset_name: lin
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_lin

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_lug.yaml

-dataset_name: lug
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_lug

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_orm.yaml

-dataset_name: orm
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_orm

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_sna.yaml

-dataset_name: sna
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_sna

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_sot.yaml

-dataset_name: sot
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_sot

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_swa.yaml

-dataset_name: swa
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_swa

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_twi.yaml

-dataset_name: twi
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_twi

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_wol.yaml

-dataset_name: wol
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_wol

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_xho.yaml

-dataset_name: xho
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_xho

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_yor.yaml

-dataset_name: yor
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_yor

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_zul.yaml

-dataset_name: zul
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_zul

lm_eval/tasks/afrimmlu/translate/afrimmlu_tt.yaml

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

lm_eval/tasks/afrimmlu/translate/prompt_1/afrimmlu_translate

+tag: afrimmlu_tt_tasks
+dataset_path: masakhane/afrimmlu-translate-test
+dataset_name: null
+output_type: multiple_choice
+test_split: test
+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/translate/prompt_1/afrimmlu_translate_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimmlu_translate
+task: afrimmlu_translate_amh_prompt_1

lm_eval/tasks/afrimmlu/translate/prompt_1/afrimmlu_translate_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimmlu_translate
+task: afrimmlu_translate_ewe_prompt_1

lm_eval/tasks/afrimmlu/translate/prompt_1/afrimmlu_translate_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimmlu_translate
+task: afrimmlu_translate_fra_prompt_1

lm_eval/tasks/afrimmlu/translate/prompt_1/afrimmlu_translate_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimmlu_translate
+task: afrimmlu_translate_hau_prompt_1

lm_eval/tasks/afrimmlu/translate/prompt_1/afrimmlu_translate_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimmlu_translate
+task: afrimmlu_translate_ibo_prompt_1