Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrimmlu_translate
+task: afrimmlu_translate_lin_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrimmlu_translate
+task: afrimmlu_translate_lug_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrimmlu_translate
+task: afrimmlu_translate_orm_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrimmlu_translate
+task: afrimmlu_translate_sna_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrimmlu_translate
+task: afrimmlu_translate_sot_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrimmlu_translate
+task: afrimmlu_translate_swa_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrimmlu_translate
+task: afrimmlu_translate_twi_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrimmlu_translate
+task: afrimmlu_translate_wol_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrimmlu_translate
+task: afrimmlu_translate_xho_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrimmlu_translate
+task: afrimmlu_translate_yor_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/afrimmlu_translate_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrimmlu_translate
+task: afrimmlu_translate_zul_prompt_2

lm_eval/tasks/afrimmlu/translate/prompt_2/utils.py

+from lm_eval.utils import weighted_f1_score
+
+
+def doc_to_choice(doc):
+    choices = eval(doc["choices"])
+    return choices
+
+
+def doc_to_text(doc):
+    output = """As an expert in {subject}, choose the most accurate answer to the question below.
+Your goal is to select the correct option 'A', 'B', 'C', or 'D' by understanding the nuances of the topic.
+
+Question: {question}
+Choices:
+        A: {choice1}
+        B: {choice2}
+        C: {choice3}
+        D: {choice4}
+Answer: """
+
+    choices = eval(doc["choices"])
+    text = output.format(
+        subject=doc["subject"],
+        question=doc["question"],
+        choice1=choices[0],
+        choice2=choices[1],
+        choice3=choices[2],
+        choice4=choices[3],
+    )
+    return text

lm_eval/tasks/afrimmlu/translate/prompt_3/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_3/afrimmlu_translate_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimmlu_translate
+task: afrimmlu_translate_amh_prompt_3

lm_eval/tasks/afrimmlu/translate/prompt_3/afrimmlu_translate_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimmlu_translate
+task: afrimmlu_translate_ewe_prompt_3

lm_eval/tasks/afrimmlu/translate/prompt_3/afrimmlu_translate_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimmlu_translate
+task: afrimmlu_translate_fra_prompt_3

lm_eval/tasks/afrimmlu/translate/prompt_3/afrimmlu_translate_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimmlu_translate
+task: afrimmlu_translate_hau_prompt_3

lm_eval/tasks/afrimmlu/translate/prompt_3/afrimmlu_translate_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimmlu_translate
+task: afrimmlu_translate_ibo_prompt_3

lm_eval/tasks/afrimmlu/translate/prompt_3/afrimmlu_translate_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrimmlu_translate
+task: afrimmlu_translate_kin_prompt_3

lm_eval/tasks/afrimmlu/translate/prompt_3/afrimmlu_translate_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrimmlu_translate
+task: afrimmlu_translate_lin_prompt_3