Merge branch 'main' into feature/eval_from_config

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrimmlu_direct
+task: afrimmlu_direct_kin_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrimmlu_direct
+task: afrimmlu_direct_lin_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrimmlu_direct
+task: afrimmlu_direct_lug_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrimmlu_direct
+task: afrimmlu_direct_orm_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrimmlu_direct
+task: afrimmlu_direct_sna_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrimmlu_direct
+task: afrimmlu_direct_sot_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrimmlu_direct
+task: afrimmlu_direct_swa_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrimmlu_direct
+task: afrimmlu_direct_twi_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrimmlu_direct
+task: afrimmlu_direct_wol_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrimmlu_direct
+task: afrimmlu_direct_xho_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrimmlu_direct
+task: afrimmlu_direct_yor_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/afrimmlu_direct_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrimmlu_direct
+task: afrimmlu_direct_zul_prompt_4

lm_eval/tasks/afrimmlu/direct/prompt_4/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 = """Analyze each question critically and determine the most correct option based on your understanding of the subject matter
+
+Question: {question}
+Choices:
+        A: {choice1}
+        B: {choice2}
+        C: {choice3}
+        D: {choice4}
+Answer: """
+
+    choices = eval(doc["choices"])
+    text = output.format(
+        question=doc["question"],
+        choice1=choices[0],
+        choice2=choices[1],
+        choice3=choices[2],
+        choice4=choices[3],
+    )
+    return text

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct

+tag:
+    - afrimmlu_tasks
+    - afrimmlu_tasks_prompt_5
+    - 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_5/afrimmlu_direct_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrimmlu_direct
+task: afrimmlu_direct_amh_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_eng.yaml

+# Generated by utils.py
+dataset_name: eng
+include: afrimmlu_direct
+task: afrimmlu_direct_eng_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrimmlu_direct
+task: afrimmlu_direct_ewe_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrimmlu_direct
+task: afrimmlu_direct_fra_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrimmlu_direct
+task: afrimmlu_direct_hau_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/afrimmlu_direct_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrimmlu_direct
+task: afrimmlu_direct_ibo_prompt_5