Merge branch 'main' into feature/eval_from_config

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

+# Generated by utils.py
+dataset_name: kin
+include: afrimmlu_direct
+task: afrimmlu_direct_kin_prompt_5

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

+# Generated by utils.py
+dataset_name: lin
+include: afrimmlu_direct
+task: afrimmlu_direct_lin_prompt_5

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

+# Generated by utils.py
+dataset_name: lug
+include: afrimmlu_direct
+task: afrimmlu_direct_lug_prompt_5

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

+# Generated by utils.py
+dataset_name: orm
+include: afrimmlu_direct
+task: afrimmlu_direct_orm_prompt_5

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

+# Generated by utils.py
+dataset_name: sna
+include: afrimmlu_direct
+task: afrimmlu_direct_sna_prompt_5

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

+# Generated by utils.py
+dataset_name: sot
+include: afrimmlu_direct
+task: afrimmlu_direct_sot_prompt_5

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

+# Generated by utils.py
+dataset_name: swa
+include: afrimmlu_direct
+task: afrimmlu_direct_swa_prompt_5

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

+# Generated by utils.py
+dataset_name: twi
+include: afrimmlu_direct
+task: afrimmlu_direct_twi_prompt_5

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

+# Generated by utils.py
+dataset_name: wol
+include: afrimmlu_direct
+task: afrimmlu_direct_wol_prompt_5

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

+# Generated by utils.py
+dataset_name: xho
+include: afrimmlu_direct
+task: afrimmlu_direct_xho_prompt_5

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

+# Generated by utils.py
+dataset_name: yor
+include: afrimmlu_direct
+task: afrimmlu_direct_yor_prompt_5

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

+# Generated by utils.py
+dataset_name: zul
+include: afrimmlu_direct
+task: afrimmlu_direct_zul_prompt_5

lm_eval/tasks/afrimmlu/direct/prompt_5/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 = """Given your proficiency in {subject}, please answer the subsequent multiple-choice question with 'A', 'B', 'C', or 'D'.
+
+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/gen_utils.py

+import argparse
+import os
+
+import yaml
+
+
+class FunctionTag:
+    def __init__(self, value):
+        self.value = value
+
+
+def gen_lang_yamls(output_dir: str, overwrite: bool, mode: str) -> None:
+    """
+    Generate a yaml file for each language.
+
+    :param output_dir: The directory to output the files to.
+    :param overwrite: Whether to overwrite files if they already exist.
+    """
+    err = []
+    languages = {
+        "eng": "English",
+        "amh": "Amharic",
+        "ibo": "Igbo",
+        "fra": "French",
+        "sna": "chiShona",
+        "wol": "Wolof",
+        "ewe": "Ewe",
+        "lin": "Lingala",
+        "lug": "Luganda",
+        "xho": "isiXhosa",
+        "kin": "Kinyarwanda",
+        "twi": "Twi",
+        "zul": "Zulu",
+        "orm": "Oromo",
+        "yor": "Yoruba",
+        "hau": "Hausa",
+        "sot": "Sesotho",
+        "swa": "Swahili",
+    }
+
+    for lang in languages.keys():
+        try:
+            file_name = f"afrimmlu_direct_{lang}.yaml"
+            task_name = f"afrimmlu_direct_{lang}_{mode}"
+            yaml_template = "afrimmlu_direct"
+            if output_dir.split("/")[-1] == "translate":
+                file_name = f"afrimmlu_translate_{lang}.yaml"
+                task_name = f"afrimmlu_translate_{lang}_{mode}"
+                yaml_template = "afrimmlu_translate"
+            yaml_details = {
+                "include": yaml_template,
+                "task": task_name,
+                "dataset_name": lang,
+            }
+            os.makedirs(f"{output_dir}/{mode}", exist_ok=True)
+            with open(
+                f"{output_dir}/{mode}/{file_name}",
+                "w" if overwrite else "x",
+                encoding="utf8",
+            ) as f:
+                f.write("# Generated by utils.py\n")
+                yaml.dump(
+                    yaml_details,
+                    f,
+                    allow_unicode=True,
+                )
+        except FileExistsError:
+            err.append(file_name)
+
+    if len(err) > 0:
+        raise FileExistsError(
+            "Files were not created because they already exist (use --overwrite flag):"
+            f" {', '.join(err)}"
+        )
+
+
+def main() -> None:
+    """Parse CLI args and generate language-specific yaml files."""
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--overwrite",
+        default=True,
+        action="store_true",
+        help="Overwrite files if they already exist",
+    )
+    parser.add_argument(
+        "--output-dir",
+        default="./direct",
+        help="Directory to write yaml files to",
+    )
+    parser.add_argument(
+        "--mode",
+        default="prompt_4",
+        choices=["prompt_1", "prompt_2", "prompt_3", "prompt_4", "prompt_5"],
+        help="Prompt number",
+    )
+    args = parser.parse_args()
+
+    gen_lang_yamls(output_dir=args.output_dir, overwrite=args.overwrite, mode=args.mode)
+
+
+if __name__ == "__main__":
+    main()

lm_eval/tasks/afrimmlu/translate/afrimmlu_common_translate_yaml

-tag:
-  - afrimmlu_translate
-task: null
-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/afrimmlu_translate_amh.yaml

-dataset_name: amh
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_amh

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_eng.yaml

-dataset_name: eng
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_eng

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_ewe.yaml

-dataset_name: ewe
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_ewe

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_fra.yaml

-dataset_name: fra
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_fra

lm_eval/tasks/afrimmlu/translate/afrimmlu_translate_hau.yaml

-dataset_name: hau
-include: afrimmlu_common_translate_yaml
-task: afrimmlu_translate_hau