merged latest

lm_eval/tasks/cmmlu/cmmlu_default_marxist_theory.yaml

+"dataset_name": "marxist_theory"
+"description": "以下是关于马克思主义理论的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_marxist_theory"

lm_eval/tasks/cmmlu/cmmlu_default_modern_chinese.yaml

+"dataset_name": "modern_chinese"
+"description": "以下是关于现代汉语的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_modern_chinese"

lm_eval/tasks/cmmlu/cmmlu_default_nutrition.yaml

+"dataset_name": "nutrition"
+"description": "以下是关于营养学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_nutrition"

lm_eval/tasks/cmmlu/cmmlu_default_philosophy.yaml

+"dataset_name": "philosophy"
+"description": "以下是关于哲学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_philosophy"

lm_eval/tasks/cmmlu/cmmlu_default_professional_accounting.yaml

+"dataset_name": "professional_accounting"
+"description": "以下是关于专业会计的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_professional_accounting"

lm_eval/tasks/cmmlu/cmmlu_default_professional_law.yaml

+"dataset_name": "professional_law"
+"description": "以下是关于专业法学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_professional_law"

lm_eval/tasks/cmmlu/cmmlu_default_professional_medicine.yaml

+"dataset_name": "professional_medicine"
+"description": "以下是关于专业医学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_professional_medicine"

lm_eval/tasks/cmmlu/cmmlu_default_professional_psychology.yaml

+"dataset_name": "professional_psychology"
+"description": "以下是关于专业心理学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_professional_psychology"

lm_eval/tasks/cmmlu/cmmlu_default_public_relations.yaml

+"dataset_name": "public_relations"
+"description": "以下是关于公共关系的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_public_relations"

lm_eval/tasks/cmmlu/cmmlu_default_security_study.yaml

+"dataset_name": "security_study"
+"description": "以下是关于安全研究的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_security_study"

lm_eval/tasks/cmmlu/cmmlu_default_sociology.yaml

+"dataset_name": "sociology"
+"description": "以下是关于社会学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_sociology"

lm_eval/tasks/cmmlu/cmmlu_default_sports_science.yaml

+"dataset_name": "sports_science"
+"description": "以下是关于体育学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_sports_science"

lm_eval/tasks/cmmlu/cmmlu_default_traditional_chinese_medicine.yaml

+"dataset_name": "traditional_chinese_medicine"
+"description": "以下是关于中医中药的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_traditional_chinese_medicine"

lm_eval/tasks/cmmlu/cmmlu_default_virology.yaml

+"dataset_name": "virology"
+"description": "以下是关于病毒学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_virology"

lm_eval/tasks/cmmlu/cmmlu_default_world_history.yaml

+"dataset_name": "world_history"
+"description": "以下是关于世界历史的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_world_history"

lm_eval/tasks/cmmlu/cmmlu_default_world_religions.yaml

+"dataset_name": "world_religions"
+"description": "以下是关于世界宗教的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_world_religions"

lm_eval/tasks/crows_pairs/README.md

@@ -93,10 +93,9 @@ All tasks evaluate the percentage of more-stereotypical sentences that are rated
 * [x] Is the task an existing benchmark in the literature?
   * [x] Have you referenced the original paper that introduced the task?
   * [x] If yes, does the original paper provide a reference implementation?
-    * [x] The original paper does not for causal language models, so
+    * [x] The original paper does not for causal language models, so this is a novel formulation of the task for autoregressive LMs.
 
 If other tasks on this dataset are already supported:
 * [x] Is the "Main" variant of this task clearly denoted?
 * [x] Have you provided a short sentence in a README on what each new variant adds / evaluates?
 * [x] Have you noted which, if any, published evaluation setups are matched by this variant?
-  * [x] This matches the evaluations performed in the [Pythia paper](https://arxiv.org/abs/2304.01373)

lm_eval/tasks/csatqa/_default_csatqa_yaml

+group: csatqa
+dataset_path: EleutherAI/csatqa
+test_split: test
+output_type: multiple_choice
+process_docs: !function utils.process_docs
+doc_to_text: "{{question}}"
+doc_to_choice: "{{choices}}"
+doc_to_target: "{{gold}}"
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/csatqa/_generate_configs.py

+"""
+Take in a YAML, and output all other splits with this YAML
+"""
+import os
+import yaml
+import argparse
+
+from tqdm import tqdm
+
+from lm_eval.logger import eval_logger
+
+SUBSETS = ["WR", "GR", "RCS", "RCSS", "RCH", "LI"]
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--base_yaml_path", required=True)
+    parser.add_argument("--save_prefix_path", default="csatqa")
+    parser.add_argument("--task_prefix", default="")
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+
+    args = parse_args()
+
+    # get filename of base_yaml so we can `"include": ` it in our other YAMLs.
+    base_yaml_name = os.path.split(args.base_yaml_path)[-1]
+    with open(args.base_yaml_path) as f:
+        base_yaml = yaml.full_load(f)
+
+    for name in tqdm(SUBSETS):
+
+        yaml_dict = {
+            "include": base_yaml_name,
+            "task": f"csatqa_{args.task_prefix}_{name}"
+            if args.task_prefix != ""
+            else f"csatqa_{name.lower()}",
+            "dataset_name": name,
+        }
+
+        file_save_path = args.save_prefix_path + f"_{name.lower()}.yaml"
+        eval_logger.info(f"Saving yaml for subset {name} to {file_save_path}")
+        with open(file_save_path, "w") as yaml_file:
+            yaml.dump(
+                yaml_dict,
+                yaml_file,
+                width=float("inf"),
+                allow_unicode=True,
+                default_style='"',
+            )

lm_eval/tasks/csatqa/csatqa_gr.yaml

+"dataset_name": "GR"
+"include": "_default_csatqa_yaml"
+"task": "csatqa_gr"