Merge branch 'upstream' into 'mmlu-pro'

add tokenizer logs info (#1731)

See merge request shijie.yu/lm-evaluation-harness!4

lm_eval/tasks/cmmlu/cmmlu_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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_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/commonsense_qa/README.md

+# Task-name
+
+### Paper
+
+Title: `COMMONSENSEQA: A Question Answering Challenge Targeting
+Commonsense Knowledge`
+
+Abstract: https://arxiv.org/pdf/1811.00937.pdf
+
+CommonsenseQA is a multiple-choice question answering dataset that requires different types of commonsense knowledge to predict the correct answers.
+It contains 12,102 questions with one correct answer and four distractor answers.
+
+Homepage: https://www.tau-nlp.org/commonsenseqa
+
+
+### Citation
+
+```
+@inproceedings{talmor-etal-2019-commonsenseqa,
+    title = "{C}ommonsense{QA}: A Question Answering Challenge Targeting Commonsense Knowledge",
+    author = "Talmor, Alon  and
+      Herzig, Jonathan  and
+      Lourie, Nicholas  and
+      Berant, Jonathan",
+    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
+    month = jun,
+    year = "2019",
+    address = "Minneapolis, Minnesota",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/N19-1421",
+    doi = "10.18653/v1/N19-1421",
+    pages = "4149--4158",
+    archivePrefix = "arXiv",
+    eprint        = "1811.00937",
+    primaryClass  = "cs",
+}
+```
+
+### Groups and Tasks
+
+#### Groups
+
+* Not part of a group yet.
+
+#### Tasks
+
+* `commonsense_qa`: Represents the "random" split from the paper. Uses an MMLU-style prompt, as (presumably) used by Llama evaluations.
+
+### Checklist
+
+For adding novel benchmarks/datasets to the library:
+* [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? If so, have you checked against the reference implementation and documented how to run such a test?
+
+
+If other tasks on this dataset are already supported:
+* [ ] Is the "Main" variant of this task clearly denoted?
+* [ ] Have you provided a short sentence in a README on what each new variant adds / evaluates?
+* [ ] Have you noted which, if any, published evaluation setups are matched by this variant?

lm_eval/tasks/commonsense_qa/default.yaml

+task: commonsense_qa
+dataset_path: tau/commonsense_qa
+training_split: train
+validation_split: validation
+output_type: multiple_choice
+doc_to_text: "Question: {{ question.strip() }}\nA. {{choices['text'][0]}}\nB. {{choices['text'][1]}}\nC. {{choices['text'][2]}}\nD. {{choices['text'][3]}}\nE. {{choices['text'][4]}}\nAnswer:"
+doc_to_target: answerKey
+doc_to_choice: ['A', 'B', 'C', 'D', 'E']
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/copal_id/standard.yaml

-group: copal_id
+tag: copal_id
 task: copal_id_standard
 task_alias: standard
 dataset_path: haryoaw/COPAL

lm_eval/tasks/crows_pairs/crows_pairs_english.yaml

-group:
+tag:
   - crows_pairs
-  - social_bias
-  - loglikelihood
 task: crows_pairs_english
 dataset_path: BigScienceBiasEval/crows_pairs_multilingual
 dataset_name: english