standardize spaces

Author: jannalulu

lm_eval/tasks/longbench/_generate_config.py

@@ -64,13 +64,13 @@
     "multi_news": "You are given several news passages. Write a one-page summary of all news. \n\nNews:\n{context}\n\nNow, write a one-page summary of all the news.\n\nSummary:",
     "vcsum": "下面有一段会议记录，请你阅读后，写一段总结，总结会议的内容。\n会议记录：\n{context}\n\n会议总结：",
     "trec": "Please determine the type of the question below. Here are some examples of questions.\n\n{context}\n{question}",
-    "triviaqa": "Answer the question based on the given passage. Only give me the answer and do not output any other words. The following are some examples.\n\n{context}\n\n{question}",
-    "samsum": "Summarize the dialogue into a few short sentences. The following are some examples.\n\n{context}\n\n{question}",
+    "triviaqa": "Answer the question based on the given passage. Only give me the answer and do not output any other words. The following are some examples.\n\n{context}\n{question}",
+    "samsum": "Summarize the dialogue into a few short sentences. The following are some examples.\n\n{context}\n{question}",
     "lsht": "请判断给定新闻的类别，下面是一些例子。\n\n{context}\n{question}",
     "passage_count": "There are some paragraphs below sourced from Wikipedia. Some of them may be duplicates. Please carefully read these paragraphs and determine how many unique paragraphs there are after removing duplicates. In other words, how many non-repeating paragraphs are there in total?\n\n{context}\n\nPlease enter the final count of unique paragraphs after removing duplicates. The output format should only contain the number, such as 1, 2, 3, and so on.\n\nThe final answer is:",
     "passage_retrieval_en": 'Here are 30 paragraphs from Wikipedia, along with an abstract. Please determine which paragraph the abstract is from.\n\n{context}\n\nThe following is an abstract.\n\n{question}\n\nPlease enter the number of the paragraph that the abstract is from. The answer format must be like "Paragraph 1", "Paragraph 2", etc.\n\nThe answer is:',
     "passage_retrieval_zh": '以下是若干段落文字，以及其中一个段落的摘要。请确定给定的摘要出自哪一段。\n\n{context}\n\n下面是一个摘要\n\n{question}\n\n请输入摘要所属段落的编号。答案格式必须是"段落1"，"段落2"等格式\n\n答案是：',
-    "lcc": "Please complete the code given below. \n{context}Next line of code:\n",
+    "lcc": "Please complete the code given below. \n{context}Next line of code:",
     "repobench-p": "Please complete the code given below. \n{context}{question}Next line of code:",
 }
 

lm_eval/tasks/longbench/lcc.yaml

@@ -5,7 +5,7 @@ task: longbench_lcc
 dataset_path: Xnhyacinth/LongBench
 test_split: test
 dataset_name: lcc
-doc_to_text: "Please complete the code given below. \n{{context}}Next line of code:\n"
+doc_to_text: "Please complete the code given below. \n{{context}}Next line of code:"
 doc_to_target: '{{answers}}'
 process_results: !function metrics.get_code_sim_score
 generation_kwargs:

lm_eval/tasks/longbench/lcc_e.yaml

@@ -5,7 +5,7 @@ task: longbench_lcc_e
 dataset_path: Xnhyacinth/LongBench
 test_split: test
 dataset_name: lcc_e
-doc_to_text: "Please complete the code given below. \n{{context}}Next line of code:\n"
+doc_to_text: "Please complete the code given below. \n{{context}}Next line of code:"
 doc_to_target: '{{answers}}'
 process_results: !function metrics.get_code_sim_score
 generation_kwargs:

lm_eval/tasks/longbench/samsum.yaml

@@ -5,7 +5,7 @@ task: longbench_samsum
 dataset_path: Xnhyacinth/LongBench
 test_split: test
 dataset_name: samsum
-doc_to_text: "Summarize the dialogue into a few short sentences. The following are some examples.\n\n{{context}}\n\n{{question}}"
+doc_to_text: "Summarize the dialogue into a few short sentences. The following are some examples.\n\n{{context}}\n{{question}}"
 doc_to_target: '{{answers}}'
 process_results: !function metrics.get_rouge_score
 generation_kwargs:

lm_eval/tasks/longbench/samsum_e.yaml

@@ -5,7 +5,7 @@ task: longbench_samsum_e
 dataset_path: Xnhyacinth/LongBench
 test_split: test
 dataset_name: samsum_e
-doc_to_text: "Summarize the dialogue into a few short sentences. The following are some examples.\n\n{{context}}\n\n{{question}}"
+doc_to_text: "Summarize the dialogue into a few short sentences. The following are some examples.\n\n{{context}}\n{{question}}"
 doc_to_target: '{{answers}}'
 process_results: !function metrics.get_rouge_score
 generation_kwargs:

lm_eval/tasks/longbench/triviaqa.yaml

@@ -5,7 +5,7 @@ task: longbench_triviaqa
 dataset_path: Xnhyacinth/LongBench
 test_split: test
 dataset_name: triviaqa
-doc_to_text: "Answer the question based on the given passage. Only give me the answer and do not output any other words. The following are some examples.\n\n{{context}}\n\n{{question}}"
+doc_to_text: "Answer the question based on the given passage. Only give me the answer and do not output any other words. The following are some examples.\n\n{{context}}\n{{question}}"
 doc_to_target: '{{answers}}'
 process_results: !function metrics.get_qa_f1_score
 generation_kwargs:

lm_eval/tasks/longbench/triviaqa_e.yaml

@@ -5,7 +5,7 @@ task: longbench_triviaqa_e
 dataset_path: Xnhyacinth/LongBench
 test_split: test
 dataset_name: triviaqa_e
-doc_to_text: "Answer the question based on the given passage. Only give me the answer and do not output any other words. The following are some examples.\n\n{{context}}\n\n{{question}}"
+doc_to_text: "Answer the question based on the given passage. Only give me the answer and do not output any other words. The following are some examples.\n\n{{context}}\n{{question}}"
 doc_to_target: '{{answers}}'
 process_results: !function metrics.get_qa_f1_score
 generation_kwargs: