添加Megatron项目

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/salient_translation_error_detection.yaml

+"dataset_name": "salient_translation_error_detection"
+"description": "Detect the type of error in an English translation of a German source sentence.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_salient_translation_error_detection"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: -1
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/snarks.yaml

+"dataset_name": "snarks"
+"description": "Determine which of two sentences is sarcastic.\n\nAccording to Cambridge University Dictionary, sarcasm is \"the use of remarks that clearly mean the opposite of what they say, made in order to hurt someone's feelings or to criticize something in a humorous way.\" Sarcastic sentences often contain satirical or ironic utterances, hyperboles, ambivalent or witty remarks.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_snarks"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: -1
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/sports_understanding.yaml

+"dataset_name": "sports_understanding"
+"description": "Determine whether an artificially constructed sentence relating to sports is plausible or not.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_sports_understanding"
+
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MapRegexFilter
+        group_select: -1
+        ignore_case: true
+        regex_pattern_to_value:
+          \b(no|not plausible)\b: "no"
+          \b(yes|plausible)\b: "yes"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/temporal_sequences.yaml

+"dataset_name": "temporal_sequences"
+"description": "Task description: Answer questions about which times certain events could have occurred.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_temporal_sequences"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: -1
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/tracking_shuffled_objects_five_objects.yaml

+"dataset_name": "tracking_shuffled_objects_five_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_tracking_shuffled_objects_five_objects"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: -1
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/tracking_shuffled_objects_seven_objects.yaml

+"dataset_name": "tracking_shuffled_objects_seven_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_tracking_shuffled_objects_seven_objects"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: -1
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/tracking_shuffled_objects_three_objects.yaml

+"dataset_name": "tracking_shuffled_objects_three_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_tracking_shuffled_objects_three_objects"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MultiChoiceRegexFilter
+        group_select: -1
+        ignore_case: true
+        ignore_punctuation: true
+        regex_pattern: "(\\([A-Z]\\))"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/utils.py

+import collections
+import re
+import sys
+import unicodedata
+
+from lm_eval.filters.extraction import Filter, RegexFilter
+
+
+class ExtendedRegexFilter(RegexFilter):
+    punct_tbl = dict.fromkeys(
+        i for i in range(sys.maxunicode) if unicodedata.category(chr(i)).startswith("P")
+    )
+
+    def __init__(
+        self,
+        regex_pattern: str = r"#### (\-?[0-9\.\,]+)",
+        group_select=0,
+        fallback: str = "[invalid]",
+        ignore_case=False,
+        ignore_punctuation=False,
+        regexes_to_ignore=None,
+    ) -> None:
+        super().__init__(regex_pattern, group_select, fallback)
+        self.ignore_case = ignore_case
+        self.ignore_punctuation = ignore_punctuation
+        self.regexes_to_ignore = regexes_to_ignore
+
+    def filter_ignores(self, st):
+        if self.regexes_to_ignore is not None:
+            for s in self.regexes_to_ignore:
+                st = re.sub(s, "", st)
+
+        if self.ignore_case:
+            st = st.lower()
+
+        if self.ignore_punctuation:
+            # https://stackoverflow.com/a/266162
+            st = st.translate(self.punct_tbl)
+        return st
+
+    def find_match(self, regex, resp, convert_dict={}):
+        match = regex.findall(resp)
+        if match:
+            match = match[self.group_select]
+            if isinstance(match, tuple):
+                match = [m for m in match if m][0]
+            match = match.strip()
+            if match and match in convert_dict:
+                match = convert_dict[match]
+        return match
+
+
+class MapRegexFilter(ExtendedRegexFilter):
+    def __init__(
+        self,
+        regex_pattern_to_value: dict = {},
+        group_select=0,
+        fallback: str = "[invalid]",
+        ignore_case=False,
+        ignore_punctuation=False,
+        regexes_to_ignore=None,
+    ) -> None:
+        """
+        regex_pattern_to_value: Match the regex pattern and change the result into the value
+        group_select: Selects the (group_select)th match from the findall result. We use the whole regex_patterns, concatenated by |
+        ignore_case: Lowers the case of response before matching with the given regex
+        ignore_punctuation: Remove the punctuation before matching with the given regex
+        regexes_to_ignore: Remove these regexes before matching with the given regex
+        """
+        super().__init__(
+            "|".join(list(regex_pattern_to_value.keys())),
+            group_select,
+            fallback,
+            ignore_case,
+            ignore_punctuation,
+            regexes_to_ignore,
+        )
+        self.regex_to_value = {
+            re.compile(r): v for r, v in regex_pattern_to_value.items()
+        }
+
+    def apply(self, resps, docs):
+        filtered_resps = []
+
+        for r in resps:
+            filtered = []
+            for resp in r:
+                whole_match_considering_group_select = self.find_match(
+                    self.regex, self.filter_ignores(resp)
+                )
+                if whole_match_considering_group_select:
+                    for regex, mapped_value in self.regex_to_value.items():
+                        match = self.find_match(
+                            regex,
+                            self.filter_ignores(whole_match_considering_group_select),
+                        )
+                        if match:
+                            match = mapped_value
+                            break
+                if not whole_match_considering_group_select or not match:
+                    match = self.fallback
+
+                filtered.append(match)
+            filtered_resps.append(filtered)
+
+        return filtered_resps
+
+
+class NumberParseRegexFilter(ExtendedRegexFilter):
+    def apply(self, resps, docs):
+        # here, we assume we have a list, in which each element is
+        # a list of model responses for some particular input/target pair.
+        # so we process each of these (same input/target response sets)
+        # independently (and keep them a list.)
+        filtered_resps = []
+        import regex
+        from word2number import w2n
+
+        # https://www.reddit.com/r/regex/comments/11a38uk/parsing_numbers_written_out_as_english_words
+        english_number_regex = regex.compile(
+            "((?:(?:zero|one|two|three|four|five|(?:twen|thir|for|fif|six|seven|nine)(?|teen|ty)|eight(?:|een|y)|ten|eleven|twelve|fourteen|hundred|thousand|(?:m|b|tr)illion)(?:zero|one|two|three|four|five|(?:twen|thir|for|fif|six|seven|nine)(?:|teen|ty)|eight(?|een|y)|ten|eleven|twelve|fourteen|hundred|thousand|(?:m|b|tr)illion|[^\S\r\n]|,|and|&)+)?(?:zero|one|two|three|four|five|(?:twen|thir|for|fif|six|seven|nine)(?|teen|ty)|eight(?|een|y)|ten|eleven|twelve|fourteen|hundred|thousand|(?:m|b|tr)illion))"
+        )
+
+        for r in resps:
+            filtered = []
+            for resp in r:
+                match = self.find_match(self.regex, resp)
+                if not match:
+                    match = self.find_match(english_number_regex, resp.lower())
+                    if match:
+                        match = str(w2n.word_to_num(match))
+                if not match:
+                    match = self.fallback
+                filtered.append(match)
+            filtered_resps.append(filtered)
+
+        return filtered_resps
+
+
+class WordSortFilter(Filter):
+    """ """
+
+    def apply(self, resps, docs):
+        filtered_resps = []
+
+        for r, doc in zip(resps, docs):
+            words = doc["input"].split("List:")[1].strip().split()
+            regex = re.compile("|".join([f"\\b{w}\\b" for w in words]))
+            filtered = []
+            for resp in r:
+                match = regex.findall(resp)
+                match.reverse()
+                ordered_words = reversed(
+                    collections.OrderedDict(zip(match, [None] * len(match)))
+                )
+                filtered.append(" ".join(ordered_words))
+            filtered_resps.append(filtered)
+
+        return filtered_resps
+
+
+class MultiChoiceRegexFilter(ExtendedRegexFilter):
+    def __init__(self, *args, **kwargs):
+        """
+        regex_pattern: The basic regex pattern to use. If fails to match, we will use the customized match procedure
+                        - step 1 : We parse the choices between ([A-Z])s then try to find these choices in the response.
+                        - step 2 : We parse the choice with regex :[\s]*([A-?]), where ? varies by number of choices.
+        group_select: Selects the (group_select)th match from the findall result.
+        ignore_case: Ignores the case during step 1 matching
+        ignore_punctuation: Remove the punctuation during step 1 matching
+        regexes_to_ignore: Remove these regexes during step 1 matching
+        """
+        super().__init__(*args, **kwargs)
+
+    def apply(self, resps, docs):
+        # here, we assume we have a list, in which each element is
+        # a list of model responses for some particular input/target pair.
+        # so we process each of these (same input/target response sets)
+        # independently (and keep them a list.)
+
+        filtered_resps = []
+
+        for r, doc in zip(resps, docs):
+            fallback_regexes = []
+            choice_to_alpha = {}
+            next_alpha = "A"
+
+            without_paren_fallback_regexes = []
+            without_paren_to_target = {}
+
+            multiple_choices_regex = re.compile(r"\([A-Z]\)([^\n^(]*)")
+            match = multiple_choices_regex.findall(doc["input"])
+            for m in match:
+                m = self.filter_ignores(m.strip())
+                fallback_regexes.append(f"{re.escape(m)}")
+                choice_to_alpha[m] = f"({next_alpha})"
+
+                without_paren_fallback_regexes.append(next_alpha)
+                without_paren_to_target[next_alpha] = f"({next_alpha})"
+
+                next_alpha = chr(ord(next_alpha) + 1)
+            fallback_regex = re.compile("|".join(fallback_regexes))
+            without_paren_fallback_regex = "|".join(without_paren_fallback_regexes)
+            without_paren_fallback_regex = re.compile(
+                f":[\s]*({without_paren_fallback_regex})"
+            )
+
+            filtered = []
+            for resp in r:
+                match = self.find_match(self.regex, resp)
+                if not match:
+                    match = self.find_match(
+                        fallback_regex, self.filter_ignores(resp), choice_to_alpha
+                    )
+                    if not match:
+                        match = self.find_match(
+                            without_paren_fallback_regex, resp, without_paren_to_target
+                        )
+                if not match:
+                    match = self.fallback
+                filtered.append(match)
+            filtered_resps.append(filtered)
+
+        return filtered_resps

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/web_of_lies.yaml

+"dataset_name": "web_of_lies"
+"description": "Evaluate a random boolean function expressed as a word problem.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_web_of_lies"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MapRegexFilter
+        group_select: -1
+        ignore_case: true
+        regex_pattern_to_value:
+          \b(no|does not tell the truth|is not telling the truth)\b: "no"
+          \b(yes|tells the truth|is telling the truth)\b: "yes"
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/cot_zeroshot/word_sorting.yaml

+"dataset_name": "word_sorting"
+"description": "Sort a list of words.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step."
+"include": "_cot_zeroshot_template_yaml"
+"task": "bbh_cot_zeroshot_word_sorting"
+filter_list:
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.WordSortFilter
+      - function: "take_first"
+  - name: "strict-match"
+    filter:
+      - function: "regex"
+        regex_pattern: "((?<=The answer is )(.*)(?=.)|(?<=the answer is )(.*)(?=.)|(?<=The answer: )(.*)(?=.)|(?<=The final answer: )(.*)(?=.))"
+      - function: "take_first"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/_fewshot_template_yaml

+group: bbh_fewshot
+dataset_path: lukaemon/bbh
+output_type: generate_until
+test_split: test
+doc_to_target: "{{target}}"
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    # ignore_case: true
+    # ignore_punctuation: true
+generation_kwargs:
+  until:
+    - "</s>"
+    - "Q"
+    - "\n\n"
+  do_sample: false
+  temperature: 0.0
+num_fewshot: 0
+metadata:
+  version: 1.0
+  num_fewshot: 3 # will be printed in results table

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/boolean_expressions.yaml

+"dataset_name": "boolean_expressions"
+"description": "Evaluate the result of a random Boolean expression.\n\n"
+"doc_to_text": "Q: not ( ( not not True ) ) is\nA: False\n\nQ: True and False and not True and True is\nA: False\n\nQ: not not ( not ( False ) ) is\nA: True\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_boolean_expressions"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/causal_judgement.yaml

+"dataset_name": "causal_judgement"
+"description": "Answer questions about causal attribution.\n\n"
+"doc_to_text": "Q: How would a typical person answer each of the following questions about causation?\nFrank T., had an ongoing dispute with his neighbor over a stretch of land and one day decided to shoot his neighbor in the body. Frank T. had no experience with guns, his hand slipped on the barrel of the gun, and the shot went wild. Nonetheless, the bullet bounced off a large boulder several feet away and hit the neighbor's body, causing significant injury. Did Frank T. intentionally shoot his neighbor in the body?\nOptions:\n- Yes\n- No\nA: No\n\nQ: How would a typical person answer each of the following questions about causation?\nSuzy and Billy are working on a project that is very important for our nation's security. The boss tells them both: \"Be sure that you are here at exactly 9 am. It is absolutely essential that you arrive at that time.\" Both Billy and Suzy arrive at 9 am. As it happens, there was a motion detector installed in the room where they arrived. The motion detector was set up to be triggered if at least one person appeared in the room at the same time. So the motion detector went off. Did Billy cause the motion detector to go off?\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: How would a typical person answer each of the following questions about causation?\nGeorge and his sister Lena reunite at their parents' house for Thanksgiving. Whereas George just got into medical school, Lena is unhappy in her marriage and recently lost her job. Over the course of the day, George and Lena get into a number of heated arguments. Later in the afternoon they play a game of darts. They split the first two games, and the third game is close until the end. Who will win comes down to George's last shot. If he hits a high point region, he wins; if he hits a low point region, Lena wins. George thinks of the difficult time Lena is having, and he really wants to let her win. He aims the dart at the low point region. He sets up his shot and the dart lands in the low point region. After his shot, Lena wins the game and is very happy. Did George hit the low point region intentionally?\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_causal_judgement"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/date_understanding.yaml

+"dataset_name": "date_understanding"
+"description": "Infer the date from context.\n\n"
+"doc_to_text": "Q: Today is Christmas Eve of 1937. What is the date 10 days ago in MM/DD/YYYY?\nOptions:\n(A) 12/14/2026\n(B) 12/14/1950\n(C) 12/14/2007\n(D) 12/14/1937\n(E) 07/14/1938\n(F) 12/14/1988\nA: (D)\n\nQ: Tomorrow is 11/12/2019. What is the date one year ago from today in MM/DD/YYYY?\nOptions:\n(A) 09/04/2018\n(B) 11/11/2018\n(C) 08/25/2018\n(D) 11/02/2018\n(E) 11/04/2018\nA: (B)\n\nQ: Jane and John married on Jan 2, 1958. It is their 5-year anniversary today. What is the date tomorrow in MM/DD/YYYY?\nOptions:\n(A) 01/11/1961\n(B) 01/03/1963\n(C) 01/18/1961\n(D) 10/14/1960\n(E) 01/03/1982\n(F) 12/03/1960\nA: (B)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_date_understanding"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/disambiguation_qa.yaml

+"dataset_name": "disambiguation_qa"
+"description": "Clarify the meaning of sentences with ambiguous pronouns.\n\n"
+"doc_to_text": "Q: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The chief told the counselor that they took the day off.\nOptions:\n(A) The chief took the day off\n(B) The counselor took the day off\n(C) Ambiguous\nA: (A)\n\nQ: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The manager sent a message to the secretary, but he didn't reply yet.\nOptions:\n(A) The secretary didn't reply yet\n(B) The manager didn't reply yet\n(C) Ambiguous\nA: (A)\n\nQ: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: Bailey will plan to meet the director at his office\nOptions:\n(A) It will be Bailey's office\n(B) It will be the director's office\n(C) Ambiguous\nA: (C)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_disambiguation_qa"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/dyck_languages.yaml

+"dataset_name": "dyck_languages"
+"description": "Correctly close a Dyck-n word.\n\n"
+"doc_to_text": "Q: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: [ { [\nA: ] } ]\n\nQ: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: < > ( ( [ [ ( { } ) [ < > ] ]\nA: ] ) )\n\nQ: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: < [ < [ { < [ ] < { } > > } ] > { { ( ) } { < [ < > ] > }\nA: } ] >\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_dyck_languages"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/formal_fallacies.yaml

+"dataset_name": "formal_fallacies"
+"description": "Distinguish deductively valid arguments from formal fallacies.\n\n"
+"doc_to_text": "Q: \"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: To begin with, Lesley is a close friend of Fernando. Moreover, being a close friend of Fernando or a schoolmate of Lowell is sufficient for being a great-grandfather of Leroy. It follows that Lesley is a great-grandfather of Leroy.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: valid\n\nQ: \"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: Whoever is not a great-grandfather of Clyde is a stepbrother of Brian. Being an ancestor of Dana is sufficient for not being a great-grandfather of Clyde. We may conclude: Everyone who is an ancestor of Dana is a stepbrother of Brian, too.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: valid\n\nQ: \"It is not always easy to grasp who is consuming which products. The following argument pertains to this question: Every infrequent user of Paul Mitchell shampoo is either a rare consumer of Nioxin shampoo or a loyal buyer of Caress soap, or both. No regular consumer of Lush soap is a rare consumer of Nioxin shampoo and, in the same time, a loyal buyer of Caress soap. It follows that whoever is an infrequent user of Paul Mitchell shampoo is not a regular consumer of Lush soap.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: invalid\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_formal_fallacies"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/geometric_shapes.yaml

+"dataset_name": "geometric_shapes"
+"description": "Name geometric shapes from their SVG paths.\n\n"
+"doc_to_text": "Q: This SVG path element <path d=\"M 31.00,73.00 L 32.00,59.00 L 44.00,50.00 L 49.00,41.00 L 64.00,37.00 L 71.00,55.00 L 64.00,76.00 L 52.00,61.00 L 31.00,73.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (F)\n\nQ: This SVG path element <path d=\"M 14.19,26.04 L 51.43,39.21 L 58.44,36.69 L 56.63,30.17 L 48.53,26.66 L 14.19,26.04\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (G)\n\nQ: This SVG path element <path d=\"M 41.00,43.00 L 37.00,34.00 L 41.00,33.00 L 45.00,34.00 L 41.00,43.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (D)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_geometric_shapes"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/hyperbaton.yaml

+"dataset_name": "hyperbaton"
+"description": "Order adjectives correctly in English sentences.\n\n"
+"doc_to_text": "Q: Which sentence has the correct adjective order:\nOptions:\n(A) rubber terrible ship\n(B) terrible rubber ship\nA: (B)\n\nQ: Which sentence has the correct adjective order:\nOptions:\n(A) repulsive small Brazilian exercise ship\n(B) Brazilian repulsive exercise small ship\nA: (A)\n\nQ: Which sentence has the correct adjective order:\nOptions:\n(A) blue gold wonderful square shoe\n(B) wonderful square blue gold shoe\nA: (B)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_hyperbaton"

LM-Evaluation-Harness-240310/lm_eval/tasks/bbh/fewshot/logical_deduction_five_objects.yaml

+"dataset_name": "logical_deduction_five_objects"
+"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
+"doc_to_text": "Q: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_logical_deduction_five_objects"