Merge remote-tracking branch 'origin/big-refactor' into calibration

lm_eval/tasks/minerva_math/minerva_math_prealgebra.yaml

+include: minerva_math_algebra.yaml
+dataset_name: prealgebra
+task: minerva_math_prealgebra

lm_eval/tasks/minerva_math/minerva_math_precalc.yaml

+include: minerva_math_algebra.yaml
+dataset_name: precalculus
+task: minerva_math_precalc

lm_eval/tasks/minerva_math/utils.py

+import datasets
+import re
+import signal
+from lm_eval.utils import eval_logger
+from typing import Optional, List, Dict
+
+try:
+    import sympy
+    from sympy.parsing.latex import parse_latex
+except ModuleNotFoundError:
+    raise Exception(
+        "`sympy` is required for generating translation task prompt templates. \
+please install sympy via pip install lm-eval[math] or pip install -e .[math]",
+    )
+
+
+# taken from
+# https://github.com/wellecks/lm-evaluation-harness/blob/master/lm_eval/tasks/minerva_math.py
+def doc_to_text(doc: dict) -> str:
+    PROMPT = r"""Problem:
+Find the domain of the expression  $\frac{\sqrt{x-2}}{\sqrt{5-x}}$.}
+
+Solution:
+The expressions inside each square root must be non-negative. Therefore, $x-2 \ge 0$, so $x\ge2$, and $5 - x \ge 0$, so $x \le 5$. Also, the denominator cannot be equal to zero, so $5-x>0$, which gives $x<5$. Therefore, the domain of the expression is $\boxed{[2,5)}$.
+Final Answer: The final answer is $[2,5)$. I hope it is correct.
+
+Problem:
+If $\det \mathbf{A} = 2$ and $\det \mathbf{B} = 12,$ then find $\det (\mathbf{A} \mathbf{B}).$
+
+Solution:
+We have that $\det (\mathbf{A} \mathbf{B}) = (\det \mathbf{A})(\det \mathbf{B}) = (2)(12) = \boxed{24}.$
+Final Answer: The final answer is $24$. I hope it is correct.
+
+Problem:
+Terrell usually lifts two 20-pound weights 12 times. If he uses two 15-pound weights instead, how many times must Terrell lift them in order to lift the same total weight?
+
+Solution:
+If Terrell lifts two 20-pound weights 12 times, he lifts a total of $2\cdot 12\cdot20=480$ pounds of weight.  If he lifts two 15-pound weights instead for $n$ times, he will lift a total of $2\cdot15\cdot n=30n$ pounds of weight.  Equating this to 480 pounds, we can solve for $n$:
+\begin{align*}
+30n&=480\\
+\Rightarrow\qquad n&=480/30=\boxed{16}
+\end{align*}
+Final Answer: The final answer is $16$. I hope it is correct.
+
+Problem:
+If the system of equations
+
+\begin{align*}
+6x-4y&=a,\\
+6y-9x &=b.
+\end{align*}has a solution $(x, y)$ where $x$ and $y$ are both nonzero,
+find $\frac{a}{b},$ assuming $b$ is nonzero.
+
+Solution:
+If we multiply the first equation by $-\frac{3}{2}$, we obtain
+
+$$6y-9x=-\frac{3}{2}a.$$Since we also know that $6y-9x=b$, we have
+
+$$-\frac{3}{2}a=b\Rightarrow\frac{a}{b}=\boxed{-\frac{2}{3}}.$$
+Final Answer: The final answer is $-\frac{2}{3}$. I hope it is correct."""
+
+    return PROMPT + "\n\n" + "Problem:" + "\n" + doc["problem"] + "\n\n" + "Solution:"
+
+
+def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:
+    def _process_doc(doc: dict) -> dict:
+        out_doc = {
+            "problem": doc["problem"],
+            "solution": doc["solution"],
+            "answer": normalize_final_answer(
+                remove_boxed(last_boxed_only_string(doc["solution"]))
+            ),
+        }
+        return out_doc
+
+    return dataset.map(_process_doc)
+
+
+def process_results(doc: dict, results: List[str]) -> Dict[str, int]:
+    candidates = results[0]
+
+    unnormalized_answer = get_unnormalized_answer(candidates)
+    answer = normalize_final_answer(unnormalized_answer)
+
+    if is_equiv(answer, doc["answer"]):
+        retval = 1
+    else:
+        retval = 0
+
+    results = {
+        "exact_match": retval,
+    }
+    return results
+
+
+def last_boxed_only_string(string: str) -> Optional[str]:
+    idx = string.rfind("\\boxed")
+    if "\\boxed " in string:
+        return "\\boxed " + string.split("\\boxed ")[-1].split("$")[0]
+    if idx < 0:
+        idx = string.rfind("\\fbox")
+        if idx < 0:
+            return None
+
+    i = idx
+    right_brace_idx = None
+    num_left_braces_open = 0
+    while i < len(string):
+        if string[i] == "{":
+            num_left_braces_open += 1
+        if string[i] == "}":
+            num_left_braces_open -= 1
+            if num_left_braces_open == 0:
+                right_brace_idx = i
+                break
+        i += 1
+
+    if right_brace_idx is None:
+        retval = None
+    else:
+        retval = string[idx : right_brace_idx + 1]
+
+    return retval
+
+
+def remove_boxed(s: str) -> str:
+    if "\\boxed " in s:
+        left = "\\boxed "
+        assert s[: len(left)] == left
+        return s[len(left) :]
+
+    left = "\\boxed{"
+
+    assert s[: len(left)] == left
+    assert s[-1] == "}"
+
+    return s[len(left) : -1]
+
+
+class timeout:
+    def __init__(self, seconds=1, error_message="Timeout"):
+        self.seconds = seconds
+        self.error_message = error_message
+
+    def handle_timeout(self, signum, frame):
+        raise TimeoutError(self.error_message)
+
+    def __enter__(self):
+        signal.signal(signal.SIGALRM, self.handle_timeout)
+        signal.alarm(self.seconds)
+
+    def __exit__(self, type, value, traceback):
+        signal.alarm(0)
+
+
+def is_equiv(x1: str, x2: str) -> bool:
+    """
+    x1 and x2 are normalized latex string
+    """
+    try:
+        with timeout(seconds=5):
+            try:
+                parsed_x1 = parse_latex(x1)
+                parsed_x2 = parse_latex(x2)
+            except (
+                sympy.parsing.latex.errors.LaTeXParsingError,
+                sympy.SympifyError,
+                TypeError,
+            ):
+                eval_logger.debug(f"couldn't parse one of {x1} or {x2}")
+                return False
+
+            try:
+                diff = parsed_x1 - parsed_x2
+            except TypeError:
+                eval_logger.debug(f"couldn't subtract {x1} and {x2}")
+                return False
+
+            try:
+                if sympy.simplify(diff) == 0:
+                    return True
+                else:
+                    return False
+            except ValueError:
+                eval_logger.debug(
+                    f"Had some trouble simplifying when comparing {x1} and {x2}"
+                )
+    except TimeoutError:
+        eval_logger.debug(f"Timed out comparing {x1} and {x2}")
+        return False
+    except ImportError as e:
+        eval_logger.error(e)
+        raise
+    except Exception as e:
+        eval_logger.debug(f"Failed comparing {x1} and {x2} with {e}")
+        return False
+
+
+def get_unnormalized_answer(text: str) -> str:
+    INVALID_ANSWER = "[invalidanswer]"
+    end_seq = "I hope it is correct."
+    text += end_seq
+    match = re.search(
+        r"Final Answer: The final answer is(.*?). I hope it is correct.",
+        text,
+    )
+    if match:
+        return match.group(1).strip()
+    else:
+        return INVALID_ANSWER
+
+
+SUBSTITUTIONS = [
+    ("an ", ""),
+    ("a ", ""),
+    (".$", "$"),
+    ("\\$", ""),
+    (r"\ ", ""),
+    (" ", ""),
+    ("mbox", "text"),
+    (",\\text{and}", ","),
+    ("\\text{and}", ","),
+    ("\\text{m}", "\\text{}"),
+]
+REMOVED_EXPRESSIONS = [
+    "square",
+    "ways",
+    "integers",
+    "dollars",
+    "mph",
+    "inches",
+    "ft",
+    "hours",
+    "km",
+    "units",
+    "\\ldots",
+    "sue",
+    "points",
+    "feet",
+    "minutes",
+    "digits",
+    "cents",
+    "degrees",
+    "cm",
+    "gm",
+    "pounds",
+    "meters",
+    "meals",
+    "edges",
+    "students",
+    "childrentickets",
+    "multiples",
+    "\\text{s}",
+    "\\text{.}",
+    "\\text{\ns}",
+    "\\text{}^2",
+    "\\text{}^3",
+    "\\text{\n}",
+    "\\text{}",
+    r"\mathrm{th}",
+    r"^\circ",
+    r"^{\circ}",
+    r"\;",
+    r",\!",
+    "{,}",
+    '"',
+    "\\dots",
+]
+
+
+def normalize_final_answer(final_answer: str) -> str:
+    """
+    Normalize a final answer to a quantitative reasoning question.
+
+    Copied character for character from appendix D of Lewkowycz et al. (2022)
+    """
+    final_answer = final_answer.split("=")[-1]
+
+    for before, after in SUBSTITUTIONS:
+        final_answer = final_answer.replace(before, after)
+    for expr in REMOVED_EXPRESSIONS:
+        final_answer = final_answer.replace(expr, "")
+
+    # Extract answer that is in LaTeX math, is bold,
+    # is surrounded by a box, etc.
+    final_answer = re.sub(r"(.*?)(\$)(.*?)(\$)(.*)", "$\\3$", final_answer)
+    final_answer = re.sub(r"(\\text\{)(.*?)(\})", "\\2", final_answer)
+    final_answer = re.sub(r"(\\textbf\{)(.*?)(\})", "\\2", final_answer)
+    final_answer = re.sub(r"(\\overline\{)(.*?)(\})", "\\2", final_answer)
+    final_answer = re.sub(r"(\\boxed\{)(.*)(\})", "\\2", final_answer)
+
+    # Normalize shorthand TeX:
+    #  \fracab -> \frac{a}{b}
+    #  \frac{abc}{bef} -> \frac{abc}{bef}
+    #  \fracabc -> \frac{a}{b}c
+    #  \sqrta -> \sqrt{a}
+    #  \sqrtab -> sqrt{a}b
+    final_answer = re.sub(r"(frac)([^{])(.)", "frac{\\2}{\\3}", final_answer)
+    final_answer = re.sub(r"(sqrt)([^{])", "sqrt{\\2}", final_answer)
+    final_answer = final_answer.replace("$", "")
+
+    # Normalize 100,000 -> 100000
+    if final_answer.replace(",", "").isdigit():
+        final_answer = final_answer.replace(",", "")
+
+    return final_answer

lm_eval/tasks/mmlu/_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 import utils
+from lm_eval.logger import eval_logger
+
+SUBJECTS = {
+    "abstract_algebra": "stem",
+    "anatomy": "stem",
+    "astronomy": "stem",
+    "business_ethics": "other",
+    "clinical_knowledge": "other",
+    "college_biology": "stem",
+    "college_chemistry": "stem",
+    "college_computer_science": "stem",
+    "college_mathematics": "stem",
+    "college_medicine": "other",
+    "college_physics": "stem",
+    "computer_security": "stem",
+    "conceptual_physics": "stem",
+    "econometrics": "social_sciences",
+    "electrical_engineering": "stem",
+    "elementary_mathematics": "stem",
+    "formal_logic": "humanities",
+    "global_facts": "other",
+    "high_school_biology": "stem",
+    "high_school_chemistry": "stem",
+    "high_school_computer_science": "stem",
+    "high_school_european_history": "humanities",
+    "high_school_geography": "social_sciences",
+    "high_school_government_and_politics": "social_sciences",
+    "high_school_macroeconomics": "social_sciences",
+    "high_school_mathematics": "stem",
+    "high_school_microeconomics": "social_sciences",
+    "high_school_physics": "stem",
+    "high_school_psychology": "social_sciences",
+    "high_school_statistics": "stem",
+    "high_school_us_history": "humanities",
+    "high_school_world_history": "humanities",
+    "human_aging": "other",
+    "human_sexuality": "social_sciences",
+    "international_law": "humanities",
+    "jurisprudence": "humanities",
+    "logical_fallacies": "humanities",
+    "machine_learning": "stem",
+    "management": "other",
+    "marketing": "other",
+    "medical_genetics": "other",
+    "miscellaneous": "other",
+    "moral_disputes": "humanities",
+    "moral_scenarios": "humanities",
+    "nutrition": "other",
+    "philosophy": "humanities",
+    "prehistory": "humanities",
+    "professional_accounting": "other",
+    "professional_law": "humanities",
+    "professional_medicine": "other",
+    "professional_psychology": "social_sciences",
+    "public_relations": "social_sciences",
+    "security_studies": "social_sciences",
+    "sociology": "social_sciences",
+    "us_foreign_policy": "social_sciences",
+    "virology": "other",
+    "world_religions": "humanities",
+}
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--base_yaml_path", required=True)
+    parser.add_argument("--save_prefix_path", default="mmlu")
+    parser.add_argument("--cot_prompt_path", default=None)
+    parser.add_argument("--task_prefix", default="")
+    parser.add_argument("--group_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)
+
+    if args.cot_prompt_path is not None:
+        import json
+
+        with open(args.cot_prompt_path) as f:
+            cot_file = json.load(f)
+
+    ALL_CATEGORIES = []
+    for subject, category in tqdm(SUBJECTS.items()):
+
+        if category not in ALL_CATEGORIES:
+            ALL_CATEGORIES.append(category)
+
+        if args.cot_prompt_path is not None:
+            description = cot_file[subject]
+        else:
+            description = f"The following are multiple choice questions (with answers) about {' '.join(subject.split('_'))}.\n\n"
+
+        yaml_dict = {
+            "include": base_yaml_name,
+            "group": f"mmlu_{args.task_prefix}_{category}"
+            if args.task_prefix != ""
+            else f"mmlu_{category}",
+            "group_alias": category.replace("_", " "),
+            "task": f"mmlu_{args.task_prefix}_{subject}"
+            if args.task_prefix != ""
+            else f"mmlu_{subject}",
+            "task_alias": subject.replace("_", " "),
+            "dataset_name": subject,
+            "description": description,
+        }
+
+        file_save_path = args.save_prefix_path + f"_{subject}.yaml"
+        eval_logger.info(f"Saving yaml for subset {subject} 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='"',
+            )
+
+    if args.task_prefix != "":
+        mmlu_subcategories = [
+            f"mmlu_{args.task_prefix}_{category}" for category in ALL_CATEGORIES
+        ]
+    else:
+        mmlu_subcategories = [f"mmlu_{category}" for category in ALL_CATEGORIES]
+
+    if args.group_prefix != "":
+        file_save_path = args.group_prefix + ".yaml"
+    else:
+        file_save_path = args.save_prefix_path + ".yaml"
+
+    eval_logger.info(f"Saving benchmark config to {file_save_path}")
+    with open(file_save_path, "w") as yaml_file:
+        yaml.dump(
+            {
+                "group": f"mmlu_{args.task_prefix}"
+                if args.task_prefix != ""
+                else "mmlu",
+                "task": mmlu_subcategories,
+            },
+            yaml_file,
+            indent=4,
+            default_flow_style=False,
+        )

lm_eval/tasks/mmlu/default/_default_template_yaml

+dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
+test_split: test
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+output_type: multiple_choice
+doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
+doc_to_choice: ["A", "B", "C", "D"]
+doc_to_target: answer
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/mmlu/default/_mmlu.yaml

+group: mmlu
+task:
+  - mmlu_stem
+  - mmlu_other
+  - mmlu_social_sciences
+  - mmlu_humanities

lm_eval/tasks/mmlu/default/mmlu_abstract_algebra.yaml

+"dataset_name": "abstract_algebra"
+"description": "The following are multiple choice questions (with answers) about abstract\
+  \ algebra.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_abstract_algebra"
+"task_alias": "abstract_algebra"

lm_eval/tasks/mmlu/default/mmlu_anatomy.yaml

+"dataset_name": "anatomy"
+"description": "The following are multiple choice questions (with answers) about anatomy.\n\
+  \n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_anatomy"
+"task_alias": "anatomy"

lm_eval/tasks/mmlu/default/mmlu_astronomy.yaml

+"dataset_name": "astronomy"
+"description": "The following are multiple choice questions (with answers) about astronomy.\n\
+  \n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_astronomy"
+"task_alias": "astronomy"

lm_eval/tasks/mmlu/default/mmlu_business_ethics.yaml

+"dataset_name": "business_ethics"
+"description": "The following are multiple choice questions (with answers) about business\
+  \ ethics.\n\n"
+"group": "mmlu_other"
+"group_alias": "other"
+"include": "_default_template_yaml"
+"task": "mmlu_business_ethics"
+"task_alias": "business_ethics"

lm_eval/tasks/mmlu/default/mmlu_clinical_knowledge.yaml

+"dataset_name": "clinical_knowledge"
+"description": "The following are multiple choice questions (with answers) about clinical\
+  \ knowledge.\n\n"
+"group": "mmlu_other"
+"group_alias": "other"
+"include": "_default_template_yaml"
+"task": "mmlu_clinical_knowledge"
+"task_alias": "clinical_knowledge"

lm_eval/tasks/mmlu/default/mmlu_college_biology.yaml

+"dataset_name": "college_biology"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ biology.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_college_biology"
+"task_alias": "college_biology"

lm_eval/tasks/mmlu/default/mmlu_college_chemistry.yaml

+"dataset_name": "college_chemistry"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ chemistry.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_college_chemistry"
+"task_alias": "college_chemistry"

lm_eval/tasks/mmlu/default/mmlu_college_computer_science.yaml

+"dataset_name": "college_computer_science"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ computer science.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_college_computer_science"
+"task_alias": "college_computer_science"

lm_eval/tasks/mmlu/default/mmlu_college_mathematics.yaml

+"dataset_name": "college_mathematics"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ mathematics.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_college_mathematics"
+"task_alias": "college_mathematics"

lm_eval/tasks/mmlu/default/mmlu_college_medicine.yaml

+"dataset_name": "college_medicine"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ medicine.\n\n"
+"group": "mmlu_other"
+"group_alias": "other"
+"include": "_default_template_yaml"
+"task": "mmlu_college_medicine"
+"task_alias": "college_medicine"

lm_eval/tasks/mmlu/default/mmlu_college_physics.yaml

+"dataset_name": "college_physics"
+"description": "The following are multiple choice questions (with answers) about college\
+  \ physics.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_college_physics"
+"task_alias": "college_physics"

lm_eval/tasks/mmlu/default/mmlu_computer_security.yaml

+"dataset_name": "computer_security"
+"description": "The following are multiple choice questions (with answers) about computer\
+  \ security.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_computer_security"
+"task_alias": "computer_security"

lm_eval/tasks/mmlu/default/mmlu_conceptual_physics.yaml

+"dataset_name": "conceptual_physics"
+"description": "The following are multiple choice questions (with answers) about conceptual\
+  \ physics.\n\n"
+"group": "mmlu_stem"
+"group_alias": "stem"
+"include": "_default_template_yaml"
+"task": "mmlu_conceptual_physics"
+"task_alias": "conceptual_physics"

lm_eval/tasks/mmlu/default/mmlu_econometrics.yaml

+"dataset_name": "econometrics"
+"description": "The following are multiple choice questions (with answers) about econometrics.\n\
+  \n"
+"group": "mmlu_social_sciences"
+"group_alias": "social_sciences"
+"include": "_default_template_yaml"
+"task": "mmlu_econometrics"
+"task_alias": "econometrics"