File size: 7,789 Bytes
e34b94f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
# Copyright 2024 Bytedance Ltd. and/or its affiliates
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Adapted from https://github.com/EleutherAI/lm-evaluation-harness/blob/main/lm_eval/tasks/hendrycks_math/utils.py
def compute_score(completion, ground_truth) -> float:
retval = 0.0
try:
# string_in_last_boxed = last_boxed_only_string(solution_str)
string_in_first_boxed = first_boxed_only_string(completion)
ground_truth_in_last_boxed = last_boxed_only_string(ground_truth)
if string_in_first_boxed is not None:
answer = remove_boxed(string_in_first_boxed)
ground_truth = remove_boxed(ground_truth_in_last_boxed)
if is_equiv(answer, ground_truth):
retval = 1.0
except Exception as e:
print(e)
return retval
# string normalization from https://github.com/EleutherAI/lm-evaluation-harness/blob/master/lm_eval/tasks/hendrycks_math.py
def is_equiv(str1, str2, verbose=False):
if str1 is None and str2 is None:
print("WARNING: Both None")
return True
if str1 is None or str2 is None:
return False
try:
ss1 = strip_string(str1)
ss2 = strip_string(str2)
if verbose:
print(ss1, ss2)
return ss1 == ss2
except Exception:
return str1 == str2
def remove_boxed(s):
# Robust to None or non-string inputs
if not isinstance(s, str):
return s
if "\\boxed " in s:
left = "\\boxed "
assert s[: len(left)] == left
return s[len(left) :]
left = "\\boxed{"
# If not boxed-format, return as-is to avoid raising
if not (s[: len(left)] == left and len(s) > 0 and s[-1] == "}"):
return s
return s[len(left) : -1]
def first_boxed_only_string(string):
if "\\boxed " in string:
return "\\boxed " + string.split("\\boxed ")[1].split("$")[0]
idx = string.find("\\boxed")
if idx < 0:
idx = string.find("\\fbox")
if idx < 0:
return None
i = idx
right_brace_idx = None
num_left_braces_open = 0
while i < len(string):
if string[i] == "{":
num_left_braces_open += 1
if string[i] == "}":
num_left_braces_open -= 1
if num_left_braces_open == 0:
right_brace_idx = i
break
i += 1
retval = None if right_brace_idx is None else string[idx : right_brace_idx + 1]
return retval
def last_boxed_only_string(string):
idx = string.rfind("\\boxed")
if "\\boxed " in string:
return "\\boxed " + string.split("\\boxed ")[-1].split("$")[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
retval = None if right_brace_idx is None else string[idx : right_brace_idx + 1]
return retval
def fix_fracs(string):
substrs = string.split("\\frac")
new_str = substrs[0]
if len(substrs) > 1:
substrs = substrs[1:]
for substr in substrs:
new_str += "\\frac"
if substr[0] == "{":
new_str += substr
else:
try:
assert len(substr) >= 2
except: # noqa: E722
return string
a = substr[0]
b = substr[1]
if b != "{":
if len(substr) > 2:
post_substr = substr[2:]
new_str += "{" + a + "}{" + b + "}" + post_substr
else:
new_str += "{" + a + "}{" + b + "}"
else:
if len(substr) > 2:
post_substr = substr[2:]
new_str += "{" + a + "}" + b + post_substr
else:
new_str += "{" + a + "}" + b
string = new_str
return string
def fix_a_slash_b(string):
if len(string.split("/")) != 2:
return string
a = string.split("/")[0]
b = string.split("/")[1]
try:
a = int(a)
b = int(b)
assert string == "{}/{}".format(a, b)
new_string = "\\frac{" + str(a) + "}{" + str(b) + "}"
return new_string
except: # noqa: E722
return string
def remove_right_units(string):
# "\\text{ " only ever occurs (at least in the val set) when describing units
if "\\text{ " in string:
splits = string.split("\\text{ ")
assert len(splits) == 2
return splits[0]
else:
return string
def fix_sqrt(string):
if "\\sqrt" not in string:
return string
splits = string.split("\\sqrt")
new_string = splits[0]
for split in splits[1:]:
if split[0] != "{":
a = split[0]
new_substr = "\\sqrt{" + a + "}" + split[1:]
else:
new_substr = "\\sqrt" + split
new_string += new_substr
return new_string
def strip_string(string):
# linebreaks
string = string.replace("\n", "")
# remove inverse spaces
string = string.replace("\\!", "")
# replace \\ with \
string = string.replace("\\\\", "\\")
# replace tfrac and dfrac with frac
string = string.replace("tfrac", "frac")
string = string.replace("dfrac", "frac")
# remove \left and \right
string = string.replace("\\left", "")
string = string.replace("\\right", "")
# Remove circ (degrees)
string = string.replace("^{\\circ}", "")
string = string.replace("^\\circ", "")
# remove dollar signs
string = string.replace("\\$", "")
# remove units (on the right)
string = remove_right_units(string)
# remove percentage
string = string.replace("\\%", "")
string = string.replace("\%", "") # noqa: W605
# " 0." equivalent to " ." and "{0." equivalent to "{." Alternatively, add "0" if "." is the start of the string
string = string.replace(" .", " 0.")
string = string.replace("{.", "{0.")
# if empty, return empty string
if len(string) == 0:
return string
if string[0] == ".":
string = "0" + string
# to consider: get rid of e.g. "k = " or "q = " at beginning
if len(string.split("=")) == 2 and len(string.split("=")[0]) <= 2:
string = string.split("=")[1]
# fix sqrt3 --> sqrt{3}
string = fix_sqrt(string)
# remove spaces
string = string.replace(" ", "")
# \frac1b or \frac12 --> \frac{1}{b} and \frac{1}{2}, etc. Even works with \frac1{72} (but not \frac{72}1).
# Also does a/b --> \\frac{a}{b}
string = fix_fracs(string)
# manually change 0.5 --> \frac{1}{2}
if string == "0.5":
string = "\\frac{1}{2}"
# NOTE: X/Y changed to \frac{X}{Y} in dataset, but in simple cases fix in case the model output is X/Y
string = fix_a_slash_b(string)
return string |