Update README.md
#2
by
MaziyarPanahi
- opened
README.md
CHANGED
|
@@ -67,3 +67,388 @@ Step 3: Finally, perform the remaining addition operation.
|
|
| 67 |
So, 25-4*2+3 equals 20.
|
| 68 |
```
|
| 69 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
So, 25-4*2+3 equals 20.
|
| 68 |
```
|
| 69 |
|
| 70 |
+
## Eval
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
```python
|
| 74 |
+
{
|
| 75 |
+
"all": {
|
| 76 |
+
"acc": 0.6914116069568377,
|
| 77 |
+
"acc_stderr": 0.03063431437342948,
|
| 78 |
+
"acc_norm": 0.6938613221179539,
|
| 79 |
+
"acc_norm_stderr": 0.031238741076549784,
|
| 80 |
+
"mc1": 0.40269277845777235,
|
| 81 |
+
"mc1_stderr": 0.01716883093518722,
|
| 82 |
+
"mc2": 0.5707095526544473,
|
| 83 |
+
"mc2_stderr": 0.01525040450448649
|
| 84 |
+
},
|
| 85 |
+
"harness|arc:challenge|25": {
|
| 86 |
+
"acc": 0.6322525597269625,
|
| 87 |
+
"acc_stderr": 0.014090995618168482,
|
| 88 |
+
"acc_norm": 0.6706484641638225,
|
| 89 |
+
"acc_norm_stderr": 0.013734057652635474
|
| 90 |
+
},
|
| 91 |
+
"harness|hellaswag|10": {
|
| 92 |
+
"acc": 0.6746664011153157,
|
| 93 |
+
"acc_stderr": 0.0046754187743142306,
|
| 94 |
+
"acc_norm": 0.8600876319458275,
|
| 95 |
+
"acc_norm_stderr": 0.0034618713240671846
|
| 96 |
+
},
|
| 97 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 98 |
+
"acc": 0.34,
|
| 99 |
+
"acc_stderr": 0.04760952285695236,
|
| 100 |
+
"acc_norm": 0.34,
|
| 101 |
+
"acc_norm_stderr": 0.04760952285695236
|
| 102 |
+
},
|
| 103 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 104 |
+
"acc": 0.6518518518518519,
|
| 105 |
+
"acc_stderr": 0.041153246103369526,
|
| 106 |
+
"acc_norm": 0.6518518518518519,
|
| 107 |
+
"acc_norm_stderr": 0.041153246103369526
|
| 108 |
+
},
|
| 109 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 110 |
+
"acc": 0.7894736842105263,
|
| 111 |
+
"acc_stderr": 0.03317672787533157,
|
| 112 |
+
"acc_norm": 0.7894736842105263,
|
| 113 |
+
"acc_norm_stderr": 0.03317672787533157
|
| 114 |
+
},
|
| 115 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 116 |
+
"acc": 0.73,
|
| 117 |
+
"acc_stderr": 0.04461960433384741,
|
| 118 |
+
"acc_norm": 0.73,
|
| 119 |
+
"acc_norm_stderr": 0.04461960433384741
|
| 120 |
+
},
|
| 121 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 122 |
+
"acc": 0.7283018867924528,
|
| 123 |
+
"acc_stderr": 0.027377706624670713,
|
| 124 |
+
"acc_norm": 0.7283018867924528,
|
| 125 |
+
"acc_norm_stderr": 0.027377706624670713
|
| 126 |
+
},
|
| 127 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 128 |
+
"acc": 0.8194444444444444,
|
| 129 |
+
"acc_stderr": 0.032166008088022675,
|
| 130 |
+
"acc_norm": 0.8194444444444444,
|
| 131 |
+
"acc_norm_stderr": 0.032166008088022675
|
| 132 |
+
},
|
| 133 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 134 |
+
"acc": 0.5,
|
| 135 |
+
"acc_stderr": 0.050251890762960605,
|
| 136 |
+
"acc_norm": 0.5,
|
| 137 |
+
"acc_norm_stderr": 0.050251890762960605
|
| 138 |
+
},
|
| 139 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 140 |
+
"acc": 0.57,
|
| 141 |
+
"acc_stderr": 0.049756985195624284,
|
| 142 |
+
"acc_norm": 0.57,
|
| 143 |
+
"acc_norm_stderr": 0.049756985195624284
|
| 144 |
+
},
|
| 145 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 146 |
+
"acc": 0.37,
|
| 147 |
+
"acc_stderr": 0.04852365870939099,
|
| 148 |
+
"acc_norm": 0.37,
|
| 149 |
+
"acc_norm_stderr": 0.04852365870939099
|
| 150 |
+
},
|
| 151 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 152 |
+
"acc": 0.6878612716763006,
|
| 153 |
+
"acc_stderr": 0.035331333893236574,
|
| 154 |
+
"acc_norm": 0.6878612716763006,
|
| 155 |
+
"acc_norm_stderr": 0.035331333893236574
|
| 156 |
+
},
|
| 157 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 158 |
+
"acc": 0.35294117647058826,
|
| 159 |
+
"acc_stderr": 0.047551296160629475,
|
| 160 |
+
"acc_norm": 0.35294117647058826,
|
| 161 |
+
"acc_norm_stderr": 0.047551296160629475
|
| 162 |
+
},
|
| 163 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 164 |
+
"acc": 0.7,
|
| 165 |
+
"acc_stderr": 0.046056618647183814,
|
| 166 |
+
"acc_norm": 0.7,
|
| 167 |
+
"acc_norm_stderr": 0.046056618647183814
|
| 168 |
+
},
|
| 169 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 170 |
+
"acc": 0.676595744680851,
|
| 171 |
+
"acc_stderr": 0.030579442773610337,
|
| 172 |
+
"acc_norm": 0.676595744680851,
|
| 173 |
+
"acc_norm_stderr": 0.030579442773610337
|
| 174 |
+
},
|
| 175 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 176 |
+
"acc": 0.40350877192982454,
|
| 177 |
+
"acc_stderr": 0.046151869625837026,
|
| 178 |
+
"acc_norm": 0.40350877192982454,
|
| 179 |
+
"acc_norm_stderr": 0.046151869625837026
|
| 180 |
+
},
|
| 181 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 182 |
+
"acc": 0.5793103448275863,
|
| 183 |
+
"acc_stderr": 0.04113914981189261,
|
| 184 |
+
"acc_norm": 0.5793103448275863,
|
| 185 |
+
"acc_norm_stderr": 0.04113914981189261
|
| 186 |
+
},
|
| 187 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 188 |
+
"acc": 0.4497354497354497,
|
| 189 |
+
"acc_stderr": 0.02562085704293665,
|
| 190 |
+
"acc_norm": 0.4497354497354497,
|
| 191 |
+
"acc_norm_stderr": 0.02562085704293665
|
| 192 |
+
},
|
| 193 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 194 |
+
"acc": 0.46825396825396826,
|
| 195 |
+
"acc_stderr": 0.04463112720677172,
|
| 196 |
+
"acc_norm": 0.46825396825396826,
|
| 197 |
+
"acc_norm_stderr": 0.04463112720677172
|
| 198 |
+
},
|
| 199 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 200 |
+
"acc": 0.46,
|
| 201 |
+
"acc_stderr": 0.05009082659620332,
|
| 202 |
+
"acc_norm": 0.46,
|
| 203 |
+
"acc_norm_stderr": 0.05009082659620332
|
| 204 |
+
},
|
| 205 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 206 |
+
"acc": 0.8129032258064516,
|
| 207 |
+
"acc_stderr": 0.022185710092252252,
|
| 208 |
+
"acc_norm": 0.8129032258064516,
|
| 209 |
+
"acc_norm_stderr": 0.022185710092252252
|
| 210 |
+
},
|
| 211 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 212 |
+
"acc": 0.5369458128078818,
|
| 213 |
+
"acc_stderr": 0.035083705204426656,
|
| 214 |
+
"acc_norm": 0.5369458128078818,
|
| 215 |
+
"acc_norm_stderr": 0.035083705204426656
|
| 216 |
+
},
|
| 217 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 218 |
+
"acc": 0.79,
|
| 219 |
+
"acc_stderr": 0.040936018074033256,
|
| 220 |
+
"acc_norm": 0.79,
|
| 221 |
+
"acc_norm_stderr": 0.040936018074033256
|
| 222 |
+
},
|
| 223 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 224 |
+
"acc": 0.8363636363636363,
|
| 225 |
+
"acc_stderr": 0.02888787239548795,
|
| 226 |
+
"acc_norm": 0.8363636363636363,
|
| 227 |
+
"acc_norm_stderr": 0.02888787239548795
|
| 228 |
+
},
|
| 229 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 230 |
+
"acc": 0.8686868686868687,
|
| 231 |
+
"acc_stderr": 0.024063156416822502,
|
| 232 |
+
"acc_norm": 0.8686868686868687,
|
| 233 |
+
"acc_norm_stderr": 0.024063156416822502
|
| 234 |
+
},
|
| 235 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 236 |
+
"acc": 0.927461139896373,
|
| 237 |
+
"acc_stderr": 0.018718998520678178,
|
| 238 |
+
"acc_norm": 0.927461139896373,
|
| 239 |
+
"acc_norm_stderr": 0.018718998520678178
|
| 240 |
+
},
|
| 241 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 242 |
+
"acc": 0.7025641025641025,
|
| 243 |
+
"acc_stderr": 0.023177408131465953,
|
| 244 |
+
"acc_norm": 0.7025641025641025,
|
| 245 |
+
"acc_norm_stderr": 0.023177408131465953
|
| 246 |
+
},
|
| 247 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 248 |
+
"acc": 0.34814814814814815,
|
| 249 |
+
"acc_stderr": 0.02904560029061626,
|
| 250 |
+
"acc_norm": 0.34814814814814815,
|
| 251 |
+
"acc_norm_stderr": 0.02904560029061626
|
| 252 |
+
},
|
| 253 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 254 |
+
"acc": 0.7941176470588235,
|
| 255 |
+
"acc_stderr": 0.02626502460827588,
|
| 256 |
+
"acc_norm": 0.7941176470588235,
|
| 257 |
+
"acc_norm_stderr": 0.02626502460827588
|
| 258 |
+
},
|
| 259 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 260 |
+
"acc": 0.4503311258278146,
|
| 261 |
+
"acc_stderr": 0.04062290018683776,
|
| 262 |
+
"acc_norm": 0.4503311258278146,
|
| 263 |
+
"acc_norm_stderr": 0.04062290018683776
|
| 264 |
+
},
|
| 265 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 266 |
+
"acc": 0.8954128440366973,
|
| 267 |
+
"acc_stderr": 0.013120530245265593,
|
| 268 |
+
"acc_norm": 0.8954128440366973,
|
| 269 |
+
"acc_norm_stderr": 0.013120530245265593
|
| 270 |
+
},
|
| 271 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 272 |
+
"acc": 0.5787037037037037,
|
| 273 |
+
"acc_stderr": 0.03367462138896078,
|
| 274 |
+
"acc_norm": 0.5787037037037037,
|
| 275 |
+
"acc_norm_stderr": 0.03367462138896078
|
| 276 |
+
},
|
| 277 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 278 |
+
"acc": 0.9166666666666666,
|
| 279 |
+
"acc_stderr": 0.019398452135813905,
|
| 280 |
+
"acc_norm": 0.9166666666666666,
|
| 281 |
+
"acc_norm_stderr": 0.019398452135813905
|
| 282 |
+
},
|
| 283 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 284 |
+
"acc": 0.8860759493670886,
|
| 285 |
+
"acc_stderr": 0.020681745135884565,
|
| 286 |
+
"acc_norm": 0.8860759493670886,
|
| 287 |
+
"acc_norm_stderr": 0.020681745135884565
|
| 288 |
+
},
|
| 289 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 290 |
+
"acc": 0.757847533632287,
|
| 291 |
+
"acc_stderr": 0.028751392398694755,
|
| 292 |
+
"acc_norm": 0.757847533632287,
|
| 293 |
+
"acc_norm_stderr": 0.028751392398694755
|
| 294 |
+
},
|
| 295 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 296 |
+
"acc": 0.8702290076335878,
|
| 297 |
+
"acc_stderr": 0.029473649496907065,
|
| 298 |
+
"acc_norm": 0.8702290076335878,
|
| 299 |
+
"acc_norm_stderr": 0.029473649496907065
|
| 300 |
+
},
|
| 301 |
+
"harness|hendrycksTest-international_law|5": {
|
| 302 |
+
"acc": 0.8181818181818182,
|
| 303 |
+
"acc_stderr": 0.03520893951097655,
|
| 304 |
+
"acc_norm": 0.8181818181818182,
|
| 305 |
+
"acc_norm_stderr": 0.03520893951097655
|
| 306 |
+
},
|
| 307 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 308 |
+
"acc": 0.8148148148148148,
|
| 309 |
+
"acc_stderr": 0.03755265865037181,
|
| 310 |
+
"acc_norm": 0.8148148148148148,
|
| 311 |
+
"acc_norm_stderr": 0.03755265865037181
|
| 312 |
+
},
|
| 313 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 314 |
+
"acc": 0.7791411042944786,
|
| 315 |
+
"acc_stderr": 0.03259177392742179,
|
| 316 |
+
"acc_norm": 0.7791411042944786,
|
| 317 |
+
"acc_norm_stderr": 0.03259177392742179
|
| 318 |
+
},
|
| 319 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 320 |
+
"acc": 0.48214285714285715,
|
| 321 |
+
"acc_stderr": 0.047427623612430116,
|
| 322 |
+
"acc_norm": 0.48214285714285715,
|
| 323 |
+
"acc_norm_stderr": 0.047427623612430116
|
| 324 |
+
},
|
| 325 |
+
"harness|hendrycksTest-management|5": {
|
| 326 |
+
"acc": 0.8446601941747572,
|
| 327 |
+
"acc_stderr": 0.03586594738573974,
|
| 328 |
+
"acc_norm": 0.8446601941747572,
|
| 329 |
+
"acc_norm_stderr": 0.03586594738573974
|
| 330 |
+
},
|
| 331 |
+
"harness|hendrycksTest-marketing|5": {
|
| 332 |
+
"acc": 0.905982905982906,
|
| 333 |
+
"acc_stderr": 0.019119892798924974,
|
| 334 |
+
"acc_norm": 0.905982905982906,
|
| 335 |
+
"acc_norm_stderr": 0.019119892798924974
|
| 336 |
+
},
|
| 337 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 338 |
+
"acc": 0.67,
|
| 339 |
+
"acc_stderr": 0.047258156262526066,
|
| 340 |
+
"acc_norm": 0.67,
|
| 341 |
+
"acc_norm_stderr": 0.047258156262526066
|
| 342 |
+
},
|
| 343 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 344 |
+
"acc": 0.8697318007662835,
|
| 345 |
+
"acc_stderr": 0.012036729568216054,
|
| 346 |
+
"acc_norm": 0.8697318007662835,
|
| 347 |
+
"acc_norm_stderr": 0.012036729568216054
|
| 348 |
+
},
|
| 349 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 350 |
+
"acc": 0.7774566473988439,
|
| 351 |
+
"acc_stderr": 0.02239421566194282,
|
| 352 |
+
"acc_norm": 0.7774566473988439,
|
| 353 |
+
"acc_norm_stderr": 0.02239421566194282
|
| 354 |
+
},
|
| 355 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 356 |
+
"acc": 0.5553072625698324,
|
| 357 |
+
"acc_stderr": 0.016619881988177012,
|
| 358 |
+
"acc_norm": 0.5553072625698324,
|
| 359 |
+
"acc_norm_stderr": 0.016619881988177012
|
| 360 |
+
},
|
| 361 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 362 |
+
"acc": 0.7516339869281046,
|
| 363 |
+
"acc_stderr": 0.024739981355113592,
|
| 364 |
+
"acc_norm": 0.7516339869281046,
|
| 365 |
+
"acc_norm_stderr": 0.024739981355113592
|
| 366 |
+
},
|
| 367 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 368 |
+
"acc": 0.77491961414791,
|
| 369 |
+
"acc_stderr": 0.023720088516179027,
|
| 370 |
+
"acc_norm": 0.77491961414791,
|
| 371 |
+
"acc_norm_stderr": 0.023720088516179027
|
| 372 |
+
},
|
| 373 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 374 |
+
"acc": 0.7962962962962963,
|
| 375 |
+
"acc_stderr": 0.02240967454730417,
|
| 376 |
+
"acc_norm": 0.7962962962962963,
|
| 377 |
+
"acc_norm_stderr": 0.02240967454730417
|
| 378 |
+
},
|
| 379 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 380 |
+
"acc": 0.5390070921985816,
|
| 381 |
+
"acc_stderr": 0.029736592526424445,
|
| 382 |
+
"acc_norm": 0.5390070921985816,
|
| 383 |
+
"acc_norm_stderr": 0.029736592526424445
|
| 384 |
+
},
|
| 385 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 386 |
+
"acc": 0.5586701434159062,
|
| 387 |
+
"acc_stderr": 0.012682016335646683,
|
| 388 |
+
"acc_norm": 0.5586701434159062,
|
| 389 |
+
"acc_norm_stderr": 0.012682016335646683
|
| 390 |
+
},
|
| 391 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 392 |
+
"acc": 0.7242647058823529,
|
| 393 |
+
"acc_stderr": 0.027146271936625162,
|
| 394 |
+
"acc_norm": 0.7242647058823529,
|
| 395 |
+
"acc_norm_stderr": 0.027146271936625162
|
| 396 |
+
},
|
| 397 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 398 |
+
"acc": 0.761437908496732,
|
| 399 |
+
"acc_stderr": 0.017242385828779627,
|
| 400 |
+
"acc_norm": 0.761437908496732,
|
| 401 |
+
"acc_norm_stderr": 0.017242385828779627
|
| 402 |
+
},
|
| 403 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 404 |
+
"acc": 0.7454545454545455,
|
| 405 |
+
"acc_stderr": 0.041723430387053825,
|
| 406 |
+
"acc_norm": 0.7454545454545455,
|
| 407 |
+
"acc_norm_stderr": 0.041723430387053825
|
| 408 |
+
},
|
| 409 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 410 |
+
"acc": 0.7877551020408163,
|
| 411 |
+
"acc_stderr": 0.026176967197866767,
|
| 412 |
+
"acc_norm": 0.7877551020408163,
|
| 413 |
+
"acc_norm_stderr": 0.026176967197866767
|
| 414 |
+
},
|
| 415 |
+
"harness|hendrycksTest-sociology|5": {
|
| 416 |
+
"acc": 0.8805970149253731,
|
| 417 |
+
"acc_stderr": 0.02292879327721974,
|
| 418 |
+
"acc_norm": 0.8805970149253731,
|
| 419 |
+
"acc_norm_stderr": 0.02292879327721974
|
| 420 |
+
},
|
| 421 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 422 |
+
"acc": 0.9,
|
| 423 |
+
"acc_stderr": 0.030151134457776334,
|
| 424 |
+
"acc_norm": 0.9,
|
| 425 |
+
"acc_norm_stderr": 0.030151134457776334
|
| 426 |
+
},
|
| 427 |
+
"harness|hendrycksTest-virology|5": {
|
| 428 |
+
"acc": 0.5602409638554217,
|
| 429 |
+
"acc_stderr": 0.03864139923699122,
|
| 430 |
+
"acc_norm": 0.5602409638554217,
|
| 431 |
+
"acc_norm_stderr": 0.03864139923699122
|
| 432 |
+
},
|
| 433 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 434 |
+
"acc": 0.8596491228070176,
|
| 435 |
+
"acc_stderr": 0.0266405825391332,
|
| 436 |
+
"acc_norm": 0.8596491228070176,
|
| 437 |
+
"acc_norm_stderr": 0.0266405825391332
|
| 438 |
+
},
|
| 439 |
+
"harness|truthfulqa:mc|0": {
|
| 440 |
+
"mc1": 0.40269277845777235,
|
| 441 |
+
"mc1_stderr": 0.01716883093518722,
|
| 442 |
+
"mc2": 0.5707095526544473,
|
| 443 |
+
"mc2_stderr": 0.01525040450448649
|
| 444 |
+
},
|
| 445 |
+
"harness|winogrande|5": {
|
| 446 |
+
"acc": 0.8176795580110497,
|
| 447 |
+
"acc_stderr": 0.010851565594267207
|
| 448 |
+
},
|
| 449 |
+
"harness|gsm8k|5": {
|
| 450 |
+
"acc": 0.6444275966641395,
|
| 451 |
+
"acc_stderr": 0.013185402252713852
|
| 452 |
+
}
|
| 453 |
+
}
|
| 454 |
+
```
|