Update README.md
Browse filesupdated evaluation result
README.md
CHANGED
|
@@ -41,4 +41,389 @@ experts:
|
|
| 41 |
- "solve"
|
| 42 |
- "count"
|
| 43 |
tokenizer_source: union
|
| 44 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
- "solve"
|
| 42 |
- "count"
|
| 43 |
tokenizer_source: union
|
| 44 |
+
```
|
| 45 |
+
|
| 46 |
+
Evaluation Result:
|
| 47 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__openmixtral-4x7b-merged
|
| 48 |
+
```
|
| 49 |
+
{
|
| 50 |
+
"all": {
|
| 51 |
+
"acc": 0.657144834577193,
|
| 52 |
+
"acc_stderr": 0.03198053543647407,
|
| 53 |
+
"acc_norm": 0.6572006879598793,
|
| 54 |
+
"acc_norm_stderr": 0.0326392415851668,
|
| 55 |
+
"mc1": 0.44430844553243576,
|
| 56 |
+
"mc1_stderr": 0.01739458625074317,
|
| 57 |
+
"mc2": 0.6132594486430695,
|
| 58 |
+
"mc2_stderr": 0.015532509494332434
|
| 59 |
+
},
|
| 60 |
+
"harness|arc:challenge|25": {
|
| 61 |
+
"acc": 0.6604095563139932,
|
| 62 |
+
"acc_stderr": 0.013839039762820166,
|
| 63 |
+
"acc_norm": 0.6945392491467577,
|
| 64 |
+
"acc_norm_stderr": 0.01346008047800251
|
| 65 |
+
},
|
| 66 |
+
"harness|hellaswag|10": {
|
| 67 |
+
"acc": 0.6901015733917546,
|
| 68 |
+
"acc_stderr": 0.004615063817741861,
|
| 69 |
+
"acc_norm": 0.8674566819358693,
|
| 70 |
+
"acc_norm_stderr": 0.0033838751726700217
|
| 71 |
+
},
|
| 72 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 73 |
+
"acc": 0.38,
|
| 74 |
+
"acc_stderr": 0.048783173121456316,
|
| 75 |
+
"acc_norm": 0.38,
|
| 76 |
+
"acc_norm_stderr": 0.048783173121456316
|
| 77 |
+
},
|
| 78 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 79 |
+
"acc": 0.6444444444444445,
|
| 80 |
+
"acc_stderr": 0.04135176749720385,
|
| 81 |
+
"acc_norm": 0.6444444444444445,
|
| 82 |
+
"acc_norm_stderr": 0.04135176749720385
|
| 83 |
+
},
|
| 84 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 85 |
+
"acc": 0.6776315789473685,
|
| 86 |
+
"acc_stderr": 0.03803510248351585,
|
| 87 |
+
"acc_norm": 0.6776315789473685,
|
| 88 |
+
"acc_norm_stderr": 0.03803510248351585
|
| 89 |
+
},
|
| 90 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 91 |
+
"acc": 0.63,
|
| 92 |
+
"acc_stderr": 0.04852365870939099,
|
| 93 |
+
"acc_norm": 0.63,
|
| 94 |
+
"acc_norm_stderr": 0.04852365870939099
|
| 95 |
+
},
|
| 96 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 97 |
+
"acc": 0.7358490566037735,
|
| 98 |
+
"acc_stderr": 0.027134291628741713,
|
| 99 |
+
"acc_norm": 0.7358490566037735,
|
| 100 |
+
"acc_norm_stderr": 0.027134291628741713
|
| 101 |
+
},
|
| 102 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 103 |
+
"acc": 0.7777777777777778,
|
| 104 |
+
"acc_stderr": 0.03476590104304134,
|
| 105 |
+
"acc_norm": 0.7777777777777778,
|
| 106 |
+
"acc_norm_stderr": 0.03476590104304134
|
| 107 |
+
},
|
| 108 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 109 |
+
"acc": 0.49,
|
| 110 |
+
"acc_stderr": 0.05024183937956911,
|
| 111 |
+
"acc_norm": 0.49,
|
| 112 |
+
"acc_norm_stderr": 0.05024183937956911
|
| 113 |
+
},
|
| 114 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 115 |
+
"acc": 0.57,
|
| 116 |
+
"acc_stderr": 0.04975698519562428,
|
| 117 |
+
"acc_norm": 0.57,
|
| 118 |
+
"acc_norm_stderr": 0.04975698519562428
|
| 119 |
+
},
|
| 120 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 121 |
+
"acc": 0.35,
|
| 122 |
+
"acc_stderr": 0.047937248544110196,
|
| 123 |
+
"acc_norm": 0.35,
|
| 124 |
+
"acc_norm_stderr": 0.047937248544110196
|
| 125 |
+
},
|
| 126 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 127 |
+
"acc": 0.6763005780346821,
|
| 128 |
+
"acc_stderr": 0.0356760379963917,
|
| 129 |
+
"acc_norm": 0.6763005780346821,
|
| 130 |
+
"acc_norm_stderr": 0.0356760379963917
|
| 131 |
+
},
|
| 132 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 133 |
+
"acc": 0.4117647058823529,
|
| 134 |
+
"acc_stderr": 0.048971049527263666,
|
| 135 |
+
"acc_norm": 0.4117647058823529,
|
| 136 |
+
"acc_norm_stderr": 0.048971049527263666
|
| 137 |
+
},
|
| 138 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 139 |
+
"acc": 0.76,
|
| 140 |
+
"acc_stderr": 0.04292346959909283,
|
| 141 |
+
"acc_norm": 0.76,
|
| 142 |
+
"acc_norm_stderr": 0.04292346959909283
|
| 143 |
+
},
|
| 144 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 145 |
+
"acc": 0.5531914893617021,
|
| 146 |
+
"acc_stderr": 0.0325005368436584,
|
| 147 |
+
"acc_norm": 0.5531914893617021,
|
| 148 |
+
"acc_norm_stderr": 0.0325005368436584
|
| 149 |
+
},
|
| 150 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 151 |
+
"acc": 0.5,
|
| 152 |
+
"acc_stderr": 0.047036043419179864,
|
| 153 |
+
"acc_norm": 0.5,
|
| 154 |
+
"acc_norm_stderr": 0.047036043419179864
|
| 155 |
+
},
|
| 156 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 157 |
+
"acc": 0.5655172413793104,
|
| 158 |
+
"acc_stderr": 0.04130740879555497,
|
| 159 |
+
"acc_norm": 0.5655172413793104,
|
| 160 |
+
"acc_norm_stderr": 0.04130740879555497
|
| 161 |
+
},
|
| 162 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 163 |
+
"acc": 0.42328042328042326,
|
| 164 |
+
"acc_stderr": 0.025446365634406793,
|
| 165 |
+
"acc_norm": 0.42328042328042326,
|
| 166 |
+
"acc_norm_stderr": 0.025446365634406793
|
| 167 |
+
},
|
| 168 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 169 |
+
"acc": 0.47619047619047616,
|
| 170 |
+
"acc_stderr": 0.04467062628403273,
|
| 171 |
+
"acc_norm": 0.47619047619047616,
|
| 172 |
+
"acc_norm_stderr": 0.04467062628403273
|
| 173 |
+
},
|
| 174 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 175 |
+
"acc": 0.33,
|
| 176 |
+
"acc_stderr": 0.047258156262526045,
|
| 177 |
+
"acc_norm": 0.33,
|
| 178 |
+
"acc_norm_stderr": 0.047258156262526045
|
| 179 |
+
},
|
| 180 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 181 |
+
"acc": 0.8064516129032258,
|
| 182 |
+
"acc_stderr": 0.022475258525536057,
|
| 183 |
+
"acc_norm": 0.8064516129032258,
|
| 184 |
+
"acc_norm_stderr": 0.022475258525536057
|
| 185 |
+
},
|
| 186 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 187 |
+
"acc": 0.5123152709359606,
|
| 188 |
+
"acc_stderr": 0.035169204442208966,
|
| 189 |
+
"acc_norm": 0.5123152709359606,
|
| 190 |
+
"acc_norm_stderr": 0.035169204442208966
|
| 191 |
+
},
|
| 192 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 193 |
+
"acc": 0.72,
|
| 194 |
+
"acc_stderr": 0.04512608598542127,
|
| 195 |
+
"acc_norm": 0.72,
|
| 196 |
+
"acc_norm_stderr": 0.04512608598542127
|
| 197 |
+
},
|
| 198 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 199 |
+
"acc": 0.7757575757575758,
|
| 200 |
+
"acc_stderr": 0.03256866661681102,
|
| 201 |
+
"acc_norm": 0.7757575757575758,
|
| 202 |
+
"acc_norm_stderr": 0.03256866661681102
|
| 203 |
+
},
|
| 204 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 205 |
+
"acc": 0.8080808080808081,
|
| 206 |
+
"acc_stderr": 0.028057791672989017,
|
| 207 |
+
"acc_norm": 0.8080808080808081,
|
| 208 |
+
"acc_norm_stderr": 0.028057791672989017
|
| 209 |
+
},
|
| 210 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 211 |
+
"acc": 0.8963730569948186,
|
| 212 |
+
"acc_stderr": 0.02199531196364424,
|
| 213 |
+
"acc_norm": 0.8963730569948186,
|
| 214 |
+
"acc_norm_stderr": 0.02199531196364424
|
| 215 |
+
},
|
| 216 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 217 |
+
"acc": 0.6666666666666666,
|
| 218 |
+
"acc_stderr": 0.023901157979402534,
|
| 219 |
+
"acc_norm": 0.6666666666666666,
|
| 220 |
+
"acc_norm_stderr": 0.023901157979402534
|
| 221 |
+
},
|
| 222 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 223 |
+
"acc": 0.34814814814814815,
|
| 224 |
+
"acc_stderr": 0.029045600290616255,
|
| 225 |
+
"acc_norm": 0.34814814814814815,
|
| 226 |
+
"acc_norm_stderr": 0.029045600290616255
|
| 227 |
+
},
|
| 228 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 229 |
+
"acc": 0.7142857142857143,
|
| 230 |
+
"acc_stderr": 0.029344572500634335,
|
| 231 |
+
"acc_norm": 0.7142857142857143,
|
| 232 |
+
"acc_norm_stderr": 0.029344572500634335
|
| 233 |
+
},
|
| 234 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 235 |
+
"acc": 0.31788079470198677,
|
| 236 |
+
"acc_stderr": 0.038020397601079024,
|
| 237 |
+
"acc_norm": 0.31788079470198677,
|
| 238 |
+
"acc_norm_stderr": 0.038020397601079024
|
| 239 |
+
},
|
| 240 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 241 |
+
"acc": 0.8495412844036697,
|
| 242 |
+
"acc_stderr": 0.015328563932669237,
|
| 243 |
+
"acc_norm": 0.8495412844036697,
|
| 244 |
+
"acc_norm_stderr": 0.015328563932669237
|
| 245 |
+
},
|
| 246 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 247 |
+
"acc": 0.5231481481481481,
|
| 248 |
+
"acc_stderr": 0.03406315360711507,
|
| 249 |
+
"acc_norm": 0.5231481481481481,
|
| 250 |
+
"acc_norm_stderr": 0.03406315360711507
|
| 251 |
+
},
|
| 252 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 253 |
+
"acc": 0.8480392156862745,
|
| 254 |
+
"acc_stderr": 0.025195658428931796,
|
| 255 |
+
"acc_norm": 0.8480392156862745,
|
| 256 |
+
"acc_norm_stderr": 0.025195658428931796
|
| 257 |
+
},
|
| 258 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 259 |
+
"acc": 0.810126582278481,
|
| 260 |
+
"acc_stderr": 0.025530100460233504,
|
| 261 |
+
"acc_norm": 0.810126582278481,
|
| 262 |
+
"acc_norm_stderr": 0.025530100460233504
|
| 263 |
+
},
|
| 264 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 265 |
+
"acc": 0.695067264573991,
|
| 266 |
+
"acc_stderr": 0.030898610882477515,
|
| 267 |
+
"acc_norm": 0.695067264573991,
|
| 268 |
+
"acc_norm_stderr": 0.030898610882477515
|
| 269 |
+
},
|
| 270 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 271 |
+
"acc": 0.7709923664122137,
|
| 272 |
+
"acc_stderr": 0.036853466317118506,
|
| 273 |
+
"acc_norm": 0.7709923664122137,
|
| 274 |
+
"acc_norm_stderr": 0.036853466317118506
|
| 275 |
+
},
|
| 276 |
+
"harness|hendrycksTest-international_law|5": {
|
| 277 |
+
"acc": 0.8016528925619835,
|
| 278 |
+
"acc_stderr": 0.03640118271990947,
|
| 279 |
+
"acc_norm": 0.8016528925619835,
|
| 280 |
+
"acc_norm_stderr": 0.03640118271990947
|
| 281 |
+
},
|
| 282 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 283 |
+
"acc": 0.8240740740740741,
|
| 284 |
+
"acc_stderr": 0.036809181416738807,
|
| 285 |
+
"acc_norm": 0.8240740740740741,
|
| 286 |
+
"acc_norm_stderr": 0.036809181416738807
|
| 287 |
+
},
|
| 288 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 289 |
+
"acc": 0.754601226993865,
|
| 290 |
+
"acc_stderr": 0.03380939813943354,
|
| 291 |
+
"acc_norm": 0.754601226993865,
|
| 292 |
+
"acc_norm_stderr": 0.03380939813943354
|
| 293 |
+
},
|
| 294 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 295 |
+
"acc": 0.4642857142857143,
|
| 296 |
+
"acc_stderr": 0.04733667890053756,
|
| 297 |
+
"acc_norm": 0.4642857142857143,
|
| 298 |
+
"acc_norm_stderr": 0.04733667890053756
|
| 299 |
+
},
|
| 300 |
+
"harness|hendrycksTest-management|5": {
|
| 301 |
+
"acc": 0.7961165048543689,
|
| 302 |
+
"acc_stderr": 0.039891398595317706,
|
| 303 |
+
"acc_norm": 0.7961165048543689,
|
| 304 |
+
"acc_norm_stderr": 0.039891398595317706
|
| 305 |
+
},
|
| 306 |
+
"harness|hendrycksTest-marketing|5": {
|
| 307 |
+
"acc": 0.8846153846153846,
|
| 308 |
+
"acc_stderr": 0.020930193185179326,
|
| 309 |
+
"acc_norm": 0.8846153846153846,
|
| 310 |
+
"acc_norm_stderr": 0.020930193185179326
|
| 311 |
+
},
|
| 312 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 313 |
+
"acc": 0.72,
|
| 314 |
+
"acc_stderr": 0.045126085985421276,
|
| 315 |
+
"acc_norm": 0.72,
|
| 316 |
+
"acc_norm_stderr": 0.045126085985421276
|
| 317 |
+
},
|
| 318 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 319 |
+
"acc": 0.8288633461047255,
|
| 320 |
+
"acc_stderr": 0.0134682016140663,
|
| 321 |
+
"acc_norm": 0.8288633461047255,
|
| 322 |
+
"acc_norm_stderr": 0.0134682016140663
|
| 323 |
+
},
|
| 324 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 325 |
+
"acc": 0.7369942196531792,
|
| 326 |
+
"acc_stderr": 0.023703099525258172,
|
| 327 |
+
"acc_norm": 0.7369942196531792,
|
| 328 |
+
"acc_norm_stderr": 0.023703099525258172
|
| 329 |
+
},
|
| 330 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 331 |
+
"acc": 0.41564245810055866,
|
| 332 |
+
"acc_stderr": 0.016482782187500676,
|
| 333 |
+
"acc_norm": 0.41564245810055866,
|
| 334 |
+
"acc_norm_stderr": 0.016482782187500676
|
| 335 |
+
},
|
| 336 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 337 |
+
"acc": 0.7320261437908496,
|
| 338 |
+
"acc_stderr": 0.025360603796242557,
|
| 339 |
+
"acc_norm": 0.7320261437908496,
|
| 340 |
+
"acc_norm_stderr": 0.025360603796242557
|
| 341 |
+
},
|
| 342 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 343 |
+
"acc": 0.7363344051446945,
|
| 344 |
+
"acc_stderr": 0.02502553850053234,
|
| 345 |
+
"acc_norm": 0.7363344051446945,
|
| 346 |
+
"acc_norm_stderr": 0.02502553850053234
|
| 347 |
+
},
|
| 348 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 349 |
+
"acc": 0.7376543209876543,
|
| 350 |
+
"acc_stderr": 0.024477222856135107,
|
| 351 |
+
"acc_norm": 0.7376543209876543,
|
| 352 |
+
"acc_norm_stderr": 0.024477222856135107
|
| 353 |
+
},
|
| 354 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 355 |
+
"acc": 0.5141843971631206,
|
| 356 |
+
"acc_stderr": 0.02981549448368206,
|
| 357 |
+
"acc_norm": 0.5141843971631206,
|
| 358 |
+
"acc_norm_stderr": 0.02981549448368206
|
| 359 |
+
},
|
| 360 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 361 |
+
"acc": 0.46740547588005216,
|
| 362 |
+
"acc_stderr": 0.012743072942653349,
|
| 363 |
+
"acc_norm": 0.46740547588005216,
|
| 364 |
+
"acc_norm_stderr": 0.012743072942653349
|
| 365 |
+
},
|
| 366 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 367 |
+
"acc": 0.6801470588235294,
|
| 368 |
+
"acc_stderr": 0.028332959514031218,
|
| 369 |
+
"acc_norm": 0.6801470588235294,
|
| 370 |
+
"acc_norm_stderr": 0.028332959514031218
|
| 371 |
+
},
|
| 372 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 373 |
+
"acc": 0.6699346405228758,
|
| 374 |
+
"acc_stderr": 0.019023726160724553,
|
| 375 |
+
"acc_norm": 0.6699346405228758,
|
| 376 |
+
"acc_norm_stderr": 0.019023726160724553
|
| 377 |
+
},
|
| 378 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 379 |
+
"acc": 0.6727272727272727,
|
| 380 |
+
"acc_stderr": 0.0449429086625209,
|
| 381 |
+
"acc_norm": 0.6727272727272727,
|
| 382 |
+
"acc_norm_stderr": 0.0449429086625209
|
| 383 |
+
},
|
| 384 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 385 |
+
"acc": 0.7142857142857143,
|
| 386 |
+
"acc_stderr": 0.0289205832206756,
|
| 387 |
+
"acc_norm": 0.7142857142857143,
|
| 388 |
+
"acc_norm_stderr": 0.0289205832206756
|
| 389 |
+
},
|
| 390 |
+
"harness|hendrycksTest-sociology|5": {
|
| 391 |
+
"acc": 0.845771144278607,
|
| 392 |
+
"acc_stderr": 0.025538433368578337,
|
| 393 |
+
"acc_norm": 0.845771144278607,
|
| 394 |
+
"acc_norm_stderr": 0.025538433368578337
|
| 395 |
+
},
|
| 396 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 397 |
+
"acc": 0.84,
|
| 398 |
+
"acc_stderr": 0.03684529491774708,
|
| 399 |
+
"acc_norm": 0.84,
|
| 400 |
+
"acc_norm_stderr": 0.03684529491774708
|
| 401 |
+
},
|
| 402 |
+
"harness|hendrycksTest-virology|5": {
|
| 403 |
+
"acc": 0.536144578313253,
|
| 404 |
+
"acc_stderr": 0.038823108508905954,
|
| 405 |
+
"acc_norm": 0.536144578313253,
|
| 406 |
+
"acc_norm_stderr": 0.038823108508905954
|
| 407 |
+
},
|
| 408 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 409 |
+
"acc": 0.8245614035087719,
|
| 410 |
+
"acc_stderr": 0.02917088550072767,
|
| 411 |
+
"acc_norm": 0.8245614035087719,
|
| 412 |
+
"acc_norm_stderr": 0.02917088550072767
|
| 413 |
+
},
|
| 414 |
+
"harness|truthfulqa:mc|0": {
|
| 415 |
+
"mc1": 0.44430844553243576,
|
| 416 |
+
"mc1_stderr": 0.01739458625074317,
|
| 417 |
+
"mc2": 0.6132594486430695,
|
| 418 |
+
"mc2_stderr": 0.015532509494332434
|
| 419 |
+
},
|
| 420 |
+
"harness|winogrande|5": {
|
| 421 |
+
"acc": 0.8105761641673244,
|
| 422 |
+
"acc_stderr": 0.011012790432989245
|
| 423 |
+
},
|
| 424 |
+
"harness|gsm8k|5": {
|
| 425 |
+
"acc": 0.7119029567854435,
|
| 426 |
+
"acc_stderr": 0.012474469737197916
|
| 427 |
+
}
|
| 428 |
+
}
|
| 429 |
+
```
|