Update README.md
Browse files
README.md
CHANGED
|
@@ -48,4 +48,390 @@ prompt.
|
|
| 48 |
>>> """
|
| 49 |
>>> res = generate_text(prompt)
|
| 50 |
>>> res
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
```
|
|
|
|
| 48 |
>>> """
|
| 49 |
>>> res = generate_text(prompt)
|
| 50 |
>>> res
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
## Leaderboard
|
| 54 |
+
|
| 55 |
+
```python
|
| 56 |
+
{
|
| 57 |
+
"all": {
|
| 58 |
+
"acc": 0.24915779048270345,
|
| 59 |
+
"acc_stderr": 0.030509906389610868,
|
| 60 |
+
"acc_norm": 0.25041231816215265,
|
| 61 |
+
"acc_norm_stderr": 0.03132600249114931,
|
| 62 |
+
"mc1": 0.2521419828641371,
|
| 63 |
+
"mc1_stderr": 0.015201522246299965,
|
| 64 |
+
"mc2": 0.41257163824244014,
|
| 65 |
+
"mc2_stderr": 0.015127188811834062
|
| 66 |
+
},
|
| 67 |
+
"harness|arc:challenge|25": {
|
| 68 |
+
"acc": 0.18686006825938567,
|
| 69 |
+
"acc_stderr": 0.011391015649694391,
|
| 70 |
+
"acc_norm": 0.23976109215017063,
|
| 71 |
+
"acc_norm_stderr": 0.012476304127453954
|
| 72 |
+
},
|
| 73 |
+
"harness|hellaswag|10": {
|
| 74 |
+
"acc": 0.28978291177056364,
|
| 75 |
+
"acc_stderr": 0.004527343651130803,
|
| 76 |
+
"acc_norm": 0.3121888070105557,
|
| 77 |
+
"acc_norm_stderr": 0.0046243936909668975
|
| 78 |
+
},
|
| 79 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 80 |
+
"acc": 0.22,
|
| 81 |
+
"acc_stderr": 0.04163331998932268,
|
| 82 |
+
"acc_norm": 0.22,
|
| 83 |
+
"acc_norm_stderr": 0.04163331998932268
|
| 84 |
+
},
|
| 85 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 86 |
+
"acc": 0.3037037037037037,
|
| 87 |
+
"acc_stderr": 0.039725528847851375,
|
| 88 |
+
"acc_norm": 0.3037037037037037,
|
| 89 |
+
"acc_norm_stderr": 0.039725528847851375
|
| 90 |
+
},
|
| 91 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 92 |
+
"acc": 0.17763157894736842,
|
| 93 |
+
"acc_stderr": 0.031103182383123398,
|
| 94 |
+
"acc_norm": 0.17763157894736842,
|
| 95 |
+
"acc_norm_stderr": 0.031103182383123398
|
| 96 |
+
},
|
| 97 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 98 |
+
"acc": 0.26,
|
| 99 |
+
"acc_stderr": 0.0440844002276808,
|
| 100 |
+
"acc_norm": 0.26,
|
| 101 |
+
"acc_norm_stderr": 0.0440844002276808
|
| 102 |
+
},
|
| 103 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 104 |
+
"acc": 0.23018867924528302,
|
| 105 |
+
"acc_stderr": 0.025907897122408173,
|
| 106 |
+
"acc_norm": 0.23018867924528302,
|
| 107 |
+
"acc_norm_stderr": 0.025907897122408173
|
| 108 |
+
},
|
| 109 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 110 |
+
"acc": 0.2569444444444444,
|
| 111 |
+
"acc_stderr": 0.03653946969442099,
|
| 112 |
+
"acc_norm": 0.2569444444444444,
|
| 113 |
+
"acc_norm_stderr": 0.03653946969442099
|
| 114 |
+
},
|
| 115 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 116 |
+
"acc": 0.19,
|
| 117 |
+
"acc_stderr": 0.039427724440366234,
|
| 118 |
+
"acc_norm": 0.19,
|
| 119 |
+
"acc_norm_stderr": 0.039427724440366234
|
| 120 |
+
},
|
| 121 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 122 |
+
"acc": 0.24,
|
| 123 |
+
"acc_stderr": 0.04292346959909283,
|
| 124 |
+
"acc_norm": 0.24,
|
| 125 |
+
"acc_norm_stderr": 0.04292346959909283
|
| 126 |
+
},
|
| 127 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 128 |
+
"acc": 0.29,
|
| 129 |
+
"acc_stderr": 0.04560480215720684,
|
| 130 |
+
"acc_norm": 0.29,
|
| 131 |
+
"acc_norm_stderr": 0.04560480215720684
|
| 132 |
+
},
|
| 133 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 134 |
+
"acc": 0.2543352601156069,
|
| 135 |
+
"acc_stderr": 0.0332055644308557,
|
| 136 |
+
"acc_norm": 0.2543352601156069,
|
| 137 |
+
"acc_norm_stderr": 0.0332055644308557
|
| 138 |
+
},
|
| 139 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 140 |
+
"acc": 0.21568627450980393,
|
| 141 |
+
"acc_stderr": 0.04092563958237654,
|
| 142 |
+
"acc_norm": 0.21568627450980393,
|
| 143 |
+
"acc_norm_stderr": 0.04092563958237654
|
| 144 |
+
},
|
| 145 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 146 |
+
"acc": 0.34,
|
| 147 |
+
"acc_stderr": 0.04760952285695236,
|
| 148 |
+
"acc_norm": 0.34,
|
| 149 |
+
"acc_norm_stderr": 0.04760952285695236
|
| 150 |
+
},
|
| 151 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 152 |
+
"acc": 0.26382978723404255,
|
| 153 |
+
"acc_stderr": 0.028809989854102973,
|
| 154 |
+
"acc_norm": 0.26382978723404255,
|
| 155 |
+
"acc_norm_stderr": 0.028809989854102973
|
| 156 |
+
},
|
| 157 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 158 |
+
"acc": 0.24561403508771928,
|
| 159 |
+
"acc_stderr": 0.04049339297748142,
|
| 160 |
+
"acc_norm": 0.24561403508771928,
|
| 161 |
+
"acc_norm_stderr": 0.04049339297748142
|
| 162 |
+
},
|
| 163 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 164 |
+
"acc": 0.2413793103448276,
|
| 165 |
+
"acc_stderr": 0.03565998174135302,
|
| 166 |
+
"acc_norm": 0.2413793103448276,
|
| 167 |
+
"acc_norm_stderr": 0.03565998174135302
|
| 168 |
+
},
|
| 169 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 170 |
+
"acc": 0.24074074074074073,
|
| 171 |
+
"acc_stderr": 0.02201908001221789,
|
| 172 |
+
"acc_norm": 0.24074074074074073,
|
| 173 |
+
"acc_norm_stderr": 0.02201908001221789
|
| 174 |
+
},
|
| 175 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 176 |
+
"acc": 0.1349206349206349,
|
| 177 |
+
"acc_stderr": 0.030557101589417515,
|
| 178 |
+
"acc_norm": 0.1349206349206349,
|
| 179 |
+
"acc_norm_stderr": 0.030557101589417515
|
| 180 |
+
},
|
| 181 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 182 |
+
"acc": 0.16,
|
| 183 |
+
"acc_stderr": 0.03684529491774708,
|
| 184 |
+
"acc_norm": 0.16,
|
| 185 |
+
"acc_norm_stderr": 0.03684529491774708
|
| 186 |
+
},
|
| 187 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 188 |
+
"acc": 0.1774193548387097,
|
| 189 |
+
"acc_stderr": 0.02173254068932927,
|
| 190 |
+
"acc_norm": 0.1774193548387097,
|
| 191 |
+
"acc_norm_stderr": 0.02173254068932927
|
| 192 |
+
},
|
| 193 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 194 |
+
"acc": 0.24630541871921183,
|
| 195 |
+
"acc_stderr": 0.030315099285617736,
|
| 196 |
+
"acc_norm": 0.24630541871921183,
|
| 197 |
+
"acc_norm_stderr": 0.030315099285617736
|
| 198 |
+
},
|
| 199 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 200 |
+
"acc": 0.28,
|
| 201 |
+
"acc_stderr": 0.04512608598542126,
|
| 202 |
+
"acc_norm": 0.28,
|
| 203 |
+
"acc_norm_stderr": 0.04512608598542126
|
| 204 |
+
},
|
| 205 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 206 |
+
"acc": 0.21818181818181817,
|
| 207 |
+
"acc_stderr": 0.03225078108306289,
|
| 208 |
+
"acc_norm": 0.21818181818181817,
|
| 209 |
+
"acc_norm_stderr": 0.03225078108306289
|
| 210 |
+
},
|
| 211 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 212 |
+
"acc": 0.3282828282828283,
|
| 213 |
+
"acc_stderr": 0.03345678422756776,
|
| 214 |
+
"acc_norm": 0.3282828282828283,
|
| 215 |
+
"acc_norm_stderr": 0.03345678422756776
|
| 216 |
+
},
|
| 217 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 218 |
+
"acc": 0.37305699481865284,
|
| 219 |
+
"acc_stderr": 0.03490205592048573,
|
| 220 |
+
"acc_norm": 0.37305699481865284,
|
| 221 |
+
"acc_norm_stderr": 0.03490205592048573
|
| 222 |
+
},
|
| 223 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 224 |
+
"acc": 0.26666666666666666,
|
| 225 |
+
"acc_stderr": 0.02242127361292371,
|
| 226 |
+
"acc_norm": 0.26666666666666666,
|
| 227 |
+
"acc_norm_stderr": 0.02242127361292371
|
| 228 |
+
},
|
| 229 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 230 |
+
"acc": 0.21481481481481482,
|
| 231 |
+
"acc_stderr": 0.025040443877000683,
|
| 232 |
+
"acc_norm": 0.21481481481481482,
|
| 233 |
+
"acc_norm_stderr": 0.025040443877000683
|
| 234 |
+
},
|
| 235 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 236 |
+
"acc": 0.22268907563025211,
|
| 237 |
+
"acc_stderr": 0.027025433498882364,
|
| 238 |
+
"acc_norm": 0.22268907563025211,
|
| 239 |
+
"acc_norm_stderr": 0.027025433498882364
|
| 240 |
+
},
|
| 241 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 242 |
+
"acc": 0.23178807947019867,
|
| 243 |
+
"acc_stderr": 0.034454062719870546,
|
| 244 |
+
"acc_norm": 0.23178807947019867,
|
| 245 |
+
"acc_norm_stderr": 0.034454062719870546
|
| 246 |
+
},
|
| 247 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 248 |
+
"acc": 0.3302752293577982,
|
| 249 |
+
"acc_stderr": 0.02016446633634298,
|
| 250 |
+
"acc_norm": 0.3302752293577982,
|
| 251 |
+
"acc_norm_stderr": 0.02016446633634298
|
| 252 |
+
},
|
| 253 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 254 |
+
"acc": 0.19444444444444445,
|
| 255 |
+
"acc_stderr": 0.026991454502036733,
|
| 256 |
+
"acc_norm": 0.19444444444444445,
|
| 257 |
+
"acc_norm_stderr": 0.026991454502036733
|
| 258 |
+
},
|
| 259 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 260 |
+
"acc": 0.25,
|
| 261 |
+
"acc_stderr": 0.03039153369274154,
|
| 262 |
+
"acc_norm": 0.25,
|
| 263 |
+
"acc_norm_stderr": 0.03039153369274154
|
| 264 |
+
},
|
| 265 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 266 |
+
"acc": 0.26582278481012656,
|
| 267 |
+
"acc_stderr": 0.028756799629658342,
|
| 268 |
+
"acc_norm": 0.26582278481012656,
|
| 269 |
+
"acc_norm_stderr": 0.028756799629658342
|
| 270 |
+
},
|
| 271 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 272 |
+
"acc": 0.17937219730941703,
|
| 273 |
+
"acc_stderr": 0.0257498195691928,
|
| 274 |
+
"acc_norm": 0.17937219730941703,
|
| 275 |
+
"acc_norm_stderr": 0.0257498195691928
|
| 276 |
+
},
|
| 277 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 278 |
+
"acc": 0.2366412213740458,
|
| 279 |
+
"acc_stderr": 0.037276735755969174,
|
| 280 |
+
"acc_norm": 0.2366412213740458,
|
| 281 |
+
"acc_norm_stderr": 0.037276735755969174
|
| 282 |
+
},
|
| 283 |
+
"harness|hendrycksTest-international_law|5": {
|
| 284 |
+
"acc": 0.35537190082644626,
|
| 285 |
+
"acc_stderr": 0.04369236326573981,
|
| 286 |
+
"acc_norm": 0.35537190082644626,
|
| 287 |
+
"acc_norm_stderr": 0.04369236326573981
|
| 288 |
+
},
|
| 289 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 290 |
+
"acc": 0.25925925925925924,
|
| 291 |
+
"acc_stderr": 0.042365112580946336,
|
| 292 |
+
"acc_norm": 0.25925925925925924,
|
| 293 |
+
"acc_norm_stderr": 0.042365112580946336
|
| 294 |
+
},
|
| 295 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 296 |
+
"acc": 0.2822085889570552,
|
| 297 |
+
"acc_stderr": 0.03536117886664742,
|
| 298 |
+
"acc_norm": 0.2822085889570552,
|
| 299 |
+
"acc_norm_stderr": 0.03536117886664742
|
| 300 |
+
},
|
| 301 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 302 |
+
"acc": 0.32142857142857145,
|
| 303 |
+
"acc_stderr": 0.04432804055291519,
|
| 304 |
+
"acc_norm": 0.32142857142857145,
|
| 305 |
+
"acc_norm_stderr": 0.04432804055291519
|
| 306 |
+
},
|
| 307 |
+
"harness|hendrycksTest-management|5": {
|
| 308 |
+
"acc": 0.1941747572815534,
|
| 309 |
+
"acc_stderr": 0.03916667762822585,
|
| 310 |
+
"acc_norm": 0.1941747572815534,
|
| 311 |
+
"acc_norm_stderr": 0.03916667762822585
|
| 312 |
+
},
|
| 313 |
+
"harness|hendrycksTest-marketing|5": {
|
| 314 |
+
"acc": 0.2905982905982906,
|
| 315 |
+
"acc_stderr": 0.02974504857267404,
|
| 316 |
+
"acc_norm": 0.2905982905982906,
|
| 317 |
+
"acc_norm_stderr": 0.02974504857267404
|
| 318 |
+
},
|
| 319 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 320 |
+
"acc": 0.25,
|
| 321 |
+
"acc_stderr": 0.04351941398892446,
|
| 322 |
+
"acc_norm": 0.25,
|
| 323 |
+
"acc_norm_stderr": 0.04351941398892446
|
| 324 |
+
},
|
| 325 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 326 |
+
"acc": 0.23627075351213284,
|
| 327 |
+
"acc_stderr": 0.015190473717037497,
|
| 328 |
+
"acc_norm": 0.23627075351213284,
|
| 329 |
+
"acc_norm_stderr": 0.015190473717037497
|
| 330 |
+
},
|
| 331 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 332 |
+
"acc": 0.24566473988439305,
|
| 333 |
+
"acc_stderr": 0.02317629820399201,
|
| 334 |
+
"acc_norm": 0.24566473988439305,
|
| 335 |
+
"acc_norm_stderr": 0.02317629820399201
|
| 336 |
+
},
|
| 337 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 338 |
+
"acc": 0.24581005586592178,
|
| 339 |
+
"acc_stderr": 0.014400296429225587,
|
| 340 |
+
"acc_norm": 0.24581005586592178,
|
| 341 |
+
"acc_norm_stderr": 0.014400296429225587
|
| 342 |
+
},
|
| 343 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 344 |
+
"acc": 0.25163398692810457,
|
| 345 |
+
"acc_stderr": 0.024848018263875195,
|
| 346 |
+
"acc_norm": 0.25163398692810457,
|
| 347 |
+
"acc_norm_stderr": 0.024848018263875195
|
| 348 |
+
},
|
| 349 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 350 |
+
"acc": 0.18006430868167203,
|
| 351 |
+
"acc_stderr": 0.021823422857744953,
|
| 352 |
+
"acc_norm": 0.18006430868167203,
|
| 353 |
+
"acc_norm_stderr": 0.021823422857744953
|
| 354 |
+
},
|
| 355 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 356 |
+
"acc": 0.25617283950617287,
|
| 357 |
+
"acc_stderr": 0.024288533637726095,
|
| 358 |
+
"acc_norm": 0.25617283950617287,
|
| 359 |
+
"acc_norm_stderr": 0.024288533637726095
|
| 360 |
+
},
|
| 361 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 362 |
+
"acc": 0.2801418439716312,
|
| 363 |
+
"acc_stderr": 0.02678917235114023,
|
| 364 |
+
"acc_norm": 0.2801418439716312,
|
| 365 |
+
"acc_norm_stderr": 0.02678917235114023
|
| 366 |
+
},
|
| 367 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 368 |
+
"acc": 0.24837027379400262,
|
| 369 |
+
"acc_stderr": 0.011035212598034503,
|
| 370 |
+
"acc_norm": 0.24837027379400262,
|
| 371 |
+
"acc_norm_stderr": 0.011035212598034503
|
| 372 |
+
},
|
| 373 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 374 |
+
"acc": 0.3125,
|
| 375 |
+
"acc_stderr": 0.02815637344037142,
|
| 376 |
+
"acc_norm": 0.3125,
|
| 377 |
+
"acc_norm_stderr": 0.02815637344037142
|
| 378 |
+
},
|
| 379 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 380 |
+
"acc": 0.25,
|
| 381 |
+
"acc_stderr": 0.01751781884501444,
|
| 382 |
+
"acc_norm": 0.25,
|
| 383 |
+
"acc_norm_stderr": 0.01751781884501444
|
| 384 |
+
},
|
| 385 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 386 |
+
"acc": 0.18181818181818182,
|
| 387 |
+
"acc_stderr": 0.03694284335337801,
|
| 388 |
+
"acc_norm": 0.18181818181818182,
|
| 389 |
+
"acc_norm_stderr": 0.03694284335337801
|
| 390 |
+
},
|
| 391 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 392 |
+
"acc": 0.31020408163265306,
|
| 393 |
+
"acc_stderr": 0.029613459872484378,
|
| 394 |
+
"acc_norm": 0.31020408163265306,
|
| 395 |
+
"acc_norm_stderr": 0.029613459872484378
|
| 396 |
+
},
|
| 397 |
+
"harness|hendrycksTest-sociology|5": {
|
| 398 |
+
"acc": 0.24875621890547264,
|
| 399 |
+
"acc_stderr": 0.030567675938916707,
|
| 400 |
+
"acc_norm": 0.24875621890547264,
|
| 401 |
+
"acc_norm_stderr": 0.030567675938916707
|
| 402 |
+
},
|
| 403 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 404 |
+
"acc": 0.25,
|
| 405 |
+
"acc_stderr": 0.04351941398892446,
|
| 406 |
+
"acc_norm": 0.25,
|
| 407 |
+
"acc_norm_stderr": 0.04351941398892446
|
| 408 |
+
},
|
| 409 |
+
"harness|hendrycksTest-virology|5": {
|
| 410 |
+
"acc": 0.19879518072289157,
|
| 411 |
+
"acc_stderr": 0.03106939026078942,
|
| 412 |
+
"acc_norm": 0.19879518072289157,
|
| 413 |
+
"acc_norm_stderr": 0.03106939026078942
|
| 414 |
+
},
|
| 415 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 416 |
+
"acc": 0.29239766081871343,
|
| 417 |
+
"acc_stderr": 0.034886477134579215,
|
| 418 |
+
"acc_norm": 0.29239766081871343,
|
| 419 |
+
"acc_norm_stderr": 0.034886477134579215
|
| 420 |
+
},
|
| 421 |
+
"harness|truthfulqa:mc|0": {
|
| 422 |
+
"mc1": 0.2521419828641371,
|
| 423 |
+
"mc1_stderr": 0.015201522246299965,
|
| 424 |
+
"mc2": 0.41257163824244014,
|
| 425 |
+
"mc2_stderr": 0.015127188811834062
|
| 426 |
+
},
|
| 427 |
+
"harness|winogrande|5": {
|
| 428 |
+
"acc": 0.4996053670086819,
|
| 429 |
+
"acc_stderr": 0.014052481306049512
|
| 430 |
+
},
|
| 431 |
+
"harness|gsm8k|5": {
|
| 432 |
+
"acc": 0.0,
|
| 433 |
+
"acc_stderr": 0.0
|
| 434 |
+
}
|
| 435 |
+
}
|
| 436 |
+
|
| 437 |
```
|