attach result
Browse files
README.md
CHANGED
|
@@ -43,4 +43,391 @@ parameters:
|
|
| 43 |
int8_mask: true
|
| 44 |
dtype: bfloat16
|
| 45 |
|
| 46 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
int8_mask: true
|
| 44 |
dtype: bfloat16
|
| 45 |
|
| 46 |
+
```
|
| 47 |
+
## Evaluation
|
| 48 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-dare_6x7
|
| 49 |
+
|
| 50 |
+
## Result
|
| 51 |
+
```
|
| 52 |
+
{
|
| 53 |
+
"all": {
|
| 54 |
+
"acc": 0.6563139414530638,
|
| 55 |
+
"acc_stderr": 0.031967569574421976,
|
| 56 |
+
"acc_norm": 0.6562534942043537,
|
| 57 |
+
"acc_norm_stderr": 0.03262528877791407,
|
| 58 |
+
"mc1": 0.5067319461444308,
|
| 59 |
+
"mc1_stderr": 0.017501914492655396,
|
| 60 |
+
"mc2": 0.6698288226697681,
|
| 61 |
+
"mc2_stderr": 0.015121056875692264
|
| 62 |
+
},
|
| 63 |
+
"harness|arc:challenge|25": {
|
| 64 |
+
"acc": 0.6689419795221843,
|
| 65 |
+
"acc_stderr": 0.013752062419817837,
|
| 66 |
+
"acc_norm": 0.6962457337883959,
|
| 67 |
+
"acc_norm_stderr": 0.013438909184778768
|
| 68 |
+
},
|
| 69 |
+
"harness|hellaswag|10": {
|
| 70 |
+
"acc": 0.6946823341963753,
|
| 71 |
+
"acc_stderr": 0.004596006250433551,
|
| 72 |
+
"acc_norm": 0.870444134634535,
|
| 73 |
+
"acc_norm_stderr": 0.003351278403392407
|
| 74 |
+
},
|
| 75 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 76 |
+
"acc": 0.32,
|
| 77 |
+
"acc_stderr": 0.046882617226215034,
|
| 78 |
+
"acc_norm": 0.32,
|
| 79 |
+
"acc_norm_stderr": 0.046882617226215034
|
| 80 |
+
},
|
| 81 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 82 |
+
"acc": 0.6370370370370371,
|
| 83 |
+
"acc_stderr": 0.041539484047423976,
|
| 84 |
+
"acc_norm": 0.6370370370370371,
|
| 85 |
+
"acc_norm_stderr": 0.041539484047423976
|
| 86 |
+
},
|
| 87 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 88 |
+
"acc": 0.6907894736842105,
|
| 89 |
+
"acc_stderr": 0.037610708698674805,
|
| 90 |
+
"acc_norm": 0.6907894736842105,
|
| 91 |
+
"acc_norm_stderr": 0.037610708698674805
|
| 92 |
+
},
|
| 93 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 94 |
+
"acc": 0.64,
|
| 95 |
+
"acc_stderr": 0.04824181513244218,
|
| 96 |
+
"acc_norm": 0.64,
|
| 97 |
+
"acc_norm_stderr": 0.04824181513244218
|
| 98 |
+
},
|
| 99 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 100 |
+
"acc": 0.7018867924528301,
|
| 101 |
+
"acc_stderr": 0.028152837942493864,
|
| 102 |
+
"acc_norm": 0.7018867924528301,
|
| 103 |
+
"acc_norm_stderr": 0.028152837942493864
|
| 104 |
+
},
|
| 105 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 106 |
+
"acc": 0.7638888888888888,
|
| 107 |
+
"acc_stderr": 0.03551446610810826,
|
| 108 |
+
"acc_norm": 0.7638888888888888,
|
| 109 |
+
"acc_norm_stderr": 0.03551446610810826
|
| 110 |
+
},
|
| 111 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 112 |
+
"acc": 0.47,
|
| 113 |
+
"acc_stderr": 0.050161355804659205,
|
| 114 |
+
"acc_norm": 0.47,
|
| 115 |
+
"acc_norm_stderr": 0.050161355804659205
|
| 116 |
+
},
|
| 117 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 118 |
+
"acc": 0.54,
|
| 119 |
+
"acc_stderr": 0.05009082659620333,
|
| 120 |
+
"acc_norm": 0.54,
|
| 121 |
+
"acc_norm_stderr": 0.05009082659620333
|
| 122 |
+
},
|
| 123 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 124 |
+
"acc": 0.32,
|
| 125 |
+
"acc_stderr": 0.04688261722621504,
|
| 126 |
+
"acc_norm": 0.32,
|
| 127 |
+
"acc_norm_stderr": 0.04688261722621504
|
| 128 |
+
},
|
| 129 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 130 |
+
"acc": 0.6589595375722543,
|
| 131 |
+
"acc_stderr": 0.036146654241808254,
|
| 132 |
+
"acc_norm": 0.6589595375722543,
|
| 133 |
+
"acc_norm_stderr": 0.036146654241808254
|
| 134 |
+
},
|
| 135 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 136 |
+
"acc": 0.4019607843137255,
|
| 137 |
+
"acc_stderr": 0.048786087144669955,
|
| 138 |
+
"acc_norm": 0.4019607843137255,
|
| 139 |
+
"acc_norm_stderr": 0.048786087144669955
|
| 140 |
+
},
|
| 141 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 142 |
+
"acc": 0.77,
|
| 143 |
+
"acc_stderr": 0.04229525846816507,
|
| 144 |
+
"acc_norm": 0.77,
|
| 145 |
+
"acc_norm_stderr": 0.04229525846816507
|
| 146 |
+
},
|
| 147 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 148 |
+
"acc": 0.5829787234042553,
|
| 149 |
+
"acc_stderr": 0.03223276266711712,
|
| 150 |
+
"acc_norm": 0.5829787234042553,
|
| 151 |
+
"acc_norm_stderr": 0.03223276266711712
|
| 152 |
+
},
|
| 153 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 154 |
+
"acc": 0.45614035087719296,
|
| 155 |
+
"acc_stderr": 0.046854730419077895,
|
| 156 |
+
"acc_norm": 0.45614035087719296,
|
| 157 |
+
"acc_norm_stderr": 0.046854730419077895
|
| 158 |
+
},
|
| 159 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 160 |
+
"acc": 0.5724137931034483,
|
| 161 |
+
"acc_stderr": 0.04122737111370333,
|
| 162 |
+
"acc_norm": 0.5724137931034483,
|
| 163 |
+
"acc_norm_stderr": 0.04122737111370333
|
| 164 |
+
},
|
| 165 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 166 |
+
"acc": 0.42063492063492064,
|
| 167 |
+
"acc_stderr": 0.025424835086924,
|
| 168 |
+
"acc_norm": 0.42063492063492064,
|
| 169 |
+
"acc_norm_stderr": 0.025424835086924
|
| 170 |
+
},
|
| 171 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 172 |
+
"acc": 0.49206349206349204,
|
| 173 |
+
"acc_stderr": 0.044715725362943486,
|
| 174 |
+
"acc_norm": 0.49206349206349204,
|
| 175 |
+
"acc_norm_stderr": 0.044715725362943486
|
| 176 |
+
},
|
| 177 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 178 |
+
"acc": 0.39,
|
| 179 |
+
"acc_stderr": 0.04902071300001974,
|
| 180 |
+
"acc_norm": 0.39,
|
| 181 |
+
"acc_norm_stderr": 0.04902071300001974
|
| 182 |
+
},
|
| 183 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 184 |
+
"acc": 0.7838709677419354,
|
| 185 |
+
"acc_stderr": 0.02341529343356853,
|
| 186 |
+
"acc_norm": 0.7838709677419354,
|
| 187 |
+
"acc_norm_stderr": 0.02341529343356853
|
| 188 |
+
},
|
| 189 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 190 |
+
"acc": 0.5024630541871922,
|
| 191 |
+
"acc_stderr": 0.03517945038691063,
|
| 192 |
+
"acc_norm": 0.5024630541871922,
|
| 193 |
+
"acc_norm_stderr": 0.03517945038691063
|
| 194 |
+
},
|
| 195 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 196 |
+
"acc": 0.72,
|
| 197 |
+
"acc_stderr": 0.04512608598542127,
|
| 198 |
+
"acc_norm": 0.72,
|
| 199 |
+
"acc_norm_stderr": 0.04512608598542127
|
| 200 |
+
},
|
| 201 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 202 |
+
"acc": 0.7696969696969697,
|
| 203 |
+
"acc_stderr": 0.0328766675860349,
|
| 204 |
+
"acc_norm": 0.7696969696969697,
|
| 205 |
+
"acc_norm_stderr": 0.0328766675860349
|
| 206 |
+
},
|
| 207 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 208 |
+
"acc": 0.7929292929292929,
|
| 209 |
+
"acc_stderr": 0.028869778460267042,
|
| 210 |
+
"acc_norm": 0.7929292929292929,
|
| 211 |
+
"acc_norm_stderr": 0.028869778460267042
|
| 212 |
+
},
|
| 213 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 214 |
+
"acc": 0.8963730569948186,
|
| 215 |
+
"acc_stderr": 0.02199531196364424,
|
| 216 |
+
"acc_norm": 0.8963730569948186,
|
| 217 |
+
"acc_norm_stderr": 0.02199531196364424
|
| 218 |
+
},
|
| 219 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 220 |
+
"acc": 0.6641025641025641,
|
| 221 |
+
"acc_stderr": 0.023946724741563976,
|
| 222 |
+
"acc_norm": 0.6641025641025641,
|
| 223 |
+
"acc_norm_stderr": 0.023946724741563976
|
| 224 |
+
},
|
| 225 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 226 |
+
"acc": 0.35185185185185186,
|
| 227 |
+
"acc_stderr": 0.02911661760608301,
|
| 228 |
+
"acc_norm": 0.35185185185185186,
|
| 229 |
+
"acc_norm_stderr": 0.02911661760608301
|
| 230 |
+
},
|
| 231 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 232 |
+
"acc": 0.7016806722689075,
|
| 233 |
+
"acc_stderr": 0.02971914287634286,
|
| 234 |
+
"acc_norm": 0.7016806722689075,
|
| 235 |
+
"acc_norm_stderr": 0.02971914287634286
|
| 236 |
+
},
|
| 237 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 238 |
+
"acc": 0.37748344370860926,
|
| 239 |
+
"acc_stderr": 0.03958027231121569,
|
| 240 |
+
"acc_norm": 0.37748344370860926,
|
| 241 |
+
"acc_norm_stderr": 0.03958027231121569
|
| 242 |
+
},
|
| 243 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 244 |
+
"acc": 0.8587155963302753,
|
| 245 |
+
"acc_stderr": 0.014933868987028075,
|
| 246 |
+
"acc_norm": 0.8587155963302753,
|
| 247 |
+
"acc_norm_stderr": 0.014933868987028075
|
| 248 |
+
},
|
| 249 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 250 |
+
"acc": 0.5324074074074074,
|
| 251 |
+
"acc_stderr": 0.03402801581358966,
|
| 252 |
+
"acc_norm": 0.5324074074074074,
|
| 253 |
+
"acc_norm_stderr": 0.03402801581358966
|
| 254 |
+
},
|
| 255 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 256 |
+
"acc": 0.8480392156862745,
|
| 257 |
+
"acc_stderr": 0.025195658428931792,
|
| 258 |
+
"acc_norm": 0.8480392156862745,
|
| 259 |
+
"acc_norm_stderr": 0.025195658428931792
|
| 260 |
+
},
|
| 261 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 262 |
+
"acc": 0.8016877637130801,
|
| 263 |
+
"acc_stderr": 0.02595502084162113,
|
| 264 |
+
"acc_norm": 0.8016877637130801,
|
| 265 |
+
"acc_norm_stderr": 0.02595502084162113
|
| 266 |
+
},
|
| 267 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 268 |
+
"acc": 0.6905829596412556,
|
| 269 |
+
"acc_stderr": 0.03102441174057221,
|
| 270 |
+
"acc_norm": 0.6905829596412556,
|
| 271 |
+
"acc_norm_stderr": 0.03102441174057221
|
| 272 |
+
},
|
| 273 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 274 |
+
"acc": 0.8091603053435115,
|
| 275 |
+
"acc_stderr": 0.03446513350752598,
|
| 276 |
+
"acc_norm": 0.8091603053435115,
|
| 277 |
+
"acc_norm_stderr": 0.03446513350752598
|
| 278 |
+
},
|
| 279 |
+
"harness|hendrycksTest-international_law|5": {
|
| 280 |
+
"acc": 0.7933884297520661,
|
| 281 |
+
"acc_stderr": 0.03695980128098824,
|
| 282 |
+
"acc_norm": 0.7933884297520661,
|
| 283 |
+
"acc_norm_stderr": 0.03695980128098824
|
| 284 |
+
},
|
| 285 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 286 |
+
"acc": 0.8055555555555556,
|
| 287 |
+
"acc_stderr": 0.038260763248848646,
|
| 288 |
+
"acc_norm": 0.8055555555555556,
|
| 289 |
+
"acc_norm_stderr": 0.038260763248848646
|
| 290 |
+
},
|
| 291 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 292 |
+
"acc": 0.7423312883435583,
|
| 293 |
+
"acc_stderr": 0.03436150827846917,
|
| 294 |
+
"acc_norm": 0.7423312883435583,
|
| 295 |
+
"acc_norm_stderr": 0.03436150827846917
|
| 296 |
+
},
|
| 297 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 298 |
+
"acc": 0.45535714285714285,
|
| 299 |
+
"acc_stderr": 0.047268355537191,
|
| 300 |
+
"acc_norm": 0.45535714285714285,
|
| 301 |
+
"acc_norm_stderr": 0.047268355537191
|
| 302 |
+
},
|
| 303 |
+
"harness|hendrycksTest-management|5": {
|
| 304 |
+
"acc": 0.8058252427184466,
|
| 305 |
+
"acc_stderr": 0.039166677628225836,
|
| 306 |
+
"acc_norm": 0.8058252427184466,
|
| 307 |
+
"acc_norm_stderr": 0.039166677628225836
|
| 308 |
+
},
|
| 309 |
+
"harness|hendrycksTest-marketing|5": {
|
| 310 |
+
"acc": 0.8717948717948718,
|
| 311 |
+
"acc_stderr": 0.021901905115073325,
|
| 312 |
+
"acc_norm": 0.8717948717948718,
|
| 313 |
+
"acc_norm_stderr": 0.021901905115073325
|
| 314 |
+
},
|
| 315 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 316 |
+
"acc": 0.76,
|
| 317 |
+
"acc_stderr": 0.042923469599092816,
|
| 318 |
+
"acc_norm": 0.76,
|
| 319 |
+
"acc_norm_stderr": 0.042923469599092816
|
| 320 |
+
},
|
| 321 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 322 |
+
"acc": 0.8326947637292464,
|
| 323 |
+
"acc_stderr": 0.013347327202920332,
|
| 324 |
+
"acc_norm": 0.8326947637292464,
|
| 325 |
+
"acc_norm_stderr": 0.013347327202920332
|
| 326 |
+
},
|
| 327 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 328 |
+
"acc": 0.7283236994219653,
|
| 329 |
+
"acc_stderr": 0.023948512905468365,
|
| 330 |
+
"acc_norm": 0.7283236994219653,
|
| 331 |
+
"acc_norm_stderr": 0.023948512905468365
|
| 332 |
+
},
|
| 333 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 334 |
+
"acc": 0.4770949720670391,
|
| 335 |
+
"acc_stderr": 0.016704945740326188,
|
| 336 |
+
"acc_norm": 0.4770949720670391,
|
| 337 |
+
"acc_norm_stderr": 0.016704945740326188
|
| 338 |
+
},
|
| 339 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 340 |
+
"acc": 0.7450980392156863,
|
| 341 |
+
"acc_stderr": 0.02495418432487991,
|
| 342 |
+
"acc_norm": 0.7450980392156863,
|
| 343 |
+
"acc_norm_stderr": 0.02495418432487991
|
| 344 |
+
},
|
| 345 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 346 |
+
"acc": 0.7106109324758842,
|
| 347 |
+
"acc_stderr": 0.025755865922632952,
|
| 348 |
+
"acc_norm": 0.7106109324758842,
|
| 349 |
+
"acc_norm_stderr": 0.025755865922632952
|
| 350 |
+
},
|
| 351 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 352 |
+
"acc": 0.75,
|
| 353 |
+
"acc_stderr": 0.02409347123262133,
|
| 354 |
+
"acc_norm": 0.75,
|
| 355 |
+
"acc_norm_stderr": 0.02409347123262133
|
| 356 |
+
},
|
| 357 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 358 |
+
"acc": 0.475177304964539,
|
| 359 |
+
"acc_stderr": 0.02979071924382972,
|
| 360 |
+
"acc_norm": 0.475177304964539,
|
| 361 |
+
"acc_norm_stderr": 0.02979071924382972
|
| 362 |
+
},
|
| 363 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 364 |
+
"acc": 0.46284224250325945,
|
| 365 |
+
"acc_stderr": 0.012734923579532069,
|
| 366 |
+
"acc_norm": 0.46284224250325945,
|
| 367 |
+
"acc_norm_stderr": 0.012734923579532069
|
| 368 |
+
},
|
| 369 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 370 |
+
"acc": 0.6985294117647058,
|
| 371 |
+
"acc_stderr": 0.027875982114273168,
|
| 372 |
+
"acc_norm": 0.6985294117647058,
|
| 373 |
+
"acc_norm_stderr": 0.027875982114273168
|
| 374 |
+
},
|
| 375 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 376 |
+
"acc": 0.6666666666666666,
|
| 377 |
+
"acc_stderr": 0.0190709855896875,
|
| 378 |
+
"acc_norm": 0.6666666666666666,
|
| 379 |
+
"acc_norm_stderr": 0.0190709855896875
|
| 380 |
+
},
|
| 381 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 382 |
+
"acc": 0.6545454545454545,
|
| 383 |
+
"acc_stderr": 0.04554619617541054,
|
| 384 |
+
"acc_norm": 0.6545454545454545,
|
| 385 |
+
"acc_norm_stderr": 0.04554619617541054
|
| 386 |
+
},
|
| 387 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 388 |
+
"acc": 0.726530612244898,
|
| 389 |
+
"acc_stderr": 0.02853556033712844,
|
| 390 |
+
"acc_norm": 0.726530612244898,
|
| 391 |
+
"acc_norm_stderr": 0.02853556033712844
|
| 392 |
+
},
|
| 393 |
+
"harness|hendrycksTest-sociology|5": {
|
| 394 |
+
"acc": 0.845771144278607,
|
| 395 |
+
"acc_stderr": 0.025538433368578337,
|
| 396 |
+
"acc_norm": 0.845771144278607,
|
| 397 |
+
"acc_norm_stderr": 0.025538433368578337
|
| 398 |
+
},
|
| 399 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 400 |
+
"acc": 0.86,
|
| 401 |
+
"acc_stderr": 0.0348735088019777,
|
| 402 |
+
"acc_norm": 0.86,
|
| 403 |
+
"acc_norm_stderr": 0.0348735088019777
|
| 404 |
+
},
|
| 405 |
+
"harness|hendrycksTest-virology|5": {
|
| 406 |
+
"acc": 0.5180722891566265,
|
| 407 |
+
"acc_stderr": 0.03889951252827216,
|
| 408 |
+
"acc_norm": 0.5180722891566265,
|
| 409 |
+
"acc_norm_stderr": 0.03889951252827216
|
| 410 |
+
},
|
| 411 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 412 |
+
"acc": 0.8362573099415205,
|
| 413 |
+
"acc_stderr": 0.028380919596145866,
|
| 414 |
+
"acc_norm": 0.8362573099415205,
|
| 415 |
+
"acc_norm_stderr": 0.028380919596145866
|
| 416 |
+
},
|
| 417 |
+
"harness|truthfulqa:mc|0": {
|
| 418 |
+
"mc1": 0.5067319461444308,
|
| 419 |
+
"mc1_stderr": 0.017501914492655396,
|
| 420 |
+
"mc2": 0.6698288226697681,
|
| 421 |
+
"mc2_stderr": 0.015121056875692264
|
| 422 |
+
},
|
| 423 |
+
"harness|winogrande|5": {
|
| 424 |
+
"acc": 0.8058405682715075,
|
| 425 |
+
"acc_stderr": 0.01111698339239267
|
| 426 |
+
},
|
| 427 |
+
"harness|gsm8k|5": {
|
| 428 |
+
"acc": 0.7134192570128886,
|
| 429 |
+
"acc_stderr": 0.0124548416683377
|
| 430 |
+
}
|
| 431 |
+
}
|
| 432 |
+
|
| 433 |
+
```
|