Update README.md
Browse files
README.md
CHANGED
|
@@ -32,4 +32,391 @@ Output:
|
|
| 32 |
Who was the was the second president of the United States?
|
| 33 |
|
| 34 |
Output:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
```
|
|
|
|
| 32 |
Who was the was the second president of the United States?
|
| 33 |
|
| 34 |
Output:
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## Latest results
|
| 38 |
+
|
| 39 |
+
These are the [latest results from run 2024-01-04T13:27:32.660899](https://huggingface.co/datasets/open-llm-leaderboard/details_HenryJJ__Instruct_Mistral-7B-v0.1_Dolly15K/blob/main/results_2024-01-04T13-27-32.660899.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
|
| 40 |
+
|
| 41 |
+
```python
|
| 42 |
+
{
|
| 43 |
+
"all": {
|
| 44 |
+
"acc": 0.6241143484289186,
|
| 45 |
+
"acc_stderr": 0.032689663124831826,
|
| 46 |
+
"acc_norm": 0.6299031400315822,
|
| 47 |
+
"acc_norm_stderr": 0.033361474961048916,
|
| 48 |
+
"mc1": 0.2802937576499388,
|
| 49 |
+
"mc1_stderr": 0.015723139524608767,
|
| 50 |
+
"mc2": 0.435601924823795,
|
| 51 |
+
"mc2_stderr": 0.014179199089974604
|
| 52 |
+
},
|
| 53 |
+
"harness|arc:challenge|25": {
|
| 54 |
+
"acc": 0.5571672354948806,
|
| 55 |
+
"acc_stderr": 0.014515573873348906,
|
| 56 |
+
"acc_norm": 0.5938566552901023,
|
| 57 |
+
"acc_norm_stderr": 0.014351656690097862
|
| 58 |
+
},
|
| 59 |
+
"harness|hellaswag|10": {
|
| 60 |
+
"acc": 0.6253734315873332,
|
| 61 |
+
"acc_stderr": 0.004830371317841054,
|
| 62 |
+
"acc_norm": 0.826229834694284,
|
| 63 |
+
"acc_norm_stderr": 0.00378137335887
|
| 64 |
+
},
|
| 65 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 66 |
+
"acc": 0.31,
|
| 67 |
+
"acc_stderr": 0.04648231987117316,
|
| 68 |
+
"acc_norm": 0.31,
|
| 69 |
+
"acc_norm_stderr": 0.04648231987117316
|
| 70 |
+
},
|
| 71 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 72 |
+
"acc": 0.6148148148148148,
|
| 73 |
+
"acc_stderr": 0.04203921040156279,
|
| 74 |
+
"acc_norm": 0.6148148148148148,
|
| 75 |
+
"acc_norm_stderr": 0.04203921040156279
|
| 76 |
+
},
|
| 77 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 78 |
+
"acc": 0.6513157894736842,
|
| 79 |
+
"acc_stderr": 0.03878139888797611,
|
| 80 |
+
"acc_norm": 0.6513157894736842,
|
| 81 |
+
"acc_norm_stderr": 0.03878139888797611
|
| 82 |
+
},
|
| 83 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 84 |
+
"acc": 0.57,
|
| 85 |
+
"acc_stderr": 0.04975698519562428,
|
| 86 |
+
"acc_norm": 0.57,
|
| 87 |
+
"acc_norm_stderr": 0.04975698519562428
|
| 88 |
+
},
|
| 89 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 90 |
+
"acc": 0.660377358490566,
|
| 91 |
+
"acc_stderr": 0.029146904747798328,
|
| 92 |
+
"acc_norm": 0.660377358490566,
|
| 93 |
+
"acc_norm_stderr": 0.029146904747798328
|
| 94 |
+
},
|
| 95 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 96 |
+
"acc": 0.7291666666666666,
|
| 97 |
+
"acc_stderr": 0.03716177437566017,
|
| 98 |
+
"acc_norm": 0.7291666666666666,
|
| 99 |
+
"acc_norm_stderr": 0.03716177437566017
|
| 100 |
+
},
|
| 101 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 102 |
+
"acc": 0.46,
|
| 103 |
+
"acc_stderr": 0.05009082659620332,
|
| 104 |
+
"acc_norm": 0.46,
|
| 105 |
+
"acc_norm_stderr": 0.05009082659620332
|
| 106 |
+
},
|
| 107 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 108 |
+
"acc": 0.54,
|
| 109 |
+
"acc_stderr": 0.05009082659620333,
|
| 110 |
+
"acc_norm": 0.54,
|
| 111 |
+
"acc_norm_stderr": 0.05009082659620333
|
| 112 |
+
},
|
| 113 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 114 |
+
"acc": 0.38,
|
| 115 |
+
"acc_stderr": 0.04878317312145632,
|
| 116 |
+
"acc_norm": 0.38,
|
| 117 |
+
"acc_norm_stderr": 0.04878317312145632
|
| 118 |
+
},
|
| 119 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 120 |
+
"acc": 0.5838150289017341,
|
| 121 |
+
"acc_stderr": 0.03758517775404947,
|
| 122 |
+
"acc_norm": 0.5838150289017341,
|
| 123 |
+
"acc_norm_stderr": 0.03758517775404947
|
| 124 |
+
},
|
| 125 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 126 |
+
"acc": 0.35294117647058826,
|
| 127 |
+
"acc_stderr": 0.04755129616062946,
|
| 128 |
+
"acc_norm": 0.35294117647058826,
|
| 129 |
+
"acc_norm_stderr": 0.04755129616062946
|
| 130 |
+
},
|
| 131 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 132 |
+
"acc": 0.77,
|
| 133 |
+
"acc_stderr": 0.04229525846816505,
|
| 134 |
+
"acc_norm": 0.77,
|
| 135 |
+
"acc_norm_stderr": 0.04229525846816505
|
| 136 |
+
},
|
| 137 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 138 |
+
"acc": 0.5574468085106383,
|
| 139 |
+
"acc_stderr": 0.032469569197899575,
|
| 140 |
+
"acc_norm": 0.5574468085106383,
|
| 141 |
+
"acc_norm_stderr": 0.032469569197899575
|
| 142 |
+
},
|
| 143 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 144 |
+
"acc": 0.5,
|
| 145 |
+
"acc_stderr": 0.047036043419179864,
|
| 146 |
+
"acc_norm": 0.5,
|
| 147 |
+
"acc_norm_stderr": 0.047036043419179864
|
| 148 |
+
},
|
| 149 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 150 |
+
"acc": 0.5724137931034483,
|
| 151 |
+
"acc_stderr": 0.041227371113703316,
|
| 152 |
+
"acc_norm": 0.5724137931034483,
|
| 153 |
+
"acc_norm_stderr": 0.041227371113703316
|
| 154 |
+
},
|
| 155 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 156 |
+
"acc": 0.3994708994708995,
|
| 157 |
+
"acc_stderr": 0.02522545028406788,
|
| 158 |
+
"acc_norm": 0.3994708994708995,
|
| 159 |
+
"acc_norm_stderr": 0.02522545028406788
|
| 160 |
+
},
|
| 161 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 162 |
+
"acc": 0.3968253968253968,
|
| 163 |
+
"acc_stderr": 0.04375888492727061,
|
| 164 |
+
"acc_norm": 0.3968253968253968,
|
| 165 |
+
"acc_norm_stderr": 0.04375888492727061
|
| 166 |
+
},
|
| 167 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 168 |
+
"acc": 0.35,
|
| 169 |
+
"acc_stderr": 0.0479372485441102,
|
| 170 |
+
"acc_norm": 0.35,
|
| 171 |
+
"acc_norm_stderr": 0.0479372485441102
|
| 172 |
+
},
|
| 173 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 174 |
+
"acc": 0.7483870967741936,
|
| 175 |
+
"acc_stderr": 0.024685979286239956,
|
| 176 |
+
"acc_norm": 0.7483870967741936,
|
| 177 |
+
"acc_norm_stderr": 0.024685979286239956
|
| 178 |
+
},
|
| 179 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 180 |
+
"acc": 0.5221674876847291,
|
| 181 |
+
"acc_stderr": 0.03514528562175008,
|
| 182 |
+
"acc_norm": 0.5221674876847291,
|
| 183 |
+
"acc_norm_stderr": 0.03514528562175008
|
| 184 |
+
},
|
| 185 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 186 |
+
"acc": 0.67,
|
| 187 |
+
"acc_stderr": 0.04725815626252607,
|
| 188 |
+
"acc_norm": 0.67,
|
| 189 |
+
"acc_norm_stderr": 0.04725815626252607
|
| 190 |
+
},
|
| 191 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 192 |
+
"acc": 0.7636363636363637,
|
| 193 |
+
"acc_stderr": 0.03317505930009182,
|
| 194 |
+
"acc_norm": 0.7636363636363637,
|
| 195 |
+
"acc_norm_stderr": 0.03317505930009182
|
| 196 |
+
},
|
| 197 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 198 |
+
"acc": 0.7525252525252525,
|
| 199 |
+
"acc_stderr": 0.030746300742124498,
|
| 200 |
+
"acc_norm": 0.7525252525252525,
|
| 201 |
+
"acc_norm_stderr": 0.030746300742124498
|
| 202 |
+
},
|
| 203 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 204 |
+
"acc": 0.844559585492228,
|
| 205 |
+
"acc_stderr": 0.026148483469153314,
|
| 206 |
+
"acc_norm": 0.844559585492228,
|
| 207 |
+
"acc_norm_stderr": 0.026148483469153314
|
| 208 |
+
},
|
| 209 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 210 |
+
"acc": 0.6205128205128205,
|
| 211 |
+
"acc_stderr": 0.024603626924097417,
|
| 212 |
+
"acc_norm": 0.6205128205128205,
|
| 213 |
+
"acc_norm_stderr": 0.024603626924097417
|
| 214 |
+
},
|
| 215 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 216 |
+
"acc": 0.337037037037037,
|
| 217 |
+
"acc_stderr": 0.028820884666253252,
|
| 218 |
+
"acc_norm": 0.337037037037037,
|
| 219 |
+
"acc_norm_stderr": 0.028820884666253252
|
| 220 |
+
},
|
| 221 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 222 |
+
"acc": 0.6260504201680672,
|
| 223 |
+
"acc_stderr": 0.031429466378837076,
|
| 224 |
+
"acc_norm": 0.6260504201680672,
|
| 225 |
+
"acc_norm_stderr": 0.031429466378837076
|
| 226 |
+
},
|
| 227 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 228 |
+
"acc": 0.33774834437086093,
|
| 229 |
+
"acc_stderr": 0.03861557546255169,
|
| 230 |
+
"acc_norm": 0.33774834437086093,
|
| 231 |
+
"acc_norm_stderr": 0.03861557546255169
|
| 232 |
+
},
|
| 233 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 234 |
+
"acc": 0.7944954128440367,
|
| 235 |
+
"acc_stderr": 0.01732435232501601,
|
| 236 |
+
"acc_norm": 0.7944954128440367,
|
| 237 |
+
"acc_norm_stderr": 0.01732435232501601
|
| 238 |
+
},
|
| 239 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 240 |
+
"acc": 0.5046296296296297,
|
| 241 |
+
"acc_stderr": 0.03409825519163572,
|
| 242 |
+
"acc_norm": 0.5046296296296297,
|
| 243 |
+
"acc_norm_stderr": 0.03409825519163572
|
| 244 |
+
},
|
| 245 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 246 |
+
"acc": 0.8137254901960784,
|
| 247 |
+
"acc_stderr": 0.027325470966716312,
|
| 248 |
+
"acc_norm": 0.8137254901960784,
|
| 249 |
+
"acc_norm_stderr": 0.027325470966716312
|
| 250 |
+
},
|
| 251 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 252 |
+
"acc": 0.7763713080168776,
|
| 253 |
+
"acc_stderr": 0.027123298205229966,
|
| 254 |
+
"acc_norm": 0.7763713080168776,
|
| 255 |
+
"acc_norm_stderr": 0.027123298205229966
|
| 256 |
+
},
|
| 257 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 258 |
+
"acc": 0.6860986547085202,
|
| 259 |
+
"acc_stderr": 0.031146796482972465,
|
| 260 |
+
"acc_norm": 0.6860986547085202,
|
| 261 |
+
"acc_norm_stderr": 0.031146796482972465
|
| 262 |
+
},
|
| 263 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 264 |
+
"acc": 0.7557251908396947,
|
| 265 |
+
"acc_stderr": 0.037683359597287434,
|
| 266 |
+
"acc_norm": 0.7557251908396947,
|
| 267 |
+
"acc_norm_stderr": 0.037683359597287434
|
| 268 |
+
},
|
| 269 |
+
"harness|hendrycksTest-international_law|5": {
|
| 270 |
+
"acc": 0.7851239669421488,
|
| 271 |
+
"acc_stderr": 0.037494924487096966,
|
| 272 |
+
"acc_norm": 0.7851239669421488,
|
| 273 |
+
"acc_norm_stderr": 0.037494924487096966
|
| 274 |
+
},
|
| 275 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 276 |
+
"acc": 0.75,
|
| 277 |
+
"acc_stderr": 0.04186091791394607,
|
| 278 |
+
"acc_norm": 0.75,
|
| 279 |
+
"acc_norm_stderr": 0.04186091791394607
|
| 280 |
+
},
|
| 281 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 282 |
+
"acc": 0.7791411042944786,
|
| 283 |
+
"acc_stderr": 0.03259177392742178,
|
| 284 |
+
"acc_norm": 0.7791411042944786,
|
| 285 |
+
"acc_norm_stderr": 0.03259177392742178
|
| 286 |
+
},
|
| 287 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 288 |
+
"acc": 0.41964285714285715,
|
| 289 |
+
"acc_stderr": 0.04684099321077106,
|
| 290 |
+
"acc_norm": 0.41964285714285715,
|
| 291 |
+
"acc_norm_stderr": 0.04684099321077106
|
| 292 |
+
},
|
| 293 |
+
"harness|hendrycksTest-management|5": {
|
| 294 |
+
"acc": 0.7961165048543689,
|
| 295 |
+
"acc_stderr": 0.039891398595317706,
|
| 296 |
+
"acc_norm": 0.7961165048543689,
|
| 297 |
+
"acc_norm_stderr": 0.039891398595317706
|
| 298 |
+
},
|
| 299 |
+
"harness|hendrycksTest-marketing|5": {
|
| 300 |
+
"acc": 0.8589743589743589,
|
| 301 |
+
"acc_stderr": 0.022801382534597528,
|
| 302 |
+
"acc_norm": 0.8589743589743589,
|
| 303 |
+
"acc_norm_stderr": 0.022801382534597528
|
| 304 |
+
},
|
| 305 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 306 |
+
"acc": 0.73,
|
| 307 |
+
"acc_stderr": 0.044619604333847394,
|
| 308 |
+
"acc_norm": 0.73,
|
| 309 |
+
"acc_norm_stderr": 0.044619604333847394
|
| 310 |
+
},
|
| 311 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 312 |
+
"acc": 0.8135376756066411,
|
| 313 |
+
"acc_stderr": 0.013927751372001501,
|
| 314 |
+
"acc_norm": 0.8135376756066411,
|
| 315 |
+
"acc_norm_stderr": 0.013927751372001501
|
| 316 |
+
},
|
| 317 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 318 |
+
"acc": 0.6994219653179191,
|
| 319 |
+
"acc_stderr": 0.0246853168672578,
|
| 320 |
+
"acc_norm": 0.6994219653179191,
|
| 321 |
+
"acc_norm_stderr": 0.0246853168672578
|
| 322 |
+
},
|
| 323 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 324 |
+
"acc": 0.4033519553072626,
|
| 325 |
+
"acc_stderr": 0.01640712303219525,
|
| 326 |
+
"acc_norm": 0.4033519553072626,
|
| 327 |
+
"acc_norm_stderr": 0.01640712303219525
|
| 328 |
+
},
|
| 329 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 330 |
+
"acc": 0.7320261437908496,
|
| 331 |
+
"acc_stderr": 0.02536060379624255,
|
| 332 |
+
"acc_norm": 0.7320261437908496,
|
| 333 |
+
"acc_norm_stderr": 0.02536060379624255
|
| 334 |
+
},
|
| 335 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 336 |
+
"acc": 0.7009646302250804,
|
| 337 |
+
"acc_stderr": 0.02600330111788514,
|
| 338 |
+
"acc_norm": 0.7009646302250804,
|
| 339 |
+
"acc_norm_stderr": 0.02600330111788514
|
| 340 |
+
},
|
| 341 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 342 |
+
"acc": 0.7067901234567902,
|
| 343 |
+
"acc_stderr": 0.025329888171900926,
|
| 344 |
+
"acc_norm": 0.7067901234567902,
|
| 345 |
+
"acc_norm_stderr": 0.025329888171900926
|
| 346 |
+
},
|
| 347 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 348 |
+
"acc": 0.49645390070921985,
|
| 349 |
+
"acc_stderr": 0.02982674915328092,
|
| 350 |
+
"acc_norm": 0.49645390070921985,
|
| 351 |
+
"acc_norm_stderr": 0.02982674915328092
|
| 352 |
+
},
|
| 353 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 354 |
+
"acc": 0.44784876140808344,
|
| 355 |
+
"acc_stderr": 0.01270058240476822,
|
| 356 |
+
"acc_norm": 0.44784876140808344,
|
| 357 |
+
"acc_norm_stderr": 0.01270058240476822
|
| 358 |
+
},
|
| 359 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 360 |
+
"acc": 0.6397058823529411,
|
| 361 |
+
"acc_stderr": 0.029163128570670733,
|
| 362 |
+
"acc_norm": 0.6397058823529411,
|
| 363 |
+
"acc_norm_stderr": 0.029163128570670733
|
| 364 |
+
},
|
| 365 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 366 |
+
"acc": 0.6666666666666666,
|
| 367 |
+
"acc_stderr": 0.019070985589687495,
|
| 368 |
+
"acc_norm": 0.6666666666666666,
|
| 369 |
+
"acc_norm_stderr": 0.019070985589687495
|
| 370 |
+
},
|
| 371 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 372 |
+
"acc": 0.6727272727272727,
|
| 373 |
+
"acc_stderr": 0.0449429086625209,
|
| 374 |
+
"acc_norm": 0.6727272727272727,
|
| 375 |
+
"acc_norm_stderr": 0.0449429086625209
|
| 376 |
+
},
|
| 377 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 378 |
+
"acc": 0.7020408163265306,
|
| 379 |
+
"acc_stderr": 0.029279567411065677,
|
| 380 |
+
"acc_norm": 0.7020408163265306,
|
| 381 |
+
"acc_norm_stderr": 0.029279567411065677
|
| 382 |
+
},
|
| 383 |
+
"harness|hendrycksTest-sociology|5": {
|
| 384 |
+
"acc": 0.7960199004975125,
|
| 385 |
+
"acc_stderr": 0.02849317624532607,
|
| 386 |
+
"acc_norm": 0.7960199004975125,
|
| 387 |
+
"acc_norm_stderr": 0.02849317624532607
|
| 388 |
+
},
|
| 389 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 390 |
+
"acc": 0.84,
|
| 391 |
+
"acc_stderr": 0.03684529491774709,
|
| 392 |
+
"acc_norm": 0.84,
|
| 393 |
+
"acc_norm_stderr": 0.03684529491774709
|
| 394 |
+
},
|
| 395 |
+
"harness|hendrycksTest-virology|5": {
|
| 396 |
+
"acc": 0.5542168674698795,
|
| 397 |
+
"acc_stderr": 0.03869543323472101,
|
| 398 |
+
"acc_norm": 0.5542168674698795,
|
| 399 |
+
"acc_norm_stderr": 0.03869543323472101
|
| 400 |
+
},
|
| 401 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 402 |
+
"acc": 0.8011695906432749,
|
| 403 |
+
"acc_stderr": 0.03061111655743253,
|
| 404 |
+
"acc_norm": 0.8011695906432749,
|
| 405 |
+
"acc_norm_stderr": 0.03061111655743253
|
| 406 |
+
},
|
| 407 |
+
"harness|truthfulqa:mc|0": {
|
| 408 |
+
"mc1": 0.2802937576499388,
|
| 409 |
+
"mc1_stderr": 0.015723139524608767,
|
| 410 |
+
"mc2": 0.435601924823795,
|
| 411 |
+
"mc2_stderr": 0.014179199089974604
|
| 412 |
+
},
|
| 413 |
+
"harness|winogrande|5": {
|
| 414 |
+
"acc": 0.7932123125493291,
|
| 415 |
+
"acc_stderr": 0.011382566829235805
|
| 416 |
+
},
|
| 417 |
+
"harness|gsm8k|5": {
|
| 418 |
+
"acc": 0.3510235026535254,
|
| 419 |
+
"acc_stderr": 0.01314694594139722
|
| 420 |
+
}
|
| 421 |
+
}
|
| 422 |
```
|