Update README.md
Browse filesadd evaluation result
README.md
CHANGED
|
@@ -38,4 +38,394 @@ parameters:
|
|
| 38 |
int8_mask: true
|
| 39 |
dtype: bfloat16
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
```
|
|
|
|
| 38 |
int8_mask: true
|
| 39 |
dtype: bfloat16
|
| 40 |
|
| 41 |
+
```
|
| 42 |
+
|
| 43 |
+
### Evaluation Details
|
| 44 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-dare
|
| 45 |
+
|
| 46 |
+
### Result:
|
| 47 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-dare/blob/main/results_2024-03-10T11-06-23.658904.json
|
| 48 |
+
|
| 49 |
+
```
|
| 50 |
+
{
|
| 51 |
+
"all": {
|
| 52 |
+
"acc": 0.6555984630611819,
|
| 53 |
+
"acc_stderr": 0.03202413494937558,
|
| 54 |
+
"acc_norm": 0.6552172318444804,
|
| 55 |
+
"acc_norm_stderr": 0.03269035140382117,
|
| 56 |
+
"mc1": 0.46878824969400246,
|
| 57 |
+
"mc1_stderr": 0.017469364874577537,
|
| 58 |
+
"mc2": 0.6324196158065736,
|
| 59 |
+
"mc2_stderr": 0.015183642172146008
|
| 60 |
+
},
|
| 61 |
+
"harness|arc:challenge|25": {
|
| 62 |
+
"acc": 0.6655290102389079,
|
| 63 |
+
"acc_stderr": 0.013787460322441374,
|
| 64 |
+
"acc_norm": 0.697098976109215,
|
| 65 |
+
"acc_norm_stderr": 0.013428241573185349
|
| 66 |
+
},
|
| 67 |
+
"harness|hellaswag|10": {
|
| 68 |
+
"acc": 0.6896036646086438,
|
| 69 |
+
"acc_stderr": 0.004617103280372031,
|
| 70 |
+
"acc_norm": 0.8705437163911571,
|
| 71 |
+
"acc_norm_stderr": 0.003350181812941611
|
| 72 |
+
},
|
| 73 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 74 |
+
"acc": 0.36,
|
| 75 |
+
"acc_stderr": 0.04824181513244218,
|
| 76 |
+
"acc_norm": 0.36,
|
| 77 |
+
"acc_norm_stderr": 0.04824181513244218
|
| 78 |
+
},
|
| 79 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 80 |
+
"acc": 0.6296296296296297,
|
| 81 |
+
"acc_stderr": 0.041716541613545426,
|
| 82 |
+
"acc_norm": 0.6296296296296297,
|
| 83 |
+
"acc_norm_stderr": 0.041716541613545426
|
| 84 |
+
},
|
| 85 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 86 |
+
"acc": 0.6842105263157895,
|
| 87 |
+
"acc_stderr": 0.0378272898086547,
|
| 88 |
+
"acc_norm": 0.6842105263157895,
|
| 89 |
+
"acc_norm_stderr": 0.0378272898086547
|
| 90 |
+
},
|
| 91 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 92 |
+
"acc": 0.64,
|
| 93 |
+
"acc_stderr": 0.04824181513244218,
|
| 94 |
+
"acc_norm": 0.64,
|
| 95 |
+
"acc_norm_stderr": 0.04824181513244218
|
| 96 |
+
},
|
| 97 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 98 |
+
"acc": 0.7245283018867924,
|
| 99 |
+
"acc_stderr": 0.027495663683724057,
|
| 100 |
+
"acc_norm": 0.7245283018867924,
|
| 101 |
+
"acc_norm_stderr": 0.027495663683724057
|
| 102 |
+
},
|
| 103 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 104 |
+
"acc": 0.7708333333333334,
|
| 105 |
+
"acc_stderr": 0.03514697467862388,
|
| 106 |
+
"acc_norm": 0.7708333333333334,
|
| 107 |
+
"acc_norm_stderr": 0.03514697467862388
|
| 108 |
+
},
|
| 109 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 110 |
+
"acc": 0.48,
|
| 111 |
+
"acc_stderr": 0.050211673156867795,
|
| 112 |
+
"acc_norm": 0.48,
|
| 113 |
+
"acc_norm_stderr": 0.050211673156867795
|
| 114 |
+
},
|
| 115 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 116 |
+
"acc": 0.55,
|
| 117 |
+
"acc_stderr": 0.05,
|
| 118 |
+
"acc_norm": 0.55,
|
| 119 |
+
"acc_norm_stderr": 0.05
|
| 120 |
+
},
|
| 121 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 122 |
+
"acc": 0.33,
|
| 123 |
+
"acc_stderr": 0.04725815626252604,
|
| 124 |
+
"acc_norm": 0.33,
|
| 125 |
+
"acc_norm_stderr": 0.04725815626252604
|
| 126 |
+
},
|
| 127 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 128 |
+
"acc": 0.653179190751445,
|
| 129 |
+
"acc_stderr": 0.036291466701596636,
|
| 130 |
+
"acc_norm": 0.653179190751445,
|
| 131 |
+
"acc_norm_stderr": 0.036291466701596636
|
| 132 |
+
},
|
| 133 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 134 |
+
"acc": 0.4411764705882353,
|
| 135 |
+
"acc_stderr": 0.049406356306056595,
|
| 136 |
+
"acc_norm": 0.4411764705882353,
|
| 137 |
+
"acc_norm_stderr": 0.049406356306056595
|
| 138 |
+
},
|
| 139 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 140 |
+
"acc": 0.76,
|
| 141 |
+
"acc_stderr": 0.04292346959909282,
|
| 142 |
+
"acc_norm": 0.76,
|
| 143 |
+
"acc_norm_stderr": 0.04292346959909282
|
| 144 |
+
},
|
| 145 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 146 |
+
"acc": 0.6,
|
| 147 |
+
"acc_stderr": 0.03202563076101735,
|
| 148 |
+
"acc_norm": 0.6,
|
| 149 |
+
"acc_norm_stderr": 0.03202563076101735
|
| 150 |
+
},
|
| 151 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 152 |
+
"acc": 0.47368421052631576,
|
| 153 |
+
"acc_stderr": 0.046970851366478626,
|
| 154 |
+
"acc_norm": 0.47368421052631576,
|
| 155 |
+
"acc_norm_stderr": 0.046970851366478626
|
| 156 |
+
},
|
| 157 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 158 |
+
"acc": 0.5655172413793104,
|
| 159 |
+
"acc_stderr": 0.04130740879555498,
|
| 160 |
+
"acc_norm": 0.5655172413793104,
|
| 161 |
+
"acc_norm_stderr": 0.04130740879555498
|
| 162 |
+
},
|
| 163 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 164 |
+
"acc": 0.42063492063492064,
|
| 165 |
+
"acc_stderr": 0.025424835086924,
|
| 166 |
+
"acc_norm": 0.42063492063492064,
|
| 167 |
+
"acc_norm_stderr": 0.025424835086924
|
| 168 |
+
},
|
| 169 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 170 |
+
"acc": 0.47619047619047616,
|
| 171 |
+
"acc_stderr": 0.04467062628403273,
|
| 172 |
+
"acc_norm": 0.47619047619047616,
|
| 173 |
+
"acc_norm_stderr": 0.04467062628403273
|
| 174 |
+
},
|
| 175 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 176 |
+
"acc": 0.36,
|
| 177 |
+
"acc_stderr": 0.048241815132442176,
|
| 178 |
+
"acc_norm": 0.36,
|
| 179 |
+
"acc_norm_stderr": 0.048241815132442176
|
| 180 |
+
},
|
| 181 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 182 |
+
"acc": 0.7774193548387097,
|
| 183 |
+
"acc_stderr": 0.023664216671642518,
|
| 184 |
+
"acc_norm": 0.7774193548387097,
|
| 185 |
+
"acc_norm_stderr": 0.023664216671642518
|
| 186 |
+
},
|
| 187 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 188 |
+
"acc": 0.49261083743842365,
|
| 189 |
+
"acc_stderr": 0.035176035403610084,
|
| 190 |
+
"acc_norm": 0.49261083743842365,
|
| 191 |
+
"acc_norm_stderr": 0.035176035403610084
|
| 192 |
+
},
|
| 193 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 194 |
+
"acc": 0.72,
|
| 195 |
+
"acc_stderr": 0.04512608598542127,
|
| 196 |
+
"acc_norm": 0.72,
|
| 197 |
+
"acc_norm_stderr": 0.04512608598542127
|
| 198 |
+
},
|
| 199 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 200 |
+
"acc": 0.7757575757575758,
|
| 201 |
+
"acc_stderr": 0.03256866661681102,
|
| 202 |
+
"acc_norm": 0.7757575757575758,
|
| 203 |
+
"acc_norm_stderr": 0.03256866661681102
|
| 204 |
+
},
|
| 205 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 206 |
+
"acc": 0.7878787878787878,
|
| 207 |
+
"acc_stderr": 0.02912652283458682,
|
| 208 |
+
"acc_norm": 0.7878787878787878,
|
| 209 |
+
"acc_norm_stderr": 0.02912652283458682
|
| 210 |
+
},
|
| 211 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 212 |
+
"acc": 0.9067357512953368,
|
| 213 |
+
"acc_stderr": 0.020986854593289733,
|
| 214 |
+
"acc_norm": 0.9067357512953368,
|
| 215 |
+
"acc_norm_stderr": 0.020986854593289733
|
| 216 |
+
},
|
| 217 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 218 |
+
"acc": 0.6743589743589744,
|
| 219 |
+
"acc_stderr": 0.02375966576741229,
|
| 220 |
+
"acc_norm": 0.6743589743589744,
|
| 221 |
+
"acc_norm_stderr": 0.02375966576741229
|
| 222 |
+
},
|
| 223 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 224 |
+
"acc": 0.32222222222222224,
|
| 225 |
+
"acc_stderr": 0.028493465091028593,
|
| 226 |
+
"acc_norm": 0.32222222222222224,
|
| 227 |
+
"acc_norm_stderr": 0.028493465091028593
|
| 228 |
+
},
|
| 229 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 230 |
+
"acc": 0.6848739495798319,
|
| 231 |
+
"acc_stderr": 0.030176808288974337,
|
| 232 |
+
"acc_norm": 0.6848739495798319,
|
| 233 |
+
"acc_norm_stderr": 0.030176808288974337
|
| 234 |
+
},
|
| 235 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 236 |
+
"acc": 0.3576158940397351,
|
| 237 |
+
"acc_stderr": 0.03913453431177258,
|
| 238 |
+
"acc_norm": 0.3576158940397351,
|
| 239 |
+
"acc_norm_stderr": 0.03913453431177258
|
| 240 |
+
},
|
| 241 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 242 |
+
"acc": 0.8477064220183487,
|
| 243 |
+
"acc_stderr": 0.015405084393157074,
|
| 244 |
+
"acc_norm": 0.8477064220183487,
|
| 245 |
+
"acc_norm_stderr": 0.015405084393157074
|
| 246 |
+
},
|
| 247 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 248 |
+
"acc": 0.5324074074074074,
|
| 249 |
+
"acc_stderr": 0.03402801581358966,
|
| 250 |
+
"acc_norm": 0.5324074074074074,
|
| 251 |
+
"acc_norm_stderr": 0.03402801581358966
|
| 252 |
+
},
|
| 253 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 254 |
+
"acc": 0.8529411764705882,
|
| 255 |
+
"acc_stderr": 0.024857478080250454,
|
| 256 |
+
"acc_norm": 0.8529411764705882,
|
| 257 |
+
"acc_norm_stderr": 0.024857478080250454
|
| 258 |
+
},
|
| 259 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 260 |
+
"acc": 0.8059071729957806,
|
| 261 |
+
"acc_stderr": 0.025744902532290916,
|
| 262 |
+
"acc_norm": 0.8059071729957806,
|
| 263 |
+
"acc_norm_stderr": 0.025744902532290916
|
| 264 |
+
},
|
| 265 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 266 |
+
"acc": 0.6860986547085202,
|
| 267 |
+
"acc_stderr": 0.031146796482972465,
|
| 268 |
+
"acc_norm": 0.6860986547085202,
|
| 269 |
+
"acc_norm_stderr": 0.031146796482972465
|
| 270 |
+
},
|
| 271 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 272 |
+
"acc": 0.8091603053435115,
|
| 273 |
+
"acc_stderr": 0.03446513350752599,
|
| 274 |
+
"acc_norm": 0.8091603053435115,
|
| 275 |
+
"acc_norm_stderr": 0.03446513350752599
|
| 276 |
+
},
|
| 277 |
+
"harness|hendrycksTest-international_law|5": {
|
| 278 |
+
"acc": 0.7851239669421488,
|
| 279 |
+
"acc_stderr": 0.037494924487096966,
|
| 280 |
+
"acc_norm": 0.7851239669421488,
|
| 281 |
+
"acc_norm_stderr": 0.037494924487096966
|
| 282 |
+
},
|
| 283 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 284 |
+
"acc": 0.7870370370370371,
|
| 285 |
+
"acc_stderr": 0.039578354719809805,
|
| 286 |
+
"acc_norm": 0.7870370370370371,
|
| 287 |
+
"acc_norm_stderr": 0.039578354719809805
|
| 288 |
+
},
|
| 289 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 290 |
+
"acc": 0.7730061349693251,
|
| 291 |
+
"acc_stderr": 0.03291099578615769,
|
| 292 |
+
"acc_norm": 0.7730061349693251,
|
| 293 |
+
"acc_norm_stderr": 0.03291099578615769
|
| 294 |
+
},
|
| 295 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 296 |
+
"acc": 0.42857142857142855,
|
| 297 |
+
"acc_stderr": 0.04697113923010212,
|
| 298 |
+
"acc_norm": 0.42857142857142855,
|
| 299 |
+
"acc_norm_stderr": 0.04697113923010212
|
| 300 |
+
},
|
| 301 |
+
"harness|hendrycksTest-management|5": {
|
| 302 |
+
"acc": 0.7669902912621359,
|
| 303 |
+
"acc_stderr": 0.04185832598928315,
|
| 304 |
+
"acc_norm": 0.7669902912621359,
|
| 305 |
+
"acc_norm_stderr": 0.04185832598928315
|
| 306 |
+
},
|
| 307 |
+
"harness|hendrycksTest-marketing|5": {
|
| 308 |
+
"acc": 0.8803418803418803,
|
| 309 |
+
"acc_stderr": 0.021262719400406957,
|
| 310 |
+
"acc_norm": 0.8803418803418803,
|
| 311 |
+
"acc_norm_stderr": 0.021262719400406957
|
| 312 |
+
},
|
| 313 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 314 |
+
"acc": 0.71,
|
| 315 |
+
"acc_stderr": 0.045604802157206845,
|
| 316 |
+
"acc_norm": 0.71,
|
| 317 |
+
"acc_norm_stderr": 0.045604802157206845
|
| 318 |
+
},
|
| 319 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 320 |
+
"acc": 0.8352490421455939,
|
| 321 |
+
"acc_stderr": 0.01326534626132379,
|
| 322 |
+
"acc_norm": 0.8352490421455939,
|
| 323 |
+
"acc_norm_stderr": 0.01326534626132379
|
| 324 |
+
},
|
| 325 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 326 |
+
"acc": 0.7456647398843931,
|
| 327 |
+
"acc_stderr": 0.02344582627654554,
|
| 328 |
+
"acc_norm": 0.7456647398843931,
|
| 329 |
+
"acc_norm_stderr": 0.02344582627654554
|
| 330 |
+
},
|
| 331 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 332 |
+
"acc": 0.42569832402234636,
|
| 333 |
+
"acc_stderr": 0.016536829648997112,
|
| 334 |
+
"acc_norm": 0.42569832402234636,
|
| 335 |
+
"acc_norm_stderr": 0.016536829648997112
|
| 336 |
+
},
|
| 337 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 338 |
+
"acc": 0.738562091503268,
|
| 339 |
+
"acc_stderr": 0.025160998214292452,
|
| 340 |
+
"acc_norm": 0.738562091503268,
|
| 341 |
+
"acc_norm_stderr": 0.025160998214292452
|
| 342 |
+
},
|
| 343 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 344 |
+
"acc": 0.7138263665594855,
|
| 345 |
+
"acc_stderr": 0.02567025924218893,
|
| 346 |
+
"acc_norm": 0.7138263665594855,
|
| 347 |
+
"acc_norm_stderr": 0.02567025924218893
|
| 348 |
+
},
|
| 349 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 350 |
+
"acc": 0.7438271604938271,
|
| 351 |
+
"acc_stderr": 0.0242885336377261,
|
| 352 |
+
"acc_norm": 0.7438271604938271,
|
| 353 |
+
"acc_norm_stderr": 0.0242885336377261
|
| 354 |
+
},
|
| 355 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 356 |
+
"acc": 0.4929078014184397,
|
| 357 |
+
"acc_stderr": 0.02982449855912901,
|
| 358 |
+
"acc_norm": 0.4929078014184397,
|
| 359 |
+
"acc_norm_stderr": 0.02982449855912901
|
| 360 |
+
},
|
| 361 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 362 |
+
"acc": 0.46740547588005216,
|
| 363 |
+
"acc_stderr": 0.012743072942653342,
|
| 364 |
+
"acc_norm": 0.46740547588005216,
|
| 365 |
+
"acc_norm_stderr": 0.012743072942653342
|
| 366 |
+
},
|
| 367 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 368 |
+
"acc": 0.6727941176470589,
|
| 369 |
+
"acc_stderr": 0.028501452860396553,
|
| 370 |
+
"acc_norm": 0.6727941176470589,
|
| 371 |
+
"acc_norm_stderr": 0.028501452860396553
|
| 372 |
+
},
|
| 373 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 374 |
+
"acc": 0.6764705882352942,
|
| 375 |
+
"acc_stderr": 0.018926082916083383,
|
| 376 |
+
"acc_norm": 0.6764705882352942,
|
| 377 |
+
"acc_norm_stderr": 0.018926082916083383
|
| 378 |
+
},
|
| 379 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 380 |
+
"acc": 0.6818181818181818,
|
| 381 |
+
"acc_stderr": 0.044612721759105085,
|
| 382 |
+
"acc_norm": 0.6818181818181818,
|
| 383 |
+
"acc_norm_stderr": 0.044612721759105085
|
| 384 |
+
},
|
| 385 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 386 |
+
"acc": 0.726530612244898,
|
| 387 |
+
"acc_stderr": 0.02853556033712844,
|
| 388 |
+
"acc_norm": 0.726530612244898,
|
| 389 |
+
"acc_norm_stderr": 0.02853556033712844
|
| 390 |
+
},
|
| 391 |
+
"harness|hendrycksTest-sociology|5": {
|
| 392 |
+
"acc": 0.8407960199004975,
|
| 393 |
+
"acc_stderr": 0.02587064676616913,
|
| 394 |
+
"acc_norm": 0.8407960199004975,
|
| 395 |
+
"acc_norm_stderr": 0.02587064676616913
|
| 396 |
+
},
|
| 397 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 398 |
+
"acc": 0.86,
|
| 399 |
+
"acc_stderr": 0.0348735088019777,
|
| 400 |
+
"acc_norm": 0.86,
|
| 401 |
+
"acc_norm_stderr": 0.0348735088019777
|
| 402 |
+
},
|
| 403 |
+
"harness|hendrycksTest-virology|5": {
|
| 404 |
+
"acc": 0.5421686746987951,
|
| 405 |
+
"acc_stderr": 0.0387862677100236,
|
| 406 |
+
"acc_norm": 0.5421686746987951,
|
| 407 |
+
"acc_norm_stderr": 0.0387862677100236
|
| 408 |
+
},
|
| 409 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 410 |
+
"acc": 0.8421052631578947,
|
| 411 |
+
"acc_stderr": 0.027966785859160893,
|
| 412 |
+
"acc_norm": 0.8421052631578947,
|
| 413 |
+
"acc_norm_stderr": 0.027966785859160893
|
| 414 |
+
},
|
| 415 |
+
"harness|truthfulqa:mc|0": {
|
| 416 |
+
"mc1": 0.46878824969400246,
|
| 417 |
+
"mc1_stderr": 0.017469364874577537,
|
| 418 |
+
"mc2": 0.6324196158065736,
|
| 419 |
+
"mc2_stderr": 0.015183642172146008
|
| 420 |
+
},
|
| 421 |
+
"harness|winogrande|5": {
|
| 422 |
+
"acc": 0.8161010260457774,
|
| 423 |
+
"acc_stderr": 0.010887916013305889
|
| 424 |
+
},
|
| 425 |
+
"harness|gsm8k|5": {
|
| 426 |
+
"acc": 0.730098559514784,
|
| 427 |
+
"acc_stderr": 0.012227442856468897
|
| 428 |
+
}
|
| 429 |
+
}
|
| 430 |
+
|
| 431 |
```
|