Update README.md
Browse filesadd evaluation result
README.md
CHANGED
|
@@ -32,4 +32,393 @@ parameters:
|
|
| 32 |
- value: 0.5
|
| 33 |
dtype: bfloat16
|
| 34 |
|
| 35 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
- value: 0.5
|
| 33 |
dtype: bfloat16
|
| 34 |
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## Evaluation
|
| 38 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-slerp
|
| 39 |
+
|
| 40 |
+
Latest Result:
|
| 41 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-slerp/blob/main/results_2024-03-10T11-04-57.263703.json
|
| 42 |
+
|
| 43 |
+
```
|
| 44 |
+
{
|
| 45 |
+
"all": {
|
| 46 |
+
"acc": 0.6444688446653744,
|
| 47 |
+
"acc_stderr": 0.03217564834975917,
|
| 48 |
+
"acc_norm": 0.6448609553287138,
|
| 49 |
+
"acc_norm_stderr": 0.032833467276313325,
|
| 50 |
+
"mc1": 0.4283965728274174,
|
| 51 |
+
"mc1_stderr": 0.017323088597314754,
|
| 52 |
+
"mc2": 0.5985018412437423,
|
| 53 |
+
"mc2_stderr": 0.01514980059720055
|
| 54 |
+
},
|
| 55 |
+
"harness|arc:challenge|25": {
|
| 56 |
+
"acc": 0.6476109215017065,
|
| 57 |
+
"acc_stderr": 0.013960142600598675,
|
| 58 |
+
"acc_norm": 0.6774744027303754,
|
| 59 |
+
"acc_norm_stderr": 0.013659980894277364
|
| 60 |
+
},
|
| 61 |
+
"harness|hellaswag|10": {
|
| 62 |
+
"acc": 0.6700856403106951,
|
| 63 |
+
"acc_stderr": 0.004692208279690595,
|
| 64 |
+
"acc_norm": 0.8616809400517825,
|
| 65 |
+
"acc_norm_stderr": 0.0034452899250117337
|
| 66 |
+
},
|
| 67 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 68 |
+
"acc": 0.3,
|
| 69 |
+
"acc_stderr": 0.046056618647183814,
|
| 70 |
+
"acc_norm": 0.3,
|
| 71 |
+
"acc_norm_stderr": 0.046056618647183814
|
| 72 |
+
},
|
| 73 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 74 |
+
"acc": 0.6074074074074074,
|
| 75 |
+
"acc_stderr": 0.0421850621536888,
|
| 76 |
+
"acc_norm": 0.6074074074074074,
|
| 77 |
+
"acc_norm_stderr": 0.0421850621536888
|
| 78 |
+
},
|
| 79 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 80 |
+
"acc": 0.7105263157894737,
|
| 81 |
+
"acc_stderr": 0.03690677986137283,
|
| 82 |
+
"acc_norm": 0.7105263157894737,
|
| 83 |
+
"acc_norm_stderr": 0.03690677986137283
|
| 84 |
+
},
|
| 85 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 86 |
+
"acc": 0.61,
|
| 87 |
+
"acc_stderr": 0.04902071300001975,
|
| 88 |
+
"acc_norm": 0.61,
|
| 89 |
+
"acc_norm_stderr": 0.04902071300001975
|
| 90 |
+
},
|
| 91 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 92 |
+
"acc": 0.6830188679245283,
|
| 93 |
+
"acc_stderr": 0.02863723563980089,
|
| 94 |
+
"acc_norm": 0.6830188679245283,
|
| 95 |
+
"acc_norm_stderr": 0.02863723563980089
|
| 96 |
+
},
|
| 97 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 98 |
+
"acc": 0.7777777777777778,
|
| 99 |
+
"acc_stderr": 0.03476590104304134,
|
| 100 |
+
"acc_norm": 0.7777777777777778,
|
| 101 |
+
"acc_norm_stderr": 0.03476590104304134
|
| 102 |
+
},
|
| 103 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 104 |
+
"acc": 0.45,
|
| 105 |
+
"acc_stderr": 0.05,
|
| 106 |
+
"acc_norm": 0.45,
|
| 107 |
+
"acc_norm_stderr": 0.05
|
| 108 |
+
},
|
| 109 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 110 |
+
"acc": 0.49,
|
| 111 |
+
"acc_stderr": 0.05024183937956912,
|
| 112 |
+
"acc_norm": 0.49,
|
| 113 |
+
"acc_norm_stderr": 0.05024183937956912
|
| 114 |
+
},
|
| 115 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 116 |
+
"acc": 0.29,
|
| 117 |
+
"acc_stderr": 0.045604802157206845,
|
| 118 |
+
"acc_norm": 0.29,
|
| 119 |
+
"acc_norm_stderr": 0.045604802157206845
|
| 120 |
+
},
|
| 121 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 122 |
+
"acc": 0.6473988439306358,
|
| 123 |
+
"acc_stderr": 0.036430371689585475,
|
| 124 |
+
"acc_norm": 0.6473988439306358,
|
| 125 |
+
"acc_norm_stderr": 0.036430371689585475
|
| 126 |
+
},
|
| 127 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 128 |
+
"acc": 0.39215686274509803,
|
| 129 |
+
"acc_stderr": 0.04858083574266345,
|
| 130 |
+
"acc_norm": 0.39215686274509803,
|
| 131 |
+
"acc_norm_stderr": 0.04858083574266345
|
| 132 |
+
},
|
| 133 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 134 |
+
"acc": 0.74,
|
| 135 |
+
"acc_stderr": 0.04408440022768078,
|
| 136 |
+
"acc_norm": 0.74,
|
| 137 |
+
"acc_norm_stderr": 0.04408440022768078
|
| 138 |
+
},
|
| 139 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 140 |
+
"acc": 0.5829787234042553,
|
| 141 |
+
"acc_stderr": 0.03223276266711712,
|
| 142 |
+
"acc_norm": 0.5829787234042553,
|
| 143 |
+
"acc_norm_stderr": 0.03223276266711712
|
| 144 |
+
},
|
| 145 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 146 |
+
"acc": 0.5,
|
| 147 |
+
"acc_stderr": 0.047036043419179864,
|
| 148 |
+
"acc_norm": 0.5,
|
| 149 |
+
"acc_norm_stderr": 0.047036043419179864
|
| 150 |
+
},
|
| 151 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 152 |
+
"acc": 0.5448275862068965,
|
| 153 |
+
"acc_stderr": 0.04149886942192117,
|
| 154 |
+
"acc_norm": 0.5448275862068965,
|
| 155 |
+
"acc_norm_stderr": 0.04149886942192117
|
| 156 |
+
},
|
| 157 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 158 |
+
"acc": 0.41534391534391535,
|
| 159 |
+
"acc_stderr": 0.025379524910778405,
|
| 160 |
+
"acc_norm": 0.41534391534391535,
|
| 161 |
+
"acc_norm_stderr": 0.025379524910778405
|
| 162 |
+
},
|
| 163 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 164 |
+
"acc": 0.4603174603174603,
|
| 165 |
+
"acc_stderr": 0.04458029125470973,
|
| 166 |
+
"acc_norm": 0.4603174603174603,
|
| 167 |
+
"acc_norm_stderr": 0.04458029125470973
|
| 168 |
+
},
|
| 169 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 170 |
+
"acc": 0.38,
|
| 171 |
+
"acc_stderr": 0.048783173121456316,
|
| 172 |
+
"acc_norm": 0.38,
|
| 173 |
+
"acc_norm_stderr": 0.048783173121456316
|
| 174 |
+
},
|
| 175 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 176 |
+
"acc": 0.7774193548387097,
|
| 177 |
+
"acc_stderr": 0.023664216671642518,
|
| 178 |
+
"acc_norm": 0.7774193548387097,
|
| 179 |
+
"acc_norm_stderr": 0.023664216671642518
|
| 180 |
+
},
|
| 181 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 182 |
+
"acc": 0.5073891625615764,
|
| 183 |
+
"acc_stderr": 0.035176035403610105,
|
| 184 |
+
"acc_norm": 0.5073891625615764,
|
| 185 |
+
"acc_norm_stderr": 0.035176035403610105
|
| 186 |
+
},
|
| 187 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 188 |
+
"acc": 0.69,
|
| 189 |
+
"acc_stderr": 0.04648231987117316,
|
| 190 |
+
"acc_norm": 0.69,
|
| 191 |
+
"acc_norm_stderr": 0.04648231987117316
|
| 192 |
+
},
|
| 193 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 194 |
+
"acc": 0.7696969696969697,
|
| 195 |
+
"acc_stderr": 0.0328766675860349,
|
| 196 |
+
"acc_norm": 0.7696969696969697,
|
| 197 |
+
"acc_norm_stderr": 0.0328766675860349
|
| 198 |
+
},
|
| 199 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 200 |
+
"acc": 0.7878787878787878,
|
| 201 |
+
"acc_stderr": 0.029126522834586818,
|
| 202 |
+
"acc_norm": 0.7878787878787878,
|
| 203 |
+
"acc_norm_stderr": 0.029126522834586818
|
| 204 |
+
},
|
| 205 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 206 |
+
"acc": 0.9015544041450777,
|
| 207 |
+
"acc_stderr": 0.02150024957603346,
|
| 208 |
+
"acc_norm": 0.9015544041450777,
|
| 209 |
+
"acc_norm_stderr": 0.02150024957603346
|
| 210 |
+
},
|
| 211 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 212 |
+
"acc": 0.6538461538461539,
|
| 213 |
+
"acc_stderr": 0.02412112541694119,
|
| 214 |
+
"acc_norm": 0.6538461538461539,
|
| 215 |
+
"acc_norm_stderr": 0.02412112541694119
|
| 216 |
+
},
|
| 217 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 218 |
+
"acc": 0.32222222222222224,
|
| 219 |
+
"acc_stderr": 0.028493465091028593,
|
| 220 |
+
"acc_norm": 0.32222222222222224,
|
| 221 |
+
"acc_norm_stderr": 0.028493465091028593
|
| 222 |
+
},
|
| 223 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 224 |
+
"acc": 0.6890756302521008,
|
| 225 |
+
"acc_stderr": 0.03006676158297793,
|
| 226 |
+
"acc_norm": 0.6890756302521008,
|
| 227 |
+
"acc_norm_stderr": 0.03006676158297793
|
| 228 |
+
},
|
| 229 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 230 |
+
"acc": 0.32450331125827814,
|
| 231 |
+
"acc_stderr": 0.03822746937658752,
|
| 232 |
+
"acc_norm": 0.32450331125827814,
|
| 233 |
+
"acc_norm_stderr": 0.03822746937658752
|
| 234 |
+
},
|
| 235 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 236 |
+
"acc": 0.8550458715596331,
|
| 237 |
+
"acc_stderr": 0.01509421569970048,
|
| 238 |
+
"acc_norm": 0.8550458715596331,
|
| 239 |
+
"acc_norm_stderr": 0.01509421569970048
|
| 240 |
+
},
|
| 241 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 242 |
+
"acc": 0.5185185185185185,
|
| 243 |
+
"acc_stderr": 0.034076320938540516,
|
| 244 |
+
"acc_norm": 0.5185185185185185,
|
| 245 |
+
"acc_norm_stderr": 0.034076320938540516
|
| 246 |
+
},
|
| 247 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 248 |
+
"acc": 0.8186274509803921,
|
| 249 |
+
"acc_stderr": 0.027044621719474082,
|
| 250 |
+
"acc_norm": 0.8186274509803921,
|
| 251 |
+
"acc_norm_stderr": 0.027044621719474082
|
| 252 |
+
},
|
| 253 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 254 |
+
"acc": 0.8059071729957806,
|
| 255 |
+
"acc_stderr": 0.0257449025322909,
|
| 256 |
+
"acc_norm": 0.8059071729957806,
|
| 257 |
+
"acc_norm_stderr": 0.0257449025322909
|
| 258 |
+
},
|
| 259 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 260 |
+
"acc": 0.6905829596412556,
|
| 261 |
+
"acc_stderr": 0.03102441174057221,
|
| 262 |
+
"acc_norm": 0.6905829596412556,
|
| 263 |
+
"acc_norm_stderr": 0.03102441174057221
|
| 264 |
+
},
|
| 265 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 266 |
+
"acc": 0.7786259541984732,
|
| 267 |
+
"acc_stderr": 0.03641297081313729,
|
| 268 |
+
"acc_norm": 0.7786259541984732,
|
| 269 |
+
"acc_norm_stderr": 0.03641297081313729
|
| 270 |
+
},
|
| 271 |
+
"harness|hendrycksTest-international_law|5": {
|
| 272 |
+
"acc": 0.8099173553719008,
|
| 273 |
+
"acc_stderr": 0.03581796951709282,
|
| 274 |
+
"acc_norm": 0.8099173553719008,
|
| 275 |
+
"acc_norm_stderr": 0.03581796951709282
|
| 276 |
+
},
|
| 277 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 278 |
+
"acc": 0.7685185185185185,
|
| 279 |
+
"acc_stderr": 0.04077494709252626,
|
| 280 |
+
"acc_norm": 0.7685185185185185,
|
| 281 |
+
"acc_norm_stderr": 0.04077494709252626
|
| 282 |
+
},
|
| 283 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 284 |
+
"acc": 0.7730061349693251,
|
| 285 |
+
"acc_stderr": 0.03291099578615769,
|
| 286 |
+
"acc_norm": 0.7730061349693251,
|
| 287 |
+
"acc_norm_stderr": 0.03291099578615769
|
| 288 |
+
},
|
| 289 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 290 |
+
"acc": 0.4642857142857143,
|
| 291 |
+
"acc_stderr": 0.04733667890053756,
|
| 292 |
+
"acc_norm": 0.4642857142857143,
|
| 293 |
+
"acc_norm_stderr": 0.04733667890053756
|
| 294 |
+
},
|
| 295 |
+
"harness|hendrycksTest-management|5": {
|
| 296 |
+
"acc": 0.7572815533980582,
|
| 297 |
+
"acc_stderr": 0.04245022486384495,
|
| 298 |
+
"acc_norm": 0.7572815533980582,
|
| 299 |
+
"acc_norm_stderr": 0.04245022486384495
|
| 300 |
+
},
|
| 301 |
+
"harness|hendrycksTest-marketing|5": {
|
| 302 |
+
"acc": 0.8547008547008547,
|
| 303 |
+
"acc_stderr": 0.023086635086841407,
|
| 304 |
+
"acc_norm": 0.8547008547008547,
|
| 305 |
+
"acc_norm_stderr": 0.023086635086841407
|
| 306 |
+
},
|
| 307 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 308 |
+
"acc": 0.7,
|
| 309 |
+
"acc_stderr": 0.046056618647183814,
|
| 310 |
+
"acc_norm": 0.7,
|
| 311 |
+
"acc_norm_stderr": 0.046056618647183814
|
| 312 |
+
},
|
| 313 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 314 |
+
"acc": 0.8352490421455939,
|
| 315 |
+
"acc_stderr": 0.013265346261323793,
|
| 316 |
+
"acc_norm": 0.8352490421455939,
|
| 317 |
+
"acc_norm_stderr": 0.013265346261323793
|
| 318 |
+
},
|
| 319 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 320 |
+
"acc": 0.7283236994219653,
|
| 321 |
+
"acc_stderr": 0.023948512905468365,
|
| 322 |
+
"acc_norm": 0.7283236994219653,
|
| 323 |
+
"acc_norm_stderr": 0.023948512905468365
|
| 324 |
+
},
|
| 325 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 326 |
+
"acc": 0.36312849162011174,
|
| 327 |
+
"acc_stderr": 0.016083749986853697,
|
| 328 |
+
"acc_norm": 0.36312849162011174,
|
| 329 |
+
"acc_norm_stderr": 0.016083749986853697
|
| 330 |
+
},
|
| 331 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 332 |
+
"acc": 0.7450980392156863,
|
| 333 |
+
"acc_stderr": 0.02495418432487991,
|
| 334 |
+
"acc_norm": 0.7450980392156863,
|
| 335 |
+
"acc_norm_stderr": 0.02495418432487991
|
| 336 |
+
},
|
| 337 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 338 |
+
"acc": 0.7106109324758842,
|
| 339 |
+
"acc_stderr": 0.025755865922632945,
|
| 340 |
+
"acc_norm": 0.7106109324758842,
|
| 341 |
+
"acc_norm_stderr": 0.025755865922632945
|
| 342 |
+
},
|
| 343 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 344 |
+
"acc": 0.7469135802469136,
|
| 345 |
+
"acc_stderr": 0.024191808600712995,
|
| 346 |
+
"acc_norm": 0.7469135802469136,
|
| 347 |
+
"acc_norm_stderr": 0.024191808600712995
|
| 348 |
+
},
|
| 349 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 350 |
+
"acc": 0.4787234042553192,
|
| 351 |
+
"acc_stderr": 0.029800481645628693,
|
| 352 |
+
"acc_norm": 0.4787234042553192,
|
| 353 |
+
"acc_norm_stderr": 0.029800481645628693
|
| 354 |
+
},
|
| 355 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 356 |
+
"acc": 0.4726205997392438,
|
| 357 |
+
"acc_stderr": 0.012751075788015058,
|
| 358 |
+
"acc_norm": 0.4726205997392438,
|
| 359 |
+
"acc_norm_stderr": 0.012751075788015058
|
| 360 |
+
},
|
| 361 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 362 |
+
"acc": 0.6948529411764706,
|
| 363 |
+
"acc_stderr": 0.027971541370170598,
|
| 364 |
+
"acc_norm": 0.6948529411764706,
|
| 365 |
+
"acc_norm_stderr": 0.027971541370170598
|
| 366 |
+
},
|
| 367 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 368 |
+
"acc": 0.6748366013071896,
|
| 369 |
+
"acc_stderr": 0.01895088677080631,
|
| 370 |
+
"acc_norm": 0.6748366013071896,
|
| 371 |
+
"acc_norm_stderr": 0.01895088677080631
|
| 372 |
+
},
|
| 373 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 374 |
+
"acc": 0.6636363636363637,
|
| 375 |
+
"acc_stderr": 0.04525393596302506,
|
| 376 |
+
"acc_norm": 0.6636363636363637,
|
| 377 |
+
"acc_norm_stderr": 0.04525393596302506
|
| 378 |
+
},
|
| 379 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 380 |
+
"acc": 0.746938775510204,
|
| 381 |
+
"acc_stderr": 0.027833023871399673,
|
| 382 |
+
"acc_norm": 0.746938775510204,
|
| 383 |
+
"acc_norm_stderr": 0.027833023871399673
|
| 384 |
+
},
|
| 385 |
+
"harness|hendrycksTest-sociology|5": {
|
| 386 |
+
"acc": 0.835820895522388,
|
| 387 |
+
"acc_stderr": 0.026193923544454115,
|
| 388 |
+
"acc_norm": 0.835820895522388,
|
| 389 |
+
"acc_norm_stderr": 0.026193923544454115
|
| 390 |
+
},
|
| 391 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 392 |
+
"acc": 0.85,
|
| 393 |
+
"acc_stderr": 0.0358870281282637,
|
| 394 |
+
"acc_norm": 0.85,
|
| 395 |
+
"acc_norm_stderr": 0.0358870281282637
|
| 396 |
+
},
|
| 397 |
+
"harness|hendrycksTest-virology|5": {
|
| 398 |
+
"acc": 0.5301204819277109,
|
| 399 |
+
"acc_stderr": 0.03885425420866767,
|
| 400 |
+
"acc_norm": 0.5301204819277109,
|
| 401 |
+
"acc_norm_stderr": 0.03885425420866767
|
| 402 |
+
},
|
| 403 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 404 |
+
"acc": 0.8304093567251462,
|
| 405 |
+
"acc_stderr": 0.02878210810540171,
|
| 406 |
+
"acc_norm": 0.8304093567251462,
|
| 407 |
+
"acc_norm_stderr": 0.02878210810540171
|
| 408 |
+
},
|
| 409 |
+
"harness|truthfulqa:mc|0": {
|
| 410 |
+
"mc1": 0.4283965728274174,
|
| 411 |
+
"mc1_stderr": 0.017323088597314754,
|
| 412 |
+
"mc2": 0.5985018412437423,
|
| 413 |
+
"mc2_stderr": 0.01514980059720055
|
| 414 |
+
},
|
| 415 |
+
"harness|winogrande|5": {
|
| 416 |
+
"acc": 0.8018942383583267,
|
| 417 |
+
"acc_stderr": 0.01120186274448705
|
| 418 |
+
},
|
| 419 |
+
"harness|gsm8k|5": {
|
| 420 |
+
"acc": 0.6853677028051555,
|
| 421 |
+
"acc_stderr": 0.01279103722733604
|
| 422 |
+
}
|
| 423 |
+
}
|
| 424 |
+
```
|