Update README.md (#2)
Browse files- Update README.md (9c171ea698ca3574a9c0c3db01b4546cfc27f764)
README.md
CHANGED
|
@@ -75,4 +75,389 @@ Cons of Docker System:
|
|
| 75 |
- Learning curve - It takes time to learn how to use Docker effectively, as there are many commands and concepts involved.
|
| 76 |
- Limited customization options - While Docker provides some basic configuration options, more advanced features such as network routing require additional tools.
|
| 77 |
- Performance overhead - Running multiple containers on a single host may result in slower performance due to increased memory usage.</s>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
```
|
|
|
|
| 75 |
- Learning curve - It takes time to learn how to use Docker effectively, as there are many commands and concepts involved.
|
| 76 |
- Limited customization options - While Docker provides some basic configuration options, more advanced features such as network routing require additional tools.
|
| 77 |
- Performance overhead - Running multiple containers on a single host may result in slower performance due to increased memory usage.</s>
|
| 78 |
+
```
|
| 79 |
+
|
| 80 |
+
## Eval
|
| 81 |
+
|
| 82 |
+
```python
|
| 83 |
+
{
|
| 84 |
+
"all": {
|
| 85 |
+
"acc": 0.6309850839451187,
|
| 86 |
+
"acc_stderr": 0.032333688535613636,
|
| 87 |
+
"acc_norm": 0.6368691004374645,
|
| 88 |
+
"acc_norm_stderr": 0.03298401757997533,
|
| 89 |
+
"mc1": 0.29008567931456547,
|
| 90 |
+
"mc1_stderr": 0.01588623687420952,
|
| 91 |
+
"mc2": 0.41501661742948026,
|
| 92 |
+
"mc2_stderr": 0.014285902986671931
|
| 93 |
+
},
|
| 94 |
+
"harness|arc:challenge|25": {
|
| 95 |
+
"acc": 0.5750853242320819,
|
| 96 |
+
"acc_stderr": 0.014445698968520767,
|
| 97 |
+
"acc_norm": 0.6092150170648464,
|
| 98 |
+
"acc_norm_stderr": 0.01425856388051378
|
| 99 |
+
},
|
| 100 |
+
"harness|hellaswag|10": {
|
| 101 |
+
"acc": 0.6221868153754232,
|
| 102 |
+
"acc_stderr": 0.0048384969668239025,
|
| 103 |
+
"acc_norm": 0.8212507468631747,
|
| 104 |
+
"acc_norm_stderr": 0.0038235918141330347
|
| 105 |
+
},
|
| 106 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 107 |
+
"acc": 0.32,
|
| 108 |
+
"acc_stderr": 0.046882617226215034,
|
| 109 |
+
"acc_norm": 0.32,
|
| 110 |
+
"acc_norm_stderr": 0.046882617226215034
|
| 111 |
+
},
|
| 112 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 113 |
+
"acc": 0.6,
|
| 114 |
+
"acc_stderr": 0.04232073695151589,
|
| 115 |
+
"acc_norm": 0.6,
|
| 116 |
+
"acc_norm_stderr": 0.04232073695151589
|
| 117 |
+
},
|
| 118 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 119 |
+
"acc": 0.6447368421052632,
|
| 120 |
+
"acc_stderr": 0.038947344870133176,
|
| 121 |
+
"acc_norm": 0.6447368421052632,
|
| 122 |
+
"acc_norm_stderr": 0.038947344870133176
|
| 123 |
+
},
|
| 124 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 125 |
+
"acc": 0.57,
|
| 126 |
+
"acc_stderr": 0.04975698519562428,
|
| 127 |
+
"acc_norm": 0.57,
|
| 128 |
+
"acc_norm_stderr": 0.04975698519562428
|
| 129 |
+
},
|
| 130 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 131 |
+
"acc": 0.6792452830188679,
|
| 132 |
+
"acc_stderr": 0.02872750295788027,
|
| 133 |
+
"acc_norm": 0.6792452830188679,
|
| 134 |
+
"acc_norm_stderr": 0.02872750295788027
|
| 135 |
+
},
|
| 136 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 137 |
+
"acc": 0.7430555555555556,
|
| 138 |
+
"acc_stderr": 0.03653946969442099,
|
| 139 |
+
"acc_norm": 0.7430555555555556,
|
| 140 |
+
"acc_norm_stderr": 0.03653946969442099
|
| 141 |
+
},
|
| 142 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 143 |
+
"acc": 0.49,
|
| 144 |
+
"acc_stderr": 0.05024183937956912,
|
| 145 |
+
"acc_norm": 0.49,
|
| 146 |
+
"acc_norm_stderr": 0.05024183937956912
|
| 147 |
+
},
|
| 148 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 149 |
+
"acc": 0.56,
|
| 150 |
+
"acc_stderr": 0.04988876515698589,
|
| 151 |
+
"acc_norm": 0.56,
|
| 152 |
+
"acc_norm_stderr": 0.04988876515698589
|
| 153 |
+
},
|
| 154 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 155 |
+
"acc": 0.36,
|
| 156 |
+
"acc_stderr": 0.048241815132442176,
|
| 157 |
+
"acc_norm": 0.36,
|
| 158 |
+
"acc_norm_stderr": 0.048241815132442176
|
| 159 |
+
},
|
| 160 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 161 |
+
"acc": 0.653179190751445,
|
| 162 |
+
"acc_stderr": 0.036291466701596636,
|
| 163 |
+
"acc_norm": 0.653179190751445,
|
| 164 |
+
"acc_norm_stderr": 0.036291466701596636
|
| 165 |
+
},
|
| 166 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 167 |
+
"acc": 0.4019607843137255,
|
| 168 |
+
"acc_stderr": 0.048786087144669955,
|
| 169 |
+
"acc_norm": 0.4019607843137255,
|
| 170 |
+
"acc_norm_stderr": 0.048786087144669955
|
| 171 |
+
},
|
| 172 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 173 |
+
"acc": 0.79,
|
| 174 |
+
"acc_stderr": 0.04093601807403326,
|
| 175 |
+
"acc_norm": 0.79,
|
| 176 |
+
"acc_norm_stderr": 0.04093601807403326
|
| 177 |
+
},
|
| 178 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 179 |
+
"acc": 0.5702127659574469,
|
| 180 |
+
"acc_stderr": 0.03236214467715564,
|
| 181 |
+
"acc_norm": 0.5702127659574469,
|
| 182 |
+
"acc_norm_stderr": 0.03236214467715564
|
| 183 |
+
},
|
| 184 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 185 |
+
"acc": 0.49122807017543857,
|
| 186 |
+
"acc_stderr": 0.047028804320496165,
|
| 187 |
+
"acc_norm": 0.49122807017543857,
|
| 188 |
+
"acc_norm_stderr": 0.047028804320496165
|
| 189 |
+
},
|
| 190 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 191 |
+
"acc": 0.5862068965517241,
|
| 192 |
+
"acc_stderr": 0.04104269211806232,
|
| 193 |
+
"acc_norm": 0.5862068965517241,
|
| 194 |
+
"acc_norm_stderr": 0.04104269211806232
|
| 195 |
+
},
|
| 196 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 197 |
+
"acc": 0.3915343915343915,
|
| 198 |
+
"acc_stderr": 0.025138091388851116,
|
| 199 |
+
"acc_norm": 0.3915343915343915,
|
| 200 |
+
"acc_norm_stderr": 0.025138091388851116
|
| 201 |
+
},
|
| 202 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 203 |
+
"acc": 0.4444444444444444,
|
| 204 |
+
"acc_stderr": 0.04444444444444449,
|
| 205 |
+
"acc_norm": 0.4444444444444444,
|
| 206 |
+
"acc_norm_stderr": 0.04444444444444449
|
| 207 |
+
},
|
| 208 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 209 |
+
"acc": 0.32,
|
| 210 |
+
"acc_stderr": 0.04688261722621504,
|
| 211 |
+
"acc_norm": 0.32,
|
| 212 |
+
"acc_norm_stderr": 0.04688261722621504
|
| 213 |
+
},
|
| 214 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 215 |
+
"acc": 0.7419354838709677,
|
| 216 |
+
"acc_stderr": 0.02489246917246283,
|
| 217 |
+
"acc_norm": 0.7419354838709677,
|
| 218 |
+
"acc_norm_stderr": 0.02489246917246283
|
| 219 |
+
},
|
| 220 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 221 |
+
"acc": 0.5024630541871922,
|
| 222 |
+
"acc_stderr": 0.035179450386910616,
|
| 223 |
+
"acc_norm": 0.5024630541871922,
|
| 224 |
+
"acc_norm_stderr": 0.035179450386910616
|
| 225 |
+
},
|
| 226 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 227 |
+
"acc": 0.67,
|
| 228 |
+
"acc_stderr": 0.047258156262526066,
|
| 229 |
+
"acc_norm": 0.67,
|
| 230 |
+
"acc_norm_stderr": 0.047258156262526066
|
| 231 |
+
},
|
| 232 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 233 |
+
"acc": 0.7575757575757576,
|
| 234 |
+
"acc_stderr": 0.03346409881055953,
|
| 235 |
+
"acc_norm": 0.7575757575757576,
|
| 236 |
+
"acc_norm_stderr": 0.03346409881055953
|
| 237 |
+
},
|
| 238 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 239 |
+
"acc": 0.7929292929292929,
|
| 240 |
+
"acc_stderr": 0.028869778460267042,
|
| 241 |
+
"acc_norm": 0.7929292929292929,
|
| 242 |
+
"acc_norm_stderr": 0.028869778460267042
|
| 243 |
+
},
|
| 244 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 245 |
+
"acc": 0.8601036269430051,
|
| 246 |
+
"acc_stderr": 0.025033870583015184,
|
| 247 |
+
"acc_norm": 0.8601036269430051,
|
| 248 |
+
"acc_norm_stderr": 0.025033870583015184
|
| 249 |
+
},
|
| 250 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 251 |
+
"acc": 0.6358974358974359,
|
| 252 |
+
"acc_stderr": 0.024396672985094764,
|
| 253 |
+
"acc_norm": 0.6358974358974359,
|
| 254 |
+
"acc_norm_stderr": 0.024396672985094764
|
| 255 |
+
},
|
| 256 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 257 |
+
"acc": 0.362962962962963,
|
| 258 |
+
"acc_stderr": 0.029318203645206865,
|
| 259 |
+
"acc_norm": 0.362962962962963,
|
| 260 |
+
"acc_norm_stderr": 0.029318203645206865
|
| 261 |
+
},
|
| 262 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 263 |
+
"acc": 0.6218487394957983,
|
| 264 |
+
"acc_stderr": 0.03149930577784906,
|
| 265 |
+
"acc_norm": 0.6218487394957983,
|
| 266 |
+
"acc_norm_stderr": 0.03149930577784906
|
| 267 |
+
},
|
| 268 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 269 |
+
"acc": 0.32450331125827814,
|
| 270 |
+
"acc_stderr": 0.038227469376587525,
|
| 271 |
+
"acc_norm": 0.32450331125827814,
|
| 272 |
+
"acc_norm_stderr": 0.038227469376587525
|
| 273 |
+
},
|
| 274 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 275 |
+
"acc": 0.8146788990825689,
|
| 276 |
+
"acc_stderr": 0.016659279700295838,
|
| 277 |
+
"acc_norm": 0.8146788990825689,
|
| 278 |
+
"acc_norm_stderr": 0.016659279700295838
|
| 279 |
+
},
|
| 280 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 281 |
+
"acc": 0.49537037037037035,
|
| 282 |
+
"acc_stderr": 0.03409825519163572,
|
| 283 |
+
"acc_norm": 0.49537037037037035,
|
| 284 |
+
"acc_norm_stderr": 0.03409825519163572
|
| 285 |
+
},
|
| 286 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 287 |
+
"acc": 0.7892156862745098,
|
| 288 |
+
"acc_stderr": 0.028626547912437406,
|
| 289 |
+
"acc_norm": 0.7892156862745098,
|
| 290 |
+
"acc_norm_stderr": 0.028626547912437406
|
| 291 |
+
},
|
| 292 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 293 |
+
"acc": 0.7552742616033755,
|
| 294 |
+
"acc_stderr": 0.027985699387036423,
|
| 295 |
+
"acc_norm": 0.7552742616033755,
|
| 296 |
+
"acc_norm_stderr": 0.027985699387036423
|
| 297 |
+
},
|
| 298 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 299 |
+
"acc": 0.6636771300448431,
|
| 300 |
+
"acc_stderr": 0.031708824268455,
|
| 301 |
+
"acc_norm": 0.6636771300448431,
|
| 302 |
+
"acc_norm_stderr": 0.031708824268455
|
| 303 |
+
},
|
| 304 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 305 |
+
"acc": 0.7862595419847328,
|
| 306 |
+
"acc_stderr": 0.0359546161177469,
|
| 307 |
+
"acc_norm": 0.7862595419847328,
|
| 308 |
+
"acc_norm_stderr": 0.0359546161177469
|
| 309 |
+
},
|
| 310 |
+
"harness|hendrycksTest-international_law|5": {
|
| 311 |
+
"acc": 0.7933884297520661,
|
| 312 |
+
"acc_stderr": 0.03695980128098824,
|
| 313 |
+
"acc_norm": 0.7933884297520661,
|
| 314 |
+
"acc_norm_stderr": 0.03695980128098824
|
| 315 |
+
},
|
| 316 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 317 |
+
"acc": 0.7592592592592593,
|
| 318 |
+
"acc_stderr": 0.04133119440243838,
|
| 319 |
+
"acc_norm": 0.7592592592592593,
|
| 320 |
+
"acc_norm_stderr": 0.04133119440243838
|
| 321 |
+
},
|
| 322 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 323 |
+
"acc": 0.803680981595092,
|
| 324 |
+
"acc_stderr": 0.031207970394709218,
|
| 325 |
+
"acc_norm": 0.803680981595092,
|
| 326 |
+
"acc_norm_stderr": 0.031207970394709218
|
| 327 |
+
},
|
| 328 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 329 |
+
"acc": 0.5178571428571429,
|
| 330 |
+
"acc_stderr": 0.047427623612430116,
|
| 331 |
+
"acc_norm": 0.5178571428571429,
|
| 332 |
+
"acc_norm_stderr": 0.047427623612430116
|
| 333 |
+
},
|
| 334 |
+
"harness|hendrycksTest-management|5": {
|
| 335 |
+
"acc": 0.8252427184466019,
|
| 336 |
+
"acc_stderr": 0.03760178006026621,
|
| 337 |
+
"acc_norm": 0.8252427184466019,
|
| 338 |
+
"acc_norm_stderr": 0.03760178006026621
|
| 339 |
+
},
|
| 340 |
+
"harness|hendrycksTest-marketing|5": {
|
| 341 |
+
"acc": 0.8632478632478633,
|
| 342 |
+
"acc_stderr": 0.022509033937077816,
|
| 343 |
+
"acc_norm": 0.8632478632478633,
|
| 344 |
+
"acc_norm_stderr": 0.022509033937077816
|
| 345 |
+
},
|
| 346 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 347 |
+
"acc": 0.74,
|
| 348 |
+
"acc_stderr": 0.04408440022768078,
|
| 349 |
+
"acc_norm": 0.74,
|
| 350 |
+
"acc_norm_stderr": 0.04408440022768078
|
| 351 |
+
},
|
| 352 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 353 |
+
"acc": 0.8173690932311622,
|
| 354 |
+
"acc_stderr": 0.013816335389973136,
|
| 355 |
+
"acc_norm": 0.8173690932311622,
|
| 356 |
+
"acc_norm_stderr": 0.013816335389973136
|
| 357 |
+
},
|
| 358 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 359 |
+
"acc": 0.7023121387283237,
|
| 360 |
+
"acc_stderr": 0.024617055388677,
|
| 361 |
+
"acc_norm": 0.7023121387283237,
|
| 362 |
+
"acc_norm_stderr": 0.024617055388677
|
| 363 |
+
},
|
| 364 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 365 |
+
"acc": 0.2335195530726257,
|
| 366 |
+
"acc_stderr": 0.014149575348976269,
|
| 367 |
+
"acc_norm": 0.2335195530726257,
|
| 368 |
+
"acc_norm_stderr": 0.014149575348976269
|
| 369 |
+
},
|
| 370 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 371 |
+
"acc": 0.7450980392156863,
|
| 372 |
+
"acc_stderr": 0.024954184324879905,
|
| 373 |
+
"acc_norm": 0.7450980392156863,
|
| 374 |
+
"acc_norm_stderr": 0.024954184324879905
|
| 375 |
+
},
|
| 376 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 377 |
+
"acc": 0.7106109324758842,
|
| 378 |
+
"acc_stderr": 0.025755865922632945,
|
| 379 |
+
"acc_norm": 0.7106109324758842,
|
| 380 |
+
"acc_norm_stderr": 0.025755865922632945
|
| 381 |
+
},
|
| 382 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 383 |
+
"acc": 0.7191358024691358,
|
| 384 |
+
"acc_stderr": 0.025006469755799215,
|
| 385 |
+
"acc_norm": 0.7191358024691358,
|
| 386 |
+
"acc_norm_stderr": 0.025006469755799215
|
| 387 |
+
},
|
| 388 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 389 |
+
"acc": 0.4716312056737589,
|
| 390 |
+
"acc_stderr": 0.029779450957303062,
|
| 391 |
+
"acc_norm": 0.4716312056737589,
|
| 392 |
+
"acc_norm_stderr": 0.029779450957303062
|
| 393 |
+
},
|
| 394 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 395 |
+
"acc": 0.4498044328552803,
|
| 396 |
+
"acc_stderr": 0.012705721498565107,
|
| 397 |
+
"acc_norm": 0.4498044328552803,
|
| 398 |
+
"acc_norm_stderr": 0.012705721498565107
|
| 399 |
+
},
|
| 400 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 401 |
+
"acc": 0.6580882352941176,
|
| 402 |
+
"acc_stderr": 0.02881472242225418,
|
| 403 |
+
"acc_norm": 0.6580882352941176,
|
| 404 |
+
"acc_norm_stderr": 0.02881472242225418
|
| 405 |
+
},
|
| 406 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 407 |
+
"acc": 0.6519607843137255,
|
| 408 |
+
"acc_stderr": 0.019270998708223974,
|
| 409 |
+
"acc_norm": 0.6519607843137255,
|
| 410 |
+
"acc_norm_stderr": 0.019270998708223974
|
| 411 |
+
},
|
| 412 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 413 |
+
"acc": 0.6636363636363637,
|
| 414 |
+
"acc_stderr": 0.04525393596302506,
|
| 415 |
+
"acc_norm": 0.6636363636363637,
|
| 416 |
+
"acc_norm_stderr": 0.04525393596302506
|
| 417 |
+
},
|
| 418 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 419 |
+
"acc": 0.7224489795918367,
|
| 420 |
+
"acc_stderr": 0.028666857790274645,
|
| 421 |
+
"acc_norm": 0.7224489795918367,
|
| 422 |
+
"acc_norm_stderr": 0.028666857790274645
|
| 423 |
+
},
|
| 424 |
+
"harness|hendrycksTest-sociology|5": {
|
| 425 |
+
"acc": 0.8557213930348259,
|
| 426 |
+
"acc_stderr": 0.02484575321230604,
|
| 427 |
+
"acc_norm": 0.8557213930348259,
|
| 428 |
+
"acc_norm_stderr": 0.02484575321230604
|
| 429 |
+
},
|
| 430 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 431 |
+
"acc": 0.86,
|
| 432 |
+
"acc_stderr": 0.03487350880197771,
|
| 433 |
+
"acc_norm": 0.86,
|
| 434 |
+
"acc_norm_stderr": 0.03487350880197771
|
| 435 |
+
},
|
| 436 |
+
"harness|hendrycksTest-virology|5": {
|
| 437 |
+
"acc": 0.5481927710843374,
|
| 438 |
+
"acc_stderr": 0.03874371556587953,
|
| 439 |
+
"acc_norm": 0.5481927710843374,
|
| 440 |
+
"acc_norm_stderr": 0.03874371556587953
|
| 441 |
+
},
|
| 442 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 443 |
+
"acc": 0.8421052631578947,
|
| 444 |
+
"acc_stderr": 0.027966785859160896,
|
| 445 |
+
"acc_norm": 0.8421052631578947,
|
| 446 |
+
"acc_norm_stderr": 0.027966785859160896
|
| 447 |
+
},
|
| 448 |
+
"harness|truthfulqa:mc|0": {
|
| 449 |
+
"mc1": 0.29008567931456547,
|
| 450 |
+
"mc1_stderr": 0.01588623687420952,
|
| 451 |
+
"mc2": 0.41501661742948026,
|
| 452 |
+
"mc2_stderr": 0.014285902986671931
|
| 453 |
+
},
|
| 454 |
+
"harness|winogrande|5": {
|
| 455 |
+
"acc": 0.7734806629834254,
|
| 456 |
+
"acc_stderr": 0.011764149054698332
|
| 457 |
+
},
|
| 458 |
+
"harness|gsm8k|5": {
|
| 459 |
+
"acc": 0.37452615617892343,
|
| 460 |
+
"acc_stderr": 0.013331774158491393
|
| 461 |
+
}
|
| 462 |
+
}
|
| 463 |
```
|