Isaak Carter Augustus
commited on
Commit
•
0caf7af
1
Parent(s):
f6673f4
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,391 @@ parameters:
|
|
| 38 |
dtype: bfloat16
|
| 39 |
```
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
## 💻 Usage
|
| 42 |
|
| 43 |
```python
|
|
|
|
| 38 |
dtype: bfloat16
|
| 39 |
```
|
| 40 |
|
| 41 |
+
## Evaluation
|
| 42 |
+
|
| 43 |
+
```json
|
| 44 |
+
{
|
| 45 |
+
"all": {
|
| 46 |
+
"acc": 0.6312165296664113,
|
| 47 |
+
"acc_stderr": 0.03236370559394293,
|
| 48 |
+
"acc_norm": 0.6324439925872714,
|
| 49 |
+
"acc_norm_stderr": 0.033019786616359854,
|
| 50 |
+
"mc1": 0.39657282741738065,
|
| 51 |
+
"mc1_stderr": 0.017124930942023518,
|
| 52 |
+
"mc2": 0.5688038233837539,
|
| 53 |
+
"mc2_stderr": 0.015263125204118244
|
| 54 |
+
},
|
| 55 |
+
"harness|arc:challenge|25": {
|
| 56 |
+
"acc": 0.6126279863481229,
|
| 57 |
+
"acc_stderr": 0.014235872487909869,
|
| 58 |
+
"acc_norm": 0.6348122866894198,
|
| 59 |
+
"acc_norm_stderr": 0.014070265519268802
|
| 60 |
+
},
|
| 61 |
+
"harness|hellaswag|10": {
|
| 62 |
+
"acc": 0.643397729535949,
|
| 63 |
+
"acc_stderr": 0.00478016987333285,
|
| 64 |
+
"acc_norm": 0.8378809002190799,
|
| 65 |
+
"acc_norm_stderr": 0.0036780679944244735
|
| 66 |
+
},
|
| 67 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 68 |
+
"acc": 0.32,
|
| 69 |
+
"acc_stderr": 0.046882617226215034,
|
| 70 |
+
"acc_norm": 0.32,
|
| 71 |
+
"acc_norm_stderr": 0.046882617226215034
|
| 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": 0.6907894736842105,
|
| 81 |
+
"acc_stderr": 0.037610708698674805,
|
| 82 |
+
"acc_norm": 0.6907894736842105,
|
| 83 |
+
"acc_norm_stderr": 0.037610708698674805
|
| 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": 0.6754716981132075,
|
| 93 |
+
"acc_stderr": 0.02881561571343211,
|
| 94 |
+
"acc_norm": 0.6754716981132075,
|
| 95 |
+
"acc_norm_stderr": 0.02881561571343211
|
| 96 |
+
},
|
| 97 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 98 |
+
"acc": 0.7291666666666666,
|
| 99 |
+
"acc_stderr": 0.03716177437566017,
|
| 100 |
+
"acc_norm": 0.7291666666666666,
|
| 101 |
+
"acc_norm_stderr": 0.03716177437566017
|
| 102 |
+
},
|
| 103 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 104 |
+
"acc": 0.47,
|
| 105 |
+
"acc_stderr": 0.05016135580465919,
|
| 106 |
+
"acc_norm": 0.47,
|
| 107 |
+
"acc_norm_stderr": 0.05016135580465919
|
| 108 |
+
},
|
| 109 |
+
"harness|hendrycksTest-college_computer_science|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_mathematics|5": {
|
| 116 |
+
"acc": 0.34,
|
| 117 |
+
"acc_stderr": 0.04760952285695235,
|
| 118 |
+
"acc_norm": 0.34,
|
| 119 |
+
"acc_norm_stderr": 0.04760952285695235
|
| 120 |
+
},
|
| 121 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 122 |
+
"acc": 0.6011560693641619,
|
| 123 |
+
"acc_stderr": 0.037336266553835096,
|
| 124 |
+
"acc_norm": 0.6011560693641619,
|
| 125 |
+
"acc_norm_stderr": 0.037336266553835096
|
| 126 |
+
},
|
| 127 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 128 |
+
"acc": 0.29411764705882354,
|
| 129 |
+
"acc_stderr": 0.04533838195929775,
|
| 130 |
+
"acc_norm": 0.29411764705882354,
|
| 131 |
+
"acc_norm_stderr": 0.04533838195929775
|
| 132 |
+
},
|
| 133 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 134 |
+
"acc": 0.72,
|
| 135 |
+
"acc_stderr": 0.045126085985421276,
|
| 136 |
+
"acc_norm": 0.72,
|
| 137 |
+
"acc_norm_stderr": 0.045126085985421276
|
| 138 |
+
},
|
| 139 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 140 |
+
"acc": 0.5659574468085107,
|
| 141 |
+
"acc_stderr": 0.03240038086792747,
|
| 142 |
+
"acc_norm": 0.5659574468085107,
|
| 143 |
+
"acc_norm_stderr": 0.03240038086792747
|
| 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": 0.4021164021164021,
|
| 159 |
+
"acc_stderr": 0.02525303255499769,
|
| 160 |
+
"acc_norm": 0.4021164021164021,
|
| 161 |
+
"acc_norm_stderr": 0.02525303255499769
|
| 162 |
+
},
|
| 163 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 164 |
+
"acc": 0.42063492063492064,
|
| 165 |
+
"acc_stderr": 0.04415438226743744,
|
| 166 |
+
"acc_norm": 0.42063492063492064,
|
| 167 |
+
"acc_norm_stderr": 0.04415438226743744
|
| 168 |
+
},
|
| 169 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 170 |
+
"acc": 0.39,
|
| 171 |
+
"acc_stderr": 0.04902071300001975,
|
| 172 |
+
"acc_norm": 0.39,
|
| 173 |
+
"acc_norm_stderr": 0.04902071300001975
|
| 174 |
+
},
|
| 175 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 176 |
+
"acc": 0.7774193548387097,
|
| 177 |
+
"acc_stderr": 0.02366421667164251,
|
| 178 |
+
"acc_norm": 0.7774193548387097,
|
| 179 |
+
"acc_norm_stderr": 0.02366421667164251
|
| 180 |
+
},
|
| 181 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 182 |
+
"acc": 0.4876847290640394,
|
| 183 |
+
"acc_stderr": 0.035169204442208966,
|
| 184 |
+
"acc_norm": 0.4876847290640394,
|
| 185 |
+
"acc_norm_stderr": 0.035169204442208966
|
| 186 |
+
},
|
| 187 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 188 |
+
"acc": 0.68,
|
| 189 |
+
"acc_stderr": 0.04688261722621505,
|
| 190 |
+
"acc_norm": 0.68,
|
| 191 |
+
"acc_norm_stderr": 0.04688261722621505
|
| 192 |
+
},
|
| 193 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 194 |
+
"acc": 0.7818181818181819,
|
| 195 |
+
"acc_stderr": 0.03225078108306289,
|
| 196 |
+
"acc_norm": 0.7818181818181819,
|
| 197 |
+
"acc_norm_stderr": 0.03225078108306289
|
| 198 |
+
},
|
| 199 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 200 |
+
"acc": 0.803030303030303,
|
| 201 |
+
"acc_stderr": 0.02833560973246336,
|
| 202 |
+
"acc_norm": 0.803030303030303,
|
| 203 |
+
"acc_norm_stderr": 0.02833560973246336
|
| 204 |
+
},
|
| 205 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 206 |
+
"acc": 0.8549222797927462,
|
| 207 |
+
"acc_stderr": 0.025416343096306433,
|
| 208 |
+
"acc_norm": 0.8549222797927462,
|
| 209 |
+
"acc_norm_stderr": 0.025416343096306433
|
| 210 |
+
},
|
| 211 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 212 |
+
"acc": 0.6435897435897436,
|
| 213 |
+
"acc_stderr": 0.02428314052946731,
|
| 214 |
+
"acc_norm": 0.6435897435897436,
|
| 215 |
+
"acc_norm_stderr": 0.02428314052946731
|
| 216 |
+
},
|
| 217 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 218 |
+
"acc": 0.32592592592592595,
|
| 219 |
+
"acc_stderr": 0.028578348365473072,
|
| 220 |
+
"acc_norm": 0.32592592592592595,
|
| 221 |
+
"acc_norm_stderr": 0.028578348365473072
|
| 222 |
+
},
|
| 223 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 224 |
+
"acc": 0.6638655462184874,
|
| 225 |
+
"acc_stderr": 0.030684737115135367,
|
| 226 |
+
"acc_norm": 0.6638655462184874,
|
| 227 |
+
"acc_norm_stderr": 0.030684737115135367
|
| 228 |
+
},
|
| 229 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 230 |
+
"acc": 0.31788079470198677,
|
| 231 |
+
"acc_stderr": 0.038020397601079024,
|
| 232 |
+
"acc_norm": 0.31788079470198677,
|
| 233 |
+
"acc_norm_stderr": 0.038020397601079024
|
| 234 |
+
},
|
| 235 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 236 |
+
"acc": 0.8220183486238533,
|
| 237 |
+
"acc_stderr": 0.01639943636661289,
|
| 238 |
+
"acc_norm": 0.8220183486238533,
|
| 239 |
+
"acc_norm_stderr": 0.01639943636661289
|
| 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": 0.803921568627451,
|
| 249 |
+
"acc_stderr": 0.027865942286639318,
|
| 250 |
+
"acc_norm": 0.803921568627451,
|
| 251 |
+
"acc_norm_stderr": 0.027865942286639318
|
| 252 |
+
},
|
| 253 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 254 |
+
"acc": 0.7974683544303798,
|
| 255 |
+
"acc_stderr": 0.026160568246601453,
|
| 256 |
+
"acc_norm": 0.7974683544303798,
|
| 257 |
+
"acc_norm_stderr": 0.026160568246601453
|
| 258 |
+
},
|
| 259 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 260 |
+
"acc": 0.6995515695067265,
|
| 261 |
+
"acc_stderr": 0.03076935200822914,
|
| 262 |
+
"acc_norm": 0.6995515695067265,
|
| 263 |
+
"acc_norm_stderr": 0.03076935200822914
|
| 264 |
+
},
|
| 265 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 266 |
+
"acc": 0.7480916030534351,
|
| 267 |
+
"acc_stderr": 0.03807387116306085,
|
| 268 |
+
"acc_norm": 0.7480916030534351,
|
| 269 |
+
"acc_norm_stderr": 0.03807387116306085
|
| 270 |
+
},
|
| 271 |
+
"harness|hendrycksTest-international_law|5": {
|
| 272 |
+
"acc": 0.8016528925619835,
|
| 273 |
+
"acc_stderr": 0.036401182719909456,
|
| 274 |
+
"acc_norm": 0.8016528925619835,
|
| 275 |
+
"acc_norm_stderr": 0.036401182719909456
|
| 276 |
+
},
|
| 277 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 278 |
+
"acc": 0.8055555555555556,
|
| 279 |
+
"acc_stderr": 0.038260763248848646,
|
| 280 |
+
"acc_norm": 0.8055555555555556,
|
| 281 |
+
"acc_norm_stderr": 0.038260763248848646
|
| 282 |
+
},
|
| 283 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 284 |
+
"acc": 0.754601226993865,
|
| 285 |
+
"acc_stderr": 0.03380939813943354,
|
| 286 |
+
"acc_norm": 0.754601226993865,
|
| 287 |
+
"acc_norm_stderr": 0.03380939813943354
|
| 288 |
+
},
|
| 289 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 290 |
+
"acc": 0.44642857142857145,
|
| 291 |
+
"acc_stderr": 0.04718471485219588,
|
| 292 |
+
"acc_norm": 0.44642857142857145,
|
| 293 |
+
"acc_norm_stderr": 0.04718471485219588
|
| 294 |
+
},
|
| 295 |
+
"harness|hendrycksTest-management|5": {
|
| 296 |
+
"acc": 0.7961165048543689,
|
| 297 |
+
"acc_stderr": 0.039891398595317706,
|
| 298 |
+
"acc_norm": 0.7961165048543689,
|
| 299 |
+
"acc_norm_stderr": 0.039891398595317706
|
| 300 |
+
},
|
| 301 |
+
"harness|hendrycksTest-marketing|5": {
|
| 302 |
+
"acc": 0.8589743589743589,
|
| 303 |
+
"acc_stderr": 0.02280138253459754,
|
| 304 |
+
"acc_norm": 0.8589743589743589,
|
| 305 |
+
"acc_norm_stderr": 0.02280138253459754
|
| 306 |
+
},
|
| 307 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 308 |
+
"acc": 0.73,
|
| 309 |
+
"acc_stderr": 0.044619604333847394,
|
| 310 |
+
"acc_norm": 0.73,
|
| 311 |
+
"acc_norm_stderr": 0.044619604333847394
|
| 312 |
+
},
|
| 313 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 314 |
+
"acc": 0.8084291187739464,
|
| 315 |
+
"acc_stderr": 0.014072859310451949,
|
| 316 |
+
"acc_norm": 0.8084291187739464,
|
| 317 |
+
"acc_norm_stderr": 0.014072859310451949
|
| 318 |
+
},
|
| 319 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 320 |
+
"acc": 0.7312138728323699,
|
| 321 |
+
"acc_stderr": 0.023868003262500104,
|
| 322 |
+
"acc_norm": 0.7312138728323699,
|
| 323 |
+
"acc_norm_stderr": 0.023868003262500104
|
| 324 |
+
},
|
| 325 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 326 |
+
"acc": 0.24916201117318434,
|
| 327 |
+
"acc_stderr": 0.014465893829859924,
|
| 328 |
+
"acc_norm": 0.24916201117318434,
|
| 329 |
+
"acc_norm_stderr": 0.014465893829859924
|
| 330 |
+
},
|
| 331 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 332 |
+
"acc": 0.7124183006535948,
|
| 333 |
+
"acc_stderr": 0.02591780611714716,
|
| 334 |
+
"acc_norm": 0.7124183006535948,
|
| 335 |
+
"acc_norm_stderr": 0.02591780611714716
|
| 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": 0.6975308641975309,
|
| 345 |
+
"acc_stderr": 0.02555765398186806,
|
| 346 |
+
"acc_norm": 0.6975308641975309,
|
| 347 |
+
"acc_norm_stderr": 0.02555765398186806
|
| 348 |
+
},
|
| 349 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 350 |
+
"acc": 0.49645390070921985,
|
| 351 |
+
"acc_stderr": 0.02982674915328092,
|
| 352 |
+
"acc_norm": 0.49645390070921985,
|
| 353 |
+
"acc_norm_stderr": 0.02982674915328092
|
| 354 |
+
},
|
| 355 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 356 |
+
"acc": 0.4745762711864407,
|
| 357 |
+
"acc_stderr": 0.01275371692910101,
|
| 358 |
+
"acc_norm": 0.4745762711864407,
|
| 359 |
+
"acc_norm_stderr": 0.01275371692910101
|
| 360 |
+
},
|
| 361 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 362 |
+
"acc": 0.6507352941176471,
|
| 363 |
+
"acc_stderr": 0.028959755196824862,
|
| 364 |
+
"acc_norm": 0.6507352941176471,
|
| 365 |
+
"acc_norm_stderr": 0.028959755196824862
|
| 366 |
+
},
|
| 367 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 368 |
+
"acc": 0.6323529411764706,
|
| 369 |
+
"acc_stderr": 0.019506291693954843,
|
| 370 |
+
"acc_norm": 0.6323529411764706,
|
| 371 |
+
"acc_norm_stderr": 0.019506291693954843
|
| 372 |
+
},
|
| 373 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 374 |
+
"acc": 0.6363636363636364,
|
| 375 |
+
"acc_stderr": 0.046075820907199756,
|
| 376 |
+
"acc_norm": 0.6363636363636364,
|
| 377 |
+
"acc_norm_stderr": 0.046075820907199756
|
| 378 |
+
},
|
| 379 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 380 |
+
"acc": 0.7183673469387755,
|
| 381 |
+
"acc_stderr": 0.028795185574291293,
|
| 382 |
+
"acc_norm": 0.7183673469387755,
|
| 383 |
+
"acc_norm_stderr": 0.028795185574291293
|
| 384 |
+
},
|
| 385 |
+
"harness|hendrycksTest-sociology|5": {
|
| 386 |
+
"acc": 0.835820895522388,
|
| 387 |
+
"acc_stderr": 0.026193923544454125,
|
| 388 |
+
"acc_norm": 0.835820895522388,
|
| 389 |
+
"acc_norm_stderr": 0.026193923544454125
|
| 390 |
+
},
|
| 391 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 392 |
+
"acc": 0.87,
|
| 393 |
+
"acc_stderr": 0.033799766898963086,
|
| 394 |
+
"acc_norm": 0.87,
|
| 395 |
+
"acc_norm_stderr": 0.033799766898963086
|
| 396 |
+
},
|
| 397 |
+
"harness|hendrycksTest-virology|5": {
|
| 398 |
+
"acc": 0.5180722891566265,
|
| 399 |
+
"acc_stderr": 0.03889951252827216,
|
| 400 |
+
"acc_norm": 0.5180722891566265,
|
| 401 |
+
"acc_norm_stderr": 0.03889951252827216
|
| 402 |
+
},
|
| 403 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 404 |
+
"acc": 0.8187134502923976,
|
| 405 |
+
"acc_stderr": 0.029547741687640038,
|
| 406 |
+
"acc_norm": 0.8187134502923976,
|
| 407 |
+
"acc_norm_stderr": 0.029547741687640038
|
| 408 |
+
},
|
| 409 |
+
"harness|truthfulqa:mc|0": {
|
| 410 |
+
"mc1": 0.39657282741738065,
|
| 411 |
+
"mc1_stderr": 0.017124930942023518,
|
| 412 |
+
"mc2": 0.5688038233837539,
|
| 413 |
+
"mc2_stderr": 0.015263125204118244
|
| 414 |
+
},
|
| 415 |
+
"harness|winogrande|5": {
|
| 416 |
+
"acc": 0.7963693764798737,
|
| 417 |
+
"acc_stderr": 0.011317798781626918
|
| 418 |
+
},
|
| 419 |
+
"harness|gsm8k|5": {
|
| 420 |
+
"acc": 0.6103108415466262,
|
| 421 |
+
"acc_stderr": 0.01343312323611072
|
| 422 |
+
}
|
| 423 |
+
}
|
| 424 |
+
```
|
| 425 |
+
|
| 426 |
## 💻 Usage
|
| 427 |
|
| 428 |
```python
|