Update README.md
Browse files
README.md
CHANGED
|
@@ -31,4 +31,393 @@ parameters:
|
|
| 31 |
normalize: true
|
| 32 |
dtype: bfloat16
|
| 33 |
|
| 34 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
normalize: true
|
| 32 |
dtype: bfloat16
|
| 33 |
|
| 34 |
+
```
|
| 35 |
+
## Evaluation
|
| 36 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-ties
|
| 37 |
+
|
| 38 |
+
Latest Result:
|
| 39 |
+
https://huggingface.co/datasets/open-llm-leaderboard/details_mychen76__mistral-7b-merged-ties/blob/main/results_2024-03-10T11-05-18.535141.json
|
| 40 |
+
|
| 41 |
+
```
|
| 42 |
+
{
|
| 43 |
+
"all": {
|
| 44 |
+
"acc": 0.6445924072176131,
|
| 45 |
+
"acc_stderr": 0.03213293328697562,
|
| 46 |
+
"acc_norm": 0.6450342620069291,
|
| 47 |
+
"acc_norm_stderr": 0.032788565108750604,
|
| 48 |
+
"mc1": 0.4455324357405141,
|
| 49 |
+
"mc1_stderr": 0.017399335280140357,
|
| 50 |
+
"mc2": 0.6131109579182783,
|
| 51 |
+
"mc2_stderr": 0.015351738756398125
|
| 52 |
+
},
|
| 53 |
+
"harness|arc:challenge|25": {
|
| 54 |
+
"acc": 0.6390784982935154,
|
| 55 |
+
"acc_stderr": 0.014034761386175452,
|
| 56 |
+
"acc_norm": 0.6791808873720137,
|
| 57 |
+
"acc_norm_stderr": 0.013640943091946531
|
| 58 |
+
},
|
| 59 |
+
"harness|hellaswag|10": {
|
| 60 |
+
"acc": 0.6722764389563832,
|
| 61 |
+
"acc_stderr": 0.004684241685200317,
|
| 62 |
+
"acc_norm": 0.85929097789285,
|
| 63 |
+
"acc_norm_stderr": 0.00347010499020439
|
| 64 |
+
},
|
| 65 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 66 |
+
"acc": 0.28,
|
| 67 |
+
"acc_stderr": 0.04512608598542128,
|
| 68 |
+
"acc_norm": 0.28,
|
| 69 |
+
"acc_norm_stderr": 0.04512608598542128
|
| 70 |
+
},
|
| 71 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 72 |
+
"acc": 0.6074074074074074,
|
| 73 |
+
"acc_stderr": 0.0421850621536888,
|
| 74 |
+
"acc_norm": 0.6074074074074074,
|
| 75 |
+
"acc_norm_stderr": 0.0421850621536888
|
| 76 |
+
},
|
| 77 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 78 |
+
"acc": 0.743421052631579,
|
| 79 |
+
"acc_stderr": 0.0355418036802569,
|
| 80 |
+
"acc_norm": 0.743421052631579,
|
| 81 |
+
"acc_norm_stderr": 0.0355418036802569
|
| 82 |
+
},
|
| 83 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 84 |
+
"acc": 0.61,
|
| 85 |
+
"acc_stderr": 0.04902071300001975,
|
| 86 |
+
"acc_norm": 0.61,
|
| 87 |
+
"acc_norm_stderr": 0.04902071300001975
|
| 88 |
+
},
|
| 89 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 90 |
+
"acc": 0.6867924528301886,
|
| 91 |
+
"acc_stderr": 0.028544793319055326,
|
| 92 |
+
"acc_norm": 0.6867924528301886,
|
| 93 |
+
"acc_norm_stderr": 0.028544793319055326
|
| 94 |
+
},
|
| 95 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 96 |
+
"acc": 0.7777777777777778,
|
| 97 |
+
"acc_stderr": 0.03476590104304134,
|
| 98 |
+
"acc_norm": 0.7777777777777778,
|
| 99 |
+
"acc_norm_stderr": 0.03476590104304134
|
| 100 |
+
},
|
| 101 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 102 |
+
"acc": 0.48,
|
| 103 |
+
"acc_stderr": 0.050211673156867795,
|
| 104 |
+
"acc_norm": 0.48,
|
| 105 |
+
"acc_norm_stderr": 0.050211673156867795
|
| 106 |
+
},
|
| 107 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 108 |
+
"acc": 0.48,
|
| 109 |
+
"acc_stderr": 0.050211673156867795,
|
| 110 |
+
"acc_norm": 0.48,
|
| 111 |
+
"acc_norm_stderr": 0.050211673156867795
|
| 112 |
+
},
|
| 113 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 114 |
+
"acc": 0.32,
|
| 115 |
+
"acc_stderr": 0.04688261722621504,
|
| 116 |
+
"acc_norm": 0.32,
|
| 117 |
+
"acc_norm_stderr": 0.04688261722621504
|
| 118 |
+
},
|
| 119 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 120 |
+
"acc": 0.630057803468208,
|
| 121 |
+
"acc_stderr": 0.036812296333943194,
|
| 122 |
+
"acc_norm": 0.630057803468208,
|
| 123 |
+
"acc_norm_stderr": 0.036812296333943194
|
| 124 |
+
},
|
| 125 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 126 |
+
"acc": 0.4117647058823529,
|
| 127 |
+
"acc_stderr": 0.048971049527263666,
|
| 128 |
+
"acc_norm": 0.4117647058823529,
|
| 129 |
+
"acc_norm_stderr": 0.048971049527263666
|
| 130 |
+
},
|
| 131 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 132 |
+
"acc": 0.76,
|
| 133 |
+
"acc_stderr": 0.042923469599092816,
|
| 134 |
+
"acc_norm": 0.76,
|
| 135 |
+
"acc_norm_stderr": 0.042923469599092816
|
| 136 |
+
},
|
| 137 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 138 |
+
"acc": 0.574468085106383,
|
| 139 |
+
"acc_stderr": 0.03232146916224468,
|
| 140 |
+
"acc_norm": 0.574468085106383,
|
| 141 |
+
"acc_norm_stderr": 0.03232146916224468
|
| 142 |
+
},
|
| 143 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 144 |
+
"acc": 0.5175438596491229,
|
| 145 |
+
"acc_stderr": 0.04700708033551038,
|
| 146 |
+
"acc_norm": 0.5175438596491229,
|
| 147 |
+
"acc_norm_stderr": 0.04700708033551038
|
| 148 |
+
},
|
| 149 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 150 |
+
"acc": 0.5448275862068965,
|
| 151 |
+
"acc_stderr": 0.04149886942192117,
|
| 152 |
+
"acc_norm": 0.5448275862068965,
|
| 153 |
+
"acc_norm_stderr": 0.04149886942192117
|
| 154 |
+
},
|
| 155 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 156 |
+
"acc": 0.4126984126984127,
|
| 157 |
+
"acc_stderr": 0.025355741263055263,
|
| 158 |
+
"acc_norm": 0.4126984126984127,
|
| 159 |
+
"acc_norm_stderr": 0.025355741263055263
|
| 160 |
+
},
|
| 161 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 162 |
+
"acc": 0.4365079365079365,
|
| 163 |
+
"acc_stderr": 0.04435932892851466,
|
| 164 |
+
"acc_norm": 0.4365079365079365,
|
| 165 |
+
"acc_norm_stderr": 0.04435932892851466
|
| 166 |
+
},
|
| 167 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 168 |
+
"acc": 0.35,
|
| 169 |
+
"acc_stderr": 0.047937248544110196,
|
| 170 |
+
"acc_norm": 0.35,
|
| 171 |
+
"acc_norm_stderr": 0.047937248544110196
|
| 172 |
+
},
|
| 173 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 174 |
+
"acc": 0.7645161290322581,
|
| 175 |
+
"acc_stderr": 0.02413763242933771,
|
| 176 |
+
"acc_norm": 0.7645161290322581,
|
| 177 |
+
"acc_norm_stderr": 0.02413763242933771
|
| 178 |
+
},
|
| 179 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 180 |
+
"acc": 0.49261083743842365,
|
| 181 |
+
"acc_stderr": 0.035176035403610084,
|
| 182 |
+
"acc_norm": 0.49261083743842365,
|
| 183 |
+
"acc_norm_stderr": 0.035176035403610084
|
| 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": 0.7757575757575758,
|
| 193 |
+
"acc_stderr": 0.03256866661681102,
|
| 194 |
+
"acc_norm": 0.7757575757575758,
|
| 195 |
+
"acc_norm_stderr": 0.03256866661681102
|
| 196 |
+
},
|
| 197 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 198 |
+
"acc": 0.7828282828282829,
|
| 199 |
+
"acc_stderr": 0.02937661648494563,
|
| 200 |
+
"acc_norm": 0.7828282828282829,
|
| 201 |
+
"acc_norm_stderr": 0.02937661648494563
|
| 202 |
+
},
|
| 203 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 204 |
+
"acc": 0.8963730569948186,
|
| 205 |
+
"acc_stderr": 0.02199531196364424,
|
| 206 |
+
"acc_norm": 0.8963730569948186,
|
| 207 |
+
"acc_norm_stderr": 0.02199531196364424
|
| 208 |
+
},
|
| 209 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 210 |
+
"acc": 0.6410256410256411,
|
| 211 |
+
"acc_stderr": 0.024321738484602354,
|
| 212 |
+
"acc_norm": 0.6410256410256411,
|
| 213 |
+
"acc_norm_stderr": 0.024321738484602354
|
| 214 |
+
},
|
| 215 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 216 |
+
"acc": 0.34814814814814815,
|
| 217 |
+
"acc_stderr": 0.029045600290616255,
|
| 218 |
+
"acc_norm": 0.34814814814814815,
|
| 219 |
+
"acc_norm_stderr": 0.029045600290616255
|
| 220 |
+
},
|
| 221 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 222 |
+
"acc": 0.6890756302521008,
|
| 223 |
+
"acc_stderr": 0.03006676158297793,
|
| 224 |
+
"acc_norm": 0.6890756302521008,
|
| 225 |
+
"acc_norm_stderr": 0.03006676158297793
|
| 226 |
+
},
|
| 227 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 228 |
+
"acc": 0.2980132450331126,
|
| 229 |
+
"acc_stderr": 0.037345356767871984,
|
| 230 |
+
"acc_norm": 0.2980132450331126,
|
| 231 |
+
"acc_norm_stderr": 0.037345356767871984
|
| 232 |
+
},
|
| 233 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 234 |
+
"acc": 0.8495412844036697,
|
| 235 |
+
"acc_stderr": 0.015328563932669237,
|
| 236 |
+
"acc_norm": 0.8495412844036697,
|
| 237 |
+
"acc_norm_stderr": 0.015328563932669237
|
| 238 |
+
},
|
| 239 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 240 |
+
"acc": 0.5231481481481481,
|
| 241 |
+
"acc_stderr": 0.03406315360711507,
|
| 242 |
+
"acc_norm": 0.5231481481481481,
|
| 243 |
+
"acc_norm_stderr": 0.03406315360711507
|
| 244 |
+
},
|
| 245 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 246 |
+
"acc": 0.8186274509803921,
|
| 247 |
+
"acc_stderr": 0.027044621719474086,
|
| 248 |
+
"acc_norm": 0.8186274509803921,
|
| 249 |
+
"acc_norm_stderr": 0.027044621719474086
|
| 250 |
+
},
|
| 251 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 252 |
+
"acc": 0.8185654008438819,
|
| 253 |
+
"acc_stderr": 0.025085961144579665,
|
| 254 |
+
"acc_norm": 0.8185654008438819,
|
| 255 |
+
"acc_norm_stderr": 0.025085961144579665
|
| 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": 0.7862595419847328,
|
| 265 |
+
"acc_stderr": 0.0359546161177469,
|
| 266 |
+
"acc_norm": 0.7862595419847328,
|
| 267 |
+
"acc_norm_stderr": 0.0359546161177469
|
| 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": 0.7962962962962963,
|
| 277 |
+
"acc_stderr": 0.03893542518824847,
|
| 278 |
+
"acc_norm": 0.7962962962962963,
|
| 279 |
+
"acc_norm_stderr": 0.03893542518824847
|
| 280 |
+
},
|
| 281 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 282 |
+
"acc": 0.7607361963190185,
|
| 283 |
+
"acc_stderr": 0.033519538795212696,
|
| 284 |
+
"acc_norm": 0.7607361963190185,
|
| 285 |
+
"acc_norm_stderr": 0.033519538795212696
|
| 286 |
+
},
|
| 287 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 288 |
+
"acc": 0.4642857142857143,
|
| 289 |
+
"acc_stderr": 0.04733667890053756,
|
| 290 |
+
"acc_norm": 0.4642857142857143,
|
| 291 |
+
"acc_norm_stderr": 0.04733667890053756
|
| 292 |
+
},
|
| 293 |
+
"harness|hendrycksTest-management|5": {
|
| 294 |
+
"acc": 0.7766990291262136,
|
| 295 |
+
"acc_stderr": 0.04123553189891431,
|
| 296 |
+
"acc_norm": 0.7766990291262136,
|
| 297 |
+
"acc_norm_stderr": 0.04123553189891431
|
| 298 |
+
},
|
| 299 |
+
"harness|hendrycksTest-marketing|5": {
|
| 300 |
+
"acc": 0.8547008547008547,
|
| 301 |
+
"acc_stderr": 0.023086635086841407,
|
| 302 |
+
"acc_norm": 0.8547008547008547,
|
| 303 |
+
"acc_norm_stderr": 0.023086635086841407
|
| 304 |
+
},
|
| 305 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 306 |
+
"acc": 0.71,
|
| 307 |
+
"acc_stderr": 0.045604802157206845,
|
| 308 |
+
"acc_norm": 0.71,
|
| 309 |
+
"acc_norm_stderr": 0.045604802157206845
|
| 310 |
+
},
|
| 311 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 312 |
+
"acc": 0.8301404853128991,
|
| 313 |
+
"acc_stderr": 0.013428186370608304,
|
| 314 |
+
"acc_norm": 0.8301404853128991,
|
| 315 |
+
"acc_norm_stderr": 0.013428186370608304
|
| 316 |
+
},
|
| 317 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 318 |
+
"acc": 0.7369942196531792,
|
| 319 |
+
"acc_stderr": 0.023703099525258172,
|
| 320 |
+
"acc_norm": 0.7369942196531792,
|
| 321 |
+
"acc_norm_stderr": 0.023703099525258172
|
| 322 |
+
},
|
| 323 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 324 |
+
"acc": 0.3664804469273743,
|
| 325 |
+
"acc_stderr": 0.016115235504865467,
|
| 326 |
+
"acc_norm": 0.3664804469273743,
|
| 327 |
+
"acc_norm_stderr": 0.016115235504865467
|
| 328 |
+
},
|
| 329 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 330 |
+
"acc": 0.7320261437908496,
|
| 331 |
+
"acc_stderr": 0.025360603796242553,
|
| 332 |
+
"acc_norm": 0.7320261437908496,
|
| 333 |
+
"acc_norm_stderr": 0.025360603796242553
|
| 334 |
+
},
|
| 335 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 336 |
+
"acc": 0.7170418006430869,
|
| 337 |
+
"acc_stderr": 0.02558306248998481,
|
| 338 |
+
"acc_norm": 0.7170418006430869,
|
| 339 |
+
"acc_norm_stderr": 0.02558306248998481
|
| 340 |
+
},
|
| 341 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 342 |
+
"acc": 0.7376543209876543,
|
| 343 |
+
"acc_stderr": 0.024477222856135114,
|
| 344 |
+
"acc_norm": 0.7376543209876543,
|
| 345 |
+
"acc_norm_stderr": 0.024477222856135114
|
| 346 |
+
},
|
| 347 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 348 |
+
"acc": 0.5070921985815603,
|
| 349 |
+
"acc_stderr": 0.02982449855912901,
|
| 350 |
+
"acc_norm": 0.5070921985815603,
|
| 351 |
+
"acc_norm_stderr": 0.02982449855912901
|
| 352 |
+
},
|
| 353 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 354 |
+
"acc": 0.4667535853976532,
|
| 355 |
+
"acc_stderr": 0.01274197433389723,
|
| 356 |
+
"acc_norm": 0.4667535853976532,
|
| 357 |
+
"acc_norm_stderr": 0.01274197433389723
|
| 358 |
+
},
|
| 359 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 360 |
+
"acc": 0.6764705882352942,
|
| 361 |
+
"acc_stderr": 0.02841820861940676,
|
| 362 |
+
"acc_norm": 0.6764705882352942,
|
| 363 |
+
"acc_norm_stderr": 0.02841820861940676
|
| 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": 0.6545454545454545,
|
| 373 |
+
"acc_stderr": 0.04554619617541054,
|
| 374 |
+
"acc_norm": 0.6545454545454545,
|
| 375 |
+
"acc_norm_stderr": 0.04554619617541054
|
| 376 |
+
},
|
| 377 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 378 |
+
"acc": 0.7306122448979592,
|
| 379 |
+
"acc_stderr": 0.02840125202902294,
|
| 380 |
+
"acc_norm": 0.7306122448979592,
|
| 381 |
+
"acc_norm_stderr": 0.02840125202902294
|
| 382 |
+
},
|
| 383 |
+
"harness|hendrycksTest-sociology|5": {
|
| 384 |
+
"acc": 0.845771144278607,
|
| 385 |
+
"acc_stderr": 0.025538433368578337,
|
| 386 |
+
"acc_norm": 0.845771144278607,
|
| 387 |
+
"acc_norm_stderr": 0.025538433368578337
|
| 388 |
+
},
|
| 389 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 390 |
+
"acc": 0.86,
|
| 391 |
+
"acc_stderr": 0.0348735088019777,
|
| 392 |
+
"acc_norm": 0.86,
|
| 393 |
+
"acc_norm_stderr": 0.0348735088019777
|
| 394 |
+
},
|
| 395 |
+
"harness|hendrycksTest-virology|5": {
|
| 396 |
+
"acc": 0.5481927710843374,
|
| 397 |
+
"acc_stderr": 0.03874371556587953,
|
| 398 |
+
"acc_norm": 0.5481927710843374,
|
| 399 |
+
"acc_norm_stderr": 0.03874371556587953
|
| 400 |
+
},
|
| 401 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 402 |
+
"acc": 0.8304093567251462,
|
| 403 |
+
"acc_stderr": 0.02878210810540171,
|
| 404 |
+
"acc_norm": 0.8304093567251462,
|
| 405 |
+
"acc_norm_stderr": 0.02878210810540171
|
| 406 |
+
},
|
| 407 |
+
"harness|truthfulqa:mc|0": {
|
| 408 |
+
"mc1": 0.4455324357405141,
|
| 409 |
+
"mc1_stderr": 0.017399335280140357,
|
| 410 |
+
"mc2": 0.6131109579182783,
|
| 411 |
+
"mc2_stderr": 0.015351738756398125
|
| 412 |
+
},
|
| 413 |
+
"harness|winogrande|5": {
|
| 414 |
+
"acc": 0.8003157063930545,
|
| 415 |
+
"acc_stderr": 0.011235328382625842
|
| 416 |
+
},
|
| 417 |
+
"harness|gsm8k|5": {
|
| 418 |
+
"acc": 0.6899166034874905,
|
| 419 |
+
"acc_stderr": 0.01274030571737627
|
| 420 |
+
}
|
| 421 |
+
}
|
| 422 |
+
|
| 423 |
+
```
|