Isaak Carter Augustus
commited on
Commit
•
9281c64
1
Parent(s):
ce6ec12
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,394 @@ JOSIE_Beta-4-7B-slerp is a merge of the following models using [LazyMergekit](ht
|
|
| 17 |
* [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
|
| 18 |
* [cognitivecomputations/dolphin-2.8-experiment26-7b](https://huggingface.co/cognitivecomputations/dolphin-2.8-experiment26-7b)
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## 🧩 Configuration
|
| 21 |
|
| 22 |
```yaml
|
|
|
|
| 17 |
* [Weyaxi/Einstein-v4-7B](https://huggingface.co/Weyaxi/Einstein-v4-7B)
|
| 18 |
* [cognitivecomputations/dolphin-2.8-experiment26-7b](https://huggingface.co/cognitivecomputations/dolphin-2.8-experiment26-7b)
|
| 19 |
|
| 20 |
+
# IMPORTANT!!!
|
| 21 |
+
|
| 22 |
+
Upon seeing the eval results on the LLM Leaderboard, this is my second best performing model, the best one it beta 3.
|
| 23 |
+
|
| 24 |
+
```json
|
| 25 |
+
{
|
| 26 |
+
"all": {
|
| 27 |
+
"acc": 0.6395082113582112,
|
| 28 |
+
"acc_stderr": 0.0321581453772247,
|
| 29 |
+
"acc_norm": 0.6406802207782241,
|
| 30 |
+
"acc_norm_stderr": 0.032807499003593296,
|
| 31 |
+
"mc1": 0.379436964504284,
|
| 32 |
+
"mc1_stderr": 0.01698703926614299,
|
| 33 |
+
"mc2": 0.5593281467190233,
|
| 34 |
+
"mc2_stderr": 0.0156123862411416
|
| 35 |
+
},
|
| 36 |
+
"harness|arc:challenge|25": {
|
| 37 |
+
"acc": 0.6143344709897611,
|
| 38 |
+
"acc_stderr": 0.014224250973257182,
|
| 39 |
+
"acc_norm": 0.6356655290102389,
|
| 40 |
+
"acc_norm_stderr": 0.014063260279882419
|
| 41 |
+
},
|
| 42 |
+
"harness|hellaswag|10": {
|
| 43 |
+
"acc": 0.6618203545110536,
|
| 44 |
+
"acc_stderr": 0.004721231637092722,
|
| 45 |
+
"acc_norm": 0.8409679346743677,
|
| 46 |
+
"acc_norm_stderr": 0.0036495858528211842
|
| 47 |
+
},
|
| 48 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 49 |
+
"acc": 0.34,
|
| 50 |
+
"acc_stderr": 0.047609522856952365,
|
| 51 |
+
"acc_norm": 0.34,
|
| 52 |
+
"acc_norm_stderr": 0.047609522856952365
|
| 53 |
+
},
|
| 54 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 55 |
+
"acc": 0.6,
|
| 56 |
+
"acc_stderr": 0.04232073695151589,
|
| 57 |
+
"acc_norm": 0.6,
|
| 58 |
+
"acc_norm_stderr": 0.04232073695151589
|
| 59 |
+
},
|
| 60 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 61 |
+
"acc": 0.6973684210526315,
|
| 62 |
+
"acc_stderr": 0.037385206761196686,
|
| 63 |
+
"acc_norm": 0.6973684210526315,
|
| 64 |
+
"acc_norm_stderr": 0.037385206761196686
|
| 65 |
+
},
|
| 66 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 67 |
+
"acc": 0.6,
|
| 68 |
+
"acc_stderr": 0.04923659639173309,
|
| 69 |
+
"acc_norm": 0.6,
|
| 70 |
+
"acc_norm_stderr": 0.04923659639173309
|
| 71 |
+
},
|
| 72 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 73 |
+
"acc": 0.6943396226415094,
|
| 74 |
+
"acc_stderr": 0.028353298073322666,
|
| 75 |
+
"acc_norm": 0.6943396226415094,
|
| 76 |
+
"acc_norm_stderr": 0.028353298073322666
|
| 77 |
+
},
|
| 78 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 79 |
+
"acc": 0.7638888888888888,
|
| 80 |
+
"acc_stderr": 0.03551446610810826,
|
| 81 |
+
"acc_norm": 0.7638888888888888,
|
| 82 |
+
"acc_norm_stderr": 0.03551446610810826
|
| 83 |
+
},
|
| 84 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 85 |
+
"acc": 0.46,
|
| 86 |
+
"acc_stderr": 0.05009082659620333,
|
| 87 |
+
"acc_norm": 0.46,
|
| 88 |
+
"acc_norm_stderr": 0.05009082659620333
|
| 89 |
+
},
|
| 90 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 91 |
+
"acc": 0.52,
|
| 92 |
+
"acc_stderr": 0.050211673156867795,
|
| 93 |
+
"acc_norm": 0.52,
|
| 94 |
+
"acc_norm_stderr": 0.050211673156867795
|
| 95 |
+
},
|
| 96 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 97 |
+
"acc": 0.32,
|
| 98 |
+
"acc_stderr": 0.04688261722621504,
|
| 99 |
+
"acc_norm": 0.32,
|
| 100 |
+
"acc_norm_stderr": 0.04688261722621504
|
| 101 |
+
},
|
| 102 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 103 |
+
"acc": 0.6705202312138728,
|
| 104 |
+
"acc_stderr": 0.03583901754736412,
|
| 105 |
+
"acc_norm": 0.6705202312138728,
|
| 106 |
+
"acc_norm_stderr": 0.03583901754736412
|
| 107 |
+
},
|
| 108 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 109 |
+
"acc": 0.3627450980392157,
|
| 110 |
+
"acc_stderr": 0.04784060704105654,
|
| 111 |
+
"acc_norm": 0.3627450980392157,
|
| 112 |
+
"acc_norm_stderr": 0.04784060704105654
|
| 113 |
+
},
|
| 114 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 115 |
+
"acc": 0.75,
|
| 116 |
+
"acc_stderr": 0.04351941398892446,
|
| 117 |
+
"acc_norm": 0.75,
|
| 118 |
+
"acc_norm_stderr": 0.04351941398892446
|
| 119 |
+
},
|
| 120 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 121 |
+
"acc": 0.5574468085106383,
|
| 122 |
+
"acc_stderr": 0.03246956919789958,
|
| 123 |
+
"acc_norm": 0.5574468085106383,
|
| 124 |
+
"acc_norm_stderr": 0.03246956919789958
|
| 125 |
+
},
|
| 126 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 127 |
+
"acc": 0.4473684210526316,
|
| 128 |
+
"acc_stderr": 0.04677473004491199,
|
| 129 |
+
"acc_norm": 0.4473684210526316,
|
| 130 |
+
"acc_norm_stderr": 0.04677473004491199
|
| 131 |
+
},
|
| 132 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 133 |
+
"acc": 0.5586206896551724,
|
| 134 |
+
"acc_stderr": 0.04137931034482758,
|
| 135 |
+
"acc_norm": 0.5586206896551724,
|
| 136 |
+
"acc_norm_stderr": 0.04137931034482758
|
| 137 |
+
},
|
| 138 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 139 |
+
"acc": 0.41005291005291006,
|
| 140 |
+
"acc_stderr": 0.025331202438944444,
|
| 141 |
+
"acc_norm": 0.41005291005291006,
|
| 142 |
+
"acc_norm_stderr": 0.025331202438944444
|
| 143 |
+
},
|
| 144 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 145 |
+
"acc": 0.42857142857142855,
|
| 146 |
+
"acc_stderr": 0.0442626668137991,
|
| 147 |
+
"acc_norm": 0.42857142857142855,
|
| 148 |
+
"acc_norm_stderr": 0.0442626668137991
|
| 149 |
+
},
|
| 150 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 151 |
+
"acc": 0.34,
|
| 152 |
+
"acc_stderr": 0.04760952285695235,
|
| 153 |
+
"acc_norm": 0.34,
|
| 154 |
+
"acc_norm_stderr": 0.04760952285695235
|
| 155 |
+
},
|
| 156 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 157 |
+
"acc": 0.7709677419354839,
|
| 158 |
+
"acc_stderr": 0.023904914311782648,
|
| 159 |
+
"acc_norm": 0.7709677419354839,
|
| 160 |
+
"acc_norm_stderr": 0.023904914311782648
|
| 161 |
+
},
|
| 162 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 163 |
+
"acc": 0.5073891625615764,
|
| 164 |
+
"acc_stderr": 0.035176035403610105,
|
| 165 |
+
"acc_norm": 0.5073891625615764,
|
| 166 |
+
"acc_norm_stderr": 0.035176035403610105
|
| 167 |
+
},
|
| 168 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 169 |
+
"acc": 0.69,
|
| 170 |
+
"acc_stderr": 0.04648231987117316,
|
| 171 |
+
"acc_norm": 0.69,
|
| 172 |
+
"acc_norm_stderr": 0.04648231987117316
|
| 173 |
+
},
|
| 174 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 175 |
+
"acc": 0.7818181818181819,
|
| 176 |
+
"acc_stderr": 0.03225078108306289,
|
| 177 |
+
"acc_norm": 0.7818181818181819,
|
| 178 |
+
"acc_norm_stderr": 0.03225078108306289
|
| 179 |
+
},
|
| 180 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 181 |
+
"acc": 0.8080808080808081,
|
| 182 |
+
"acc_stderr": 0.028057791672989017,
|
| 183 |
+
"acc_norm": 0.8080808080808081,
|
| 184 |
+
"acc_norm_stderr": 0.028057791672989017
|
| 185 |
+
},
|
| 186 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 187 |
+
"acc": 0.8963730569948186,
|
| 188 |
+
"acc_stderr": 0.02199531196364424,
|
| 189 |
+
"acc_norm": 0.8963730569948186,
|
| 190 |
+
"acc_norm_stderr": 0.02199531196364424
|
| 191 |
+
},
|
| 192 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 193 |
+
"acc": 0.6435897435897436,
|
| 194 |
+
"acc_stderr": 0.02428314052946731,
|
| 195 |
+
"acc_norm": 0.6435897435897436,
|
| 196 |
+
"acc_norm_stderr": 0.02428314052946731
|
| 197 |
+
},
|
| 198 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 199 |
+
"acc": 0.32592592592592595,
|
| 200 |
+
"acc_stderr": 0.028578348365473072,
|
| 201 |
+
"acc_norm": 0.32592592592592595,
|
| 202 |
+
"acc_norm_stderr": 0.028578348365473072
|
| 203 |
+
},
|
| 204 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 205 |
+
"acc": 0.6764705882352942,
|
| 206 |
+
"acc_stderr": 0.030388353551886797,
|
| 207 |
+
"acc_norm": 0.6764705882352942,
|
| 208 |
+
"acc_norm_stderr": 0.030388353551886797
|
| 209 |
+
},
|
| 210 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 211 |
+
"acc": 0.3576158940397351,
|
| 212 |
+
"acc_stderr": 0.03913453431177258,
|
| 213 |
+
"acc_norm": 0.3576158940397351,
|
| 214 |
+
"acc_norm_stderr": 0.03913453431177258
|
| 215 |
+
},
|
| 216 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 217 |
+
"acc": 0.8440366972477065,
|
| 218 |
+
"acc_stderr": 0.015555802713590167,
|
| 219 |
+
"acc_norm": 0.8440366972477065,
|
| 220 |
+
"acc_norm_stderr": 0.015555802713590167
|
| 221 |
+
},
|
| 222 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 223 |
+
"acc": 0.5324074074074074,
|
| 224 |
+
"acc_stderr": 0.03402801581358966,
|
| 225 |
+
"acc_norm": 0.5324074074074074,
|
| 226 |
+
"acc_norm_stderr": 0.03402801581358966
|
| 227 |
+
},
|
| 228 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 229 |
+
"acc": 0.803921568627451,
|
| 230 |
+
"acc_stderr": 0.027865942286639318,
|
| 231 |
+
"acc_norm": 0.803921568627451,
|
| 232 |
+
"acc_norm_stderr": 0.027865942286639318
|
| 233 |
+
},
|
| 234 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 235 |
+
"acc": 0.7932489451476793,
|
| 236 |
+
"acc_stderr": 0.0263616516683891,
|
| 237 |
+
"acc_norm": 0.7932489451476793,
|
| 238 |
+
"acc_norm_stderr": 0.0263616516683891
|
| 239 |
+
},
|
| 240 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 241 |
+
"acc": 0.6905829596412556,
|
| 242 |
+
"acc_stderr": 0.03102441174057221,
|
| 243 |
+
"acc_norm": 0.6905829596412556,
|
| 244 |
+
"acc_norm_stderr": 0.03102441174057221
|
| 245 |
+
},
|
| 246 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 247 |
+
"acc": 0.7938931297709924,
|
| 248 |
+
"acc_stderr": 0.035477710041594654,
|
| 249 |
+
"acc_norm": 0.7938931297709924,
|
| 250 |
+
"acc_norm_stderr": 0.035477710041594654
|
| 251 |
+
},
|
| 252 |
+
"harness|hendrycksTest-international_law|5": {
|
| 253 |
+
"acc": 0.7851239669421488,
|
| 254 |
+
"acc_stderr": 0.03749492448709696,
|
| 255 |
+
"acc_norm": 0.7851239669421488,
|
| 256 |
+
"acc_norm_stderr": 0.03749492448709696
|
| 257 |
+
},
|
| 258 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 259 |
+
"acc": 0.8240740740740741,
|
| 260 |
+
"acc_stderr": 0.036809181416738807,
|
| 261 |
+
"acc_norm": 0.8240740740740741,
|
| 262 |
+
"acc_norm_stderr": 0.036809181416738807
|
| 263 |
+
},
|
| 264 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 265 |
+
"acc": 0.7239263803680982,
|
| 266 |
+
"acc_stderr": 0.035123852837050475,
|
| 267 |
+
"acc_norm": 0.7239263803680982,
|
| 268 |
+
"acc_norm_stderr": 0.035123852837050475
|
| 269 |
+
},
|
| 270 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 271 |
+
"acc": 0.44642857142857145,
|
| 272 |
+
"acc_stderr": 0.04718471485219588,
|
| 273 |
+
"acc_norm": 0.44642857142857145,
|
| 274 |
+
"acc_norm_stderr": 0.04718471485219588
|
| 275 |
+
},
|
| 276 |
+
"harness|hendrycksTest-management|5": {
|
| 277 |
+
"acc": 0.7766990291262136,
|
| 278 |
+
"acc_stderr": 0.04123553189891431,
|
| 279 |
+
"acc_norm": 0.7766990291262136,
|
| 280 |
+
"acc_norm_stderr": 0.04123553189891431
|
| 281 |
+
},
|
| 282 |
+
"harness|hendrycksTest-marketing|5": {
|
| 283 |
+
"acc": 0.8760683760683761,
|
| 284 |
+
"acc_stderr": 0.021586494001281376,
|
| 285 |
+
"acc_norm": 0.8760683760683761,
|
| 286 |
+
"acc_norm_stderr": 0.021586494001281376
|
| 287 |
+
},
|
| 288 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 289 |
+
"acc": 0.73,
|
| 290 |
+
"acc_stderr": 0.044619604333847394,
|
| 291 |
+
"acc_norm": 0.73,
|
| 292 |
+
"acc_norm_stderr": 0.044619604333847394
|
| 293 |
+
},
|
| 294 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 295 |
+
"acc": 0.8212005108556832,
|
| 296 |
+
"acc_stderr": 0.01370264371536898,
|
| 297 |
+
"acc_norm": 0.8212005108556832,
|
| 298 |
+
"acc_norm_stderr": 0.01370264371536898
|
| 299 |
+
},
|
| 300 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 301 |
+
"acc": 0.7167630057803468,
|
| 302 |
+
"acc_stderr": 0.024257901705323374,
|
| 303 |
+
"acc_norm": 0.7167630057803468,
|
| 304 |
+
"acc_norm_stderr": 0.024257901705323374
|
| 305 |
+
},
|
| 306 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 307 |
+
"acc": 0.2759776536312849,
|
| 308 |
+
"acc_stderr": 0.014950103002475356,
|
| 309 |
+
"acc_norm": 0.2759776536312849,
|
| 310 |
+
"acc_norm_stderr": 0.014950103002475356
|
| 311 |
+
},
|
| 312 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 313 |
+
"acc": 0.7189542483660131,
|
| 314 |
+
"acc_stderr": 0.02573885479781873,
|
| 315 |
+
"acc_norm": 0.7189542483660131,
|
| 316 |
+
"acc_norm_stderr": 0.02573885479781873
|
| 317 |
+
},
|
| 318 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 319 |
+
"acc": 0.7202572347266881,
|
| 320 |
+
"acc_stderr": 0.02549425935069491,
|
| 321 |
+
"acc_norm": 0.7202572347266881,
|
| 322 |
+
"acc_norm_stderr": 0.02549425935069491
|
| 323 |
+
},
|
| 324 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 325 |
+
"acc": 0.7314814814814815,
|
| 326 |
+
"acc_stderr": 0.024659685185967284,
|
| 327 |
+
"acc_norm": 0.7314814814814815,
|
| 328 |
+
"acc_norm_stderr": 0.024659685185967284
|
| 329 |
+
},
|
| 330 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 331 |
+
"acc": 0.475177304964539,
|
| 332 |
+
"acc_stderr": 0.02979071924382972,
|
| 333 |
+
"acc_norm": 0.475177304964539,
|
| 334 |
+
"acc_norm_stderr": 0.02979071924382972
|
| 335 |
+
},
|
| 336 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 337 |
+
"acc": 0.4621903520208605,
|
| 338 |
+
"acc_stderr": 0.012733671880342504,
|
| 339 |
+
"acc_norm": 0.4621903520208605,
|
| 340 |
+
"acc_norm_stderr": 0.012733671880342504
|
| 341 |
+
},
|
| 342 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 343 |
+
"acc": 0.6691176470588235,
|
| 344 |
+
"acc_stderr": 0.028582709753898445,
|
| 345 |
+
"acc_norm": 0.6691176470588235,
|
| 346 |
+
"acc_norm_stderr": 0.028582709753898445
|
| 347 |
+
},
|
| 348 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 349 |
+
"acc": 0.6535947712418301,
|
| 350 |
+
"acc_stderr": 0.01924978569171721,
|
| 351 |
+
"acc_norm": 0.6535947712418301,
|
| 352 |
+
"acc_norm_stderr": 0.01924978569171721
|
| 353 |
+
},
|
| 354 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 355 |
+
"acc": 0.6636363636363637,
|
| 356 |
+
"acc_stderr": 0.04525393596302506,
|
| 357 |
+
"acc_norm": 0.6636363636363637,
|
| 358 |
+
"acc_norm_stderr": 0.04525393596302506
|
| 359 |
+
},
|
| 360 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 361 |
+
"acc": 0.7428571428571429,
|
| 362 |
+
"acc_stderr": 0.027979823538744546,
|
| 363 |
+
"acc_norm": 0.7428571428571429,
|
| 364 |
+
"acc_norm_stderr": 0.027979823538744546
|
| 365 |
+
},
|
| 366 |
+
"harness|hendrycksTest-sociology|5": {
|
| 367 |
+
"acc": 0.835820895522388,
|
| 368 |
+
"acc_stderr": 0.026193923544454125,
|
| 369 |
+
"acc_norm": 0.835820895522388,
|
| 370 |
+
"acc_norm_stderr": 0.026193923544454125
|
| 371 |
+
},
|
| 372 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 373 |
+
"acc": 0.87,
|
| 374 |
+
"acc_stderr": 0.033799766898963086,
|
| 375 |
+
"acc_norm": 0.87,
|
| 376 |
+
"acc_norm_stderr": 0.033799766898963086
|
| 377 |
+
},
|
| 378 |
+
"harness|hendrycksTest-virology|5": {
|
| 379 |
+
"acc": 0.5481927710843374,
|
| 380 |
+
"acc_stderr": 0.03874371556587953,
|
| 381 |
+
"acc_norm": 0.5481927710843374,
|
| 382 |
+
"acc_norm_stderr": 0.03874371556587953
|
| 383 |
+
},
|
| 384 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 385 |
+
"acc": 0.8187134502923976,
|
| 386 |
+
"acc_stderr": 0.029547741687640038,
|
| 387 |
+
"acc_norm": 0.8187134502923976,
|
| 388 |
+
"acc_norm_stderr": 0.029547741687640038
|
| 389 |
+
},
|
| 390 |
+
"harness|truthfulqa:mc|0": {
|
| 391 |
+
"mc1": 0.379436964504284,
|
| 392 |
+
"mc1_stderr": 0.01698703926614299,
|
| 393 |
+
"mc2": 0.5593281467190233,
|
| 394 |
+
"mc2_stderr": 0.0156123862411416
|
| 395 |
+
},
|
| 396 |
+
"harness|winogrande|5": {
|
| 397 |
+
"acc": 0.7932123125493291,
|
| 398 |
+
"acc_stderr": 0.011382566829235803
|
| 399 |
+
},
|
| 400 |
+
"harness|gsm8k|5": {
|
| 401 |
+
"acc": 0.6171341925701289,
|
| 402 |
+
"acc_stderr": 0.013389223491820474
|
| 403 |
+
}
|
| 404 |
+
}
|
| 405 |
+
|
| 406 |
+
```
|
| 407 |
+
|
| 408 |
## 🧩 Configuration
|
| 409 |
|
| 410 |
```yaml
|