Update README.md
Browse files
README.md
CHANGED
|
@@ -30,4 +30,411 @@ parameters:
|
|
| 30 |
value: [1, 0.5, 0.7, 0.3, 0]
|
| 31 |
- value: 0.5
|
| 32 |
dtype: bfloat16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
```
|
|
|
|
| 30 |
value: [1, 0.5, 0.7, 0.3, 0]
|
| 31 |
- value: 0.5
|
| 32 |
dtype: bfloat16
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
+
# Dataset Card for Evaluation run of gagan3012/MetaModel
|
| 36 |
+
|
| 37 |
+
<!-- Provide a quick summary of the dataset. -->
|
| 38 |
+
|
| 39 |
+
Dataset automatically created during the evaluation run of model [gagan3012/MetaModel](https://huggingface.co/gagan3012/MetaModel) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
|
| 40 |
+
|
| 41 |
+
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
|
| 42 |
+
|
| 43 |
+
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
|
| 44 |
+
|
| 45 |
+
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
|
| 46 |
+
|
| 47 |
+
To load the details from a run, you can for instance do the following:
|
| 48 |
+
```python
|
| 49 |
+
from datasets import load_dataset
|
| 50 |
+
data = load_dataset("open-llm-leaderboard/details_gagan3012__MetaModel",
|
| 51 |
+
"harness_winogrande_5",
|
| 52 |
+
split="train")
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
## Latest results
|
| 56 |
+
|
| 57 |
+
These are the [latest results from run 2024-01-04T14:09:43.780941](https://huggingface.co/datasets/open-llm-leaderboard/details_gagan3012__MetaModel/blob/main/results_2024-01-04T14-09-43.780941.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
|
| 58 |
+
|
| 59 |
+
```python
|
| 60 |
+
{
|
| 61 |
+
"all": {
|
| 62 |
+
"acc": 0.6664380298886512,
|
| 63 |
+
"acc_stderr": 0.031642195230944255,
|
| 64 |
+
"acc_norm": 0.6671639222858992,
|
| 65 |
+
"acc_norm_stderr": 0.03228745343467652,
|
| 66 |
+
"mc1": 0.5691554467564259,
|
| 67 |
+
"mc1_stderr": 0.01733527247533237,
|
| 68 |
+
"mc2": 0.7184177934834866,
|
| 69 |
+
"mc2_stderr": 0.014995634120330182
|
| 70 |
+
},
|
| 71 |
+
"harness|arc:challenge|25": {
|
| 72 |
+
"acc": 0.6843003412969283,
|
| 73 |
+
"acc_stderr": 0.013582571095815291,
|
| 74 |
+
"acc_norm": 0.7107508532423208,
|
| 75 |
+
"acc_norm_stderr": 0.01325001257939344
|
| 76 |
+
},
|
| 77 |
+
"harness|hellaswag|10": {
|
| 78 |
+
"acc": 0.7132045409281019,
|
| 79 |
+
"acc_stderr": 0.004513409114983828,
|
| 80 |
+
"acc_norm": 0.8844851623182632,
|
| 81 |
+
"acc_norm_stderr": 0.0031898897894046684
|
| 82 |
+
},
|
| 83 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 84 |
+
"acc": 0.43,
|
| 85 |
+
"acc_stderr": 0.049756985195624284,
|
| 86 |
+
"acc_norm": 0.43,
|
| 87 |
+
"acc_norm_stderr": 0.049756985195624284
|
| 88 |
+
},
|
| 89 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 90 |
+
"acc": 0.6148148148148148,
|
| 91 |
+
"acc_stderr": 0.04203921040156279,
|
| 92 |
+
"acc_norm": 0.6148148148148148,
|
| 93 |
+
"acc_norm_stderr": 0.04203921040156279
|
| 94 |
+
},
|
| 95 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 96 |
+
"acc": 0.743421052631579,
|
| 97 |
+
"acc_stderr": 0.0355418036802569,
|
| 98 |
+
"acc_norm": 0.743421052631579,
|
| 99 |
+
"acc_norm_stderr": 0.0355418036802569
|
| 100 |
+
},
|
| 101 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 102 |
+
"acc": 0.75,
|
| 103 |
+
"acc_stderr": 0.04351941398892446,
|
| 104 |
+
"acc_norm": 0.75,
|
| 105 |
+
"acc_norm_stderr": 0.04351941398892446
|
| 106 |
+
},
|
| 107 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 108 |
+
"acc": 0.6830188679245283,
|
| 109 |
+
"acc_stderr": 0.02863723563980089,
|
| 110 |
+
"acc_norm": 0.6830188679245283,
|
| 111 |
+
"acc_norm_stderr": 0.02863723563980089
|
| 112 |
+
},
|
| 113 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 114 |
+
"acc": 0.7638888888888888,
|
| 115 |
+
"acc_stderr": 0.03551446610810826,
|
| 116 |
+
"acc_norm": 0.7638888888888888,
|
| 117 |
+
"acc_norm_stderr": 0.03551446610810826
|
| 118 |
+
},
|
| 119 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 120 |
+
"acc": 0.47,
|
| 121 |
+
"acc_stderr": 0.050161355804659205,
|
| 122 |
+
"acc_norm": 0.47,
|
| 123 |
+
"acc_norm_stderr": 0.050161355804659205
|
| 124 |
+
},
|
| 125 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 126 |
+
"acc": 0.48,
|
| 127 |
+
"acc_stderr": 0.05021167315686781,
|
| 128 |
+
"acc_norm": 0.48,
|
| 129 |
+
"acc_norm_stderr": 0.05021167315686781
|
| 130 |
+
},
|
| 131 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 132 |
+
"acc": 0.32,
|
| 133 |
+
"acc_stderr": 0.046882617226215034,
|
| 134 |
+
"acc_norm": 0.32,
|
| 135 |
+
"acc_norm_stderr": 0.046882617226215034
|
| 136 |
+
},
|
| 137 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 138 |
+
"acc": 0.6647398843930635,
|
| 139 |
+
"acc_stderr": 0.03599586301247077,
|
| 140 |
+
"acc_norm": 0.6647398843930635,
|
| 141 |
+
"acc_norm_stderr": 0.03599586301247077
|
| 142 |
+
},
|
| 143 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 144 |
+
"acc": 0.38235294117647056,
|
| 145 |
+
"acc_stderr": 0.04835503696107223,
|
| 146 |
+
"acc_norm": 0.38235294117647056,
|
| 147 |
+
"acc_norm_stderr": 0.04835503696107223
|
| 148 |
+
},
|
| 149 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 150 |
+
"acc": 0.75,
|
| 151 |
+
"acc_stderr": 0.04351941398892446,
|
| 152 |
+
"acc_norm": 0.75,
|
| 153 |
+
"acc_norm_stderr": 0.04351941398892446
|
| 154 |
+
},
|
| 155 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 156 |
+
"acc": 0.625531914893617,
|
| 157 |
+
"acc_stderr": 0.03163910665367291,
|
| 158 |
+
"acc_norm": 0.625531914893617,
|
| 159 |
+
"acc_norm_stderr": 0.03163910665367291
|
| 160 |
+
},
|
| 161 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 162 |
+
"acc": 0.4824561403508772,
|
| 163 |
+
"acc_stderr": 0.04700708033551038,
|
| 164 |
+
"acc_norm": 0.4824561403508772,
|
| 165 |
+
"acc_norm_stderr": 0.04700708033551038
|
| 166 |
+
},
|
| 167 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 168 |
+
"acc": 0.6413793103448275,
|
| 169 |
+
"acc_stderr": 0.039966295748767186,
|
| 170 |
+
"acc_norm": 0.6413793103448275,
|
| 171 |
+
"acc_norm_stderr": 0.039966295748767186
|
| 172 |
+
},
|
| 173 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 174 |
+
"acc": 0.5,
|
| 175 |
+
"acc_stderr": 0.025751310131230234,
|
| 176 |
+
"acc_norm": 0.5,
|
| 177 |
+
"acc_norm_stderr": 0.025751310131230234
|
| 178 |
+
},
|
| 179 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 180 |
+
"acc": 0.42857142857142855,
|
| 181 |
+
"acc_stderr": 0.0442626668137991,
|
| 182 |
+
"acc_norm": 0.42857142857142855,
|
| 183 |
+
"acc_norm_stderr": 0.0442626668137991
|
| 184 |
+
},
|
| 185 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 186 |
+
"acc": 0.35,
|
| 187 |
+
"acc_stderr": 0.047937248544110196,
|
| 188 |
+
"acc_norm": 0.35,
|
| 189 |
+
"acc_norm_stderr": 0.047937248544110196
|
| 190 |
+
},
|
| 191 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 192 |
+
"acc": 0.8129032258064516,
|
| 193 |
+
"acc_stderr": 0.022185710092252252,
|
| 194 |
+
"acc_norm": 0.8129032258064516,
|
| 195 |
+
"acc_norm_stderr": 0.022185710092252252
|
| 196 |
+
},
|
| 197 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 198 |
+
"acc": 0.5073891625615764,
|
| 199 |
+
"acc_stderr": 0.035176035403610105,
|
| 200 |
+
"acc_norm": 0.5073891625615764,
|
| 201 |
+
"acc_norm_stderr": 0.035176035403610105
|
| 202 |
+
},
|
| 203 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 204 |
+
"acc": 0.72,
|
| 205 |
+
"acc_stderr": 0.04512608598542128,
|
| 206 |
+
"acc_norm": 0.72,
|
| 207 |
+
"acc_norm_stderr": 0.04512608598542128
|
| 208 |
+
},
|
| 209 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 210 |
+
"acc": 0.8121212121212121,
|
| 211 |
+
"acc_stderr": 0.03050193405942914,
|
| 212 |
+
"acc_norm": 0.8121212121212121,
|
| 213 |
+
"acc_norm_stderr": 0.03050193405942914
|
| 214 |
+
},
|
| 215 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 216 |
+
"acc": 0.8636363636363636,
|
| 217 |
+
"acc_stderr": 0.024450155973189835,
|
| 218 |
+
"acc_norm": 0.8636363636363636,
|
| 219 |
+
"acc_norm_stderr": 0.024450155973189835
|
| 220 |
+
},
|
| 221 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 222 |
+
"acc": 0.8963730569948186,
|
| 223 |
+
"acc_stderr": 0.021995311963644244,
|
| 224 |
+
"acc_norm": 0.8963730569948186,
|
| 225 |
+
"acc_norm_stderr": 0.021995311963644244
|
| 226 |
+
},
|
| 227 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 228 |
+
"acc": 0.6692307692307692,
|
| 229 |
+
"acc_stderr": 0.02385479568097114,
|
| 230 |
+
"acc_norm": 0.6692307692307692,
|
| 231 |
+
"acc_norm_stderr": 0.02385479568097114
|
| 232 |
+
},
|
| 233 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 234 |
+
"acc": 0.37037037037037035,
|
| 235 |
+
"acc_stderr": 0.02944316932303154,
|
| 236 |
+
"acc_norm": 0.37037037037037035,
|
| 237 |
+
"acc_norm_stderr": 0.02944316932303154
|
| 238 |
+
},
|
| 239 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 240 |
+
"acc": 0.7142857142857143,
|
| 241 |
+
"acc_stderr": 0.029344572500634332,
|
| 242 |
+
"acc_norm": 0.7142857142857143,
|
| 243 |
+
"acc_norm_stderr": 0.029344572500634332
|
| 244 |
+
},
|
| 245 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 246 |
+
"acc": 0.3708609271523179,
|
| 247 |
+
"acc_stderr": 0.03943966699183629,
|
| 248 |
+
"acc_norm": 0.3708609271523179,
|
| 249 |
+
"acc_norm_stderr": 0.03943966699183629
|
| 250 |
+
},
|
| 251 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 252 |
+
"acc": 0.8422018348623853,
|
| 253 |
+
"acc_stderr": 0.01563002297009246,
|
| 254 |
+
"acc_norm": 0.8422018348623853,
|
| 255 |
+
"acc_norm_stderr": 0.01563002297009246
|
| 256 |
+
},
|
| 257 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 258 |
+
"acc": 0.5740740740740741,
|
| 259 |
+
"acc_stderr": 0.03372343271653062,
|
| 260 |
+
"acc_norm": 0.5740740740740741,
|
| 261 |
+
"acc_norm_stderr": 0.03372343271653062
|
| 262 |
+
},
|
| 263 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 264 |
+
"acc": 0.8578431372549019,
|
| 265 |
+
"acc_stderr": 0.02450980392156862,
|
| 266 |
+
"acc_norm": 0.8578431372549019,
|
| 267 |
+
"acc_norm_stderr": 0.02450980392156862
|
| 268 |
+
},
|
| 269 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 270 |
+
"acc": 0.8565400843881856,
|
| 271 |
+
"acc_stderr": 0.022818291821017012,
|
| 272 |
+
"acc_norm": 0.8565400843881856,
|
| 273 |
+
"acc_norm_stderr": 0.022818291821017012
|
| 274 |
+
},
|
| 275 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 276 |
+
"acc": 0.672645739910314,
|
| 277 |
+
"acc_stderr": 0.03149384670994131,
|
| 278 |
+
"acc_norm": 0.672645739910314,
|
| 279 |
+
"acc_norm_stderr": 0.03149384670994131
|
| 280 |
+
},
|
| 281 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 282 |
+
"acc": 0.7557251908396947,
|
| 283 |
+
"acc_stderr": 0.03768335959728743,
|
| 284 |
+
"acc_norm": 0.7557251908396947,
|
| 285 |
+
"acc_norm_stderr": 0.03768335959728743
|
| 286 |
+
},
|
| 287 |
+
"harness|hendrycksTest-international_law|5": {
|
| 288 |
+
"acc": 0.7851239669421488,
|
| 289 |
+
"acc_stderr": 0.037494924487096966,
|
| 290 |
+
"acc_norm": 0.7851239669421488,
|
| 291 |
+
"acc_norm_stderr": 0.037494924487096966
|
| 292 |
+
},
|
| 293 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 294 |
+
"acc": 0.8055555555555556,
|
| 295 |
+
"acc_stderr": 0.038260763248848646,
|
| 296 |
+
"acc_norm": 0.8055555555555556,
|
| 297 |
+
"acc_norm_stderr": 0.038260763248848646
|
| 298 |
+
},
|
| 299 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 300 |
+
"acc": 0.754601226993865,
|
| 301 |
+
"acc_stderr": 0.03380939813943354,
|
| 302 |
+
"acc_norm": 0.754601226993865,
|
| 303 |
+
"acc_norm_stderr": 0.03380939813943354
|
| 304 |
+
},
|
| 305 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 306 |
+
"acc": 0.4732142857142857,
|
| 307 |
+
"acc_stderr": 0.047389751192741546,
|
| 308 |
+
"acc_norm": 0.4732142857142857,
|
| 309 |
+
"acc_norm_stderr": 0.047389751192741546
|
| 310 |
+
},
|
| 311 |
+
"harness|hendrycksTest-management|5": {
|
| 312 |
+
"acc": 0.8446601941747572,
|
| 313 |
+
"acc_stderr": 0.035865947385739734,
|
| 314 |
+
"acc_norm": 0.8446601941747572,
|
| 315 |
+
"acc_norm_stderr": 0.035865947385739734
|
| 316 |
+
},
|
| 317 |
+
"harness|hendrycksTest-marketing|5": {
|
| 318 |
+
"acc": 0.8589743589743589,
|
| 319 |
+
"acc_stderr": 0.02280138253459753,
|
| 320 |
+
"acc_norm": 0.8589743589743589,
|
| 321 |
+
"acc_norm_stderr": 0.02280138253459753
|
| 322 |
+
},
|
| 323 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 324 |
+
"acc": 0.7,
|
| 325 |
+
"acc_stderr": 0.046056618647183814,
|
| 326 |
+
"acc_norm": 0.7,
|
| 327 |
+
"acc_norm_stderr": 0.046056618647183814
|
| 328 |
+
},
|
| 329 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 330 |
+
"acc": 0.8084291187739464,
|
| 331 |
+
"acc_stderr": 0.014072859310451949,
|
| 332 |
+
"acc_norm": 0.8084291187739464,
|
| 333 |
+
"acc_norm_stderr": 0.014072859310451949
|
| 334 |
+
},
|
| 335 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 336 |
+
"acc": 0.7572254335260116,
|
| 337 |
+
"acc_stderr": 0.023083658586984204,
|
| 338 |
+
"acc_norm": 0.7572254335260116,
|
| 339 |
+
"acc_norm_stderr": 0.023083658586984204
|
| 340 |
+
},
|
| 341 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 342 |
+
"acc": 0.39664804469273746,
|
| 343 |
+
"acc_stderr": 0.016361354769822468,
|
| 344 |
+
"acc_norm": 0.39664804469273746,
|
| 345 |
+
"acc_norm_stderr": 0.016361354769822468
|
| 346 |
+
},
|
| 347 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 348 |
+
"acc": 0.7581699346405228,
|
| 349 |
+
"acc_stderr": 0.024518195641879334,
|
| 350 |
+
"acc_norm": 0.7581699346405228,
|
| 351 |
+
"acc_norm_stderr": 0.024518195641879334
|
| 352 |
+
},
|
| 353 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 354 |
+
"acc": 0.7202572347266881,
|
| 355 |
+
"acc_stderr": 0.025494259350694905,
|
| 356 |
+
"acc_norm": 0.7202572347266881,
|
| 357 |
+
"acc_norm_stderr": 0.025494259350694905
|
| 358 |
+
},
|
| 359 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 360 |
+
"acc": 0.7777777777777778,
|
| 361 |
+
"acc_stderr": 0.02313237623454333,
|
| 362 |
+
"acc_norm": 0.7777777777777778,
|
| 363 |
+
"acc_norm_stderr": 0.02313237623454333
|
| 364 |
+
},
|
| 365 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 366 |
+
"acc": 0.5035460992907801,
|
| 367 |
+
"acc_stderr": 0.02982674915328092,
|
| 368 |
+
"acc_norm": 0.5035460992907801,
|
| 369 |
+
"acc_norm_stderr": 0.02982674915328092
|
| 370 |
+
},
|
| 371 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 372 |
+
"acc": 0.49478487614080835,
|
| 373 |
+
"acc_stderr": 0.012769541449652547,
|
| 374 |
+
"acc_norm": 0.49478487614080835,
|
| 375 |
+
"acc_norm_stderr": 0.012769541449652547
|
| 376 |
+
},
|
| 377 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 378 |
+
"acc": 0.75,
|
| 379 |
+
"acc_stderr": 0.026303648393696036,
|
| 380 |
+
"acc_norm": 0.75,
|
| 381 |
+
"acc_norm_stderr": 0.026303648393696036
|
| 382 |
+
},
|
| 383 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 384 |
+
"acc": 0.6813725490196079,
|
| 385 |
+
"acc_stderr": 0.018850084696468712,
|
| 386 |
+
"acc_norm": 0.6813725490196079,
|
| 387 |
+
"acc_norm_stderr": 0.018850084696468712
|
| 388 |
+
},
|
| 389 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 390 |
+
"acc": 0.6818181818181818,
|
| 391 |
+
"acc_stderr": 0.04461272175910509,
|
| 392 |
+
"acc_norm": 0.6818181818181818,
|
| 393 |
+
"acc_norm_stderr": 0.04461272175910509
|
| 394 |
+
},
|
| 395 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 396 |
+
"acc": 0.746938775510204,
|
| 397 |
+
"acc_stderr": 0.027833023871399677,
|
| 398 |
+
"acc_norm": 0.746938775510204,
|
| 399 |
+
"acc_norm_stderr": 0.027833023871399677
|
| 400 |
+
},
|
| 401 |
+
"harness|hendrycksTest-sociology|5": {
|
| 402 |
+
"acc": 0.8258706467661692,
|
| 403 |
+
"acc_stderr": 0.026814951200421603,
|
| 404 |
+
"acc_norm": 0.8258706467661692,
|
| 405 |
+
"acc_norm_stderr": 0.026814951200421603
|
| 406 |
+
},
|
| 407 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 408 |
+
"acc": 0.91,
|
| 409 |
+
"acc_stderr": 0.028762349126466125,
|
| 410 |
+
"acc_norm": 0.91,
|
| 411 |
+
"acc_norm_stderr": 0.028762349126466125
|
| 412 |
+
},
|
| 413 |
+
"harness|hendrycksTest-virology|5": {
|
| 414 |
+
"acc": 0.5783132530120482,
|
| 415 |
+
"acc_stderr": 0.038444531817709175,
|
| 416 |
+
"acc_norm": 0.5783132530120482,
|
| 417 |
+
"acc_norm_stderr": 0.038444531817709175
|
| 418 |
+
},
|
| 419 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 420 |
+
"acc": 0.7777777777777778,
|
| 421 |
+
"acc_stderr": 0.03188578017686398,
|
| 422 |
+
"acc_norm": 0.7777777777777778,
|
| 423 |
+
"acc_norm_stderr": 0.03188578017686398
|
| 424 |
+
},
|
| 425 |
+
"harness|truthfulqa:mc|0": {
|
| 426 |
+
"mc1": 0.5691554467564259,
|
| 427 |
+
"mc1_stderr": 0.01733527247533237,
|
| 428 |
+
"mc2": 0.7184177934834866,
|
| 429 |
+
"mc2_stderr": 0.014995634120330182
|
| 430 |
+
},
|
| 431 |
+
"harness|winogrande|5": {
|
| 432 |
+
"acc": 0.8342541436464088,
|
| 433 |
+
"acc_stderr": 0.010450899545370632
|
| 434 |
+
},
|
| 435 |
+
"harness|gsm8k|5": {
|
| 436 |
+
"acc": 0.6535253980288097,
|
| 437 |
+
"acc_stderr": 0.013107179054313398
|
| 438 |
+
}
|
| 439 |
+
}
|
| 440 |
```
|