Update README.md
Browse files
README.md
CHANGED
|
@@ -38,4 +38,411 @@ Fully opensourced at: https://github.com/hengjiUSTC/learn-llm/blob/main/trl_fine
|
|
| 38 |
|
| 39 |
```
|
| 40 |
python3 trl_finetune.py --config configs/yi_6b.yml
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
```
|
|
|
|
| 38 |
|
| 39 |
```
|
| 40 |
python3 trl_finetune.py --config configs/yi_6b.yml
|
| 41 |
+
```
|
| 42 |
+
|
| 43 |
+
# Dataset Card for Evaluation run of HenryJJ/Instruct_Yi-6B_Dolly15K
|
| 44 |
+
|
| 45 |
+
<!-- Provide a quick summary of the dataset. -->
|
| 46 |
+
|
| 47 |
+
Dataset automatically created during the evaluation run of model [HenryJJ/Instruct_Yi-6B_Dolly15K](https://huggingface.co/HenryJJ/Instruct_Yi-6B_Dolly15K) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
|
| 48 |
+
|
| 49 |
+
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
|
| 50 |
+
|
| 51 |
+
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.
|
| 52 |
+
|
| 53 |
+
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)).
|
| 54 |
+
|
| 55 |
+
To load the details from a run, you can for instance do the following:
|
| 56 |
+
```python
|
| 57 |
+
from datasets import load_dataset
|
| 58 |
+
data = load_dataset("open-llm-leaderboard/details_HenryJJ__Instruct_Yi-6B_Dolly15K",
|
| 59 |
+
"harness_winogrande_5",
|
| 60 |
+
split="train")
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
+
## Latest results
|
| 64 |
+
|
| 65 |
+
These are the [latest results from run 2024-01-06T09:45:44.755529](https://huggingface.co/datasets/open-llm-leaderboard/details_HenryJJ__Instruct_Yi-6B_Dolly15K/blob/main/results_2024-01-06T09-45-44.755529.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):
|
| 66 |
+
|
| 67 |
+
```python
|
| 68 |
+
{
|
| 69 |
+
"all": {
|
| 70 |
+
"acc": 0.6267070831158695,
|
| 71 |
+
"acc_stderr": 0.03222713761046951,
|
| 72 |
+
"acc_norm": 0.6343965374667763,
|
| 73 |
+
"acc_norm_stderr": 0.032887983229700546,
|
| 74 |
+
"mc1": 0.28886168910648713,
|
| 75 |
+
"mc1_stderr": 0.01586634640138431,
|
| 76 |
+
"mc2": 0.42839602626744816,
|
| 77 |
+
"mc2_stderr": 0.014270024501714959
|
| 78 |
+
},
|
| 79 |
+
"harness|arc:challenge|25": {
|
| 80 |
+
"acc": 0.5,
|
| 81 |
+
"acc_stderr": 0.014611390804670088,
|
| 82 |
+
"acc_norm": 0.5486348122866894,
|
| 83 |
+
"acc_norm_stderr": 0.014542104569955265
|
| 84 |
+
},
|
| 85 |
+
"harness|hellaswag|10": {
|
| 86 |
+
"acc": 0.5654252141007767,
|
| 87 |
+
"acc_stderr": 0.004946879874422681,
|
| 88 |
+
"acc_norm": 0.7587134037044413,
|
| 89 |
+
"acc_norm_stderr": 0.00426989301158892
|
| 90 |
+
},
|
| 91 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 92 |
+
"acc": 0.35,
|
| 93 |
+
"acc_stderr": 0.0479372485441102,
|
| 94 |
+
"acc_norm": 0.35,
|
| 95 |
+
"acc_norm_stderr": 0.0479372485441102
|
| 96 |
+
},
|
| 97 |
+
"harness|hendrycksTest-anatomy|5": {
|
| 98 |
+
"acc": 0.562962962962963,
|
| 99 |
+
"acc_stderr": 0.04284958639753401,
|
| 100 |
+
"acc_norm": 0.562962962962963,
|
| 101 |
+
"acc_norm_stderr": 0.04284958639753401
|
| 102 |
+
},
|
| 103 |
+
"harness|hendrycksTest-astronomy|5": {
|
| 104 |
+
"acc": 0.6776315789473685,
|
| 105 |
+
"acc_stderr": 0.03803510248351585,
|
| 106 |
+
"acc_norm": 0.6776315789473685,
|
| 107 |
+
"acc_norm_stderr": 0.03803510248351585
|
| 108 |
+
},
|
| 109 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 110 |
+
"acc": 0.7,
|
| 111 |
+
"acc_stderr": 0.046056618647183814,
|
| 112 |
+
"acc_norm": 0.7,
|
| 113 |
+
"acc_norm_stderr": 0.046056618647183814
|
| 114 |
+
},
|
| 115 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 116 |
+
"acc": 0.690566037735849,
|
| 117 |
+
"acc_stderr": 0.028450154794118637,
|
| 118 |
+
"acc_norm": 0.690566037735849,
|
| 119 |
+
"acc_norm_stderr": 0.028450154794118637
|
| 120 |
+
},
|
| 121 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 122 |
+
"acc": 0.6666666666666666,
|
| 123 |
+
"acc_stderr": 0.039420826399272135,
|
| 124 |
+
"acc_norm": 0.6666666666666666,
|
| 125 |
+
"acc_norm_stderr": 0.039420826399272135
|
| 126 |
+
},
|
| 127 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 128 |
+
"acc": 0.41,
|
| 129 |
+
"acc_stderr": 0.049431107042371025,
|
| 130 |
+
"acc_norm": 0.41,
|
| 131 |
+
"acc_norm_stderr": 0.049431107042371025
|
| 132 |
+
},
|
| 133 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 134 |
+
"acc": 0.44,
|
| 135 |
+
"acc_stderr": 0.04988876515698589,
|
| 136 |
+
"acc_norm": 0.44,
|
| 137 |
+
"acc_norm_stderr": 0.04988876515698589
|
| 138 |
+
},
|
| 139 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 140 |
+
"acc": 0.36,
|
| 141 |
+
"acc_stderr": 0.04824181513244218,
|
| 142 |
+
"acc_norm": 0.36,
|
| 143 |
+
"acc_norm_stderr": 0.04824181513244218
|
| 144 |
+
},
|
| 145 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 146 |
+
"acc": 0.6069364161849711,
|
| 147 |
+
"acc_stderr": 0.03724249595817731,
|
| 148 |
+
"acc_norm": 0.6069364161849711,
|
| 149 |
+
"acc_norm_stderr": 0.03724249595817731
|
| 150 |
+
},
|
| 151 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 152 |
+
"acc": 0.3235294117647059,
|
| 153 |
+
"acc_stderr": 0.04655010411319617,
|
| 154 |
+
"acc_norm": 0.3235294117647059,
|
| 155 |
+
"acc_norm_stderr": 0.04655010411319617
|
| 156 |
+
},
|
| 157 |
+
"harness|hendrycksTest-computer_security|5": {
|
| 158 |
+
"acc": 0.77,
|
| 159 |
+
"acc_stderr": 0.04229525846816507,
|
| 160 |
+
"acc_norm": 0.77,
|
| 161 |
+
"acc_norm_stderr": 0.04229525846816507
|
| 162 |
+
},
|
| 163 |
+
"harness|hendrycksTest-conceptual_physics|5": {
|
| 164 |
+
"acc": 0.6212765957446809,
|
| 165 |
+
"acc_stderr": 0.03170995606040655,
|
| 166 |
+
"acc_norm": 0.6212765957446809,
|
| 167 |
+
"acc_norm_stderr": 0.03170995606040655
|
| 168 |
+
},
|
| 169 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 170 |
+
"acc": 0.35964912280701755,
|
| 171 |
+
"acc_stderr": 0.045144961328736334,
|
| 172 |
+
"acc_norm": 0.35964912280701755,
|
| 173 |
+
"acc_norm_stderr": 0.045144961328736334
|
| 174 |
+
},
|
| 175 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 176 |
+
"acc": 0.6482758620689655,
|
| 177 |
+
"acc_stderr": 0.0397923663749741,
|
| 178 |
+
"acc_norm": 0.6482758620689655,
|
| 179 |
+
"acc_norm_stderr": 0.0397923663749741
|
| 180 |
+
},
|
| 181 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 182 |
+
"acc": 0.4470899470899471,
|
| 183 |
+
"acc_stderr": 0.02560672399577703,
|
| 184 |
+
"acc_norm": 0.4470899470899471,
|
| 185 |
+
"acc_norm_stderr": 0.02560672399577703
|
| 186 |
+
},
|
| 187 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 188 |
+
"acc": 0.38095238095238093,
|
| 189 |
+
"acc_stderr": 0.04343525428949098,
|
| 190 |
+
"acc_norm": 0.38095238095238093,
|
| 191 |
+
"acc_norm_stderr": 0.04343525428949098
|
| 192 |
+
},
|
| 193 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 194 |
+
"acc": 0.4,
|
| 195 |
+
"acc_stderr": 0.04923659639173309,
|
| 196 |
+
"acc_norm": 0.4,
|
| 197 |
+
"acc_norm_stderr": 0.04923659639173309
|
| 198 |
+
},
|
| 199 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 200 |
+
"acc": 0.7774193548387097,
|
| 201 |
+
"acc_stderr": 0.023664216671642525,
|
| 202 |
+
"acc_norm": 0.7774193548387097,
|
| 203 |
+
"acc_norm_stderr": 0.023664216671642525
|
| 204 |
+
},
|
| 205 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 206 |
+
"acc": 0.4975369458128079,
|
| 207 |
+
"acc_stderr": 0.03517945038691063,
|
| 208 |
+
"acc_norm": 0.4975369458128079,
|
| 209 |
+
"acc_norm_stderr": 0.03517945038691063
|
| 210 |
+
},
|
| 211 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 212 |
+
"acc": 0.64,
|
| 213 |
+
"acc_stderr": 0.04824181513244218,
|
| 214 |
+
"acc_norm": 0.64,
|
| 215 |
+
"acc_norm_stderr": 0.04824181513244218
|
| 216 |
+
},
|
| 217 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 218 |
+
"acc": 0.7393939393939394,
|
| 219 |
+
"acc_stderr": 0.034277431758165236,
|
| 220 |
+
"acc_norm": 0.7393939393939394,
|
| 221 |
+
"acc_norm_stderr": 0.034277431758165236
|
| 222 |
+
},
|
| 223 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 224 |
+
"acc": 0.8181818181818182,
|
| 225 |
+
"acc_stderr": 0.0274796030105388,
|
| 226 |
+
"acc_norm": 0.8181818181818182,
|
| 227 |
+
"acc_norm_stderr": 0.0274796030105388
|
| 228 |
+
},
|
| 229 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 230 |
+
"acc": 0.9015544041450777,
|
| 231 |
+
"acc_stderr": 0.021500249576033456,
|
| 232 |
+
"acc_norm": 0.9015544041450777,
|
| 233 |
+
"acc_norm_stderr": 0.021500249576033456
|
| 234 |
+
},
|
| 235 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 236 |
+
"acc": 0.617948717948718,
|
| 237 |
+
"acc_stderr": 0.02463554916390823,
|
| 238 |
+
"acc_norm": 0.617948717948718,
|
| 239 |
+
"acc_norm_stderr": 0.02463554916390823
|
| 240 |
+
},
|
| 241 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 242 |
+
"acc": 0.31851851851851853,
|
| 243 |
+
"acc_stderr": 0.028406533090608463,
|
| 244 |
+
"acc_norm": 0.31851851851851853,
|
| 245 |
+
"acc_norm_stderr": 0.028406533090608463
|
| 246 |
+
},
|
| 247 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 248 |
+
"acc": 0.7647058823529411,
|
| 249 |
+
"acc_stderr": 0.027553614467863797,
|
| 250 |
+
"acc_norm": 0.7647058823529411,
|
| 251 |
+
"acc_norm_stderr": 0.027553614467863797
|
| 252 |
+
},
|
| 253 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 254 |
+
"acc": 0.36423841059602646,
|
| 255 |
+
"acc_stderr": 0.03929111781242742,
|
| 256 |
+
"acc_norm": 0.36423841059602646,
|
| 257 |
+
"acc_norm_stderr": 0.03929111781242742
|
| 258 |
+
},
|
| 259 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 260 |
+
"acc": 0.8348623853211009,
|
| 261 |
+
"acc_stderr": 0.01591955782997604,
|
| 262 |
+
"acc_norm": 0.8348623853211009,
|
| 263 |
+
"acc_norm_stderr": 0.01591955782997604
|
| 264 |
+
},
|
| 265 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 266 |
+
"acc": 0.5694444444444444,
|
| 267 |
+
"acc_stderr": 0.03376922151252335,
|
| 268 |
+
"acc_norm": 0.5694444444444444,
|
| 269 |
+
"acc_norm_stderr": 0.03376922151252335
|
| 270 |
+
},
|
| 271 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 272 |
+
"acc": 0.8088235294117647,
|
| 273 |
+
"acc_stderr": 0.027599174300640766,
|
| 274 |
+
"acc_norm": 0.8088235294117647,
|
| 275 |
+
"acc_norm_stderr": 0.027599174300640766
|
| 276 |
+
},
|
| 277 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 278 |
+
"acc": 0.7932489451476793,
|
| 279 |
+
"acc_stderr": 0.026361651668389094,
|
| 280 |
+
"acc_norm": 0.7932489451476793,
|
| 281 |
+
"acc_norm_stderr": 0.026361651668389094
|
| 282 |
+
},
|
| 283 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 284 |
+
"acc": 0.695067264573991,
|
| 285 |
+
"acc_stderr": 0.030898610882477515,
|
| 286 |
+
"acc_norm": 0.695067264573991,
|
| 287 |
+
"acc_norm_stderr": 0.030898610882477515
|
| 288 |
+
},
|
| 289 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 290 |
+
"acc": 0.7480916030534351,
|
| 291 |
+
"acc_stderr": 0.03807387116306085,
|
| 292 |
+
"acc_norm": 0.7480916030534351,
|
| 293 |
+
"acc_norm_stderr": 0.03807387116306085
|
| 294 |
+
},
|
| 295 |
+
"harness|hendrycksTest-international_law|5": {
|
| 296 |
+
"acc": 0.7768595041322314,
|
| 297 |
+
"acc_stderr": 0.03800754475228733,
|
| 298 |
+
"acc_norm": 0.7768595041322314,
|
| 299 |
+
"acc_norm_stderr": 0.03800754475228733
|
| 300 |
+
},
|
| 301 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 302 |
+
"acc": 0.7777777777777778,
|
| 303 |
+
"acc_stderr": 0.040191074725573483,
|
| 304 |
+
"acc_norm": 0.7777777777777778,
|
| 305 |
+
"acc_norm_stderr": 0.040191074725573483
|
| 306 |
+
},
|
| 307 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 308 |
+
"acc": 0.7852760736196319,
|
| 309 |
+
"acc_stderr": 0.03226219377286775,
|
| 310 |
+
"acc_norm": 0.7852760736196319,
|
| 311 |
+
"acc_norm_stderr": 0.03226219377286775
|
| 312 |
+
},
|
| 313 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 314 |
+
"acc": 0.4375,
|
| 315 |
+
"acc_stderr": 0.04708567521880525,
|
| 316 |
+
"acc_norm": 0.4375,
|
| 317 |
+
"acc_norm_stderr": 0.04708567521880525
|
| 318 |
+
},
|
| 319 |
+
"harness|hendrycksTest-management|5": {
|
| 320 |
+
"acc": 0.8155339805825242,
|
| 321 |
+
"acc_stderr": 0.03840423627288276,
|
| 322 |
+
"acc_norm": 0.8155339805825242,
|
| 323 |
+
"acc_norm_stderr": 0.03840423627288276
|
| 324 |
+
},
|
| 325 |
+
"harness|hendrycksTest-marketing|5": {
|
| 326 |
+
"acc": 0.8974358974358975,
|
| 327 |
+
"acc_stderr": 0.01987565502786744,
|
| 328 |
+
"acc_norm": 0.8974358974358975,
|
| 329 |
+
"acc_norm_stderr": 0.01987565502786744
|
| 330 |
+
},
|
| 331 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 332 |
+
"acc": 0.76,
|
| 333 |
+
"acc_stderr": 0.042923469599092816,
|
| 334 |
+
"acc_norm": 0.76,
|
| 335 |
+
"acc_norm_stderr": 0.042923469599092816
|
| 336 |
+
},
|
| 337 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 338 |
+
"acc": 0.8007662835249042,
|
| 339 |
+
"acc_stderr": 0.014283378044296417,
|
| 340 |
+
"acc_norm": 0.8007662835249042,
|
| 341 |
+
"acc_norm_stderr": 0.014283378044296417
|
| 342 |
+
},
|
| 343 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 344 |
+
"acc": 0.708092485549133,
|
| 345 |
+
"acc_stderr": 0.024476994076247333,
|
| 346 |
+
"acc_norm": 0.708092485549133,
|
| 347 |
+
"acc_norm_stderr": 0.024476994076247333
|
| 348 |
+
},
|
| 349 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 350 |
+
"acc": 0.33519553072625696,
|
| 351 |
+
"acc_stderr": 0.015788007190185884,
|
| 352 |
+
"acc_norm": 0.33519553072625696,
|
| 353 |
+
"acc_norm_stderr": 0.015788007190185884
|
| 354 |
+
},
|
| 355 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 356 |
+
"acc": 0.7222222222222222,
|
| 357 |
+
"acc_stderr": 0.025646863097137897,
|
| 358 |
+
"acc_norm": 0.7222222222222222,
|
| 359 |
+
"acc_norm_stderr": 0.025646863097137897
|
| 360 |
+
},
|
| 361 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 362 |
+
"acc": 0.6913183279742765,
|
| 363 |
+
"acc_stderr": 0.026236965881153262,
|
| 364 |
+
"acc_norm": 0.6913183279742765,
|
| 365 |
+
"acc_norm_stderr": 0.026236965881153262
|
| 366 |
+
},
|
| 367 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 368 |
+
"acc": 0.7191358024691358,
|
| 369 |
+
"acc_stderr": 0.025006469755799208,
|
| 370 |
+
"acc_norm": 0.7191358024691358,
|
| 371 |
+
"acc_norm_stderr": 0.025006469755799208
|
| 372 |
+
},
|
| 373 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 374 |
+
"acc": 0.48226950354609927,
|
| 375 |
+
"acc_stderr": 0.02980873964223777,
|
| 376 |
+
"acc_norm": 0.48226950354609927,
|
| 377 |
+
"acc_norm_stderr": 0.02980873964223777
|
| 378 |
+
},
|
| 379 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 380 |
+
"acc": 0.4876140808344198,
|
| 381 |
+
"acc_stderr": 0.012766317315473565,
|
| 382 |
+
"acc_norm": 0.4876140808344198,
|
| 383 |
+
"acc_norm_stderr": 0.012766317315473565
|
| 384 |
+
},
|
| 385 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 386 |
+
"acc": 0.6213235294117647,
|
| 387 |
+
"acc_stderr": 0.02946513363977613,
|
| 388 |
+
"acc_norm": 0.6213235294117647,
|
| 389 |
+
"acc_norm_stderr": 0.02946513363977613
|
| 390 |
+
},
|
| 391 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 392 |
+
"acc": 0.6568627450980392,
|
| 393 |
+
"acc_stderr": 0.019206606848825365,
|
| 394 |
+
"acc_norm": 0.6568627450980392,
|
| 395 |
+
"acc_norm_stderr": 0.019206606848825365
|
| 396 |
+
},
|
| 397 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 398 |
+
"acc": 0.6909090909090909,
|
| 399 |
+
"acc_stderr": 0.044262946482000985,
|
| 400 |
+
"acc_norm": 0.6909090909090909,
|
| 401 |
+
"acc_norm_stderr": 0.044262946482000985
|
| 402 |
+
},
|
| 403 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 404 |
+
"acc": 0.7306122448979592,
|
| 405 |
+
"acc_stderr": 0.02840125202902294,
|
| 406 |
+
"acc_norm": 0.7306122448979592,
|
| 407 |
+
"acc_norm_stderr": 0.02840125202902294
|
| 408 |
+
},
|
| 409 |
+
"harness|hendrycksTest-sociology|5": {
|
| 410 |
+
"acc": 0.8159203980099502,
|
| 411 |
+
"acc_stderr": 0.027403859410786862,
|
| 412 |
+
"acc_norm": 0.8159203980099502,
|
| 413 |
+
"acc_norm_stderr": 0.027403859410786862
|
| 414 |
+
},
|
| 415 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 416 |
+
"acc": 0.84,
|
| 417 |
+
"acc_stderr": 0.03684529491774708,
|
| 418 |
+
"acc_norm": 0.84,
|
| 419 |
+
"acc_norm_stderr": 0.03684529491774708
|
| 420 |
+
},
|
| 421 |
+
"harness|hendrycksTest-virology|5": {
|
| 422 |
+
"acc": 0.4578313253012048,
|
| 423 |
+
"acc_stderr": 0.0387862677100236,
|
| 424 |
+
"acc_norm": 0.4578313253012048,
|
| 425 |
+
"acc_norm_stderr": 0.0387862677100236
|
| 426 |
+
},
|
| 427 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 428 |
+
"acc": 0.8070175438596491,
|
| 429 |
+
"acc_stderr": 0.030267457554898458,
|
| 430 |
+
"acc_norm": 0.8070175438596491,
|
| 431 |
+
"acc_norm_stderr": 0.030267457554898458
|
| 432 |
+
},
|
| 433 |
+
"harness|truthfulqa:mc|0": {
|
| 434 |
+
"mc1": 0.28886168910648713,
|
| 435 |
+
"mc1_stderr": 0.01586634640138431,
|
| 436 |
+
"mc2": 0.42839602626744816,
|
| 437 |
+
"mc2_stderr": 0.014270024501714959
|
| 438 |
+
},
|
| 439 |
+
"harness|winogrande|5": {
|
| 440 |
+
"acc": 0.7490134175217048,
|
| 441 |
+
"acc_stderr": 0.012185776220516148
|
| 442 |
+
},
|
| 443 |
+
"harness|gsm8k|5": {
|
| 444 |
+
"acc": 0.2926459438968916,
|
| 445 |
+
"acc_stderr": 0.012532334368242888
|
| 446 |
+
}
|
| 447 |
+
}
|
| 448 |
```
|