Isaak Carter Augustus
commited on
Commit
•
9fafa58
1
Parent(s):
6d97107
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,393 @@ JOSIE_Beta-8-7B-slerp is a merge of the following models using [LazyMergekit](ht
|
|
| 17 |
* [HuggingFaceH4/mistral-7b-anthropic](https://huggingface.co/HuggingFaceH4/mistral-7b-anthropic)
|
| 18 |
* [HuggingFaceH4/mistral-7b-grok](https://huggingface.co/HuggingFaceH4/mistral-7b-grok)
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## 🧩 Configuration
|
| 21 |
|
| 22 |
```yaml
|
|
|
|
| 17 |
* [HuggingFaceH4/mistral-7b-anthropic](https://huggingface.co/HuggingFaceH4/mistral-7b-anthropic)
|
| 18 |
* [HuggingFaceH4/mistral-7b-grok](https://huggingface.co/HuggingFaceH4/mistral-7b-grok)
|
| 19 |
|
| 20 |
+
# Important!!!
|
| 21 |
+
|
| 22 |
+
Upon seing the eval benchmarks on the LLM Leaderbard this model performs the worst. the best performing one (in the leaderboard) is the 3 beta version.
|
| 23 |
+
|
| 24 |
+
```json
|
| 25 |
+
{
|
| 26 |
+
"all": {
|
| 27 |
+
"acc": 0.6212846416057433,
|
| 28 |
+
"acc_stderr": 0.03289607423593368,
|
| 29 |
+
"acc_norm": 0.6268274539918854,
|
| 30 |
+
"acc_norm_stderr": 0.03356884635772938,
|
| 31 |
+
"mc1": 0.3157894736842105,
|
| 32 |
+
"mc1_stderr": 0.016272287957916923,
|
| 33 |
+
"mc2": 0.4868797251828956,
|
| 34 |
+
"mc2_stderr": 0.01529943410920313
|
| 35 |
+
},
|
| 36 |
+
"harness|arc:challenge|25": {
|
| 37 |
+
"acc": 0.5776450511945392,
|
| 38 |
+
"acc_stderr": 0.014434138713379981,
|
| 39 |
+
"acc_norm": 0.6040955631399317,
|
| 40 |
+
"acc_norm_stderr": 0.014291228393536592
|
| 41 |
+
},
|
| 42 |
+
"harness|hellaswag|10": {
|
| 43 |
+
"acc": 0.6363274248157738,
|
| 44 |
+
"acc_stderr": 0.004800728138792394,
|
| 45 |
+
"acc_norm": 0.8365863373829915,
|
| 46 |
+
"acc_norm_stderr": 0.0036898701424130753
|
| 47 |
+
},
|
| 48 |
+
"harness|hendrycksTest-abstract_algebra|5": {
|
| 49 |
+
"acc": 0.31,
|
| 50 |
+
"acc_stderr": 0.046482319871173156,
|
| 51 |
+
"acc_norm": 0.31,
|
| 52 |
+
"acc_norm_stderr": 0.046482319871173156
|
| 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": 0.5986842105263158,
|
| 62 |
+
"acc_stderr": 0.039889037033362836,
|
| 63 |
+
"acc_norm": 0.5986842105263158,
|
| 64 |
+
"acc_norm_stderr": 0.039889037033362836
|
| 65 |
+
},
|
| 66 |
+
"harness|hendrycksTest-business_ethics|5": {
|
| 67 |
+
"acc": 0.58,
|
| 68 |
+
"acc_stderr": 0.049604496374885836,
|
| 69 |
+
"acc_norm": 0.58,
|
| 70 |
+
"acc_norm_stderr": 0.049604496374885836
|
| 71 |
+
},
|
| 72 |
+
"harness|hendrycksTest-clinical_knowledge|5": {
|
| 73 |
+
"acc": 0.6867924528301886,
|
| 74 |
+
"acc_stderr": 0.028544793319055326,
|
| 75 |
+
"acc_norm": 0.6867924528301886,
|
| 76 |
+
"acc_norm_stderr": 0.028544793319055326
|
| 77 |
+
},
|
| 78 |
+
"harness|hendrycksTest-college_biology|5": {
|
| 79 |
+
"acc": 0.7083333333333334,
|
| 80 |
+
"acc_stderr": 0.038009680605548594,
|
| 81 |
+
"acc_norm": 0.7083333333333334,
|
| 82 |
+
"acc_norm_stderr": 0.038009680605548594
|
| 83 |
+
},
|
| 84 |
+
"harness|hendrycksTest-college_chemistry|5": {
|
| 85 |
+
"acc": 0.53,
|
| 86 |
+
"acc_stderr": 0.05016135580465919,
|
| 87 |
+
"acc_norm": 0.53,
|
| 88 |
+
"acc_norm_stderr": 0.05016135580465919
|
| 89 |
+
},
|
| 90 |
+
"harness|hendrycksTest-college_computer_science|5": {
|
| 91 |
+
"acc": 0.51,
|
| 92 |
+
"acc_stderr": 0.05024183937956912,
|
| 93 |
+
"acc_norm": 0.51,
|
| 94 |
+
"acc_norm_stderr": 0.05024183937956912
|
| 95 |
+
},
|
| 96 |
+
"harness|hendrycksTest-college_mathematics|5": {
|
| 97 |
+
"acc": 0.39,
|
| 98 |
+
"acc_stderr": 0.04902071300001975,
|
| 99 |
+
"acc_norm": 0.39,
|
| 100 |
+
"acc_norm_stderr": 0.04902071300001975
|
| 101 |
+
},
|
| 102 |
+
"harness|hendrycksTest-college_medicine|5": {
|
| 103 |
+
"acc": 0.6184971098265896,
|
| 104 |
+
"acc_stderr": 0.03703851193099521,
|
| 105 |
+
"acc_norm": 0.6184971098265896,
|
| 106 |
+
"acc_norm_stderr": 0.03703851193099521
|
| 107 |
+
},
|
| 108 |
+
"harness|hendrycksTest-college_physics|5": {
|
| 109 |
+
"acc": 0.39215686274509803,
|
| 110 |
+
"acc_stderr": 0.048580835742663454,
|
| 111 |
+
"acc_norm": 0.39215686274509803,
|
| 112 |
+
"acc_norm_stderr": 0.048580835742663454
|
| 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": 0.5659574468085107,
|
| 122 |
+
"acc_stderr": 0.03240038086792747,
|
| 123 |
+
"acc_norm": 0.5659574468085107,
|
| 124 |
+
"acc_norm_stderr": 0.03240038086792747
|
| 125 |
+
},
|
| 126 |
+
"harness|hendrycksTest-econometrics|5": {
|
| 127 |
+
"acc": 0.47368421052631576,
|
| 128 |
+
"acc_stderr": 0.04697085136647863,
|
| 129 |
+
"acc_norm": 0.47368421052631576,
|
| 130 |
+
"acc_norm_stderr": 0.04697085136647863
|
| 131 |
+
},
|
| 132 |
+
"harness|hendrycksTest-electrical_engineering|5": {
|
| 133 |
+
"acc": 0.5586206896551724,
|
| 134 |
+
"acc_stderr": 0.04137931034482757,
|
| 135 |
+
"acc_norm": 0.5586206896551724,
|
| 136 |
+
"acc_norm_stderr": 0.04137931034482757
|
| 137 |
+
},
|
| 138 |
+
"harness|hendrycksTest-elementary_mathematics|5": {
|
| 139 |
+
"acc": 0.41005291005291006,
|
| 140 |
+
"acc_stderr": 0.025331202438944437,
|
| 141 |
+
"acc_norm": 0.41005291005291006,
|
| 142 |
+
"acc_norm_stderr": 0.025331202438944437
|
| 143 |
+
},
|
| 144 |
+
"harness|hendrycksTest-formal_logic|5": {
|
| 145 |
+
"acc": 0.3888888888888889,
|
| 146 |
+
"acc_stderr": 0.04360314860077459,
|
| 147 |
+
"acc_norm": 0.3888888888888889,
|
| 148 |
+
"acc_norm_stderr": 0.04360314860077459
|
| 149 |
+
},
|
| 150 |
+
"harness|hendrycksTest-global_facts|5": {
|
| 151 |
+
"acc": 0.4,
|
| 152 |
+
"acc_stderr": 0.049236596391733084,
|
| 153 |
+
"acc_norm": 0.4,
|
| 154 |
+
"acc_norm_stderr": 0.049236596391733084
|
| 155 |
+
},
|
| 156 |
+
"harness|hendrycksTest-high_school_biology|5": {
|
| 157 |
+
"acc": 0.7580645161290323,
|
| 158 |
+
"acc_stderr": 0.024362599693031083,
|
| 159 |
+
"acc_norm": 0.7580645161290323,
|
| 160 |
+
"acc_norm_stderr": 0.024362599693031083
|
| 161 |
+
},
|
| 162 |
+
"harness|hendrycksTest-high_school_chemistry|5": {
|
| 163 |
+
"acc": 0.5221674876847291,
|
| 164 |
+
"acc_stderr": 0.03514528562175008,
|
| 165 |
+
"acc_norm": 0.5221674876847291,
|
| 166 |
+
"acc_norm_stderr": 0.03514528562175008
|
| 167 |
+
},
|
| 168 |
+
"harness|hendrycksTest-high_school_computer_science|5": {
|
| 169 |
+
"acc": 0.63,
|
| 170 |
+
"acc_stderr": 0.04852365870939099,
|
| 171 |
+
"acc_norm": 0.63,
|
| 172 |
+
"acc_norm_stderr": 0.04852365870939099
|
| 173 |
+
},
|
| 174 |
+
"harness|hendrycksTest-high_school_european_history|5": {
|
| 175 |
+
"acc": 0.7515151515151515,
|
| 176 |
+
"acc_stderr": 0.033744026441394036,
|
| 177 |
+
"acc_norm": 0.7515151515151515,
|
| 178 |
+
"acc_norm_stderr": 0.033744026441394036
|
| 179 |
+
},
|
| 180 |
+
"harness|hendrycksTest-high_school_geography|5": {
|
| 181 |
+
"acc": 0.7727272727272727,
|
| 182 |
+
"acc_stderr": 0.029857515673386417,
|
| 183 |
+
"acc_norm": 0.7727272727272727,
|
| 184 |
+
"acc_norm_stderr": 0.029857515673386417
|
| 185 |
+
},
|
| 186 |
+
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
| 187 |
+
"acc": 0.8497409326424871,
|
| 188 |
+
"acc_stderr": 0.025787723180723875,
|
| 189 |
+
"acc_norm": 0.8497409326424871,
|
| 190 |
+
"acc_norm_stderr": 0.025787723180723875
|
| 191 |
+
},
|
| 192 |
+
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
| 193 |
+
"acc": 0.6384615384615384,
|
| 194 |
+
"acc_stderr": 0.024359581465396997,
|
| 195 |
+
"acc_norm": 0.6384615384615384,
|
| 196 |
+
"acc_norm_stderr": 0.024359581465396997
|
| 197 |
+
},
|
| 198 |
+
"harness|hendrycksTest-high_school_mathematics|5": {
|
| 199 |
+
"acc": 0.337037037037037,
|
| 200 |
+
"acc_stderr": 0.028820884666253255,
|
| 201 |
+
"acc_norm": 0.337037037037037,
|
| 202 |
+
"acc_norm_stderr": 0.028820884666253255
|
| 203 |
+
},
|
| 204 |
+
"harness|hendrycksTest-high_school_microeconomics|5": {
|
| 205 |
+
"acc": 0.6764705882352942,
|
| 206 |
+
"acc_stderr": 0.03038835355188679,
|
| 207 |
+
"acc_norm": 0.6764705882352942,
|
| 208 |
+
"acc_norm_stderr": 0.03038835355188679
|
| 209 |
+
},
|
| 210 |
+
"harness|hendrycksTest-high_school_physics|5": {
|
| 211 |
+
"acc": 0.3443708609271523,
|
| 212 |
+
"acc_stderr": 0.038796870240733264,
|
| 213 |
+
"acc_norm": 0.3443708609271523,
|
| 214 |
+
"acc_norm_stderr": 0.038796870240733264
|
| 215 |
+
},
|
| 216 |
+
"harness|hendrycksTest-high_school_psychology|5": {
|
| 217 |
+
"acc": 0.8055045871559633,
|
| 218 |
+
"acc_stderr": 0.01697028909045804,
|
| 219 |
+
"acc_norm": 0.8055045871559633,
|
| 220 |
+
"acc_norm_stderr": 0.01697028909045804
|
| 221 |
+
},
|
| 222 |
+
"harness|hendrycksTest-high_school_statistics|5": {
|
| 223 |
+
"acc": 0.5370370370370371,
|
| 224 |
+
"acc_stderr": 0.03400603625538272,
|
| 225 |
+
"acc_norm": 0.5370370370370371,
|
| 226 |
+
"acc_norm_stderr": 0.03400603625538272
|
| 227 |
+
},
|
| 228 |
+
"harness|hendrycksTest-high_school_us_history|5": {
|
| 229 |
+
"acc": 0.7794117647058824,
|
| 230 |
+
"acc_stderr": 0.02910225438967407,
|
| 231 |
+
"acc_norm": 0.7794117647058824,
|
| 232 |
+
"acc_norm_stderr": 0.02910225438967407
|
| 233 |
+
},
|
| 234 |
+
"harness|hendrycksTest-high_school_world_history|5": {
|
| 235 |
+
"acc": 0.759493670886076,
|
| 236 |
+
"acc_stderr": 0.027820781981149685,
|
| 237 |
+
"acc_norm": 0.759493670886076,
|
| 238 |
+
"acc_norm_stderr": 0.027820781981149685
|
| 239 |
+
},
|
| 240 |
+
"harness|hendrycksTest-human_aging|5": {
|
| 241 |
+
"acc": 0.6636771300448431,
|
| 242 |
+
"acc_stderr": 0.031708824268455,
|
| 243 |
+
"acc_norm": 0.6636771300448431,
|
| 244 |
+
"acc_norm_stderr": 0.031708824268455
|
| 245 |
+
},
|
| 246 |
+
"harness|hendrycksTest-human_sexuality|5": {
|
| 247 |
+
"acc": 0.7251908396946565,
|
| 248 |
+
"acc_stderr": 0.03915345408847836,
|
| 249 |
+
"acc_norm": 0.7251908396946565,
|
| 250 |
+
"acc_norm_stderr": 0.03915345408847836
|
| 251 |
+
},
|
| 252 |
+
"harness|hendrycksTest-international_law|5": {
|
| 253 |
+
"acc": 0.71900826446281,
|
| 254 |
+
"acc_stderr": 0.04103203830514512,
|
| 255 |
+
"acc_norm": 0.71900826446281,
|
| 256 |
+
"acc_norm_stderr": 0.04103203830514512
|
| 257 |
+
},
|
| 258 |
+
"harness|hendrycksTest-jurisprudence|5": {
|
| 259 |
+
"acc": 0.7685185185185185,
|
| 260 |
+
"acc_stderr": 0.04077494709252626,
|
| 261 |
+
"acc_norm": 0.7685185185185185,
|
| 262 |
+
"acc_norm_stderr": 0.04077494709252626
|
| 263 |
+
},
|
| 264 |
+
"harness|hendrycksTest-logical_fallacies|5": {
|
| 265 |
+
"acc": 0.7177914110429447,
|
| 266 |
+
"acc_stderr": 0.03536117886664743,
|
| 267 |
+
"acc_norm": 0.7177914110429447,
|
| 268 |
+
"acc_norm_stderr": 0.03536117886664743
|
| 269 |
+
},
|
| 270 |
+
"harness|hendrycksTest-machine_learning|5": {
|
| 271 |
+
"acc": 0.41964285714285715,
|
| 272 |
+
"acc_stderr": 0.04684099321077106,
|
| 273 |
+
"acc_norm": 0.41964285714285715,
|
| 274 |
+
"acc_norm_stderr": 0.04684099321077106
|
| 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": 0.8974358974358975,
|
| 284 |
+
"acc_stderr": 0.019875655027867447,
|
| 285 |
+
"acc_norm": 0.8974358974358975,
|
| 286 |
+
"acc_norm_stderr": 0.019875655027867447
|
| 287 |
+
},
|
| 288 |
+
"harness|hendrycksTest-medical_genetics|5": {
|
| 289 |
+
"acc": 0.71,
|
| 290 |
+
"acc_stderr": 0.045604802157206845,
|
| 291 |
+
"acc_norm": 0.71,
|
| 292 |
+
"acc_norm_stderr": 0.045604802157206845
|
| 293 |
+
},
|
| 294 |
+
"harness|hendrycksTest-miscellaneous|5": {
|
| 295 |
+
"acc": 0.7918263090676884,
|
| 296 |
+
"acc_stderr": 0.014518592248904033,
|
| 297 |
+
"acc_norm": 0.7918263090676884,
|
| 298 |
+
"acc_norm_stderr": 0.014518592248904033
|
| 299 |
+
},
|
| 300 |
+
"harness|hendrycksTest-moral_disputes|5": {
|
| 301 |
+
"acc": 0.7052023121387283,
|
| 302 |
+
"acc_stderr": 0.024547617794803828,
|
| 303 |
+
"acc_norm": 0.7052023121387283,
|
| 304 |
+
"acc_norm_stderr": 0.024547617794803828
|
| 305 |
+
},
|
| 306 |
+
"harness|hendrycksTest-moral_scenarios|5": {
|
| 307 |
+
"acc": 0.4044692737430168,
|
| 308 |
+
"acc_stderr": 0.016414440917293147,
|
| 309 |
+
"acc_norm": 0.4044692737430168,
|
| 310 |
+
"acc_norm_stderr": 0.016414440917293147
|
| 311 |
+
},
|
| 312 |
+
"harness|hendrycksTest-nutrition|5": {
|
| 313 |
+
"acc": 0.7091503267973857,
|
| 314 |
+
"acc_stderr": 0.02600480036395213,
|
| 315 |
+
"acc_norm": 0.7091503267973857,
|
| 316 |
+
"acc_norm_stderr": 0.02600480036395213
|
| 317 |
+
},
|
| 318 |
+
"harness|hendrycksTest-philosophy|5": {
|
| 319 |
+
"acc": 0.707395498392283,
|
| 320 |
+
"acc_stderr": 0.02583989833487798,
|
| 321 |
+
"acc_norm": 0.707395498392283,
|
| 322 |
+
"acc_norm_stderr": 0.02583989833487798
|
| 323 |
+
},
|
| 324 |
+
"harness|hendrycksTest-prehistory|5": {
|
| 325 |
+
"acc": 0.6944444444444444,
|
| 326 |
+
"acc_stderr": 0.025630824975621355,
|
| 327 |
+
"acc_norm": 0.6944444444444444,
|
| 328 |
+
"acc_norm_stderr": 0.025630824975621355
|
| 329 |
+
},
|
| 330 |
+
"harness|hendrycksTest-professional_accounting|5": {
|
| 331 |
+
"acc": 0.4716312056737589,
|
| 332 |
+
"acc_stderr": 0.029779450957303055,
|
| 333 |
+
"acc_norm": 0.4716312056737589,
|
| 334 |
+
"acc_norm_stderr": 0.029779450957303055
|
| 335 |
+
},
|
| 336 |
+
"harness|hendrycksTest-professional_law|5": {
|
| 337 |
+
"acc": 0.4302477183833116,
|
| 338 |
+
"acc_stderr": 0.012645361435115233,
|
| 339 |
+
"acc_norm": 0.4302477183833116,
|
| 340 |
+
"acc_norm_stderr": 0.012645361435115233
|
| 341 |
+
},
|
| 342 |
+
"harness|hendrycksTest-professional_medicine|5": {
|
| 343 |
+
"acc": 0.6397058823529411,
|
| 344 |
+
"acc_stderr": 0.02916312857067073,
|
| 345 |
+
"acc_norm": 0.6397058823529411,
|
| 346 |
+
"acc_norm_stderr": 0.02916312857067073
|
| 347 |
+
},
|
| 348 |
+
"harness|hendrycksTest-professional_psychology|5": {
|
| 349 |
+
"acc": 0.6470588235294118,
|
| 350 |
+
"acc_stderr": 0.01933314202079716,
|
| 351 |
+
"acc_norm": 0.6470588235294118,
|
| 352 |
+
"acc_norm_stderr": 0.01933314202079716
|
| 353 |
+
},
|
| 354 |
+
"harness|hendrycksTest-public_relations|5": {
|
| 355 |
+
"acc": 0.6363636363636364,
|
| 356 |
+
"acc_stderr": 0.04607582090719976,
|
| 357 |
+
"acc_norm": 0.6363636363636364,
|
| 358 |
+
"acc_norm_stderr": 0.04607582090719976
|
| 359 |
+
},
|
| 360 |
+
"harness|hendrycksTest-security_studies|5": {
|
| 361 |
+
"acc": 0.6775510204081633,
|
| 362 |
+
"acc_stderr": 0.029923100563683906,
|
| 363 |
+
"acc_norm": 0.6775510204081633,
|
| 364 |
+
"acc_norm_stderr": 0.029923100563683906
|
| 365 |
+
},
|
| 366 |
+
"harness|hendrycksTest-sociology|5": {
|
| 367 |
+
"acc": 0.8208955223880597,
|
| 368 |
+
"acc_stderr": 0.027113286753111844,
|
| 369 |
+
"acc_norm": 0.8208955223880597,
|
| 370 |
+
"acc_norm_stderr": 0.027113286753111844
|
| 371 |
+
},
|
| 372 |
+
"harness|hendrycksTest-us_foreign_policy|5": {
|
| 373 |
+
"acc": 0.85,
|
| 374 |
+
"acc_stderr": 0.03588702812826371,
|
| 375 |
+
"acc_norm": 0.85,
|
| 376 |
+
"acc_norm_stderr": 0.03588702812826371
|
| 377 |
+
},
|
| 378 |
+
"harness|hendrycksTest-virology|5": {
|
| 379 |
+
"acc": 0.5,
|
| 380 |
+
"acc_stderr": 0.03892494720807614,
|
| 381 |
+
"acc_norm": 0.5,
|
| 382 |
+
"acc_norm_stderr": 0.03892494720807614
|
| 383 |
+
},
|
| 384 |
+
"harness|hendrycksTest-world_religions|5": {
|
| 385 |
+
"acc": 0.8245614035087719,
|
| 386 |
+
"acc_stderr": 0.029170885500727665,
|
| 387 |
+
"acc_norm": 0.8245614035087719,
|
| 388 |
+
"acc_norm_stderr": 0.029170885500727665
|
| 389 |
+
},
|
| 390 |
+
"harness|truthfulqa:mc|0": {
|
| 391 |
+
"mc1": 0.3157894736842105,
|
| 392 |
+
"mc1_stderr": 0.016272287957916923,
|
| 393 |
+
"mc2": 0.4868797251828956,
|
| 394 |
+
"mc2_stderr": 0.01529943410920313
|
| 395 |
+
},
|
| 396 |
+
"harness|winogrande|5": {
|
| 397 |
+
"acc": 0.7813733228097869,
|
| 398 |
+
"acc_stderr": 0.011616198215773239
|
| 399 |
+
},
|
| 400 |
+
"harness|gsm8k|5": {
|
| 401 |
+
"acc": 0.36087945413191813,
|
| 402 |
+
"acc_stderr": 0.013228626753925143
|
| 403 |
+
}
|
| 404 |
+
}
|
| 405 |
+
```
|
| 406 |
+
|
| 407 |
## 🧩 Configuration
|
| 408 |
|
| 409 |
```yaml
|