Update README.md
Browse files
README.md
CHANGED
|
@@ -86,4 +86,85 @@ Parseable: 167.0
|
|
| 86 |
Batch completed
|
| 87 |
Time taken: 178.3 mins
|
| 88 |
---------------
|
| 89 |
-
</pre>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
Batch completed
|
| 87 |
Time taken: 178.3 mins
|
| 88 |
---------------
|
| 89 |
+
</pre>
|
| 90 |
+
|
| 91 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
| 92 |
+
|---------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
| 93 |
+
|[OmniCorso-7B](https://huggingface.co/macadeliccc/OmniCorso-7B)| 45.89| 77.66| 74.12| 49.24| 61.73|
|
| 94 |
+
|
| 95 |
+
### AGIEval
|
| 96 |
+
| Task |Version| Metric |Value| |Stderr|
|
| 97 |
+
|------------------------------|------:|--------|----:|---|-----:|
|
| 98 |
+
|agieval_aqua_rat | 0|acc |29.13|± | 2.86|
|
| 99 |
+
| | |acc_norm|27.17|± | 2.80|
|
| 100 |
+
|agieval_logiqa_en | 0|acc |39.32|± | 1.92|
|
| 101 |
+
| | |acc_norm|39.63|± | 1.92|
|
| 102 |
+
|agieval_lsat_ar | 0|acc |23.91|± | 2.82|
|
| 103 |
+
| | |acc_norm|23.91|± | 2.82|
|
| 104 |
+
|agieval_lsat_lr | 0|acc |53.14|± | 2.21|
|
| 105 |
+
| | |acc_norm|53.92|± | 2.21|
|
| 106 |
+
|agieval_lsat_rc | 0|acc |66.54|± | 2.88|
|
| 107 |
+
| | |acc_norm|67.29|± | 2.87|
|
| 108 |
+
|agieval_sat_en | 0|acc |80.58|± | 2.76|
|
| 109 |
+
| | |acc_norm|80.58|± | 2.76|
|
| 110 |
+
|agieval_sat_en_without_passage| 0|acc |45.63|± | 3.48|
|
| 111 |
+
| | |acc_norm|43.69|± | 3.46|
|
| 112 |
+
|agieval_sat_math | 0|acc |33.18|± | 3.18|
|
| 113 |
+
| | |acc_norm|30.91|± | 3.12|
|
| 114 |
+
|
| 115 |
+
Average: 45.89%
|
| 116 |
+
|
| 117 |
+
### GPT4All
|
| 118 |
+
| Task |Version| Metric |Value| |Stderr|
|
| 119 |
+
|-------------|------:|--------|----:|---|-----:|
|
| 120 |
+
|arc_challenge| 0|acc |67.32|± | 1.37|
|
| 121 |
+
| | |acc_norm|68.43|± | 1.36|
|
| 122 |
+
|arc_easy | 0|acc |87.46|± | 0.68|
|
| 123 |
+
| | |acc_norm|83.50|± | 0.76|
|
| 124 |
+
|boolq | 1|acc |88.13|± | 0.57|
|
| 125 |
+
|hellaswag | 0|acc |68.47|± | 0.46|
|
| 126 |
+
| | |acc_norm|86.96|± | 0.34|
|
| 127 |
+
|openbookqa | 0|acc |38.80|± | 2.18|
|
| 128 |
+
| | |acc_norm|50.00|± | 2.24|
|
| 129 |
+
|piqa | 0|acc |83.03|± | 0.88|
|
| 130 |
+
| | |acc_norm|85.31|± | 0.83|
|
| 131 |
+
|winogrande | 0|acc |81.29|± | 1.10|
|
| 132 |
+
|
| 133 |
+
Average: 77.66%
|
| 134 |
+
|
| 135 |
+
### TruthfulQA
|
| 136 |
+
| Task |Version|Metric|Value| |Stderr|
|
| 137 |
+
|-------------|------:|------|----:|---|-----:|
|
| 138 |
+
|truthfulqa_mc| 1|mc1 |58.26|± | 1.73|
|
| 139 |
+
| | |mc2 |74.12|± | 1.43|
|
| 140 |
+
|
| 141 |
+
Average: 74.12%
|
| 142 |
+
|
| 143 |
+
### Bigbench
|
| 144 |
+
| Task |Version| Metric |Value| |Stderr|
|
| 145 |
+
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|
| 146 |
+
|bigbench_causal_judgement | 0|multiple_choice_grade|56.84|± | 3.60|
|
| 147 |
+
|bigbench_date_understanding | 0|multiple_choice_grade|63.41|± | 2.51|
|
| 148 |
+
|bigbench_disambiguation_qa | 0|multiple_choice_grade|49.22|± | 3.12|
|
| 149 |
+
|bigbench_geometric_shapes | 0|multiple_choice_grade|23.96|± | 2.26|
|
| 150 |
+
| | |exact_str_match | 1.39|± | 0.62|
|
| 151 |
+
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|34.20|± | 2.12|
|
| 152 |
+
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|23.71|± | 1.61|
|
| 153 |
+
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|60.33|± | 2.83|
|
| 154 |
+
|bigbench_movie_recommendation | 0|multiple_choice_grade|49.00|± | 2.24|
|
| 155 |
+
|bigbench_navigate | 0|multiple_choice_grade|55.20|± | 1.57|
|
| 156 |
+
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|70.75|± | 1.02|
|
| 157 |
+
|bigbench_ruin_names | 0|multiple_choice_grade|55.80|± | 2.35|
|
| 158 |
+
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|36.97|± | 1.53|
|
| 159 |
+
|bigbench_snarks | 0|multiple_choice_grade|72.38|± | 3.33|
|
| 160 |
+
|bigbench_sports_understanding | 0|multiple_choice_grade|76.27|± | 1.36|
|
| 161 |
+
|bigbench_temporal_sequences | 0|multiple_choice_grade|54.50|± | 1.58|
|
| 162 |
+
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|23.12|± | 1.19|
|
| 163 |
+
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|20.34|± | 0.96|
|
| 164 |
+
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|60.33|± | 2.83|
|
| 165 |
+
|
| 166 |
+
Average: 49.24%
|
| 167 |
+
|
| 168 |
+
Average score: 61.73%
|
| 169 |
+
|
| 170 |
+
Elapsed time: 02:20:06
|