Create README.md
3a9acf4
verified
Tasks |
Version |
Filter |
n-shot |
Metric |
Value |
± |
Stderr |
assin2_rte |
1.1 |
all |
15 |
f1_macro |
0.9358 |
± |
0.0035 |
|
|
all |
15 |
acc |
0.9359 |
± |
0.0035 |
assin2_sts |
1.1 |
all |
15 |
pearson |
0.7803 |
± |
0.0068 |
|
|
all |
15 |
mse |
0.5815 |
± |
N/A |
bluex |
1.1 |
all |
3 |
acc |
0.6745 |
± |
0.0101 |
|
|
exam_id__USP_2019 |
3 |
acc |
0.5500 |
± |
0.0453 |
|
|
exam_id__UNICAMP_2021_1 |
3 |
acc |
0.5870 |
± |
0.0418 |
|
|
exam_id__USP_2020 |
3 |
acc |
0.6250 |
± |
0.0373 |
|
|
exam_id__USP_2022 |
3 |
acc |
0.6939 |
± |
0.0381 |
|
|
exam_id__UNICAMP_2019 |
3 |
acc |
0.7200 |
± |
0.0367 |
|
|
exam_id__UNICAMP_2024 |
3 |
acc |
0.5778 |
± |
0.0425 |
|
|
exam_id__USP_2018 |
3 |
acc |
0.5926 |
± |
0.0385 |
|
|
exam_id__USP_2021 |
3 |
acc |
0.6538 |
± |
0.0381 |
|
|
exam_id__UNICAMP_2023 |
3 |
acc |
0.7442 |
± |
0.0385 |
|
|
exam_id__UNICAMP_2021_2 |
3 |
acc |
0.6667 |
± |
0.0380 |
|
|
exam_id__UNICAMP_2020 |
3 |
acc |
0.7091 |
± |
0.0355 |
|
|
exam_id__USP_2023 |
3 |
acc |
0.8182 |
± |
0.0336 |
|
|
exam_id__USP_2024 |
3 |
acc |
0.8537 |
± |
0.0318 |
|
|
exam_id__UNICAMP_2022 |
3 |
acc |
0.6667 |
± |
0.0435 |
|
|
exam_id__UNICAMP_2018 |
3 |
acc |
0.6852 |
± |
0.0364 |
enem |
1.1 |
all |
3 |
acc |
0.8062 |
± |
0.0060 |
|
|
exam_id__2016_2 |
3 |
acc |
0.7967 |
± |
0.0210 |
|
|
exam_id__2014 |
3 |
acc |
0.8165 |
± |
0.0214 |
|
|
exam_id__2010 |
3 |
acc |
0.8291 |
± |
0.0202 |
|
|
exam_id__2023 |
3 |
acc |
0.8000 |
± |
0.0199 |
|
|
exam_id__2009 |
3 |
acc |
0.7913 |
± |
0.0219 |
|
|
exam_id__2017 |
3 |
acc |
0.7931 |
± |
0.0217 |
|
|
exam_id__2011 |
3 |
acc |
0.8718 |
± |
0.0178 |
|
|
exam_id__2015 |
3 |
acc |
0.8151 |
± |
0.0205 |
|
|
exam_id__2012 |
3 |
acc |
0.8621 |
± |
0.0185 |
|
|
exam_id__2016 |
3 |
acc |
0.8430 |
± |
0.0190 |
|
|
exam_id__2013 |
3 |
acc |
0.7870 |
± |
0.0228 |
|
|
exam_id__2022 |
3 |
acc |
0.6842 |
± |
0.0233 |
faquad_nli |
1.1 |
all |
15 |
f1_macro |
0.4545 |
± |
0.0081 |
|
|
all |
15 |
acc |
0.7877 |
± |
0.0113 |
hatebr_offensive_binary |
1.0 |
all |
25 |
f1_macro |
0.7212 |
± |
0.0087 |
|
|
all |
25 |
acc |
0.7393 |
± |
0.0083 |
oab_exams |
1.5 |
all |
3 |
acc |
0.5718 |
± |
0.0061 |
|
|
exam_id__2014-15 |
3 |
acc |
0.6795 |
± |
0.0305 |
|
|
exam_id__2012-09 |
3 |
acc |
0.4805 |
± |
0.0329 |
... |
|
|
|
|
|
|
|