Cabra-72b / README.md
nicolasdec's picture
Create README.md
3a9acf4 verified
|
raw
history blame
4.62 kB
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
...