structroberta_s1_final / all_metrics_results.txt
EC2 Default User
l
3788a7a
cola: 0.707556426525116: 1019
sst2: 0.874015748500824: 508
mrpc: 0.7649402390438248: 177
qqp: 0.8170573479802784: 26889
mnli: 0.7160926461219788: 6562
mnli-mm: 0.7272437810897827: 6284
qnli: 0.712598443031311: 2286
rte: 0.46464645862579346: 99
boolq: 0.6556016802787781: 723
multirc: 0.6166484355926514: 913
wsc: 0.6144578456878662: 83
main_verb_control: 0.9599388241767883: 16350
control_raising_control: 0.8782693147659302: 13382
syntactic_category_control: 0.9465081095695496: 17741
relative_position_control: 0.963740885257721: 18092
lexical_content_the_control: 0.9999450445175171: 18200
main_verb_lexical_content_the: 0.6661840081214905: 22099
main_verb_relative_token_position: 0.6683009266853333: 24272
control_raising_lexical_content_the: 0.6650972962379456: 20603
control_raising_relative_token_position: 0.6671966314315796: 24531
syntactic_category_lexical_content_the: 0.7285891771316528: 23341
syntactic_category_relative_position: 0.6505087018013: 25849
anaphor_agreement: 0.8926380368098159: 0
argument_structure: 0.6892580019398642: 0
binding: 0.7224695755417038: 0
control_raising: 0.6942112240388865: 0
determiner_noun_agreement: 0.9185892336250332: 0
ellipsis: 0.7032332563510393: 0
filler_gap: 0.6864301276065982: 0
irregular_forms: 0.8284987277353689: 0
island_effects: 0.4850523168908819: 0
npi_licensing: 0.5472213786820529: 0
quantifiers: 0.7058217413704276: 0
subject_verb_agreement: 0.7544715447154472: 0
hypernym: 0.4848837209302326: 0
qa_congruence_easy: 0.640625: 0
qa_congruence_tricky: 0.28484848484848485: 0
subject_aux_inversion: 0.7013905830690412: 0
turn_taking: 0.6107142857142858: 0