structroberta_sx_final / all_metrics_results.txt
EC2 Default User
p
a5e0a85
raw
history blame
1.64 kB
cola: 0.7114818692207336: 1019
sst2: 0.8602362275123596: 508
mrpc: 0.7722007722007722: 177
qqp: 0.8048906048906048: 26889
mnli: 0.6892715692520142: 6562
mnli-mm: 0.704805850982666: 6284
qnli: 0.6561679840087891: 2286
rte: 0.5252525210380554: 99
boolq: 0.6403872966766357: 723
multirc: 0.5925520062446594: 913
wsc: 0.6144578456878662: 83
main_verb_control: 0.9900305867195129: 16350
control_raising_control: 0.917276918888092: 13382
syntactic_category_control: 0.9147173166275024: 17741
relative_position_control: 0.9935883283615112: 18092
lexical_content_the_control: 0.9991208910942078: 18200
main_verb_lexical_content_the: 0.6656862497329712: 22099
main_verb_relative_token_position: 0.673038899898529: 24272
control_raising_lexical_content_the: 0.6819880604743958: 20603
control_raising_relative_token_position: 0.6678488254547119: 24531
syntactic_category_lexical_content_the: 0.7269611358642578: 23341
syntactic_category_relative_position: 0.680683970451355: 25849
anaphor_agreement: 0.8951942740286298: 0
argument_structure: 0.7269641125121241: 0
binding: 0.7025823686553874: 0
control_raising: 0.6785240830755634: 0
determiner_noun_agreement: 0.9323786793953859: 0
ellipsis: 0.7661662817551963: 0
filler_gap: 0.7421413009648303: 0
irregular_forms: 0.8478371501272265: 0
island_effects: 0.523542600896861: 0
npi_licensing: 0.6840267233525661: 0
quantifiers: 0.6798042246264812: 0
subject_verb_agreement: 0.7636856368563686: 0
hypernym: 0.5023255813953489: 0
qa_congruence_easy: 0.65625: 0
qa_congruence_tricky: 0.28484848484848485: 0
subject_aux_inversion: 0.7557940961210051: 0
turn_taking: 0.6: 0