structroberta_s2_final / all_metrics_results.txt
EC2 Default User
i
6cee8b2
raw
history blame contribute delete
No virus
1.65 kB
cola: 0.7006869316101074: 1019
sst2: 0.8248031735420227: 508
mrpc: 0.8102189781021898: 177
qqp: 0.8182447038478167: 26889
mnli: 0.7163974642753601: 6562
mnli-mm: 0.72835773229599: 6284
qnli: 0.7230970859527588: 2286
rte: 0.5656565427780151: 99
boolq: 0.658367931842804: 723
multirc: 0.5903614163398743: 913
wsc: 0.5903614163398743: 83
main_verb_control: 0.9953516721725464: 16350
control_raising_control: 0.880810022354126: 13382
syntactic_category_control: 0.9285835027694702: 17741
relative_position_control: 0.98629230260849: 18092
lexical_content_the_control: 0.9949450492858887: 18200
main_verb_lexical_content_the: 0.666229248046875: 22099
main_verb_relative_token_position: 0.6702373027801514: 24272
control_raising_lexical_content_the: 0.6656312346458435: 20603
control_raising_relative_token_position: 0.6673596501350403: 24531
syntactic_category_lexical_content_the: 0.6893877983093262: 23341
syntactic_category_relative_position: 0.6425006985664368: 25849
anaphor_agreement: 0.873721881390593: 0
argument_structure: 0.7229631425800194: 0
binding: 0.6996141288216088: 0
control_raising: 0.7030490499337163: 0
determiner_noun_agreement: 0.9256165473349244: 0
ellipsis: 0.7055427251732102: 0
filler_gap: 0.6651104886399004: 0
irregular_forms: 0.9180661577608142: 0
island_effects: 0.45104633781763825: 0
npi_licensing: 0.5939872456726389: 0
quantifiers: 0.6813498196805771: 0
subject_verb_agreement: 0.7457994579945799: 0
hypernym: 0.4813953488372093: 0
qa_congruence_easy: 0.6875: 0
qa_congruence_tricky: 0.3393939393939394: 0
subject_aux_inversion: 0.708709441327153: 0
turn_taking: 0.5857142857142857: 0