bloomz-7b1-p3/evaluation_bloomz-7b1-p3/evaluation_xwinostorycopamt/merged.csv

1	dataset	prompt	metric	value
2	xcopa_id	C1 or C2? premise_idmt	accuracy	0.51
3	xcopa_id	best_option_idmt	accuracy	0.53
4	xcopa_id	cause_effect_idmt	accuracy	0.69
5	xcopa_id	i_am_hesitating_idmt	accuracy	0.64
6	xcopa_id	plausible_alternatives_idmt	accuracy	0.7
7	xcopa_id	median	accuracy	0.64
8	xcopa_sw	C1 or C2? premise_swmt	accuracy	0.6
9	xcopa_sw	best_option_swmt	accuracy	0.62
10	xcopa_sw	cause_effect_swmt	accuracy	0.49
11	xcopa_sw	i_am_hesitating_swmt	accuracy	0.56
12	xcopa_sw	plausible_alternatives_swmt	accuracy	0.54
13	xcopa_sw	median	accuracy	0.56
14	xcopa_ta	C1 or C2? premise_tamt	accuracy	0.52
15	xcopa_ta	best_option_tamt	accuracy	0.55
16	xcopa_ta	cause_effect_tamt	accuracy	0.63
17	xcopa_ta	i_am_hesitating_tamt	accuracy	0.63
18	xcopa_ta	plausible_alternatives_tamt	accuracy	0.66
19	xcopa_ta	median	accuracy	0.63
20	xcopa_vi	C1 or C2? premise_vimt	accuracy	0.55
21	xcopa_vi	best_option_vimt	accuracy	0.61
22	xcopa_vi	cause_effect_vimt	accuracy	0.64
23	xcopa_vi	i_am_hesitating_vimt	accuracy	0.6
24	xcopa_vi	plausible_alternatives_vimt	accuracy	0.64
25	xcopa_vi	median	accuracy	0.61
26	xcopa_zh	C1 or C2? premise_zhmt	accuracy	0.52
27	xcopa_zh	best_option_zhmt	accuracy	0.61
28	xcopa_zh	cause_effect_zhmt	accuracy	0.75
29	xcopa_zh	i_am_hesitating_zhmt	accuracy	0.72
30	xcopa_zh	plausible_alternatives_zhmt	accuracy	0.76
31	xcopa_zh	median	accuracy	0.72
32	xstory_cloze_ar	Answer Given options_armt	accuracy	0.7061548643282595
33	xstory_cloze_ar	Choose Story Ending_armt	accuracy	0.786896095301125
34	xstory_cloze_ar	Generate Ending_armt	accuracy	0.600926538716082
35	xstory_cloze_ar	Novel Correct Ending_armt	accuracy	0.7511581733951026
36	xstory_cloze_ar	Story Continuation and Options_armt	accuracy	0.757114493712773
37	xstory_cloze_ar	median	accuracy	0.7511581733951026
38	xstory_cloze_es	Answer Given options_esmt	accuracy	0.7902051621442753
39	xstory_cloze_es	Choose Story Ending_esmt	accuracy	0.8160158835208471
40	xstory_cloze_es	Generate Ending_esmt	accuracy	0.657180675049636
41	xstory_cloze_es	Novel Correct Ending_esmt	accuracy	0.784910655195235
42	xstory_cloze_es	Story Continuation and Options_esmt	accuracy	0.7696889477167439
43	xstory_cloze_es	median	accuracy	0.784910655195235
44	xstory_cloze_eu	Answer Given options_eumt	accuracy	0.6227663798808736
45	xstory_cloze_eu	Choose Story Ending_eumt	accuracy	0.6763732627399074
46	xstory_cloze_eu	Generate Ending_eumt	accuracy	0.5737921906022502
47	xstory_cloze_eu	Novel Correct Ending_eumt	accuracy	0.686300463269358
48	xstory_cloze_eu	Story Continuation and Options_eumt	accuracy	0.6637988087359364
49	xstory_cloze_eu	median	accuracy	0.6637988087359364
50	xstory_cloze_hi	Answer Given options_himt	accuracy	0.6697551290536069
51	xstory_cloze_hi	Choose Story Ending_himt	accuracy	0.7160820648577101
52	xstory_cloze_hi	Generate Ending_himt	accuracy	0.5923229649238915
53	xstory_cloze_hi	Novel Correct Ending_himt	accuracy	0.6882859033752482
54	xstory_cloze_hi	Story Continuation and Options_himt	accuracy	0.7048312375909993
55	xstory_cloze_hi	median	accuracy	0.6882859033752482
56	xstory_cloze_id	Answer Given options_idmt	accuracy	0.7346128391793514
57	xstory_cloze_id	Choose Story Ending_idmt	accuracy	0.7511581733951026
58	xstory_cloze_id	Generate Ending_idmt	accuracy	0.6201191264063534
59	xstory_cloze_id	Novel Correct Ending_idmt	accuracy	0.728656518861681
60	xstory_cloze_id	Story Continuation and Options_idmt	accuracy	0.7412309728656519
61	xstory_cloze_id	median	accuracy	0.7346128391793514
62	xstory_cloze_zh	Answer Given options_zhmt	accuracy	0.7425545996029119
63	xstory_cloze_zh	Choose Story Ending_zhmt	accuracy	0.7941760423560555
64	xstory_cloze_zh	Generate Ending_zhmt	accuracy	0.6247518199867638
65	xstory_cloze_zh	Novel Correct Ending_zhmt	accuracy	0.7842488418266049
66	xstory_cloze_zh	Story Continuation and Options_zhmt	accuracy	0.8034414295168762
67	xstory_cloze_zh	median	accuracy	0.7842488418266049
68	xwinograd_fr	Replace_frmt	accuracy	0.5180722891566265
69	xwinograd_fr	True or False_frmt	accuracy	0.46987951807228917
70	xwinograd_fr	does underscore refer to_frmt	accuracy	0.5421686746987951
71	xwinograd_fr	stand for_frmt	accuracy	0.5060240963855421
72	xwinograd_fr	underscore refer to_frmt	accuracy	0.5421686746987951
73	xwinograd_fr	median	accuracy	0.5180722891566265
74	xwinograd_pt	Replace_ptmt	accuracy	0.5057034220532319
75	xwinograd_pt	True or False_ptmt	accuracy	0.5133079847908745
76	xwinograd_pt	does underscore refer to_ptmt	accuracy	0.5209125475285171
77	xwinograd_pt	stand for_ptmt	accuracy	0.5209125475285171
78	xwinograd_pt	underscore refer to_ptmt	accuracy	0.49049429657794674
79	xwinograd_pt	median	accuracy	0.5133079847908745
80	xwinograd_zh	Replace_zhmt	accuracy	0.5238095238095238
81	xwinograd_zh	True or False_zhmt	accuracy	0.5138888888888888
82	xwinograd_zh	does underscore refer to_zhmt	accuracy	0.49404761904761907
83	xwinograd_zh	stand for_zhmt	accuracy	0.49603174603174605
84	xwinograd_zh	underscore refer to_zhmt	accuracy	0.503968253968254
85	xwinograd_zh	median	accuracy	0.503968253968254
86	multiple	average	multiple	0.6501688392588024