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

1	dataset	prompt	metric	value
2	xcopa_zh	C1 or C2? premise_zhht	accuracy	0.55
3	xcopa_zh	best_option_zhht	accuracy	0.67
4	xcopa_zh	cause_effect_zhht	accuracy	0.79
5	xcopa_zh	i_am_hesitating_zhht	accuracy	0.77
6	xcopa_zh	plausible_alternatives_zhht	accuracy	0.75
7	xcopa_zh	median	accuracy	0.75
8	xstory_cloze_zh	Answer Given options_zhht	accuracy	0.7054930509596293
9	xstory_cloze_zh	Choose Story Ending_zhht	accuracy	0.7948378557246857
10	xstory_cloze_zh	Generate Ending_zhht	accuracy	0.6366644606221046
11	xstory_cloze_zh	Novel Correct Ending_zhht	accuracy	0.7782925215089345
12	xstory_cloze_zh	Story Continuation and Options_zhht	accuracy	0.771012574454004
13	xstory_cloze_zh	median	accuracy	0.771012574454004
14	xwinograd_zh	Replace_zhht	accuracy	0.5178571428571429
15	xwinograd_zh	True or False_zhht	accuracy	0.5218253968253969
16	xwinograd_zh	does underscore refer to_zhht	accuracy	0.4662698412698413
17	xwinograd_zh	stand for_zhht	accuracy	0.49404761904761907
18	xwinograd_zh	underscore refer to_zhht	accuracy	0.44047619047619047
19	xwinograd_zh	median	accuracy	0.49404761904761907
20	multiple	average	multiple	0.6716867311672077