Commit 8c997e53 authored by jon-tow's avatar jon-tow
Browse files

Revert `tests/testdata` changes and address flake8 issues

parent d95a4333
{"results": {"headqa": {"acc": 0.23559445660102116, "acc_norm": 0.25018234865062, "acc_norm_stderr": 0.008272783230806014, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa": 0}}
{"results": {"headqa": {"acc": 0.23559445660102116, "acc_norm": 0.25018234865062, "acc_norm_stderr": 0.008272783230806014, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa": 0}}
\ No newline at end of file
09da45119b12a0144e3081f8fb790c2a22af7b9c3aac42f54423d348a711fbf5
09da45119b12a0144e3081f8fb790c2a22af7b9c3aac42f54423d348a711fbf5
\ No newline at end of file
{"results": {"headqa_en": {"acc": 0.23559445660102116, "acc_norm": 0.2447118891320204, "acc_norm_stderr": 0.008211629406841468, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_en": 0}}
{"results": {"headqa_en": {"acc": 0.23559445660102116, "acc_norm": 0.2447118891320204, "acc_norm_stderr": 0.008211629406841468, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_en": 0}}
\ No newline at end of file
767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f
767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f
\ No newline at end of file
{"results": {"headqa_es": {"acc": 0.23559445660102116, "acc_norm": 0.25018234865062, "acc_norm_stderr": 0.008272783230806014, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_es": 0}}
{"results": {"headqa_es": {"acc": 0.23559445660102116, "acc_norm": 0.25018234865062, "acc_norm_stderr": 0.008272783230806014, "acc_stderr": 0.008105688874297972}}, "versions": {"headqa_es": 0}}
\ No newline at end of file
abb808c97d6529eda6c11067837a132c62d25cba0394d720f80cca6df9f7196e
abb808c97d6529eda6c11067837a132c62d25cba0394d720f80cca6df9f7196e
\ No newline at end of file
{"results": {"hellaswag": {"acc": 0.24965146385182235, "acc_norm": 0.24756024696275641, "acc_norm_stderr": 0.004307128573285236, "acc_stderr": 0.004319267432460666}}, "versions": {"hellaswag": 0}}
{"results": {"hellaswag": {"acc": 0.24965146385182235, "acc_norm": 0.24756024696275641, "acc_norm_stderr": 0.004307128573285236, "acc_stderr": 0.004319267432460666}}, "versions": {"hellaswag": 0}}
\ No newline at end of file
e35d1eeb356ac1084d4e9773f028cb3c81ba1c6e5574d598ac4a78aa467cd797
e35d1eeb356ac1084d4e9773f028cb3c81ba1c6e5574d598ac4a78aa467cd797
\ No newline at end of file
{"results": {"hendrycksTest-abstract_algebra": {"acc": 0.32, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235, "acc_stderr": 0.04688261722621504}}, "versions": {"hendrycksTest-abstract_algebra": 0}}
{"results": {"hendrycksTest-abstract_algebra": {"acc": 0.32, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235, "acc_stderr": 0.04688261722621504}}, "versions": {"hendrycksTest-abstract_algebra": 0}}
\ No newline at end of file
bf05e04ed8cf61cf3aad294ed3f5a16137775ffdd20f1b129022ddffc1251768
bf05e04ed8cf61cf3aad294ed3f5a16137775ffdd20f1b129022ddffc1251768
\ No newline at end of file
{"results": {"hendrycksTest-anatomy": {"acc": 0.2222222222222222, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.03673731683969506, "acc_stderr": 0.0359144408419697}}, "versions": {"hendrycksTest-anatomy": 0}}
{"results": {"hendrycksTest-anatomy": {"acc": 0.2222222222222222, "acc_norm": 0.23703703703703705, "acc_norm_stderr": 0.03673731683969506, "acc_stderr": 0.0359144408419697}}, "versions": {"hendrycksTest-anatomy": 0}}
\ No newline at end of file
bed1e47127cc2893c6aef63b9a0909cca31aa351a703da2a166b01cae03c3311
bed1e47127cc2893c6aef63b9a0909cca31aa351a703da2a166b01cae03c3311
\ No newline at end of file
{"results": {"hendrycksTest-astronomy": {"acc": 0.2565789473684211, "acc_norm": 0.29605263157894735, "acc_norm_stderr": 0.03715062154998904, "acc_stderr": 0.0355418036802569}}, "versions": {"hendrycksTest-astronomy": 0}}
{"results": {"hendrycksTest-astronomy": {"acc": 0.2565789473684211, "acc_norm": 0.29605263157894735, "acc_norm_stderr": 0.03715062154998904, "acc_stderr": 0.0355418036802569}}, "versions": {"hendrycksTest-astronomy": 0}}
\ No newline at end of file
b3b27e9dbad587377d3c8cab1072782de883e245da93a563bd8b3099017b1fc0
b3b27e9dbad587377d3c8cab1072782de883e245da93a563bd8b3099017b1fc0
\ No newline at end of file
{"results": {"hendrycksTest-business_ethics": {"acc": 0.29, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394, "acc_stderr": 0.045604802157206845}}, "versions": {"hendrycksTest-business_ethics": 0}}
{"results": {"hendrycksTest-business_ethics": {"acc": 0.29, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394, "acc_stderr": 0.045604802157206845}}, "versions": {"hendrycksTest-business_ethics": 0}}
\ No newline at end of file
fbcb7ce507e0675d811e71e10a67c8d05a6605e29036f46776e04a6588cefbda
fbcb7ce507e0675d811e71e10a67c8d05a6605e29036f46776e04a6588cefbda
\ No newline at end of file
{"results": {"hendrycksTest-clinical_knowledge": {"acc": 0.23773584905660378, "acc_norm": 0.27169811320754716, "acc_norm_stderr": 0.027377706624670713, "acc_stderr": 0.02619980880756191}}, "versions": {"hendrycksTest-clinical_knowledge": 0}}
{"results": {"hendrycksTest-clinical_knowledge": {"acc": 0.23773584905660378, "acc_norm": 0.27169811320754716, "acc_norm_stderr": 0.027377706624670713, "acc_stderr": 0.02619980880756191}}, "versions": {"hendrycksTest-clinical_knowledge": 0}}
\ No newline at end of file
c29e4e67ff91af29b9434884874414d1b1b32ccc32903c6b1639469b19907419
c29e4e67ff91af29b9434884874414d1b1b32ccc32903c6b1639469b19907419
\ No newline at end of file
{"results": {"hendrycksTest-college_biology": {"acc": 0.24305555555555555, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826, "acc_stderr": 0.03586879280080341}}, "versions": {"hendrycksTest-college_biology": 0}}
{"results": {"hendrycksTest-college_biology": {"acc": 0.24305555555555555, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826, "acc_stderr": 0.03586879280080341}}, "versions": {"hendrycksTest-college_biology": 0}}
\ No newline at end of file
044752b21540db95118b8cbe7e75c4c9b8758e27df56543deaeadec7f749a28d
044752b21540db95118b8cbe7e75c4c9b8758e27df56543deaeadec7f749a28d
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment