Merge branch 'master' of https://github.com/EleutherAI/lm-evaluation-harness into task-guide

4d147bdd · Jonathan Tow · 011cc891 · dc937d4b · 4d147bdd · 4d147bdd
Commit 4d147bdd authored Sep 17, 2021 by Jonathan Tow
20 changed files
--- a/tests/testdata/ethics_virtue-v0-res.json
+++ b/tests/testdata/ethics_virtue-v0-res.json
+{"results": {"ethics_virtue": {"acc": 0.5035175879396985, "acc_stderr": 0.0070893491553555765, "em": 0.036180904522613064}}, "versions": {"ethics_virtue": 0}}
\ No newline at end of file
--- a/tests/testdata/gpt3_test_0deb8e9bde8e8327bbc48157f638ff3ba06b0cd816dad2beb8ad90f7fbe795c7.pkl
+++ b/tests/testdata/gpt3_test_0deb8e9bde8e8327bbc48157f638ff3ba06b0cd816dad2beb8ad90f7fbe795c7.pkl
--- a/tests/testdata/gpt3_test_57ec3d53a1dca09a4d4eca161692ad3c5f42b1a033d1315ce096ff67eb45f4b8.pkl
+++ b/tests/testdata/gpt3_test_57ec3d53a1dca09a4d4eca161692ad3c5f42b1a033d1315ce096ff67eb45f4b8.pkl
--- a/tests/testdata/gpt3_test_6e1182575a66b5d7fd9cfd5276d4f77d00932dc587870352e881c10347e00bc5.pkl
+++ b/tests/testdata/gpt3_test_6e1182575a66b5d7fd9cfd5276d4f77d00932dc587870352e881c10347e00bc5.pkl
--- a/tests/testdata/gpt3_test_8025023377febbd8c5f2b9f26705c394ff375d0cad7c89c10fd9b8e1eb66ff1c.pkl
+++ b/tests/testdata/gpt3_test_8025023377febbd8c5f2b9f26705c394ff375d0cad7c89c10fd9b8e1eb66ff1c.pkl
--- a/tests/testdata/gpt3_test_823a1a729bdb9f91884b1b986b2fa400aabd8436224328b60fa2314d43e779d2.pkl
+++ b/tests/testdata/gpt3_test_823a1a729bdb9f91884b1b986b2fa400aabd8436224328b60fa2314d43e779d2.pkl
--- a/tests/testdata/gpt3_test_941d8b6f1eba82d9575bbdc7053ec97fc8d77844679199101d00f1096c133a83.pkl
+++ b/tests/testdata/gpt3_test_941d8b6f1eba82d9575bbdc7053ec97fc8d77844679199101d00f1096c133a83.pkl
--- a/tests/testdata/gpt3_test_b795dbbd09256ac8c903e9f7e6dd247aad0dd32cd17108f9e8fa628b9424b9da.pkl
+++ b/tests/testdata/gpt3_test_b795dbbd09256ac8c903e9f7e6dd247aad0dd32cd17108f9e8fa628b9424b9da.pkl
--- a/tests/testdata/gpt3_test_f307d52964c295e2005c5e782b688c24388e0cecadf29f1e6fc7f394236ea9c0.pkl
+++ b/tests/testdata/gpt3_test_f307d52964c295e2005c5e782b688c24388e0cecadf29f1e6fc7f394236ea9c0.pkl
--- a/tests/testdata/headqa-v0-loglikelihood
+++ b/tests/testdata/headqa-v0-loglikelihood
+767ca34d9714edd9fb030ddbcc35a64e5180d1e247b0cb557fbb22fdf971ad1f
\ No newline at end of file
--- a/tests/testdata/headqa-v0-res.json
+++ b/tests/testdata/headqa-v0-res.json
+{"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
--- a/tests/testdata/hellaswag-v0-loglikelihood
+++ b/tests/testdata/hellaswag-v0-loglikelihood
+abb808c97d6529eda6c11067837a132c62d25cba0394d720f80cca6df9f7196e
\ No newline at end of file
--- a/tests/testdata/hellaswag-v0-res.json
+++ b/tests/testdata/hellaswag-v0-res.json
+{"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
--- a/tests/testdata/hendrycksTest-abstract_algebra-v0-loglikelihood
+++ b/tests/testdata/hendrycksTest-abstract_algebra-v0-loglikelihood
+e35d1eeb356ac1084d4e9773f028cb3c81ba1c6e5574d598ac4a78aa467cd797
\ No newline at end of file
--- a/tests/testdata/hendrycksTest-abstract_algebra-v0-res.json
+++ b/tests/testdata/hendrycksTest-abstract_algebra-v0-res.json
+{"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
--- a/tests/testdata/hendrycksTest-anatomy-v0-loglikelihood
+++ b/tests/testdata/hendrycksTest-anatomy-v0-loglikelihood
+bf05e04ed8cf61cf3aad294ed3f5a16137775ffdd20f1b129022ddffc1251768
\ No newline at end of file
--- a/tests/testdata/hendrycksTest-anatomy-v0-res.json
+++ b/tests/testdata/hendrycksTest-anatomy-v0-res.json
+{"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
--- a/tests/testdata/hendrycksTest-astronomy-v0-loglikelihood
+++ b/tests/testdata/hendrycksTest-astronomy-v0-loglikelihood
+bed1e47127cc2893c6aef63b9a0909cca31aa351a703da2a166b01cae03c3311
\ No newline at end of file
--- a/tests/testdata/hendrycksTest-astronomy-v0-res.json
+++ b/tests/testdata/hendrycksTest-astronomy-v0-res.json
+{"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
--- a/tests/testdata/hendrycksTest-business_ethics-v0-loglikelihood
+++ b/tests/testdata/hendrycksTest-business_ethics-v0-loglikelihood
+b3b27e9dbad587377d3c8cab1072782de883e245da93a563bd8b3099017b1fc0
\ No newline at end of file