Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- lm-evaluation-harness/tests/testdata/pile_pile-cc-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_pile-cc-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_pile-cc-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-central-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-central-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-central-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_pubmed-central-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_stackexchange-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_stackexchange-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_stackexchange-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_stackexchange-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_uspto-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_uspto-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_uspto-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_uspto-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_wikipedia-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_wikipedia-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_wikipedia-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_wikipedia-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v0-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v1-loglikelihood_rolling +1 -0
- lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v1-res.json +1 -0
- lm-evaluation-harness/tests/testdata/piqa-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/piqa-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/prost-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/prost-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/pubmedqa-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/pubmedqa-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/qa4mre_2011-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/qa4mre_2011-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/qa4mre_2012-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/qa4mre_2012-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/qa4mre_2013-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/qa4mre_2013-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/qnli-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/qnli-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/qqp-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/qqp-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/race-v0-loglikelihood +1 -0
- lm-evaluation-harness/tests/testdata/race-v0-res.json +1 -0
- lm-evaluation-harness/tests/testdata/random_insertion-v0-greedy_until +1 -0
lm-evaluation-harness/tests/testdata/pile_pile-cc-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
731fdef4a43949b179ba0c540148ebc2fa41583dd583ef580dd812076c66a451
|
lm-evaluation-harness/tests/testdata/pile_pile-cc-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
731fdef4a43949b179ba0c540148ebc2fa41583dd583ef580dd812076c66a451
|
lm-evaluation-harness/tests/testdata/pile_pile-cc-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_pile-cc": {"bits_per_byte": 0.0001620742639125056, "byte_perplexity": 1.0001123476295946, "word_perplexity": 1.0006738958554477}}, "versions": {"pile_pile-cc": 1}}
|
lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
66436569a43163afb2caf422d32c5f329899e74c49865d4d13881fd465fd9976
|
lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_pubmed-abstracts": {"bits_per_byte": 0.00037553733051528816, "byte_perplexity": 1.0003756078534862, "word_perplexity": 1.0025884332779}}, "versions": {"pile_pubmed-abstracts": 0}}
|
lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
66436569a43163afb2caf422d32c5f329899e74c49865d4d13881fd465fd9976
|
lm-evaluation-harness/tests/testdata/pile_pubmed-abstracts-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_pubmed-abstracts": {"bits_per_byte": 0.0005417858444030858, "byte_perplexity": 1.0003756078534862, "word_perplexity": 1.0025884332779}}, "versions": {"pile_pubmed-abstracts": 1}}
|
lm-evaluation-harness/tests/testdata/pile_pubmed-central-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
40b39d120d99a145690444e86acc3e3e24d41e6e0538a75e26929ad84926e5e0
|
lm-evaluation-harness/tests/testdata/pile_pubmed-central-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_pubmed-central": {"bits_per_byte": 1.5812411832795375e-05, "byte_perplexity": 1.0000158125368497, "word_perplexity": 1.000123107107861}}, "versions": {"pile_pubmed-central": 0}}
|
lm-evaluation-harness/tests/testdata/pile_pubmed-central-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
40b39d120d99a145690444e86acc3e3e24d41e6e0538a75e26929ad84926e5e0
|
lm-evaluation-harness/tests/testdata/pile_pubmed-central-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_pubmed-central": {"bits_per_byte": 2.2812488135667854e-05, "byte_perplexity": 1.0000158125368497, "word_perplexity": 1.000123107107861}}, "versions": {"pile_pubmed-central": 1}}
|
lm-evaluation-harness/tests/testdata/pile_stackexchange-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
e524bfb3e21cbdaddc117403a50df598520c7bf5b2c60ad8f2372cfa564e79be
|
lm-evaluation-harness/tests/testdata/pile_stackexchange-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_stackexchange": {"bits_per_byte": 0.0002288815898835956, "byte_perplexity": 1.0002289077852733, "word_perplexity": 1.0016993562258851}}, "versions": {"pile_stackexchange": 0}}
|
lm-evaluation-harness/tests/testdata/pile_stackexchange-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
e524bfb3e21cbdaddc117403a50df598520c7bf5b2c60ad8f2372cfa564e79be
|
lm-evaluation-harness/tests/testdata/pile_stackexchange-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_stackexchange": {"bits_per_byte": 0.0003302063346758449, "byte_perplexity": 1.0002289077852733, "word_perplexity": 1.0016993562258851}}, "versions": {"pile_stackexchange": 1}}
|
lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
4eb69e314f0864ec8890e2323d7e76f8a8309692c4f090e2b41bf4be681a811d
|
lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_ubuntu-irc": {"bits_per_byte": 1.6298315496830533e-06, "byte_perplexity": 1.0000016298328778, "word_perplexity": 1.0000108866656874}}, "versions": {"pile_ubuntu-irc": 0}}
|
lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
4eb69e314f0864ec8890e2323d7e76f8a8309692c4f090e2b41bf4be681a811d
|
lm-evaluation-harness/tests/testdata/pile_ubuntu-irc-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_ubuntu-irc": {"bits_per_byte": 2.3513498942121155e-06, "byte_perplexity": 1.0000016298328778, "word_perplexity": 1.0000108866656874}}, "versions": {"pile_ubuntu-irc": 1}}
|
lm-evaluation-harness/tests/testdata/pile_uspto-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
789b2bdb31564d512b70f801316f49320a26c83ba361226bac0afb255341d477
|
lm-evaluation-harness/tests/testdata/pile_uspto-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_uspto": {"bits_per_byte": 0.00012062434384130924, "byte_perplexity": 1.00012063161925, "word_perplexity": 1.0007716198916954}}, "versions": {"pile_uspto": 0}}
|
lm-evaluation-harness/tests/testdata/pile_uspto-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
789b2bdb31564d512b70f801316f49320a26c83ba361226bac0afb255341d477
|
lm-evaluation-harness/tests/testdata/pile_uspto-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_uspto": {"bits_per_byte": 0.000174024142670342, "byte_perplexity": 1.00012063161925, "word_perplexity": 1.0007716198916954}}, "versions": {"pile_uspto": 1}}
|
lm-evaluation-harness/tests/testdata/pile_wikipedia-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
ef9ec0dd408316ca6537228a6812e839f14b30608973081d41efc47c138338da
|
lm-evaluation-harness/tests/testdata/pile_wikipedia-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_wikipedia": {"bits_per_byte": 0.00016834722287561703, "byte_perplexity": 1.0001683613940646, "word_perplexity": 1.001084677949439}}, "versions": {"pile_wikipedia": 0}}
|
lm-evaluation-harness/tests/testdata/pile_wikipedia-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
ef9ec0dd408316ca6537228a6812e839f14b30608973081d41efc47c138338da
|
lm-evaluation-harness/tests/testdata/pile_wikipedia-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_wikipedia": {"bits_per_byte": 0.00024287370359008176, "byte_perplexity": 1.0001683613940646, "word_perplexity": 1.001084677949439}}, "versions": {"pile_wikipedia": 1}}
|
lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v0-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967
|
lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_youtubesubtitles": {"bits_per_byte": 2.3447170928931888e-05, "byte_perplexity": 1.000023447445816, "word_perplexity": 1.0001529192262875}}, "versions": {"pile_youtubesubtitles": 0}}
|
lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v1-loglikelihood_rolling
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
68263c52adc0086011e2220b619983935cabb1cc1f5f9f8ee1a74ab2a7457967
|
lm-evaluation-harness/tests/testdata/pile_youtubesubtitles-v1-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pile_youtubesubtitles": {"bits_per_byte": 3.3827117222045906e-05, "byte_perplexity": 1.000023447445816, "word_perplexity": 1.0001529192262875}}, "versions": {"pile_youtubesubtitles": 1}}
|
lm-evaluation-harness/tests/testdata/piqa-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
6048a3a2bb3ad1e6a3d98139618e06b4d7de766edd685bd38837596199c3f69f
|
lm-evaluation-harness/tests/testdata/piqa-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"piqa": {"acc": 0.514145810663765, "acc_norm": 0.5114254624591947, "acc_norm_stderr": 0.01166277802645167, "acc_stderr": 0.011661154475524836}}, "versions": {"piqa": 0}}
|
lm-evaluation-harness/tests/testdata/prost-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
7c475f5b36a8b79f94c2be035441e7fd59dac021b0713b1fc72d256424c70b0b
|
lm-evaluation-harness/tests/testdata/prost-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"prost": {"acc": 0.24631725021349274, "acc_norm": 0.2581127241673783, "acc_norm_stderr": 0.00319703079646546, "acc_stderr": 0.003147855968061357}}, "versions": {"prost": 0}}
|
lm-evaluation-harness/tests/testdata/pubmedqa-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
7a04a1fb1d2b19db84fd15c224015d6c0306a41195a4e71fe6abd48fb4d53b9f
|
lm-evaluation-harness/tests/testdata/pubmedqa-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"pubmedqa": {"acc": 0.324, "acc_stderr": 0.01480686473373886}}, "versions": {"pubmedqa": 0}}
|
lm-evaluation-harness/tests/testdata/qa4mre_2011-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
0d09f17c65768e797633494d2d218e4e46a26f718cab8b0bf3d156b073a8c437
|
lm-evaluation-harness/tests/testdata/qa4mre_2011-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"qa4mre_2011": {"acc": 0.225, "acc_norm": 0.23333333333333334, "acc_norm_stderr": 0.03877199986918664, "acc_stderr": 0.0382797091741014}}, "versions": {"qa4mre_2011": 0}}
|
lm-evaluation-harness/tests/testdata/qa4mre_2012-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
7e17261820acb365966cb9431d93aec983b14393eaeefbc96e30a11cf58bc6df
|
lm-evaluation-harness/tests/testdata/qa4mre_2012-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"qa4mre_2012": {"acc": 0.15625, "acc_norm": 0.16875, "acc_norm_stderr": 0.029702236908328808, "acc_stderr": 0.02879508360159146}}, "versions": {"qa4mre_2012": 0}}
|
lm-evaluation-harness/tests/testdata/qa4mre_2013-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
52fc431e94c67f983e28ebc70cf45e6c14116b0ae77dc1bf22347c705a65d054
|
lm-evaluation-harness/tests/testdata/qa4mre_2013-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"qa4mre_2013": {"acc": 0.18309859154929578, "acc_norm": 0.22183098591549297, "acc_norm_stderr": 0.02469760575535269, "acc_stderr": 0.022989742475464973}}, "versions": {"qa4mre_2013": 0}}
|
lm-evaluation-harness/tests/testdata/qnli-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
4281d4ff5cf1244358b0ea0220c67863c69fbade850696b43e8ff05138e01e12
|
lm-evaluation-harness/tests/testdata/qnli-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"qnli": {"acc": 0.5108914515833791, "acc_stderr": 0.00676380528502966}}, "versions": {"qnli": 0}}
|
lm-evaluation-harness/tests/testdata/qqp-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
97b551b0fc3d239aad4929a2e8e79c986891aefd9fcd19441fea0382d507889e
|
lm-evaluation-harness/tests/testdata/qqp-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"qqp": {"acc": 0.49782339846648527, "acc_stderr": 0.0024866770696239894, "f1": 0.42322661288031593, "f1_stderr": 0.002695903831328166}}, "versions": {"qqp": 0}}
|
lm-evaluation-harness/tests/testdata/race-v0-loglikelihood
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
bdfdfab7fa1c7af0c1e161785e347b1b8071a15cbf971f6f2a9ae8c8e845199f
|
lm-evaluation-harness/tests/testdata/race-v0-res.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"results": {"race": {"acc": 0.23253588516746412, "acc_stderr": 0.013074460615265295}}, "versions": {"race": 0}}
|
lm-evaluation-harness/tests/testdata/random_insertion-v0-greedy_until
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
6c48baa6924f3635120f33062251c4b571b3d4e9fe46b14d91f54ddd1c857997
|