Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
4d147bdd
Commit
4d147bdd
authored
Sep 17, 2021
by
Jonathan Tow
Browse files
Merge branch 'master' of
https://github.com/EleutherAI/lm-evaluation-harness
into task-guide
parents
011cc891
dc937d4b
Changes
479
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
20 additions
and
0 deletions
+20
-0
tests/testdata/hendrycksTest-sociology-v0-res.json
tests/testdata/hendrycksTest-sociology-v0-res.json
+1
-0
tests/testdata/hendrycksTest-us_foreign_policy-v0-loglikelihood
...testdata/hendrycksTest-us_foreign_policy-v0-loglikelihood
+1
-0
tests/testdata/hendrycksTest-us_foreign_policy-v0-res.json
tests/testdata/hendrycksTest-us_foreign_policy-v0-res.json
+1
-0
tests/testdata/hendrycksTest-virology-v0-loglikelihood
tests/testdata/hendrycksTest-virology-v0-loglikelihood
+1
-0
tests/testdata/hendrycksTest-virology-v0-res.json
tests/testdata/hendrycksTest-virology-v0-res.json
+1
-0
tests/testdata/hendrycksTest-world_religions-v0-loglikelihood
...s/testdata/hendrycksTest-world_religions-v0-loglikelihood
+1
-0
tests/testdata/hendrycksTest-world_religions-v0-res.json
tests/testdata/hendrycksTest-world_religions-v0-res.json
+1
-0
tests/testdata/iwslt17-ar-en-v0-greedy_until
tests/testdata/iwslt17-ar-en-v0-greedy_until
+1
-0
tests/testdata/iwslt17-ar-en-v0-res.json
tests/testdata/iwslt17-ar-en-v0-res.json
+1
-0
tests/testdata/iwslt17-en-ar-v0-greedy_until
tests/testdata/iwslt17-en-ar-v0-greedy_until
+1
-0
tests/testdata/iwslt17-en-ar-v0-res.json
tests/testdata/iwslt17-en-ar-v0-res.json
+1
-0
tests/testdata/lambada-v0-loglikelihood
tests/testdata/lambada-v0-loglikelihood
+1
-0
tests/testdata/lambada-v0-res.json
tests/testdata/lambada-v0-res.json
+1
-0
tests/testdata/lambada_cloze-v0-loglikelihood
tests/testdata/lambada_cloze-v0-loglikelihood
+1
-0
tests/testdata/lambada_cloze-v0-res.json
tests/testdata/lambada_cloze-v0-res.json
+1
-0
tests/testdata/lambada_mt_de-v0-loglikelihood
tests/testdata/lambada_mt_de-v0-loglikelihood
+1
-0
tests/testdata/lambada_mt_de-v0-res.json
tests/testdata/lambada_mt_de-v0-res.json
+1
-0
tests/testdata/lambada_mt_en-v0-loglikelihood
tests/testdata/lambada_mt_en-v0-loglikelihood
+1
-0
tests/testdata/lambada_mt_en-v0-res.json
tests/testdata/lambada_mt_en-v0-res.json
+1
-0
tests/testdata/lambada_mt_es-v0-loglikelihood
tests/testdata/lambada_mt_es-v0-loglikelihood
+1
-0
No files found.
tests/testdata/hendrycksTest-sociology-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"hendrycksTest-sociology"
:
{
"acc"
:
0.23383084577114427
,
"acc_norm"
:
0.24875621890547264
,
"acc_norm_stderr"
:
0.030567675938916707
,
"acc_stderr"
:
0.02992941540834838
}},
"versions"
:
{
"hendrycksTest-sociology"
:
0
}}
\ No newline at end of file
tests/testdata/hendrycksTest-us_foreign_policy-v0-loglikelihood
0 → 100644
View file @
4d147bdd
a1a338d0083a21054f74d36a296d6bd8e2e457327c0fd630bebcc61ed758044d
\ No newline at end of file
tests/testdata/hendrycksTest-us_foreign_policy-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"hendrycksTest-us_foreign_policy"
:
{
"acc"
:
0.2
,
"acc_norm"
:
0.24
,
"acc_norm_stderr"
:
0.04292346959909283
,
"acc_stderr"
:
0.040201512610368445
}},
"versions"
:
{
"hendrycksTest-us_foreign_policy"
:
0
}}
\ No newline at end of file
tests/testdata/hendrycksTest-virology-v0-loglikelihood
0 → 100644
View file @
4d147bdd
0ffa491f7bad2abbb64ecd752a295729167599b3815238cab0ecf4cb08bba9b6
\ No newline at end of file
tests/testdata/hendrycksTest-virology-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"hendrycksTest-virology"
:
{
"acc"
:
0.27710843373493976
,
"acc_norm"
:
0.2710843373493976
,
"acc_norm_stderr"
:
0.03460579907553027
,
"acc_stderr"
:
0.034843315926805875
}},
"versions"
:
{
"hendrycksTest-virology"
:
0
}}
\ No newline at end of file
tests/testdata/hendrycksTest-world_religions-v0-loglikelihood
0 → 100644
View file @
4d147bdd
97a0f68ba30ea3a6ef1db1a2925c964b09ecc54455a0a930da083e52677815bd
\ No newline at end of file
tests/testdata/hendrycksTest-world_religions-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"hendrycksTest-world_religions"
:
{
"acc"
:
0.21637426900584794
,
"acc_norm"
:
0.22807017543859648
,
"acc_norm_stderr"
:
0.03218093795602357
,
"acc_stderr"
:
0.03158149539338734
}},
"versions"
:
{
"hendrycksTest-world_religions"
:
0
}}
\ No newline at end of file
tests/testdata/iwslt17-ar-en-v0-greedy_until
0 → 100644
View file @
4d147bdd
e94d310de91fad7ce36f4cf3305552020221482c5588f2efcefaa019893504f1
\ No newline at end of file
tests/testdata/iwslt17-ar-en-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"iwslt17-ar-en"
:
{
"bleu"
:
0.0
,
"bleu_stderr"
:
0.0
,
"chrf"
:
0.015049895477752772
,
"chrf_stderr"
:
0.0002940315671893584
,
"ter"
:
1.0
,
"ter_stderr"
:
0.0
}},
"versions"
:
{
"iwslt17-ar-en"
:
0
}}
\ No newline at end of file
tests/testdata/iwslt17-en-ar-v0-greedy_until
0 → 100644
View file @
4d147bdd
b20adbcd2c6d135e28600b427113532c5df624cb3a90e8c5e48715c09a3a38fa
\ No newline at end of file
tests/testdata/iwslt17-en-ar-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"iwslt17-en-ar"
:
{
"bleu"
:
0.0
,
"bleu_stderr"
:
0.0
,
"chrf"
:
0.0
,
"chrf_stderr"
:
0.0
,
"ter"
:
1.0
,
"ter_stderr"
:
0.0
}},
"versions"
:
{
"iwslt17-en-ar"
:
0
}}
\ No newline at end of file
tests/testdata/lambada-v0-loglikelihood
0 → 100644
View file @
4d147bdd
6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20
\ No newline at end of file
tests/testdata/lambada-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"lambada"
:
{
"acc"
:
0.0
,
"acc_stderr"
:
0.0
,
"ppl"
:
1.6479047769869253
,
"ppl_stderr"
:
0.006497321146240192
}},
"versions"
:
{
"lambada"
:
0
}}
\ No newline at end of file
tests/testdata/lambada_cloze-v0-loglikelihood
0 → 100644
View file @
4d147bdd
7655e748b63ae7e9911411d2d2a2577221d6c861ca4448509992541294d689f3
\ No newline at end of file
tests/testdata/lambada_cloze-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"lambada_cloze"
:
{
"acc"
:
0.0
,
"acc_stderr"
:
0.0
,
"ppl"
:
1.6479047769869253
,
"ppl_stderr"
:
0.006497321146240192
}},
"versions"
:
{
"lambada_cloze"
:
0
}}
\ No newline at end of file
tests/testdata/lambada_mt_de-v0-loglikelihood
0 → 100644
View file @
4d147bdd
5ad125e1708499832b2cee8c3388f89f9c0277010fd96fbd3359039ce8105984
\ No newline at end of file
tests/testdata/lambada_mt_de-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"lambada_mt_de"
:
{
"acc"
:
0.0
,
"acc_stderr"
:
0.0
,
"ppl"
:
1.6479047769869253
,
"ppl_stderr"
:
0.006497321146240192
}},
"versions"
:
{
"lambada_mt_de"
:
0
}}
\ No newline at end of file
tests/testdata/lambada_mt_en-v0-loglikelihood
0 → 100644
View file @
4d147bdd
6829e6a8aa5922e6c92dd31403cc060f242dc0ede4a775e085a70da095ab2e20
\ No newline at end of file
tests/testdata/lambada_mt_en-v0-res.json
0 → 100644
View file @
4d147bdd
{
"results"
:
{
"lambada_mt_en"
:
{
"acc"
:
0.0
,
"acc_stderr"
:
0.0
,
"ppl"
:
1.6479047769869253
,
"ppl_stderr"
:
0.006497321146240192
}},
"versions"
:
{
"lambada_mt_en"
:
0
}}
\ No newline at end of file
tests/testdata/lambada_mt_es-v0-loglikelihood
0 → 100644
View file @
4d147bdd
4a88f4b316c72fe0396c382d6cbb33568ac4d0ad225150d3536635c085359fc9
\ No newline at end of file
Prev
1
…
10
11
12
13
14
15
16
17
18
…
24
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment