df02c30ea0011049233ddef057ddff3ca8f64119
roberta_large_no_ft

 

challenge
Challenging America word-gap prediction
submitter
kubapok
submitted
2021-12-11 17:25:22.967549 UTC
original repo
https://git.wmi.amu.edu.pl/kubapok/challenging-america-word-gap-prediction / branch master
publicly available at
git://gonito.net/challenging-america-word-gap-prediction / branch submission-07115
browsable at
https://gonito.net/gitlist/challenging-america-word-gap-prediction.git/submission-07115/
clone by
git clone --single-branch git://gonito.net/challenging-america-word-gap-prediction -b submission-07115
file basename
out

test-A / 69188baac0935409f92feb870314375a61b6ee37
Metric Score
PerplexityHashed 52.58

dev-0 / df911b4cad5db097b18d28a5b479671de52c8b2b
Metric Score
PerplexityHashed 45.33

worst items

note: the gold standard is taken from the submission itself, not from the challenge data!
# input expected output actual output test-A PerplexityHashed
1 16b9eb2107c6352464ca43134f296b01 THE JASPER WEEKLY COURIER ChronAm 1917.2999999682902 38.391448 -86.930874 know what women will accept, for … another, another:0.9935686588287354 other:0.00528142973780632 the:0.0003993632271885872 that:0.0001885242381831631 another:0.00011049798922613263 ,:9… 6634737.74
2 3864e02c4c3867d4cf58f4b7326eb561 THE JASPER WEEKLY COURIER ChronAm 1917.2808218860985 38.391448 -86.930874 know what women will accept, for … another, another:0.9948902130126953 other:0.0039202980697155 the:0.000312045740429312 that:0.00022257135424297303 ,:0.00015379533579107374 two:9.8716… 5614097.37
3 5a07c7ee7eccfc3463b2c488f7a52d44 EVENING CAPITAL ChronAm 1923.250684899797 38.97864 -76.492786 structures that really look like noth-\ning s… tliut that:0.8954482674598694 which:0.10330512374639511 and:0.00017812562873587012 than:0.00014834999456070364 with:0.00012914463877677917 that:0.… 3789398.38
4 21a4004987635d163f83641f4f115d48 THE DICKINSON PRESS ChronAm 1897.905479420345 46.879176 -102.789624 Ill Groceries\n» We carry a full and co… bs be:0.9991563558578491 be:0.000262171815847978 get:4.8898345994530246e-05 are:3.965184441767633e-05 been:3.5978166124550626e-05 become:3.1074… 3669100.28
5 1fa6f97bc6da5439b57490f665b67d42 EVENING CAPITAL ChronAm 1901.5438355847286 38.97864 -76.492786 Section 4. As soon as may Ik- after the tak-… fifty-five fifty:0.9482989311218262 sixty:0.04745461419224739 55:0.001040992676280439 seventy:0.000998199451714754 five:0.0005458217347040772 50:0.0003… 3575725.38
6 6f662c99d63c26e8f7b908735c45471f THE CHARLOTTE DEMOCRAT ChronAm 1880.6352458700162 35.227087 -80.843127 have her blood upon their hands, and… but, but:0.9370191693305969 and:0.0569678470492363 but:0.0032018404453992844 though:0.0006875822436995804 yet:0.0005115880048833787 and:0.0003172… 3325703.07
7 1879f42e9e0de79a444c78db0bd0aa4a ARIZONA REPUBLICAN ChronAm 1913.1575342148656 33.448587 -112.077346 point 22o feet west of the west line 01… lino line:0.9979199767112732 lines:0.0005207238718867302 line:0.00044307709322310984 side:0.0003409094351809472 end:0.00015453579544555396 Line:0… 3112043.28
8 04adc71dc87a793c22a5a0eaf607fb31 ARIZONA REPUBLICAN ChronAm 1913.1493150367833 33.448587 -112.077346 stitution was copied from the constitu\… preme reme:0.9991204142570496 eme:0.00011755752348108217 cise:8.659125887788832e-05 ajor:6.41291044303216e-05 ple:6.014635437168181e-05 ame:4.3585… 3100276.54
9 1221c85f4f34c36930e6e7dea1936d27 WATERBURY EVENING DEMOCRAT ChronAm 1891.1931506532217 41.558153 -73.051497 petition to any judge of the sup… Bhall shall:0.9768428802490234 must:0.008720818907022476 will:0.0074177696369588375 should:0.0026335909496992826 may:0.0021698398049920797 shall:0… 2877564.51
10 0e87a3ce896157158c64fcf1da14e636 THE DICKINSON PRESS ChronAm 1916.4221311159179 46.879176 -102.789624 On account of these policies, the\nabs… "I I:0.9903676509857178 I:0.005773012526333332 We:0.0028700188267976046 You:0.00023395911557599902 They:9.184156078845263e-05 People:5.15579631… 2798182.30
11 05e25a1fab880a1d546fb2d773ba94d6 LOS ANGELES HERALD ChronAm 1892.6243169082675 34.054935 -118.244476 MR. M . VARCO-E , formerly proprietor N… years' years:0.966692328453064 months:0.025517158210277557 year:0.0037567452527582645 years:0.0009839950362220407 weeks:0.0009628118714317679 long:… 2673530.00
12 017a2aa6c0189099bb783a5d1ecc5ce1 FREMONT WEEKLY FREEMAN ChronAm 1850.856164351852 41.35033 -83.121863 In Ballville Townshin there is an extr… No. No:0.9933759570121765 no:0.002518726047128439 No:0.0018273809691891074 NO:0.0008047629962675273 Number:0.0005212636897340417 Yes:0.000188738… 2532576.87
13 480831bc48fb377b73c058012784c502 THE WICHITA CITY EAGLE ChronAm 1873.9438355847285 37.692236 -97.337545 be entitled to indemnity. A copy of\… bo be:0.9986771941184998 by:0.00034116421011276543 bee:6.77236748742871e-05 been:6.770662002963945e-05 have:5.7847853895509616e-05 be:5.3522770… 2084198.86
14 234cd6343fbae36af202aea5802c265e THE REVIEW ChronAm 1916.8374316623658 35.955692 -80.005318 the day dawned the ship was lightened\nfor a thi… The, The:0.9849704504013062 The:0.008950203657150269 This:0.002043982734903693 the:0.0012569766258820891 His:0.0006372721400111914 That:0.0004005… 1900870.96
15 3123a2757dc1d6e1cfe6797de1af378e MOUNTAIN HOME REPUBLICAN ChronAm 1923.0726027080163 43.13295 -115.691197 89. I. D . Stokes, Hill City.\n90.… 121. 121:0.9912416934967041 121:0.0049237036146223545 123:0.001648403936997056 120:0.0002670554385986179 131:0.00021099328296259046 122:0.0001892… 1760189.03
16 2f20c5e34082c919371200e6a1159565 ARIZONA REPUBLICAN ChronAm 1912.56420761865 33.448587 -112.077346 Accompanying this showing will be\na requ… sides, sides:0.993354082107544 side:0.0032738817390054464 parties:0.001108909142203629 teams:0.0005469056195579469 benches:0.0005324441590346396 ,:… 1745893.12
17 27cd62b1fdae153e36b67ae1b72993bc COURIER DEMOCRAT ChronAm 1913.4068492833587 48.76059 -98.367824 I pulled up tbe fugs from the door\nand sea… bad had:0.9905520677566528 has:0.0035139641258865595 Had:0.002869239542633295 had:0.0012116911821067333 was:0.0006437894771806896 having:0.00021… 1723946.33
18 25286d0278f585c625e9871754ae4038 ARIZONA REPUBLICAN ChronAm 1910.4260273655505 33.448587 -112.077346 were to appear before such distin-\ngui… course, course:0.9935632944107056 course:0.003207672853022814 late:0.000670292996801436 Course:0.0006531341350637376 coarse:0.0005727417301386595 ne… 1610741.90
19 07e679bf097f195dc2c8bb27d7ad44a5 LOS ANGELES HERALD ChronAm 1891.3575342148656 34.054935 -118.244476 The regular Saturday evening hop\nwas w… Mrs. Miss:0.8277224898338318 Mrs:0.16826726496219635 Miss:0.0009501861059106886 .:0.0008920010877773166 Mrs:0.00033509876811876893 Lady:0.0002970… 1578598.00
20 15c94c68060cbbf51a5c5e9d79e7bf76 LA JUNTA TRIBUNE ChronAm 1903.0178081874683 37.985009 -103.543832 with all the rights to the use of water f… di«|n*se dispose:0.9982730150222778 disposed:0.0002457068767398596 give:0.0002240064350189641 convey:0.00020292877161409706 all:5.164835602045059e-05… 1510629.27
21 17facb03faad061cffc3580b47e45bcd THE CHARLOTTE DEMOCRAT ChronAm 1887.746575310756 35.227087 -80.843127 Ia Regard to North Carolina Farmers.\… whioh which:0.937422513961792 this:0.04572274163365364 that:0.01307721622288227 whom:0.001014739042147994 which:0.0007598594529554248 such:0.00028… 1437413.30
22 a8ff5ec194533f00737e94e8b450efa4 THE WICHITA CITY EAGLE ChronAm 1872.9467212798522 37.692236 -97.337545 iu developing the diamond mines. Ar-… .New New:0.9968969821929932 New:0.0009730226011015475 new:0.0008022451074793935 Wall:0.00020895585475955158 Old:8.508633618475869e-05 the:7.37128… 1425224.04
23 b6244ff65e11ea40bb97af65c4fd1467 RICHMOND ENQUIRER ChronAm 1838.6369862696602 37.538509 -77.43428 bank had existed, and that ils branches ha… g»ld gold:0.996227502822876 Gold:0.0018969340017065406 money:0.00039677502354606986 copper:0.00013203533308114856 gold:0.00011570224887691438 iro… 1405821.00
24 7a1e16fcdb34a9d42bb760b8cff04fb4 RICHMOND ENQUIRER ChronAm 1840.408469913732 37.538509 -77.43428 [Mr. Adams presented the memorial of Lysand… ihe the:0.7269036769866943 this:0.2668381929397583 his:0.0024786596186459064 our:0.0014955010265111923 that:0.0007798079750500619 The:0.00012041… 1387795.71
25 24a2e46bd47831994af1ffd16a8bfefc GREAT FALLS DAILY TRIBUNE ChronAm 1920.908469913732 47.504885 -111.291891 Bonds numbered 1 to 7, Inclusive,… inclusive, inclusive:0.9980942606925964 including:0.00028148418641649187 excluding:0.0001621442352188751 all:0.00016130150470416993 also:9.545139619149… 1360239.26
26 27d8e0b66f17c7a17159e90b8f480444 THE DAYTONA DAILY NEWS ChronAm 1912.9221311159179 29.210815 -81.022833 bravely in the Eternal City's defens… Cellini he:0.998588502407074 he:0.00017873855540528893 his:5.4642932809656486e-05 Rome:3.688296055770479e-05 the:3.493753683869727e-05 they:3.348139… 1113733.02
27 1a4d8480064e27a48ebc052fe9d47b11 THE EMPIRE COUNTY ARGUS ChronAm 1854.6890410641806 38.799901 -120.890216 On the amount of postage on letter… pf of:0.9950622916221619 of:0.0017270412063226104 from:0.0006748397718183696 among:0.00036569673102349043 ot:0.00033401764812879264 a:0.0002055… 1109576.82
28 10533cbd104c24317c0cd6ba388c1a96 THE DICKINSON PRESS ChronAm 1907.0698629819888 46.879176 -102.789624 a thousand ailments, I. think that we\… lias has:0.9796327352523804 's:0.012150670401751995 had:0.0028878652956336737 is:0.0015416526002809405 hath:0.0012078526197001338 has:0.000605142… 1049898.28
29 135e95f45070388d778006ee7dbb2011 ELK CITY MINING NEWS ChronAm 1906.2260273655504 45.78769 -115.200118 The present ownership of said prop­\ne… niade made:0.9963387250900269 imposed:0.0006222326192073524 placed:0.0005878989468328655 served:0.0005024251877330244 make:0.0002692172711249441 p… 1034390.26
30 42c2ac6b59ecb8701adfcfc705e913aa EVENING CAPITAL ChronAm 1884.4877048864096 38.97864 -76.492786 The impression which Mr. Bannon,\nw th usual… wards, wards:0.9050788879394531 ward:0.09140300750732422 noon:0.0011381353251636028 words:0.0004946793778799474 ,:0.0002810631413012743 word:0.0001… 906583.79
31 2c1495a0e715d056345db225147ce3d7 RAFTSMAN'S JOURNAL ChronAm 1858.187671201167 41.02728 -78.439188 Wiat collect in pools and smaller lakes, i… j)f of:0.9813758134841919 in:0.012168390676379204 within:0.0022976165637373924 on:0.001431223121471703 surrounding:0.00033451156923547387 throug… 886010.12
32 d9bc96641fa83cddc9aae7009c734da5 RICHMOND ENQUIRER ChronAm 1820.3237704601802 37.538509 -77.43428 employment which it would not natu\nrally … impoii import:0.9939541220664978 import:0.0023194255772978067 Import:0.0007929379935376346 export:0.0005887311999686062 imports:0.00030023831641301… 883140.66
33 2c0d95582280cbfe0d09338e19d935c6 ARIZONA REPUBLICAN ChronAm 1910.5136985984273 33.448587 -112.077346 The voters of this district should\nbe … grounds. grounds:0.9858603477478027 ground:0.011336355470120907 lands:0.0006235001492314041 yards:0.00029269829974509776 ...:0.00010999387450283393 p… 856516.68
34 a435c0d98f76ab5dd4f63ee490a48be0 RICHMOND ENQUIRER ChronAm 1834.0999999682901 37.538509 -77.43428 W’e have li.i«l such a tloo<l ol declamati… (lie the:0.9961541295051575 the:0.0010078911436721683 they:0.00026199998683296144 those:0.00021056385594420135 he:0.00020269745436962694 we:0.000… 822034.42
35 615ad34cff55268995289bff73c43d53 THE NEVADA JOURNAL ChronAm 1852.2117486022566 39.261561 -121.016059 An Act Repealing tkf Charter\nOf the Oi… Sec. Sec:0.9790775179862976 Sec:0.006865577772259712 sec:0.005491681396961212 SEC:0.004202018026262522 Section:0.0013268569018691778 Sub:0.000943… 812664.77
36 233e479ab40c6b9b0ccecfc7e6fc2f3b EVENING CAPITAL ChronAm 1885.401369831304 38.97864 -76.492786 is to grow grain instead of fodder, the\nears… lbs. pounds:0.5975978374481201 lbs:0.3910689353942871 lb:0.003947873134166002 lbs:0.0027719384524971247 tons:0.0019700576085597277 pound:0.000344… 784861.40
37 4ea04266cda6c8522e257896e383ab2f RICHMOND ENQUIRER ChronAm 1835.6753424340436 37.538509 -77.43428 palpable, but how would it benefit even th… curs ears:0.9912300109863281 voices:0.0016744768945500255 minds:0.0010977969504892826 hearing:0.0010597154032438993 tongues:0.0006700926460325718… 760019.14
38 0042369cdb852f469465ee2ee3beedeb THE NEVADA JOURNAL ChronAm 1860.684426197885 39.261561 -121.016059 at pr- >int. when stacks of anonymous le… docs does:0.8686684370040894 did:0.10911467671394348 would:0.007410519290715456 do:0.005101376213133335 will:0.0023688694927841425 should:0.00179… 734238.58
39 1e941cd60e674ba9c524f797ed9ad4b6 EVENING CAPITAL ChronAm 1886.7109588723997 38.97864 -76.492786 Why the End of the World is Near.\nlley. Mus… lions ions:0.9648569226264954 ion:0.029684755951166153 illions:0.0019373273244127631 its:0.0003500625607557595 IONS:0.0003226920962333679 ures:0.0… 679160.09
40 1b302265d60087388bdb5bb36496e74c RICHMOND ENQUIRER ChronAm 1842.919178050482 37.538509 -77.43428 thrown away an a spoil bank, the late fresh… slock stock:0.9942485094070435 stocks:0.0009825662709772587 shares:0.000616600620560348 equity:0.0004980675876140594 company:0.0004895402817055583… 646954.63

Compare with other submission