diff --git "a/data/plots/dedup_attempts.json" "b/data/plots/dedup_attempts.json"
new file mode 100644--- /dev/null
+++ "b/data/plots/dedup_attempts.json"
@@ -0,0 +1 @@
+{"data":{"agg_score":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308933284133672,0.3534814938902855,0.3764607086777687,0.38782499730587,0.3981050960719585,0.4028486795723438,0.4125883243978023,0.4117814563214779,0.414029736071825,0.4197172522544861,0.4211113378405571,0.4279881417751312,0.4280137903988361,0.4280424378812313,0.4326301179826259,0.4371833503246307,0.4346669465303421,0.4336562640964985,0.4432648755609989,0.4401291646063328,0.4394684173166752,0.4476612061262131,0.4465444348752498,0.4472153298556804,0.4433343075215816,0.4510187618434429,0.4459567815065384,0.4460812956094742,0.4498684890568256,0.4529943652451038,0.4528274349868297,0.4551213420927524,0.4549156539142132,0.4564928151667118,0.4576693661510944,0.4557182416319847,0.4536240361630916,0.457439012825489,0.4570476822555065,0.4589823484420776,0.462024375796318,0.4540738053619861,0.4550252184271812,0.4576593860983848,0.4573238864541054,0.4575810581445694,0.4622134491801262,0.4592566937208175,0.4614734016358852,0.4637473002076149,0.4625372551381588,0.4613912180066108,0.4597448222339153,0.4594792164862156,0.4662549719214439,0.4634026065468788,0.4633508697152138,0.4635734222829342,0.4628961533308029,0.4670135043561458,0.4639505892992019,0.4631133340299129,0.4665167145431041,0.4672448337078094,0.4693268723785877,0.4630668573081493,0.4676454700529575,0.4646359197795391,0.4621579721570015,0.4692446552217006,0.4704835228621959,0.4663223996758461,0.4680556617677212,0.466339822858572,0.4682099223136902,0.4711195565760135,0.4722655527293682,0.4727961830794811,0.4676857478916645,0.4719390422105789,0.4713102728128433,0.4712141714990139,0.4721613004803657,0.4713456854224205,0.4682970903813839,0.4679934531450271,0.4685162976384163,0.4679946713149547,0.4681242071092129,0.4702276065945625,0.472664151340723,0.4730790853500366,0.4731674715876579,0.4718914777040481,0.4719801284372806,0.4761029370129108,0.4735167175531387,0.4730370938777923,0.4730173237621784,0.4735377207398414,0.4777223989367485,0.4796326830983162,0.4734170883893966,0.4739485755562782,0.4748299159109592,0.4765299335122108,0.4745025858283043,0.4754423759877682,0.4784592799842357,0.4761341325938701,0.4760282784700393,0.4769757278263569,0.47154351323843,0.4786738082766533,0.4804279990494251,0.4777076803147793,0.4798569902777672,0.4759011939167976,0.4784621745347976,0.479673832654953,0.4780617095530033,0.48076206818223,0.47995800152421,0.4790860973298549,0.4817167408764362,0.4811586998403072,0.482547752559185,0.4816697351634502,0.4809327870607376,0.4816545359790325,0.4804601892828941,0.4776877984404564,0.4813711903989315,0.4844604581594467,0.4819537848234176,0.4820829331874847,0.4778126627206802,0.482935007661581,0.48230691999197,0.4826001971960068,0.4823969900608063,0.4811219945549965,0.4789146520197391,0.484035175293684,0.4848698377609253,0.4855728335678577,0.4825376532971859,0.485215101391077,0.4824351668357849,0.4835342466831207,0.4822137206792831,0.4838785007596016,0.4837255179882049,0.4853012599050998,0.4857851006090641,0.4863366298377514,0.4856646582484245,0.4842503517866134,0.4838776960968971,0.4846346862614155,0.4837041422724724,0.4813097268342972,0.4873070046305656,0.4841253720223903,0.4837464913725853,0.483069509267807,0.4851242564618587,0.4861010462045669],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308308329433203,0.355873454362154,0.3717029839754104,0.3850074633955955,0.3948501460254192,0.4002154655754566,0.4048329554498195,0.4044438898563385,0.4131320044398308,0.4137198776006698,0.4165390767157078,0.4196449033915996,0.4205479398369789,0.4222151450812816,0.4212445206940174,0.4244092293083668,0.4277604334056377,0.427376389503479,0.4262414835393429,0.4298982694745064,0.4329856485128402,0.4265631958842277,0.4315988644957542,0.4367391280829906,0.4370421804487705,0.4362500943243503,0.4383381716907024,0.4335947260260582,0.4387018792331218,0.4335667714476585,0.4412745684385299,0.4406604655086994,0.4356823228299618,0.4362218379974365,0.4408080875873565,0.4434515759348869,0.4448937810957432,0.4424510970711708,0.4430350214242935,0.4398098587989807,0.4392542839050293,0.4422871097922325,0.4439756348729133,0.4448361732065677,0.4429450072348118,0.4497613534331321,0.4483206793665886,0.4488913342356682,0.4440611749887466,0.4460635632276535,0.4469517581164837,0.4481476135551929,0.4448935501277447,0.4471675381064415,0.4498751349747181,0.4490758515894413,0.4465720430016517,0.4493694715201854,0.4454591646790504,0.447767786681652,0.4479016810655594,0.4479022771120071,0.4474163949489593,0.4515160135924816,0.4483969658613205,0.4495454505085945,0.4492970518767833,0.4489475302398205,0.4519097618758678,0.4515041932463646,0.454867634922266,0.4489680118858814,0.4518683515489101,0.4536855891346931,0.451835598796606,0.4549431204795837,0.4537704475224018,0.4562799036502838,0.457330010831356,0.4557053260505199,0.4576276987791061,0.4563160315155983,0.4585874639451504,0.4577482156455517,0.4591701366007328,0.4584229178726673,0.4549796842038631,0.4565540738403797,0.4582190774381161,0.4576648361980915,0.4584826976060867,0.4574222974479198,0.4575085714459419,0.4604001343250274,0.4602601155638695,0.4588502235710621,0.4561002403497696,0.4577819295227527,0.4627111777663231,0.4549977220594883,0.4597621336579323,0.4620603285729885,0.4619736894965172,0.4629591591656208,0.4604080803692341,0.4620218686759472,0.4619343020021915,0.462139643728733,0.4596432670950889,0.4610168747603893,0.4592630453407764,0.4639177322387695,0.4613785184919834,0.4594772197306156,0.4636840783059597,0.463115282356739,0.461802527308464,0.4626253843307495,0.4628584422171116,0.4632321447134018,0.4645288437604904,0.4674957022070884,0.4636055491864681,0.4643399268388748,0.4634718783199787,0.4657545685768127,0.4628178887069225,0.464877501130104,0.4662026464939117,0.4674328118562698,0.4655415900051594,0.4650668017566204,0.4669830277562141,0.4688208885490894,0.4660262241959572,0.4662852995097637,0.4683628305792808,0.4677518717944622,0.4667136706411838,0.4663513116538524,0.4685670658946037,0.4666911773383617,0.4728740304708481,0.4678730070590973,0.4703183099627495,0.4696491584181785,0.4700132384896278,0.4697400406002998,0.4685918800532818,0.46814751252532,0.4673261418938637,0.470584113150835,0.4694550149142742,0.470704548060894,0.4715876877307892,0.4692848213016987,0.4708489589393139,0.4670525975525379,0.4684995450079441,0.4672425948083401,0.4723889231681824,0.4692804664373398,0.4703824110329151,0.4705350138247013,0.4720613472163677,0.4692051671445369,0.4743253402411937,0.4704593606293201],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308933284133672,0.3605199865996837,0.3733148723840713,0.3882005847990513,0.3934122696518898,0.3947227671742439,0.4042885974049568,0.3974800482392311,0.4055779427289963,0.4133470430970192,0.4117913842201233,0.4113653488457203,0.4149517640471458,0.4187851920723915,0.4206527359783649,0.4240428246557712,0.422003373503685,0.4280910938978195,0.4244147576391697,0.4316282644867897,0.4295645765960216,0.4310102686285972,0.4360743537545204,0.4313482865691185,0.4350991360843181,0.4378576353192329,0.4335876516997814,0.4347924515604973,0.4348904751241207,0.436600212007761,0.430036511272192,0.4350974671542644,0.4399556629359722,0.4371416717767715,0.4363861419260502,0.4376698136329651,0.4405004419386387,0.4373639523983001,0.4379038028419018,0.4371281825006008,0.4393439553678036,0.440426729619503,0.4401675276458263,0.4429537951946258,0.4449137263000011,0.4434786736965179,0.4450470842421055,0.4454202279448509,0.4394537284970283,0.442185215651989,0.4461225643754005,0.4427758157253265,0.4430646039545536,0.4476901069283485,0.4478763341903686,0.4493869319558143,0.4448477327823639,0.450044184923172,0.4498609118163585,0.4457665979862213,0.4506924152374267,0.449855338782072,0.448790930211544,0.4474099352955818,0.4546772800385952,0.4529431238770485,0.452015146613121,0.4502020999789238,0.4493804536759853,0.4523266032338142,0.4551868587732315,0.4501944817602634,0.4493303671479225,0.4526805207133293,0.4533850513398647,0.4518048763275146,0.4518973492085933,0.4531301632523536,0.4518006071448326,0.4553494565188885,0.4528752230107784,0.4536322727799415,0.4561733976006508,0.4549491256475448,0.4574789106845855,0.4577847123146057,0.4563642293214798,0.4578686729073524,0.4561499990522861,0.4537816494703293,0.4542164430022239,0.4559455662965774,0.4554723873734474,0.4575514122843742,0.4575202167034149,0.4592722058296203,0.4585275091230869,0.4580587856471538,0.456934317946434,0.4577495418488979,0.4540119916200638,0.4570806957781315,0.4608120545744896,0.4588425755500793,0.4578334167599678,0.4610816091299057,0.4598177038133144,0.461849745362997,0.4631866924464702,0.4601576402783394,0.4646804705262184,0.4632389545440674,0.4604574106633663,0.4602976888418197,0.4581312239170074,0.4654182009398937,0.4655338563024997,0.4616620391607284,0.461054053157568,0.4613021649420261,0.4658613465726375,0.4633531905710697,0.4613638147711754,0.4643996246159076,0.462500050663948,0.4650798961520195,0.4648764543235302,0.4639869071543216,0.4634246975183487,0.46585888043046,0.4639799632132053,0.4630857892334461,0.4644265696406364,0.4642998576164245,0.4686848931014538,0.4687492996454239,0.4650243632495403,0.4627032242715359,0.4665953740477562,0.4660026729106903,0.4664581045508384,0.4676475040614605,0.4657339677214622,0.4664678275585174,0.4673498086631298,0.4676674827933311,0.4680955372750759,0.4681585058569908,0.4659864418208599,0.4686457589268684,0.4661462865769863,0.4658931568264961,0.4674226939678192,0.46805215254426,0.4682257212698459,0.4689070098102093,0.4699570722877979,0.4655096270143986,0.4688013233244419,0.4707522802054882,0.4661469310522079,0.4688841328024864,0.4671329781413078,0.4662554152309894,0.4697433896362781,0.4698473587632179,0.4676505327224731,0.4696521013975143],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3309558313339948,0.3538124784827232,0.37185013666749,0.3877692185342312,0.3914083503186703,0.4010260887444019,0.4037069156765938,0.4121054448187351,0.4127887561917305,0.4155575633049011,0.4216000400483608,0.4232191406190395,0.4181633740663528,0.4257264025509357,0.427829060703516,0.4308106526732445,0.4314793534576893,0.4330048598349094,0.4297344386577606,0.4336135908961296,0.4340258985757828,0.4368554055690765,0.4375467486679554,0.4335941858589649,0.4450543634593487,0.4373151436448097,0.4369653351604938,0.4415915794670582,0.4384337663650512,0.4450566470623016,0.4422409497201442,0.4419688135385513,0.4450363777577877,0.4457494169473648,0.4455417431890964,0.4459860995411873,0.4461090452969074,0.446805752813816,0.4482321478426456,0.4462801218032837,0.4435462653636932,0.4511248581111431,0.4476403780281544,0.4510995522141456,0.4532633535563946,0.4535753317177295,0.4489720612764358,0.4530585929751396,0.453516773879528,0.4489232487976551,0.4519186392426491,0.4544922187924385,0.4515446722507477,0.4592985138297081,0.456744235008955,0.4564405381679535,0.4528606571257114,0.4522130489349365,0.4521078057587147,0.4561075419187546,0.4557581916451454,0.4607794433832168,0.4577110521495342,0.455207671970129,0.4574900865554809,0.457570593804121,0.4596013724803924,0.4575626701116562,0.4596348777413368,0.4590061604976654,0.4593263976275921,0.460021074861288,0.4566548988223076,0.4592928476631641,0.4582078419625759,0.4563231095671654,0.4631936550140381,0.4618166126310825,0.4600832983851433,0.4603766538202762,0.462534986436367,0.4621461853384971,0.4598785378038883,0.46295265853405,0.4618266113102436,0.4641485996544361,0.4624244682490825,0.4638310670852661,0.4641022570431232,0.4648221023380756,0.4621741473674774,0.4655880220234394,0.462023451924324,0.4663394354283809,0.4639224037528038,0.4656381383538246,0.4624673314392566,0.4601731114089489,0.4657526090741157,0.4621315188705921,0.4619199633598327,0.4682006165385246,0.4623510390520096,0.468154851347208,0.4675651639699936,0.4644951075315475,0.4669772274792194,0.4666073098778724,0.4707877598702907,0.4658938273787498,0.4632246196269989,0.4684121496975422,0.4667719639837742,0.4672759622335434,0.4707333780825138,0.4681494198739528,0.4656308777630329,0.4639791175723076,0.4669930078089237,0.4667269177734852,0.4677531644701957,0.4667962417006492,0.4679369106888771,0.4691582284867763,0.4691857397556305,0.4688138552010059,0.4700452089309692,0.4680078886449337,0.4719941802322864,0.4678915552794933,0.4694531373679638,0.4705856889486313,0.4731360003352165,0.4688334502279758,0.4684324786067009,0.4672457464039325,0.4689518697559833,0.471104834228754,0.475016463547945,0.4718285202980041,0.4744332246482372,0.4725923612713814,0.4717464968562126,0.4710442833602428,0.4735120050609112,0.4713596552610397,0.4738523736596107,0.4724103510379791,0.4728292748332023,0.4765149317681789,0.4730028733611107,0.472226895391941,0.4714370593428612,0.4729198738932609,0.4724982976913452,0.4754611887037754,0.4721586741507053,0.4749660044908523,0.4741441793739795,0.4758410491049289,0.4727112278342247,0.4732854701578617,0.4749884530901909,0.4750290811061859,0.4759654812514782,0.4755739048123359,0.4755616523325443,0.4750100895762443],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308933284133672,0.3608616776764393,0.3745453506708145,0.3862277194857597,0.3989979773759842,0.406296543776989,0.4094927236437797,0.4138859286904335,0.4177777022123337,0.4208802655339241,0.4254550077021122,0.4283009432256222,0.429458349943161,0.4330311268568039,0.4349483698606491,0.4348161295056343,0.438955657184124,0.4389265701174736,0.4393925778567791,0.4383306242525577,0.4436748661100864,0.4423373565077781,0.4460027255117893,0.4440812170505523,0.4476902261376381,0.4465879611670971,0.4497823156416416,0.4513350501656532,0.4518667235970497,0.45149727165699,0.4513994492590427,0.4521937072277069,0.4520382955670357,0.4530793912708759,0.4516105614602566,0.4530563354492187,0.4495660625398159,0.4520940892398357,0.4561133235692978,0.4522969461977482,0.4575686641037464,0.4589144177734852,0.4582882039248943,0.457970168441534,0.4554797261953354,0.4622044861316681,0.4596928395330906,0.4624353349208832,0.4619148448109627,0.461100060492754,0.458431463688612,0.4620467089116573,0.4562215581536293,0.4620163068175316,0.4631462283432483,0.4600549824535846,0.4620365314185619,0.458735141903162,0.461642112582922,0.461245734244585,0.4645131677389145,0.4629777930676937,0.4651660025119781,0.4653937108814716,0.4676259346306324,0.4667201824486255,0.4650012850761413,0.4676916748285293,0.4708514772355556,0.4673572592437267,0.4689626581966877,0.4678038358688354,0.4667215310037136,0.4646228328347206,0.4662510119378567,0.4674677737057209,0.4690804108977318,0.4634581170976162,0.4701276533305645,0.4676450751721859,0.4672758504748344,0.4674397967755794,0.4656238108873367,0.4690065123140812,0.4677213467657566,0.4678985886275768,0.4735414572060108,0.4705612398684025,0.4703374318778515,0.4704933613538742,0.4688010476529598,0.4699571952223778,0.4674785658717155,0.4701188169419765,0.4682065695524215,0.4729971997439861,0.4748715870082378,0.4745333231985569,0.4737020246684551,0.4747246317565441,0.4771635122597217,0.4740425907075405,0.475264236330986,0.4744705818593502,0.474684040993452,0.4721556939184665,0.475641455501318,0.476833701133728,0.4746401384472847,0.4742486327886581,0.4730467088520527,0.4773029200732708,0.4760043211281299,0.4770320989191532,0.4742161482572555,0.4780259765684604,0.4806670732796192,0.4784667380154133,0.4788618609309196,0.4762138128280639,0.4777246937155723,0.4796081893146038,0.4798486456274986,0.475479181855917,0.4779988899827003,0.4765858314931392,0.4772914499044418,0.47843898832798,0.4799034222960472,0.4803600236773491,0.4751846008002758,0.4777872562408447,0.4779460839927196,0.4787487275898456,0.4808406494557857,0.4810357913374901,0.4797308407723903,0.4800078608095646,0.4806460626423359,0.4810502976179123,0.4797912389039993,0.477332629263401,0.4818884879350662,0.482621606439352,0.4833096489310264,0.4821632876992225,0.4831674285233021,0.4830279909074306,0.4849893450736999,0.4845218025147915,0.4825541749596596,0.4833571836352348,0.4853803217411041,0.483093187212944,0.4850797094404697,0.485261783003807,0.4837660938501358,0.4835929833352566,0.4855643883347511,0.4832059442996979,0.484714712947607,0.4839249886572361,0.4829078912734985,0.4818423055112362,0.482727088034153,0.4824129492044449,0.4820138849318027,0.4865870922803879],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308933284133672,0.3521807119250297,0.3753322064876556,0.3814844712615013,0.3921241238713264,0.4009848497807979,0.4042861610651016,0.4115334674715996,0.4122494459152221,0.4161616265773773,0.4198154620826244,0.4198628477752208,0.4218641929328441,0.4237341359257698,0.4280204549431801,0.4243046343326568,0.4297068268060684,0.4260851107537746,0.4275948479771614,0.4352251775562763,0.435413621366024,0.4334152638912201,0.4382088854908943,0.4347397200763225,0.4370345771312713,0.4359434098005295,0.4377594217658043,0.4387318082153797,0.4392597377300262,0.4389313124120235,0.444620031863451,0.4392029196023941,0.4410344138741493,0.4409831240773201,0.4461070112884044,0.4398480653762817,0.4437307938933372,0.4483219124376774,0.4429171904921531,0.4441797249019146,0.4433346502482891,0.4409643001854419,0.4454749636352062,0.4449969530105591,0.4484771974384784,0.4457860104739666,0.444888774305582,0.4471950978040695,0.4521629251539707,0.4483534656465053,0.4478100799024105,0.4506555907428264,0.4456943683326244,0.4488134793937206,0.4538563638925552,0.4476338438689708,0.4509812667965889,0.4455831907689571,0.4513924270868301,0.4549835473299026,0.4541421681642532,0.452974934130907,0.4493634849786758,0.4561821892857551,0.4494254030287266,0.4550966694951057,0.4541749954223633,0.4557304121553898,0.454387255012989,0.4535508193075657,0.4546832703053951,0.4562776647508144,0.4565397091209888,0.4546332433819771,0.4533810243010521,0.4581005237996578,0.4545918367803097,0.453194610774517,0.4591345377266407,0.4579273164272308,0.4659051410853863,0.4654802642762661,0.4573172442615032,0.4601948149502277,0.465323694050312,0.4596584029495716,0.4615897536277771,0.4585014395415783,0.4580343812704086,0.4614832140505314,0.4585752412676811,0.4580584801733494,0.4588260576128959,0.4614599421620369,0.4631590731441974,0.4621837958693504,0.4638531729578972,0.4650365859270096,0.4628637246787548,0.4633012004196644,0.4612757787108421,0.4614142216742039,0.4662776477634907,0.4692945666611194,0.4635134115815162,0.4651613272726536,0.4650036655366421,0.4608926959335804,0.462869431823492,0.4673346988856792,0.4626451060175895,0.4661711789667606,0.4644980132579803,0.4665859006345272,0.4649474620819092,0.4663644470274448,0.4684919565916061,0.4680317379534244,0.4629725739359855,0.4633644074201584,0.4671604074537754,0.4681667201220989,0.4686234965920448,0.4708802327513695,0.4683560691773891,0.4672846049070358,0.4679780788719654,0.4640534855425358,0.4679219797253608,0.4672939106822014,0.4655701518058777,0.4701646231114864,0.470640879124403,0.4660611040890217,0.4671303518116474,0.4675955064594745,0.467900313436985,0.4713941998779773,0.4683218672871589,0.4685247465968132,0.4693273864686489,0.4727042093873024,0.4696716107428074,0.4699413068592548,0.4713758826255798,0.470614280551672,0.4707841426134109,0.4716117829084396,0.4685231260955333,0.4715239778161049,0.4700995720922947,0.4695573821663856,0.4687556736171245,0.4733567237854004,0.4738567247986793,0.4719441048800945,0.4719101414084434,0.4723450466990471,0.4731270968914032,0.4711598604917526,0.4695496521890163,0.471214510500431,0.4706138074398041,0.4691229425370693,0.4681768789887428,0.4705207794904709,0.4696074612438679,0.4721779748797416],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308933284133672,0.3520014714449644,0.3728324100375175,0.3846734091639519,0.3966936804354191,0.401569340378046,0.4016355276107788,0.4116213396191597,0.415747556835413,0.4118983596563339,0.4147546552121639,0.4175429232418537,0.4193802326917648,0.4210347309708595,0.4232813976705074,0.4224660508334636,0.4259530901908874,0.435084518045187,0.4323600456118583,0.4344198070466518,0.4324463531374931,0.4357072487473488,0.4331384040415287,0.4372057989239692,0.4373790808022022,0.4350348822772503,0.4394325315952301,0.4397556111216545,0.4393733851611614,0.4427020847797394,0.4423091523349285,0.4462971985340118,0.445355799049139,0.4425348825752735,0.4450080431997776,0.446200929582119,0.4488413631916046,0.4456907659769058,0.4440508894622326,0.4466222934424877,0.4478743113577366,0.4543321244418621,0.4479517787694931,0.4477473832666874,0.4464762397110462,0.4499345533549785,0.4467369467020035,0.4523977525532245,0.4476423896849155,0.4532668218016624,0.453446052968502,0.4530359432101249,0.4525354765355587,0.4536577314138412,0.4525476135313511,0.4512894563376903,0.4542004279792309,0.4568968787789345,0.4579006694257259,0.4573367051780224,0.460737831890583,0.4605224542319774,0.4593199267983436,0.4565713107585907,0.4580115526914596,0.4566531553864479,0.4571566134691238,0.4588995426893234,0.4605681896209717,0.4559327475726604,0.4570840820670128,0.4584307335317135,0.4562503434717655,0.4605820141732692,0.4604894854128361,0.4551392756402492,0.4593157023191452,0.4622145108878612,0.4627775400876999,0.4630993865430355,0.4651060812175274,0.4610257484018802,0.4629311040043831,0.466909646987915,0.4636974520981312,0.4627483524382114,0.4637505896389484,0.4624840058386326,0.4637664444744587,0.4617507234215736,0.4636625200510025,0.4660447128117084,0.4651080593466759,0.4654295742511749,0.4679228588938713,0.4647865705192089,0.46364626288414,0.4649210348725319,0.4673826247453689,0.4677468314766884,0.465425606817007,0.4701338112354278,0.4678912609815597,0.4691201969981193,0.4716861806809902,0.4692598916590214,0.473090149462223,0.4720913246273994,0.4710985831916332,0.4733619019389152,0.4728242270648479,0.4696990177035332,0.473460890352726,0.469140063971281,0.467971783131361,0.4684571400284767,0.4718846604228019,0.4736220799386501,0.4717770330607891,0.4721070267260074,0.4715679474174976,0.470394417643547,0.4722143225371837,0.4740938805043697,0.4741401933133602,0.4754103310406208,0.4715753979980945,0.4737458080053329,0.4725647941231727,0.4735384173691273,0.4749026075005531,0.4729001969099045,0.474270336329937,0.475382313132286,0.4782308116555214,0.476322028785944,0.4768581986427307,0.4779540970921516,0.4768891893327236,0.4775341488420963,0.4771354757249355,0.4768393598496914,0.4756478480994701,0.4752643927931785,0.4765472523868084,0.4755738526582718,0.4791633263230324,0.4759882129728794,0.475241232663393,0.4750130213797092,0.4800478257238865,0.4751877933740616,0.4750237762928009,0.4757923185825348,0.4768571034073829,0.4790637120604515,0.4783112443983555,0.4768976084887981,0.4776681922376156,0.475880067795515,0.4768129214644432,0.4777411594986915,0.4756934717297554,0.4780301302671432,0.4782200120389461,0.4771671816706657,0.4767774641513824,0.4778990671038627],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3309533800929785,0.3636399246752262,0.3710412681102752,0.3888256475329399,0.3967294991016388,0.4046294242143631,0.4068691842257976,0.4103619195520878,0.4143245853483677,0.4222683906555176,0.422239176928997,0.4238695614039898,0.4203561432659626,0.421596635133028,0.4287461563944816,0.4193425215780735,0.4284681789577007,0.4313152357935905,0.4327069334685802,0.4380974695086479,0.4344737902283668,0.4380814805626869,0.4341486506164074,0.4345419965684414,0.4355490021407604,0.4387085922062397,0.4430766925215721,0.4417844377458095,0.4410139098763466,0.4438675120472908,0.4431937448680401,0.4467405341565609,0.4458528459072113,0.4483747519552707,0.4509704895317554,0.4454758279025554,0.4497617967426777,0.4486398547887802,0.4491447769105434,0.4438848234713077,0.4473658539354801,0.450075838714838,0.4539189636707306,0.4520601592957973,0.4463697746396065,0.4483959302306175,0.4481877014040947,0.4518255740404129,0.4497339054942131,0.4493288770318031,0.4503022730350494,0.4540660046041012,0.4580982290208339,0.4533965550363064,0.4588938988745212,0.4549886174499988,0.4559481851756573,0.4538953453302383,0.457434069365263,0.4531894363462925,0.45671147108078,0.4575185514986515,0.4593377001583576,0.4609355852007866,0.4630855545401573,0.4629644714295864,0.4588358551263809,0.4598908349871635,0.4635431952774524,0.4629068300127983,0.4588603004813194,0.4604493491351604,0.4602258019149303,0.4595636501908302,0.4617040269076824,0.4603953845798969,0.4650216288864612,0.4633625410497188,0.4639836139976978,0.4648987986147403,0.4650229513645172,0.4635105952620506,0.4652433209121227,0.4651935659348964,0.4638204835355282,0.4636901803314686,0.462987121194601,0.4625051543116569,0.4603339917957783,0.4642346836626529,0.4610650539398193,0.4640212133526802,0.4610569588840008,0.4620924368500709,0.4620952159166336,0.4637346342206001,0.466573104262352,0.4709350205957889,0.4703476168215275,0.4665980003774166,0.4634359143674373,0.4657214656472206,0.4673617482185364,0.4639917202293873,0.4690569713711738,0.4732854031026363,0.4706726670265198,0.4684937708079815,0.4680767469108104,0.4704035334289074,0.4714839942753315,0.4634643904864788,0.4695122875273227,0.4699761942028999,0.4690134599804878,0.469760064035654,0.4720391035079956,0.4746227674186229,0.4724990427494049,0.4714022949337959,0.4744094684720039,0.4697907231748104,0.4725967906415462,0.4712755270302295,0.4711885452270508,0.4720206931233406,0.4742479138076305,0.4725426137447357,0.4718611650168895,0.4724567010998726,0.4717644490301609,0.473195556551218,0.4751759842038154,0.474845141172409,0.4751902781426906,0.4762182980775833,0.4747962728142738,0.4711819812655449,0.4768646955490112,0.4731461927294731,0.4728570468723774,0.4747268110513687,0.4751599170267582,0.4743171781301498,0.4759622104465961,0.4793889559805393,0.4748627580702305,0.4789143167436123,0.4758364073932171,0.4769822880625725,0.477603156119585,0.4740673415362835,0.4740849696099758,0.4763797596096992,0.4790925271809101,0.4784910716116428,0.4790930971503258,0.4772730730473995,0.4803534112870693,0.476247426122427,0.4769651032984257,0.4782710410654545,0.4791845344007015,0.4776942282915115,0.4765905104577541,0.4789641499519348,0.4774674624204635,0.4766297414898872],"label":"FineWeb URL dedup"}},"commonsense_qa/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2329999953508377,0.2820000052452087,0.2820000052452087,0.3100000023841858,0.3030000030994415,0.3350000083446502,0.335999995470047,0.3429999947547912,0.3409999907016754,0.3519999980926513,0.3600000143051147,0.3420000076293945,0.3529999852180481,0.3490000069141388,0.3600000143051147,0.3490000069141388,0.3619999885559082,0.356000006198883,0.3619999885559082,0.3700000047683716,0.3959999978542328,0.367000013589859,0.3840000033378601,0.3860000073909759,0.3810000121593475,0.4020000100135803,0.382999986410141,0.3970000147819519,0.4000000059604645,0.3759999871253967,0.3840000033378601,0.3989999890327453,0.3989999890327453,0.3889999985694885,0.3989999890327453,0.3770000040531158,0.3849999904632568,0.3970000147819519,0.4040000140666961,0.4000000059604645,0.3930000066757202,0.3939999938011169,0.4040000140666961,0.3919999897480011,0.3939999938011169,0.4099999964237213,0.395000010728836,0.4050000011920929,0.4050000011920929,0.395000010728836,0.4059999883174896,0.4000000059604645,0.4059999883174896,0.4120000004768371,0.4090000092983246,0.4129999876022339,0.4090000092983246,0.4000000059604645,0.4009999930858612,0.4020000100135803,0.4000000059604645,0.4239999949932098,0.395000010728836,0.4000000059604645,0.4090000092983246,0.3989999890327453,0.4050000011920929,0.4099999964237213,0.4090000092983246,0.4129999876022339,0.4079999923706054,0.4099999964237213,0.3989999890327453,0.4199999868869781,0.4169999957084656,0.4210000038146972,0.4259999990463257,0.4230000078678131,0.4070000052452087,0.4189999997615814,0.4180000126361847,0.4149999916553497,0.4189999997615814,0.4099999964237213,0.4180000126361847,0.4210000038146972,0.4230000078678131,0.4070000052452087,0.4120000004768371,0.4289999902248382,0.4210000038146972,0.4269999861717224,0.4300000071525574,0.4239999949932098,0.4300000071525574,0.4289999902248382,0.421999990940094,0.4199999868869781,0.4300000071525574,0.4259999990463257,0.4269999861717224,0.421999990940094,0.4189999997615814,0.4300000071525574,0.4390000104904175,0.4259999990463257,0.4230000078678131,0.4339999854564667,0.4329999983310699,0.4280000030994415,0.4309999942779541,0.4359999895095825,0.4250000119209289,0.4329999983310699,0.4339999854564667,0.4350000023841858,0.4239999949932098,0.4300000071525574,0.4410000145435333,0.4390000104904175,0.4359999895095825,0.4339999854564667,0.4480000138282776,0.44200000166893,0.4460000097751617,0.44200000166893,0.4379999935626983,0.4370000064373016,0.4350000023841858,0.4440000057220459,0.4309999942779541,0.4429999887943268,0.4329999983310699,0.4359999895095825,0.4399999976158142,0.4239999949932098,0.4289999902248382,0.4429999887943268,0.4339999854564667,0.4280000030994415,0.4370000064373016,0.4320000112056732,0.4269999861717224,0.4379999935626983,0.4370000064373016,0.4359999895095825,0.4379999935626983,0.4390000104904175,0.4460000097751617,0.4329999983310699,0.4320000112056732,0.4429999887943268,0.4480000138282776,0.4410000145435333,0.4329999983310699,0.4390000104904175,0.4359999895095825,0.4429999887943268,0.4429999887943268,0.4449999928474426,0.44200000166893,0.4460000097751617,0.4410000145435333,0.4370000064373016,0.4410000145435333,0.4379999935626983,0.4390000104904175],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2409999966621399,0.257999986410141,0.2849999964237213,0.289000004529953,0.2910000085830688,0.3109999895095825,0.3219999969005584,0.324999988079071,0.3210000097751617,0.3160000145435333,0.324999988079071,0.335999995470047,0.3300000131130218,0.3310000002384186,0.3440000116825104,0.3429999947547912,0.3350000083446502,0.3589999973773956,0.3490000069141388,0.3540000021457672,0.3459999859333038,0.3659999966621399,0.3440000116825104,0.3479999899864197,0.3600000143051147,0.3459999859333038,0.3549999892711639,0.3529999852180481,0.3529999852180481,0.3580000102519989,0.363999992609024,0.3499999940395355,0.3569999933242798,0.3689999878406524,0.3630000054836273,0.3549999892711639,0.3610000014305115,0.3449999988079071,0.3689999878406524,0.367000013589859,0.3519999980926513,0.3689999878406524,0.3619999885559082,0.3589999973773956,0.3770000040531158,0.3600000143051147,0.3770000040531158,0.363999992609024,0.3810000121593475,0.3610000014305115,0.3790000081062317,0.3659999966621399,0.3689999878406524,0.3740000128746032,0.382999986410141,0.3729999959468841,0.3709999918937683,0.3700000047683716,0.375,0.3770000040531158,0.3720000088214874,0.3759999871253967,0.375,0.3729999959468841,0.382999986410141,0.3840000033378601,0.3779999911785126,0.3770000040531158,0.3729999959468841,0.3729999959468841,0.3790000081062317,0.3759999871253967,0.3819999992847442,0.3759999871253967,0.3889999985694885,0.3849999904632568,0.3840000033378601,0.3860000073909759,0.3819999992847442,0.3840000033378601,0.3910000026226043,0.3759999871253967,0.3939999938011169,0.3709999918937683,0.3849999904632568,0.3849999904632568,0.3910000026226043,0.3840000033378601,0.3880000114440918,0.3989999890327453,0.3740000128746032,0.3849999904632568,0.3930000066757202,0.3939999938011169,0.395000010728836,0.3970000147819519,0.4040000140666961,0.3939999938011169,0.3939999938011169,0.3919999897480011,0.382999986410141,0.3930000066757202,0.3919999897480011,0.3799999952316284,0.4009999930858612,0.3910000026226043,0.3989999890327453,0.3989999890327453,0.3910000026226043,0.3849999904632568,0.395000010728836,0.3930000066757202,0.3919999897480011,0.3810000121593475,0.3819999992847442,0.395000010728836,0.3980000019073486,0.3919999897480011,0.4000000059604645,0.3970000147819519,0.3989999890327453,0.395000010728836,0.3869999945163727,0.3869999945163727,0.3970000147819519,0.3930000066757202,0.3980000019073486,0.3939999938011169,0.3899999856948852,0.3989999890327453,0.3930000066757202,0.4020000100135803,0.3930000066757202,0.3930000066757202,0.3959999978542328,0.402999997138977,0.4079999923706054,0.4110000133514404,0.3970000147819519,0.395000010728836,0.4050000011920929,0.4070000052452087,0.4099999964237213,0.3970000147819519,0.4020000100135803,0.402999997138977,0.3930000066757202,0.3989999890327453,0.3980000019073486,0.3989999890327453,0.4070000052452087,0.4020000100135803,0.3959999978542328,0.3939999938011169,0.3980000019073486,0.4070000052452087,0.3980000019073486,0.395000010728836,0.4020000100135803,0.4099999964237213,0.4090000092983246,0.4110000133514404,0.4050000011920929,0.4059999883174896,0.402999997138977,0.4070000052452087,0.4090000092983246],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2540000081062317,0.2849999964237213,0.2939999997615814,0.3059999942779541,0.31700000166893,0.3109999895095825,0.3160000145435333,0.3310000002384186,0.3310000002384186,0.3319999873638153,0.3300000131130218,0.3219999969005584,0.3510000109672546,0.3490000069141388,0.3549999892711639,0.3540000021457672,0.3650000095367431,0.3440000116825104,0.3610000014305115,0.3449999988079071,0.3540000021457672,0.3589999973773956,0.3700000047683716,0.3910000026226043,0.3659999966621399,0.3759999871253967,0.3619999885559082,0.3630000054836273,0.3899999856948852,0.375,0.4020000100135803,0.3849999904632568,0.3709999918937683,0.382999986410141,0.382999986410141,0.3700000047683716,0.3840000033378601,0.3610000014305115,0.3790000081062317,0.3729999959468841,0.3770000040531158,0.3600000143051147,0.3740000128746032,0.3720000088214874,0.363999992609024,0.3770000040531158,0.3569999933242798,0.3659999966621399,0.3840000033378601,0.3700000047683716,0.3740000128746032,0.367000013589859,0.3729999959468841,0.3740000128746032,0.3810000121593475,0.367000013589859,0.3779999911785126,0.3959999978542328,0.3930000066757202,0.3759999871253967,0.3860000073909759,0.3939999938011169,0.3720000088214874,0.3970000147819519,0.3899999856948852,0.382999986410141,0.3989999890327453,0.3869999945163727,0.3919999897480011,0.3840000033378601,0.3779999911785126,0.3889999985694885,0.4000000059604645,0.402999997138977,0.3819999992847442,0.3970000147819519,0.3889999985694885,0.3939999938011169,0.395000010728836,0.3899999856948852,0.3910000026226043,0.3910000026226043,0.3819999992847442,0.3970000147819519,0.4059999883174896,0.4020000100135803,0.3970000147819519,0.4009999930858612,0.4070000052452087,0.3980000019073486,0.3930000066757202,0.3889999985694885,0.3970000147819519,0.395000010728836,0.3930000066757202,0.3919999897480011,0.3989999890327453,0.3910000026226043,0.3970000147819519,0.3910000026226043,0.402999997138977,0.4169999957084656,0.3980000019073486,0.4149999916553497,0.4120000004768371,0.4040000140666961,0.4169999957084656,0.4169999957084656,0.4149999916553497,0.4129999876022339,0.4110000133514404,0.4210000038146972,0.4090000092983246,0.4099999964237213,0.4040000140666961,0.4090000092983246,0.4180000126361847,0.4070000052452087,0.4090000092983246,0.4070000052452087,0.4050000011920929,0.4059999883174896,0.4099999964237213,0.4079999923706054,0.4110000133514404,0.4079999923706054,0.421999990940094,0.4090000092983246,0.4110000133514404,0.4169999957084656,0.4000000059604645,0.4129999876022339,0.402999997138977,0.4050000011920929,0.4079999923706054,0.4059999883174896,0.414000004529953,0.4189999997615814,0.4169999957084656,0.4090000092983246,0.4149999916553497,0.4149999916553497,0.4169999957084656,0.4180000126361847,0.4250000119209289,0.414000004529953,0.414000004529953,0.4120000004768371,0.4180000126361847,0.4070000052452087,0.4110000133514404,0.4129999876022339,0.4120000004768371,0.4169999957084656,0.4169999957084656,0.4120000004768371,0.4180000126361847,0.4239999949932098,0.4280000030994415,0.4239999949932098,0.4210000038146972,0.421999990940094,0.4259999990463257,0.4309999942779541,0.4259999990463257,0.4230000078678131,0.4160000085830688],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2319999933242797,0.2610000073909759,0.2860000133514404,0.3140000104904175,0.3030000030994415,0.2949999868869781,0.3230000138282776,0.3199999928474426,0.3300000131130218,0.3339999914169311,0.3289999961853027,0.3339999914169311,0.3420000076293945,0.335999995470047,0.3409999907016754,0.3479999899864197,0.3420000076293945,0.328000009059906,0.3510000109672546,0.3490000069141388,0.3510000109672546,0.3420000076293945,0.3569999933242798,0.3569999933242798,0.3519999980926513,0.3569999933242798,0.3580000102519989,0.3529999852180481,0.3569999933242798,0.3540000021457672,0.3759999871253967,0.3650000095367431,0.367000013589859,0.3779999911785126,0.3659999966621399,0.3540000021457672,0.3799999952316284,0.3770000040531158,0.3779999911785126,0.3619999885559082,0.3779999911785126,0.3720000088214874,0.3510000109672546,0.3819999992847442,0.3680000007152557,0.3659999966621399,0.3770000040531158,0.3630000054836273,0.3799999952316284,0.375,0.363999992609024,0.3779999911785126,0.3919999897480011,0.3709999918937683,0.382999986410141,0.3880000114440918,0.3790000081062317,0.375,0.3770000040531158,0.3779999911785126,0.3860000073909759,0.3899999856948852,0.3770000040531158,0.3729999959468841,0.3770000040531158,0.3759999871253967,0.3650000095367431,0.3819999992847442,0.3709999918937683,0.3880000114440918,0.3790000081062317,0.3689999878406524,0.3740000128746032,0.3759999871253967,0.3910000026226043,0.3770000040531158,0.3790000081062317,0.3689999878406524,0.3770000040531158,0.3790000081062317,0.382999986410141,0.3849999904632568,0.3790000081062317,0.3799999952316284,0.3880000114440918,0.3729999959468841,0.3759999871253967,0.3910000026226043,0.3840000033378601,0.382999986410141,0.3680000007152557,0.3860000073909759,0.3889999985694885,0.3860000073909759,0.3880000114440918,0.3899999856948852,0.3819999992847442,0.3880000114440918,0.3959999978542328,0.3819999992847442,0.3910000026226043,0.3889999985694885,0.3959999978542328,0.4000000059604645,0.4020000100135803,0.3930000066757202,0.3860000073909759,0.4070000052452087,0.3980000019073486,0.3959999978542328,0.3939999938011169,0.3840000033378601,0.3939999938011169,0.4000000059604645,0.3989999890327453,0.3939999938011169,0.3930000066757202,0.4020000100135803,0.3939999938011169,0.4059999883174896,0.3989999890327453,0.4040000140666961,0.4099999964237213,0.3889999985694885,0.3939999938011169,0.4020000100135803,0.402999997138977,0.4090000092983246,0.3939999938011169,0.4050000011920929,0.402999997138977,0.4099999964237213,0.4000000059604645,0.395000010728836,0.402999997138977,0.4009999930858612,0.3989999890327453,0.4000000059604645,0.4059999883174896,0.3899999856948852,0.395000010728836,0.3989999890327453,0.3980000019073486,0.4149999916553497,0.4040000140666961,0.4000000059604645,0.3959999978542328,0.4129999876022339,0.4120000004768371,0.4070000052452087,0.3970000147819519,0.4090000092983246,0.3980000019073486,0.3959999978542328,0.4050000011920929,0.3989999890327453,0.4020000100135803,0.4070000052452087,0.4079999923706054,0.4020000100135803,0.4099999964237213,0.4090000092983246,0.4000000059604645,0.4099999964237213,0.4079999923706054,0.4059999883174896,0.4149999916553497],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2450000047683715,0.2730000019073486,0.2800000011920929,0.2939999997615814,0.3140000104904175,0.3079999983310699,0.31700000166893,0.3319999873638153,0.3429999947547912,0.3370000123977661,0.3449999988079071,0.3540000021457672,0.3700000047683716,0.3770000040531158,0.363999992609024,0.3630000054836273,0.3720000088214874,0.3610000014305115,0.3659999966621399,0.3860000073909759,0.3810000121593475,0.3899999856948852,0.3759999871253967,0.3790000081062317,0.3729999959468841,0.3790000081062317,0.3790000081062317,0.3889999985694885,0.3729999959468841,0.3819999992847442,0.3779999911785126,0.3770000040531158,0.3779999911785126,0.3810000121593475,0.3849999904632568,0.3790000081062317,0.3790000081062317,0.3980000019073486,0.3939999938011169,0.3980000019073486,0.382999986410141,0.4009999930858612,0.3930000066757202,0.4000000059604645,0.3959999978542328,0.4020000100135803,0.3959999978542328,0.395000010728836,0.3910000026226043,0.3970000147819519,0.3980000019073486,0.3989999890327453,0.4040000140666961,0.3899999856948852,0.4000000059604645,0.3889999985694885,0.382999986410141,0.3899999856948852,0.3919999897480011,0.4129999876022339,0.3980000019073486,0.3939999938011169,0.3980000019073486,0.4040000140666961,0.4009999930858612,0.4050000011920929,0.3939999938011169,0.4020000100135803,0.395000010728836,0.3939999938011169,0.4070000052452087,0.3989999890327453,0.3860000073909759,0.3980000019073486,0.4059999883174896,0.4040000140666961,0.4020000100135803,0.4110000133514404,0.4180000126361847,0.4090000092983246,0.4059999883174896,0.4050000011920929,0.402999997138977,0.3889999985694885,0.4149999916553497,0.4090000092983246,0.4059999883174896,0.4070000052452087,0.4180000126361847,0.4210000038146972,0.4180000126361847,0.4040000140666961,0.4059999883174896,0.4099999964237213,0.4230000078678131,0.4099999964237213,0.4309999942779541,0.3989999890327453,0.3980000019073486,0.4110000133514404,0.4169999957084656,0.4239999949932098,0.4259999990463257,0.4120000004768371,0.4120000004768371,0.4189999997615814,0.4180000126361847,0.4129999876022339,0.4090000092983246,0.4169999957084656,0.4199999868869781,0.4050000011920929,0.4040000140666961,0.4199999868869781,0.4160000085830688,0.4180000126361847,0.4040000140666961,0.4169999957084656,0.421999990940094,0.4280000030994415,0.4250000119209289,0.4210000038146972,0.4250000119209289,0.4250000119209289,0.4309999942779541,0.4210000038146972,0.4149999916553497,0.4160000085830688,0.4300000071525574,0.4239999949932098,0.4320000112056732,0.414000004529953,0.402999997138977,0.4149999916553497,0.4189999997615814,0.4129999876022339,0.4250000119209289,0.4199999868869781,0.4180000126361847,0.4329999983310699,0.4169999957084656,0.4230000078678131,0.4309999942779541,0.4259999990463257,0.4320000112056732,0.4169999957084656,0.4379999935626983,0.4280000030994415,0.421999990940094,0.4329999983310699,0.4239999949932098,0.4289999902248382,0.4189999997615814,0.4210000038146972,0.4250000119209289,0.4199999868869781,0.414000004529953,0.4169999957084656,0.4289999902248382,0.4250000119209289,0.4239999949932098,0.421999990940094,0.4269999861717224,0.4259999990463257,0.4230000078678131,0.421999990940094,0.4239999949932098],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2349999994039535,0.2770000100135803,0.2800000011920929,0.3000000119209289,0.3100000023841858,0.3230000138282776,0.328000009059906,0.3350000083446502,0.3319999873638153,0.3330000042915344,0.3420000076293945,0.3379999995231628,0.3479999899864197,0.3449999988079071,0.3499999940395355,0.3519999980926513,0.3499999940395355,0.3650000095367431,0.3709999918937683,0.3630000054836273,0.3680000007152557,0.3490000069141388,0.3470000028610229,0.356000006198883,0.3549999892711639,0.3619999885559082,0.3680000007152557,0.3529999852180481,0.367000013589859,0.3889999985694885,0.3810000121593475,0.3889999985694885,0.3770000040531158,0.3919999897480011,0.3729999959468841,0.3740000128746032,0.3740000128746032,0.382999986410141,0.3770000040531158,0.3860000073909759,0.375,0.3810000121593475,0.3779999911785126,0.375,0.3709999918937683,0.375,0.3779999911785126,0.3790000081062317,0.395000010728836,0.3819999992847442,0.3840000033378601,0.382999986410141,0.4000000059604645,0.382999986410141,0.3849999904632568,0.4009999930858612,0.3810000121593475,0.3729999959468841,0.3840000033378601,0.3939999938011169,0.3930000066757202,0.3840000033378601,0.3970000147819519,0.3840000033378601,0.3740000128746032,0.382999986410141,0.3889999985694885,0.3939999938011169,0.395000010728836,0.3989999890327453,0.3869999945163727,0.3930000066757202,0.3790000081062317,0.3799999952316284,0.3980000019073486,0.3959999978542328,0.3860000073909759,0.3919999897480011,0.3889999985694885,0.3880000114440918,0.3880000114440918,0.3860000073909759,0.3899999856948852,0.395000010728836,0.3910000026226043,0.3959999978542328,0.3939999938011169,0.3899999856948852,0.3919999897480011,0.3930000066757202,0.3689999878406524,0.3849999904632568,0.3939999938011169,0.3860000073909759,0.3939999938011169,0.3889999985694885,0.3910000026226043,0.4009999930858612,0.3910000026226043,0.4000000059604645,0.3849999904632568,0.3919999897480011,0.414000004529953,0.3880000114440918,0.4020000100135803,0.402999997138977,0.3959999978542328,0.3919999897480011,0.4059999883174896,0.375,0.4009999930858612,0.3860000073909759,0.3980000019073486,0.3959999978542328,0.3889999985694885,0.3980000019073486,0.4040000140666961,0.3959999978542328,0.3959999978542328,0.3810000121593475,0.4009999930858612,0.4009999930858612,0.4020000100135803,0.3959999978542328,0.3970000147819519,0.4050000011920929,0.4000000059604645,0.4040000140666961,0.4020000100135803,0.4009999930858612,0.4110000133514404,0.4129999876022339,0.4079999923706054,0.4090000092983246,0.4050000011920929,0.4020000100135803,0.4009999930858612,0.4059999883174896,0.3970000147819519,0.4009999930858612,0.402999997138977,0.4169999957084656,0.4040000140666961,0.4070000052452087,0.3919999897480011,0.4070000052452087,0.3980000019073486,0.4050000011920929,0.395000010728836,0.3989999890327453,0.4020000100135803,0.4070000052452087,0.4099999964237213,0.3989999890327453,0.3989999890327453,0.4059999883174896,0.4070000052452087,0.3980000019073486,0.4149999916553497,0.4079999923706054,0.4059999883174896,0.4050000011920929,0.3959999978542328,0.4149999916553497,0.4040000140666961,0.3939999938011169,0.4070000052452087],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2430000007152557,0.2599999904632568,0.2899999916553497,0.2930000126361847,0.2960000038146972,0.3109999895095825,0.3269999921321869,0.31700000166893,0.3199999928474426,0.3219999969005584,0.3300000131130218,0.3370000123977661,0.3339999914169311,0.3470000028610229,0.3219999969005584,0.3429999947547912,0.3370000123977661,0.3529999852180481,0.3519999980926513,0.363999992609024,0.3519999980926513,0.3589999973773956,0.3600000143051147,0.3589999973773956,0.3689999878406524,0.3420000076293945,0.3549999892711639,0.3549999892711639,0.3650000095367431,0.3610000014305115,0.3680000007152557,0.3659999966621399,0.3779999911785126,0.363999992609024,0.375,0.3709999918937683,0.3659999966621399,0.3650000095367431,0.3630000054836273,0.3650000095367431,0.3659999966621399,0.3689999878406524,0.3700000047683716,0.3709999918937683,0.363999992609024,0.375,0.3799999952316284,0.3689999878406524,0.3799999952316284,0.3849999904632568,0.3860000073909759,0.3810000121593475,0.3799999952316284,0.3790000081062317,0.382999986410141,0.3860000073909759,0.3810000121593475,0.3849999904632568,0.3860000073909759,0.3840000033378601,0.3849999904632568,0.3880000114440918,0.3790000081062317,0.3779999911785126,0.3819999992847442,0.3849999904632568,0.3869999945163727,0.3799999952316284,0.3840000033378601,0.3899999856948852,0.3759999871253967,0.3729999959468841,0.3860000073909759,0.3919999897480011,0.3759999871253967,0.3919999897480011,0.3989999890327453,0.4000000059604645,0.3849999904632568,0.4079999923706054,0.402999997138977,0.4000000059604645,0.3899999856948852,0.3970000147819519,0.395000010728836,0.3880000114440918,0.3939999938011169,0.3919999897480011,0.3899999856948852,0.3910000026226043,0.4040000140666961,0.395000010728836,0.3970000147819519,0.3989999890327453,0.3989999890327453,0.3989999890327453,0.4000000059604645,0.4009999930858612,0.3910000026226043,0.3939999938011169,0.4050000011920929,0.3980000019073486,0.3989999890327453,0.3919999897480011,0.395000010728836,0.3939999938011169,0.4070000052452087,0.3930000066757202,0.3930000066757202,0.4129999876022339,0.395000010728836,0.4050000011920929,0.4169999957084656,0.4079999923706054,0.4169999957084656,0.4110000133514404,0.4239999949932098,0.4120000004768371,0.4099999964237213,0.4059999883174896,0.4110000133514404,0.4020000100135803,0.4000000059604645,0.4000000059604645,0.4129999876022339,0.3959999978542328,0.402999997138977,0.4099999964237213,0.4110000133514404,0.4099999964237213,0.4079999923706054,0.4110000133514404,0.4099999964237213,0.4120000004768371,0.4120000004768371,0.4160000085830688,0.402999997138977,0.4120000004768371,0.4160000085830688,0.4050000011920929,0.402999997138977,0.414000004529953,0.4050000011920929,0.4050000011920929,0.4079999923706054,0.4059999883174896,0.4149999916553497,0.4070000052452087,0.4059999883174896,0.402999997138977,0.4110000133514404,0.4099999964237213,0.4040000140666961,0.402999997138977,0.3989999890327453,0.4070000052452087,0.402999997138977,0.4050000011920929,0.4020000100135803,0.402999997138977,0.4009999930858612,0.4020000100135803,0.4149999916553497,0.4050000011920929,0.4079999923706054,0.4090000092983246,0.4040000140666961],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1860000044107437,0.2450000047683715,0.2660000026226043,0.3009999990463257,0.3140000104904175,0.324999988079071,0.3199999928474426,0.3129999935626983,0.3129999935626983,0.3409999907016754,0.3370000123977661,0.3440000116825104,0.3370000123977661,0.3440000116825104,0.3379999995231628,0.3339999914169311,0.3389999866485595,0.3319999873638153,0.3339999914169311,0.3650000095367431,0.3630000054836273,0.3420000076293945,0.3479999899864197,0.3409999907016754,0.3429999947547912,0.3700000047683716,0.3610000014305115,0.3740000128746032,0.3709999918937683,0.3680000007152557,0.356000006198883,0.3549999892711639,0.3729999959468841,0.3720000088214874,0.3779999911785126,0.3709999918937683,0.3589999973773956,0.375,0.3689999878406524,0.3729999959468841,0.375,0.3650000095367431,0.3720000088214874,0.3799999952316284,0.3680000007152557,0.3680000007152557,0.3740000128746032,0.3939999938011169,0.3680000007152557,0.3810000121593475,0.367000013589859,0.3740000128746032,0.3799999952316284,0.3799999952316284,0.382999986410141,0.3819999992847442,0.3770000040531158,0.3880000114440918,0.3849999904632568,0.3970000147819519,0.3899999856948852,0.3919999897480011,0.3860000073909759,0.3910000026226043,0.3860000073909759,0.4000000059604645,0.3899999856948852,0.3869999945163727,0.3790000081062317,0.3980000019073486,0.3970000147819519,0.3840000033378601,0.3849999904632568,0.3799999952316284,0.3899999856948852,0.3889999985694885,0.3819999992847442,0.3869999945163727,0.4090000092983246,0.3880000114440918,0.3799999952316284,0.3799999952316284,0.3720000088214874,0.3849999904632568,0.3819999992847442,0.3919999897480011,0.382999986410141,0.3860000073909759,0.375,0.3720000088214874,0.3849999904632568,0.3759999871253967,0.3810000121593475,0.3849999904632568,0.3880000114440918,0.3880000114440918,0.3810000121593475,0.3849999904632568,0.3939999938011169,0.3799999952316284,0.3889999985694885,0.3819999992847442,0.3939999938011169,0.3930000066757202,0.3869999945163727,0.3860000073909759,0.3849999904632568,0.3880000114440918,0.3959999978542328,0.3889999985694885,0.4059999883174896,0.3880000114440918,0.3959999978542328,0.4000000059604645,0.3919999897480011,0.395000010728836,0.4000000059604645,0.3980000019073486,0.4070000052452087,0.3930000066757202,0.4009999930858612,0.3959999978542328,0.3970000147819519,0.3889999985694885,0.4079999923706054,0.3799999952316284,0.3860000073909759,0.4090000092983246,0.4040000140666961,0.4020000100135803,0.3980000019073486,0.4110000133514404,0.4110000133514404,0.395000010728836,0.395000010728836,0.4110000133514404,0.402999997138977,0.4000000059604645,0.3989999890327453,0.3959999978542328,0.3980000019073486,0.3930000066757202,0.4000000059604645,0.4079999923706054,0.4009999930858612,0.402999997138977,0.3970000147819519,0.4000000059604645,0.4099999964237213,0.4059999883174896,0.414000004529953,0.402999997138977,0.4050000011920929,0.402999997138977,0.4050000011920929,0.4040000140666961,0.4099999964237213,0.4040000140666961,0.4040000140666961,0.4009999930858612,0.4070000052452087,0.4000000059604645,0.4099999964237213,0.3959999978542328,0.3959999978542328,0.4050000011920929,0.3980000019073486,0.3980000019073486],"label":"FineWeb URL dedup"}},"commonsense_qa/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2529999911785126,0.2800000011920929,0.2870000004768371,0.3179999887943268,0.3129999935626983,0.3210000097751617,0.3160000145435333,0.3210000097751617,0.31700000166893,0.3330000042915344,0.3389999866485595,0.3289999961853027,0.3429999947547912,0.3379999995231628,0.3459999859333038,0.3490000069141388,0.3470000028610229,0.3600000143051147,0.3569999933242798,0.3449999988079071,0.3650000095367431,0.3499999940395355,0.3540000021457672,0.3569999933242798,0.3619999885559082,0.3619999885559082,0.3580000102519989,0.3740000128746032,0.3709999918937683,0.3720000088214874,0.3759999871253967,0.3720000088214874,0.3659999966621399,0.3790000081062317,0.3610000014305115,0.3650000095367431,0.3650000095367431,0.3720000088214874,0.3729999959468841,0.3790000081062317,0.3680000007152557,0.3659999966621399,0.3680000007152557,0.3619999885559082,0.3619999885559082,0.3729999959468841,0.3720000088214874,0.3650000095367431,0.3759999871253967,0.367000013589859,0.3650000095367431,0.3680000007152557,0.3580000102519989,0.3589999973773956,0.3700000047683716,0.3680000007152557,0.367000013589859,0.3709999918937683,0.3880000114440918,0.3810000121593475,0.375,0.4040000140666961,0.3860000073909759,0.3840000033378601,0.3779999911785126,0.3729999959468841,0.3720000088214874,0.3799999952316284,0.3799999952316284,0.3779999911785126,0.3689999878406524,0.3770000040531158,0.3740000128746032,0.3819999992847442,0.3899999856948852,0.3799999952316284,0.3919999897480011,0.3720000088214874,0.3770000040531158,0.3930000066757202,0.3849999904632568,0.3899999856948852,0.3740000128746032,0.3740000128746032,0.3799999952316284,0.3779999911785126,0.3880000114440918,0.3709999918937683,0.3810000121593475,0.3880000114440918,0.3980000019073486,0.3819999992847442,0.3849999904632568,0.3810000121593475,0.3819999992847442,0.3889999985694885,0.3840000033378601,0.3910000026226043,0.3899999856948852,0.3959999978542328,0.3880000114440918,0.3869999945163727,0.3779999911785126,0.3819999992847442,0.3919999897480011,0.3849999904632568,0.3860000073909759,0.3919999897480011,0.3819999992847442,0.3819999992847442,0.3889999985694885,0.3889999985694885,0.3860000073909759,0.3880000114440918,0.3889999985694885,0.3939999938011169,0.3899999856948852,0.3869999945163727,0.3910000026226043,0.3910000026226043,0.3910000026226043,0.3970000147819519,0.3970000147819519,0.3970000147819519,0.3970000147819519,0.3939999938011169,0.4000000059604645,0.3970000147819519,0.402999997138977,0.3959999978542328,0.3959999978542328,0.4000000059604645,0.4040000140666961,0.4020000100135803,0.3989999890327453,0.3919999897480011,0.3930000066757202,0.3930000066757202,0.3980000019073486,0.4000000059604645,0.395000010728836,0.3899999856948852,0.4059999883174896,0.4020000100135803,0.4020000100135803,0.4059999883174896,0.3970000147819519,0.4110000133514404,0.4050000011920929,0.4000000059604645,0.4090000092983246,0.3989999890327453,0.402999997138977,0.4009999930858612,0.3980000019073486,0.4090000092983246,0.4079999923706054,0.4079999923706054,0.4020000100135803,0.402999997138977,0.402999997138977,0.4059999883174896,0.4040000140666961,0.4059999883174896,0.3989999890327453,0.4070000052452087,0.4059999883174896],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2669999897480011,0.2759999930858612,0.2829999923706054,0.3030000030994415,0.3070000112056732,0.3140000104904175,0.3039999902248382,0.3199999928474426,0.3140000104904175,0.3129999935626983,0.3179999887943268,0.324999988079071,0.3240000009536743,0.3199999928474426,0.3319999873638153,0.3230000138282776,0.3210000097751617,0.3319999873638153,0.3339999914169311,0.328000009059906,0.324999988079071,0.335999995470047,0.3409999907016754,0.3459999859333038,0.3429999947547912,0.3529999852180481,0.3389999866485595,0.3409999907016754,0.3370000123977661,0.3440000116825104,0.3490000069141388,0.3440000116825104,0.3569999933242798,0.3519999980926513,0.3540000021457672,0.3580000102519989,0.3470000028610229,0.3479999899864197,0.3549999892711639,0.3429999947547912,0.3490000069141388,0.3499999940395355,0.3529999852180481,0.3490000069141388,0.3529999852180481,0.3569999933242798,0.367000013589859,0.3470000028610229,0.3540000021457672,0.3540000021457672,0.3549999892711639,0.3429999947547912,0.3479999899864197,0.3600000143051147,0.3610000014305115,0.356000006198883,0.3589999973773956,0.356000006198883,0.3600000143051147,0.3470000028610229,0.3549999892711639,0.3549999892711639,0.3580000102519989,0.3549999892711639,0.3510000109672546,0.3600000143051147,0.3610000014305115,0.367000013589859,0.363999992609024,0.3680000007152557,0.3549999892711639,0.3549999892711639,0.3720000088214874,0.3549999892711639,0.3720000088214874,0.3709999918937683,0.3580000102519989,0.3689999878406524,0.3680000007152557,0.3819999992847442,0.3610000014305115,0.3650000095367431,0.367000013589859,0.3659999966621399,0.363999992609024,0.3619999885559082,0.3689999878406524,0.367000013589859,0.3759999871253967,0.375,0.3589999973773956,0.3619999885559082,0.3720000088214874,0.3729999959468841,0.3659999966621399,0.3720000088214874,0.3700000047683716,0.3779999911785126,0.3729999959468841,0.3720000088214874,0.3779999911785126,0.3740000128746032,0.3799999952316284,0.3700000047683716,0.375,0.3709999918937683,0.3729999959468841,0.367000013589859,0.3650000095367431,0.375,0.382999986410141,0.3799999952316284,0.3779999911785126,0.3740000128746032,0.3650000095367431,0.3619999885559082,0.3720000088214874,0.3720000088214874,0.3740000128746032,0.3580000102519989,0.3779999911785126,0.375,0.3700000047683716,0.382999986410141,0.3779999911785126,0.3709999918937683,0.3790000081062317,0.3799999952316284,0.3810000121593475,0.3770000040531158,0.3790000081062317,0.3740000128746032,0.3779999911785126,0.3709999918937683,0.3779999911785126,0.382999986410141,0.3819999992847442,0.382999986410141,0.3799999952316284,0.3819999992847442,0.3709999918937683,0.3930000066757202,0.3860000073909759,0.3840000033378601,0.3860000073909759,0.3779999911785126,0.3880000114440918,0.3840000033378601,0.382999986410141,0.382999986410141,0.3840000033378601,0.3880000114440918,0.3869999945163727,0.3889999985694885,0.3790000081062317,0.3889999985694885,0.3770000040531158,0.3819999992847442,0.3840000033378601,0.3910000026226043,0.3799999952316284,0.3840000033378601,0.3889999985694885,0.3860000073909759,0.3770000040531158,0.3880000114440918,0.3880000114440918],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2599999904632568,0.277999997138977,0.2910000085830688,0.3070000112056732,0.3140000104904175,0.3019999861717224,0.3059999942779541,0.3210000097751617,0.3230000138282776,0.324999988079071,0.3149999976158142,0.3109999895095825,0.3339999914169311,0.3319999873638153,0.3319999873638153,0.3300000131130218,0.3370000123977661,0.3219999969005584,0.3370000123977661,0.328000009059906,0.3339999914169311,0.3420000076293945,0.3400000035762787,0.3440000116825104,0.3510000109672546,0.3409999907016754,0.3449999988079071,0.3339999914169311,0.3540000021457672,0.3339999914169311,0.3470000028610229,0.3470000028610229,0.3440000116825104,0.3589999973773956,0.3569999933242798,0.3630000054836273,0.3549999892711639,0.3589999973773956,0.3449999988079071,0.3549999892711639,0.3449999988079071,0.3389999866485595,0.3499999940395355,0.3610000014305115,0.3619999885559082,0.3600000143051147,0.3519999980926513,0.3479999899864197,0.356000006198883,0.3519999980926513,0.3440000116825104,0.3490000069141388,0.3519999980926513,0.3470000028610229,0.3589999973773956,0.3449999988079071,0.3490000069141388,0.356000006198883,0.3619999885559082,0.3569999933242798,0.3659999966621399,0.3610000014305115,0.3549999892711639,0.3700000047683716,0.363999992609024,0.3600000143051147,0.3580000102519989,0.3549999892711639,0.3619999885559082,0.3689999878406524,0.3630000054836273,0.363999992609024,0.3700000047683716,0.367000013589859,0.3630000054836273,0.3630000054836273,0.3700000047683716,0.3589999973773956,0.3540000021457672,0.3540000021457672,0.3659999966621399,0.3619999885559082,0.3589999973773956,0.3650000095367431,0.3709999918937683,0.3680000007152557,0.3689999878406524,0.3650000095367431,0.3729999959468841,0.3619999885559082,0.3689999878406524,0.3569999933242798,0.3510000109672546,0.3680000007152557,0.363999992609024,0.3700000047683716,0.3659999966621399,0.3659999966621399,0.363999992609024,0.3619999885559082,0.3659999966621399,0.3680000007152557,0.3610000014305115,0.3720000088214874,0.3729999959468841,0.3810000121593475,0.3630000054836273,0.3689999878406524,0.3709999918937683,0.3759999871253967,0.382999986410141,0.3729999959468841,0.3720000088214874,0.3680000007152557,0.3659999966621399,0.3650000095367431,0.363999992609024,0.3589999973773956,0.356000006198883,0.3650000095367431,0.3659999966621399,0.367000013589859,0.3729999959468841,0.3720000088214874,0.375,0.3740000128746032,0.3700000047683716,0.3569999933242798,0.3759999871253967,0.3740000128746032,0.367000013589859,0.3770000040531158,0.3759999871253967,0.3709999918937683,0.3779999911785126,0.3709999918937683,0.3689999878406524,0.3799999952316284,0.3630000054836273,0.375,0.3700000047683716,0.3700000047683716,0.3729999959468841,0.3720000088214874,0.3790000081062317,0.375,0.3729999959468841,0.3770000040531158,0.3799999952316284,0.3779999911785126,0.3720000088214874,0.3799999952316284,0.3759999871253967,0.3799999952316284,0.3790000081062317,0.375,0.3740000128746032,0.3729999959468841,0.3840000033378601,0.3659999966621399,0.3759999871253967,0.3720000088214874,0.3720000088214874,0.3759999871253967,0.375,0.3650000095367431,0.3729999959468841],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2590000033378601,0.2840000092983246,0.2980000078678131,0.3039999902248382,0.3190000057220459,0.3059999942779541,0.3210000097751617,0.328000009059906,0.3240000009536743,0.3330000042915344,0.328000009059906,0.3190000057220459,0.328000009059906,0.3310000002384186,0.3409999907016754,0.3470000028610229,0.3510000109672546,0.3409999907016754,0.3490000069141388,0.3379999995231628,0.3420000076293945,0.3510000109672546,0.3400000035762787,0.3540000021457672,0.3429999947547912,0.3440000116825104,0.3589999973773956,0.3420000076293945,0.356000006198883,0.3470000028610229,0.3529999852180481,0.3440000116825104,0.3459999859333038,0.3569999933242798,0.3529999852180481,0.3470000028610229,0.3479999899864197,0.3569999933242798,0.3540000021457672,0.3700000047683716,0.3619999885559082,0.3499999940395355,0.3610000014305115,0.3779999911785126,0.3650000095367431,0.3479999899864197,0.3650000095367431,0.356000006198883,0.3540000021457672,0.3680000007152557,0.3630000054836273,0.3610000014305115,0.363999992609024,0.3680000007152557,0.3740000128746032,0.3569999933242798,0.3619999885559082,0.3569999933242798,0.367000013589859,0.367000013589859,0.3680000007152557,0.363999992609024,0.3720000088214874,0.3689999878406524,0.3709999918937683,0.363999992609024,0.3580000102519989,0.3610000014305115,0.3610000014305115,0.3729999959468841,0.3740000128746032,0.3630000054836273,0.356000006198883,0.3700000047683716,0.375,0.3729999959468841,0.3689999878406524,0.3680000007152557,0.367000013589859,0.3650000095367431,0.363999992609024,0.363999992609024,0.3650000095367431,0.3680000007152557,0.3729999959468841,0.3680000007152557,0.3700000047683716,0.3720000088214874,0.3740000128746032,0.3610000014305115,0.3720000088214874,0.3729999959468841,0.3740000128746032,0.3720000088214874,0.3740000128746032,0.3650000095367431,0.375,0.382999986410141,0.3700000047683716,0.3680000007152557,0.363999992609024,0.3700000047683716,0.3720000088214874,0.3720000088214874,0.3709999918937683,0.3770000040531158,0.3650000095367431,0.3779999911785126,0.3700000047683716,0.3659999966621399,0.3650000095367431,0.3619999885559082,0.3759999871253967,0.375,0.3810000121593475,0.3689999878406524,0.3610000014305115,0.3650000095367431,0.3689999878406524,0.3689999878406524,0.3610000014305115,0.3770000040531158,0.3799999952316284,0.3740000128746032,0.382999986410141,0.3799999952316284,0.3799999952316284,0.3799999952316284,0.3790000081062317,0.3810000121593475,0.3740000128746032,0.3880000114440918,0.3740000128746032,0.3709999918937683,0.3729999959468841,0.375,0.3779999911785126,0.3810000121593475,0.3759999871253967,0.382999986410141,0.3779999911785126,0.3779999911785126,0.3790000081062317,0.3869999945163727,0.3810000121593475,0.3779999911785126,0.3770000040531158,0.3790000081062317,0.3819999992847442,0.3790000081062317,0.3790000081062317,0.375,0.375,0.3779999911785126,0.3799999952316284,0.3799999952316284,0.3799999952316284,0.3819999992847442,0.3869999945163727,0.3849999904632568,0.3840000033378601,0.3899999856948852,0.3840000033378601,0.3899999856948852,0.3810000121593475,0.3810000121593475,0.3869999945163727],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2639999985694885,0.2790000140666961,0.296999990940094,0.3109999895095825,0.3240000009536743,0.3070000112056732,0.3210000097751617,0.31700000166893,0.3339999914169311,0.324999988079071,0.3260000050067901,0.3330000042915344,0.3409999907016754,0.3400000035762787,0.3529999852180481,0.3400000035762787,0.3490000069141388,0.3529999852180481,0.3499999940395355,0.3459999859333038,0.3370000123977661,0.356000006198883,0.3490000069141388,0.3429999947547912,0.3490000069141388,0.3610000014305115,0.3499999940395355,0.3569999933242798,0.3610000014305115,0.3619999885559082,0.3449999988079071,0.3409999907016754,0.3420000076293945,0.3449999988079071,0.3409999907016754,0.3379999995231628,0.3420000076293945,0.3569999933242798,0.3529999852180481,0.3610000014305115,0.363999992609024,0.3600000143051147,0.3540000021457672,0.3499999940395355,0.3689999878406524,0.367000013589859,0.3569999933242798,0.3610000014305115,0.3680000007152557,0.3630000054836273,0.3709999918937683,0.3540000021457672,0.3580000102519989,0.367000013589859,0.3529999852180481,0.356000006198883,0.3569999933242798,0.3610000014305115,0.3700000047683716,0.375,0.3709999918937683,0.3819999992847442,0.3709999918937683,0.3650000095367431,0.3709999918937683,0.3650000095367431,0.3709999918937683,0.3840000033378601,0.3740000128746032,0.375,0.356000006198883,0.3689999878406524,0.3700000047683716,0.3819999992847442,0.3799999952316284,0.3779999911785126,0.3729999959468841,0.3709999918937683,0.3759999871253967,0.3709999918937683,0.3759999871253967,0.3779999911785126,0.3779999911785126,0.3689999878406524,0.3840000033378601,0.3860000073909759,0.3849999904632568,0.3790000081062317,0.375,0.3849999904632568,0.3720000088214874,0.3770000040531158,0.3799999952316284,0.3810000121593475,0.382999986410141,0.3650000095367431,0.3740000128746032,0.382999986410141,0.3689999878406524,0.3759999871253967,0.3869999945163727,0.3889999985694885,0.3860000073909759,0.3819999992847442,0.3689999878406524,0.3860000073909759,0.3810000121593475,0.382999986410141,0.3819999992847442,0.3840000033378601,0.3889999985694885,0.3880000114440918,0.3849999904632568,0.3799999952316284,0.3910000026226043,0.3989999890327453,0.3880000114440918,0.3880000114440918,0.3840000033378601,0.3880000114440918,0.3860000073909759,0.3919999897480011,0.3880000114440918,0.3939999938011169,0.3869999945163727,0.3919999897480011,0.3910000026226043,0.382999986410141,0.3930000066757202,0.3840000033378601,0.3880000114440918,0.3840000033378601,0.3819999992847442,0.382999986410141,0.3880000114440918,0.3860000073909759,0.3860000073909759,0.3869999945163727,0.3860000073909759,0.3899999856948852,0.3819999992847442,0.3860000073909759,0.3889999985694885,0.3840000033378601,0.395000010728836,0.3899999856948852,0.3899999856948852,0.3910000026226043,0.3959999978542328,0.3959999978542328,0.3919999897480011,0.3980000019073486,0.3880000114440918,0.3930000066757202,0.4000000059604645,0.3919999897480011,0.3919999897480011,0.4040000140666961,0.3930000066757202,0.3970000147819519,0.3889999985694885,0.3959999978542328,0.3930000066757202,0.3939999938011169,0.3970000147819519,0.3910000026226043,0.4020000100135803],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2569999992847442,0.2960000038146972,0.2949999868869781,0.3030000030994415,0.3149999976158142,0.3219999969005584,0.3370000123977661,0.335999995470047,0.335999995470047,0.3370000123977661,0.3379999995231628,0.3300000131130218,0.3330000042915344,0.3490000069141388,0.335999995470047,0.3379999995231628,0.3370000123977661,0.3389999866485595,0.3499999940395355,0.335999995470047,0.356000006198883,0.3459999859333038,0.3389999866485595,0.3490000069141388,0.3470000028610229,0.3339999914169311,0.3549999892711639,0.3519999980926513,0.3490000069141388,0.3610000014305115,0.3540000021457672,0.3619999885559082,0.3619999885559082,0.363999992609024,0.3549999892711639,0.3600000143051147,0.367000013589859,0.3459999859333038,0.356000006198883,0.3650000095367431,0.3569999933242798,0.3510000109672546,0.3580000102519989,0.3689999878406524,0.3529999852180481,0.3459999859333038,0.3540000021457672,0.3650000095367431,0.3549999892711639,0.3569999933242798,0.3700000047683716,0.3600000143051147,0.3650000095367431,0.3630000054836273,0.3540000021457672,0.363999992609024,0.3519999980926513,0.363999992609024,0.3630000054836273,0.375,0.3709999918937683,0.3519999980926513,0.363999992609024,0.3610000014305115,0.3529999852180481,0.3610000014305115,0.3700000047683716,0.367000013589859,0.3650000095367431,0.3619999885559082,0.3619999885559082,0.3709999918937683,0.3659999966621399,0.3589999973773956,0.3709999918937683,0.3650000095367431,0.3700000047683716,0.3810000121593475,0.3680000007152557,0.3779999911785126,0.3810000121593475,0.3659999966621399,0.3680000007152557,0.3759999871253967,0.3729999959468841,0.3720000088214874,0.363999992609024,0.3630000054836273,0.3700000047683716,0.3680000007152557,0.3659999966621399,0.3709999918937683,0.3759999871253967,0.3619999885559082,0.3729999959468841,0.3729999959468841,0.3779999911785126,0.363999992609024,0.3610000014305115,0.3680000007152557,0.3650000095367431,0.367000013589859,0.3860000073909759,0.367000013589859,0.3680000007152557,0.3720000088214874,0.3619999885559082,0.363999992609024,0.3720000088214874,0.3650000095367431,0.3650000095367431,0.3740000128746032,0.363999992609024,0.3720000088214874,0.382999986410141,0.3740000128746032,0.3740000128746032,0.3759999871253967,0.3720000088214874,0.3759999871253967,0.367000013589859,0.3709999918937683,0.375,0.375,0.3659999966621399,0.3689999878406524,0.3709999918937683,0.3720000088214874,0.3770000040531158,0.3799999952316284,0.3779999911785126,0.3770000040531158,0.3840000033378601,0.3790000081062317,0.3790000081062317,0.3779999911785126,0.3819999992847442,0.3650000095367431,0.3810000121593475,0.3700000047683716,0.3729999959468841,0.375,0.3700000047683716,0.3799999952316284,0.3729999959468841,0.3740000128746032,0.367000013589859,0.3790000081062317,0.3790000081062317,0.3740000128746032,0.375,0.3729999959468841,0.3759999871253967,0.3759999871253967,0.3740000128746032,0.3779999911785126,0.3849999904632568,0.3819999992847442,0.3779999911785126,0.3790000081062317,0.3740000128746032,0.3729999959468841,0.3700000047683716,0.3740000128746032,0.3729999959468841,0.3709999918937683,0.3799999952316284],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2649999856948852,0.2730000019073486,0.3039999902248382,0.3149999976158142,0.3129999935626983,0.324999988079071,0.3230000138282776,0.3310000002384186,0.328000009059906,0.3260000050067901,0.3319999873638153,0.3240000009536743,0.3339999914169311,0.3429999947547912,0.3389999866485595,0.335999995470047,0.3440000116825104,0.3389999866485595,0.3379999995231628,0.3440000116825104,0.3420000076293945,0.3440000116825104,0.3499999940395355,0.3470000028610229,0.3470000028610229,0.3490000069141388,0.3490000069141388,0.3389999866485595,0.3449999988079071,0.3459999859333038,0.3449999988079071,0.3510000109672546,0.3449999988079071,0.3440000116825104,0.3510000109672546,0.3459999859333038,0.3490000069141388,0.3479999899864197,0.3510000109672546,0.3440000116825104,0.3580000102519989,0.3449999988079071,0.3440000116825104,0.3420000076293945,0.3490000069141388,0.3549999892711639,0.3619999885559082,0.3420000076293945,0.3659999966621399,0.3689999878406524,0.356000006198883,0.363999992609024,0.3519999980926513,0.3600000143051147,0.3630000054836273,0.3600000143051147,0.3490000069141388,0.3700000047683716,0.3689999878406524,0.3689999878406524,0.3630000054836273,0.3729999959468841,0.3680000007152557,0.356000006198883,0.363999992609024,0.367000013589859,0.3580000102519989,0.3650000095367431,0.356000006198883,0.3630000054836273,0.3630000054836273,0.3470000028610229,0.3549999892711639,0.3569999933242798,0.3630000054836273,0.3680000007152557,0.3700000047683716,0.3589999973773956,0.3680000007152557,0.3779999911785126,0.3619999885559082,0.3689999878406524,0.3689999878406524,0.3689999878406524,0.3680000007152557,0.3709999918937683,0.3709999918937683,0.3779999911785126,0.3680000007152557,0.3619999885559082,0.3709999918937683,0.3720000088214874,0.3720000088214874,0.3790000081062317,0.3740000128746032,0.363999992609024,0.3709999918937683,0.3799999952316284,0.3770000040531158,0.3680000007152557,0.3709999918937683,0.3659999966621399,0.3779999911785126,0.3740000128746032,0.375,0.3790000081062317,0.3729999959468841,0.375,0.367000013589859,0.3819999992847442,0.3790000081062317,0.3720000088214874,0.3779999911785126,0.3799999952316284,0.3659999966621399,0.3810000121593475,0.3840000033378601,0.3700000047683716,0.3779999911785126,0.3759999871253967,0.375,0.3740000128746032,0.3779999911785126,0.3849999904632568,0.3819999992847442,0.375,0.3779999911785126,0.3819999992847442,0.3770000040531158,0.3819999992847442,0.3799999952316284,0.3799999952316284,0.3740000128746032,0.3799999952316284,0.3819999992847442,0.382999986410141,0.3869999945163727,0.3810000121593475,0.3889999985694885,0.3799999952316284,0.382999986410141,0.382999986410141,0.3869999945163727,0.382999986410141,0.3810000121593475,0.3790000081062317,0.3790000081062317,0.3810000121593475,0.3779999911785126,0.3840000033378601,0.3810000121593475,0.3810000121593475,0.3759999871253967,0.3720000088214874,0.3779999911785126,0.375,0.375,0.3799999952316284,0.3709999918937683,0.3799999952316284,0.3720000088214874,0.3659999966621399,0.3849999904632568,0.3770000040531158,0.3779999911785126,0.3759999871253967,0.3740000128746032],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2329999953508377,0.2529999911785126,0.2720000147819519,0.2879999876022339,0.3199999928474426,0.3039999902248382,0.31700000166893,0.3210000097751617,0.3149999976158142,0.3429999947547912,0.3319999873638153,0.335999995470047,0.3230000138282776,0.3400000035762787,0.3319999873638153,0.3319999873638153,0.3429999947547912,0.3479999899864197,0.3289999961853027,0.3510000109672546,0.3389999866485595,0.3510000109672546,0.3440000116825104,0.3449999988079071,0.3449999988079071,0.3470000028610229,0.3510000109672546,0.3549999892711639,0.3490000069141388,0.3610000014305115,0.3569999933242798,0.3600000143051147,0.3499999940395355,0.3580000102519989,0.3689999878406524,0.3370000123977661,0.3519999980926513,0.3659999966621399,0.3580000102519989,0.3409999907016754,0.367000013589859,0.3479999899864197,0.3580000102519989,0.356000006198883,0.3519999980926513,0.363999992609024,0.3630000054836273,0.367000013589859,0.3549999892711639,0.3519999980926513,0.3529999852180481,0.3610000014305115,0.3549999892711639,0.3709999918937683,0.367000013589859,0.3519999980926513,0.3589999973773956,0.3580000102519989,0.367000013589859,0.363999992609024,0.3659999966621399,0.3650000095367431,0.3689999878406524,0.3650000095367431,0.3740000128746032,0.375,0.367000013589859,0.3540000021457672,0.3619999885559082,0.375,0.363999992609024,0.3680000007152557,0.3589999973773956,0.3630000054836273,0.3529999852180481,0.3510000109672546,0.3630000054836273,0.363999992609024,0.3680000007152557,0.367000013589859,0.363999992609024,0.3619999885559082,0.3600000143051147,0.3619999885559082,0.3720000088214874,0.3680000007152557,0.3580000102519989,0.363999992609024,0.3630000054836273,0.3729999959468841,0.3589999973773956,0.3689999878406524,0.3580000102519989,0.3720000088214874,0.3600000143051147,0.3619999885559082,0.363999992609024,0.3680000007152557,0.3720000088214874,0.3630000054836273,0.3740000128746032,0.3630000054836273,0.3700000047683716,0.3680000007152557,0.3709999918937683,0.3720000088214874,0.3729999959468841,0.3680000007152557,0.3799999952316284,0.3740000128746032,0.3720000088214874,0.3650000095367431,0.3680000007152557,0.3720000088214874,0.3799999952316284,0.3700000047683716,0.3709999918937683,0.3759999871253967,0.3689999878406524,0.3709999918937683,0.3779999911785126,0.3650000095367431,0.3709999918937683,0.3600000143051147,0.3729999959468841,0.363999992609024,0.3779999911785126,0.3729999959468841,0.3740000128746032,0.3700000047683716,0.3600000143051147,0.3709999918937683,0.3740000128746032,0.3630000054836273,0.3740000128746032,0.3729999959468841,0.3799999952316284,0.367000013589859,0.3849999904632568,0.3740000128746032,0.3680000007152557,0.3709999918937683,0.3740000128746032,0.375,0.3799999952316284,0.3779999911785126,0.3740000128746032,0.3689999878406524,0.3799999952316284,0.375,0.3779999911785126,0.375,0.3740000128746032,0.3869999945163727,0.3810000121593475,0.382999986410141,0.3770000040531158,0.382999986410141,0.3799999952316284,0.3790000081062317,0.3779999911785126,0.3819999992847442,0.3880000114440918,0.375,0.375,0.3880000114440918,0.3810000121593475,0.3700000047683716],"label":"FineWeb URL dedup"}},"hellaswag/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2879999876022339,0.3149999976158142,0.3310000002384186,0.3400000035762787,0.3420000076293945,0.3510000109672546,0.3569999933242798,0.3689999878406524,0.3720000088214874,0.3860000073909759,0.3790000081062317,0.3840000033378601,0.395000010728836,0.4040000140666961,0.395000010728836,0.3980000019073486,0.4059999883174896,0.4090000092983246,0.414000004529953,0.4110000133514404,0.4079999923706054,0.4169999957084656,0.4149999916553497,0.4199999868869781,0.414000004529953,0.4230000078678131,0.4230000078678131,0.4199999868869781,0.4180000126361847,0.4269999861717224,0.4339999854564667,0.4329999983310699,0.4300000071525574,0.4289999902248382,0.4370000064373016,0.4390000104904175,0.4259999990463257,0.4379999935626983,0.4329999983310699,0.4300000071525574,0.4339999854564667,0.4309999942779541,0.4239999949932098,0.4399999976158142,0.4379999935626983,0.4370000064373016,0.4359999895095825,0.4410000145435333,0.4339999854564667,0.4390000104904175,0.4390000104904175,0.4379999935626983,0.4350000023841858,0.4350000023841858,0.4350000023841858,0.4329999983310699,0.4350000023841858,0.4359999895095825,0.4490000009536743,0.4449999928474426,0.4550000131130218,0.4390000104904175,0.4379999935626983,0.4490000009536743,0.4379999935626983,0.4410000145435333,0.4480000138282776,0.44200000166893,0.4370000064373016,0.4429999887943268,0.4539999961853027,0.4490000009536743,0.453000009059906,0.4539999961853027,0.4410000145435333,0.44200000166893,0.4510000050067901,0.4399999976158142,0.4460000097751617,0.449999988079071,0.4550000131130218,0.4480000138282776,0.453000009059906,0.4519999921321869,0.453000009059906,0.4429999887943268,0.4539999961853027,0.4519999921321869,0.4539999961853027,0.4490000009536743,0.4560000002384186,0.4519999921321869,0.4589999914169311,0.4539999961853027,0.4580000042915344,0.4550000131130218,0.4600000083446502,0.4490000009536743,0.4480000138282776,0.4589999914169311,0.4589999914169311,0.4519999921321869,0.4580000042915344,0.4429999887943268,0.4580000042915344,0.4510000050067901,0.4589999914169311,0.4510000050067901,0.4490000009536743,0.4440000057220459,0.4600000083446502,0.4600000083446502,0.453000009059906,0.4600000083446502,0.4569999873638153,0.460999995470047,0.4629999995231628,0.4620000123977661,0.4600000083446502,0.4600000083446502,0.4650000035762787,0.4620000123977661,0.4629999995231628,0.4659999907016754,0.4709999859333038,0.4679999947547912,0.4629999995231628,0.4589999914169311,0.4699999988079071,0.4650000035762787,0.4639999866485595,0.4600000083446502,0.4670000076293945,0.4740000069141388,0.4720000028610229,0.4720000028610229,0.4679999947547912,0.4720000028610229,0.4639999866485595,0.4679999947547912,0.4740000069141388,0.4659999907016754,0.4629999995231628,0.4740000069141388,0.4709999859333038,0.4729999899864197,0.460999995470047,0.4740000069141388,0.4720000028610229,0.4720000028610229,0.4709999859333038,0.4709999859333038,0.4769999980926513,0.4699999988079071,0.4679999947547912,0.4670000076293945,0.4699999988079071,0.4650000035762787,0.4659999907016754,0.4659999907016754,0.4670000076293945,0.4740000069141388,0.4709999859333038,0.4720000028610229,0.4690000116825104,0.4690000116825104,0.4670000076293945],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2870000004768371,0.3199999928474426,0.335999995470047,0.3370000123977661,0.3449999988079071,0.3529999852180481,0.3610000014305115,0.3650000095367431,0.367000013589859,0.3650000095367431,0.3790000081062317,0.3810000121593475,0.382999986410141,0.3849999904632568,0.3889999985694885,0.3899999856948852,0.382999986410141,0.3819999992847442,0.3980000019073486,0.3939999938011169,0.3939999938011169,0.4000000059604645,0.4009999930858612,0.402999997138977,0.3930000066757202,0.4050000011920929,0.4040000140666961,0.414000004529953,0.4070000052452087,0.4110000133514404,0.4099999964237213,0.4059999883174896,0.4040000140666961,0.4129999876022339,0.4149999916553497,0.4149999916553497,0.4160000085830688,0.4120000004768371,0.4160000085830688,0.4210000038146972,0.4199999868869781,0.4099999964237213,0.4160000085830688,0.4230000078678131,0.4199999868869781,0.4160000085830688,0.4110000133514404,0.4180000126361847,0.421999990940094,0.4269999861717224,0.4280000030994415,0.421999990940094,0.4210000038146972,0.4259999990463257,0.4230000078678131,0.4269999861717224,0.4199999868869781,0.4250000119209289,0.4239999949932098,0.4269999861717224,0.4269999861717224,0.414000004529953,0.4250000119209289,0.4250000119209289,0.4350000023841858,0.4320000112056732,0.4230000078678131,0.4309999942779541,0.4289999902248382,0.4239999949932098,0.4309999942779541,0.4269999861717224,0.4320000112056732,0.4210000038146972,0.4259999990463257,0.4329999983310699,0.4289999902248382,0.4269999861717224,0.4289999902248382,0.4339999854564667,0.4399999976158142,0.4390000104904175,0.4350000023841858,0.4350000023841858,0.4329999983310699,0.4359999895095825,0.4329999983310699,0.4359999895095825,0.4269999861717224,0.4359999895095825,0.4309999942779541,0.4350000023841858,0.4379999935626983,0.4399999976158142,0.4410000145435333,0.4329999983310699,0.4460000097751617,0.4469999969005584,0.4399999976158142,0.4429999887943268,0.4480000138282776,0.4469999969005584,0.4410000145435333,0.4469999969005584,0.4460000097751617,0.4410000145435333,0.4350000023841858,0.4440000057220459,0.4410000145435333,0.4449999928474426,0.44200000166893,0.4410000145435333,0.4469999969005584,0.44200000166893,0.4429999887943268,0.4490000009536743,0.4469999969005584,0.4440000057220459,0.4410000145435333,0.44200000166893,0.44200000166893,0.4449999928474426,0.4449999928474426,0.4449999928474426,0.4519999921321869,0.4550000131130218,0.449999988079071,0.4490000009536743,0.4460000097751617,0.4510000050067901,0.4469999969005584,0.4580000042915344,0.4480000138282776,0.4480000138282776,0.4480000138282776,0.4490000009536743,0.4560000002384186,0.4449999928474426,0.4519999921321869,0.4519999921321869,0.4429999887943268,0.4449999928474426,0.4490000009536743,0.4519999921321869,0.4460000097751617,0.4510000050067901,0.453000009059906,0.4449999928474426,0.4510000050067901,0.4490000009536743,0.4560000002384186,0.4510000050067901,0.453000009059906,0.4460000097751617,0.4469999969005584,0.453000009059906,0.4490000009536743,0.4510000050067901,0.4510000050067901,0.4539999961853027,0.4519999921321869,0.4580000042915344,0.4539999961853027,0.4560000002384186,0.453000009059906,0.4490000009536743,0.4519999921321869],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2899999916553497,0.3149999976158142,0.3269999921321869,0.3370000123977661,0.3459999859333038,0.3569999933242798,0.356000006198883,0.3630000054836273,0.3729999959468841,0.3630000054836273,0.3689999878406524,0.3840000033378601,0.3799999952316284,0.3819999992847442,0.3790000081062317,0.3790000081062317,0.3939999938011169,0.3989999890327453,0.3919999897480011,0.3970000147819519,0.4120000004768371,0.4079999923706054,0.3939999938011169,0.4090000092983246,0.4000000059604645,0.4090000092983246,0.4000000059604645,0.4099999964237213,0.4090000092983246,0.4090000092983246,0.4149999916553497,0.4160000085830688,0.4070000052452087,0.4110000133514404,0.4189999997615814,0.421999990940094,0.414000004529953,0.421999990940094,0.4269999861717224,0.4210000038146972,0.4129999876022339,0.4269999861717224,0.421999990940094,0.4269999861717224,0.4239999949932098,0.4289999902248382,0.4309999942779541,0.4329999983310699,0.4339999854564667,0.4390000104904175,0.4339999854564667,0.4350000023841858,0.4300000071525574,0.4350000023841858,0.4350000023841858,0.4280000030994415,0.4309999942779541,0.4350000023841858,0.4329999983310699,0.4480000138282776,0.4410000145435333,0.4410000145435333,0.4379999935626983,0.4390000104904175,0.4429999887943268,0.4480000138282776,0.4440000057220459,0.4460000097751617,0.4390000104904175,0.4449999928474426,0.4440000057220459,0.4390000104904175,0.4460000097751617,0.4379999935626983,0.4449999928474426,0.4399999976158142,0.4359999895095825,0.4410000145435333,0.4399999976158142,0.4449999928474426,0.4370000064373016,0.4449999928474426,0.4510000050067901,0.4460000097751617,0.4469999969005584,0.4519999921321869,0.4490000009536743,0.4460000097751617,0.4390000104904175,0.4580000042915344,0.4460000097751617,0.4469999969005584,0.4510000050067901,0.453000009059906,0.4510000050067901,0.4469999969005584,0.4510000050067901,0.4519999921321869,0.4589999914169311,0.4639999866485595,0.4519999921321869,0.4539999961853027,0.4519999921321869,0.449999988079071,0.4600000083446502,0.4569999873638153,0.4550000131130218,0.4539999961853027,0.4510000050067901,0.4620000123977661,0.4550000131130218,0.4560000002384186,0.453000009059906,0.4550000131130218,0.4629999995231628,0.4469999969005584,0.4569999873638153,0.4550000131130218,0.4539999961853027,0.4580000042915344,0.4539999961853027,0.4580000042915344,0.460999995470047,0.460999995470047,0.4560000002384186,0.4699999988079071,0.4629999995231628,0.4589999914169311,0.4629999995231628,0.4629999995231628,0.4580000042915344,0.4679999947547912,0.460999995470047,0.4629999995231628,0.4620000123977661,0.4659999907016754,0.4650000035762787,0.4580000042915344,0.4679999947547912,0.4580000042915344,0.4629999995231628,0.4659999907016754,0.4670000076293945,0.4629999995231628,0.4620000123977661,0.4670000076293945,0.4699999988079071,0.4679999947547912,0.4670000076293945,0.4690000116825104,0.4670000076293945,0.4659999907016754,0.4629999995231628,0.4650000035762787,0.4699999988079071,0.4659999907016754,0.4690000116825104,0.4699999988079071,0.4670000076293945,0.4679999947547912,0.4650000035762787,0.4690000116825104,0.4690000116825104,0.4670000076293945,0.4720000028610229,0.4699999988079071,0.4690000116825104],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2899999916553497,0.3120000064373016,0.3199999928474426,0.3389999866485595,0.3409999907016754,0.3490000069141388,0.3680000007152557,0.3630000054836273,0.3720000088214874,0.3720000088214874,0.3860000073909759,0.3939999938011169,0.3860000073909759,0.3919999897480011,0.3930000066757202,0.4079999923706054,0.4000000059604645,0.402999997138977,0.4000000059604645,0.4110000133514404,0.4090000092983246,0.4070000052452087,0.4180000126361847,0.4129999876022339,0.4099999964237213,0.4120000004768371,0.4189999997615814,0.4169999957084656,0.4210000038146972,0.4099999964237213,0.4210000038146972,0.4230000078678131,0.421999990940094,0.4300000071525574,0.4320000112056732,0.4300000071525574,0.4280000030994415,0.4289999902248382,0.4350000023841858,0.4250000119209289,0.4329999983310699,0.4359999895095825,0.4339999854564667,0.4359999895095825,0.4390000104904175,0.4289999902248382,0.4320000112056732,0.4250000119209289,0.4300000071525574,0.4309999942779541,0.4230000078678131,0.4339999854564667,0.4359999895095825,0.4339999854564667,0.4300000071525574,0.4269999861717224,0.4410000145435333,0.4399999976158142,0.4339999854564667,0.4370000064373016,0.4399999976158142,0.4250000119209289,0.4429999887943268,0.4309999942779541,0.4370000064373016,0.4429999887943268,0.4410000145435333,0.4350000023841858,0.4339999854564667,0.4460000097751617,0.4449999928474426,0.4379999935626983,0.4410000145435333,0.4449999928474426,0.4469999969005584,0.4379999935626983,0.4449999928474426,0.4440000057220459,0.449999988079071,0.4440000057220459,0.4480000138282776,0.4449999928474426,0.4460000097751617,0.4429999887943268,0.4469999969005584,0.4469999969005584,0.449999988079071,0.4569999873638153,0.4510000050067901,0.4460000097751617,0.4519999921321869,0.4469999969005584,0.4440000057220459,0.453000009059906,0.449999988079071,0.4460000097751617,0.449999988079071,0.4460000097751617,0.453000009059906,0.4510000050067901,0.4480000138282776,0.4510000050067901,0.4589999914169311,0.4580000042915344,0.4560000002384186,0.4510000050067901,0.449999988079071,0.4510000050067901,0.453000009059906,0.4519999921321869,0.4519999921321869,0.460999995470047,0.4569999873638153,0.4629999995231628,0.4580000042915344,0.4460000097751617,0.4589999914169311,0.4550000131130218,0.4659999907016754,0.4539999961853027,0.4510000050067901,0.4550000131130218,0.4569999873638153,0.4569999873638153,0.4569999873638153,0.4569999873638153,0.4480000138282776,0.4629999995231628,0.4639999866485595,0.4580000042915344,0.4650000035762787,0.4650000035762787,0.460999995470047,0.4589999914169311,0.460999995470047,0.4600000083446502,0.4670000076293945,0.460999995470047,0.460999995470047,0.4709999859333038,0.4629999995231628,0.4650000035762787,0.4589999914169311,0.4729999899864197,0.4670000076293945,0.4589999914169311,0.4629999995231628,0.4659999907016754,0.4659999907016754,0.4699999988079071,0.4639999866485595,0.4639999866485595,0.4709999859333038,0.4650000035762787,0.4709999859333038,0.460999995470047,0.4659999907016754,0.4690000116825104,0.4670000076293945,0.4670000076293945,0.4639999866485595,0.4650000035762787,0.4690000116825104,0.4670000076293945,0.4699999988079071,0.4709999859333038,0.4720000028610229],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2860000133514404,0.31700000166893,0.3190000057220459,0.3300000131130218,0.3499999940395355,0.3650000095367431,0.3630000054836273,0.3729999959468841,0.3840000033378601,0.3930000066757202,0.3910000026226043,0.3959999978542328,0.3919999897480011,0.3989999890327453,0.3910000026226043,0.4070000052452087,0.4110000133514404,0.4059999883174896,0.4070000052452087,0.4090000092983246,0.4189999997615814,0.4120000004768371,0.4189999997615814,0.4230000078678131,0.4120000004768371,0.4169999957084656,0.421999990940094,0.4210000038146972,0.4230000078678131,0.4239999949932098,0.4280000030994415,0.4269999861717224,0.421999990940094,0.4309999942779541,0.4280000030994415,0.4269999861717224,0.4269999861717224,0.4370000064373016,0.4329999983310699,0.4379999935626983,0.4309999942779541,0.4410000145435333,0.4399999976158142,0.4359999895095825,0.4440000057220459,0.4410000145435333,0.4469999969005584,0.449999988079071,0.4469999969005584,0.4519999921321869,0.460999995470047,0.44200000166893,0.4399999976158142,0.4410000145435333,0.4480000138282776,0.4589999914169311,0.453000009059906,0.4539999961853027,0.4469999969005584,0.4449999928474426,0.4469999969005584,0.4560000002384186,0.4519999921321869,0.4560000002384186,0.4550000131130218,0.453000009059906,0.4519999921321869,0.4539999961853027,0.4580000042915344,0.4589999914169311,0.4569999873638153,0.4550000131130218,0.4589999914169311,0.4600000083446502,0.4600000083446502,0.460999995470047,0.4589999914169311,0.4600000083446502,0.4539999961853027,0.4589999914169311,0.4580000042915344,0.4639999866485595,0.4629999995231628,0.4659999907016754,0.460999995470047,0.4690000116825104,0.4670000076293945,0.4709999859333038,0.4629999995231628,0.4620000123977661,0.4729999899864197,0.4670000076293945,0.4670000076293945,0.4740000069141388,0.4709999859333038,0.4690000116825104,0.4690000116825104,0.4709999859333038,0.460999995470047,0.4749999940395355,0.4729999899864197,0.4749999940395355,0.4740000069141388,0.4729999899864197,0.4650000035762787,0.4690000116825104,0.4839999973773956,0.4659999907016754,0.4830000102519989,0.4720000028610229,0.4659999907016754,0.4729999899864197,0.4760000109672546,0.4740000069141388,0.4690000116825104,0.4740000069141388,0.4769999980926513,0.4749999940395355,0.4679999947547912,0.4729999899864197,0.4720000028610229,0.4659999907016754,0.4720000028610229,0.4729999899864197,0.4769999980926513,0.4760000109672546,0.4779999852180481,0.4779999852180481,0.4749999940395355,0.4769999980926513,0.4749999940395355,0.4790000021457672,0.481000006198883,0.4720000028610229,0.4760000109672546,0.4799999892711639,0.4860000014305115,0.4839999973773956,0.4860000014305115,0.4790000021457672,0.4850000143051147,0.4799999892711639,0.4880000054836273,0.4860000014305115,0.4760000109672546,0.4830000102519989,0.4830000102519989,0.4799999892711639,0.4850000143051147,0.4830000102519989,0.4869999885559082,0.4760000109672546,0.4850000143051147,0.4819999933242798,0.4830000102519989,0.481000006198883,0.4869999885559082,0.4779999852180481,0.4830000102519989,0.4799999892711639,0.4850000143051147,0.4869999885559082,0.4880000054836273,0.4869999885559082,0.4819999933242798,0.4769999980926513,0.4900000095367431],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2840000092983246,0.3100000023841858,0.3260000050067901,0.3420000076293945,0.3510000109672546,0.3529999852180481,0.3549999892711639,0.3619999885559082,0.3700000047683716,0.3770000040531158,0.3680000007152557,0.3810000121593475,0.3819999992847442,0.3869999945163727,0.3779999911785126,0.3910000026226043,0.3889999985694885,0.3919999897480011,0.3849999904632568,0.382999986410141,0.3889999985694885,0.3970000147819519,0.3989999890327453,0.4050000011920929,0.3959999978542328,0.4020000100135803,0.4059999883174896,0.4059999883174896,0.4059999883174896,0.4040000140666961,0.4040000140666961,0.4099999964237213,0.4189999997615814,0.4090000092983246,0.4099999964237213,0.4160000085830688,0.4059999883174896,0.4160000085830688,0.4199999868869781,0.4169999957084656,0.4189999997615814,0.4180000126361847,0.4230000078678131,0.421999990940094,0.421999990940094,0.4169999957084656,0.4199999868869781,0.4230000078678131,0.4239999949932098,0.4189999997615814,0.4280000030994415,0.4149999916553497,0.4230000078678131,0.4329999983310699,0.4269999861717224,0.4289999902248382,0.4259999990463257,0.4280000030994415,0.4390000104904175,0.4309999942779541,0.4359999895095825,0.4250000119209289,0.4320000112056732,0.4230000078678131,0.4379999935626983,0.4410000145435333,0.44200000166893,0.4339999854564667,0.4370000064373016,0.4410000145435333,0.4359999895095825,0.4320000112056732,0.4269999861717224,0.4329999983310699,0.4379999935626983,0.4399999976158142,0.4390000104904175,0.4320000112056732,0.4399999976158142,0.4410000145435333,0.4379999935626983,0.4410000145435333,0.4410000145435333,0.4379999935626983,0.4339999854564667,0.4399999976158142,0.4449999928474426,0.4460000097751617,0.453000009059906,0.453000009059906,0.44200000166893,0.44200000166893,0.4490000009536743,0.4490000009536743,0.4480000138282776,0.4569999873638153,0.4469999969005584,0.4460000097751617,0.4550000131130218,0.4440000057220459,0.4560000002384186,0.4569999873638153,0.4589999914169311,0.4539999961853027,0.453000009059906,0.449999988079071,0.4519999921321869,0.4519999921321869,0.4510000050067901,0.4560000002384186,0.4600000083446502,0.4580000042915344,0.4600000083446502,0.4560000002384186,0.453000009059906,0.453000009059906,0.4539999961853027,0.4569999873638153,0.4580000042915344,0.4519999921321869,0.4650000035762787,0.453000009059906,0.4519999921321869,0.4569999873638153,0.4539999961853027,0.4620000123977661,0.4589999914169311,0.453000009059906,0.4580000042915344,0.460999995470047,0.4569999873638153,0.4580000042915344,0.4580000042915344,0.4679999947547912,0.4580000042915344,0.4600000083446502,0.4629999995231628,0.4569999873638153,0.4560000002384186,0.4589999914169311,0.4580000042915344,0.4560000002384186,0.4620000123977661,0.460999995470047,0.460999995470047,0.4600000083446502,0.4620000123977661,0.4519999921321869,0.4639999866485595,0.4629999995231628,0.4560000002384186,0.4659999907016754,0.4550000131130218,0.4589999914169311,0.4659999907016754,0.4629999995231628,0.4589999914169311,0.4639999866485595,0.4569999873638153,0.460999995470047,0.4589999914169311,0.4650000035762787,0.4629999995231628,0.4600000083446502,0.4620000123977661,0.4620000123977661,0.4659999907016754],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2910000085830688,0.3160000145435333,0.3289999961853027,0.3429999947547912,0.3499999940395355,0.3529999852180481,0.3630000054836273,0.3650000095367431,0.3729999959468841,0.3650000095367431,0.3689999878406524,0.3799999952316284,0.3819999992847442,0.375,0.3759999871253967,0.3939999938011169,0.3959999978542328,0.3980000019073486,0.3989999890327453,0.4000000059604645,0.3980000019073486,0.4040000140666961,0.4070000052452087,0.414000004529953,0.4059999883174896,0.4099999964237213,0.4110000133514404,0.4160000085830688,0.4160000085830688,0.414000004529953,0.414000004529953,0.421999990940094,0.4160000085830688,0.421999990940094,0.4149999916553497,0.4160000085830688,0.4259999990463257,0.4189999997615814,0.421999990940094,0.4180000126361847,0.4259999990463257,0.4280000030994415,0.4339999854564667,0.4189999997615814,0.4269999861717224,0.4239999949932098,0.4320000112056732,0.4350000023841858,0.421999990940094,0.4320000112056732,0.4289999902248382,0.4390000104904175,0.4320000112056732,0.4230000078678131,0.4359999895095825,0.4289999902248382,0.4429999887943268,0.4379999935626983,0.4429999887943268,0.4289999902248382,0.4429999887943268,0.4429999887943268,0.4399999976158142,0.4370000064373016,0.44200000166893,0.4440000057220459,0.4480000138282776,0.4429999887943268,0.4460000097751617,0.44200000166893,0.44200000166893,0.4399999976158142,0.4440000057220459,0.4469999969005584,0.4429999887943268,0.4390000104904175,0.4390000104904175,0.4440000057220459,0.4370000064373016,0.4399999976158142,0.44200000166893,0.4469999969005584,0.4379999935626983,0.44200000166893,0.4449999928474426,0.4390000104904175,0.4390000104904175,0.4440000057220459,0.4390000104904175,0.4440000057220459,0.4569999873638153,0.4510000050067901,0.4620000123977661,0.4510000050067901,0.4490000009536743,0.4510000050067901,0.4550000131130218,0.4510000050067901,0.4469999969005584,0.4449999928474426,0.4399999976158142,0.4480000138282776,0.4490000009536743,0.4469999969005584,0.4510000050067901,0.4519999921321869,0.460999995470047,0.4519999921321869,0.4550000131130218,0.4659999907016754,0.453000009059906,0.4539999961853027,0.4480000138282776,0.4519999921321869,0.4550000131130218,0.4539999961853027,0.4510000050067901,0.4539999961853027,0.4629999995231628,0.4620000123977661,0.4629999995231628,0.4600000083446502,0.4539999961853027,0.4600000083446502,0.4580000042915344,0.4569999873638153,0.4620000123977661,0.4639999866485595,0.4679999947547912,0.4650000035762787,0.4659999907016754,0.4629999995231628,0.4580000042915344,0.4729999899864197,0.4670000076293945,0.4629999995231628,0.4629999995231628,0.4659999907016754,0.4699999988079071,0.4650000035762787,0.4589999914169311,0.4620000123977661,0.4659999907016754,0.4679999947547912,0.4629999995231628,0.4629999995231628,0.4679999947547912,0.4690000116825104,0.4740000069141388,0.460999995470047,0.4699999988079071,0.4690000116825104,0.4709999859333038,0.4690000116825104,0.4690000116825104,0.4679999947547912,0.4699999988079071,0.4679999947547912,0.4650000035762787,0.4620000123977661,0.4670000076293945,0.4679999947547912,0.4720000028610229,0.4699999988079071,0.4650000035762787,0.4639999866485595,0.4690000116825104],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2720000147819519,0.2849999964237213,0.3100000023841858,0.3230000138282776,0.335999995470047,0.3540000021457672,0.3600000143051147,0.3759999871253967,0.375,0.3720000088214874,0.3889999985694885,0.3790000081062317,0.3819999992847442,0.3939999938011169,0.3880000114440918,0.3959999978542328,0.3980000019073486,0.3939999938011169,0.4040000140666961,0.4110000133514404,0.4110000133514404,0.4099999964237213,0.4169999957084656,0.414000004529953,0.4199999868869781,0.4230000078678131,0.4280000030994415,0.4189999997615814,0.4189999997615814,0.4280000030994415,0.4239999949932098,0.414000004529953,0.4309999942779541,0.4230000078678131,0.4250000119209289,0.4149999916553497,0.421999990940094,0.4180000126361847,0.421999990940094,0.4269999861717224,0.4289999902248382,0.4350000023841858,0.4350000023841858,0.4410000145435333,0.4350000023841858,0.4350000023841858,0.4329999983310699,0.4370000064373016,0.4379999935626983,0.4410000145435333,0.4280000030994415,0.4370000064373016,0.4469999969005584,0.4390000104904175,0.4379999935626983,0.4359999895095825,0.4429999887943268,0.4399999976158142,0.4399999976158142,0.4460000097751617,0.4440000057220459,0.4399999976158142,0.4410000145435333,0.4440000057220459,0.4359999895095825,0.4309999942779541,0.4429999887943268,0.4490000009536743,0.4429999887943268,0.4440000057220459,0.4519999921321869,0.449999988079071,0.4460000097751617,0.4469999969005584,0.4490000009536743,0.44200000166893,0.4440000057220459,0.4410000145435333,0.4399999976158142,0.4519999921321869,0.4469999969005584,0.4429999887943268,0.4440000057220459,0.4429999887943268,0.4460000097751617,0.4560000002384186,0.4510000050067901,0.4469999969005584,0.4620000123977661,0.4460000097751617,0.4560000002384186,0.4560000002384186,0.4580000042915344,0.453000009059906,0.4539999961853027,0.4539999961853027,0.4569999873638153,0.4569999873638153,0.4569999873638153,0.4539999961853027,0.4510000050067901,0.4490000009536743,0.453000009059906,0.4539999961853027,0.4519999921321869,0.4620000123977661,0.4620000123977661,0.460999995470047,0.4650000035762787,0.460999995470047,0.4670000076293945,0.4639999866485595,0.4709999859333038,0.4639999866485595,0.4760000109672546,0.4679999947547912,0.4639999866485595,0.4690000116825104,0.4679999947547912,0.4650000035762787,0.4709999859333038,0.4709999859333038,0.4639999866485595,0.4699999988079071,0.4670000076293945,0.4690000116825104,0.4670000076293945,0.4639999866485595,0.4629999995231628,0.4650000035762787,0.4620000123977661,0.4690000116825104,0.4650000035762787,0.4659999907016754,0.4639999866485595,0.4699999988079071,0.4720000028610229,0.4740000069141388,0.4740000069141388,0.4720000028610229,0.4729999899864197,0.4679999947547912,0.4709999859333038,0.4720000028610229,0.4690000116825104,0.4749999940395355,0.4729999899864197,0.4830000102519989,0.4779999852180481,0.4740000069141388,0.4769999980926513,0.4760000109672546,0.4699999988079071,0.4679999947547912,0.4779999852180481,0.4779999852180481,0.4729999899864197,0.4709999859333038,0.4760000109672546,0.4790000021457672,0.4760000109672546,0.4769999980926513,0.4779999852180481,0.4769999980926513,0.4779999852180481,0.4740000069141388,0.4699999988079071,0.4769999980926513],"label":"FineWeb URL dedup"}},"hellaswag/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.2759999930858612,0.328000009059906,0.3499999940395355,0.3889999985694885,0.3910000026226043,0.402999997138977,0.4210000038146972,0.4280000030994415,0.4359999895095825,0.4469999969005584,0.4440000057220459,0.4600000083446502,0.4690000116825104,0.4679999947547912,0.4729999899864197,0.4760000109672546,0.4839999973773956,0.4939999878406524,0.488999992609024,0.4990000128746032,0.4979999959468841,0.4979999959468841,0.5009999871253967,0.5,0.5090000033378601,0.5070000290870667,0.5180000066757202,0.5199999809265137,0.5109999775886536,0.5130000114440918,0.5249999761581421,0.5149999856948853,0.5299999713897705,0.5339999794960022,0.5189999938011169,0.5289999842643738,0.5249999761581421,0.5320000052452087,0.5460000038146973,0.5419999957084656,0.5260000228881836,0.5289999842643738,0.546999990940094,0.5419999957084656,0.5419999957084656,0.5460000038146973,0.5419999957084656,0.5389999747276306,0.5440000295639038,0.5569999814033508,0.5450000166893005,0.5329999923706055,0.5580000281333923,0.5339999794960022,0.5540000200271606,0.5460000038146973,0.5479999780654907,0.5529999732971191,0.5540000200271606,0.5619999766349792,0.5490000247955322,0.5410000085830688,0.5490000247955322,0.5569999814033508,0.550000011920929,0.5479999780654907,0.5630000233650208,0.546999990940094,0.5559999942779541,0.5600000023841858,0.5509999990463257,0.5569999814033508,0.5569999814033508,0.5580000281333923,0.5619999766349792,0.5580000281333923,0.5669999718666077,0.5569999814033508,0.5709999799728394,0.5529999732971191,0.5649999976158142,0.5659999847412109,0.5659999847412109,0.5690000057220459,0.5600000023841858,0.5580000281333923,0.5540000200271606,0.5640000104904175,0.5680000185966492,0.5709999799728394,0.5649999976158142,0.5680000185966492,0.5730000138282776,0.5640000104904175,0.5799999833106995,0.5699999928474426,0.5669999718666077,0.5680000185966492,0.5770000219345093,0.5709999799728394,0.5759999752044678,0.5690000057220459,0.5789999961853027,0.5740000009536743,0.5709999799728394,0.5789999961853027,0.5709999799728394,0.5770000219345093,0.5770000219345093,0.5730000138282776,0.5809999704360962,0.5720000267028809,0.5849999785423279,0.5820000171661377,0.5799999833106995,0.5830000042915344,0.5759999752044678,0.5730000138282776,0.5799999833106995,0.5830000042915344,0.5860000252723694,0.5789999961853027,0.5789999961853027,0.5860000252723694,0.5979999899864197,0.5920000076293945,0.5820000171661377,0.5870000123977661,0.5889999866485596,0.5839999914169312,0.5849999785423279,0.5899999737739563,0.5920000076293945,0.593999981880188,0.597000002861023,0.5889999866485596,0.5889999866485596,0.5849999785423279,0.5899999737739563,0.5989999771118164,0.5899999737739563,0.5839999914169312,0.5910000205039978,0.5910000205039978,0.5929999947547913,0.5920000076293945,0.5929999947547913,0.5889999866485596,0.5899999737739563,0.593999981880188,0.5910000205039978,0.5960000157356262,0.5920000076293945,0.5889999866485596,0.593999981880188,0.5879999995231628,0.5960000157356262,0.5920000076293945,0.5960000157356262,0.5960000157356262,0.5920000076293945,0.6010000109672546,0.5920000076293945,0.5899999737739563,0.5889999866485596,0.5920000076293945,0.6019999980926514],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.2809999883174896,0.3219999969005584,0.3499999940395355,0.3529999852180481,0.3759999871253967,0.3869999945163727,0.4009999930858612,0.4090000092983246,0.4129999876022339,0.4269999861717224,0.4320000112056732,0.4300000071525574,0.44200000166893,0.4429999887943268,0.449999988079071,0.4519999921321869,0.4639999866485595,0.4589999914169311,0.4720000028610229,0.4729999899864197,0.4670000076293945,0.4749999940395355,0.4790000021457672,0.4690000116825104,0.4720000028610229,0.4729999899864197,0.4699999988079071,0.4830000102519989,0.4699999988079071,0.4930000007152557,0.4939999878406524,0.4850000143051147,0.4860000014305115,0.4979999959468841,0.4950000047683716,0.4990000128746032,0.4900000095367431,0.4900000095367431,0.4959999918937683,0.4950000047683716,0.492000013589859,0.4909999966621399,0.4990000128746032,0.5090000033378601,0.5090000033378601,0.5090000033378601,0.5040000081062317,0.5059999823570251,0.4990000128746032,0.5149999856948853,0.5090000033378601,0.5049999952316284,0.5139999985694885,0.5139999985694885,0.5120000243186951,0.5130000114440918,0.5180000066757202,0.515999972820282,0.5109999775886536,0.5260000228881836,0.5130000114440918,0.5070000290870667,0.5239999890327454,0.5130000114440918,0.5199999809265137,0.515999972820282,0.5199999809265137,0.5230000019073486,0.5249999761581421,0.5249999761581421,0.5090000033378601,0.5210000276565552,0.5339999794960022,0.5210000276565552,0.5320000052452087,0.5260000228881836,0.527999997138977,0.5299999713897705,0.5199999809265137,0.5289999842643738,0.5370000004768372,0.5289999842643738,0.5260000228881836,0.5370000004768372,0.5389999747276306,0.5249999761581421,0.5320000052452087,0.5339999794960022,0.5239999890327454,0.5360000133514404,0.5270000100135803,0.5339999794960022,0.5389999747276306,0.5379999876022339,0.5320000052452087,0.5289999842643738,0.5370000004768372,0.5410000085830688,0.531000018119812,0.5360000133514404,0.531000018119812,0.5360000133514404,0.5350000262260437,0.5450000166893005,0.5329999923706055,0.5429999828338623,0.5490000247955322,0.5419999957084656,0.5410000085830688,0.5379999876022339,0.5419999957084656,0.5460000038146973,0.5339999794960022,0.5550000071525574,0.5529999732971191,0.5509999990463257,0.546999990940094,0.5429999828338623,0.5450000166893005,0.5509999990463257,0.5509999990463257,0.5419999957084656,0.550000011920929,0.5440000295639038,0.5410000085830688,0.5400000214576721,0.5479999780654907,0.5529999732971191,0.5509999990463257,0.5460000038146973,0.5529999732971191,0.5479999780654907,0.5490000247955322,0.5519999861717224,0.546999990940094,0.5460000038146973,0.546999990940094,0.5479999780654907,0.5479999780654907,0.5580000281333923,0.5519999861717224,0.5580000281333923,0.5559999942779541,0.5550000071525574,0.5590000152587891,0.5540000200271606,0.5509999990463257,0.5519999861717224,0.5580000281333923,0.5550000071525574,0.5509999990463257,0.5479999780654907,0.5580000281333923,0.5529999732971191,0.5509999990463257,0.5529999732971191,0.5550000071525574,0.5529999732971191,0.5590000152587891,0.5559999942779541,0.5569999814033508,0.5590000152587891,0.5509999990463257,0.5540000200271606,0.5569999814033508,0.5569999814033508,0.5559999942779541],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.2809999883174896,0.3230000138282776,0.3409999907016754,0.3600000143051147,0.3569999933242798,0.3889999985694885,0.395000010728836,0.4199999868869781,0.4180000126361847,0.421999990940094,0.4289999902248382,0.4350000023841858,0.4359999895095825,0.4350000023841858,0.4480000138282776,0.4480000138282776,0.453000009059906,0.4550000131130218,0.4589999914169311,0.4639999866485595,0.4600000083446502,0.460999995470047,0.4589999914169311,0.481000006198883,0.4769999980926513,0.4709999859333038,0.4740000069141388,0.4679999947547912,0.4790000021457672,0.4729999899864197,0.4819999933242798,0.4850000143051147,0.4819999933242798,0.4819999933242798,0.4880000054836273,0.4869999885559082,0.4959999918937683,0.4850000143051147,0.4959999918937683,0.492000013589859,0.503000020980835,0.4930000007152557,0.5099999904632568,0.5040000081062317,0.5009999871253967,0.4970000088214874,0.4979999959468841,0.5059999823570251,0.5070000290870667,0.5040000081062317,0.5059999823570251,0.5049999952316284,0.5080000162124634,0.5049999952316284,0.5019999742507935,0.5120000243186951,0.5170000195503235,0.5170000195503235,0.5090000033378601,0.5239999890327454,0.527999997138977,0.5230000019073486,0.5210000276565552,0.5149999856948853,0.5189999938011169,0.5270000100135803,0.5149999856948853,0.5099999904632568,0.5299999713897705,0.5199999809265137,0.5230000019073486,0.5260000228881836,0.5249999761581421,0.5239999890327454,0.5329999923706055,0.5210000276565552,0.5260000228881836,0.5170000195503235,0.531000018119812,0.5289999842643738,0.531000018119812,0.5270000100135803,0.5299999713897705,0.5370000004768372,0.5379999876022339,0.5419999957084656,0.5329999923706055,0.5360000133514404,0.5299999713897705,0.5360000133514404,0.5270000100135803,0.5450000166893005,0.5410000085830688,0.546999990940094,0.5329999923706055,0.5329999923706055,0.5379999876022339,0.5299999713897705,0.5429999828338623,0.5360000133514404,0.5339999794960022,0.5419999957084656,0.5410000085830688,0.5370000004768372,0.5389999747276306,0.527999997138977,0.5400000214576721,0.5400000214576721,0.531000018119812,0.5440000295639038,0.5460000038146973,0.5479999780654907,0.5460000038146973,0.5410000085830688,0.5509999990463257,0.5479999780654907,0.5410000085830688,0.5389999747276306,0.550000011920929,0.5569999814033508,0.550000011920929,0.5490000247955322,0.5490000247955322,0.5569999814033508,0.5519999861717224,0.5479999780654907,0.5559999942779541,0.5550000071525574,0.5460000038146973,0.5540000200271606,0.5460000038146973,0.5460000038146973,0.5509999990463257,0.5460000038146973,0.5550000071525574,0.5479999780654907,0.5479999780654907,0.5540000200271606,0.5550000071525574,0.5529999732971191,0.5529999732971191,0.5509999990463257,0.5509999990463257,0.5419999957084656,0.546999990940094,0.5509999990463257,0.5559999942779541,0.5490000247955322,0.5509999990463257,0.5529999732971191,0.550000011920929,0.5540000200271606,0.5550000071525574,0.5580000281333923,0.550000011920929,0.5569999814033508,0.5490000247955322,0.5519999861717224,0.5519999861717224,0.5559999942779541,0.5569999814033508,0.5559999942779541,0.5550000071525574,0.5559999942779541,0.5490000247955322,0.5550000071525574,0.5600000023841858],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.2800000011920929,0.3210000097751617,0.3370000123977661,0.3569999933242798,0.3849999904632568,0.3959999978542328,0.4099999964237213,0.4189999997615814,0.4199999868869781,0.4289999902248382,0.4410000145435333,0.4490000009536743,0.4539999961853027,0.4589999914169311,0.4620000123977661,0.453000009059906,0.4729999899864197,0.4779999852180481,0.4709999859333038,0.4850000143051147,0.4839999973773956,0.4839999973773956,0.4729999899864197,0.4880000054836273,0.4930000007152557,0.4779999852180481,0.503000020980835,0.4939999878406524,0.4990000128746032,0.5,0.5019999742507935,0.5120000243186951,0.5130000114440918,0.5109999775886536,0.5109999775886536,0.5049999952316284,0.5049999952316284,0.5149999856948853,0.5199999809265137,0.515999972820282,0.5130000114440918,0.5149999856948853,0.5090000033378601,0.5210000276565552,0.5149999856948853,0.5170000195503235,0.5149999856948853,0.5260000228881836,0.5189999938011169,0.5239999890327454,0.531000018119812,0.5239999890327454,0.5260000228881836,0.5270000100135803,0.527999997138977,0.5299999713897705,0.5320000052452087,0.5299999713897705,0.5329999923706055,0.531000018119812,0.5370000004768372,0.5329999923706055,0.531000018119812,0.5350000262260437,0.5329999923706055,0.5299999713897705,0.5410000085830688,0.5450000166893005,0.5440000295639038,0.5370000004768372,0.5339999794960022,0.5379999876022339,0.5329999923706055,0.5350000262260437,0.5339999794960022,0.5410000085830688,0.5490000247955322,0.5509999990463257,0.5400000214576721,0.5509999990463257,0.550000011920929,0.5490000247955322,0.5389999747276306,0.546999990940094,0.546999990940094,0.5360000133514404,0.5329999923706055,0.5339999794960022,0.546999990940094,0.5440000295639038,0.5600000023841858,0.5460000038146973,0.5490000247955322,0.5479999780654907,0.5509999990463257,0.5479999780654907,0.5429999828338623,0.5490000247955322,0.5419999957084656,0.5460000038146973,0.5519999861717224,0.5460000038146973,0.5550000071525574,0.5450000166893005,0.5440000295639038,0.5519999861717224,0.5490000247955322,0.550000011920929,0.5509999990463257,0.5479999780654907,0.5649999976158142,0.550000011920929,0.5600000023841858,0.5609999895095825,0.5580000281333923,0.5529999732971191,0.5529999732971191,0.5529999732971191,0.5590000152587891,0.5590000152587891,0.5590000152587891,0.5559999942779541,0.5479999780654907,0.5580000281333923,0.5550000071525574,0.5550000071525574,0.5550000071525574,0.5550000071525574,0.5559999942779541,0.5609999895095825,0.5580000281333923,0.5619999766349792,0.5619999766349792,0.5580000281333923,0.5619999766349792,0.5600000023841858,0.5590000152587891,0.5669999718666077,0.5690000057220459,0.5669999718666077,0.5640000104904175,0.5680000185966492,0.5630000233650208,0.5569999814033508,0.5569999814033508,0.5590000152587891,0.5659999847412109,0.5640000104904175,0.5699999928474426,0.5669999718666077,0.5709999799728394,0.5680000185966492,0.5680000185966492,0.5640000104904175,0.5690000057220459,0.5690000057220459,0.5649999976158142,0.5690000057220459,0.574999988079071,0.574999988079071,0.5720000267028809,0.5759999752044678,0.5649999976158142,0.5720000267028809,0.5690000057220459,0.5699999928474426,0.5630000233650208],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.3019999861717224,0.3059999942779541,0.335999995470047,0.3610000014305115,0.3819999992847442,0.4009999930858612,0.4020000100135803,0.4250000119209289,0.4309999942779541,0.4469999969005584,0.4519999921321869,0.453000009059906,0.4580000042915344,0.4749999940395355,0.4699999988079071,0.4799999892711639,0.4749999940395355,0.4769999980926513,0.481000006198883,0.4839999973773956,0.4959999918937683,0.5040000081062317,0.4970000088214874,0.4979999959468841,0.5070000290870667,0.5049999952316284,0.5109999775886536,0.515999972820282,0.5120000243186951,0.5120000243186951,0.515999972820282,0.5120000243186951,0.5249999761581421,0.5170000195503235,0.5199999809265137,0.5270000100135803,0.5170000195503235,0.5220000147819519,0.5260000228881836,0.5360000133514404,0.5339999794960022,0.5370000004768372,0.5339999794960022,0.5329999923706055,0.531000018119812,0.5329999923706055,0.5400000214576721,0.5429999828338623,0.5389999747276306,0.5419999957084656,0.5429999828338623,0.5360000133514404,0.5299999713897705,0.546999990940094,0.5360000133514404,0.5450000166893005,0.5440000295639038,0.5350000262260437,0.5339999794960022,0.5419999957084656,0.5450000166893005,0.5460000038146973,0.5370000004768372,0.5490000247955322,0.5440000295639038,0.550000011920929,0.5490000247955322,0.5450000166893005,0.5490000247955322,0.5559999942779541,0.5559999942779541,0.5410000085830688,0.5419999957084656,0.5529999732971191,0.5460000038146973,0.5540000200271606,0.5379999876022339,0.5509999990463257,0.5540000200271606,0.5419999957084656,0.546999990940094,0.5479999780654907,0.5460000038146973,0.5460000038146973,0.5519999861717224,0.5600000023841858,0.5540000200271606,0.5509999990463257,0.5609999895095825,0.5619999766349792,0.5590000152587891,0.5559999942779541,0.5580000281333923,0.5640000104904175,0.5649999976158142,0.5590000152587891,0.5550000071525574,0.5630000233650208,0.5630000233650208,0.5609999895095825,0.5559999942779541,0.5609999895095825,0.5630000233650208,0.5680000185966492,0.5630000233650208,0.5690000057220459,0.5609999895095825,0.5590000152587891,0.5640000104904175,0.5690000057220459,0.5640000104904175,0.5630000233650208,0.574999988079071,0.5630000233650208,0.5619999766349792,0.5690000057220459,0.5770000219345093,0.5690000057220459,0.5609999895095825,0.5649999976158142,0.5680000185966492,0.5590000152587891,0.5600000023841858,0.5619999766349792,0.5799999833106995,0.5619999766349792,0.5699999928474426,0.5709999799728394,0.5669999718666077,0.5680000185966492,0.5609999895095825,0.5649999976158142,0.5680000185966492,0.5730000138282776,0.5720000267028809,0.5709999799728394,0.5770000219345093,0.574999988079071,0.5730000138282776,0.5690000057220459,0.5740000009536743,0.578000009059906,0.574999988079071,0.5820000171661377,0.5730000138282776,0.5740000009536743,0.574999988079071,0.5770000219345093,0.5789999961853027,0.5759999752044678,0.5720000267028809,0.5770000219345093,0.5759999752044678,0.5789999961853027,0.5789999961853027,0.5730000138282776,0.5789999961853027,0.5759999752044678,0.5690000057220459,0.5849999785423279,0.5759999752044678,0.5699999928474426,0.5789999961853027,0.5820000171661377,0.5730000138282776,0.5730000138282776,0.5789999961853027],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.2800000011920929,0.3219999969005584,0.3310000002384186,0.3659999966621399,0.3869999945163727,0.3869999945163727,0.3970000147819519,0.4129999876022339,0.4169999957084656,0.4280000030994415,0.4269999861717224,0.4280000030994415,0.4469999969005584,0.4519999921321869,0.453000009059906,0.4480000138282776,0.4589999914169311,0.4629999995231628,0.4690000116825104,0.4729999899864197,0.4690000116825104,0.4720000028610229,0.4589999914169311,0.4839999973773956,0.4769999980926513,0.4860000014305115,0.4860000014305115,0.4869999885559082,0.488999992609024,0.4990000128746032,0.4970000088214874,0.4860000014305115,0.4939999878406524,0.5139999985694885,0.4880000054836273,0.4959999918937683,0.5059999823570251,0.503000020980835,0.503000020980835,0.5040000081062317,0.5009999871253967,0.5139999985694885,0.5080000162124634,0.5120000243186951,0.5080000162124634,0.5019999742507935,0.5220000147819519,0.5170000195503235,0.5170000195503235,0.5149999856948853,0.4990000128746032,0.5139999985694885,0.5139999985694885,0.5139999985694885,0.5170000195503235,0.5149999856948853,0.5189999938011169,0.5080000162124634,0.5199999809265137,0.5170000195503235,0.5249999761581421,0.5180000066757202,0.5299999713897705,0.5210000276565552,0.5260000228881836,0.5270000100135803,0.527999997138977,0.5329999923706055,0.5270000100135803,0.5350000262260437,0.5329999923706055,0.527999997138977,0.527999997138977,0.5410000085830688,0.5350000262260437,0.5210000276565552,0.5270000100135803,0.5299999713897705,0.5329999923706055,0.5400000214576721,0.5389999747276306,0.5339999794960022,0.5339999794960022,0.5379999876022339,0.5370000004768372,0.5379999876022339,0.5389999747276306,0.5389999747276306,0.5440000295639038,0.5440000295639038,0.5410000085830688,0.5360000133514404,0.5460000038146973,0.5339999794960022,0.5460000038146973,0.5450000166893005,0.5479999780654907,0.546999990940094,0.5440000295639038,0.5479999780654907,0.546999990940094,0.5540000200271606,0.5490000247955322,0.5490000247955322,0.5450000166893005,0.5529999732971191,0.5450000166893005,0.550000011920929,0.5559999942779541,0.5519999861717224,0.550000011920929,0.5460000038146973,0.550000011920929,0.5550000071525574,0.5479999780654907,0.5550000071525574,0.5540000200271606,0.5529999732971191,0.5540000200271606,0.5519999861717224,0.5580000281333923,0.5559999942779541,0.5580000281333923,0.550000011920929,0.5569999814033508,0.5609999895095825,0.5569999814033508,0.5600000023841858,0.550000011920929,0.5519999861717224,0.5569999814033508,0.5720000267028809,0.5600000023841858,0.5609999895095825,0.5690000057220459,0.5590000152587891,0.5669999718666077,0.5630000233650208,0.5619999766349792,0.5690000057220459,0.5709999799728394,0.5609999895095825,0.5709999799728394,0.5699999928474426,0.5680000185966492,0.5580000281333923,0.5680000185966492,0.5659999847412109,0.5690000057220459,0.5659999847412109,0.5619999766349792,0.5619999766349792,0.5649999976158142,0.5730000138282776,0.5669999718666077,0.5649999976158142,0.5690000057220459,0.5669999718666077,0.5649999976158142,0.5680000185966492,0.5699999928474426,0.5680000185966492,0.5640000104904175,0.5649999976158142,0.5640000104904175,0.5669999718666077,0.5590000152587891],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.2750000059604645,0.3269999921321869,0.3470000028610229,0.3549999892711639,0.3729999959468841,0.3740000128746032,0.4090000092983246,0.4189999997615814,0.4250000119209289,0.4359999895095825,0.4399999976158142,0.4560000002384186,0.4550000131130218,0.4620000123977661,0.4519999921321869,0.4620000123977661,0.4729999899864197,0.4699999988079071,0.4639999866485595,0.4740000069141388,0.4790000021457672,0.481000006198883,0.4749999940395355,0.4869999885559082,0.4930000007152557,0.4930000007152557,0.4909999966621399,0.4939999878406524,0.4970000088214874,0.4970000088214874,0.5009999871253967,0.5070000290870667,0.5139999985694885,0.4979999959468841,0.5109999775886536,0.5059999823570251,0.5,0.5019999742507935,0.5139999985694885,0.5180000066757202,0.5270000100135803,0.5180000066757202,0.5080000162124634,0.515999972820282,0.5260000228881836,0.5199999809265137,0.5329999923706055,0.5170000195503235,0.5220000147819519,0.5329999923706055,0.5249999761581421,0.5249999761581421,0.5270000100135803,0.5320000052452087,0.5199999809265137,0.5270000100135803,0.5329999923706055,0.5270000100135803,0.5299999713897705,0.5339999794960022,0.5379999876022339,0.5350000262260437,0.5270000100135803,0.5400000214576721,0.5389999747276306,0.5479999780654907,0.5450000166893005,0.5490000247955322,0.5429999828338623,0.5360000133514404,0.5450000166893005,0.5360000133514404,0.5429999828338623,0.5419999957084656,0.5429999828338623,0.5509999990463257,0.5479999780654907,0.5400000214576721,0.5490000247955322,0.5379999876022339,0.5490000247955322,0.5490000247955322,0.5529999732971191,0.5410000085830688,0.5429999828338623,0.546999990940094,0.5490000247955322,0.5490000247955322,0.5490000247955322,0.546999990940094,0.5550000071525574,0.5479999780654907,0.5559999942779541,0.5550000071525574,0.5529999732971191,0.5509999990463257,0.5649999976158142,0.5559999942779541,0.5600000023841858,0.5600000023841858,0.5609999895095825,0.5640000104904175,0.5609999895095825,0.5640000104904175,0.5559999942779541,0.5619999766349792,0.5709999799728394,0.5600000023841858,0.5630000233650208,0.5600000023841858,0.5630000233650208,0.5630000233650208,0.5559999942779541,0.5590000152587891,0.5609999895095825,0.5690000057220459,0.5569999814033508,0.5690000057220459,0.5669999718666077,0.5690000057220459,0.5709999799728394,0.5730000138282776,0.5699999928474426,0.5709999799728394,0.5680000185966492,0.5699999928474426,0.574999988079071,0.5649999976158142,0.574999988079071,0.5730000138282776,0.5720000267028809,0.5699999928474426,0.5709999799728394,0.5720000267028809,0.5720000267028809,0.5759999752044678,0.578000009059906,0.5759999752044678,0.5659999847412109,0.5709999799728394,0.574999988079071,0.574999988079071,0.5680000185966492,0.5669999718666077,0.5640000104904175,0.578000009059906,0.5809999704360962,0.5709999799728394,0.5699999928474426,0.578000009059906,0.5740000009536743,0.574999988079071,0.5759999752044678,0.574999988079071,0.5799999833106995,0.578000009059906,0.5809999704360962,0.5799999833106995,0.5740000009536743,0.574999988079071,0.5820000171661377,0.5759999752044678,0.5809999704360962,0.5820000171661377,0.574999988079071,0.574999988079071,0.5820000171661377],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.257999986410141,0.3009999990463257,0.3219999969005584,0.3479999899864197,0.3600000143051147,0.4000000059604645,0.3930000066757202,0.4110000133514404,0.4339999854564667,0.4390000104904175,0.4480000138282776,0.449999988079071,0.4629999995231628,0.4510000050067901,0.4629999995231628,0.4519999921321869,0.4679999947547912,0.4749999940395355,0.4799999892711639,0.4979999959468841,0.4860000014305115,0.488999992609024,0.4850000143051147,0.4939999878406524,0.4909999966621399,0.4979999959468841,0.4970000088214874,0.5040000081062317,0.503000020980835,0.5059999823570251,0.5059999823570251,0.5049999952316284,0.5090000033378601,0.503000020980835,0.5040000081062317,0.5149999856948853,0.5109999775886536,0.5019999742507935,0.5080000162124634,0.515999972820282,0.5170000195503235,0.5170000195503235,0.5210000276565552,0.5130000114440918,0.5249999761581421,0.527999997138977,0.5199999809265137,0.5239999890327454,0.515999972820282,0.5199999809265137,0.5230000019073486,0.5299999713897705,0.5329999923706055,0.5189999938011169,0.5350000262260437,0.5339999794960022,0.5260000228881836,0.531000018119812,0.5320000052452087,0.527999997138977,0.5350000262260437,0.5329999923706055,0.5429999828338623,0.5410000085830688,0.5429999828338623,0.5400000214576721,0.5339999794960022,0.5460000038146973,0.5450000166893005,0.5419999957084656,0.5509999990463257,0.5440000295639038,0.5440000295639038,0.5509999990463257,0.5529999732971191,0.5580000281333923,0.5519999861717224,0.5600000023841858,0.5519999861717224,0.5600000023841858,0.5550000071525574,0.5680000185966492,0.5569999814033508,0.5619999766349792,0.550000011920929,0.5529999732971191,0.5600000023841858,0.550000011920929,0.5540000200271606,0.5540000200271606,0.5580000281333923,0.5559999942779541,0.5509999990463257,0.5590000152587891,0.5590000152587891,0.5600000023841858,0.5609999895095825,0.5699999928474426,0.5590000152587891,0.5640000104904175,0.5609999895095825,0.5680000185966492,0.5600000023841858,0.5600000023841858,0.5609999895095825,0.5649999976158142,0.5680000185966492,0.5590000152587891,0.5690000057220459,0.5690000057220459,0.5740000009536743,0.5649999976158142,0.5740000009536743,0.5699999928474426,0.5709999799728394,0.5709999799728394,0.5699999928474426,0.5740000009536743,0.5669999718666077,0.5699999928474426,0.5699999928474426,0.5820000171661377,0.5740000009536743,0.574999988079071,0.5709999799728394,0.5690000057220459,0.5759999752044678,0.5770000219345093,0.5680000185966492,0.5740000009536743,0.5759999752044678,0.5709999799728394,0.5789999961853027,0.5789999961853027,0.5759999752044678,0.5730000138282776,0.5730000138282776,0.5799999833106995,0.5820000171661377,0.5699999928474426,0.574999988079071,0.5740000009536743,0.5770000219345093,0.5759999752044678,0.5789999961853027,0.5759999752044678,0.578000009059906,0.578000009059906,0.5809999704360962,0.5820000171661377,0.5770000219345093,0.574999988079071,0.574999988079071,0.5820000171661377,0.5770000219345093,0.5699999928474426,0.5860000252723694,0.5799999833106995,0.5770000219345093,0.5820000171661377,0.5799999833106995,0.5789999961853027,0.574999988079071,0.578000009059906,0.5809999704360962,0.5830000042915344,0.5789999961853027,0.5770000219345093],"label":"FineWeb URL dedup"}},"openbookqa/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1199999973177909,0.1539999991655349,0.1519999951124191,0.1679999977350235,0.1739999949932098,0.1759999990463256,0.19200000166893,0.1700000017881393,0.181999996304512,0.1720000058412552,0.1899999976158142,0.1780000030994415,0.1780000030994415,0.1840000003576278,0.1959999948740005,0.1899999976158142,0.1759999990463256,0.1959999948740005,0.202000007033348,0.1879999935626983,0.2060000002384185,0.2060000002384185,0.1959999948740005,0.2039999961853027,0.209999993443489,0.202000007033348,0.1940000057220459,0.2000000029802322,0.19200000166893,0.2039999961853027,0.209999993443489,0.2179999947547912,0.2179999947547912,0.2160000056028366,0.2300000041723251,0.2220000028610229,0.2220000028610229,0.2119999974966049,0.2160000056028366,0.209999993443489,0.2240000069141388,0.2440000027418136,0.2280000001192093,0.2280000001192093,0.2399999946355819,0.2259999960660934,0.2300000041723251,0.2360000014305114,0.2259999960660934,0.2179999947547912,0.2300000041723251,0.2199999988079071,0.2140000015497207,0.2319999933242797,0.2280000001192093,0.2080000042915344,0.2220000028610229,0.2179999947547912,0.2220000028610229,0.2280000001192093,0.2119999974966049,0.2399999946355819,0.2259999960660934,0.2339999973773956,0.209999993443489,0.2080000042915344,0.2160000056028366,0.2259999960660934,0.2140000015497207,0.2199999988079071,0.2319999933242797,0.2339999973773956,0.2259999960660934,0.2140000015497207,0.2199999988079071,0.2259999960660934,0.2220000028610229,0.2160000056028366,0.2179999947547912,0.2199999988079071,0.2259999960660934,0.2179999947547912,0.2280000001192093,0.202000007033348,0.2039999961853027,0.2000000029802322,0.2220000028610229,0.2220000028610229,0.2199999988079071,0.2199999988079071,0.2280000001192093,0.2360000014305114,0.2140000015497207,0.2240000069141388,0.2220000028610229,0.2119999974966049,0.2179999947547912,0.2240000069141388,0.2179999947547912,0.2300000041723251,0.2119999974966049,0.2199999988079071,0.2039999961853027,0.2280000001192093,0.2240000069141388,0.2199999988079071,0.2199999988079071,0.2140000015497207,0.2259999960660934,0.2220000028610229,0.2240000069141388,0.209999993443489,0.2319999933242797,0.2280000001192093,0.2360000014305114,0.2179999947547912,0.2259999960660934,0.2280000001192093,0.2300000041723251,0.2339999973773956,0.2280000001192093,0.2199999988079071,0.2360000014305114,0.2259999960660934,0.2319999933242797,0.2179999947547912,0.2300000041723251,0.2280000001192093,0.2280000001192093,0.2199999988079071,0.2280000001192093,0.2240000069141388,0.2460000067949295,0.2380000054836273,0.2220000028610229,0.2339999973773956,0.2319999933242797,0.2199999988079071,0.2280000001192093,0.2339999973773956,0.2280000001192093,0.2280000001192093,0.2319999933242797,0.2339999973773956,0.2360000014305114,0.2280000001192093,0.2339999973773956,0.2399999946355819,0.2339999973773956,0.2380000054836273,0.2339999973773956,0.2280000001192093,0.2259999960660934,0.2339999973773956,0.2319999933242797,0.2399999946355819,0.2440000027418136,0.2360000014305114,0.2259999960660934,0.2220000028610229,0.2360000014305114,0.2319999933242797,0.2360000014305114,0.2419999986886978,0.2360000014305114,0.2419999986886978,0.2300000041723251],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1400000005960464,0.1340000033378601,0.1439999938011169,0.1599999964237213,0.1580000072717666,0.1539999991655349,0.1580000072717666,0.1840000003576278,0.1679999977350235,0.1759999990463256,0.1860000044107437,0.1679999977350235,0.1840000003576278,0.1700000017881393,0.164000004529953,0.1800000071525573,0.1599999964237213,0.1759999990463256,0.1720000058412552,0.1879999935626983,0.19200000166893,0.1860000044107437,0.1739999949932098,0.1780000030994415,0.19200000166893,0.1800000071525573,0.1679999977350235,0.1940000057220459,0.1800000071525573,0.1860000044107437,0.1759999990463256,0.19200000166893,0.2000000029802322,0.19200000166893,0.2060000002384185,0.19200000166893,0.1940000057220459,0.2000000029802322,0.2060000002384185,0.19200000166893,0.202000007033348,0.1979999989271164,0.2000000029802322,0.2060000002384185,0.209999993443489,0.2039999961853027,0.209999993443489,0.2140000015497207,0.1940000057220459,0.1959999948740005,0.209999993443489,0.202000007033348,0.2119999974966049,0.2080000042915344,0.2140000015497207,0.2080000042915344,0.2000000029802322,0.1959999948740005,0.2000000029802322,0.2039999961853027,0.2080000042915344,0.2039999961853027,0.1879999935626983,0.202000007033348,0.2000000029802322,0.2240000069141388,0.202000007033348,0.2060000002384185,0.2119999974966049,0.2199999988079071,0.2119999974966049,0.2140000015497207,0.2119999974966049,0.2140000015497207,0.2060000002384185,0.2039999961853027,0.2140000015497207,0.2160000056028366,0.2080000042915344,0.2080000042915344,0.2179999947547912,0.2160000056028366,0.209999993443489,0.1940000057220459,0.2039999961853027,0.1940000057220459,0.1879999935626983,0.2039999961853027,0.1899999976158142,0.2039999961853027,0.1959999948740005,0.2039999961853027,0.1940000057220459,0.209999993443489,0.2199999988079071,0.19200000166893,0.1959999948740005,0.1979999989271164,0.209999993443489,0.2039999961853027,0.2060000002384185,0.2119999974966049,0.2179999947547912,0.209999993443489,0.2080000042915344,0.2000000029802322,0.2220000028610229,0.2000000029802322,0.2179999947547912,0.209999993443489,0.2199999988079071,0.1959999948740005,0.2119999974966049,0.209999993443489,0.2080000042915344,0.2140000015497207,0.2140000015497207,0.209999993443489,0.2140000015497207,0.2039999961853027,0.2080000042915344,0.2140000015497207,0.2140000015497207,0.209999993443489,0.2220000028610229,0.2080000042915344,0.2039999961853027,0.2060000002384185,0.2060000002384185,0.2119999974966049,0.202000007033348,0.2080000042915344,0.2060000002384185,0.202000007033348,0.2000000029802322,0.1959999948740005,0.2080000042915344,0.2140000015497207,0.202000007033348,0.1940000057220459,0.2039999961853027,0.2060000002384185,0.209999993443489,0.202000007033348,0.2179999947547912,0.2060000002384185,0.1979999989271164,0.1959999948740005,0.1979999989271164,0.2060000002384185,0.2000000029802322,0.2160000056028366,0.2060000002384185,0.2119999974966049,0.2160000056028366,0.2280000001192093,0.209999993443489,0.2179999947547912,0.209999993443489,0.2140000015497207,0.2000000029802322,0.2000000029802322,0.209999993443489,0.2080000042915344,0.2140000015497207,0.2140000015497207,0.202000007033348],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1379999965429306,0.1379999965429306,0.1519999951124191,0.1720000058412552,0.1500000059604644,0.1580000072717666,0.1580000072717666,0.1679999977350235,0.1700000017881393,0.1700000017881393,0.1780000030994415,0.1899999976158142,0.1899999976158142,0.1800000071525573,0.19200000166893,0.1840000003576278,0.202000007033348,0.1899999976158142,0.181999996304512,0.1959999948740005,0.1780000030994415,0.2060000002384185,0.1879999935626983,0.1940000057220459,0.2060000002384185,0.2000000029802322,0.1800000071525573,0.209999993443489,0.1860000044107437,0.1879999935626983,0.2060000002384185,0.1940000057220459,0.2080000042915344,0.1979999989271164,0.1860000044107437,0.202000007033348,0.1959999948740005,0.1979999989271164,0.1979999989271164,0.1879999935626983,0.1959999948740005,0.2060000002384185,0.2039999961853027,0.2000000029802322,0.209999993443489,0.2060000002384185,0.2199999988079071,0.2140000015497207,0.2039999961853027,0.209999993443489,0.2220000028610229,0.2160000056028366,0.209999993443489,0.209999993443489,0.202000007033348,0.2039999961853027,0.2160000056028366,0.2199999988079071,0.2060000002384185,0.2179999947547912,0.2220000028610229,0.2140000015497207,0.202000007033348,0.2140000015497207,0.2199999988079071,0.202000007033348,0.2080000042915344,0.1979999989271164,0.2140000015497207,0.2179999947547912,0.209999993443489,0.2119999974966049,0.2119999974966049,0.2140000015497207,0.2080000042915344,0.209999993443489,0.2140000015497207,0.2119999974966049,0.2160000056028366,0.2119999974966049,0.2060000002384185,0.2240000069141388,0.2039999961853027,0.2280000001192093,0.2140000015497207,0.2119999974966049,0.2060000002384185,0.2199999988079071,0.2160000056028366,0.2179999947547912,0.2179999947547912,0.2140000015497207,0.2119999974966049,0.2080000042915344,0.2060000002384185,0.2220000028610229,0.2199999988079071,0.2160000056028366,0.2160000056028366,0.2259999960660934,0.2300000041723251,0.2319999933242797,0.2240000069141388,0.2240000069141388,0.209999993443489,0.2399999946355819,0.2160000056028366,0.2220000028610229,0.209999993443489,0.2220000028610229,0.2240000069141388,0.2280000001192093,0.2240000069141388,0.2119999974966049,0.2179999947547912,0.2199999988079071,0.2259999960660934,0.2220000028610229,0.2220000028610229,0.2220000028610229,0.2179999947547912,0.2199999988079071,0.2300000041723251,0.2339999973773956,0.2380000054836273,0.2240000069141388,0.2259999960660934,0.2339999973773956,0.2240000069141388,0.2240000069141388,0.2160000056028366,0.2199999988079071,0.2300000041723251,0.2280000001192093,0.2240000069141388,0.2199999988079071,0.2220000028610229,0.2199999988079071,0.2160000056028366,0.2300000041723251,0.2319999933242797,0.2380000054836273,0.2319999933242797,0.2319999933242797,0.2220000028610229,0.2199999988079071,0.2199999988079071,0.2259999960660934,0.2280000001192093,0.2280000001192093,0.2199999988079071,0.2300000041723251,0.2240000069141388,0.2199999988079071,0.2380000054836273,0.2339999973773956,0.2280000001192093,0.2300000041723251,0.2300000041723251,0.2259999960660934,0.2300000041723251,0.2300000041723251,0.2419999986886978,0.2319999933242797,0.2339999973773956,0.2259999960660934,0.2339999973773956],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1340000033378601,0.1439999938011169,0.1539999991655349,0.1780000030994415,0.1720000058412552,0.1720000058412552,0.1860000044107437,0.1759999990463256,0.19200000166893,0.1899999976158142,0.1860000044107437,0.181999996304512,0.1959999948740005,0.1879999935626983,0.1959999948740005,0.1800000071525573,0.1800000071525573,0.1879999935626983,0.1800000071525573,0.1780000030994415,0.1959999948740005,0.19200000166893,0.1860000044107437,0.19200000166893,0.1959999948740005,0.209999993443489,0.1959999948740005,0.2039999961853027,0.1899999976158142,0.1879999935626983,0.1959999948740005,0.2000000029802322,0.1979999989271164,0.2179999947547912,0.2179999947547912,0.2039999961853027,0.2080000042915344,0.2039999961853027,0.1879999935626983,0.1959999948740005,0.1979999989271164,0.1940000057220459,0.1959999948740005,0.202000007033348,0.202000007033348,0.2039999961853027,0.2080000042915344,0.2160000056028366,0.209999993443489,0.202000007033348,0.2080000042915344,0.2039999961853027,0.1959999948740005,0.202000007033348,0.2060000002384185,0.2000000029802322,0.2119999974966049,0.1959999948740005,0.209999993443489,0.2179999947547912,0.2000000029802322,0.2080000042915344,0.2000000029802322,0.2160000056028366,0.2080000042915344,0.1860000044107437,0.2080000042915344,0.2119999974966049,0.2080000042915344,0.2319999933242797,0.2119999974966049,0.2179999947547912,0.2300000041723251,0.2319999933242797,0.2039999961853027,0.2080000042915344,0.2220000028610229,0.2199999988079071,0.209999993443489,0.2080000042915344,0.2140000015497207,0.2039999961853027,0.2220000028610229,0.2080000042915344,0.2119999974966049,0.2259999960660934,0.2259999960660934,0.2160000056028366,0.2140000015497207,0.2080000042915344,0.2259999960660934,0.2319999933242797,0.2140000015497207,0.2199999988079071,0.2199999988079071,0.202000007033348,0.2080000042915344,0.2140000015497207,0.209999993443489,0.2160000056028366,0.2080000042915344,0.2160000056028366,0.2220000028610229,0.2119999974966049,0.2080000042915344,0.2080000042915344,0.2179999947547912,0.2039999961853027,0.2240000069141388,0.2199999988079071,0.2080000042915344,0.2140000015497207,0.2140000015497207,0.2199999988079071,0.2080000042915344,0.2160000056028366,0.2119999974966049,0.2080000042915344,0.2080000042915344,0.2160000056028366,0.2119999974966049,0.2339999973773956,0.2179999947547912,0.2179999947547912,0.2199999988079071,0.2440000027418136,0.2039999961853027,0.2140000015497207,0.2259999960660934,0.2199999988079071,0.2179999947547912,0.2140000015497207,0.2259999960660934,0.2240000069141388,0.2220000028610229,0.2160000056028366,0.2160000056028366,0.2240000069141388,0.2240000069141388,0.2179999947547912,0.2259999960660934,0.2220000028610229,0.2240000069141388,0.2240000069141388,0.2259999960660934,0.2300000041723251,0.2339999973773956,0.2399999946355819,0.2300000041723251,0.2179999947547912,0.2240000069141388,0.2300000041723251,0.2460000067949295,0.2319999933242797,0.2339999973773956,0.2259999960660934,0.2240000069141388,0.2300000041723251,0.2380000054836273,0.2300000041723251,0.2220000028610229,0.2319999933242797,0.2360000014305114,0.2300000041723251,0.2380000054836273,0.2319999933242797,0.2300000041723251],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1400000005960464,0.1340000033378601,0.1599999964237213,0.164000004529953,0.1759999990463256,0.181999996304512,0.1679999977350235,0.1679999977350235,0.1700000017881393,0.1720000058412552,0.181999996304512,0.1860000044107437,0.1840000003576278,0.1959999948740005,0.1899999976158142,0.1979999989271164,0.1959999948740005,0.1959999948740005,0.2000000029802322,0.2119999974966049,0.1879999935626983,0.1899999976158142,0.2060000002384185,0.19200000166893,0.181999996304512,0.2060000002384185,0.2060000002384185,0.1959999948740005,0.2060000002384185,0.209999993443489,0.202000007033348,0.2140000015497207,0.2179999947547912,0.2179999947547912,0.2000000029802322,0.1959999948740005,0.2039999961853027,0.2000000029802322,0.2000000029802322,0.2080000042915344,0.1979999989271164,0.2080000042915344,0.2039999961853027,0.2000000029802322,0.19200000166893,0.209999993443489,0.2000000029802322,0.2140000015497207,0.2060000002384185,0.2000000029802322,0.2140000015497207,0.2000000029802322,0.2140000015497207,0.2119999974966049,0.2140000015497207,0.2039999961853027,0.209999993443489,0.2119999974966049,0.209999993443489,0.1940000057220459,0.2140000015497207,0.2060000002384185,0.209999993443489,0.1979999989271164,0.2060000002384185,0.2199999988079071,0.2140000015497207,0.2160000056028366,0.209999993443489,0.209999993443489,0.2140000015497207,0.2199999988079071,0.2199999988079071,0.2039999961853027,0.2220000028610229,0.2060000002384185,0.2179999947547912,0.2080000042915344,0.2080000042915344,0.2060000002384185,0.2280000001192093,0.2140000015497207,0.2160000056028366,0.2039999961853027,0.2160000056028366,0.2179999947547912,0.2140000015497207,0.2259999960660934,0.2140000015497207,0.2220000028610229,0.2160000056028366,0.2140000015497207,0.2300000041723251,0.2220000028610229,0.2179999947547912,0.2140000015497207,0.2300000041723251,0.2220000028610229,0.2119999974966049,0.2140000015497207,0.2319999933242797,0.2199999988079071,0.2319999933242797,0.2259999960660934,0.2319999933242797,0.2240000069141388,0.2160000056028366,0.2220000028610229,0.2240000069141388,0.209999993443489,0.2220000028610229,0.2300000041723251,0.2280000001192093,0.2300000041723251,0.2220000028610229,0.2179999947547912,0.2259999960660934,0.2319999933242797,0.2259999960660934,0.2280000001192093,0.2339999973773956,0.2339999973773956,0.2240000069141388,0.2460000067949295,0.2419999986886978,0.2280000001192093,0.2300000041723251,0.2339999973773956,0.2319999933242797,0.2319999933242797,0.2319999933242797,0.2399999946355819,0.2339999973773956,0.2380000054836273,0.2380000054836273,0.2419999986886978,0.2339999973773956,0.2399999946355819,0.2300000041723251,0.2360000014305114,0.2440000027418136,0.2360000014305114,0.2399999946355819,0.2399999946355819,0.2339999973773956,0.2339999973773956,0.2360000014305114,0.2360000014305114,0.2399999946355819,0.2360000014305114,0.2300000041723251,0.2460000067949295,0.2440000027418136,0.2300000041723251,0.2360000014305114,0.2280000001192093,0.2280000001192093,0.2259999960660934,0.2160000056028366,0.2419999986886978,0.2460000067949295,0.2319999933242797,0.2419999986886978,0.2380000054836273,0.2380000054836273,0.2300000041723251,0.2360000014305114],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1199999973177909,0.1439999938011169,0.1500000059604644,0.1560000032186508,0.1599999964237213,0.1620000004768371,0.1659999936819076,0.181999996304512,0.1979999989271164,0.181999996304512,0.2000000029802322,0.181999996304512,0.1759999990463256,0.1940000057220459,0.202000007033348,0.1800000071525573,0.1940000057220459,0.1840000003576278,0.1940000057220459,0.1940000057220459,0.2119999974966049,0.1940000057220459,0.181999996304512,0.1879999935626983,0.1860000044107437,0.1840000003576278,0.1959999948740005,0.202000007033348,0.1959999948740005,0.209999993443489,0.1940000057220459,0.1979999989271164,0.2060000002384185,0.2039999961853027,0.2039999961853027,0.2160000056028366,0.2199999988079071,0.2000000029802322,0.19200000166893,0.1899999976158142,0.2119999974966049,0.1959999948740005,0.2119999974966049,0.2080000042915344,0.19200000166893,0.2000000029802322,0.2119999974966049,0.2000000029802322,0.2119999974966049,0.2140000015497207,0.2060000002384185,0.19200000166893,0.1940000057220459,0.209999993443489,0.19200000166893,0.209999993443489,0.2160000056028366,0.2060000002384185,0.2160000056028366,0.2220000028610229,0.2080000042915344,0.2060000002384185,0.2419999986886978,0.2060000002384185,0.2179999947547912,0.2160000056028366,0.2080000042915344,0.2240000069141388,0.2080000042915344,0.2160000056028366,0.2199999988079071,0.2140000015497207,0.202000007033348,0.209999993443489,0.209999993443489,0.2160000056028366,0.2060000002384185,0.2339999973773956,0.2160000056028366,0.2339999973773956,0.2319999933242797,0.2259999960660934,0.209999993443489,0.2119999974966049,0.2259999960660934,0.2280000001192093,0.2280000001192093,0.2300000041723251,0.2140000015497207,0.2220000028610229,0.2220000028610229,0.2220000028610229,0.2339999973773956,0.2360000014305114,0.2300000041723251,0.2380000054836273,0.2360000014305114,0.2280000001192093,0.2419999986886978,0.2460000067949295,0.2360000014305114,0.2419999986886978,0.2440000027418136,0.2319999933242797,0.2399999946355819,0.2360000014305114,0.2319999933242797,0.2419999986886978,0.2220000028610229,0.2339999973773956,0.2419999986886978,0.2220000028610229,0.2220000028610229,0.2160000056028366,0.2319999933242797,0.2259999960660934,0.2300000041723251,0.2360000014305114,0.2280000001192093,0.2240000069141388,0.2300000041723251,0.2220000028610229,0.2280000001192093,0.2339999973773956,0.2240000069141388,0.2179999947547912,0.2300000041723251,0.2220000028610229,0.2259999960660934,0.2259999960660934,0.2280000001192093,0.2220000028610229,0.2160000056028366,0.2259999960660934,0.2259999960660934,0.2119999974966049,0.2259999960660934,0.2300000041723251,0.2259999960660934,0.2280000001192093,0.2360000014305114,0.2179999947547912,0.2259999960660934,0.2259999960660934,0.2380000054836273,0.2319999933242797,0.2280000001192093,0.2380000054836273,0.2240000069141388,0.2319999933242797,0.2300000041723251,0.2220000028610229,0.2280000001192093,0.2300000041723251,0.2259999960660934,0.2240000069141388,0.2300000041723251,0.2339999973773956,0.2240000069141388,0.2220000028610229,0.2300000041723251,0.2199999988079071,0.2259999960660934,0.2300000041723251,0.2339999973773956,0.2339999973773956,0.2240000069141388],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1199999973177909,0.1299999952316284,0.1500000059604644,0.1480000019073486,0.1620000004768371,0.1659999936819076,0.1759999990463256,0.1659999936819076,0.1620000004768371,0.1620000004768371,0.1800000071525573,0.181999996304512,0.181999996304512,0.1800000071525573,0.1879999935626983,0.1879999935626983,0.1759999990463256,0.1959999948740005,0.181999996304512,0.1879999935626983,0.1940000057220459,0.1940000057220459,0.1899999976158142,0.1879999935626983,0.1860000044107437,0.2060000002384185,0.1979999989271164,0.202000007033348,0.1979999989271164,0.1899999976158142,0.1959999948740005,0.181999996304512,0.1940000057220459,0.2060000002384185,0.1979999989271164,0.2160000056028366,0.2039999961853027,0.2039999961853027,0.2119999974966049,0.1940000057220459,0.2179999947547912,0.2080000042915344,0.2259999960660934,0.2039999961853027,0.209999993443489,0.1899999976158142,0.2119999974966049,0.2039999961853027,0.1879999935626983,0.2140000015497207,0.2039999961853027,0.202000007033348,0.2000000029802322,0.1979999989271164,0.2000000029802322,0.19200000166893,0.19200000166893,0.2080000042915344,0.209999993443489,0.2000000029802322,0.1959999948740005,0.2140000015497207,0.202000007033348,0.209999993443489,0.1899999976158142,0.2119999974966049,0.2060000002384185,0.2000000029802322,0.2160000056028366,0.2259999960660934,0.2080000042915344,0.2000000029802322,0.202000007033348,0.2119999974966049,0.2000000029802322,0.2080000042915344,0.202000007033348,0.2140000015497207,0.2140000015497207,0.1959999948740005,0.2160000056028366,0.2160000056028366,0.2280000001192093,0.2140000015497207,0.2240000069141388,0.2140000015497207,0.2119999974966049,0.2140000015497207,0.1979999989271164,0.209999993443489,0.2160000056028366,0.2060000002384185,0.2119999974966049,0.2080000042915344,0.202000007033348,0.2039999961853027,0.1979999989271164,0.2080000042915344,0.2179999947547912,0.2000000029802322,0.2060000002384185,0.2140000015497207,0.202000007033348,0.2039999961853027,0.2039999961853027,0.202000007033348,0.209999993443489,0.2140000015497207,0.2140000015497207,0.2080000042915344,0.2199999988079071,0.2000000029802322,0.2080000042915344,0.2160000056028366,0.2140000015497207,0.2160000056028366,0.2220000028610229,0.2140000015497207,0.2140000015497207,0.209999993443489,0.2199999988079071,0.2160000056028366,0.2140000015497207,0.2160000056028366,0.2179999947547912,0.2160000056028366,0.2140000015497207,0.2140000015497207,0.2160000056028366,0.2160000056028366,0.2160000056028366,0.209999993443489,0.2160000056028366,0.2280000001192093,0.209999993443489,0.2240000069141388,0.2220000028610229,0.2160000056028366,0.2179999947547912,0.2179999947547912,0.2199999988079071,0.2199999988079071,0.2179999947547912,0.2199999988079071,0.2220000028610229,0.2220000028610229,0.2220000028610229,0.2259999960660934,0.2280000001192093,0.2259999960660934,0.2039999961853027,0.2300000041723251,0.2240000069141388,0.2199999988079071,0.2280000001192093,0.2179999947547912,0.2259999960660934,0.2199999988079071,0.2300000041723251,0.2199999988079071,0.2259999960660934,0.2220000028610229,0.2259999960660934,0.2300000041723251,0.2199999988079071,0.2319999933242797,0.2300000041723251],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.1659999936819076,0.1360000073909759,0.1260000020265579,0.1500000059604644,0.1599999964237213,0.1620000004768371,0.1620000004768371,0.1679999977350235,0.1679999977350235,0.1840000003576278,0.1840000003576278,0.1899999976158142,0.1899999976158142,0.1879999935626983,0.1979999989271164,0.209999993443489,0.1800000071525573,0.1879999935626983,0.202000007033348,0.2060000002384185,0.2039999961853027,0.1860000044107437,0.1879999935626983,0.1899999976158142,0.2039999961853027,0.2060000002384185,0.2000000029802322,0.2080000042915344,0.209999993443489,0.2119999974966049,0.209999993443489,0.2160000056028366,0.2060000002384185,0.2060000002384185,0.2140000015497207,0.2140000015497207,0.2119999974966049,0.2179999947547912,0.2179999947547912,0.209999993443489,0.202000007033348,0.2140000015497207,0.2060000002384185,0.2179999947547912,0.1979999989271164,0.2280000001192093,0.2080000042915344,0.2140000015497207,0.1940000057220459,0.2000000029802322,0.2140000015497207,0.2199999988079071,0.2199999988079071,0.209999993443489,0.2179999947547912,0.2240000069141388,0.2119999974966049,0.2039999961853027,0.2140000015497207,0.2160000056028366,0.2119999974966049,0.2119999974966049,0.209999993443489,0.202000007033348,0.2240000069141388,0.2160000056028366,0.2140000015497207,0.2000000029802322,0.202000007033348,0.2000000029802322,0.2199999988079071,0.2119999974966049,0.2199999988079071,0.2080000042915344,0.2179999947547912,0.1959999948740005,0.2039999961853027,0.2119999974966049,0.2199999988079071,0.209999993443489,0.2140000015497207,0.2119999974966049,0.2160000056028366,0.2240000069141388,0.209999993443489,0.2060000002384185,0.2179999947547912,0.209999993443489,0.2160000056028366,0.2240000069141388,0.2259999960660934,0.2319999933242797,0.2259999960660934,0.2240000069141388,0.2179999947547912,0.2199999988079071,0.2300000041723251,0.2160000056028366,0.2119999974966049,0.209999993443489,0.2140000015497207,0.209999993443489,0.2240000069141388,0.2119999974966049,0.2259999960660934,0.2199999988079071,0.2199999988079071,0.2339999973773956,0.2339999973773956,0.2319999933242797,0.2259999960660934,0.2339999973773956,0.2220000028610229,0.2199999988079071,0.2259999960660934,0.2160000056028366,0.2199999988079071,0.2259999960660934,0.2300000041723251,0.2199999988079071,0.2280000001192093,0.2300000041723251,0.2259999960660934,0.2179999947547912,0.2240000069141388,0.2240000069141388,0.2259999960660934,0.209999993443489,0.2179999947547912,0.2240000069141388,0.2119999974966049,0.2319999933242797,0.2119999974966049,0.2319999933242797,0.2240000069141388,0.2179999947547912,0.2220000028610229,0.2259999960660934,0.2179999947547912,0.2220000028610229,0.2240000069141388,0.2119999974966049,0.2300000041723251,0.2160000056028366,0.2300000041723251,0.2319999933242797,0.2220000028610229,0.2339999973773956,0.2319999933242797,0.2280000001192093,0.2319999933242797,0.2360000014305114,0.2220000028610229,0.2380000054836273,0.2319999933242797,0.2300000041723251,0.2319999933242797,0.2419999986886978,0.2259999960660934,0.2360000014305114,0.2300000041723251,0.2339999973773956,0.2319999933242797,0.2259999960660934,0.2280000001192093,0.2300000041723251,0.2339999973773956,0.2440000027418136],"label":"FineWeb URL dedup"}},"openbookqa/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2560000121593475,0.2840000092983246,0.3059999942779541,0.3059999942779541,0.2980000078678131,0.3240000009536743,0.3100000023841858,0.3000000119209289,0.3160000145435333,0.3140000104904175,0.3260000050067901,0.3199999928474426,0.2980000078678131,0.3179999887943268,0.3319999873638153,0.3019999861717224,0.2939999997615814,0.3319999873638153,0.3319999873638153,0.3219999969005584,0.3379999995231628,0.3379999995231628,0.3339999914169311,0.3240000009536743,0.3479999899864197,0.3300000131130218,0.3240000009536743,0.3300000131130218,0.3400000035762787,0.3459999859333038,0.3319999873638153,0.3379999995231628,0.356000006198883,0.3339999914169311,0.3459999859333038,0.3440000116825104,0.3519999980926513,0.3479999899864197,0.3339999914169311,0.3400000035762787,0.3479999899864197,0.3379999995231628,0.3479999899864197,0.3499999940395355,0.3400000035762787,0.3499999940395355,0.3420000076293945,0.3659999966621399,0.3400000035762787,0.3459999859333038,0.3499999940395355,0.356000006198883,0.3400000035762787,0.356000006198883,0.3339999914169311,0.3339999914169311,0.3479999899864197,0.3420000076293945,0.3580000102519989,0.3339999914169311,0.3440000116825104,0.3400000035762787,0.3499999940395355,0.3540000021457672,0.3479999899864197,0.3499999940395355,0.3420000076293945,0.3379999995231628,0.335999995470047,0.356000006198883,0.3459999859333038,0.3499999940395355,0.3400000035762787,0.3440000116825104,0.356000006198883,0.3519999980926513,0.3400000035762787,0.3440000116825104,0.356000006198883,0.3400000035762787,0.356000006198883,0.3600000143051147,0.3540000021457672,0.3479999899864197,0.3379999995231628,0.3440000116825104,0.3300000131130218,0.3400000035762787,0.3459999859333038,0.3339999914169311,0.3499999940395355,0.3600000143051147,0.3440000116825104,0.3499999940395355,0.356000006198883,0.3420000076293945,0.3479999899864197,0.3379999995231628,0.3379999995231628,0.3459999859333038,0.356000006198883,0.328000009059906,0.3459999859333038,0.3519999980926513,0.3499999940395355,0.3519999980926513,0.3420000076293945,0.3499999940395355,0.3420000076293945,0.3339999914169311,0.335999995470047,0.3379999995231628,0.3379999995231628,0.3540000021457672,0.356000006198883,0.356000006198883,0.335999995470047,0.363999992609024,0.363999992609024,0.3499999940395355,0.356000006198883,0.3519999980926513,0.3519999980926513,0.3540000021457672,0.3459999859333038,0.3479999899864197,0.3519999980926513,0.3519999980926513,0.3420000076293945,0.3440000116825104,0.3379999995231628,0.3519999980926513,0.356000006198883,0.3420000076293945,0.3580000102519989,0.3499999940395355,0.3619999885559082,0.3519999980926513,0.3600000143051147,0.3459999859333038,0.3519999980926513,0.3519999980926513,0.3499999940395355,0.3580000102519989,0.356000006198883,0.3580000102519989,0.3600000143051147,0.3440000116825104,0.3600000143051147,0.3440000116825104,0.3479999899864197,0.3479999899864197,0.3580000102519989,0.3600000143051147,0.3580000102519989,0.3540000021457672,0.3519999980926513,0.3459999859333038,0.3459999859333038,0.3540000021457672,0.335999995470047,0.3540000021457672,0.3540000021457672,0.3519999980926513,0.356000006198883,0.3499999940395355,0.356000006198883],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2599999904632568,0.2680000066757202,0.2800000011920929,0.2919999957084656,0.2960000038146972,0.2860000133514404,0.2960000038146972,0.3059999942779541,0.3059999942779541,0.3219999969005584,0.3100000023841858,0.3120000064373016,0.3120000064373016,0.3219999969005584,0.3120000064373016,0.3199999928474426,0.3160000145435333,0.2919999957084656,0.3100000023841858,0.328000009059906,0.3100000023841858,0.3199999928474426,0.3120000064373016,0.328000009059906,0.3160000145435333,0.3240000009536743,0.3160000145435333,0.3319999873638153,0.3160000145435333,0.3179999887943268,0.3240000009536743,0.3219999969005584,0.3100000023841858,0.3339999914169311,0.328000009059906,0.3260000050067901,0.3300000131130218,0.3319999873638153,0.3240000009536743,0.3199999928474426,0.3240000009536743,0.3300000131130218,0.3440000116825104,0.3160000145435333,0.3339999914169311,0.3400000035762787,0.3260000050067901,0.3319999873638153,0.3219999969005584,0.3179999887943268,0.3260000050067901,0.3339999914169311,0.3260000050067901,0.3300000131130218,0.3260000050067901,0.3219999969005584,0.3120000064373016,0.3140000104904175,0.3160000145435333,0.328000009059906,0.3120000064373016,0.3240000009536743,0.3219999969005584,0.3260000050067901,0.3199999928474426,0.3219999969005584,0.3219999969005584,0.3260000050067901,0.3219999969005584,0.3120000064373016,0.3459999859333038,0.328000009059906,0.3199999928474426,0.335999995470047,0.3240000009536743,0.3199999928474426,0.3420000076293945,0.3300000131130218,0.3400000035762787,0.3339999914169311,0.335999995470047,0.3459999859333038,0.3300000131130218,0.328000009059906,0.3379999995231628,0.3300000131130218,0.3140000104904175,0.3219999969005584,0.3219999969005584,0.3420000076293945,0.3319999873638153,0.3199999928474426,0.3300000131130218,0.3140000104904175,0.328000009059906,0.3219999969005584,0.3260000050067901,0.3400000035762787,0.3339999914169311,0.3219999969005584,0.335999995470047,0.3379999995231628,0.3260000050067901,0.3219999969005584,0.3339999914169311,0.3339999914169311,0.328000009059906,0.3219999969005584,0.3339999914169311,0.3260000050067901,0.3300000131130218,0.3240000009536743,0.3219999969005584,0.3240000009536743,0.335999995470047,0.3319999873638153,0.3219999969005584,0.328000009059906,0.3140000104904175,0.3260000050067901,0.3300000131130218,0.3300000131130218,0.3240000009536743,0.3240000009536743,0.328000009059906,0.3179999887943268,0.3140000104904175,0.3179999887943268,0.3199999928474426,0.3160000145435333,0.3199999928474426,0.3179999887943268,0.3199999928474426,0.3160000145435333,0.3179999887943268,0.3219999969005584,0.3260000050067901,0.3199999928474426,0.3160000145435333,0.3240000009536743,0.3260000050067901,0.3339999914169311,0.3240000009536743,0.3199999928474426,0.3160000145435333,0.3199999928474426,0.3179999887943268,0.3160000145435333,0.3079999983310699,0.3100000023841858,0.3199999928474426,0.3240000009536743,0.3219999969005584,0.3219999969005584,0.328000009059906,0.3319999873638153,0.3160000145435333,0.3260000050067901,0.3079999983310699,0.328000009059906,0.3199999928474426,0.3179999887943268,0.3160000145435333,0.3179999887943268,0.3260000050067901,0.3219999969005584,0.3260000050067901],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2560000121593475,0.2720000147819519,0.2980000078678131,0.2840000092983246,0.2879999876022339,0.3039999902248382,0.2860000133514404,0.2899999916553497,0.3019999861717224,0.2960000038146972,0.3039999902248382,0.3100000023841858,0.3160000145435333,0.3160000145435333,0.3260000050067901,0.3179999887943268,0.3420000076293945,0.3219999969005584,0.328000009059906,0.3240000009536743,0.3300000131130218,0.328000009059906,0.3199999928474426,0.3379999995231628,0.3400000035762787,0.3240000009536743,0.3120000064373016,0.3319999873638153,0.3260000050067901,0.3120000064373016,0.3160000145435333,0.3140000104904175,0.3179999887943268,0.3160000145435333,0.3199999928474426,0.3240000009536743,0.3260000050067901,0.3179999887943268,0.3300000131130218,0.3179999887943268,0.328000009059906,0.3240000009536743,0.328000009059906,0.3260000050067901,0.3199999928474426,0.3400000035762787,0.3339999914169311,0.328000009059906,0.328000009059906,0.3339999914169311,0.328000009059906,0.328000009059906,0.335999995470047,0.3580000102519989,0.3499999940395355,0.3260000050067901,0.3499999940395355,0.3420000076293945,0.3160000145435333,0.3339999914169311,0.335999995470047,0.3400000035762787,0.3240000009536743,0.3319999873638153,0.3379999995231628,0.3400000035762787,0.3379999995231628,0.3319999873638153,0.3319999873638153,0.3440000116825104,0.3300000131130218,0.3219999969005584,0.3260000050067901,0.3219999969005584,0.3339999914169311,0.328000009059906,0.3300000131130218,0.3219999969005584,0.3379999995231628,0.3400000035762787,0.3319999873638153,0.328000009059906,0.3440000116825104,0.3339999914169311,0.328000009059906,0.3379999995231628,0.3499999940395355,0.3339999914169311,0.3300000131130218,0.328000009059906,0.335999995470047,0.3240000009536743,0.335999995470047,0.3240000009536743,0.3400000035762787,0.3400000035762787,0.3420000076293945,0.3319999873638153,0.3339999914169311,0.3300000131130218,0.3400000035762787,0.3459999859333038,0.3400000035762787,0.3379999995231628,0.3459999859333038,0.3379999995231628,0.3300000131130218,0.3519999980926513,0.3379999995231628,0.356000006198883,0.335999995470047,0.3420000076293945,0.3400000035762787,0.328000009059906,0.3540000021457672,0.3499999940395355,0.3479999899864197,0.3440000116825104,0.3519999980926513,0.356000006198883,0.3540000021457672,0.3440000116825104,0.3499999940395355,0.356000006198883,0.356000006198883,0.356000006198883,0.363999992609024,0.3600000143051147,0.356000006198883,0.3479999899864197,0.356000006198883,0.3459999859333038,0.3479999899864197,0.3619999885559082,0.363999992609024,0.3499999940395355,0.3379999995231628,0.3479999899864197,0.3499999940395355,0.356000006198883,0.3519999980926513,0.3540000021457672,0.3619999885559082,0.3580000102519989,0.3540000021457672,0.356000006198883,0.3479999899864197,0.3519999980926513,0.356000006198883,0.3499999940395355,0.3379999995231628,0.3479999899864197,0.3499999940395355,0.3440000116825104,0.3580000102519989,0.356000006198883,0.3499999940395355,0.3479999899864197,0.3580000102519989,0.3519999980926513,0.3540000021457672,0.3519999980926513,0.3540000021457672,0.356000006198883,0.363999992609024,0.356000006198883,0.356000006198883],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2619999945163727,0.2599999904632568,0.2800000011920929,0.277999997138977,0.2980000078678131,0.3079999983310699,0.3120000064373016,0.3039999902248382,0.3000000119209289,0.3059999942779541,0.3140000104904175,0.3000000119209289,0.3100000023841858,0.3219999969005584,0.3240000009536743,0.328000009059906,0.3219999969005584,0.3100000023841858,0.3199999928474426,0.3179999887943268,0.3240000009536743,0.3199999928474426,0.3219999969005584,0.3319999873638153,0.328000009059906,0.3319999873638153,0.328000009059906,0.328000009059906,0.3339999914169311,0.328000009059906,0.3160000145435333,0.3300000131130218,0.335999995470047,0.3240000009536743,0.3140000104904175,0.3219999969005584,0.328000009059906,0.3420000076293945,0.3140000104904175,0.3120000064373016,0.3400000035762787,0.3339999914169311,0.3219999969005584,0.3219999969005584,0.3440000116825104,0.3300000131130218,0.3339999914169311,0.3400000035762787,0.3339999914169311,0.3379999995231628,0.3339999914169311,0.3160000145435333,0.3420000076293945,0.3219999969005584,0.3319999873638153,0.3300000131130218,0.3199999928474426,0.328000009059906,0.3219999969005584,0.3300000131130218,0.3440000116825104,0.328000009059906,0.3140000104904175,0.3440000116825104,0.3240000009536743,0.3400000035762787,0.3260000050067901,0.3300000131130218,0.335999995470047,0.328000009059906,0.3319999873638153,0.3260000050067901,0.3339999914169311,0.3400000035762787,0.335999995470047,0.3379999995231628,0.3319999873638153,0.3319999873638153,0.3339999914169311,0.3339999914169311,0.328000009059906,0.3219999969005584,0.3300000131130218,0.3339999914169311,0.3260000050067901,0.3240000009536743,0.3420000076293945,0.335999995470047,0.328000009059906,0.3319999873638153,0.3339999914169311,0.3300000131130218,0.3420000076293945,0.3339999914169311,0.3379999995231628,0.3260000050067901,0.3260000050067901,0.328000009059906,0.3339999914169311,0.3179999887943268,0.335999995470047,0.3319999873638153,0.3379999995231628,0.335999995470047,0.3300000131130218,0.3400000035762787,0.3319999873638153,0.3459999859333038,0.3300000131130218,0.3160000145435333,0.3260000050067901,0.3319999873638153,0.3339999914169311,0.3499999940395355,0.3339999914169311,0.3379999995231628,0.335999995470047,0.3400000035762787,0.3339999914169311,0.3379999995231628,0.3319999873638153,0.3420000076293945,0.335999995470047,0.335999995470047,0.3319999873638153,0.3300000131130218,0.3219999969005584,0.3400000035762787,0.328000009059906,0.335999995470047,0.3379999995231628,0.3420000076293945,0.3420000076293945,0.335999995470047,0.3300000131130218,0.328000009059906,0.3459999859333038,0.3440000116825104,0.3440000116825104,0.3499999940395355,0.335999995470047,0.3300000131130218,0.335999995470047,0.3379999995231628,0.335999995470047,0.3459999859333038,0.3379999995231628,0.3319999873638153,0.3479999899864197,0.3379999995231628,0.335999995470047,0.3300000131130218,0.3319999873638153,0.3339999914169311,0.3420000076293945,0.335999995470047,0.3479999899864197,0.3400000035762787,0.3440000116825104,0.335999995470047,0.3319999873638153,0.3400000035762787,0.335999995470047,0.3379999995231628,0.328000009059906,0.3339999914169311,0.3319999873638153],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2660000026226043,0.277999997138977,0.2820000052452087,0.3079999983310699,0.3140000104904175,0.3260000050067901,0.3039999902248382,0.3319999873638153,0.3240000009536743,0.3199999928474426,0.3379999995231628,0.3339999914169311,0.3319999873638153,0.3319999873638153,0.3219999969005584,0.3319999873638153,0.3379999995231628,0.3199999928474426,0.3179999887943268,0.3400000035762787,0.3219999969005584,0.335999995470047,0.3339999914169311,0.3420000076293945,0.3240000009536743,0.3440000116825104,0.3420000076293945,0.3379999995231628,0.3459999859333038,0.328000009059906,0.3420000076293945,0.3459999859333038,0.3479999899864197,0.3379999995231628,0.356000006198883,0.3379999995231628,0.3440000116825104,0.3400000035762787,0.3379999995231628,0.3499999940395355,0.3540000021457672,0.3479999899864197,0.3479999899864197,0.3440000116825104,0.3459999859333038,0.3440000116825104,0.3519999980926513,0.356000006198883,0.3600000143051147,0.3379999995231628,0.356000006198883,0.3400000035762787,0.3519999980926513,0.3479999899864197,0.3479999899864197,0.3400000035762787,0.3459999859333038,0.3519999980926513,0.3440000116825104,0.3400000035762787,0.356000006198883,0.3420000076293945,0.356000006198883,0.3540000021457672,0.3600000143051147,0.3339999914169311,0.3499999940395355,0.3580000102519989,0.3440000116825104,0.3479999899864197,0.3580000102519989,0.3519999980926513,0.3339999914169311,0.3540000021457672,0.3459999859333038,0.3459999859333038,0.3400000035762787,0.356000006198883,0.356000006198883,0.3420000076293945,0.3420000076293945,0.3400000035762787,0.3479999899864197,0.3519999980926513,0.3319999873638153,0.3580000102519989,0.356000006198883,0.356000006198883,0.3499999940395355,0.3479999899864197,0.3400000035762787,0.3440000116825104,0.3339999914169311,0.3379999995231628,0.3479999899864197,0.3680000007152557,0.3619999885559082,0.3440000116825104,0.3619999885559082,0.3580000102519989,0.356000006198883,0.3600000143051147,0.3519999980926513,0.3519999980926513,0.3459999859333038,0.3540000021457672,0.3600000143051147,0.356000006198883,0.3540000021457672,0.3519999980926513,0.356000006198883,0.3600000143051147,0.3540000021457672,0.3540000021457672,0.363999992609024,0.3580000102519989,0.3680000007152557,0.3580000102519989,0.356000006198883,0.3519999980926513,0.3519999980926513,0.3519999980926513,0.3459999859333038,0.3499999940395355,0.356000006198883,0.3540000021457672,0.3540000021457672,0.3659999966621399,0.3619999885559082,0.3420000076293945,0.363999992609024,0.3580000102519989,0.3619999885559082,0.3759999871253967,0.3740000128746032,0.363999992609024,0.3580000102519989,0.3700000047683716,0.3700000047683716,0.363999992609024,0.3440000116825104,0.3580000102519989,0.3680000007152557,0.3700000047683716,0.3740000128746032,0.3619999885559082,0.3619999885559082,0.3700000047683716,0.363999992609024,0.363999992609024,0.363999992609024,0.3700000047683716,0.3600000143051147,0.3680000007152557,0.363999992609024,0.3659999966621399,0.363999992609024,0.3680000007152557,0.3580000102519989,0.363999992609024,0.3659999966621399,0.363999992609024,0.3580000102519989,0.3600000143051147,0.3600000143051147,0.3580000102519989,0.3600000143051147],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2599999904632568,0.2680000066757202,0.2739999890327453,0.2800000011920929,0.270000010728836,0.2939999997615814,0.3059999942779541,0.2939999997615814,0.3059999942779541,0.3039999902248382,0.328000009059906,0.3160000145435333,0.3179999887943268,0.3319999873638153,0.3240000009536743,0.3379999995231628,0.3140000104904175,0.3260000050067901,0.335999995470047,0.3260000050067901,0.3440000116825104,0.3479999899864197,0.335999995470047,0.3319999873638153,0.335999995470047,0.3420000076293945,0.3319999873638153,0.3519999980926513,0.3319999873638153,0.3260000050067901,0.3260000050067901,0.3420000076293945,0.3459999859333038,0.3440000116825104,0.3300000131130218,0.3459999859333038,0.3580000102519989,0.3499999940395355,0.3420000076293945,0.3319999873638153,0.335999995470047,0.3479999899864197,0.3420000076293945,0.335999995470047,0.3379999995231628,0.335999995470047,0.335999995470047,0.3420000076293945,0.3420000076293945,0.3339999914169311,0.3440000116825104,0.3240000009536743,0.3400000035762787,0.3499999940395355,0.328000009059906,0.3379999995231628,0.3260000050067901,0.3379999995231628,0.3420000076293945,0.3519999980926513,0.3400000035762787,0.3300000131130218,0.3479999899864197,0.3240000009536743,0.3440000116825104,0.3379999995231628,0.3420000076293945,0.335999995470047,0.3339999914169311,0.3499999940395355,0.3519999980926513,0.335999995470047,0.335999995470047,0.3339999914169311,0.3339999914169311,0.356000006198883,0.3319999873638153,0.3479999899864197,0.3479999899864197,0.3519999980926513,0.3540000021457672,0.3459999859333038,0.3540000021457672,0.356000006198883,0.3379999995231628,0.3479999899864197,0.3440000116825104,0.363999992609024,0.3600000143051147,0.3420000076293945,0.356000006198883,0.335999995470047,0.3479999899864197,0.3619999885559082,0.3499999940395355,0.3440000116825104,0.3400000035762787,0.356000006198883,0.3499999940395355,0.3519999980926513,0.3379999995231628,0.3519999980926513,0.356000006198883,0.3440000116825104,0.363999992609024,0.3420000076293945,0.3400000035762787,0.3459999859333038,0.356000006198883,0.3479999899864197,0.3619999885559082,0.3319999873638153,0.3459999859333038,0.3420000076293945,0.3519999980926513,0.3459999859333038,0.363999992609024,0.3459999859333038,0.3319999873638153,0.3400000035762787,0.3499999940395355,0.3499999940395355,0.3580000102519989,0.363999992609024,0.356000006198883,0.3540000021457672,0.335999995470047,0.3479999899864197,0.3459999859333038,0.3420000076293945,0.3499999940395355,0.3479999899864197,0.335999995470047,0.3379999995231628,0.3440000116825104,0.3440000116825104,0.3659999966621399,0.3499999940395355,0.3540000021457672,0.3459999859333038,0.3519999980926513,0.3459999859333038,0.3499999940395355,0.3519999980926513,0.3440000116825104,0.3580000102519989,0.3619999885559082,0.3499999940395355,0.3540000021457672,0.3519999980926513,0.3499999940395355,0.3580000102519989,0.363999992609024,0.3540000021457672,0.3540000021457672,0.3580000102519989,0.3420000076293945,0.3440000116825104,0.3479999899864197,0.3459999859333038,0.3440000116825104,0.3540000021457672,0.3499999940395355,0.3499999940395355,0.356000006198883,0.3519999980926513,0.3580000102519989],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2419999986886978,0.2739999890327453,0.2939999997615814,0.3059999942779541,0.3039999902248382,0.2840000092983246,0.3160000145435333,0.3179999887943268,0.3039999902248382,0.3199999928474426,0.3100000023841858,0.3120000064373016,0.3120000064373016,0.3199999928474426,0.3160000145435333,0.3300000131130218,0.335999995470047,0.3339999914169311,0.3400000035762787,0.3100000023841858,0.328000009059906,0.3199999928474426,0.3479999899864197,0.3179999887943268,0.328000009059906,0.335999995470047,0.335999995470047,0.328000009059906,0.335999995470047,0.3379999995231628,0.3499999940395355,0.3420000076293945,0.3440000116825104,0.3440000116825104,0.3339999914169311,0.3379999995231628,0.3379999995231628,0.3420000076293945,0.328000009059906,0.3400000035762787,0.3659999966621399,0.3499999940395355,0.3499999940395355,0.3420000076293945,0.3499999940395355,0.3339999914169311,0.3459999859333038,0.3440000116825104,0.3499999940395355,0.3420000076293945,0.3540000021457672,0.3379999995231628,0.3519999980926513,0.3339999914169311,0.3339999914169311,0.3379999995231628,0.3420000076293945,0.3519999980926513,0.3459999859333038,0.3420000076293945,0.3459999859333038,0.3479999899864197,0.3619999885559082,0.3619999885559082,0.3459999859333038,0.3379999995231628,0.3519999980926513,0.3420000076293945,0.3420000076293945,0.3499999940395355,0.3479999899864197,0.3519999980926513,0.3479999899864197,0.3540000021457672,0.3339999914169311,0.3400000035762787,0.3540000021457672,0.3680000007152557,0.3600000143051147,0.3519999980926513,0.3400000035762787,0.3540000021457672,0.356000006198883,0.3580000102519989,0.356000006198883,0.3499999940395355,0.3400000035762787,0.3499999940395355,0.3499999940395355,0.3619999885559082,0.3499999940395355,0.3600000143051147,0.3499999940395355,0.3379999995231628,0.3459999859333038,0.3459999859333038,0.3459999859333038,0.3479999899864197,0.3600000143051147,0.3420000076293945,0.3720000088214874,0.356000006198883,0.363999992609024,0.3580000102519989,0.3459999859333038,0.356000006198883,0.3459999859333038,0.3499999940395355,0.3659999966621399,0.3540000021457672,0.3459999859333038,0.3600000143051147,0.3459999859333038,0.3440000116825104,0.3519999980926513,0.3499999940395355,0.3619999885559082,0.356000006198883,0.3499999940395355,0.3519999980926513,0.3459999859333038,0.3440000116825104,0.3440000116825104,0.3440000116825104,0.3499999940395355,0.356000006198883,0.3420000076293945,0.3499999940395355,0.3440000116825104,0.3479999899864197,0.3420000076293945,0.3600000143051147,0.3519999980926513,0.3659999966621399,0.356000006198883,0.356000006198883,0.3540000021457672,0.356000006198883,0.3600000143051147,0.3619999885559082,0.3400000035762787,0.3420000076293945,0.3420000076293945,0.356000006198883,0.356000006198883,0.3540000021457672,0.3440000116825104,0.3519999980926513,0.3540000021457672,0.363999992609024,0.3379999995231628,0.3479999899864197,0.3459999859333038,0.3519999980926513,0.3659999966621399,0.3580000102519989,0.3519999980926513,0.3619999885559082,0.3619999885559082,0.3619999885559082,0.3600000143051147,0.3580000102519989,0.3499999940395355,0.3499999940395355,0.3580000102519989,0.3479999899864197,0.3499999940395355],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2860000133514404,0.2619999945163727,0.2540000081062317,0.2820000052452087,0.2899999916553497,0.2939999997615814,0.2980000078678131,0.3019999861717224,0.2960000038146972,0.328000009059906,0.3219999969005584,0.3140000104904175,0.3140000104904175,0.3079999983310699,0.3199999928474426,0.328000009059906,0.3260000050067901,0.3179999887943268,0.3319999873638153,0.3400000035762787,0.3260000050067901,0.3199999928474426,0.3199999928474426,0.3300000131130218,0.328000009059906,0.3179999887943268,0.3400000035762787,0.3300000131130218,0.3240000009536743,0.3319999873638153,0.3420000076293945,0.3400000035762787,0.335999995470047,0.3479999899864197,0.3440000116825104,0.3519999980926513,0.3540000021457672,0.3440000116825104,0.3400000035762787,0.328000009059906,0.3400000035762787,0.3499999940395355,0.3459999859333038,0.3420000076293945,0.335999995470047,0.328000009059906,0.328000009059906,0.3440000116825104,0.3400000035762787,0.3260000050067901,0.3440000116825104,0.3499999940395355,0.3540000021457672,0.3440000116825104,0.3420000076293945,0.3420000076293945,0.3519999980926513,0.3459999859333038,0.3440000116825104,0.3339999914169311,0.3379999995231628,0.3400000035762787,0.356000006198883,0.3519999980926513,0.3540000021457672,0.3580000102519989,0.3400000035762787,0.3459999859333038,0.3479999899864197,0.3440000116825104,0.3339999914169311,0.3479999899864197,0.3459999859333038,0.3499999940395355,0.3319999873638153,0.335999995470047,0.3459999859333038,0.3540000021457672,0.3479999899864197,0.3479999899864197,0.356000006198883,0.3459999859333038,0.3479999899864197,0.3400000035762787,0.3499999940395355,0.3319999873638153,0.3400000035762787,0.3400000035762787,0.3379999995231628,0.356000006198883,0.3479999899864197,0.3499999940395355,0.3379999995231628,0.3379999995231628,0.3379999995231628,0.3339999914169311,0.3499999940395355,0.3459999859333038,0.356000006198883,0.3479999899864197,0.3420000076293945,0.3519999980926513,0.356000006198883,0.3479999899864197,0.3619999885559082,0.3479999899864197,0.3479999899864197,0.356000006198883,0.3420000076293945,0.3440000116825104,0.3519999980926513,0.3379999995231628,0.356000006198883,0.3459999859333038,0.3479999899864197,0.3499999940395355,0.3519999980926513,0.356000006198883,0.356000006198883,0.3459999859333038,0.3580000102519989,0.3519999980926513,0.356000006198883,0.3540000021457672,0.3540000021457672,0.3619999885559082,0.3459999859333038,0.3519999980926513,0.3479999899864197,0.3400000035762787,0.335999995470047,0.356000006198883,0.3479999899864197,0.3619999885559082,0.356000006198883,0.3580000102519989,0.3540000021457672,0.3479999899864197,0.3619999885559082,0.3580000102519989,0.356000006198883,0.3479999899864197,0.3499999940395355,0.3499999940395355,0.3619999885559082,0.3659999966621399,0.3440000116825104,0.3700000047683716,0.3499999940395355,0.356000006198883,0.3580000102519989,0.3479999899864197,0.3540000021457672,0.3580000102519989,0.3540000021457672,0.363999992609024,0.356000006198883,0.3499999940395355,0.356000006198883,0.3499999940395355,0.3499999940395355,0.3580000102519989,0.3540000021457672,0.3540000021457672,0.3420000076293945,0.3619999885559082,0.3540000021457672,0.3540000021457672],"label":"FineWeb URL dedup"}},"piqa/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5419999957084656,0.5839999914169312,0.6320000290870667,0.6420000195503235,0.656000018119812,0.6650000214576721,0.6610000133514404,0.6700000166893005,0.6930000185966492,0.6890000104904175,0.6840000152587891,0.6869999766349792,0.6819999814033508,0.6990000009536743,0.6970000267028809,0.7110000252723694,0.7129999995231628,0.7020000219345093,0.7059999704360962,0.7110000252723694,0.7110000252723694,0.7179999947547913,0.7210000157356262,0.7139999866485596,0.7070000171661377,0.7229999899864197,0.7149999737739563,0.7149999737739563,0.7200000286102295,0.7289999723434448,0.7250000238418579,0.722000002861023,0.7250000238418579,0.7179999947547913,0.7099999785423279,0.718999981880188,0.7229999899864197,0.7229999899864197,0.7210000157356262,0.7229999899864197,0.7239999771118164,0.7179999947547913,0.7250000238418579,0.7269999980926514,0.7210000157356262,0.7239999771118164,0.7229999899864197,0.7289999723434448,0.7250000238418579,0.7300000190734863,0.7350000143051147,0.734000027179718,0.7279999852180481,0.7260000109672546,0.7300000190734863,0.7229999899864197,0.7300000190734863,0.7210000157356262,0.7160000205039978,0.7300000190734863,0.7229999899864197,0.7179999947547913,0.7300000190734863,0.7279999852180481,0.722000002861023,0.7239999771118164,0.7239999771118164,0.7210000157356262,0.7250000238418579,0.7250000238418579,0.7300000190734863,0.7350000143051147,0.7269999980926514,0.7279999852180481,0.7269999980926514,0.7279999852180481,0.7329999804496765,0.7289999723434448,0.7260000109672546,0.7260000109672546,0.7360000014305115,0.7250000238418579,0.7260000109672546,0.7379999756813049,0.7300000190734863,0.7350000143051147,0.7390000224113464,0.7350000143051147,0.7419999837875366,0.7319999933242798,0.7369999885559082,0.7289999723434448,0.7250000238418579,0.7319999933242798,0.7409999966621399,0.7269999980926514,0.7360000014305115,0.7329999804496765,0.7390000224113464,0.7379999756813049,0.7310000061988831,0.7450000047683716,0.7419999837875366,0.7400000095367432,0.734000027179718,0.7350000143051147,0.7429999709129333,0.7400000095367432,0.7429999709129333,0.7409999966621399,0.7429999709129333,0.7369999885559082,0.7450000047683716,0.746999979019165,0.75,0.7369999885559082,0.7329999804496765,0.7409999966621399,0.7390000224113464,0.7329999804496765,0.734000027179718,0.7419999837875366,0.7400000095367432,0.746999979019165,0.7429999709129333,0.7369999885559082,0.7360000014305115,0.7319999933242798,0.7350000143051147,0.7319999933242798,0.7300000190734863,0.7369999885559082,0.7400000095367432,0.7429999709129333,0.7400000095367432,0.7390000224113464,0.7390000224113464,0.7419999837875366,0.7429999709129333,0.7360000014305115,0.75,0.7419999837875366,0.7490000128746033,0.7509999871253967,0.7509999871253967,0.7540000081062317,0.7400000095367432,0.7549999952316284,0.7459999918937683,0.7400000095367432,0.7440000176429749,0.7409999966621399,0.7400000095367432,0.753000020980835,0.7450000047683716,0.7509999871253967,0.7509999871253967,0.7450000047683716,0.7549999952316284,0.7509999871253967,0.7459999918937683,0.7440000176429749,0.746999979019165,0.7459999918937683,0.7490000128746033,0.7490000128746033,0.7450000047683716,0.746999979019165],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5419999957084656,0.6060000061988831,0.6420000195503235,0.6480000019073486,0.640999972820282,0.6639999747276306,0.6660000085830688,0.6840000152587891,0.6840000152587891,0.6790000200271606,0.6779999732971191,0.6949999928474426,0.6880000233650208,0.6949999928474426,0.6880000233650208,0.6959999799728394,0.6940000057220459,0.6899999976158142,0.6930000185966492,0.7049999833106995,0.6959999799728394,0.6859999895095825,0.703000009059906,0.6980000138282776,0.6940000057220459,0.699999988079071,0.6919999718666077,0.6970000267028809,0.6990000009536743,0.703000009059906,0.6990000009536743,0.699999988079071,0.6959999799728394,0.6970000267028809,0.7080000042915344,0.7089999914169312,0.7059999704360962,0.7089999914169312,0.7139999866485596,0.7009999752044678,0.7039999961853027,0.6930000185966492,0.7059999704360962,0.7009999752044678,0.703000009059906,0.7099999785423279,0.7149999737739563,0.7210000157356262,0.7210000157356262,0.7080000042915344,0.7099999785423279,0.718999981880188,0.7070000171661377,0.6949999928474426,0.7099999785423279,0.7129999995231628,0.7149999737739563,0.7099999785423279,0.7059999704360962,0.7099999785423279,0.7049999833106995,0.7250000238418579,0.7170000076293945,0.722000002861023,0.7110000252723694,0.7170000076293945,0.7120000123977661,0.7170000076293945,0.7049999833106995,0.7239999771118164,0.7129999995231628,0.722000002861023,0.7110000252723694,0.7200000286102295,0.7120000123977661,0.7070000171661377,0.7139999866485596,0.722000002861023,0.7210000157356262,0.7210000157356262,0.7160000205039978,0.7179999947547913,0.718999981880188,0.7110000252723694,0.7210000157356262,0.7289999723434448,0.718999981880188,0.718999981880188,0.7129999995231628,0.722000002861023,0.7099999785423279,0.7139999866485596,0.722000002861023,0.7210000157356262,0.7170000076293945,0.7200000286102295,0.7200000286102295,0.7239999771118164,0.7319999933242798,0.7160000205039978,0.7260000109672546,0.7279999852180481,0.7279999852180481,0.7250000238418579,0.7329999804496765,0.7269999980926514,0.7260000109672546,0.7300000190734863,0.7269999980926514,0.7289999723434448,0.7200000286102295,0.7239999771118164,0.7329999804496765,0.7279999852180481,0.7319999933242798,0.7300000190734863,0.7289999723434448,0.7260000109672546,0.722000002861023,0.7369999885559082,0.7229999899864197,0.7210000157356262,0.718999981880188,0.7269999980926514,0.7329999804496765,0.722000002861023,0.7239999771118164,0.7289999723434448,0.7329999804496765,0.7239999771118164,0.7289999723434448,0.7229999899864197,0.7279999852180481,0.7239999771118164,0.7279999852180481,0.7269999980926514,0.7329999804496765,0.7369999885559082,0.7310000061988831,0.7329999804496765,0.734000027179718,0.7319999933242798,0.7319999933242798,0.7239999771118164,0.7260000109672546,0.7289999723434448,0.7300000190734863,0.734000027179718,0.734000027179718,0.734000027179718,0.7239999771118164,0.7360000014305115,0.7300000190734863,0.7300000190734863,0.7239999771118164,0.7300000190734863,0.7250000238418579,0.734000027179718,0.7269999980926514,0.7329999804496765,0.7329999804496765,0.7300000190734863,0.7319999933242798,0.7319999933242798,0.7319999933242798,0.7289999723434448,0.7260000109672546,0.7250000238418579],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5419999957084656,0.6110000014305115,0.6240000128746033,0.6520000100135803,0.6520000100135803,0.6579999923706055,0.6669999957084656,0.6669999957084656,0.6779999732971191,0.6850000023841858,0.6830000281333923,0.6840000152587891,0.6769999861717224,0.6800000071525574,0.6949999928474426,0.6919999718666077,0.6809999942779541,0.6890000104904175,0.6970000267028809,0.6930000185966492,0.6990000009536743,0.6990000009536743,0.6949999928474426,0.7080000042915344,0.7009999752044678,0.7049999833106995,0.7049999833106995,0.7099999785423279,0.7009999752044678,0.7129999995231628,0.7059999704360962,0.7080000042915344,0.7009999752044678,0.7080000042915344,0.7099999785423279,0.7099999785423279,0.7039999961853027,0.7080000042915344,0.7179999947547913,0.7129999995231628,0.7089999914169312,0.7059999704360962,0.7059999704360962,0.7120000123977661,0.7110000252723694,0.7049999833106995,0.7139999866485596,0.7099999785423279,0.718999981880188,0.7170000076293945,0.7179999947547913,0.7170000076293945,0.7239999771118164,0.7149999737739563,0.7160000205039978,0.7160000205039978,0.7110000252723694,0.722000002861023,0.7139999866485596,0.718999981880188,0.7170000076293945,0.7129999995231628,0.7129999995231628,0.7200000286102295,0.7239999771118164,0.7200000286102295,0.7239999771118164,0.7179999947547913,0.7269999980926514,0.7129999995231628,0.7110000252723694,0.7070000171661377,0.7129999995231628,0.7170000076293945,0.7279999852180481,0.7210000157356262,0.7210000157356262,0.7149999737739563,0.7200000286102295,0.7289999723434448,0.7179999947547913,0.7210000157356262,0.7289999723434448,0.7229999899864197,0.7310000061988831,0.7269999980926514,0.7139999866485596,0.7300000190734863,0.7239999771118164,0.7129999995231628,0.7229999899864197,0.7279999852180481,0.7269999980926514,0.734000027179718,0.7250000238418579,0.7229999899864197,0.7319999933242798,0.7319999933242798,0.7279999852180481,0.7329999804496765,0.7279999852180481,0.722000002861023,0.7300000190734863,0.7239999771118164,0.7210000157356262,0.7229999899864197,0.7250000238418579,0.7260000109672546,0.7269999980926514,0.7229999899864197,0.7350000143051147,0.722000002861023,0.7239999771118164,0.7269999980926514,0.7250000238418579,0.7279999852180481,0.7289999723434448,0.7329999804496765,0.7289999723434448,0.7360000014305115,0.7260000109672546,0.7300000190734863,0.7329999804496765,0.7229999899864197,0.7200000286102295,0.7260000109672546,0.722000002861023,0.7269999980926514,0.7300000190734863,0.7200000286102295,0.7269999980926514,0.7310000061988831,0.7310000061988831,0.7269999980926514,0.7300000190734863,0.7350000143051147,0.7369999885559082,0.7300000190734863,0.7269999980926514,0.7319999933242798,0.7269999980926514,0.7329999804496765,0.7379999756813049,0.7300000190734863,0.7310000061988831,0.722000002861023,0.7319999933242798,0.7300000190734863,0.734000027179718,0.7360000014305115,0.7360000014305115,0.7310000061988831,0.7329999804496765,0.734000027179718,0.7289999723434448,0.7360000014305115,0.734000027179718,0.734000027179718,0.7360000014305115,0.7329999804496765,0.7319999933242798,0.7379999756813049,0.7350000143051147,0.7279999852180481,0.7289999723434448,0.7319999933242798,0.7310000061988831,0.7319999933242798],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5429999828338623,0.6029999852180481,0.6320000290870667,0.6449999809265137,0.6389999985694885,0.6610000133514404,0.6690000295639038,0.6710000038146973,0.6690000295639038,0.6830000281333923,0.6899999976158142,0.6840000152587891,0.6859999895095825,0.7039999961853027,0.6959999799728394,0.6899999976158142,0.6980000138282776,0.6949999928474426,0.6970000267028809,0.7039999961853027,0.699999988079071,0.7020000219345093,0.6990000009536743,0.7099999785423279,0.7039999961853027,0.703000009059906,0.6990000009536743,0.7020000219345093,0.7039999961853027,0.7129999995231628,0.7049999833106995,0.718999981880188,0.7059999704360962,0.6940000057220459,0.7009999752044678,0.7049999833106995,0.7110000252723694,0.7120000123977661,0.7160000205039978,0.7070000171661377,0.6949999928474426,0.703000009059906,0.7089999914169312,0.7179999947547913,0.7170000076293945,0.7160000205039978,0.7059999704360962,0.7229999899864197,0.7129999995231628,0.7059999704360962,0.7170000076293945,0.718999981880188,0.7120000123977661,0.7179999947547913,0.7160000205039978,0.7149999737739563,0.7080000042915344,0.7160000205039978,0.718999981880188,0.7250000238418579,0.722000002861023,0.7260000109672546,0.7310000061988831,0.7310000061988831,0.7149999737739563,0.7120000123977661,0.7269999980926514,0.7239999771118164,0.7300000190734863,0.7129999995231628,0.7269999980926514,0.7250000238418579,0.7210000157356262,0.7310000061988831,0.7310000061988831,0.7229999899864197,0.7289999723434448,0.7319999933242798,0.7400000095367432,0.7350000143051147,0.7369999885559082,0.7329999804496765,0.7289999723434448,0.7329999804496765,0.7329999804496765,0.7289999723434448,0.7250000238418579,0.7279999852180481,0.7279999852180481,0.7369999885559082,0.7360000014305115,0.7379999756813049,0.7369999885559082,0.7360000014305115,0.7310000061988831,0.7390000224113464,0.7400000095367432,0.7390000224113464,0.7350000143051147,0.7390000224113464,0.7350000143051147,0.7409999966621399,0.7369999885559082,0.7329999804496765,0.746999979019165,0.7310000061988831,0.7400000095367432,0.7390000224113464,0.7360000014305115,0.7390000224113464,0.7360000014305115,0.7329999804496765,0.7369999885559082,0.7369999885559082,0.7329999804496765,0.7440000176429749,0.7300000190734863,0.7310000061988831,0.7390000224113464,0.7379999756813049,0.7360000014305115,0.746999979019165,0.7400000095367432,0.7440000176429749,0.7400000095367432,0.7429999709129333,0.7419999837875366,0.7379999756813049,0.7409999966621399,0.7319999933242798,0.7429999709129333,0.7429999709129333,0.746999979019165,0.7360000014305115,0.7419999837875366,0.7450000047683716,0.7390000224113464,0.7480000257492065,0.7450000047683716,0.7390000224113464,0.7390000224113464,0.7390000224113464,0.7360000014305115,0.7459999918937683,0.7490000128746033,0.7450000047683716,0.7419999837875366,0.7440000176429749,0.7409999966621399,0.7450000047683716,0.7429999709129333,0.7450000047683716,0.7350000143051147,0.7409999966621399,0.7379999756813049,0.7450000047683716,0.7390000224113464,0.7480000257492065,0.7400000095367432,0.7390000224113464,0.734000027179718,0.7450000047683716,0.7400000095367432,0.7450000047683716,0.7459999918937683,0.7429999709129333,0.7440000176429749,0.746999979019165],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5419999957084656,0.5929999947547913,0.6349999904632568,0.6620000004768372,0.6600000262260437,0.6669999957084656,0.6650000214576721,0.6769999861717224,0.6840000152587891,0.6880000233650208,0.6850000023841858,0.6869999766349792,0.6970000267028809,0.6990000009536743,0.7070000171661377,0.6890000104904175,0.7039999961853027,0.7089999914169312,0.7129999995231628,0.7080000042915344,0.7110000252723694,0.7200000286102295,0.7099999785423279,0.7070000171661377,0.7080000042915344,0.7089999914169312,0.7070000171661377,0.7129999995231628,0.7149999737739563,0.7289999723434448,0.7099999785423279,0.7229999899864197,0.7039999961853027,0.7070000171661377,0.718999981880188,0.7170000076293945,0.7250000238418579,0.7210000157356262,0.7269999980926514,0.7139999866485596,0.7200000286102295,0.7210000157356262,0.7229999899864197,0.7229999899864197,0.7160000205039978,0.7120000123977661,0.7080000042915344,0.718999981880188,0.7210000157356262,0.7120000123977661,0.7179999947547913,0.7250000238418579,0.718999981880188,0.7279999852180481,0.7160000205039978,0.7210000157356262,0.7260000109672546,0.7239999771118164,0.7239999771118164,0.7200000286102295,0.7319999933242798,0.7179999947547913,0.7369999885559082,0.718999981880188,0.7269999980926514,0.7250000238418579,0.7250000238418579,0.7179999947547913,0.7179999947547913,0.7250000238418579,0.7229999899864197,0.7329999804496765,0.7329999804496765,0.7300000190734863,0.734000027179718,0.7269999980926514,0.7360000014305115,0.7400000095367432,0.7269999980926514,0.7360000014305115,0.7260000109672546,0.7369999885559082,0.7360000014305115,0.7229999899864197,0.734000027179718,0.7269999980926514,0.7409999966621399,0.7329999804496765,0.7319999933242798,0.7300000190734863,0.7319999933242798,0.734000027179718,0.7269999980926514,0.7289999723434448,0.7300000190734863,0.7360000014305115,0.7419999837875366,0.7390000224113464,0.734000027179718,0.7369999885559082,0.7360000014305115,0.734000027179718,0.7350000143051147,0.7360000014305115,0.7310000061988831,0.7310000061988831,0.7319999933242798,0.7390000224113464,0.746999979019165,0.7429999709129333,0.734000027179718,0.734000027179718,0.7319999933242798,0.7419999837875366,0.7300000190734863,0.7350000143051147,0.7350000143051147,0.734000027179718,0.7409999966621399,0.7329999804496765,0.7450000047683716,0.7409999966621399,0.746999979019165,0.7409999966621399,0.7350000143051147,0.7409999966621399,0.7429999709129333,0.7390000224113464,0.7409999966621399,0.7350000143051147,0.7419999837875366,0.746999979019165,0.7459999918937683,0.7509999871253967,0.7429999709129333,0.7490000128746033,0.7450000047683716,0.7490000128746033,0.7400000095367432,0.75,0.7409999966621399,0.7409999966621399,0.7440000176429749,0.7419999837875366,0.7450000047683716,0.7459999918937683,0.7509999871253967,0.75,0.7419999837875366,0.7459999918937683,0.75,0.7480000257492065,0.7480000257492065,0.7450000047683716,0.7480000257492065,0.746999979019165,0.7369999885559082,0.7419999837875366,0.7419999837875366,0.7429999709129333,0.746999979019165,0.7329999804496765,0.7409999966621399,0.7440000176429749,0.7400000095367432,0.7459999918937683,0.75,0.7509999871253967],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5419999957084656,0.5839999914169312,0.6169999837875366,0.6470000147819519,0.6510000228881836,0.6759999990463257,0.6579999923706055,0.6769999861717224,0.671999990940094,0.6710000038146973,0.6990000009536743,0.6859999895095825,0.6959999799728394,0.6909999847412109,0.7120000123977661,0.6949999928474426,0.7020000219345093,0.6940000057220459,0.7099999785423279,0.6980000138282776,0.6899999976158142,0.6970000267028809,0.7009999752044678,0.7099999785423279,0.6980000138282776,0.7009999752044678,0.7020000219345093,0.7059999704360962,0.7080000042915344,0.6980000138282776,0.7120000123977661,0.6909999847412109,0.6930000185966492,0.7099999785423279,0.699999988079071,0.7059999704360962,0.699999988079071,0.7089999914169312,0.6990000009536743,0.7059999704360962,0.6949999928474426,0.7070000171661377,0.7049999833106995,0.6930000185966492,0.6980000138282776,0.7039999961853027,0.7080000042915344,0.7089999914169312,0.6959999799728394,0.6940000057220459,0.7039999961853027,0.7160000205039978,0.7009999752044678,0.7149999737739563,0.7099999785423279,0.7089999914169312,0.703000009059906,0.6990000009536743,0.7129999995231628,0.7009999752044678,0.718999981880188,0.6990000009536743,0.7049999833106995,0.6990000009536743,0.7070000171661377,0.7099999785423279,0.7149999737739563,0.7059999704360962,0.7089999914169312,0.7020000219345093,0.7239999771118164,0.7129999995231628,0.7049999833106995,0.7070000171661377,0.7160000205039978,0.7210000157356262,0.7110000252723694,0.7170000076293945,0.7059999704360962,0.7179999947547913,0.7080000042915344,0.7229999899864197,0.7260000109672546,0.7149999737739563,0.7139999866485596,0.7110000252723694,0.7179999947547913,0.7289999723434448,0.7110000252723694,0.7250000238418579,0.7279999852180481,0.7089999914169312,0.722000002861023,0.7229999899864197,0.7149999737739563,0.7170000076293945,0.722000002861023,0.7160000205039978,0.7179999947547913,0.7300000190734863,0.7289999723434448,0.722000002861023,0.7250000238418579,0.7200000286102295,0.722000002861023,0.7310000061988831,0.7260000109672546,0.722000002861023,0.7269999980926514,0.7279999852180481,0.7300000190734863,0.7369999885559082,0.722000002861023,0.7210000157356262,0.7170000076293945,0.7260000109672546,0.7319999933242798,0.7210000157356262,0.7310000061988831,0.7250000238418579,0.7269999980926514,0.7269999980926514,0.7279999852180481,0.7269999980926514,0.7269999980926514,0.722000002861023,0.718999981880188,0.7229999899864197,0.7210000157356262,0.7300000190734863,0.7260000109672546,0.7310000061988831,0.7300000190734863,0.7269999980926514,0.7210000157356262,0.7300000190734863,0.7269999980926514,0.722000002861023,0.7300000190734863,0.7269999980926514,0.722000002861023,0.7319999933242798,0.7229999899864197,0.7310000061988831,0.7300000190734863,0.7250000238418579,0.7289999723434448,0.7269999980926514,0.7260000109672546,0.7179999947547913,0.7289999723434448,0.7229999899864197,0.7289999723434448,0.7250000238418579,0.7239999771118164,0.7279999852180481,0.7229999899864197,0.7289999723434448,0.7319999933242798,0.7279999852180481,0.7239999771118164,0.7300000190734863,0.722000002861023,0.7229999899864197,0.7260000109672546,0.7239999771118164,0.7149999737739563,0.7300000190734863],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5419999957084656,0.5960000157356262,0.628000020980835,0.6309999823570251,0.6650000214576721,0.6600000262260437,0.6669999957084656,0.6589999794960022,0.6570000052452087,0.6700000166893005,0.6660000085830688,0.6819999814033508,0.6830000281333923,0.6729999780654907,0.6850000023841858,0.6779999732971191,0.6819999814033508,0.6890000104904175,0.6890000104904175,0.6850000023841858,0.6970000267028809,0.6970000267028809,0.6899999976158142,0.6990000009536743,0.6959999799728394,0.6880000233650208,0.7059999704360962,0.6949999928474426,0.7020000219345093,0.7009999752044678,0.7070000171661377,0.7020000219345093,0.7049999833106995,0.7080000042915344,0.6959999799728394,0.7099999785423279,0.7059999704360962,0.7110000252723694,0.703000009059906,0.7080000042915344,0.7059999704360962,0.7170000076293945,0.7099999785423279,0.6930000185966492,0.7009999752044678,0.6990000009536743,0.6959999799728394,0.7059999704360962,0.703000009059906,0.7120000123977661,0.7009999752044678,0.7139999866485596,0.699999988079071,0.7059999704360962,0.7059999704360962,0.7089999914169312,0.7049999833106995,0.722000002861023,0.7120000123977661,0.7070000171661377,0.7179999947547913,0.722000002861023,0.7210000157356262,0.7160000205039978,0.7039999961853027,0.7110000252723694,0.6980000138282776,0.7129999995231628,0.7179999947547913,0.7170000076293945,0.7099999785423279,0.7170000076293945,0.722000002861023,0.7099999785423279,0.7160000205039978,0.7179999947547913,0.7160000205039978,0.7229999899864197,0.7149999737739563,0.7229999899864197,0.7269999980926514,0.718999981880188,0.7319999933242798,0.7239999771118164,0.7279999852180481,0.7310000061988831,0.7139999866485596,0.7210000157356262,0.718999981880188,0.7200000286102295,0.7210000157356262,0.722000002861023,0.7229999899864197,0.7250000238418579,0.7250000238418579,0.7229999899864197,0.7250000238418579,0.7229999899864197,0.7319999933242798,0.7210000157356262,0.7260000109672546,0.734000027179718,0.7289999723434448,0.7250000238418579,0.7279999852180481,0.7319999933242798,0.7390000224113464,0.7369999885559082,0.722000002861023,0.7350000143051147,0.7300000190734863,0.7269999980926514,0.7369999885559082,0.7289999723434448,0.7289999723434448,0.7300000190734863,0.7419999837875366,0.7379999756813049,0.7269999980926514,0.7329999804496765,0.7300000190734863,0.7269999980926514,0.7269999980926514,0.7279999852180481,0.7319999933242798,0.722000002861023,0.7269999980926514,0.7279999852180481,0.7179999947547913,0.7279999852180481,0.7260000109672546,0.7369999885559082,0.7300000190734863,0.7279999852180481,0.7379999756813049,0.7379999756813049,0.7360000014305115,0.7360000014305115,0.7329999804496765,0.7390000224113464,0.7319999933242798,0.7289999723434448,0.7310000061988831,0.7310000061988831,0.7379999756813049,0.7300000190734863,0.7369999885559082,0.7329999804496765,0.7329999804496765,0.7350000143051147,0.7300000190734863,0.7260000109672546,0.7300000190734863,0.7289999723434448,0.7360000014305115,0.7329999804496765,0.7350000143051147,0.7300000190734863,0.7350000143051147,0.7390000224113464,0.7329999804496765,0.7310000061988831,0.734000027179718,0.7369999885559082,0.7350000143051147,0.7319999933242798,0.7390000224113464,0.7369999885559082],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5429999828338623,0.6079999804496765,0.6259999871253967,0.656000018119812,0.6679999828338623,0.6769999861717224,0.6650000214576721,0.6710000038146973,0.6740000247955322,0.6859999895095825,0.6830000281333923,0.6809999942779541,0.6869999766349792,0.675000011920929,0.6830000281333923,0.6840000152587891,0.6859999895095825,0.6859999895095825,0.699999988079071,0.6909999847412109,0.6980000138282776,0.6919999718666077,0.6869999766349792,0.6980000138282776,0.6990000009536743,0.699999988079071,0.6949999928474426,0.6970000267028809,0.6990000009536743,0.6930000185966492,0.703000009059906,0.7070000171661377,0.6930000185966492,0.7049999833106995,0.7009999752044678,0.7009999752044678,0.7179999947547913,0.7160000205039978,0.7120000123977661,0.7139999866485596,0.6990000009536743,0.7099999785423279,0.7170000076293945,0.7149999737739563,0.7149999737739563,0.7110000252723694,0.7059999704360962,0.7200000286102295,0.7160000205039978,0.7129999995231628,0.7149999737739563,0.7070000171661377,0.7129999995231628,0.7120000123977661,0.7310000061988831,0.7229999899864197,0.7279999852180481,0.7260000109672546,0.718999981880188,0.7170000076293945,0.7210000157356262,0.718999981880188,0.7239999771118164,0.7379999756813049,0.7269999980926514,0.7250000238418579,0.7229999899864197,0.7300000190734863,0.722000002861023,0.7210000157356262,0.7279999852180481,0.7120000123977661,0.7210000157356262,0.7200000286102295,0.7260000109672546,0.718999981880188,0.7269999980926514,0.7200000286102295,0.7310000061988831,0.7269999980926514,0.7250000238418579,0.7229999899864197,0.7279999852180481,0.7329999804496765,0.7350000143051147,0.7310000061988831,0.7350000143051147,0.734000027179718,0.7289999723434448,0.7289999723434448,0.7239999771118164,0.7279999852180481,0.7350000143051147,0.7310000061988831,0.7350000143051147,0.734000027179718,0.7360000014305115,0.7390000224113464,0.7379999756813049,0.7369999885559082,0.7379999756813049,0.7360000014305115,0.7440000176429749,0.7289999723434448,0.7300000190734863,0.7369999885559082,0.7440000176429749,0.7390000224113464,0.734000027179718,0.7379999756813049,0.7350000143051147,0.7289999723434448,0.7409999966621399,0.7350000143051147,0.7300000190734863,0.7269999980926514,0.7360000014305115,0.7409999966621399,0.7310000061988831,0.734000027179718,0.7419999837875366,0.7350000143051147,0.7369999885559082,0.7379999756813049,0.7390000224113464,0.7329999804496765,0.7360000014305115,0.7390000224113464,0.7409999966621399,0.7409999966621399,0.7419999837875366,0.734000027179718,0.7480000257492065,0.7509999871253967,0.7409999966621399,0.7400000095367432,0.7440000176429749,0.734000027179718,0.7480000257492065,0.7329999804496765,0.7419999837875366,0.7390000224113464,0.7379999756813049,0.7419999837875366,0.7379999756813049,0.7429999709129333,0.7450000047683716,0.7409999966621399,0.7440000176429749,0.7480000257492065,0.7440000176429749,0.746999979019165,0.7409999966621399,0.7440000176429749,0.7459999918937683,0.746999979019165,0.7390000224113464,0.7440000176429749,0.7509999871253967,0.7429999709129333,0.7459999918937683,0.7429999709129333,0.7419999837875366,0.7490000128746033,0.746999979019165,0.7400000095367432,0.746999979019165,0.7490000128746033],"label":"FineWeb URL dedup"}},"piqa/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.6019999980926514,0.652999997138977,0.6710000038146973,0.6740000247955322,0.6899999976158142,0.6919999718666077,0.6909999847412109,0.7070000171661377,0.7089999914169312,0.7129999995231628,0.7229999899864197,0.7120000123977661,0.7200000286102295,0.7279999852180481,0.7369999885559082,0.7390000224113464,0.7350000143051147,0.7319999933242798,0.7279999852180481,0.7269999980926514,0.7459999918937683,0.7400000095367432,0.7390000224113464,0.7319999933242798,0.7390000224113464,0.7379999756813049,0.7390000224113464,0.7360000014305115,0.7440000176429749,0.7400000095367432,0.7360000014305115,0.7480000257492065,0.7360000014305115,0.7440000176429749,0.7459999918937683,0.7409999966621399,0.746999979019165,0.7440000176429749,0.7450000047683716,0.753000020980835,0.7390000224113464,0.7490000128746033,0.7419999837875366,0.7390000224113464,0.7559999823570251,0.7519999742507935,0.7549999952316284,0.7419999837875366,0.7490000128746033,0.7540000081062317,0.7480000257492065,0.7450000047683716,0.7429999709129333,0.7509999871253967,0.7549999952316284,0.7490000128746033,0.7490000128746033,0.7400000095367432,0.753000020980835,0.75,0.7509999871253967,0.7570000290870667,0.7590000033378601,0.7570000290870667,0.7329999804496765,0.7540000081062317,0.746999979019165,0.7409999966621399,0.7590000033378601,0.7509999871253967,0.7570000290870667,0.75,0.7540000081062317,0.7480000257492065,0.7580000162124634,0.7639999985694885,0.7630000114440918,0.7590000033378601,0.7549999952316284,0.7480000257492065,0.7509999871253967,0.7570000290870667,0.75,0.7540000081062317,0.7480000257492065,0.7549999952316284,0.7559999823570251,0.7580000162124634,0.7580000162124634,0.753000020980835,0.7490000128746033,0.7540000081062317,0.7639999985694885,0.7580000162124634,0.7519999742507935,0.7590000033378601,0.75,0.7570000290870667,0.7620000243186951,0.7710000276565552,0.7739999890327454,0.7620000243186951,0.7549999952316284,0.7599999904632568,0.765999972820282,0.7680000066757202,0.7639999985694885,0.7540000081062317,0.7649999856948853,0.7649999856948853,0.7609999775886536,0.7549999952316284,0.765999972820282,0.7639999985694885,0.7580000162124634,0.7710000276565552,0.7570000290870667,0.7630000114440918,0.7580000162124634,0.7599999904632568,0.7649999856948853,0.7670000195503235,0.7699999809265137,0.7710000276565552,0.7559999823570251,0.7609999775886536,0.7620000243186951,0.7620000243186951,0.7609999775886536,0.753000020980835,0.7570000290870667,0.7620000243186951,0.7609999775886536,0.7609999775886536,0.7559999823570251,0.7540000081062317,0.7570000290870667,0.7639999985694885,0.7590000033378601,0.7680000066757202,0.7680000066757202,0.765999972820282,0.765999972820282,0.7670000195503235,0.7739999890327454,0.7649999856948853,0.7749999761581421,0.7699999809265137,0.7639999985694885,0.7680000066757202,0.7630000114440918,0.7680000066757202,0.7699999809265137,0.7739999890327454,0.7749999761581421,0.765999972820282,0.7680000066757202,0.7710000276565552,0.7680000066757202,0.765999972820282,0.7689999938011169,0.7760000228881836,0.7710000276565552,0.7680000066757202,0.7649999856948853,0.7720000147819519,0.7730000019073486],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.6150000095367432,0.6449999809265137,0.6669999957084656,0.675000011920929,0.6909999847412109,0.703000009059906,0.6990000009536743,0.7160000205039978,0.7070000171661377,0.7120000123977661,0.7200000286102295,0.7139999866485596,0.7179999947547913,0.7149999737739563,0.7170000076293945,0.7210000157356262,0.7200000286102295,0.7149999737739563,0.7289999723434448,0.7229999899864197,0.7179999947547913,0.7179999947547913,0.7200000286102295,0.7289999723434448,0.722000002861023,0.7229999899864197,0.7179999947547913,0.7139999866485596,0.7239999771118164,0.7200000286102295,0.7250000238418579,0.7260000109672546,0.7139999866485596,0.7239999771118164,0.7260000109672546,0.7239999771118164,0.7269999980926514,0.7310000061988831,0.718999981880188,0.7260000109672546,0.7310000061988831,0.7329999804496765,0.7289999723434448,0.7350000143051147,0.7440000176429749,0.7300000190734863,0.7319999933242798,0.7250000238418579,0.7319999933242798,0.7419999837875366,0.7360000014305115,0.7260000109672546,0.7350000143051147,0.7390000224113464,0.7440000176429749,0.7400000095367432,0.7379999756813049,0.7279999852180481,0.7440000176429749,0.7289999723434448,0.746999979019165,0.7329999804496765,0.7419999837875366,0.7390000224113464,0.7250000238418579,0.7429999709129333,0.7329999804496765,0.7350000143051147,0.7360000014305115,0.7450000047683716,0.7390000224113464,0.7409999966621399,0.7390000224113464,0.7350000143051147,0.7329999804496765,0.734000027179718,0.7459999918937683,0.7440000176429749,0.75,0.7379999756813049,0.7450000047683716,0.7450000047683716,0.7419999837875366,0.7459999918937683,0.746999979019165,0.7400000095367432,0.7310000061988831,0.7450000047683716,0.7409999966621399,0.7450000047683716,0.746999979019165,0.75,0.75,0.753000020980835,0.7519999742507935,0.7450000047683716,0.7450000047683716,0.7549999952316284,0.7429999709129333,0.75,0.746999979019165,0.7540000081062317,0.7599999904632568,0.7559999823570251,0.746999979019165,0.7559999823570251,0.7540000081062317,0.7570000290870667,0.7490000128746033,0.746999979019165,0.7509999871253967,0.7519999742507935,0.7540000081062317,0.7570000290870667,0.746999979019165,0.7570000290870667,0.7480000257492065,0.7580000162124634,0.7570000290870667,0.7580000162124634,0.7519999742507935,0.7459999918937683,0.7599999904632568,0.7580000162124634,0.7509999871253967,0.7540000081062317,0.7580000162124634,0.753000020980835,0.7429999709129333,0.7480000257492065,0.7480000257492065,0.7549999952316284,0.7570000290870667,0.7609999775886536,0.7549999952316284,0.7580000162124634,0.7620000243186951,0.7599999904632568,0.753000020980835,0.7540000081062317,0.7599999904632568,0.7580000162124634,0.7459999918937683,0.7580000162124634,0.7549999952316284,0.7590000033378601,0.7599999904632568,0.7570000290870667,0.7599999904632568,0.7559999823570251,0.7630000114440918,0.7549999952316284,0.7609999775886536,0.7609999775886536,0.7549999952316284,0.7540000081062317,0.7590000033378601,0.7540000081062317,0.753000020980835,0.7590000033378601,0.75,0.7599999904632568,0.7580000162124634,0.7559999823570251,0.7519999742507935,0.7599999904632568,0.7580000162124634],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.621999979019165,0.6439999938011169,0.6700000166893005,0.6790000200271606,0.6869999766349792,0.6959999799728394,0.6790000200271606,0.6880000233650208,0.7049999833106995,0.699999988079071,0.6990000009536743,0.6940000057220459,0.7110000252723694,0.7120000123977661,0.7070000171661377,0.7070000171661377,0.6990000009536743,0.7009999752044678,0.7160000205039978,0.7200000286102295,0.7149999737739563,0.7250000238418579,0.7210000157356262,0.722000002861023,0.7310000061988831,0.7289999723434448,0.7319999933242798,0.7250000238418579,0.722000002861023,0.7210000157356262,0.7170000076293945,0.7260000109672546,0.7250000238418579,0.7210000157356262,0.7200000286102295,0.7379999756813049,0.7239999771118164,0.7239999771118164,0.7080000042915344,0.7289999723434448,0.7289999723434448,0.7300000190734863,0.7329999804496765,0.7319999933242798,0.7350000143051147,0.7390000224113464,0.7350000143051147,0.7289999723434448,0.734000027179718,0.7329999804496765,0.7400000095367432,0.7409999966621399,0.7310000061988831,0.7350000143051147,0.7360000014305115,0.7360000014305115,0.7409999966621399,0.7319999933242798,0.7409999966621399,0.7400000095367432,0.7390000224113464,0.7329999804496765,0.7459999918937683,0.753000020980835,0.746999979019165,0.734000027179718,0.7369999885559082,0.7419999837875366,0.734000027179718,0.7419999837875366,0.7289999723434448,0.7350000143051147,0.7300000190734863,0.7519999742507935,0.7390000224113464,0.7400000095367432,0.7409999966621399,0.7429999709129333,0.7450000047683716,0.7329999804496765,0.7260000109672546,0.7570000290870667,0.7360000014305115,0.7519999742507935,0.7419999837875366,0.7379999756813049,0.7390000224113464,0.7490000128746033,0.734000027179718,0.7360000014305115,0.7390000224113464,0.7440000176429749,0.7450000047683716,0.7319999933242798,0.7429999709129333,0.7519999742507935,0.7540000081062317,0.7519999742507935,0.753000020980835,0.7480000257492065,0.7440000176429749,0.7459999918937683,0.7369999885559082,0.7419999837875366,0.7480000257492065,0.7419999837875366,0.765999972820282,0.746999979019165,0.7459999918937683,0.7570000290870667,0.7390000224113464,0.7409999966621399,0.7459999918937683,0.75,0.7570000290870667,0.753000020980835,0.7549999952316284,0.7519999742507935,0.7490000128746033,0.746999979019165,0.7459999918937683,0.7459999918937683,0.746999979019165,0.7409999966621399,0.7419999837875366,0.7459999918937683,0.7440000176429749,0.7459999918937683,0.7490000128746033,0.7450000047683716,0.7409999966621399,0.7419999837875366,0.7490000128746033,0.7590000033378601,0.7549999952316284,0.7549999952316284,0.746999979019165,0.753000020980835,0.7549999952316284,0.746999979019165,0.7580000162124634,0.7490000128746033,0.753000020980835,0.75,0.75,0.7540000081062317,0.7540000081062317,0.7490000128746033,0.7570000290870667,0.7570000290870667,0.7590000033378601,0.7559999823570251,0.7620000243186951,0.7590000033378601,0.7509999871253967,0.7639999985694885,0.7580000162124634,0.7599999904632568,0.7620000243186951,0.7590000033378601,0.7609999775886536,0.7559999823570251,0.75,0.7509999871253967,0.7549999952316284,0.7540000081062317,0.7540000081062317],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.6050000190734863,0.6420000195503235,0.6589999794960022,0.6740000247955322,0.6809999942779541,0.6919999718666077,0.6940000057220459,0.699999988079071,0.7110000252723694,0.7110000252723694,0.7049999833106995,0.7059999704360962,0.7089999914169312,0.7099999785423279,0.7210000157356262,0.7149999737739563,0.7210000157356262,0.7129999995231628,0.7210000157356262,0.7089999914169312,0.7170000076293945,0.7210000157356262,0.7250000238418579,0.7329999804496765,0.7070000171661377,0.7170000076293945,0.7200000286102295,0.7160000205039978,0.7269999980926514,0.7279999852180481,0.7239999771118164,0.7269999980926514,0.7110000252723694,0.7360000014305115,0.7239999771118164,0.7350000143051147,0.7250000238418579,0.7289999723434448,0.7310000061988831,0.718999981880188,0.7260000109672546,0.7369999885559082,0.7369999885559082,0.7400000095367432,0.734000027179718,0.7350000143051147,0.7310000061988831,0.7310000061988831,0.7239999771118164,0.7279999852180481,0.7360000014305115,0.7279999852180481,0.7440000176429749,0.7450000047683716,0.7409999966621399,0.7360000014305115,0.7379999756813049,0.7300000190734863,0.7440000176429749,0.7390000224113464,0.7459999918937683,0.7379999756813049,0.7480000257492065,0.7310000061988831,0.7390000224113464,0.746999979019165,0.7549999952316284,0.7400000095367432,0.7459999918937683,0.7459999918937683,0.7509999871253967,0.7419999837875366,0.7509999871253967,0.7480000257492065,0.7390000224113464,0.7570000290870667,0.7480000257492065,0.7480000257492065,0.7580000162124634,0.7590000033378601,0.7519999742507935,0.7519999742507935,0.753000020980835,0.753000020980835,0.7580000162124634,0.75,0.7509999871253967,0.7580000162124634,0.753000020980835,0.7620000243186951,0.7490000128746033,0.746999979019165,0.7509999871253967,0.7459999918937683,0.7519999742507935,0.7549999952316284,0.7419999837875366,0.7490000128746033,0.7419999837875366,0.7570000290870667,0.7609999775886536,0.7540000081062317,0.7570000290870667,0.7540000081062317,0.7509999871253967,0.7480000257492065,0.7609999775886536,0.7620000243186951,0.7609999775886536,0.7570000290870667,0.7559999823570251,0.7559999823570251,0.7509999871253967,0.7570000290870667,0.7590000033378601,0.7590000033378601,0.7559999823570251,0.7570000290870667,0.7540000081062317,0.7609999775886536,0.7620000243186951,0.7590000033378601,0.7630000114440918,0.7639999985694885,0.765999972820282,0.7630000114440918,0.765999972820282,0.7680000066757202,0.7559999823570251,0.7609999775886536,0.7649999856948853,0.7699999809265137,0.7630000114440918,0.7670000195503235,0.7630000114440918,0.7639999985694885,0.7639999985694885,0.7699999809265137,0.7720000147819519,0.7639999985694885,0.7680000066757202,0.7739999890327454,0.7620000243186951,0.7749999761581421,0.7710000276565552,0.7760000228881836,0.7670000195503235,0.7720000147819519,0.781000018119812,0.7710000276565552,0.7699999809265137,0.7730000019073486,0.7739999890327454,0.7689999938011169,0.7670000195503235,0.765999972820282,0.765999972820282,0.7689999938011169,0.7620000243186951,0.7649999856948853,0.765999972820282,0.7630000114440918,0.7770000100135803,0.7710000276565552,0.7730000019073486,0.7749999761581421,0.7789999842643738],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.6209999918937683,0.6549999713897705,0.6800000071525574,0.6830000281333923,0.703000009059906,0.7020000219345093,0.7110000252723694,0.7160000205039978,0.7129999995231628,0.7210000157356262,0.7250000238418579,0.7210000157356262,0.7310000061988831,0.7269999980926514,0.7329999804496765,0.7459999918937683,0.734000027179718,0.7409999966621399,0.7390000224113464,0.7350000143051147,0.7509999871253967,0.7440000176429749,0.7379999756813049,0.7599999904632568,0.7400000095367432,0.7409999966621399,0.7590000033378601,0.7409999966621399,0.7440000176429749,0.7400000095367432,0.7450000047683716,0.75,0.7440000176429749,0.7409999966621399,0.7429999709129333,0.7440000176429749,0.7440000176429749,0.7559999823570251,0.7459999918937683,0.7559999823570251,0.7540000081062317,0.7599999904632568,0.7559999823570251,0.7490000128746033,0.7490000128746033,0.7429999709129333,0.7609999775886536,0.7519999742507935,0.7480000257492065,0.7490000128746033,0.7620000243186951,0.7580000162124634,0.7580000162124634,0.7540000081062317,0.7509999871253967,0.7519999742507935,0.7440000176429749,0.7459999918937683,0.7559999823570251,0.7620000243186951,0.746999979019165,0.7570000290870667,0.7620000243186951,0.7570000290870667,0.7540000081062317,0.7540000081062317,0.7570000290870667,0.7590000033378601,0.7519999742507935,0.75,0.7559999823570251,0.7590000033378601,0.7559999823570251,0.7519999742507935,0.7639999985694885,0.7620000243186951,0.7549999952316284,0.7490000128746033,0.7559999823570251,0.7639999985694885,0.7609999775886536,0.7609999775886536,0.7519999742507935,0.7549999952316284,0.7570000290870667,0.7620000243186951,0.7599999904632568,0.7639999985694885,0.7559999823570251,0.753000020980835,0.7649999856948853,0.753000020980835,0.7549999952316284,0.7609999775886536,0.7599999904632568,0.7680000066757202,0.7540000081062317,0.7559999823570251,0.7590000033378601,0.7590000033378601,0.7649999856948853,0.7639999985694885,0.7710000276565552,0.7699999809265137,0.7609999775886536,0.765999972820282,0.7670000195503235,0.7720000147819519,0.7639999985694885,0.7609999775886536,0.7549999952316284,0.7630000114440918,0.7670000195503235,0.7599999904632568,0.765999972820282,0.7670000195503235,0.7670000195503235,0.7670000195503235,0.7720000147819519,0.7760000228881836,0.7710000276565552,0.7829999923706055,0.7630000114440918,0.7720000147819519,0.7649999856948853,0.7630000114440918,0.7699999809265137,0.7720000147819519,0.7720000147819519,0.7689999938011169,0.777999997138977,0.7689999938011169,0.7760000228881836,0.7730000019073486,0.7799999713897705,0.7720000147819519,0.7760000228881836,0.7710000276565552,0.7770000100135803,0.777999997138977,0.7670000195503235,0.7789999842643738,0.7799999713897705,0.7749999761581421,0.7730000019073486,0.777999997138977,0.777999997138977,0.7799999713897705,0.7770000100135803,0.7770000100135803,0.7789999842643738,0.7760000228881836,0.7770000100135803,0.7770000100135803,0.7770000100135803,0.7739999890327454,0.7689999938011169,0.7760000228881836,0.777999997138977,0.7699999809265137,0.7739999890327454,0.7670000195503235,0.7699999809265137,0.7710000276565552,0.7730000019073486,0.7739999890327454,0.7680000066757202],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.6060000061988831,0.6380000114440918,0.6589999794960022,0.6629999876022339,0.6909999847412109,0.6859999895095825,0.699999988079071,0.703000009059906,0.7070000171661377,0.7149999737739563,0.7059999704360962,0.7149999737739563,0.7170000076293945,0.7170000076293945,0.7059999704360962,0.7129999995231628,0.7070000171661377,0.7070000171661377,0.7160000205039978,0.7129999995231628,0.6990000009536743,0.7120000123977661,0.7129999995231628,0.7170000076293945,0.7210000157356262,0.7160000205039978,0.7149999737739563,0.7239999771118164,0.7229999899864197,0.7250000238418579,0.7110000252723694,0.7170000076293945,0.7129999995231628,0.7250000238418579,0.7260000109672546,0.7269999980926514,0.7300000190734863,0.7329999804496765,0.7289999723434448,0.7289999723434448,0.7210000157356262,0.7210000157356262,0.7319999933242798,0.7350000143051147,0.7279999852180481,0.7310000061988831,0.7319999933242798,0.7260000109672546,0.7329999804496765,0.7329999804496765,0.7360000014305115,0.7329999804496765,0.7279999852180481,0.7390000224113464,0.7480000257492065,0.7319999933242798,0.7279999852180481,0.7450000047683716,0.734000027179718,0.7379999756813049,0.7289999723434448,0.7360000014305115,0.7350000143051147,0.7369999885559082,0.7400000095367432,0.7450000047683716,0.7310000061988831,0.7300000190734863,0.7300000190734863,0.7400000095367432,0.7350000143051147,0.7369999885559082,0.7379999756813049,0.7450000047683716,0.7429999709129333,0.7329999804496765,0.7369999885559082,0.7360000014305115,0.7480000257492065,0.7400000095367432,0.7519999742507935,0.7440000176429749,0.7419999837875366,0.7480000257492065,0.7400000095367432,0.7390000224113464,0.7450000047683716,0.7319999933242798,0.7519999742507935,0.746999979019165,0.7490000128746033,0.75,0.7459999918937683,0.7419999837875366,0.7429999709129333,0.7480000257492065,0.7459999918937683,0.753000020980835,0.753000020980835,0.75,0.7509999871253967,0.7540000081062317,0.7599999904632568,0.7559999823570251,0.7580000162124634,0.7519999742507935,0.7509999871253967,0.7509999871253967,0.7590000033378601,0.75,0.7549999952316284,0.7649999856948853,0.7509999871253967,0.7620000243186951,0.7599999904632568,0.7609999775886536,0.7559999823570251,0.7419999837875366,0.746999979019165,0.7559999823570251,0.7509999871253967,0.7559999823570251,0.7570000290870667,0.753000020980835,0.7519999742507935,0.7559999823570251,0.7549999952316284,0.7559999823570251,0.7590000033378601,0.7540000081062317,0.7580000162124634,0.753000020980835,0.7559999823570251,0.7540000081062317,0.753000020980835,0.7480000257492065,0.7519999742507935,0.7509999871253967,0.7519999742507935,0.75,0.7609999775886536,0.7549999952316284,0.7630000114440918,0.7590000033378601,0.7649999856948853,0.7559999823570251,0.7580000162124634,0.7570000290870667,0.7570000290870667,0.7559999823570251,0.7549999952316284,0.7540000081062317,0.7609999775886536,0.7639999985694885,0.7620000243186951,0.7559999823570251,0.7580000162124634,0.7540000081062317,0.7620000243186951,0.7599999904632568,0.7599999904632568,0.7599999904632568,0.7570000290870667,0.7599999904632568,0.7609999775886536,0.7559999823570251,0.7570000290870667],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.6240000128746033,0.6470000147819519,0.6520000100135803,0.6700000166893005,0.6940000057220459,0.6970000267028809,0.6970000267028809,0.699999988079071,0.6890000104904175,0.6909999847412109,0.7089999914169312,0.7099999785423279,0.7059999704360962,0.7120000123977661,0.7070000171661377,0.7039999961853027,0.7210000157356262,0.7269999980926514,0.7160000205039978,0.7279999852180481,0.7260000109672546,0.7210000157356262,0.7200000286102295,0.722000002861023,0.7229999899864197,0.7310000061988831,0.722000002861023,0.7229999899864197,0.7400000095367432,0.7289999723434448,0.7390000224113464,0.7379999756813049,0.7390000224113464,0.7350000143051147,0.734000027179718,0.7329999804496765,0.7310000061988831,0.7269999980926514,0.7369999885559082,0.734000027179718,0.7409999966621399,0.7390000224113464,0.7300000190734863,0.734000027179718,0.7329999804496765,0.7310000061988831,0.7379999756813049,0.734000027179718,0.7329999804496765,0.7239999771118164,0.7289999723434448,0.7310000061988831,0.7289999723434448,0.7319999933242798,0.7279999852180481,0.7379999756813049,0.75,0.7419999837875366,0.734000027179718,0.75,0.753000020980835,0.7559999823570251,0.7419999837875366,0.7480000257492065,0.7400000095367432,0.7390000224113464,0.7429999709129333,0.7459999918937683,0.7360000014305115,0.7390000224113464,0.7459999918937683,0.7429999709129333,0.7509999871253967,0.7379999756813049,0.7360000014305115,0.7409999966621399,0.7450000047683716,0.7419999837875366,0.7400000095367432,0.7509999871253967,0.7450000047683716,0.7459999918937683,0.753000020980835,0.7490000128746033,0.7549999952316284,0.7440000176429749,0.7480000257492065,0.7440000176429749,0.753000020980835,0.7440000176429749,0.746999979019165,0.7490000128746033,0.7459999918937683,0.7509999871253967,0.746999979019165,0.7549999952316284,0.7480000257492065,0.7480000257492065,0.7519999742507935,0.7580000162124634,0.7620000243186951,0.7519999742507935,0.7390000224113464,0.7570000290870667,0.7509999871253967,0.7559999823570251,0.7480000257492065,0.7459999918937683,0.753000020980835,0.7570000290870667,0.753000020980835,0.7630000114440918,0.7540000081062317,0.7440000176429749,0.7620000243186951,0.7590000033378601,0.7570000290870667,0.7570000290870667,0.7609999775886536,0.7620000243186951,0.7570000290870667,0.7549999952316284,0.7670000195503235,0.7670000195503235,0.7599999904632568,0.7599999904632568,0.7670000195503235,0.7609999775886536,0.7540000081062317,0.7670000195503235,0.7670000195503235,0.7609999775886536,0.7680000066757202,0.7720000147819519,0.7680000066757202,0.7630000114440918,0.7670000195503235,0.7699999809265137,0.7609999775886536,0.7649999856948853,0.7649999856948853,0.7599999904632568,0.7549999952316284,0.7599999904632568,0.7519999742507935,0.7620000243186951,0.7649999856948853,0.7639999985694885,0.7639999985694885,0.7620000243186951,0.7620000243186951,0.7580000162124634,0.7680000066757202,0.7649999856948853,0.7639999985694885,0.7749999761581421,0.7649999856948853,0.7609999775886536,0.7620000243186951,0.7609999775886536,0.7670000195503235,0.7670000195503235,0.7649999856948853,0.7739999890327454,0.7599999904632568,0.7630000114440918,0.765999972820282],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.5099999904632568,0.6150000095367432,0.6420000195503235,0.6850000023841858,0.6759999990463257,0.6949999928474426,0.6949999928474426,0.7020000219345093,0.6959999799728394,0.7059999704360962,0.7099999785423279,0.7009999752044678,0.7129999995231628,0.7089999914169312,0.7229999899864197,0.703000009059906,0.7099999785423279,0.7080000042915344,0.7250000238418579,0.7080000042915344,0.7200000286102295,0.7239999771118164,0.7210000157356262,0.7099999785423279,0.7210000157356262,0.7210000157356262,0.7360000014305115,0.718999981880188,0.7269999980926514,0.7229999899864197,0.7160000205039978,0.7260000109672546,0.7300000190734863,0.7279999852180481,0.7350000143051147,0.7310000061988831,0.7279999852180481,0.7279999852180481,0.7369999885559082,0.7440000176429749,0.7300000190734863,0.7390000224113464,0.7369999885559082,0.7409999966621399,0.7409999966621399,0.7310000061988831,0.7360000014305115,0.7419999837875366,0.7450000047683716,0.7429999709129333,0.7409999966621399,0.7429999709129333,0.7559999823570251,0.7459999918937683,0.75,0.75,0.75,0.7390000224113464,0.7450000047683716,0.7419999837875366,0.7459999918937683,0.7480000257492065,0.7450000047683716,0.7570000290870667,0.746999979019165,0.7519999742507935,0.7519999742507935,0.7570000290870667,0.7549999952316284,0.7549999952316284,0.7549999952316284,0.75,0.7519999742507935,0.7680000066757202,0.7620000243186951,0.7639999985694885,0.7509999871253967,0.7490000128746033,0.753000020980835,0.7549999952316284,0.7580000162124634,0.7570000290870667,0.7590000033378601,0.7509999871253967,0.7549999952316284,0.7649999856948853,0.7570000290870667,0.7670000195503235,0.7540000081062317,0.7519999742507935,0.7490000128746033,0.7580000162124634,0.7630000114440918,0.7429999709129333,0.7440000176429749,0.7509999871253967,0.753000020980835,0.7540000081062317,0.7590000033378601,0.7509999871253967,0.7549999952316284,0.7570000290870667,0.7559999823570251,0.7590000033378601,0.7580000162124634,0.7699999809265137,0.7630000114440918,0.7630000114440918,0.75,0.7649999856948853,0.7639999985694885,0.753000020980835,0.7639999985694885,0.7540000081062317,0.7549999952316284,0.7620000243186951,0.7649999856948853,0.7599999904632568,0.7639999985694885,0.7549999952316284,0.7639999985694885,0.7639999985694885,0.7639999985694885,0.7689999938011169,0.765999972820282,0.7630000114440918,0.7580000162124634,0.765999972820282,0.7699999809265137,0.7630000114440918,0.7699999809265137,0.7639999985694885,0.7710000276565552,0.7699999809265137,0.7639999985694885,0.7620000243186951,0.7630000114440918,0.7599999904632568,0.7630000114440918,0.7549999952316284,0.7699999809265137,0.7720000147819519,0.7670000195503235,0.7630000114440918,0.7620000243186951,0.7720000147819519,0.7649999856948853,0.7720000147819519,0.7649999856948853,0.7649999856948853,0.7630000114440918,0.765999972820282,0.7680000066757202,0.7630000114440918,0.7789999842643738,0.7739999890327454,0.7689999938011169,0.7689999938011169,0.7820000052452087,0.7770000100135803,0.777999997138977,0.7739999890327454,0.7710000276565552,0.7720000147819519,0.7699999809265137,0.7720000147819519,0.765999972820282,0.7730000019073486],"label":"FineWeb URL dedup"}},"siqa/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3650000095367431,0.3680000007152557,0.3759999871253967,0.3709999918937683,0.375,0.3919999897480011,0.3880000114440918,0.3919999897480011,0.3980000019073486,0.3939999938011169,0.3930000066757202,0.3869999945163727,0.3919999897480011,0.3919999897480011,0.3939999938011169,0.382999986410141,0.3930000066757202,0.3970000147819519,0.395000010728836,0.3939999938011169,0.3939999938011169,0.3939999938011169,0.4059999883174896,0.4000000059604645,0.3899999856948852,0.4009999930858612,0.3980000019073486,0.3899999856948852,0.4050000011920929,0.3959999978542328,0.4050000011920929,0.4040000140666961,0.4000000059604645,0.3889999985694885,0.3980000019073486,0.3939999938011169,0.3959999978542328,0.3930000066757202,0.4009999930858612,0.4090000092983246,0.402999997138977,0.4079999923706054,0.3959999978542328,0.4090000092983246,0.3959999978542328,0.4009999930858612,0.4070000052452087,0.4090000092983246,0.4169999957084656,0.402999997138977,0.4070000052452087,0.4020000100135803,0.3980000019073486,0.4050000011920929,0.3959999978542328,0.3989999890327453,0.402999997138977,0.4020000100135803,0.402999997138977,0.402999997138977,0.3959999978542328,0.4040000140666961,0.4050000011920929,0.4000000059604645,0.402999997138977,0.4059999883174896,0.402999997138977,0.3970000147819519,0.4070000052452087,0.3989999890327453,0.3930000066757202,0.4000000059604645,0.4040000140666961,0.4079999923706054,0.4009999930858612,0.3910000026226043,0.3989999890327453,0.3959999978542328,0.414000004529953,0.4009999930858612,0.4050000011920929,0.4000000059604645,0.4110000133514404,0.4059999883174896,0.402999997138977,0.402999997138977,0.4079999923706054,0.395000010728836,0.4110000133514404,0.4110000133514404,0.4079999923706054,0.4050000011920929,0.4099999964237213,0.4040000140666961,0.4110000133514404,0.4059999883174896,0.3980000019073486,0.3989999890327453,0.4040000140666961,0.414000004529953,0.4009999930858612,0.4009999930858612,0.4009999930858612,0.4009999930858612,0.4059999883174896,0.4009999930858612,0.3959999978542328,0.4070000052452087,0.4059999883174896,0.4120000004768371,0.4110000133514404,0.3889999985694885,0.4090000092983246,0.4120000004768371,0.4079999923706054,0.4040000140666961,0.4079999923706054,0.4070000052452087,0.4129999876022339,0.4169999957084656,0.4070000052452087,0.4180000126361847,0.4129999876022339,0.414000004529953,0.4079999923706054,0.4110000133514404,0.4040000140666961,0.4079999923706054,0.4070000052452087,0.4009999930858612,0.4059999883174896,0.4099999964237213,0.4090000092983246,0.402999997138977,0.4050000011920929,0.4099999964237213,0.4110000133514404,0.3980000019073486,0.4070000052452087,0.4079999923706054,0.4129999876022339,0.4020000100135803,0.4129999876022339,0.4099999964237213,0.4120000004768371,0.414000004529953,0.4090000092983246,0.4070000052452087,0.4160000085830688,0.4079999923706054,0.4059999883174896,0.4129999876022339,0.402999997138977,0.4120000004768371,0.4040000140666961,0.4120000004768371,0.4120000004768371,0.4160000085830688,0.4110000133514404,0.4120000004768371,0.4099999964237213,0.4180000126361847,0.4079999923706054,0.4059999883174896,0.4090000092983246,0.402999997138977,0.4099999964237213],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3600000143051147,0.3770000040531158,0.3729999959468841,0.3869999945163727,0.3680000007152557,0.3849999904632568,0.3779999911785126,0.3880000114440918,0.3899999856948852,0.3899999856948852,0.3930000066757202,0.3930000066757202,0.3889999985694885,0.3889999985694885,0.3880000114440918,0.3889999985694885,0.3989999890327453,0.3970000147819519,0.3899999856948852,0.395000010728836,0.4040000140666961,0.3889999985694885,0.4040000140666961,0.3849999904632568,0.3970000147819519,0.3970000147819519,0.3889999985694885,0.3840000033378601,0.3779999911785126,0.382999986410141,0.3880000114440918,0.3959999978542328,0.3889999985694885,0.3770000040531158,0.3840000033378601,0.3849999904632568,0.3810000121593475,0.3899999856948852,0.3860000073909759,0.3849999904632568,0.3899999856948852,0.3860000073909759,0.3860000073909759,0.3819999992847442,0.3889999985694885,0.3860000073909759,0.3770000040531158,0.395000010728836,0.3889999985694885,0.3889999985694885,0.3910000026226043,0.3790000081062317,0.3860000073909759,0.3880000114440918,0.382999986410141,0.3959999978542328,0.3819999992847442,0.3849999904632568,0.3720000088214874,0.3930000066757202,0.3939999938011169,0.3889999985694885,0.3980000019073486,0.4040000140666961,0.3880000114440918,0.3930000066757202,0.3869999945163727,0.3970000147819519,0.3880000114440918,0.382999986410141,0.3919999897480011,0.3939999938011169,0.3880000114440918,0.3849999904632568,0.402999997138977,0.3889999985694885,0.4000000059604645,0.395000010728836,0.3959999978542328,0.3959999978542328,0.4099999964237213,0.3880000114440918,0.4059999883174896,0.395000010728836,0.4009999930858612,0.4009999930858612,0.395000010728836,0.3959999978542328,0.4040000140666961,0.3939999938011169,0.4009999930858612,0.402999997138977,0.4020000100135803,0.4090000092983246,0.395000010728836,0.3930000066757202,0.3899999856948852,0.3989999890327453,0.4070000052452087,0.395000010728836,0.3970000147819519,0.402999997138977,0.3980000019073486,0.4020000100135803,0.4000000059604645,0.3959999978542328,0.395000010728836,0.3930000066757202,0.4090000092983246,0.395000010728836,0.395000010728836,0.3930000066757202,0.3980000019073486,0.3939999938011169,0.3989999890327453,0.4020000100135803,0.3939999938011169,0.3970000147819519,0.4020000100135803,0.4009999930858612,0.3970000147819519,0.3939999938011169,0.3959999978542328,0.3939999938011169,0.3939999938011169,0.382999986410141,0.3939999938011169,0.395000010728836,0.3970000147819519,0.3939999938011169,0.3980000019073486,0.3899999856948852,0.3899999856948852,0.3959999978542328,0.3939999938011169,0.3989999890327453,0.3930000066757202,0.3970000147819519,0.395000010728836,0.395000010728836,0.4020000100135803,0.3939999938011169,0.402999997138977,0.402999997138977,0.395000010728836,0.3939999938011169,0.4009999930858612,0.4000000059604645,0.3910000026226043,0.3869999945163727,0.3869999945163727,0.3910000026226043,0.4000000059604645,0.3959999978542328,0.4009999930858612,0.4040000140666961,0.3989999890327453,0.3899999856948852,0.4009999930858612,0.4009999930858612,0.3989999890327453,0.3939999938011169,0.3910000026226043,0.4000000059604645,0.4009999930858612,0.4009999930858612,0.402999997138977],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3619999885559082,0.3650000095367431,0.3709999918937683,0.3799999952316284,0.375,0.375,0.3799999952316284,0.382999986410141,0.3899999856948852,0.3970000147819519,0.3919999897480011,0.3919999897480011,0.3790000081062317,0.382999986410141,0.3939999938011169,0.3959999978542328,0.4020000100135803,0.3889999985694885,0.3980000019073486,0.4040000140666961,0.3919999897480011,0.3930000066757202,0.3980000019073486,0.3860000073909759,0.3860000073909759,0.3919999897480011,0.3930000066757202,0.3910000026226043,0.3790000081062317,0.3869999945163727,0.3899999856948852,0.3939999938011169,0.402999997138977,0.3899999856948852,0.395000010728836,0.3880000114440918,0.3840000033378601,0.3919999897480011,0.4000000059604645,0.3989999890327453,0.3939999938011169,0.3959999978542328,0.3930000066757202,0.3970000147819519,0.3959999978542328,0.4009999930858612,0.4120000004768371,0.3939999938011169,0.3899999856948852,0.3989999890327453,0.382999986410141,0.3880000114440918,0.382999986410141,0.3959999978542328,0.3880000114440918,0.3980000019073486,0.3930000066757202,0.395000010728836,0.4000000059604645,0.395000010728836,0.4000000059604645,0.3840000033378601,0.4020000100135803,0.3799999952316284,0.3959999978542328,0.3899999856948852,0.3919999897480011,0.3869999945163727,0.395000010728836,0.395000010728836,0.3899999856948852,0.3989999890327453,0.3939999938011169,0.3930000066757202,0.3939999938011169,0.3919999897480011,0.3910000026226043,0.4050000011920929,0.4009999930858612,0.395000010728836,0.402999997138977,0.395000010728836,0.3980000019073486,0.395000010728836,0.3989999890327453,0.3959999978542328,0.3919999897480011,0.3910000026226043,0.3889999985694885,0.4000000059604645,0.382999986410141,0.395000010728836,0.4000000059604645,0.3959999978542328,0.3919999897480011,0.3930000066757202,0.3939999938011169,0.3970000147819519,0.3939999938011169,0.3970000147819519,0.4059999883174896,0.3970000147819519,0.4009999930858612,0.402999997138977,0.4020000100135803,0.4000000059604645,0.3869999945163727,0.4009999930858612,0.3939999938011169,0.3919999897480011,0.3939999938011169,0.3939999938011169,0.3939999938011169,0.3939999938011169,0.4020000100135803,0.402999997138977,0.3980000019073486,0.4020000100135803,0.3970000147819519,0.3970000147819519,0.3980000019073486,0.3989999890327453,0.402999997138977,0.4009999930858612,0.3939999938011169,0.395000010728836,0.4020000100135803,0.3989999890327453,0.3989999890327453,0.3980000019073486,0.3989999890327453,0.3930000066757202,0.4050000011920929,0.4000000059604645,0.3889999985694885,0.4009999930858612,0.3970000147819519,0.3970000147819519,0.402999997138977,0.4000000059604645,0.4000000059604645,0.395000010728836,0.3970000147819519,0.3980000019073486,0.3989999890327453,0.3889999985694885,0.3930000066757202,0.395000010728836,0.3959999978542328,0.3889999985694885,0.3930000066757202,0.395000010728836,0.3970000147819519,0.395000010728836,0.4020000100135803,0.3970000147819519,0.3970000147819519,0.3959999978542328,0.3959999978542328,0.3959999978542328,0.3989999890327453,0.4000000059604645,0.3889999985694885,0.3910000026226043,0.3889999985694885,0.3919999897480011,0.3919999897480011],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3529999852180481,0.3720000088214874,0.3770000040531158,0.3689999878406524,0.375,0.3779999911785126,0.3689999878406524,0.382999986410141,0.3899999856948852,0.3889999985694885,0.3799999952316284,0.3770000040531158,0.3880000114440918,0.3849999904632568,0.3880000114440918,0.3910000026226043,0.3810000121593475,0.3989999890327453,0.3970000147819519,0.3889999985694885,0.3860000073909759,0.3989999890327453,0.3939999938011169,0.3980000019073486,0.3919999897480011,0.3919999897480011,0.4009999930858612,0.3970000147819519,0.402999997138977,0.4009999930858612,0.4009999930858612,0.3860000073909759,0.4009999930858612,0.3899999856948852,0.3970000147819519,0.3910000026226043,0.4020000100135803,0.4000000059604645,0.3989999890327453,0.3869999945163727,0.402999997138977,0.3930000066757202,0.3840000033378601,0.3889999985694885,0.3930000066757202,0.3930000066757202,0.3959999978542328,0.4070000052452087,0.3959999978542328,0.3869999945163727,0.3880000114440918,0.4040000140666961,0.3959999978542328,0.3919999897480011,0.4000000059604645,0.3930000066757202,0.3919999897480011,0.4020000100135803,0.3860000073909759,0.395000010728836,0.3959999978542328,0.4009999930858612,0.3930000066757202,0.3970000147819519,0.3910000026226043,0.3910000026226043,0.3899999856948852,0.4000000059604645,0.3939999938011169,0.3959999978542328,0.3889999985694885,0.3980000019073486,0.3910000026226043,0.3980000019073486,0.3930000066757202,0.3939999938011169,0.3810000121593475,0.3889999985694885,0.3959999978542328,0.3970000147819519,0.3899999856948852,0.3970000147819519,0.3970000147819519,0.3889999985694885,0.4009999930858612,0.3880000114440918,0.3970000147819519,0.3860000073909759,0.3910000026226043,0.4000000059604645,0.3989999890327453,0.3970000147819519,0.4059999883174896,0.3970000147819519,0.4000000059604645,0.4009999930858612,0.4000000059604645,0.3930000066757202,0.3919999897480011,0.3970000147819519,0.4000000059604645,0.4070000052452087,0.3989999890327453,0.4090000092983246,0.3959999978542328,0.3930000066757202,0.4040000140666961,0.4020000100135803,0.4000000059604645,0.3989999890327453,0.4000000059604645,0.3989999890327453,0.3980000019073486,0.3989999890327453,0.4000000059604645,0.4020000100135803,0.3860000073909759,0.3919999897480011,0.4009999930858612,0.3970000147819519,0.3939999938011169,0.3989999890327453,0.3939999938011169,0.3919999897480011,0.3959999978542328,0.4000000059604645,0.4009999930858612,0.4020000100135803,0.4020000100135803,0.3970000147819519,0.4040000140666961,0.4000000059604645,0.4079999923706054,0.4059999883174896,0.402999997138977,0.4009999930858612,0.4059999883174896,0.3939999938011169,0.4009999930858612,0.4070000052452087,0.4059999883174896,0.4050000011920929,0.402999997138977,0.402999997138977,0.4079999923706054,0.3989999890327453,0.402999997138977,0.4000000059604645,0.4070000052452087,0.4050000011920929,0.4040000140666961,0.4009999930858612,0.4009999930858612,0.4099999964237213,0.4070000052452087,0.4000000059604645,0.4000000059604645,0.402999997138977,0.4009999930858612,0.4009999930858612,0.4020000100135803,0.402999997138977,0.4000000059604645,0.4000000059604645,0.402999997138977,0.3939999938011169,0.4009999930858612],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3519999980926513,0.3709999918937683,0.375,0.3740000128746032,0.3819999992847442,0.3759999871253967,0.3919999897480011,0.3939999938011169,0.3799999952316284,0.3919999897480011,0.3959999978542328,0.3930000066757202,0.3939999938011169,0.3919999897480011,0.4000000059604645,0.4050000011920929,0.4040000140666961,0.4120000004768371,0.4000000059604645,0.3959999978542328,0.4090000092983246,0.4009999930858612,0.3799999952316284,0.4079999923706054,0.4009999930858612,0.402999997138977,0.3970000147819519,0.3970000147819519,0.4040000140666961,0.4050000011920929,0.3790000081062317,0.3980000019073486,0.3939999938011169,0.3970000147819519,0.4059999883174896,0.3980000019073486,0.3980000019073486,0.402999997138977,0.3980000019073486,0.4090000092983246,0.4040000140666961,0.402999997138977,0.414000004529953,0.4000000059604645,0.3970000147819519,0.4040000140666961,0.4120000004768371,0.4040000140666961,0.3989999890327453,0.4020000100135803,0.4110000133514404,0.402999997138977,0.4120000004768371,0.4120000004768371,0.4050000011920929,0.4120000004768371,0.4070000052452087,0.4189999997615814,0.4020000100135803,0.4070000052452087,0.4070000052452087,0.4020000100135803,0.4070000052452087,0.4129999876022339,0.4120000004768371,0.4149999916553497,0.4160000085830688,0.4199999868869781,0.4169999957084656,0.4079999923706054,0.4120000004768371,0.4070000052452087,0.4250000119209289,0.414000004529953,0.4090000092983246,0.4070000052452087,0.4079999923706054,0.4070000052452087,0.4079999923706054,0.4059999883174896,0.421999990940094,0.4079999923706054,0.4210000038146972,0.4129999876022339,0.4110000133514404,0.4180000126361847,0.4099999964237213,0.3970000147819519,0.4070000052452087,0.4070000052452087,0.4040000140666961,0.402999997138977,0.4160000085830688,0.4070000052452087,0.4079999923706054,0.4090000092983246,0.4129999876022339,0.4070000052452087,0.4020000100135803,0.4199999868869781,0.4180000126361847,0.3959999978542328,0.4090000092983246,0.4110000133514404,0.4110000133514404,0.414000004529953,0.4099999964237213,0.4059999883174896,0.4120000004768371,0.4020000100135803,0.4120000004768371,0.4079999923706054,0.4079999923706054,0.4079999923706054,0.4180000126361847,0.4180000126361847,0.4160000085830688,0.414000004529953,0.4129999876022339,0.4120000004768371,0.4129999876022339,0.4099999964237213,0.4169999957084656,0.4129999876022339,0.4110000133514404,0.4090000092983246,0.4169999957084656,0.4129999876022339,0.4210000038146972,0.421999990940094,0.4250000119209289,0.4180000126361847,0.4099999964237213,0.414000004529953,0.4230000078678131,0.4259999990463257,0.4169999957084656,0.4169999957084656,0.4169999957084656,0.4099999964237213,0.4120000004768371,0.4199999868869781,0.4230000078678131,0.4169999957084656,0.414000004529953,0.4110000133514404,0.4199999868869781,0.4160000085830688,0.4210000038146972,0.4169999957084656,0.4180000126361847,0.4189999997615814,0.4239999949932098,0.4230000078678131,0.4180000126361847,0.4210000038146972,0.4120000004768371,0.414000004529953,0.4180000126361847,0.4189999997615814,0.4110000133514404,0.4210000038146972,0.4199999868869781,0.421999990940094,0.4090000092983246,0.4199999868869781,0.4169999957084656],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3600000143051147,0.3569999933242798,0.3799999952316284,0.3810000121593475,0.3709999918937683,0.3790000081062317,0.3729999959468841,0.3770000040531158,0.3770000040531158,0.3970000147819519,0.3849999904632568,0.3770000040531158,0.3919999897480011,0.3819999992847442,0.3989999890327453,0.3869999945163727,0.3860000073909759,0.3939999938011169,0.3799999952316284,0.395000010728836,0.395000010728836,0.3810000121593475,0.4070000052452087,0.4020000100135803,0.3899999856948852,0.382999986410141,0.3899999856948852,0.3980000019073486,0.3849999904632568,0.3869999945163727,0.395000010728836,0.3899999856948852,0.3810000121593475,0.3840000033378601,0.3899999856948852,0.3840000033378601,0.3869999945163727,0.3880000114440918,0.3840000033378601,0.3849999904632568,0.3810000121593475,0.3959999978542328,0.3759999871253967,0.3819999992847442,0.4000000059604645,0.3899999856948852,0.3790000081062317,0.3970000147819519,0.3959999978542328,0.3899999856948852,0.3930000066757202,0.3840000033378601,0.3970000147819519,0.3980000019073486,0.3959999978542328,0.3869999945163727,0.3930000066757202,0.382999986410141,0.3910000026226043,0.3849999904632568,0.395000010728836,0.3910000026226043,0.3860000073909759,0.3980000019073486,0.3889999985694885,0.3919999897480011,0.3930000066757202,0.3889999985694885,0.3930000066757202,0.3869999945163727,0.3910000026226043,0.3869999945163727,0.3899999856948852,0.4009999930858612,0.3980000019073486,0.3980000019073486,0.3939999938011169,0.3930000066757202,0.3899999856948852,0.3989999890327453,0.395000010728836,0.3919999897480011,0.402999997138977,0.3939999938011169,0.3980000019073486,0.3970000147819519,0.3970000147819519,0.395000010728836,0.3959999978542328,0.3840000033378601,0.3919999897480011,0.3910000026226043,0.395000010728836,0.3930000066757202,0.3939999938011169,0.3980000019073486,0.3919999897480011,0.3919999897480011,0.3910000026226043,0.3919999897480011,0.3880000114440918,0.3910000026226043,0.3889999985694885,0.3910000026226043,0.4009999930858612,0.3930000066757202,0.3880000114440918,0.3959999978542328,0.4040000140666961,0.3910000026226043,0.3899999856948852,0.3959999978542328,0.3919999897480011,0.3930000066757202,0.3930000066757202,0.4009999930858612,0.3899999856948852,0.4000000059604645,0.3939999938011169,0.395000010728836,0.3919999897480011,0.3970000147819519,0.395000010728836,0.4000000059604645,0.4020000100135803,0.3959999978542328,0.3959999978542328,0.3970000147819519,0.395000010728836,0.3899999856948852,0.3899999856948852,0.3919999897480011,0.3939999938011169,0.3939999938011169,0.3939999938011169,0.395000010728836,0.3919999897480011,0.3970000147819519,0.3939999938011169,0.395000010728836,0.3860000073909759,0.3849999904632568,0.3880000114440918,0.3919999897480011,0.3930000066757202,0.3910000026226043,0.3959999978542328,0.395000010728836,0.3860000073909759,0.3910000026226043,0.3930000066757202,0.3899999856948852,0.3880000114440918,0.3970000147819519,0.4000000059604645,0.4020000100135803,0.4000000059604645,0.3910000026226043,0.3930000066757202,0.3910000026226043,0.3970000147819519,0.3980000019073486,0.3959999978542328,0.3959999978542328,0.3899999856948852,0.3910000026226043,0.3849999904632568],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3580000102519989,0.3540000021457672,0.3740000128746032,0.3770000040531158,0.3709999918937683,0.3729999959468841,0.382999986410141,0.382999986410141,0.3919999897480011,0.3910000026226043,0.3860000073909759,0.3880000114440918,0.3840000033378601,0.3899999856948852,0.3849999904632568,0.3939999938011169,0.3849999904632568,0.3880000114440918,0.3980000019073486,0.3989999890327453,0.4059999883174896,0.3959999978542328,0.3939999938011169,0.3849999904632568,0.3849999904632568,0.3939999938011169,0.3910000026226043,0.382999986410141,0.3840000033378601,0.3980000019073486,0.3970000147819519,0.382999986410141,0.3799999952316284,0.3880000114440918,0.3970000147819519,0.3899999856948852,0.3849999904632568,0.382999986410141,0.3889999985694885,0.3819999992847442,0.3869999945163727,0.3840000033378601,0.3840000033378601,0.3869999945163727,0.395000010728836,0.3849999904632568,0.3790000081062317,0.3899999856948852,0.3980000019073486,0.3849999904632568,0.4059999883174896,0.3849999904632568,0.3840000033378601,0.382999986410141,0.3869999945163727,0.3849999904632568,0.3899999856948852,0.3930000066757202,0.395000010728836,0.395000010728836,0.3939999938011169,0.3889999985694885,0.3869999945163727,0.3919999897480011,0.3939999938011169,0.3959999978542328,0.3919999897480011,0.3970000147819519,0.3860000073909759,0.3889999985694885,0.4009999930858612,0.3910000026226043,0.3980000019073486,0.3840000033378601,0.395000010728836,0.3880000114440918,0.4009999930858612,0.3939999938011169,0.3930000066757202,0.4009999930858612,0.3919999897480011,0.4000000059604645,0.3970000147819519,0.4000000059604645,0.4000000059604645,0.3959999978542328,0.4020000100135803,0.4009999930858612,0.3980000019073486,0.3930000066757202,0.3930000066757202,0.3970000147819519,0.3980000019073486,0.4000000059604645,0.3930000066757202,0.395000010728836,0.3930000066757202,0.3919999897480011,0.395000010728836,0.3959999978542328,0.4040000140666961,0.4090000092983246,0.3989999890327453,0.3980000019073486,0.3970000147819519,0.3959999978542328,0.3869999945163727,0.4090000092983246,0.402999997138977,0.4079999923706054,0.3930000066757202,0.3989999890327453,0.3959999978542328,0.3989999890327453,0.3919999897480011,0.3980000019073486,0.3980000019073486,0.3970000147819519,0.4009999930858612,0.3869999945163727,0.3889999985694885,0.3919999897480011,0.395000010728836,0.3989999890327453,0.3970000147819519,0.3919999897480011,0.3889999985694885,0.3970000147819519,0.3970000147819519,0.3980000019073486,0.3919999897480011,0.3959999978542328,0.3939999938011169,0.4000000059604645,0.4020000100135803,0.3970000147819519,0.4070000052452087,0.4009999930858612,0.3980000019073486,0.4009999930858612,0.3959999978542328,0.3989999890327453,0.3910000026226043,0.3959999978542328,0.4000000059604645,0.3989999890327453,0.3959999978542328,0.4020000100135803,0.4040000140666961,0.4020000100135803,0.3919999897480011,0.4009999930858612,0.3959999978542328,0.3989999890327453,0.3989999890327453,0.4040000140666961,0.4040000140666961,0.3970000147819519,0.4000000059604645,0.4070000052452087,0.4020000100135803,0.4079999923706054,0.4000000059604645,0.402999997138977,0.4009999930858612,0.4059999883174896,0.4079999923706054],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.367000013589859,0.3689999878406524,0.3729999959468841,0.3619999885559082,0.3770000040531158,0.3759999871253967,0.3799999952316284,0.3810000121593475,0.3869999945163727,0.382999986410141,0.3910000026226043,0.3819999992847442,0.3849999904632568,0.3849999904632568,0.3959999978542328,0.3899999856948852,0.3779999911785126,0.3880000114440918,0.3939999938011169,0.3930000066757202,0.3880000114440918,0.3959999978542328,0.3889999985694885,0.3759999871253967,0.395000010728836,0.3849999904632568,0.3880000114440918,0.3910000026226043,0.3759999871253967,0.395000010728836,0.3799999952316284,0.382999986410141,0.3930000066757202,0.3860000073909759,0.3989999890327453,0.382999986410141,0.3930000066757202,0.3980000019073486,0.4000000059604645,0.4000000059604645,0.3939999938011169,0.3860000073909759,0.3759999871253967,0.3860000073909759,0.4020000100135803,0.3939999938011169,0.3899999856948852,0.3959999978542328,0.3889999985694885,0.4070000052452087,0.3919999897480011,0.3869999945163727,0.4050000011920929,0.3970000147819519,0.402999997138977,0.3939999938011169,0.4050000011920929,0.4050000011920929,0.4020000100135803,0.3980000019073486,0.4000000059604645,0.3899999856948852,0.3930000066757202,0.395000010728836,0.4050000011920929,0.395000010728836,0.3910000026226043,0.3889999985694885,0.4050000011920929,0.4059999883174896,0.395000010728836,0.3959999978542328,0.395000010728836,0.4070000052452087,0.3860000073909759,0.4000000059604645,0.3980000019073486,0.3989999890327453,0.4079999923706054,0.3980000019073486,0.3930000066757202,0.3889999985694885,0.4059999883174896,0.3989999890327453,0.4059999883174896,0.3930000066757202,0.4020000100135803,0.3919999897480011,0.4040000140666961,0.3980000019073486,0.3959999978542328,0.4110000133514404,0.4050000011920929,0.4050000011920929,0.4149999916553497,0.4099999964237213,0.4020000100135803,0.4020000100135803,0.4090000092983246,0.4009999930858612,0.4040000140666961,0.4009999930858612,0.3989999890327453,0.4020000100135803,0.3989999890327453,0.395000010728836,0.3989999890327453,0.4059999883174896,0.4120000004768371,0.3989999890327453,0.4110000133514404,0.414000004529953,0.4099999964237213,0.4090000092983246,0.4120000004768371,0.4040000140666961,0.3970000147819519,0.4059999883174896,0.402999997138977,0.4079999923706054,0.4040000140666961,0.402999997138977,0.3989999890327453,0.4149999916553497,0.4110000133514404,0.414000004529953,0.4180000126361847,0.4149999916553497,0.4180000126361847,0.414000004529953,0.421999990940094,0.4169999957084656,0.4169999957084656,0.4230000078678131,0.4110000133514404,0.4169999957084656,0.4079999923706054,0.4239999949932098,0.4250000119209289,0.4210000038146972,0.4169999957084656,0.4210000038146972,0.4160000085830688,0.414000004529953,0.4160000085830688,0.4210000038146972,0.4120000004768371,0.4129999876022339,0.4160000085830688,0.4090000092983246,0.414000004529953,0.4129999876022339,0.4090000092983246,0.4050000011920929,0.4079999923706054,0.4129999876022339,0.4189999997615814,0.4149999916553497,0.4120000004768371,0.4110000133514404,0.4079999923706054,0.4189999997615814,0.4180000126361847,0.4079999923706054,0.4169999957084656,0.414000004529953,0.4129999876022339,0.4129999876022339],"label":"FineWeb URL dedup"}},"siqa/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3619999885559082,0.3980000019073486,0.3899999856948852,0.3860000073909759,0.3919999897480011,0.402999997138977,0.3959999978542328,0.3959999978542328,0.4070000052452087,0.4009999930858612,0.4079999923706054,0.4009999930858612,0.3910000026226043,0.3980000019073486,0.4129999876022339,0.4020000100135803,0.4090000092983246,0.4120000004768371,0.4129999876022339,0.4129999876022339,0.4099999964237213,0.4110000133514404,0.4110000133514404,0.4090000092983246,0.4000000059604645,0.4050000011920929,0.3939999938011169,0.3889999985694885,0.4050000011920929,0.4099999964237213,0.3980000019073486,0.4090000092983246,0.4079999923706054,0.4070000052452087,0.4040000140666961,0.4129999876022339,0.4090000092983246,0.4059999883174896,0.4090000092983246,0.4090000092983246,0.4149999916553497,0.4059999883174896,0.4000000059604645,0.4000000059604645,0.4070000052452087,0.402999997138977,0.4040000140666961,0.3989999890327453,0.4020000100135803,0.4160000085830688,0.4050000011920929,0.4110000133514404,0.4059999883174896,0.3989999890327453,0.4169999957084656,0.4040000140666961,0.4050000011920929,0.4149999916553497,0.4020000100135803,0.402999997138977,0.4129999876022339,0.4009999930858612,0.4059999883174896,0.4040000140666961,0.4099999964237213,0.414000004529953,0.4210000038146972,0.4110000133514404,0.4070000052452087,0.4099999964237213,0.4169999957084656,0.4070000052452087,0.4199999868869781,0.4079999923706054,0.4180000126361847,0.4110000133514404,0.4110000133514404,0.4189999997615814,0.414000004529953,0.4129999876022339,0.4180000126361847,0.4070000052452087,0.4059999883174896,0.4059999883174896,0.4129999876022339,0.4149999916553497,0.4099999964237213,0.4009999930858612,0.4020000100135803,0.4099999964237213,0.4169999957084656,0.4129999876022339,0.414000004529953,0.4099999964237213,0.4189999997615814,0.4210000038146972,0.4090000092983246,0.4079999923706054,0.4099999964237213,0.4099999964237213,0.4129999876022339,0.4099999964237213,0.4099999964237213,0.4110000133514404,0.4020000100135803,0.4079999923706054,0.4079999923706054,0.414000004529953,0.4129999876022339,0.4189999997615814,0.4129999876022339,0.4180000126361847,0.4050000011920929,0.4230000078678131,0.4180000126361847,0.4120000004768371,0.4149999916553497,0.4189999997615814,0.4110000133514404,0.4160000085830688,0.4059999883174896,0.4110000133514404,0.4110000133514404,0.4110000133514404,0.4040000140666961,0.4149999916553497,0.414000004529953,0.4160000085830688,0.414000004529953,0.4129999876022339,0.4120000004768371,0.4149999916553497,0.4169999957084656,0.4110000133514404,0.414000004529953,0.4160000085830688,0.4110000133514404,0.4120000004768371,0.4110000133514404,0.4149999916553497,0.4129999876022339,0.4110000133514404,0.4129999876022339,0.4099999964237213,0.4180000126361847,0.414000004529953,0.4040000140666961,0.4099999964237213,0.4099999964237213,0.4120000004768371,0.4149999916553497,0.4129999876022339,0.4079999923706054,0.4040000140666961,0.4129999876022339,0.4149999916553497,0.4120000004768371,0.402999997138977,0.4090000092983246,0.4110000133514404,0.4090000092983246,0.4070000052452087,0.4149999916553497,0.4070000052452087,0.4120000004768371,0.4059999883174896,0.4059999883174896,0.4099999964237213],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3610000014305115,0.3930000066757202,0.3930000066757202,0.4020000100135803,0.4050000011920929,0.3980000019073486,0.3989999890327453,0.395000010728836,0.3959999978542328,0.3989999890327453,0.3959999978542328,0.4059999883174896,0.4070000052452087,0.4079999923706054,0.4000000059604645,0.4009999930858612,0.4070000052452087,0.4059999883174896,0.4040000140666961,0.4000000059604645,0.4070000052452087,0.4009999930858612,0.4079999923706054,0.4110000133514404,0.4040000140666961,0.4020000100135803,0.4129999876022339,0.4070000052452087,0.4050000011920929,0.4059999883174896,0.4090000092983246,0.3939999938011169,0.4059999883174896,0.4099999964237213,0.4020000100135803,0.4070000052452087,0.4079999923706054,0.402999997138977,0.4020000100135803,0.4120000004768371,0.4059999883174896,0.4050000011920929,0.4050000011920929,0.4020000100135803,0.3869999945163727,0.4050000011920929,0.3989999890327453,0.3919999897480011,0.3939999938011169,0.4079999923706054,0.3970000147819519,0.3959999978542328,0.3980000019073486,0.4050000011920929,0.4040000140666961,0.3980000019073486,0.3939999938011169,0.4040000140666961,0.3970000147819519,0.3980000019073486,0.3989999890327453,0.3980000019073486,0.4009999930858612,0.3980000019073486,0.3959999978542328,0.4090000092983246,0.3970000147819519,0.3910000026226043,0.4020000100135803,0.4000000059604645,0.4129999876022339,0.402999997138977,0.4020000100135803,0.4149999916553497,0.395000010728836,0.4040000140666961,0.402999997138977,0.4040000140666961,0.4000000059604645,0.4009999930858612,0.4009999930858612,0.4009999930858612,0.4099999964237213,0.4099999964237213,0.4120000004768371,0.3970000147819519,0.4099999964237213,0.4110000133514404,0.4059999883174896,0.4079999923706054,0.4000000059604645,0.4120000004768371,0.4050000011920929,0.3980000019073486,0.4110000133514404,0.4050000011920929,0.4059999883174896,0.4059999883174896,0.3989999890327453,0.3970000147819519,0.4079999923706054,0.402999997138977,0.4000000059604645,0.4050000011920929,0.3989999890327453,0.402999997138977,0.4040000140666961,0.3989999890327453,0.4070000052452087,0.4079999923706054,0.4009999930858612,0.4040000140666961,0.4020000100135803,0.4079999923706054,0.3959999978542328,0.4009999930858612,0.3989999890327453,0.4099999964237213,0.4009999930858612,0.4180000126361847,0.4090000092983246,0.4120000004768371,0.3970000147819519,0.4070000052452087,0.402999997138977,0.4120000004768371,0.4009999930858612,0.3939999938011169,0.3980000019073486,0.4169999957084656,0.4090000092983246,0.4050000011920929,0.421999990940094,0.4079999923706054,0.4070000052452087,0.4079999923706054,0.4070000052452087,0.4050000011920929,0.4059999883174896,0.4059999883174896,0.4099999964237213,0.4009999930858612,0.4070000052452087,0.4050000011920929,0.4050000011920929,0.4059999883174896,0.4079999923706054,0.4070000052452087,0.4120000004768371,0.4090000092983246,0.4009999930858612,0.4050000011920929,0.4070000052452087,0.4110000133514404,0.4090000092983246,0.4079999923706054,0.3980000019073486,0.4050000011920929,0.402999997138977,0.4000000059604645,0.402999997138977,0.4070000052452087,0.4090000092983246,0.4090000092983246,0.4099999964237213,0.4059999883174896,0.4120000004768371,0.4040000140666961],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3619999885559082,0.4000000059604645,0.395000010728836,0.3959999978542328,0.4020000100135803,0.4000000059604645,0.3959999978542328,0.3930000066757202,0.3899999856948852,0.402999997138977,0.4009999930858612,0.3930000066757202,0.4050000011920929,0.3939999938011169,0.4000000059604645,0.3989999890327453,0.3959999978542328,0.4020000100135803,0.4000000059604645,0.3939999938011169,0.395000010728836,0.3919999897480011,0.3980000019073486,0.3910000026226043,0.3880000114440918,0.3959999978542328,0.3980000019073486,0.3989999890327453,0.402999997138977,0.3959999978542328,0.3980000019073486,0.395000010728836,0.4090000092983246,0.4090000092983246,0.3889999985694885,0.3959999978542328,0.3880000114440918,0.3840000033378601,0.3959999978542328,0.3880000114440918,0.3939999938011169,0.3970000147819519,0.3910000026226043,0.3939999938011169,0.4020000100135803,0.3980000019073486,0.3970000147819519,0.4009999930858612,0.3919999897480011,0.3899999856948852,0.3989999890327453,0.3860000073909759,0.3860000073909759,0.3970000147819519,0.3959999978542328,0.3939999938011169,0.3840000033378601,0.3869999945163727,0.402999997138977,0.4050000011920929,0.395000010728836,0.3880000114440918,0.3869999945163727,0.3939999938011169,0.402999997138977,0.3899999856948852,0.3910000026226043,0.3910000026226043,0.4009999930858612,0.3919999897480011,0.3970000147819519,0.3919999897480011,0.3930000066757202,0.3869999945163727,0.3880000114440918,0.3849999904632568,0.3930000066757202,0.395000010728836,0.3889999985694885,0.3959999978542328,0.3989999890327453,0.402999997138977,0.3939999938011169,0.4000000059604645,0.4000000059604645,0.4050000011920929,0.3989999890327453,0.3869999945163727,0.3910000026226043,0.3889999985694885,0.3889999985694885,0.4000000059604645,0.3910000026226043,0.3970000147819519,0.3989999890327453,0.3989999890327453,0.3959999978542328,0.3910000026226043,0.3880000114440918,0.3939999938011169,0.382999986410141,0.3849999904632568,0.3959999978542328,0.3989999890327453,0.3959999978542328,0.3880000114440918,0.3840000033378601,0.3980000019073486,0.4000000059604645,0.4000000059604645,0.4020000100135803,0.395000010728836,0.3910000026226043,0.3919999897480011,0.4040000140666961,0.3989999890327453,0.4020000100135803,0.3910000026226043,0.4009999930858612,0.3959999978542328,0.3939999938011169,0.3930000066757202,0.3910000026226043,0.3970000147819519,0.3880000114440918,0.3970000147819519,0.3959999978542328,0.3889999985694885,0.3970000147819519,0.4009999930858612,0.3970000147819519,0.3959999978542328,0.3959999978542328,0.3989999890327453,0.4040000140666961,0.3959999978542328,0.3980000019073486,0.3970000147819519,0.3970000147819519,0.3989999890327453,0.4020000100135803,0.3980000019073486,0.4000000059604645,0.4000000059604645,0.402999997138977,0.4090000092983246,0.3970000147819519,0.4020000100135803,0.3970000147819519,0.4009999930858612,0.3959999978542328,0.3970000147819519,0.3989999890327453,0.3939999938011169,0.3989999890327453,0.4000000059604645,0.4000000059604645,0.3989999890327453,0.4050000011920929,0.4059999883174896,0.4009999930858612,0.3989999890327453,0.3959999978542328,0.3939999938011169,0.3970000147819519,0.4009999930858612,0.3989999890327453,0.3939999938011169],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3619999885559082,0.3910000026226043,0.4009999930858612,0.414000004529953,0.3959999978542328,0.4009999930858612,0.4020000100135803,0.3989999890327453,0.4009999930858612,0.4009999930858612,0.3959999978542328,0.4059999883174896,0.3869999945163727,0.4000000059604645,0.3970000147819519,0.4009999930858612,0.3980000019073486,0.3930000066757202,0.4020000100135803,0.4020000100135803,0.4099999964237213,0.4009999930858612,0.3970000147819519,0.4040000140666961,0.4079999923706054,0.395000010728836,0.3860000073909759,0.4070000052452087,0.402999997138977,0.4059999883174896,0.3989999890327453,0.4090000092983246,0.4020000100135803,0.4110000133514404,0.4050000011920929,0.4090000092983246,0.4009999930858612,0.414000004529953,0.3930000066757202,0.4009999930858612,0.3930000066757202,0.402999997138977,0.3880000114440918,0.3959999978542328,0.4050000011920929,0.3919999897480011,0.3899999856948852,0.3970000147819519,0.3930000066757202,0.3910000026226043,0.3910000026226043,0.3939999938011169,0.395000010728836,0.3939999938011169,0.3899999856948852,0.3959999978542328,0.3939999938011169,0.3919999897480011,0.3959999978542328,0.3959999978542328,0.3939999938011169,0.4059999883174896,0.4070000052452087,0.4079999923706054,0.4040000140666961,0.4079999923706054,0.3989999890327453,0.402999997138977,0.402999997138977,0.4000000059604645,0.3860000073909759,0.3939999938011169,0.3919999897480011,0.4050000011920929,0.3970000147819519,0.3970000147819519,0.3980000019073486,0.3860000073909759,0.3930000066757202,0.3989999890327453,0.3939999938011169,0.4020000100135803,0.3989999890327453,0.4059999883174896,0.3970000147819519,0.3989999890327453,0.3919999897480011,0.3980000019073486,0.4040000140666961,0.4050000011920929,0.3899999856948852,0.3980000019073486,0.4009999930858612,0.4079999923706054,0.3970000147819519,0.3970000147819519,0.3980000019073486,0.3910000026226043,0.4070000052452087,0.402999997138977,0.3989999890327453,0.4050000011920929,0.3819999992847442,0.4050000011920929,0.4099999964237213,0.3959999978542328,0.395000010728836,0.4000000059604645,0.4050000011920929,0.3970000147819519,0.3980000019073486,0.4059999883174896,0.4050000011920929,0.4000000059604645,0.3930000066757202,0.3919999897480011,0.3930000066757202,0.3919999897480011,0.3919999897480011,0.4000000059604645,0.3970000147819519,0.402999997138977,0.4040000140666961,0.3939999938011169,0.3980000019073486,0.3939999938011169,0.402999997138977,0.3899999856948852,0.3970000147819519,0.3959999978542328,0.3919999897480011,0.3989999890327453,0.3910000026226043,0.3910000026226043,0.3910000026226043,0.395000010728836,0.4000000059604645,0.3910000026226043,0.3989999890327453,0.3980000019073486,0.3959999978542328,0.3959999978542328,0.3970000147819519,0.3919999897480011,0.3939999938011169,0.3980000019073486,0.3910000026226043,0.4000000059604645,0.3959999978542328,0.3899999856948852,0.3959999978542328,0.3849999904632568,0.3939999938011169,0.3970000147819519,0.3989999890327453,0.395000010728836,0.3919999897480011,0.3930000066757202,0.3930000066757202,0.395000010728836,0.3930000066757202,0.395000010728836,0.3939999938011169,0.3970000147819519,0.3980000019073486,0.4020000100135803,0.3980000019073486,0.3989999890327453],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3619999885559082,0.3959999978542328,0.4070000052452087,0.3910000026226043,0.3939999938011169,0.3980000019073486,0.3930000066757202,0.4059999883174896,0.4000000059604645,0.3889999985694885,0.3989999890327453,0.402999997138977,0.3980000019073486,0.4000000059604645,0.3989999890327453,0.4000000059604645,0.3930000066757202,0.3939999938011169,0.3930000066757202,0.3880000114440918,0.3980000019073486,0.4020000100135803,0.3980000019073486,0.3959999978542328,0.3989999890327453,0.4020000100135803,0.402999997138977,0.4009999930858612,0.4079999923706054,0.4009999930858612,0.4070000052452087,0.4070000052452087,0.4020000100135803,0.4059999883174896,0.4079999923706054,0.4110000133514404,0.3989999890327453,0.4000000059604645,0.402999997138977,0.3939999938011169,0.3939999938011169,0.3980000019073486,0.3980000019073486,0.4050000011920929,0.4009999930858612,0.4120000004768371,0.402999997138977,0.4090000092983246,0.402999997138977,0.3980000019073486,0.3959999978542328,0.3970000147819519,0.4009999930858612,0.4070000052452087,0.4070000052452087,0.4079999923706054,0.402999997138977,0.3989999890327453,0.3980000019073486,0.4009999930858612,0.4050000011920929,0.4000000059604645,0.3959999978542328,0.3980000019073486,0.3970000147819519,0.4129999876022339,0.402999997138977,0.4090000092983246,0.4050000011920929,0.402999997138977,0.4009999930858612,0.3980000019073486,0.402999997138977,0.4020000100135803,0.3980000019073486,0.3970000147819519,0.402999997138977,0.4000000059604645,0.4149999916553497,0.3959999978542328,0.4000000059604645,0.4020000100135803,0.3919999897480011,0.4110000133514404,0.4090000092983246,0.4070000052452087,0.4059999883174896,0.4020000100135803,0.3959999978542328,0.4050000011920929,0.395000010728836,0.4020000100135803,0.3959999978542328,0.4090000092983246,0.4070000052452087,0.4040000140666961,0.4000000059604645,0.4020000100135803,0.402999997138977,0.4050000011920929,0.414000004529953,0.4009999930858612,0.402999997138977,0.4020000100135803,0.3980000019073486,0.4020000100135803,0.4000000059604645,0.402999997138977,0.395000010728836,0.4009999930858612,0.3959999978542328,0.4120000004768371,0.3989999890327453,0.3980000019073486,0.4040000140666961,0.4070000052452087,0.3989999890327453,0.3989999890327453,0.3970000147819519,0.3970000147819519,0.3980000019073486,0.3970000147819519,0.3989999890327453,0.4110000133514404,0.4050000011920929,0.3939999938011169,0.3970000147819519,0.4009999930858612,0.3989999890327453,0.3980000019073486,0.402999997138977,0.3860000073909759,0.402999997138977,0.4020000100135803,0.3959999978542328,0.3989999890327453,0.3959999978542328,0.4000000059604645,0.395000010728836,0.395000010728836,0.3939999938011169,0.3980000019073486,0.4020000100135803,0.3989999890327453,0.3989999890327453,0.3880000114440918,0.3980000019073486,0.3959999978542328,0.4009999930858612,0.4079999923706054,0.395000010728836,0.3980000019073486,0.4009999930858612,0.3980000019073486,0.4009999930858612,0.3989999890327453,0.4000000059604645,0.402999997138977,0.4000000059604645,0.4020000100135803,0.3959999978542328,0.395000010728836,0.4020000100135803,0.3970000147819519,0.3980000019073486,0.3959999978542328,0.4000000059604645,0.4050000011920929],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3619999885559082,0.3910000026226043,0.3889999985694885,0.3810000121593475,0.3970000147819519,0.3919999897480011,0.4009999930858612,0.4040000140666961,0.3899999856948852,0.3989999890327453,0.3899999856948852,0.3980000019073486,0.3980000019073486,0.3910000026226043,0.3810000121593475,0.4000000059604645,0.4009999930858612,0.3849999904632568,0.3939999938011169,0.4009999930858612,0.402999997138977,0.3899999856948852,0.395000010728836,0.3989999890327453,0.3989999890327453,0.3959999978542328,0.3959999978542328,0.3910000026226043,0.3910000026226043,0.3989999890327453,0.4230000078678131,0.3899999856948852,0.3889999985694885,0.395000010728836,0.3840000033378601,0.3980000019073486,0.3869999945163727,0.3910000026226043,0.3849999904632568,0.3939999938011169,0.3989999890327453,0.4050000011920929,0.3919999897480011,0.402999997138977,0.3930000066757202,0.3970000147819519,0.3989999890327453,0.4040000140666961,0.402999997138977,0.3939999938011169,0.3970000147819519,0.4090000092983246,0.4009999930858612,0.395000010728836,0.4020000100135803,0.3939999938011169,0.4059999883174896,0.4090000092983246,0.4020000100135803,0.4110000133514404,0.3970000147819519,0.4009999930858612,0.3919999897480011,0.4000000059604645,0.3959999978542328,0.3959999978542328,0.3910000026226043,0.3919999897480011,0.4070000052452087,0.414000004529953,0.3869999945163727,0.4009999930858612,0.4000000059604645,0.402999997138977,0.4000000059604645,0.402999997138977,0.4040000140666961,0.3989999890327453,0.4040000140666961,0.4009999930858612,0.4160000085830688,0.4079999923706054,0.4020000100135803,0.4079999923706054,0.4059999883174896,0.402999997138977,0.4050000011920929,0.395000010728836,0.3989999890327453,0.3959999978542328,0.3970000147819519,0.3970000147819519,0.4009999930858612,0.3959999978542328,0.4120000004768371,0.3989999890327453,0.4079999923706054,0.4090000092983246,0.3989999890327453,0.4090000092983246,0.3889999985694885,0.4009999930858612,0.3989999890327453,0.3980000019073486,0.4020000100135803,0.3959999978542328,0.4050000011920929,0.3910000026226043,0.3970000147819519,0.4000000059604645,0.3919999897480011,0.395000010728836,0.4040000140666961,0.3970000147819519,0.3939999938011169,0.3970000147819519,0.4020000100135803,0.3930000066757202,0.4020000100135803,0.3980000019073486,0.3939999938011169,0.3959999978542328,0.3939999938011169,0.3919999897480011,0.4000000059604645,0.402999997138977,0.3970000147819519,0.3910000026226043,0.395000010728836,0.3899999856948852,0.3880000114440918,0.3930000066757202,0.3959999978542328,0.3849999904632568,0.3910000026226043,0.3919999897480011,0.395000010728836,0.3910000026226043,0.3930000066757202,0.3869999945163727,0.3919999897480011,0.3970000147819519,0.3910000026226043,0.3849999904632568,0.3899999856948852,0.3869999945163727,0.3869999945163727,0.3880000114440918,0.3880000114440918,0.3930000066757202,0.3910000026226043,0.4009999930858612,0.3910000026226043,0.3930000066757202,0.4009999930858612,0.3939999938011169,0.3980000019073486,0.395000010728836,0.4040000140666961,0.3939999938011169,0.3910000026226043,0.3930000066757202,0.3930000066757202,0.3939999938011169,0.3970000147819519,0.3910000026226043,0.3959999978542328,0.3919999897480011],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3619999885559082,0.3819999992847442,0.3919999897480011,0.3939999938011169,0.4090000092983246,0.3939999938011169,0.3939999938011169,0.395000010728836,0.4009999930858612,0.3980000019073486,0.3939999938011169,0.3910000026226043,0.3959999978542328,0.402999997138977,0.3849999904632568,0.3939999938011169,0.4099999964237213,0.4040000140666961,0.3980000019073486,0.4149999916553497,0.4040000140666961,0.4070000052452087,0.402999997138977,0.3959999978542328,0.4020000100135803,0.4070000052452087,0.4070000052452087,0.3980000019073486,0.4070000052452087,0.4050000011920929,0.4040000140666961,0.4020000100135803,0.3810000121593475,0.3910000026226043,0.4020000100135803,0.4059999883174896,0.4050000011920929,0.4050000011920929,0.4050000011920929,0.4009999930858612,0.4040000140666961,0.4020000100135803,0.3930000066757202,0.4059999883174896,0.3939999938011169,0.3980000019073486,0.3970000147819519,0.3930000066757202,0.395000010728836,0.3989999890327453,0.4059999883174896,0.4079999923706054,0.4070000052452087,0.4050000011920929,0.3989999890327453,0.3919999897480011,0.4040000140666961,0.3989999890327453,0.4040000140666961,0.4099999964237213,0.402999997138977,0.4009999930858612,0.4009999930858612,0.3930000066757202,0.4040000140666961,0.3970000147819519,0.395000010728836,0.4040000140666961,0.4099999964237213,0.3970000147819519,0.4040000140666961,0.3989999890327453,0.4009999930858612,0.4090000092983246,0.4090000092983246,0.4020000100135803,0.4050000011920929,0.4070000052452087,0.3939999938011169,0.4090000092983246,0.4169999957084656,0.4070000052452087,0.3919999897480011,0.4110000133514404,0.4099999964237213,0.3899999856948852,0.4020000100135803,0.4099999964237213,0.4090000092983246,0.3930000066757202,0.4129999876022339,0.4149999916553497,0.4110000133514404,0.4009999930858612,0.4059999883174896,0.4169999957084656,0.4020000100135803,0.4070000052452087,0.402999997138977,0.4099999964237213,0.4050000011920929,0.4110000133514404,0.4059999883174896,0.4020000100135803,0.4120000004768371,0.4110000133514404,0.4090000092983246,0.4120000004768371,0.4169999957084656,0.4099999964237213,0.4059999883174896,0.402999997138977,0.4079999923706054,0.4099999964237213,0.4090000092983246,0.4000000059604645,0.4020000100135803,0.4079999923706054,0.4050000011920929,0.4040000140666961,0.402999997138977,0.4040000140666961,0.3989999890327453,0.4079999923706054,0.402999997138977,0.4099999964237213,0.3989999890327453,0.3989999890327453,0.3939999938011169,0.4000000059604645,0.402999997138977,0.4020000100135803,0.4070000052452087,0.4090000092983246,0.4070000052452087,0.4050000011920929,0.4099999964237213,0.4059999883174896,0.4090000092983246,0.402999997138977,0.4079999923706054,0.4120000004768371,0.4050000011920929,0.4090000092983246,0.4090000092983246,0.4079999923706054,0.4160000085830688,0.4070000052452087,0.4110000133514404,0.4070000052452087,0.4079999923706054,0.4160000085830688,0.4090000092983246,0.4070000052452087,0.4090000092983246,0.4099999964237213,0.4090000092983246,0.4120000004768371,0.4050000011920929,0.4070000052452087,0.4070000052452087,0.4070000052452087,0.4120000004768371,0.4090000092983246,0.4079999923706054,0.4110000133514404,0.4149999916553497,0.4160000085830688],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3619999885559082,0.3980000019073486,0.3970000147819519,0.3970000147819519,0.4020000100135803,0.4009999930858612,0.4040000140666961,0.4040000140666961,0.4040000140666961,0.4009999930858612,0.395000010728836,0.402999997138977,0.3959999978542328,0.4020000100135803,0.4040000140666961,0.402999997138977,0.402999997138977,0.4059999883174896,0.4040000140666961,0.4040000140666961,0.3959999978542328,0.4090000092983246,0.4020000100135803,0.3980000019073486,0.3919999897480011,0.4059999883174896,0.4009999930858612,0.4090000092983246,0.4070000052452087,0.3989999890327453,0.3899999856948852,0.4079999923706054,0.4009999930858612,0.4040000140666961,0.4110000133514404,0.3980000019073486,0.4099999964237213,0.414000004529953,0.4160000085830688,0.4000000059604645,0.4040000140666961,0.4050000011920929,0.4199999868869781,0.4020000100135803,0.3989999890327453,0.3970000147819519,0.4059999883174896,0.3899999856948852,0.3980000019073486,0.4079999923706054,0.4050000011920929,0.402999997138977,0.4020000100135803,0.395000010728836,0.4120000004768371,0.4090000092983246,0.3980000019073486,0.4050000011920929,0.4099999964237213,0.3989999890327453,0.4059999883174896,0.402999997138977,0.402999997138977,0.402999997138977,0.4079999923706054,0.4040000140666961,0.4099999964237213,0.4110000133514404,0.4059999883174896,0.4040000140666961,0.4020000100135803,0.4040000140666961,0.4059999883174896,0.3860000073909759,0.4050000011920929,0.395000010728836,0.4040000140666961,0.4099999964237213,0.4090000092983246,0.4120000004768371,0.4009999930858612,0.402999997138977,0.4040000140666961,0.4070000052452087,0.4070000052452087,0.4169999957084656,0.4000000059604645,0.4020000100135803,0.4040000140666961,0.3959999978542328,0.3910000026226043,0.4050000011920929,0.4070000052452087,0.3989999890327453,0.4090000092983246,0.4090000092983246,0.4050000011920929,0.4099999964237213,0.4129999876022339,0.4040000140666961,0.4020000100135803,0.4009999930858612,0.414000004529953,0.4000000059604645,0.4050000011920929,0.4090000092983246,0.3970000147819519,0.3980000019073486,0.4050000011920929,0.402999997138977,0.4040000140666961,0.3930000066757202,0.3959999978542328,0.402999997138977,0.4000000059604645,0.4020000100135803,0.4050000011920929,0.4050000011920929,0.4050000011920929,0.4070000052452087,0.4009999930858612,0.4050000011920929,0.3980000019073486,0.4090000092983246,0.402999997138977,0.4059999883174896,0.4099999964237213,0.4090000092983246,0.4110000133514404,0.4110000133514404,0.4040000140666961,0.4129999876022339,0.3959999978542328,0.4050000011920929,0.4129999876022339,0.4120000004768371,0.4059999883174896,0.4040000140666961,0.414000004529953,0.4050000011920929,0.402999997138977,0.4070000052452087,0.4120000004768371,0.4040000140666961,0.4099999964237213,0.4110000133514404,0.4129999876022339,0.4160000085830688,0.4020000100135803,0.4149999916553497,0.4090000092983246,0.402999997138977,0.402999997138977,0.4000000059604645,0.4099999964237213,0.4129999876022339,0.4129999876022339,0.4090000092983246,0.4169999957084656,0.4040000140666961,0.4099999964237213,0.4079999923706054,0.4180000126361847,0.4149999916553497,0.414000004529953,0.4120000004768371,0.4110000133514404,0.414000004529953],"label":"FineWeb URL dedup"}},"winogrande/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.5019999742507935,0.5109999775886536,0.5120000243186951,0.5130000114440918,0.5230000019073486,0.5370000004768372,0.527999997138977,0.5490000247955322,0.550000011920929,0.527999997138977,0.5429999828338623,0.5389999747276306,0.550000011920929,0.5350000262260437,0.5370000004768372,0.5450000166893005,0.5260000228881836,0.5490000247955322,0.5490000247955322,0.5490000247955322,0.5370000004768372,0.546999990940094,0.5389999747276306,0.5519999861717224,0.5379999876022339,0.5429999828338623,0.5490000247955322,0.546999990940094,0.5320000052452087,0.5540000200271606,0.5410000085830688,0.5440000295639038,0.550000011920929,0.5569999814033508,0.5410000085830688,0.5519999861717224,0.5350000262260437,0.5479999780654907,0.5649999976158142,0.5590000152587891,0.5659999847412109,0.5429999828338623,0.5429999828338623,0.550000011920929,0.5429999828338623,0.5590000152587891,0.546999990940094,0.5550000071525574,0.5590000152587891,0.5350000262260437,0.5590000152587891,0.5580000281333923,0.5649999976158142,0.5649999976158142,0.5690000057220459,0.5619999766349792,0.5440000295639038,0.5529999732971191,0.5550000071525574,0.5630000233650208,0.5580000281333923,0.5479999780654907,0.5609999895095825,0.5429999828338623,0.5590000152587891,0.5630000233650208,0.5540000200271606,0.5590000152587891,0.5609999895095825,0.5569999814033508,0.5490000247955322,0.5550000071525574,0.5590000152587891,0.5640000104904175,0.5630000233650208,0.5580000281333923,0.5720000267028809,0.5540000200271606,0.5680000185966492,0.5630000233650208,0.5699999928474426,0.5440000295639038,0.5669999718666077,0.5509999990463257,0.5509999990463257,0.5519999861717224,0.5479999780654907,0.5509999990463257,0.5440000295639038,0.5559999942779541,0.5569999814033508,0.5609999895095825,0.5509999990463257,0.5659999847412109,0.5460000038146973,0.5550000071525574,0.5600000023841858,0.5680000185966492,0.5619999766349792,0.5590000152587891,0.5559999942779541,0.5590000152587891,0.5540000200271606,0.5720000267028809,0.5709999799728394,0.5569999814033508,0.5690000057220459,0.5690000057220459,0.5680000185966492,0.5690000057220459,0.5580000281333923,0.5529999732971191,0.5619999766349792,0.5690000057220459,0.5559999942779541,0.5600000023841858,0.5590000152587891,0.5630000233650208,0.5720000267028809,0.5630000233650208,0.5559999942779541,0.5580000281333923,0.5640000104904175,0.5659999847412109,0.5630000233650208,0.5709999799728394,0.5669999718666077,0.5649999976158142,0.5740000009536743,0.5630000233650208,0.5619999766349792,0.5590000152587891,0.5640000104904175,0.5609999895095825,0.5709999799728394,0.5649999976158142,0.5609999895095825,0.5680000185966492,0.5559999942779541,0.5640000104904175,0.5569999814033508,0.5519999861717224,0.5559999942779541,0.5609999895095825,0.5659999847412109,0.5659999847412109,0.5699999928474426,0.5529999732971191,0.5649999976158142,0.5600000023841858,0.5630000233650208,0.5590000152587891,0.5569999814033508,0.5569999814033508,0.5640000104904175,0.5569999814033508,0.5690000057220459,0.5659999847412109,0.5550000071525574,0.5630000233650208,0.5630000233650208,0.5649999976158142,0.5600000023841858,0.5640000104904175,0.5630000233650208,0.5690000057220459,0.5609999895095825],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.4979999959468841,0.5059999823570251,0.5210000276565552,0.5170000195503235,0.5210000276565552,0.5189999938011169,0.5389999747276306,0.5260000228881836,0.5149999856948853,0.5239999890327454,0.5350000262260437,0.5350000262260437,0.5410000085830688,0.5410000085830688,0.5550000071525574,0.5260000228881836,0.5299999713897705,0.5370000004768372,0.5350000262260437,0.5350000262260437,0.5249999761581421,0.5410000085830688,0.5440000295639038,0.5350000262260437,0.546999990940094,0.5180000066757202,0.5339999794960022,0.5419999957084656,0.5379999876022339,0.5509999990463257,0.5519999861717224,0.5389999747276306,0.5260000228881836,0.5440000295639038,0.5379999876022339,0.5440000295639038,0.5479999780654907,0.5419999957084656,0.5450000166893005,0.5320000052452087,0.5440000295639038,0.5509999990463257,0.5400000214576721,0.5540000200271606,0.5429999828338623,0.5320000052452087,0.550000011920929,0.5389999747276306,0.5580000281333923,0.5460000038146973,0.5379999876022339,0.546999990940094,0.5559999942779541,0.5379999876022339,0.5580000281333923,0.5370000004768372,0.5450000166893005,0.5490000247955322,0.5329999923706055,0.5350000262260437,0.546999990940094,0.5479999780654907,0.550000011920929,0.5529999732971191,0.546999990940094,0.5440000295639038,0.5360000133514404,0.5410000085830688,0.5440000295639038,0.5440000295639038,0.5440000295639038,0.5440000295639038,0.5400000214576721,0.550000011920929,0.5410000085830688,0.5379999876022339,0.5360000133514404,0.5519999861717224,0.5440000295639038,0.5400000214576721,0.5619999766349792,0.5519999861717224,0.5590000152587891,0.5540000200271606,0.5509999990463257,0.5509999990463257,0.5619999766349792,0.5509999990463257,0.5450000166893005,0.546999990940094,0.550000011920929,0.5559999942779541,0.5609999895095825,0.5379999876022339,0.5540000200271606,0.5440000295639038,0.5429999828338623,0.5519999861717224,0.5479999780654907,0.5410000085830688,0.5559999942779541,0.5569999814033508,0.5509999990463257,0.5490000247955322,0.5659999847412109,0.5550000071525574,0.5569999814033508,0.5450000166893005,0.5569999814033508,0.5630000233650208,0.5649999976158142,0.5460000038146973,0.5580000281333923,0.5529999732971191,0.5580000281333923,0.5659999847412109,0.5569999814033508,0.546999990940094,0.5509999990463257,0.5509999990463257,0.5559999942779541,0.5540000200271606,0.546999990940094,0.5609999895095825,0.5410000085830688,0.5450000166893005,0.5569999814033508,0.5540000200271606,0.5649999976158142,0.550000011920929,0.5669999718666077,0.5550000071525574,0.5590000152587891,0.5559999942779541,0.5569999814033508,0.550000011920929,0.5619999766349792,0.5540000200271606,0.5400000214576721,0.5419999957084656,0.5509999990463257,0.5529999732971191,0.5490000247955322,0.5550000071525574,0.5529999732971191,0.546999990940094,0.5550000071525574,0.5609999895095825,0.5600000023841858,0.5619999766349792,0.5630000233650208,0.5490000247955322,0.5540000200271606,0.5529999732971191,0.5540000200271606,0.5590000152587891,0.550000011920929,0.5590000152587891,0.5509999990463257,0.5640000104904175,0.5590000152587891,0.5509999990463257,0.5559999942779541,0.5479999780654907,0.550000011920929,0.5540000200271606,0.5609999895095825],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.5170000195503235,0.5090000033378601,0.5120000243186951,0.5220000147819519,0.515999972820282,0.5239999890327454,0.5289999842643738,0.5090000033378601,0.5260000228881836,0.5230000019073486,0.5199999809265137,0.5199999809265137,0.5170000195503235,0.531000018119812,0.5339999794960022,0.5329999923706055,0.5429999828338623,0.5239999890327454,0.550000011920929,0.5460000038146973,0.5429999828338623,0.5410000085830688,0.5460000038146973,0.527999997138977,0.5320000052452087,0.5419999957084656,0.5389999747276306,0.5329999923706055,0.5249999761581421,0.5329999923706055,0.5490000247955322,0.5460000038146973,0.5360000133514404,0.5479999780654907,0.5270000100135803,0.5429999828338623,0.5289999842643738,0.5370000004768372,0.5600000023841858,0.5360000133514404,0.5249999761581421,0.5490000247955322,0.5400000214576721,0.5479999780654907,0.5450000166893005,0.5389999747276306,0.5350000262260437,0.5329999923706055,0.5419999957084656,0.5389999747276306,0.5519999861717224,0.550000011920929,0.5540000200271606,0.531000018119812,0.546999990940094,0.5389999747276306,0.5410000085830688,0.5379999876022339,0.5339999794960022,0.550000011920929,0.5419999957084656,0.5529999732971191,0.5299999713897705,0.5450000166893005,0.5630000233650208,0.5440000295639038,0.546999990940094,0.550000011920929,0.5540000200271606,0.5690000057220459,0.5540000200271606,0.5379999876022339,0.5649999976158142,0.5479999780654907,0.550000011920929,0.5460000038146973,0.5569999814033508,0.5550000071525574,0.5659999847412109,0.5569999814033508,0.5569999814033508,0.5590000152587891,0.5519999861717224,0.5550000071525574,0.5580000281333923,0.5540000200271606,0.5569999814033508,0.5609999895095825,0.5569999814033508,0.5490000247955322,0.5529999732971191,0.5479999780654907,0.5529999732971191,0.5529999732971191,0.5479999780654907,0.5590000152587891,0.5529999732971191,0.5609999895095825,0.5490000247955322,0.5540000200271606,0.5609999895095825,0.5519999861717224,0.5490000247955322,0.5509999990463257,0.550000011920929,0.5630000233650208,0.5600000023841858,0.5509999990463257,0.5640000104904175,0.5540000200271606,0.5590000152587891,0.5600000023841858,0.5669999718666077,0.5559999942779541,0.546999990940094,0.5540000200271606,0.5640000104904175,0.5669999718666077,0.5550000071525574,0.5770000219345093,0.5649999976158142,0.5640000104904175,0.5529999732971191,0.5559999942779541,0.5590000152587891,0.5640000104904175,0.5669999718666077,0.5550000071525574,0.5580000281333923,0.5720000267028809,0.5690000057220459,0.5659999847412109,0.5659999847412109,0.574999988079071,0.5580000281333923,0.5669999718666077,0.5580000281333923,0.5630000233650208,0.5569999814033508,0.5740000009536743,0.5649999976158142,0.5740000009536743,0.5720000267028809,0.5730000138282776,0.5699999928474426,0.5709999799728394,0.5709999799728394,0.5669999718666077,0.5699999928474426,0.5709999799728394,0.5720000267028809,0.5699999928474426,0.5680000185966492,0.5619999766349792,0.5709999799728394,0.5720000267028809,0.5580000281333923,0.5649999976158142,0.5619999766349792,0.5709999799728394,0.5619999766349792,0.5690000057220459,0.5630000233650208,0.5680000185966492,0.5619999766349792,0.5640000104904175,0.5649999976158142],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.5049999952316284,0.5019999742507935,0.5139999985694885,0.4979999959468841,0.5099999904632568,0.5120000243186951,0.5210000276565552,0.515999972820282,0.5070000290870667,0.5210000276565552,0.5120000243186951,0.5220000147819519,0.5299999713897705,0.5339999794960022,0.5400000214576721,0.5230000019073486,0.5260000228881836,0.5239999890327454,0.5490000247955322,0.5460000038146973,0.5490000247955322,0.5370000004768372,0.5389999747276306,0.5389999747276306,0.5260000228881836,0.5379999876022339,0.5339999794960022,0.5410000085830688,0.5339999794960022,0.550000011920929,0.5360000133514404,0.5429999828338623,0.5490000247955322,0.5370000004768372,0.5619999766349792,0.5580000281333923,0.5419999957084656,0.5389999747276306,0.5389999747276306,0.5360000133514404,0.5529999732971191,0.550000011920929,0.5630000233650208,0.5519999861717224,0.5619999766349792,0.5569999814033508,0.5569999814033508,0.5509999990463257,0.5630000233650208,0.5559999942779541,0.5529999732971191,0.5559999942779541,0.5709999799728394,0.5740000009536743,0.5410000085830688,0.5460000038146973,0.546999990940094,0.5569999814033508,0.5690000057220459,0.5529999732971191,0.5540000200271606,0.5519999861717224,0.5519999861717224,0.5509999990463257,0.5580000281333923,0.5649999976158142,0.5559999942779541,0.5640000104904175,0.5440000295639038,0.5559999942779541,0.5419999957084656,0.5580000281333923,0.5659999847412109,0.5519999861717224,0.5450000166893005,0.574999988079071,0.5799999833106995,0.5550000071525574,0.5569999814033508,0.5460000038146973,0.5590000152587891,0.5559999942779541,0.5569999814033508,0.5550000071525574,0.5550000071525574,0.5630000233650208,0.5550000071525574,0.5460000038146973,0.5540000200271606,0.5619999766349792,0.5540000200271606,0.5580000281333923,0.5659999847412109,0.5580000281333923,0.5659999847412109,0.5509999990463257,0.5490000247955322,0.5519999861717224,0.5529999732971191,0.5440000295639038,0.5540000200271606,0.5540000200271606,0.5519999861717224,0.5550000071525574,0.5400000214576721,0.5509999990463257,0.5460000038146973,0.5600000023841858,0.5540000200271606,0.5440000295639038,0.5590000152587891,0.5590000152587891,0.5680000185966492,0.5569999814033508,0.5640000104904175,0.5529999732971191,0.5669999718666077,0.5690000057220459,0.5609999895095825,0.5580000281333923,0.5540000200271606,0.550000011920929,0.5590000152587891,0.5540000200271606,0.5630000233650208,0.5649999976158142,0.5669999718666077,0.5690000057220459,0.5699999928474426,0.5669999718666077,0.5699999928474426,0.5529999732971191,0.5590000152587891,0.5699999928474426,0.5640000104904175,0.5490000247955322,0.5580000281333923,0.5619999766349792,0.5569999814033508,0.5509999990463257,0.5569999814033508,0.5550000071525574,0.5550000071525574,0.5540000200271606,0.5609999895095825,0.5659999847412109,0.5550000071525574,0.5609999895095825,0.5609999895095825,0.5600000023841858,0.5609999895095825,0.5550000071525574,0.5640000104904175,0.5580000281333923,0.5590000152587891,0.5630000233650208,0.5659999847412109,0.5600000023841858,0.5559999942779541,0.5569999814033508,0.5569999814033508,0.5540000200271606,0.5669999718666077,0.5720000267028809,0.5680000185966492,0.5699999928474426,0.5590000152587891],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.5009999871253967,0.4979999959468841,0.5040000081062317,0.5249999761581421,0.5170000195503235,0.5210000276565552,0.5379999876022339,0.5350000262260437,0.5350000262260437,0.5460000038146973,0.5289999842643738,0.5320000052452087,0.5460000038146973,0.5389999747276306,0.5450000166893005,0.5289999842643738,0.5400000214576721,0.5410000085830688,0.5379999876022339,0.5540000200271606,0.5509999990463257,0.5370000004768372,0.5419999957084656,0.5460000038146973,0.5450000166893005,0.5519999861717224,0.5299999713897705,0.5630000233650208,0.5630000233650208,0.5590000152587891,0.5550000071525574,0.5519999861717224,0.5440000295639038,0.5479999780654907,0.5440000295639038,0.5529999732971191,0.5640000104904175,0.5559999942779541,0.5619999766349792,0.550000011920929,0.5630000233650208,0.5490000247955322,0.5559999942779541,0.550000011920929,0.5590000152587891,0.5609999895095825,0.5529999732971191,0.5509999990463257,0.5529999732971191,0.5580000281333923,0.5479999780654907,0.5509999990463257,0.5590000152587891,0.5529999732971191,0.5450000166893005,0.5649999976158142,0.5590000152587891,0.5630000233650208,0.5550000071525574,0.5600000023841858,0.5550000071525574,0.5680000185966492,0.5680000185966492,0.5699999928474426,0.5580000281333923,0.5619999766349792,0.5659999847412109,0.5690000057220459,0.5820000171661377,0.5659999847412109,0.5559999942779541,0.5720000267028809,0.5609999895095825,0.5680000185966492,0.5630000233650208,0.550000011920929,0.5590000152587891,0.5649999976158142,0.5529999732971191,0.5730000138282776,0.5720000267028809,0.5569999814033508,0.5619999766349792,0.5509999990463257,0.5630000233650208,0.5619999766349792,0.5529999732971191,0.5680000185966492,0.5609999895095825,0.5640000104904175,0.5690000057220459,0.5529999732971191,0.5600000023841858,0.5699999928474426,0.5659999847412109,0.5600000023841858,0.5849999785423279,0.5809999704360962,0.5899999737739563,0.5640000104904175,0.5709999799728394,0.5680000185966492,0.5609999895095825,0.5630000233650208,0.5830000042915344,0.5740000009536743,0.5720000267028809,0.574999988079071,0.5690000057220459,0.5659999847412109,0.5680000185966492,0.5799999833106995,0.5669999718666077,0.5759999752044678,0.5699999928474426,0.578000009059906,0.5699999928474426,0.5889999866485596,0.5740000009536743,0.578000009059906,0.5830000042915344,0.5699999928474426,0.5709999799728394,0.5789999961853027,0.5759999752044678,0.578000009059906,0.5799999833106995,0.5860000252723694,0.5789999961853027,0.5899999737739563,0.574999988079071,0.5879999995231628,0.5669999718666077,0.5820000171661377,0.578000009059906,0.578000009059906,0.5690000057220459,0.5740000009536743,0.5720000267028809,0.5740000009536743,0.5820000171661377,0.5830000042915344,0.574999988079071,0.5789999961853027,0.5849999785423279,0.5720000267028809,0.5849999785423279,0.5839999914169312,0.5789999961853027,0.5899999737739563,0.5799999833106995,0.5699999928474426,0.5839999914169312,0.5879999995231628,0.5839999914169312,0.5870000123977661,0.5809999704360962,0.5889999866485596,0.5789999961853027,0.5929999947547913,0.5730000138282776,0.5809999704360962,0.5870000123977661,0.574999988079071,0.5809999704360962,0.5860000252723694,0.5849999785423279],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.515999972820282,0.5180000066757202,0.5199999809265137,0.5130000114440918,0.5189999938011169,0.5339999794960022,0.5320000052452087,0.5270000100135803,0.5220000147819519,0.531000018119812,0.5139999985694885,0.5249999761581421,0.5049999952316284,0.531000018119812,0.5249999761581421,0.5429999828338623,0.5460000038146973,0.5149999856948853,0.5180000066757202,0.515999972820282,0.5350000262260437,0.527999997138977,0.5189999938011169,0.5220000147819519,0.5329999923706055,0.5360000133514404,0.5400000214576721,0.5239999890327454,0.5320000052452087,0.5329999923706055,0.5329999923706055,0.5260000228881836,0.5329999923706055,0.5460000038146973,0.5230000019073486,0.5410000085830688,0.5320000052452087,0.5450000166893005,0.5379999876022339,0.5170000195503235,0.5379999876022339,0.5260000228881836,0.5239999890327454,0.5239999890327454,0.5440000295639038,0.5339999794960022,0.5299999713897705,0.546999990940094,0.5440000295639038,0.5419999957084656,0.5440000295639038,0.5260000228881836,0.5429999828338623,0.5429999828338623,0.5440000295639038,0.546999990940094,0.5450000166893005,0.5429999828338623,0.550000011920929,0.5450000166893005,0.5460000038146973,0.5360000133514404,0.5429999828338623,0.5419999957084656,0.5529999732971191,0.5509999990463257,0.5709999799728394,0.5450000166893005,0.5440000295639038,0.5289999842643738,0.5640000104904175,0.5460000038146973,0.5519999861717224,0.527999997138977,0.5580000281333923,0.5389999747276306,0.5479999780654907,0.546999990940094,0.5379999876022339,0.550000011920929,0.550000011920929,0.5490000247955322,0.5440000295639038,0.5490000247955322,0.5559999942779541,0.5410000085830688,0.5440000295639038,0.5529999732971191,0.5440000295639038,0.5580000281333923,0.5460000038146973,0.5600000023841858,0.5529999732971191,0.550000011920929,0.5299999713897705,0.5460000038146973,0.5559999942779541,0.5519999861717224,0.5440000295639038,0.5410000085830688,0.5659999847412109,0.5529999732971191,0.5550000071525574,0.5490000247955322,0.5529999732971191,0.5490000247955322,0.5569999814033508,0.5329999923706055,0.5479999780654907,0.5640000104904175,0.5669999718666077,0.5680000185966492,0.5630000233650208,0.5690000057220459,0.5509999990463257,0.5550000071525574,0.5600000023841858,0.5659999847412109,0.5559999942779541,0.5630000233650208,0.5600000023841858,0.5460000038146973,0.5529999732971191,0.550000011920929,0.5400000214576721,0.5529999732971191,0.5529999732971191,0.5619999766349792,0.5659999847412109,0.5559999942779541,0.5720000267028809,0.5600000023841858,0.5540000200271606,0.5550000071525574,0.5529999732971191,0.5619999766349792,0.5429999828338623,0.5619999766349792,0.5580000281333923,0.5619999766349792,0.5559999942779541,0.5609999895095825,0.5640000104904175,0.5569999814033508,0.5600000023841858,0.5569999814033508,0.5569999814033508,0.546999990940094,0.5529999732971191,0.5559999942779541,0.5419999957084656,0.5519999861717224,0.5509999990463257,0.5540000200271606,0.5509999990463257,0.5509999990463257,0.5559999942779541,0.5609999895095825,0.5580000281333923,0.5479999780654907,0.5580000281333923,0.5559999942779541,0.5519999861717224,0.5569999814033508,0.5479999780654907,0.5460000038146973,0.5540000200271606],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.5080000162124634,0.5059999823570251,0.5040000081062317,0.5009999871253967,0.5080000162124634,0.5070000290870667,0.5099999904632568,0.5099999904632568,0.5139999985694885,0.5090000033378601,0.5130000114440918,0.5099999904632568,0.5139999985694885,0.5220000147819519,0.5099999904632568,0.5239999890327454,0.5299999713897705,0.5239999890327454,0.5450000166893005,0.5329999923706055,0.5360000133514404,0.5350000262260437,0.5270000100135803,0.5249999761581421,0.5230000019073486,0.5389999747276306,0.5389999747276306,0.5220000147819519,0.5289999842643738,0.527999997138977,0.5429999828338623,0.5370000004768372,0.5320000052452087,0.5419999957084656,0.5239999890327454,0.5419999957084656,0.5460000038146973,0.5429999828338623,0.5339999794960022,0.5249999761581421,0.5450000166893005,0.5529999732971191,0.5260000228881836,0.5329999923706055,0.5260000228881836,0.5350000262260437,0.5220000147819519,0.5350000262260437,0.5339999794960022,0.5559999942779541,0.5320000052452087,0.5519999861717224,0.5339999794960022,0.5299999713897705,0.5370000004768372,0.546999990940094,0.5230000019073486,0.5339999794960022,0.5519999861717224,0.5460000038146973,0.5329999923706055,0.5249999761581421,0.5339999794960022,0.5400000214576721,0.5450000166893005,0.546999990940094,0.5339999794960022,0.5389999747276306,0.5450000166893005,0.5400000214576721,0.5400000214576721,0.531000018119812,0.5389999747276306,0.5419999957084656,0.5479999780654907,0.5379999876022339,0.5400000214576721,0.5440000295639038,0.5440000295639038,0.5429999828338623,0.5490000247955322,0.5419999957084656,0.5490000247955322,0.5509999990463257,0.5450000166893005,0.5370000004768372,0.5550000071525574,0.531000018119812,0.5230000019073486,0.5389999747276306,0.5400000214576721,0.5410000085830688,0.5400000214576721,0.5329999923706055,0.5360000133514404,0.5410000085830688,0.5360000133514404,0.5440000295639038,0.5410000085830688,0.546999990940094,0.5260000228881836,0.527999997138977,0.5299999713897705,0.5440000295639038,0.5569999814033508,0.5659999847412109,0.5550000071525574,0.5379999876022339,0.5590000152587891,0.5550000071525574,0.5460000038146973,0.5440000295639038,0.5400000214576721,0.5410000085830688,0.5450000166893005,0.5419999957084656,0.5360000133514404,0.5479999780654907,0.5419999957084656,0.5529999732971191,0.5419999957084656,0.550000011920929,0.5479999780654907,0.546999990940094,0.5450000166893005,0.5519999861717224,0.550000011920929,0.5640000104904175,0.5519999861717224,0.550000011920929,0.5440000295639038,0.5370000004768372,0.5400000214576721,0.5460000038146973,0.5490000247955322,0.5440000295639038,0.550000011920929,0.5540000200271606,0.5619999766349792,0.546999990940094,0.5419999957084656,0.5590000152587891,0.5559999942779541,0.5509999990463257,0.5440000295639038,0.5609999895095825,0.550000011920929,0.5540000200271606,0.5429999828338623,0.5540000200271606,0.5559999942779541,0.5540000200271606,0.5509999990463257,0.5460000038146973,0.5540000200271606,0.5540000200271606,0.5389999747276306,0.5490000247955322,0.5490000247955322,0.5389999747276306,0.5450000166893005,0.5460000038146973,0.5360000133514404,0.5419999957084656,0.5490000247955322,0.5460000038146973,0.5460000038146973],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.515999972820282,0.5139999985694885,0.5270000100135803,0.5130000114440918,0.5230000019073486,0.5180000066757202,0.5249999761581421,0.5059999823570251,0.5379999876022339,0.5189999938011169,0.5329999923706055,0.5379999876022339,0.5389999747276306,0.5270000100135803,0.5379999876022339,0.5199999809265137,0.5360000133514404,0.5320000052452087,0.5299999713897705,0.5320000052452087,0.5320000052452087,0.5230000019073486,0.5350000262260437,0.5320000052452087,0.515999972820282,0.5320000052452087,0.5410000085830688,0.5239999890327454,0.5270000100135803,0.5429999828338623,0.5490000247955322,0.546999990940094,0.5490000247955322,0.5479999780654907,0.5329999923706055,0.5479999780654907,0.5299999713897705,0.546999990940094,0.5400000214576721,0.5460000038146973,0.5370000004768372,0.5350000262260437,0.5529999732971191,0.5429999828338623,0.5429999828338623,0.5450000166893005,0.546999990940094,0.5460000038146973,0.5289999842643738,0.546999990940094,0.5410000085830688,0.5460000038146973,0.5569999814033508,0.5370000004768372,0.5429999828338623,0.550000011920929,0.5329999923706055,0.5540000200271606,0.5370000004768372,0.5370000004768372,0.5389999747276306,0.5419999957084656,0.5379999876022339,0.546999990940094,0.5640000104904175,0.5659999847412109,0.5519999861717224,0.5410000085830688,0.5479999780654907,0.5529999732971191,0.550000011920929,0.5479999780654907,0.5519999861717224,0.5440000295639038,0.5550000071525574,0.5569999814033508,0.5479999780654907,0.5450000166893005,0.5460000038146973,0.5540000200271606,0.5580000281333923,0.5460000038146973,0.550000011920929,0.5540000200271606,0.5519999861717224,0.5490000247955322,0.5450000166893005,0.5479999780654907,0.5550000071525574,0.5550000071525574,0.546999990940094,0.5600000023841858,0.546999990940094,0.5509999990463257,0.550000011920929,0.5490000247955322,0.5479999780654907,0.5640000104904175,0.5529999732971191,0.5609999895095825,0.5450000166893005,0.5569999814033508,0.5339999794960022,0.527999997138977,0.546999990940094,0.5569999814033508,0.5609999895095825,0.550000011920929,0.5580000281333923,0.546999990940094,0.5619999766349792,0.5519999861717224,0.5590000152587891,0.5550000071525574,0.5519999861717224,0.5619999766349792,0.5569999814033508,0.5630000233650208,0.5580000281333923,0.5680000185966492,0.5619999766349792,0.5569999814033508,0.5580000281333923,0.5490000247955322,0.5460000038146973,0.5540000200271606,0.5590000152587891,0.5460000038146973,0.5609999895095825,0.5569999814033508,0.5529999732971191,0.5550000071525574,0.5559999942779541,0.5490000247955322,0.5450000166893005,0.5519999861717224,0.5559999942779541,0.5590000152587891,0.5479999780654907,0.5590000152587891,0.5419999957084656,0.5440000295639038,0.550000011920929,0.5419999957084656,0.5519999861717224,0.5559999942779541,0.5559999942779541,0.5609999895095825,0.5600000023841858,0.5540000200271606,0.5479999780654907,0.5550000071525574,0.5619999766349792,0.5590000152587891,0.5490000247955322,0.5460000038146973,0.5609999895095825,0.5429999828338623,0.5529999732971191,0.5479999780654907,0.5509999990463257,0.5559999942779541,0.5590000152587891,0.5619999766349792,0.5550000071525574,0.5619999766349792,0.5540000200271606,0.5529999732971191],"label":"FineWeb URL dedup"}},"winogrande/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.5,0.4979999959468841,0.4950000047683716,0.4950000047683716,0.5049999952316284,0.5329999923706055,0.5220000147819519,0.5139999985694885,0.5339999794960022,0.5130000114440918,0.5389999747276306,0.5400000214576721,0.5270000100135803,0.5260000228881836,0.5370000004768372,0.527999997138977,0.5289999842643738,0.5339999794960022,0.5270000100135803,0.531000018119812,0.527999997138977,0.5400000214576721,0.5479999780654907,0.550000011920929,0.5400000214576721,0.5350000262260437,0.5410000085830688,0.5379999876022339,0.5299999713897705,0.5490000247955322,0.5509999990463257,0.5519999861717224,0.5429999828338623,0.5429999828338623,0.5440000295639038,0.5379999876022339,0.5379999876022339,0.5419999957084656,0.5609999895095825,0.5540000200271606,0.5370000004768372,0.5440000295639038,0.5410000085830688,0.5379999876022339,0.5329999923706055,0.5419999957084656,0.5419999957084656,0.5519999861717224,0.550000011920929,0.5509999990463257,0.5400000214576721,0.5450000166893005,0.5509999990463257,0.5569999814033508,0.5550000071525574,0.5590000152587891,0.5479999780654907,0.5550000071525574,0.5440000295639038,0.5460000038146973,0.546999990940094,0.5559999942779541,0.5550000071525574,0.5490000247955322,0.5440000295639038,0.546999990940094,0.5450000166893005,0.546999990940094,0.5649999976158142,0.5490000247955322,0.5519999861717224,0.550000011920929,0.5509999990463257,0.5519999861717224,0.5519999861717224,0.5529999732971191,0.5490000247955322,0.546999990940094,0.550000011920929,0.5720000267028809,0.5619999766349792,0.5490000247955322,0.5680000185966492,0.5519999861717224,0.5569999814033508,0.5509999990463257,0.5619999766349792,0.5630000233650208,0.5529999732971191,0.5619999766349792,0.5609999895095825,0.550000011920929,0.5479999780654907,0.5529999732971191,0.5519999861717224,0.5580000281333923,0.5590000152587891,0.5529999732971191,0.550000011920929,0.5680000185966492,0.5580000281333923,0.5630000233650208,0.5630000233650208,0.5559999942779541,0.5649999976158142,0.5569999814033508,0.5649999976158142,0.5659999847412109,0.5559999942779541,0.5659999847412109,0.5630000233650208,0.5509999990463257,0.5669999718666077,0.5669999718666077,0.5479999780654907,0.5540000200271606,0.5580000281333923,0.5519999861717224,0.5590000152587891,0.5590000152587891,0.5619999766349792,0.5509999990463257,0.546999990940094,0.5609999895095825,0.5540000200271606,0.5630000233650208,0.5580000281333923,0.5559999942779541,0.5680000185966492,0.5649999976158142,0.5619999766349792,0.5580000281333923,0.5630000233650208,0.5559999942779541,0.5540000200271606,0.5540000200271606,0.5569999814033508,0.5619999766349792,0.5559999942779541,0.5600000023841858,0.5460000038146973,0.5429999828338623,0.5580000281333923,0.5550000071525574,0.5580000281333923,0.5540000200271606,0.5609999895095825,0.5519999861717224,0.550000011920929,0.5519999861717224,0.5590000152587891,0.5619999766349792,0.5600000023841858,0.5590000152587891,0.5690000057220459,0.5640000104904175,0.5580000281333923,0.5559999942779541,0.5569999814033508,0.5569999814033508,0.5540000200271606,0.5640000104904175,0.5600000023841858,0.5550000071525574,0.5640000104904175,0.5600000023841858,0.5540000200271606],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.4979999959468841,0.4909999966621399,0.5040000081062317,0.5220000147819519,0.5130000114440918,0.5120000243186951,0.5120000243186951,0.5120000243186951,0.5170000195503235,0.5149999856948853,0.515999972820282,0.5270000100135803,0.5239999890327454,0.5210000276565552,0.5270000100135803,0.527999997138977,0.5289999842643738,0.5329999923706055,0.5239999890327454,0.5230000019073486,0.5239999890327454,0.527999997138977,0.5490000247955322,0.5370000004768372,0.5440000295639038,0.5320000052452087,0.5429999828338623,0.5410000085830688,0.5289999842643738,0.5529999732971191,0.5389999747276306,0.5289999842643738,0.5210000276565552,0.5320000052452087,0.5350000262260437,0.5370000004768372,0.531000018119812,0.5360000133514404,0.5299999713897705,0.5370000004768372,0.5379999876022339,0.5400000214576721,0.5270000100135803,0.5400000214576721,0.5379999876022339,0.5370000004768372,0.5490000247955322,0.5410000085830688,0.5559999942779541,0.5370000004768372,0.5419999957084656,0.5410000085830688,0.5410000085830688,0.5320000052452087,0.5370000004768372,0.5370000004768372,0.5479999780654907,0.5370000004768372,0.5239999890327454,0.531000018119812,0.5350000262260437,0.5429999828338623,0.5479999780654907,0.5400000214576721,0.5490000247955322,0.546999990940094,0.5400000214576721,0.5479999780654907,0.5339999794960022,0.5479999780654907,0.5289999842643738,0.5440000295639038,0.5389999747276306,0.5450000166893005,0.5479999780654907,0.5440000295639038,0.5440000295639038,0.5529999732971191,0.5419999957084656,0.5450000166893005,0.5540000200271606,0.5379999876022339,0.5440000295639038,0.5569999814033508,0.5429999828338623,0.5450000166893005,0.5609999895095825,0.5550000071525574,0.5460000038146973,0.5400000214576721,0.5529999732971191,0.5509999990463257,0.5600000023841858,0.5519999861717224,0.5490000247955322,0.5370000004768372,0.5550000071525574,0.5490000247955322,0.5350000262260437,0.546999990940094,0.5540000200271606,0.5479999780654907,0.5479999780654907,0.550000011920929,0.5559999942779541,0.550000011920929,0.5590000152587891,0.5550000071525574,0.5429999828338623,0.5490000247955322,0.550000011920929,0.5429999828338623,0.5460000038146973,0.5559999942779541,0.5529999732971191,0.5460000038146973,0.5460000038146973,0.5490000247955322,0.550000011920929,0.5569999814033508,0.5640000104904175,0.5590000152587891,0.5540000200271606,0.5400000214576721,0.5509999990463257,0.5540000200271606,0.5590000152587891,0.5550000071525574,0.5609999895095825,0.5559999942779541,0.5559999942779541,0.5429999828338623,0.5619999766349792,0.5509999990463257,0.5529999732971191,0.5569999814033508,0.5429999828338623,0.5509999990463257,0.5569999814033508,0.5529999732971191,0.5519999861717224,0.5640000104904175,0.5550000071525574,0.5640000104904175,0.5600000023841858,0.5600000023841858,0.5609999895095825,0.5590000152587891,0.5569999814033508,0.5559999942779541,0.5600000023841858,0.5590000152587891,0.5529999732971191,0.5649999976158142,0.5600000023841858,0.5640000104904175,0.550000011920929,0.5600000023841858,0.5519999861717224,0.5590000152587891,0.5529999732971191,0.5540000200271606,0.5580000281333923,0.5630000233650208,0.5559999942779541,0.5669999718666077,0.5559999942779541],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.5239999890327454,0.4900000095367431,0.5040000081062317,0.5099999904632568,0.4990000128746032,0.5170000195503235,0.5040000081062317,0.5009999871253967,0.5230000019073486,0.5109999775886536,0.5059999823570251,0.5130000114440918,0.5090000033378601,0.5220000147819519,0.5189999938011169,0.5180000066757202,0.5220000147819519,0.5120000243186951,0.5460000038146973,0.5239999890327454,0.5289999842643738,0.5440000295639038,0.5339999794960022,0.5299999713897705,0.5260000228881836,0.5360000133514404,0.5339999794960022,0.5360000133514404,0.5299999713897705,0.5180000066757202,0.5249999761581421,0.5440000295639038,0.5299999713897705,0.5339999794960022,0.5239999890327454,0.527999997138977,0.5139999985694885,0.5289999842643738,0.5360000133514404,0.5260000228881836,0.5389999747276306,0.5460000038146973,0.5270000100135803,0.5339999794960022,0.5320000052452087,0.5329999923706055,0.5260000228881836,0.5220000147819519,0.5260000228881836,0.5379999876022339,0.5410000085830688,0.5350000262260437,0.5389999747276306,0.5320000052452087,0.5389999747276306,0.5379999876022339,0.5329999923706055,0.5270000100135803,0.5170000195503235,0.5329999923706055,0.5370000004768372,0.5379999876022339,0.5249999761581421,0.5479999780654907,0.546999990940094,0.5400000214576721,0.5440000295639038,0.5360000133514404,0.5450000166893005,0.5440000295639038,0.5370000004768372,0.5370000004768372,0.5479999780654907,0.5379999876022339,0.5400000214576721,0.5479999780654907,0.5379999876022339,0.5509999990463257,0.5440000295639038,0.5379999876022339,0.550000011920929,0.5389999747276306,0.5370000004768372,0.5379999876022339,0.5419999957084656,0.5360000133514404,0.5509999990463257,0.5360000133514404,0.5419999957084656,0.5419999957084656,0.550000011920929,0.5360000133514404,0.5519999861717224,0.5540000200271606,0.546999990940094,0.5370000004768372,0.5379999876022339,0.5519999861717224,0.5329999923706055,0.5400000214576721,0.5429999828338623,0.550000011920929,0.5490000247955322,0.5360000133514404,0.550000011920929,0.5569999814033508,0.5490000247955322,0.5490000247955322,0.5479999780654907,0.5350000262260437,0.5490000247955322,0.5370000004768372,0.5440000295639038,0.5329999923706055,0.5440000295639038,0.5429999828338623,0.5389999747276306,0.5450000166893005,0.5320000052452087,0.5450000166893005,0.5400000214576721,0.5419999957084656,0.5460000038146973,0.5370000004768372,0.5400000214576721,0.5460000038146973,0.5370000004768372,0.5370000004768372,0.5460000038146973,0.5400000214576721,0.5490000247955322,0.5529999732971191,0.5379999876022339,0.5460000038146973,0.5450000166893005,0.5429999828338623,0.5460000038146973,0.5400000214576721,0.5479999780654907,0.5460000038146973,0.5540000200271606,0.5400000214576721,0.5350000262260437,0.5490000247955322,0.5460000038146973,0.5460000038146973,0.5509999990463257,0.5410000085830688,0.5429999828338623,0.5379999876022339,0.5450000166893005,0.5389999747276306,0.5400000214576721,0.5400000214576721,0.550000011920929,0.5440000295639038,0.5389999747276306,0.5450000166893005,0.5400000214576721,0.5389999747276306,0.5419999957084656,0.5410000085830688,0.5440000295639038,0.5519999861717224,0.5479999780654907,0.5450000166893005,0.5569999814033508],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.4830000102519989,0.4830000102519989,0.5049999952316284,0.5049999952316284,0.5019999742507935,0.492000013589859,0.5139999985694885,0.5130000114440918,0.5230000019073486,0.5270000100135803,0.5180000066757202,0.5210000276565552,0.5220000147819519,0.5270000100135803,0.5180000066757202,0.5260000228881836,0.5180000066757202,0.5130000114440918,0.5239999890327454,0.5220000147819519,0.5329999923706055,0.527999997138977,0.5189999938011169,0.5360000133514404,0.5299999713897705,0.5370000004768372,0.5220000147819519,0.5339999794960022,0.5410000085830688,0.5370000004768372,0.5339999794960022,0.5429999828338623,0.5429999828338623,0.5299999713897705,0.5479999780654907,0.5400000214576721,0.5350000262260437,0.5350000262260437,0.5339999794960022,0.5350000262260437,0.5540000200271606,0.5460000038146973,0.5630000233650208,0.5410000085830688,0.546999990940094,0.5519999861717224,0.5550000071525574,0.5479999780654907,0.5450000166893005,0.5479999780654907,0.5479999780654907,0.5550000071525574,0.5590000152587891,0.5559999942779541,0.5429999828338623,0.5450000166893005,0.5419999957084656,0.5440000295639038,0.546999990940094,0.5580000281333923,0.5429999828338623,0.5450000166893005,0.5379999876022339,0.550000011920929,0.5529999732971191,0.5569999814033508,0.5419999957084656,0.5569999814033508,0.5490000247955322,0.5540000200271606,0.5410000085830688,0.5519999861717224,0.5540000200271606,0.5370000004768372,0.5400000214576721,0.5619999766349792,0.5569999814033508,0.5479999780654907,0.5440000295639038,0.5550000071525574,0.550000011920929,0.550000011920929,0.5519999861717224,0.5479999780654907,0.5569999814033508,0.5709999799728394,0.5550000071525574,0.5490000247955322,0.5479999780654907,0.5540000200271606,0.5569999814033508,0.5490000247955322,0.5490000247955322,0.5559999942779541,0.5609999895095825,0.5540000200271606,0.5529999732971191,0.5590000152587891,0.5509999990463257,0.5490000247955322,0.5600000023841858,0.5490000247955322,0.550000011920929,0.5609999895095825,0.5529999732971191,0.5440000295639038,0.5450000166893005,0.5619999766349792,0.5450000166893005,0.5540000200271606,0.5550000071525574,0.5600000023841858,0.550000011920929,0.5569999814033508,0.5519999861717224,0.5400000214576721,0.5450000166893005,0.5600000023841858,0.5509999990463257,0.5529999732971191,0.5490000247955322,0.5440000295639038,0.5580000281333923,0.5559999942779541,0.5550000071525574,0.5659999847412109,0.5640000104904175,0.5600000023841858,0.5580000281333923,0.5550000071525574,0.5569999814033508,0.5550000071525574,0.5490000247955322,0.550000011920929,0.5460000038146973,0.5550000071525574,0.5509999990463257,0.5609999895095825,0.5529999732971191,0.5609999895095825,0.5609999895095825,0.5490000247955322,0.5569999814033508,0.550000011920929,0.5490000247955322,0.5550000071525574,0.5509999990463257,0.5569999814033508,0.5540000200271606,0.5540000200271606,0.5590000152587891,0.5540000200271606,0.5559999942779541,0.5529999732971191,0.5569999814033508,0.5580000281333923,0.5649999976158142,0.5600000023841858,0.5659999847412109,0.5509999990463257,0.5569999814033508,0.5519999861717224,0.5529999732971191,0.5630000233650208,0.5559999942779541,0.5649999976158142,0.5590000152587891],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.4880000054836273,0.492000013589859,0.5059999823570251,0.5139999985694885,0.5070000290870667,0.5090000033378601,0.5230000019073486,0.5189999938011169,0.5189999938011169,0.5220000147819519,0.5149999856948853,0.5260000228881836,0.5329999923706055,0.5180000066757202,0.5289999842643738,0.5400000214576721,0.5410000085830688,0.5440000295639038,0.5329999923706055,0.550000011920929,0.5419999957084656,0.5360000133514404,0.5429999828338623,0.5429999828338623,0.5450000166893005,0.5490000247955322,0.5400000214576721,0.5509999990463257,0.5559999942779541,0.5479999780654907,0.5540000200271606,0.5490000247955322,0.5400000214576721,0.5429999828338623,0.5460000038146973,0.5370000004768372,0.5479999780654907,0.5550000071525574,0.5490000247955322,0.5400000214576721,0.5410000085830688,0.5460000038146973,0.546999990940094,0.5479999780654907,0.546999990940094,0.5509999990463257,0.5450000166893005,0.5590000152587891,0.5419999957084656,0.5540000200271606,0.5440000295639038,0.5450000166893005,0.5580000281333923,0.5540000200271606,0.5440000295639038,0.5619999766349792,0.5450000166893005,0.5600000023841858,0.5559999942779541,0.5600000023841858,0.5400000214576721,0.5569999814033508,0.5600000023841858,0.5619999766349792,0.5529999732971191,0.5649999976158142,0.5609999895095825,0.5550000071525574,0.5609999895095825,0.5580000281333923,0.5550000071525574,0.5619999766349792,0.5550000071525574,0.5519999861717224,0.5600000023841858,0.5550000071525574,0.5550000071525574,0.5590000152587891,0.5490000247955322,0.5580000281333923,0.5600000023841858,0.5419999957084656,0.5559999942779541,0.5559999942779541,0.5529999732971191,0.5609999895095825,0.5519999861717224,0.5569999814033508,0.5569999814033508,0.5509999990463257,0.5619999766349792,0.546999990940094,0.5619999766349792,0.5460000038146973,0.5529999732971191,0.5619999766349792,0.5690000057220459,0.5680000185966492,0.5720000267028809,0.5640000104904175,0.5550000071525574,0.5509999990463257,0.550000011920929,0.5600000023841858,0.5609999895095825,0.5630000233650208,0.5649999976158142,0.5529999732971191,0.5540000200271606,0.5529999732971191,0.5659999847412109,0.5600000023841858,0.5590000152587891,0.5619999766349792,0.5600000023841858,0.5730000138282776,0.5569999814033508,0.5690000057220459,0.5619999766349792,0.5680000185966492,0.578000009059906,0.5730000138282776,0.5550000071525574,0.5529999732971191,0.5600000023841858,0.5630000233650208,0.5590000152587891,0.5659999847412109,0.5669999718666077,0.5609999895095825,0.5630000233650208,0.5569999814033508,0.5490000247955322,0.5619999766349792,0.5550000071525574,0.5630000233650208,0.5559999942779541,0.5559999942779541,0.5649999976158142,0.5569999814033508,0.5619999766349792,0.5559999942779541,0.5669999718666077,0.5609999895095825,0.5690000057220459,0.5770000219345093,0.5690000057220459,0.5720000267028809,0.5619999766349792,0.5649999976158142,0.5669999718666077,0.5680000185966492,0.5699999928474426,0.5640000104904175,0.5609999895095825,0.5740000009536743,0.5690000057220459,0.5669999718666077,0.5720000267028809,0.5699999928474426,0.5709999799728394,0.5740000009536743,0.5680000185966492,0.5619999766349792,0.5690000057220459,0.5659999847412109,0.574999988079071],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.4860000014305115,0.5040000081062317,0.5059999823570251,0.5220000147819519,0.5120000243186951,0.5220000147819519,0.5210000276565552,0.5189999938011169,0.5130000114440918,0.5199999809265137,0.5070000290870667,0.5210000276565552,0.503000020980835,0.5099999904632568,0.5139999985694885,0.527999997138977,0.5339999794960022,0.5170000195503235,0.5260000228881836,0.5320000052452087,0.5260000228881836,0.5329999923706055,0.5270000100135803,0.5260000228881836,0.5189999938011169,0.5230000019073486,0.5320000052452087,0.5170000195503235,0.5170000195503235,0.5239999890327454,0.5299999713897705,0.5260000228881836,0.5220000147819519,0.5329999923706055,0.5220000147819519,0.5339999794960022,0.527999997138977,0.5360000133514404,0.5299999713897705,0.515999972820282,0.5180000066757202,0.5180000066757202,0.5120000243186951,0.5230000019073486,0.5370000004768372,0.5289999842643738,0.5249999761581421,0.5360000133514404,0.5379999876022339,0.5350000262260437,0.5360000133514404,0.531000018119812,0.5350000262260437,0.5339999794960022,0.527999997138977,0.5370000004768372,0.5299999713897705,0.527999997138977,0.5400000214576721,0.531000018119812,0.531000018119812,0.5389999747276306,0.5419999957084656,0.531000018119812,0.5429999828338623,0.5410000085830688,0.5389999747276306,0.5370000004768372,0.5339999794960022,0.5289999842643738,0.531000018119812,0.5389999747276306,0.5329999923706055,0.5249999761581421,0.5479999780654907,0.527999997138977,0.5320000052452087,0.5370000004768372,0.5230000019073486,0.5440000295639038,0.5410000085830688,0.5329999923706055,0.5260000228881836,0.546999990940094,0.5419999957084656,0.5339999794960022,0.5350000262260437,0.5270000100135803,0.5249999761581421,0.5320000052452087,0.5239999890327454,0.527999997138977,0.5299999713897705,0.5450000166893005,0.5329999923706055,0.5440000295639038,0.5429999828338623,0.5429999828338623,0.5440000295639038,0.5350000262260437,0.5490000247955322,0.5410000085830688,0.5440000295639038,0.546999990940094,0.5270000100135803,0.5379999876022339,0.5410000085830688,0.5350000262260437,0.5360000133514404,0.5460000038146973,0.5479999780654907,0.5419999957084656,0.550000011920929,0.5410000085830688,0.5389999747276306,0.5490000247955322,0.5379999876022339,0.5400000214576721,0.550000011920929,0.5529999732971191,0.5460000038146973,0.546999990940094,0.5519999861717224,0.5440000295639038,0.5429999828338623,0.546999990940094,0.5410000085830688,0.5509999990463257,0.5479999780654907,0.5509999990463257,0.5540000200271606,0.550000011920929,0.5440000295639038,0.5419999957084656,0.5370000004768372,0.5410000085830688,0.5370000004768372,0.550000011920929,0.550000011920929,0.5429999828338623,0.550000011920929,0.550000011920929,0.5490000247955322,0.5509999990463257,0.5550000071525574,0.5540000200271606,0.5479999780654907,0.5370000004768372,0.5379999876022339,0.5389999747276306,0.5379999876022339,0.5329999923706055,0.5440000295639038,0.5479999780654907,0.5400000214576721,0.5490000247955322,0.5450000166893005,0.5490000247955322,0.5450000166893005,0.5429999828338623,0.550000011920929,0.5389999747276306,0.5400000214576721,0.5329999923706055,0.5460000038146973,0.5419999957084656,0.5479999780654907],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.4819999933242798,0.4880000054836273,0.4909999966621399,0.4979999959468841,0.5040000081062317,0.5099999904632568,0.5040000081062317,0.5120000243186951,0.503000020980835,0.5040000081062317,0.5040000081062317,0.5049999952316284,0.5009999871253967,0.5049999952316284,0.5070000290870667,0.5139999985694885,0.5239999890327454,0.5139999985694885,0.515999972820282,0.5230000019073486,0.5239999890327454,0.5170000195503235,0.5220000147819519,0.5199999809265137,0.5080000162124634,0.5149999856948853,0.5249999761581421,0.5299999713897705,0.5220000147819519,0.5220000147819519,0.5210000276565552,0.5410000085830688,0.5120000243186951,0.5320000052452087,0.5360000133514404,0.5410000085830688,0.5249999761581421,0.5239999890327454,0.5320000052452087,0.5230000019073486,0.5379999876022339,0.5389999747276306,0.5189999938011169,0.5270000100135803,0.5299999713897705,0.5270000100135803,0.5260000228881836,0.5350000262260437,0.5270000100135803,0.5389999747276306,0.531000018119812,0.5370000004768372,0.5249999761581421,0.527999997138977,0.5389999747276306,0.5320000052452087,0.5400000214576721,0.5299999713897705,0.5350000262260437,0.5490000247955322,0.5389999747276306,0.5260000228881836,0.5299999713897705,0.515999972820282,0.5360000133514404,0.5299999713897705,0.5410000085830688,0.5350000262260437,0.5410000085830688,0.5329999923706055,0.5299999713897705,0.5350000262260437,0.5419999957084656,0.5419999957084656,0.5329999923706055,0.527999997138977,0.5339999794960022,0.5509999990463257,0.5400000214576721,0.5440000295639038,0.5379999876022339,0.5410000085830688,0.5509999990463257,0.5410000085830688,0.5350000262260437,0.5479999780654907,0.5360000133514404,0.5379999876022339,0.5289999842643738,0.5460000038146973,0.5329999923706055,0.5370000004768372,0.5360000133514404,0.546999990940094,0.5360000133514404,0.5379999876022339,0.531000018119812,0.546999990940094,0.5379999876022339,0.5339999794960022,0.5339999794960022,0.5400000214576721,0.5479999780654907,0.5490000247955322,0.5490000247955322,0.5569999814033508,0.5509999990463257,0.5460000038146973,0.5540000200271606,0.550000011920929,0.5490000247955322,0.5490000247955322,0.5440000295639038,0.5460000038146973,0.5379999876022339,0.5479999780654907,0.546999990940094,0.5460000038146973,0.5419999957084656,0.5410000085830688,0.5400000214576721,0.5600000023841858,0.5569999814033508,0.5429999828338623,0.5460000038146973,0.550000011920929,0.5479999780654907,0.5479999780654907,0.5550000071525574,0.5450000166893005,0.5370000004768372,0.5379999876022339,0.5479999780654907,0.5450000166893005,0.5490000247955322,0.5440000295639038,0.5429999828338623,0.5440000295639038,0.5450000166893005,0.5450000166893005,0.550000011920929,0.5490000247955322,0.5529999732971191,0.5550000071525574,0.5509999990463257,0.5580000281333923,0.546999990940094,0.5379999876022339,0.5419999957084656,0.5529999732971191,0.5400000214576721,0.5429999828338623,0.5410000085830688,0.5479999780654907,0.5440000295639038,0.5410000085830688,0.5429999828338623,0.5400000214576721,0.5490000247955322,0.5419999957084656,0.5429999828338623,0.5410000085830688,0.5410000085830688,0.5440000295639038,0.5460000038146973,0.5450000166893005,0.5429999828338623],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.4970000088214874,0.5210000276565552,0.4990000128746032,0.5120000243186951,0.5080000162124634,0.5249999761581421,0.5090000033378601,0.5080000162124634,0.5260000228881836,0.5109999775886536,0.515999972820282,0.5239999890327454,0.5099999904632568,0.5170000195503235,0.5299999713897705,0.5109999775886536,0.5249999761581421,0.5270000100135803,0.5230000019073486,0.5289999842643738,0.531000018119812,0.5320000052452087,0.527999997138977,0.5199999809265137,0.5220000147819519,0.5239999890327454,0.5210000276565552,0.5299999713897705,0.5329999923706055,0.5360000133514404,0.5429999828338623,0.5360000133514404,0.5450000166893005,0.5440000295639038,0.5339999794960022,0.527999997138977,0.531000018119812,0.5360000133514404,0.531000018119812,0.5249999761581421,0.5199999809265137,0.5270000100135803,0.5490000247955322,0.5329999923706055,0.5149999856948853,0.527999997138977,0.515999972820282,0.5389999747276306,0.5360000133514404,0.5329999923706055,0.5389999747276306,0.5339999794960022,0.5329999923706055,0.5270000100135803,0.5360000133514404,0.5389999747276306,0.5329999923706055,0.5360000133514404,0.5320000052452087,0.5370000004768372,0.531000018119812,0.5419999957084656,0.5289999842643738,0.5339999794960022,0.5590000152587891,0.5410000085830688,0.5360000133514404,0.5460000038146973,0.5440000295639038,0.5519999861717224,0.5360000133514404,0.5440000295639038,0.5450000166893005,0.5350000262260437,0.5490000247955322,0.5389999747276306,0.5600000023841858,0.5419999957084656,0.5429999828338623,0.5429999828338623,0.550000011920929,0.5339999794960022,0.5479999780654907,0.5519999861717224,0.5419999957084656,0.5389999747276306,0.5410000085830688,0.5339999794960022,0.5299999713897705,0.5479999780654907,0.5320000052452087,0.5389999747276306,0.5350000262260437,0.5460000038146973,0.5429999828338623,0.546999990940094,0.5400000214576721,0.5490000247955322,0.5400000214576721,0.5490000247955322,0.5260000228881836,0.5419999957084656,0.5360000133514404,0.527999997138977,0.5440000295639038,0.5569999814033508,0.5460000038146973,0.5400000214576721,0.531000018119812,0.5440000295639038,0.5450000166893005,0.5379999876022339,0.5389999747276306,0.546999990940094,0.5389999747276306,0.5419999957084656,0.5419999957084656,0.5559999942779541,0.5540000200271606,0.5519999861717224,0.5559999942779541,0.5350000262260437,0.5479999780654907,0.5419999957084656,0.5329999923706055,0.5419999957084656,0.5490000247955322,0.5379999876022339,0.5419999957084656,0.5410000085830688,0.5450000166893005,0.5460000038146973,0.5509999990463257,0.546999990940094,0.5379999876022339,0.550000011920929,0.5450000166893005,0.5460000038146973,0.5389999747276306,0.5450000166893005,0.5410000085830688,0.5490000247955322,0.5479999780654907,0.5490000247955322,0.5490000247955322,0.550000011920929,0.5490000247955322,0.5580000281333923,0.550000011920929,0.5440000295639038,0.5529999732971191,0.5479999780654907,0.5360000133514404,0.5450000166893005,0.5479999780654907,0.5479999780654907,0.5509999990463257,0.5479999780654907,0.5529999732971191,0.5429999828338623,0.5410000085830688,0.5460000038146973,0.5419999957084656,0.5479999780654907,0.5440000295639038,0.5410000085830688,0.5440000295639038,0.5400000214576721],"label":"FineWeb URL dedup"}},"sciq/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2080000042915344,0.5820000171661377,0.6830000281333923,0.7480000257492065,0.7360000014305115,0.7519999742507935,0.7680000066757202,0.7760000228881836,0.8069999814033508,0.7839999794960022,0.8019999861717224,0.8100000023841858,0.8090000152587891,0.800000011920929,0.8339999914169312,0.8119999766349792,0.8330000042915344,0.8199999928474426,0.8259999752044678,0.7990000247955322,0.8240000009536743,0.843999981880188,0.8109999895095825,0.8240000009536743,0.8259999752044678,0.843999981880188,0.8190000057220459,0.824999988079071,0.8450000286102295,0.8349999785423279,0.8389999866485596,0.8429999947547913,0.8389999866485596,0.8500000238418579,0.847000002861023,0.8619999885559082,0.8429999947547913,0.8629999756813049,0.8450000286102295,0.8370000123977661,0.8500000238418579,0.8500000238418579,0.8489999771118164,0.8500000238418579,0.8519999980926514,0.843999981880188,0.8529999852180481,0.8519999980926514,0.8529999852180481,0.8529999852180481,0.843999981880188,0.8690000176429749,0.8529999852180481,0.8690000176429749,0.8709999918937683,0.8669999837875366,0.8600000143051147,0.8629999756813049,0.8460000157356262,0.8550000190734863,0.8539999723434448,0.8560000061988831,0.8450000286102295,0.8450000286102295,0.8550000190734863,0.8579999804496765,0.8659999966621399,0.8610000014305115,0.8489999771118164,0.8550000190734863,0.8640000224113464,0.878000020980835,0.8550000190734863,0.8579999804496765,0.8709999918937683,0.859000027179718,0.878000020980835,0.8849999904632568,0.8740000128746033,0.8730000257492065,0.8640000224113464,0.8650000095367432,0.8759999871253967,0.8629999756813049,0.8500000238418579,0.8659999966621399,0.8690000176429749,0.8809999823570251,0.8700000047683716,0.8679999709129333,0.8870000243186951,0.8709999918937683,0.8740000128746033,0.871999979019165,0.8840000033378601,0.8809999823570251,0.8849999904632568,0.8880000114440918,0.8790000081062317,0.8849999904632568,0.8880000114440918,0.8899999856948853,0.8820000290870667,0.871999979019165,0.8799999952316284,0.875,0.8790000081062317,0.8759999871253967,0.8899999856948853,0.8809999823570251,0.8790000081062317,0.8730000257492065,0.8700000047683716,0.8709999918937683,0.8740000128746033,0.8809999823570251,0.8769999742507935,0.8790000081062317,0.8809999823570251,0.8740000128746033,0.8809999823570251,0.890999972820282,0.8849999904632568,0.8809999823570251,0.8809999823570251,0.8870000243186951,0.8840000033378601,0.8799999952316284,0.8820000290870667,0.8870000243186951,0.8870000243186951,0.8840000033378601,0.8849999904632568,0.8939999938011169,0.8889999985694885,0.8930000066757202,0.8809999823570251,0.8859999775886536,0.8939999938011169,0.8880000114440918,0.8989999890327454,0.890999972820282,0.8960000276565552,0.8939999938011169,0.8989999890327454,0.890999972820282,0.8899999856948853,0.8859999775886536,0.8980000019073486,0.8960000276565552,0.8920000195503235,0.9010000228881836,0.890999972820282,0.890999972820282,0.9010000228881836,0.8949999809265137,0.8949999809265137,0.8949999809265137,0.8999999761581421,0.890999972820282,0.8849999904632568,0.8960000276565552,0.8899999856948853,0.8939999938011169,0.8920000195503235,0.8970000147819519,0.8939999938011169,0.8960000276565552],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2080000042915344,0.5460000038146973,0.6759999990463257,0.7279999852180481,0.7310000061988831,0.7630000114440918,0.7490000128746033,0.7850000262260437,0.7910000085830688,0.8149999976158142,0.8040000200271606,0.8100000023841858,0.7889999747276306,0.8109999895095825,0.8059999942779541,0.828000009059906,0.8370000123977661,0.8220000267028809,0.8159999847412109,0.824999988079071,0.8289999961853027,0.824999988079071,0.8240000009536743,0.8119999766349792,0.8289999961853027,0.8360000252723694,0.8349999785423279,0.8159999847412109,0.8379999995231628,0.8159999847412109,0.8429999947547913,0.8339999914169312,0.8429999947547913,0.8230000138282776,0.8460000157356262,0.8510000109672546,0.8479999899864197,0.8399999737739563,0.8379999995231628,0.8330000042915344,0.8330000042915344,0.8510000109672546,0.859000027179718,0.8700000047683716,0.8619999885559082,0.8539999723434448,0.8560000061988831,0.843999981880188,0.843999981880188,0.8450000286102295,0.8560000061988831,0.8529999852180481,0.8569999933242798,0.8489999771118164,0.8550000190734863,0.8450000286102295,0.8479999899864197,0.8479999899864197,0.8389999866485596,0.859000027179718,0.8600000143051147,0.8539999723434448,0.8539999723434448,0.8479999899864197,0.8640000224113464,0.8690000176429749,0.847000002861023,0.8529999852180481,0.859000027179718,0.8600000143051147,0.8569999933242798,0.8410000205039978,0.8460000157356262,0.847000002861023,0.8429999947547913,0.8519999980926514,0.8489999771118164,0.8659999966621399,0.8529999852180481,0.859000027179718,0.8619999885559082,0.8579999804496765,0.8619999885559082,0.8700000047683716,0.8550000190734863,0.859000027179718,0.8550000190734863,0.8579999804496765,0.8489999771118164,0.8610000014305115,0.8650000095367432,0.8600000143051147,0.8640000224113464,0.8619999885559082,0.8700000047683716,0.859000027179718,0.8619999885559082,0.859000027179718,0.8529999852180481,0.8730000257492065,0.8740000128746033,0.8679999709129333,0.8740000128746033,0.8690000176429749,0.8629999756813049,0.8610000014305115,0.8550000190734863,0.8600000143051147,0.8569999933242798,0.8610000014305115,0.8579999804496765,0.8550000190734863,0.8759999871253967,0.8629999756813049,0.8769999742507935,0.8610000014305115,0.8730000257492065,0.871999979019165,0.875,0.8690000176429749,0.8610000014305115,0.8690000176429749,0.8600000143051147,0.8659999966621399,0.8709999918937683,0.8659999966621399,0.871999979019165,0.871999979019165,0.8849999904632568,0.8769999742507935,0.8799999952316284,0.8790000081062317,0.878000020980835,0.8809999823570251,0.8849999904632568,0.8730000257492065,0.8920000195503235,0.8840000033378601,0.8769999742507935,0.8799999952316284,0.8709999918937683,0.8759999871253967,0.8790000081062317,0.8769999742507935,0.8769999742507935,0.8790000081062317,0.8809999823570251,0.878000020980835,0.8740000128746033,0.8799999952316284,0.8820000290870667,0.8799999952316284,0.8820000290870667,0.875,0.8769999742507935,0.8790000081062317,0.8809999823570251,0.8740000128746033,0.8700000047683716,0.8700000047683716,0.871999979019165,0.8820000290870667,0.875,0.8730000257492065,0.8799999952316284,0.8759999871253967,0.8790000081062317,0.8700000047683716],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2090000063180923,0.5730000138282776,0.6769999861717224,0.7120000123977661,0.7289999723434448,0.7509999871253967,0.7649999856948853,0.765999972820282,0.7789999842643738,0.781000018119812,0.7749999761581421,0.781000018119812,0.7929999828338623,0.7919999957084656,0.7940000295639038,0.8050000071525574,0.8019999861717224,0.8199999928474426,0.8069999814033508,0.8119999766349792,0.7990000247955322,0.8320000171661377,0.8289999961853027,0.8180000185966492,0.7979999780654907,0.8180000185966492,0.8299999833106995,0.8230000138282776,0.8289999961853027,0.8309999704360962,0.8270000219345093,0.8320000171661377,0.8220000267028809,0.8159999847412109,0.8169999718666077,0.8339999914169312,0.8330000042915344,0.8429999947547913,0.8230000138282776,0.8190000057220459,0.828000009059906,0.8240000009536743,0.8199999928474426,0.8360000252723694,0.8489999771118164,0.8370000123977661,0.8270000219345093,0.8489999771118164,0.8529999852180481,0.8529999852180481,0.8360000252723694,0.8349999785423279,0.8410000205039978,0.8410000205039978,0.8500000238418579,0.8370000123977661,0.8410000205039978,0.8399999737739563,0.8519999980926514,0.8600000143051147,0.8479999899864197,0.8330000042915344,0.8420000076293945,0.8429999947547913,0.8519999980926514,0.8489999771118164,0.8370000123977661,0.8339999914169312,0.8410000205039978,0.8410000205039978,0.843999981880188,0.843999981880188,0.8389999866485596,0.8289999961853027,0.8479999899864197,0.859000027179718,0.8330000042915344,0.8460000157356262,0.8489999771118164,0.843999981880188,0.8429999947547913,0.8289999961853027,0.8370000123977661,0.8550000190734863,0.847000002861023,0.8450000286102295,0.8330000042915344,0.8500000238418579,0.8550000190734863,0.8500000238418579,0.8489999771118164,0.8460000157356262,0.8600000143051147,0.8479999899864197,0.8600000143051147,0.8519999980926514,0.8740000128746033,0.8610000014305115,0.8460000157356262,0.8539999723434448,0.8560000061988831,0.843999981880188,0.8529999852180481,0.8529999852180481,0.8500000238418579,0.8489999771118164,0.8659999966621399,0.8550000190734863,0.8539999723434448,0.8550000190734863,0.8500000238418579,0.843999981880188,0.8529999852180481,0.8519999980926514,0.843999981880188,0.8500000238418579,0.8560000061988831,0.8569999933242798,0.8619999885559082,0.8600000143051147,0.8539999723434448,0.8650000095367432,0.8600000143051147,0.8539999723434448,0.8610000014305115,0.8640000224113464,0.8569999933242798,0.8539999723434448,0.8479999899864197,0.8519999980926514,0.8579999804496765,0.8560000061988831,0.8569999933242798,0.8629999756813049,0.859000027179718,0.8650000095367432,0.8679999709129333,0.8560000061988831,0.8669999837875366,0.8669999837875366,0.8690000176429749,0.859000027179718,0.8539999723434448,0.8610000014305115,0.8679999709129333,0.8709999918937683,0.8600000143051147,0.8669999837875366,0.8679999709129333,0.8740000128746033,0.859000027179718,0.8650000095367432,0.8640000224113464,0.8640000224113464,0.8709999918937683,0.8569999933242798,0.8679999709129333,0.8659999966621399,0.8600000143051147,0.8629999756813049,0.8569999933242798,0.8600000143051147,0.8640000224113464,0.8690000176429749,0.8610000014305115,0.8669999837875366,0.871999979019165,0.8669999837875366],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.209999993443489,0.6079999804496765,0.6869999766349792,0.7089999914169312,0.7429999709129333,0.7580000162124634,0.7590000033378601,0.7850000262260437,0.7879999876022339,0.7879999876022339,0.800000011920929,0.7870000004768372,0.8159999847412109,0.8080000281333923,0.8140000104904175,0.824999988079071,0.8159999847412109,0.8429999947547913,0.8349999785423279,0.8360000252723694,0.8259999752044678,0.8460000157356262,0.8270000219345093,0.8330000042915344,0.8510000109672546,0.8529999852180481,0.8510000109672546,0.8519999980926514,0.843999981880188,0.8420000076293945,0.8560000061988831,0.8450000286102295,0.8529999852180481,0.8560000061988831,0.8529999852180481,0.8679999709129333,0.8539999723434448,0.859000027179718,0.847000002861023,0.8550000190734863,0.8410000205039978,0.8510000109672546,0.8410000205039978,0.8659999966621399,0.8640000224113464,0.8579999804496765,0.8450000286102295,0.8629999756813049,0.8339999914169312,0.8619999885559082,0.8510000109672546,0.859000027179718,0.8510000109672546,0.8730000257492065,0.8659999966621399,0.859000027179718,0.8569999933242798,0.8510000109672546,0.8579999804496765,0.8679999709129333,0.8679999709129333,0.8569999933242798,0.8629999756813049,0.8600000143051147,0.8640000224113464,0.8679999709129333,0.871999979019165,0.8600000143051147,0.8560000061988831,0.8529999852180481,0.8650000095367432,0.8510000109672546,0.8740000128746033,0.8669999837875366,0.8619999885559082,0.8669999837875366,0.8669999837875366,0.871999979019165,0.8550000190734863,0.8659999966621399,0.8539999723434448,0.871999979019165,0.8640000224113464,0.8640000224113464,0.8579999804496765,0.8700000047683716,0.8679999709129333,0.8690000176429749,0.8560000061988831,0.8679999709129333,0.8730000257492065,0.8640000224113464,0.8569999933242798,0.875,0.8679999709129333,0.8740000128746033,0.8709999918937683,0.8769999742507935,0.8709999918937683,0.871999979019165,0.8830000162124634,0.8700000047683716,0.871999979019165,0.8840000033378601,0.8759999871253967,0.8679999709129333,0.878000020980835,0.8790000081062317,0.8790000081062317,0.8679999709129333,0.8790000081062317,0.8700000047683716,0.8799999952316284,0.8799999952316284,0.8790000081062317,0.8820000290870667,0.8859999775886536,0.8820000290870667,0.8790000081062317,0.878000020980835,0.8709999918937683,0.8870000243186951,0.8840000033378601,0.8799999952316284,0.8790000081062317,0.8640000224113464,0.875,0.878000020980835,0.878000020980835,0.8809999823570251,0.8830000162124634,0.878000020980835,0.8840000033378601,0.8859999775886536,0.8820000290870667,0.871999979019165,0.8679999709129333,0.878000020980835,0.8840000033378601,0.8790000081062317,0.8730000257492065,0.8830000162124634,0.8849999904632568,0.878000020980835,0.8830000162124634,0.8820000290870667,0.8889999985694885,0.8830000162124634,0.8889999985694885,0.8939999938011169,0.8859999775886536,0.8859999775886536,0.8809999823570251,0.8899999856948853,0.8849999904632568,0.890999972820282,0.8830000162124634,0.8840000033378601,0.8870000243186951,0.8859999775886536,0.8930000066757202,0.8809999823570251,0.8889999985694885,0.890999972820282,0.8790000081062317,0.8859999775886536,0.8840000033378601,0.8840000033378601],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2090000063180923,0.574999988079071,0.703000009059906,0.734000027179718,0.7419999837875366,0.7620000243186951,0.7850000262260437,0.777999997138977,0.8050000071525574,0.8019999861717224,0.8069999814033508,0.8159999847412109,0.8149999976158142,0.7950000166893005,0.8069999814033508,0.8309999704360962,0.8309999704360962,0.8140000104904175,0.8209999799728394,0.8330000042915344,0.8220000267028809,0.8259999752044678,0.8190000057220459,0.8420000076293945,0.8299999833106995,0.8349999785423279,0.8429999947547913,0.8529999852180481,0.8479999899864197,0.8320000171661377,0.8399999737739563,0.8479999899864197,0.8679999709129333,0.8399999737739563,0.8420000076293945,0.843999981880188,0.8460000157356262,0.8510000109672546,0.8320000171661377,0.8730000257492065,0.8569999933242798,0.8600000143051147,0.8539999723434448,0.8610000014305115,0.8529999852180481,0.8619999885559082,0.8709999918937683,0.8669999837875366,0.859000027179718,0.8679999709129333,0.8560000061988831,0.8659999966621399,0.8669999837875366,0.8690000176429749,0.8619999885559082,0.875,0.8790000081062317,0.8600000143051147,0.8709999918937683,0.8489999771118164,0.8669999837875366,0.8600000143051147,0.8500000238418579,0.8809999823570251,0.8669999837875366,0.8759999871253967,0.8659999966621399,0.8669999837875366,0.8769999742507935,0.871999979019165,0.8700000047683716,0.871999979019165,0.8790000081062317,0.8870000243186951,0.8759999871253967,0.8820000290870667,0.8709999918937683,0.8669999837875366,0.878000020980835,0.8790000081062317,0.8740000128746033,0.875,0.878000020980835,0.8830000162124634,0.8790000081062317,0.8790000081062317,0.8799999952316284,0.871999979019165,0.8579999804496765,0.8820000290870667,0.8740000128746033,0.875,0.8840000033378601,0.878000020980835,0.8849999904632568,0.8840000033378601,0.8799999952316284,0.8809999823570251,0.8870000243186951,0.8859999775886536,0.8920000195503235,0.8690000176429749,0.871999979019165,0.8830000162124634,0.875,0.8849999904632568,0.8759999871253967,0.8870000243186951,0.8799999952316284,0.8840000033378601,0.8809999823570251,0.8820000290870667,0.8920000195503235,0.8790000081062317,0.875,0.8840000033378601,0.8830000162124634,0.8820000290870667,0.8840000033378601,0.8880000114440918,0.8859999775886536,0.8859999775886536,0.8830000162124634,0.8949999809265137,0.8809999823570251,0.8790000081062317,0.8889999985694885,0.8859999775886536,0.8849999904632568,0.8859999775886536,0.8960000276565552,0.8920000195503235,0.8840000033378601,0.8889999985694885,0.8809999823570251,0.8889999985694885,0.8790000081062317,0.890999972820282,0.8939999938011169,0.8799999952316284,0.8889999985694885,0.8899999856948853,0.890999972820282,0.8830000162124634,0.890999972820282,0.8899999856948853,0.8870000243186951,0.8889999985694885,0.8880000114440918,0.8920000195503235,0.8880000114440918,0.8809999823570251,0.8889999985694885,0.8899999856948853,0.890999972820282,0.8920000195503235,0.8870000243186951,0.8849999904632568,0.878000020980835,0.8920000195503235,0.8870000243186951,0.8889999985694885,0.8859999775886536,0.8849999904632568,0.8849999904632568,0.8889999985694885,0.8830000162124634,0.8840000033378601],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2080000042915344,0.5849999785423279,0.6800000071525574,0.718999981880188,0.7310000061988831,0.7540000081062317,0.7599999904632568,0.7599999904632568,0.8040000200271606,0.7910000085830688,0.8080000281333923,0.8019999861717224,0.8169999718666077,0.8029999732971191,0.8050000071525574,0.8190000057220459,0.8059999942779541,0.8140000104904175,0.8149999976158142,0.8209999799728394,0.8180000185966492,0.8119999766349792,0.8349999785423279,0.8240000009536743,0.8230000138282776,0.8240000009536743,0.8510000109672546,0.8169999718666077,0.8209999799728394,0.8420000076293945,0.8389999866485596,0.8519999980926514,0.8299999833106995,0.8410000205039978,0.8389999866485596,0.8410000205039978,0.8500000238418579,0.847000002861023,0.8399999737739563,0.8320000171661377,0.8379999995231628,0.8379999995231628,0.8379999995231628,0.8399999737739563,0.8500000238418579,0.8399999737739563,0.8330000042915344,0.824999988079071,0.8349999785423279,0.859000027179718,0.8460000157356262,0.8399999737739563,0.8330000042915344,0.8569999933242798,0.8579999804496765,0.8410000205039978,0.8489999771118164,0.8399999737739563,0.843999981880188,0.8619999885559082,0.8429999947547913,0.8560000061988831,0.8519999980926514,0.8519999980926514,0.8539999723434448,0.8579999804496765,0.8489999771118164,0.8519999980926514,0.8679999709129333,0.8500000238418579,0.8460000157356262,0.8709999918937683,0.8650000095367432,0.859000027179718,0.8500000238418579,0.8550000190734863,0.8679999709129333,0.8619999885559082,0.8519999980926514,0.8579999804496765,0.8730000257492065,0.8740000128746033,0.859000027179718,0.871999979019165,0.8619999885559082,0.8500000238418579,0.8700000047683716,0.8730000257492065,0.8679999709129333,0.8610000014305115,0.8650000095367432,0.871999979019165,0.8700000047683716,0.878000020980835,0.8700000047683716,0.8650000095367432,0.8690000176429749,0.8640000224113464,0.8659999966621399,0.8709999918937683,0.8550000190734863,0.859000027179718,0.8700000047683716,0.8809999823570251,0.8659999966621399,0.878000020980835,0.8769999742507935,0.8809999823570251,0.8769999742507935,0.8820000290870667,0.8690000176429749,0.8629999756813049,0.8759999871253967,0.8740000128746033,0.8669999837875366,0.8769999742507935,0.8820000290870667,0.8669999837875366,0.8659999966621399,0.8669999837875366,0.8650000095367432,0.8769999742507935,0.8740000128746033,0.8790000081062317,0.8769999742507935,0.8669999837875366,0.8790000081062317,0.8730000257492065,0.8880000114440918,0.8740000128746033,0.8709999918937683,0.8790000081062317,0.8650000095367432,0.8690000176429749,0.8700000047683716,0.8709999918937683,0.8799999952316284,0.8799999952316284,0.8690000176429749,0.8679999709129333,0.8820000290870667,0.8809999823570251,0.8790000081062317,0.8830000162124634,0.8790000081062317,0.8809999823570251,0.8859999775886536,0.8859999775886536,0.8820000290870667,0.8790000081062317,0.8820000290870667,0.8759999871253967,0.8790000081062317,0.8889999985694885,0.8799999952316284,0.8840000033378601,0.8759999871253967,0.8799999952316284,0.8809999823570251,0.8820000290870667,0.8799999952316284,0.8820000290870667,0.8830000162124634,0.8769999742507935,0.8790000081062317,0.8730000257492065,0.8840000033378601,0.8799999952316284],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2080000042915344,0.6010000109672546,0.6869999766349792,0.7200000286102295,0.7580000162124634,0.7580000162124634,0.7749999761581421,0.7680000066757202,0.7760000228881836,0.7990000247955322,0.800000011920929,0.7860000133514404,0.8009999990463257,0.781000018119812,0.7940000295639038,0.8029999732971191,0.8069999814033508,0.8090000152587891,0.8209999799728394,0.828000009059906,0.8209999799728394,0.8040000200271606,0.8169999718666077,0.8379999995231628,0.8349999785423279,0.8349999785423279,0.8389999866485596,0.843999981880188,0.859000027179718,0.8360000252723694,0.843999981880188,0.8410000205039978,0.8339999914169312,0.8489999771118164,0.8389999866485596,0.8640000224113464,0.8560000061988831,0.8640000224113464,0.8420000076293945,0.8619999885559082,0.8529999852180481,0.8489999771118164,0.8399999737739563,0.8579999804496765,0.8560000061988831,0.8529999852180481,0.8569999933242798,0.8489999771118164,0.8539999723434448,0.8569999933242798,0.8569999933242798,0.8650000095367432,0.871999979019165,0.8769999742507935,0.8820000290870667,0.8650000095367432,0.8759999871253967,0.8730000257492065,0.875,0.8960000276565552,0.8659999966621399,0.8610000014305115,0.8740000128746033,0.8399999737739563,0.8640000224113464,0.875,0.8769999742507935,0.8659999966621399,0.8809999823570251,0.8669999837875366,0.8700000047683716,0.8730000257492065,0.8690000176429749,0.8809999823570251,0.8629999756813049,0.8640000224113464,0.8730000257492065,0.8640000224113464,0.8730000257492065,0.875,0.8849999904632568,0.8740000128746033,0.8809999823570251,0.8730000257492065,0.8679999709129333,0.8759999871253967,0.8709999918937683,0.8809999823570251,0.8740000128746033,0.8799999952316284,0.875,0.8889999985694885,0.8700000047683716,0.878000020980835,0.8870000243186951,0.878000020980835,0.8809999823570251,0.875,0.8799999952316284,0.8809999823570251,0.8799999952316284,0.8769999742507935,0.8899999856948853,0.8849999904632568,0.8889999985694885,0.8920000195503235,0.878000020980835,0.8859999775886536,0.8930000066757202,0.8880000114440918,0.8899999856948853,0.8700000047683716,0.8709999918937683,0.8799999952316284,0.878000020980835,0.8920000195503235,0.8889999985694885,0.871999979019165,0.8889999985694885,0.890999972820282,0.8759999871253967,0.8849999904632568,0.8840000033378601,0.8880000114440918,0.8849999904632568,0.8939999938011169,0.8709999918937683,0.8840000033378601,0.8730000257492065,0.8849999904632568,0.8859999775886536,0.8809999823570251,0.8790000081062317,0.8820000290870667,0.8820000290870667,0.8830000162124634,0.890999972820282,0.8849999904632568,0.8790000081062317,0.8920000195503235,0.8939999938011169,0.8899999856948853,0.8989999890327454,0.8920000195503235,0.8830000162124634,0.8939999938011169,0.8849999904632568,0.8960000276565552,0.8949999809265137,0.8899999856948853,0.8920000195503235,0.8939999938011169,0.8849999904632568,0.890999972820282,0.8920000195503235,0.8930000066757202,0.8920000195503235,0.8859999775886536,0.8899999856948853,0.8859999775886536,0.8949999809265137,0.8849999904632568,0.890999972820282,0.890999972820282,0.8809999823570251,0.8859999775886536,0.8870000243186951,0.8820000290870667],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.209999993443489,0.574999988079071,0.6919999718666077,0.7319999933242798,0.7400000095367432,0.7680000066757202,0.7739999890327454,0.7670000195503235,0.7860000133514404,0.8059999942779541,0.7940000295639038,0.8199999928474426,0.8040000200271606,0.8119999766349792,0.8119999766349792,0.7749999761581421,0.8169999718666077,0.8149999976158142,0.8199999928474426,0.8289999961853027,0.8339999914169312,0.8349999785423279,0.8389999866485596,0.8140000104904175,0.8330000042915344,0.8410000205039978,0.8330000042915344,0.8360000252723694,0.8119999766349792,0.8309999704360962,0.8259999752044678,0.8370000123977661,0.8259999752044678,0.8360000252723694,0.828000009059906,0.8220000267028809,0.8450000286102295,0.8330000042915344,0.8399999737739563,0.8339999914169312,0.8420000076293945,0.8519999980926514,0.8479999899864197,0.8560000061988831,0.8389999866485596,0.8299999833106995,0.8450000286102295,0.8429999947547913,0.847000002861023,0.8379999995231628,0.8399999737739563,0.8510000109672546,0.8539999723434448,0.8489999771118164,0.8539999723434448,0.8399999737739563,0.8569999933242798,0.8460000157356262,0.8659999966621399,0.8500000238418579,0.8600000143051147,0.8610000014305115,0.8539999723434448,0.8619999885559082,0.8539999723434448,0.859000027179718,0.8610000014305115,0.8560000061988831,0.875,0.8600000143051147,0.8659999966621399,0.8629999756813049,0.8529999852180481,0.8600000143051147,0.8690000176429749,0.875,0.8619999885559082,0.8539999723434448,0.8690000176429749,0.8569999933242798,0.847000002861023,0.8659999966621399,0.8690000176429749,0.8669999837875366,0.8629999756813049,0.8519999980926514,0.8650000095367432,0.8569999933242798,0.871999979019165,0.871999979019165,0.8730000257492065,0.878000020980835,0.8709999918937683,0.8700000047683716,0.8679999709129333,0.8629999756813049,0.878000020980835,0.8640000224113464,0.8679999709129333,0.871999979019165,0.8709999918937683,0.8579999804496765,0.8700000047683716,0.8740000128746033,0.8640000224113464,0.8820000290870667,0.8740000128746033,0.8669999837875366,0.8730000257492065,0.8730000257492065,0.875,0.871999979019165,0.8759999871253967,0.8690000176429749,0.8759999871253967,0.8730000257492065,0.8709999918937683,0.8709999918937683,0.8700000047683716,0.871999979019165,0.871999979019165,0.8700000047683716,0.8650000095367432,0.8690000176429749,0.8759999871253967,0.8730000257492065,0.8700000047683716,0.875,0.8629999756813049,0.8849999904632568,0.8809999823570251,0.8679999709129333,0.8790000081062317,0.8840000033378601,0.8709999918937683,0.8790000081062317,0.8809999823570251,0.8740000128746033,0.8700000047683716,0.8830000162124634,0.8820000290870667,0.8799999952316284,0.8640000224113464,0.8840000033378601,0.8759999871253967,0.875,0.8799999952316284,0.8759999871253967,0.8769999742507935,0.8799999952316284,0.8759999871253967,0.8820000290870667,0.8899999856948853,0.8730000257492065,0.890999972820282,0.8790000081062317,0.8830000162124634,0.8790000081062317,0.8830000162124634,0.8809999823570251,0.8809999823570251,0.8830000162124634,0.8809999823570251,0.8790000081062317,0.8830000162124634,0.8809999823570251,0.8870000243186951,0.8790000081062317],"label":"FineWeb URL dedup"}},"sciq/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.202000007033348,0.527999997138977,0.5899999737739563,0.6460000276565552,0.6340000033378601,0.6470000147819519,0.6790000200271606,0.671999990940094,0.6940000057220459,0.6990000009536743,0.699999988079071,0.7059999704360962,0.722000002861023,0.7319999933242798,0.7450000047683716,0.7289999723434448,0.746999979019165,0.7379999756813049,0.7350000143051147,0.7229999899864197,0.7350000143051147,0.7599999904632568,0.7319999933242798,0.7229999899864197,0.7329999804496765,0.7409999966621399,0.7239999771118164,0.75,0.7319999933242798,0.75,0.7519999742507935,0.7749999761581421,0.7459999918937683,0.7670000195503235,0.7699999809265137,0.7839999794960022,0.7540000081062317,0.7910000085830688,0.7609999775886536,0.7559999823570251,0.7789999842643738,0.765999972820282,0.7670000195503235,0.7760000228881836,0.7620000243186951,0.7590000033378601,0.7870000004768372,0.7710000276565552,0.777999997138977,0.7699999809265137,0.7490000128746033,0.7879999876022339,0.7749999761581421,0.7860000133514404,0.8059999942779541,0.7829999923706055,0.7860000133514404,0.8029999732971191,0.7770000100135803,0.7889999747276306,0.7770000100135803,0.7820000052452087,0.777999997138977,0.7760000228881836,0.7760000228881836,0.7870000004768372,0.8029999732971191,0.7929999828338623,0.7789999842643738,0.7950000166893005,0.8100000023841858,0.8199999928474426,0.8019999861717224,0.8180000185966492,0.7979999780654907,0.8029999732971191,0.8100000023841858,0.8209999799728394,0.8059999942779541,0.8259999752044678,0.8109999895095825,0.8040000200271606,0.8180000185966492,0.7990000247955322,0.7879999876022339,0.8009999990463257,0.8069999814033508,0.8299999833106995,0.8100000023841858,0.8069999814033508,0.8309999704360962,0.8190000057220459,0.8080000281333923,0.8100000023841858,0.8270000219345093,0.8180000185966492,0.8220000267028809,0.828000009059906,0.8230000138282776,0.8199999928474426,0.8270000219345093,0.8360000252723694,0.8220000267028809,0.7979999780654907,0.8069999814033508,0.8190000057220459,0.8009999990463257,0.800000011920929,0.8339999914169312,0.8080000281333923,0.8270000219345093,0.8330000042915344,0.8029999732971191,0.8090000152587891,0.8130000233650208,0.824999988079071,0.8069999814033508,0.8259999752044678,0.8149999976158142,0.8090000152587891,0.8230000138282776,0.8240000009536743,0.8159999847412109,0.8140000104904175,0.8190000057220459,0.8339999914169312,0.8309999704360962,0.8259999752044678,0.8339999914169312,0.8420000076293945,0.8370000123977661,0.8320000171661377,0.8349999785423279,0.8460000157356262,0.8389999866485596,0.8320000171661377,0.8379999995231628,0.8399999737739563,0.8299999833106995,0.8379999995231628,0.8360000252723694,0.8379999995231628,0.8489999771118164,0.8389999866485596,0.843999981880188,0.843999981880188,0.8339999914169312,0.8379999995231628,0.8450000286102295,0.8410000205039978,0.8479999899864197,0.8460000157356262,0.8399999737739563,0.8370000123977661,0.8349999785423279,0.8349999785423279,0.8309999704360962,0.8420000076293945,0.8360000252723694,0.8330000042915344,0.8240000009536743,0.847000002861023,0.8389999866485596,0.8309999704360962,0.8389999866485596,0.8389999866485596,0.8399999737739563,0.843999981880188],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.202000007033348,0.4900000095367431,0.6060000061988831,0.6230000257492065,0.6449999809265137,0.6859999895095825,0.6690000295639038,0.6970000267028809,0.7110000252723694,0.7129999995231628,0.6980000138282776,0.7110000252723694,0.6869999766349792,0.6959999799728394,0.7009999752044678,0.7179999947547913,0.7360000014305115,0.7239999771118164,0.7049999833106995,0.7229999899864197,0.7279999852180481,0.7379999756813049,0.7179999947547913,0.7009999752044678,0.7229999899864197,0.7429999709129333,0.7269999980926514,0.7120000123977661,0.75,0.7089999914169312,0.7329999804496765,0.75,0.7200000286102295,0.7360000014305115,0.7519999742507935,0.7480000257492065,0.753000020980835,0.7519999742507935,0.753000020980835,0.7300000190734863,0.734000027179718,0.7590000033378601,0.7670000195503235,0.7799999713897705,0.7670000195503235,0.7559999823570251,0.7739999890327454,0.7720000147819519,0.7570000290870667,0.7459999918937683,0.7870000004768372,0.7699999809265137,0.7749999761581421,0.7599999904632568,0.7649999856948853,0.765999972820282,0.7639999985694885,0.7940000295639038,0.7689999938011169,0.7990000247955322,0.777999997138977,0.781000018119812,0.7730000019073486,0.7630000114440918,0.7870000004768372,0.7870000004768372,0.7639999985694885,0.7710000276565552,0.7639999985694885,0.777999997138977,0.7760000228881836,0.7519999742507935,0.7789999842643738,0.7670000195503235,0.7540000081062317,0.7689999938011169,0.7770000100135803,0.7940000295639038,0.7900000214576721,0.7950000166893005,0.8009999990463257,0.7739999890327454,0.8029999732971191,0.8159999847412109,0.7919999957084656,0.7950000166893005,0.7760000228881836,0.7850000262260437,0.7900000214576721,0.8029999732971191,0.8109999895095825,0.7929999828338623,0.8130000233650208,0.7799999713897705,0.8090000152587891,0.8009999990463257,0.7889999747276306,0.7919999957084656,0.7990000247955322,0.7990000247955322,0.8180000185966492,0.8059999942779541,0.8230000138282776,0.8100000023841858,0.8019999861717224,0.7919999957084656,0.796999990940094,0.7940000295639038,0.7829999923706055,0.7879999876022339,0.8080000281333923,0.7879999876022339,0.8059999942779541,0.8019999861717224,0.8080000281333923,0.7889999747276306,0.8149999976158142,0.8169999718666077,0.8299999833106995,0.8029999732971191,0.7799999713897705,0.8040000200271606,0.8050000071525574,0.8009999990463257,0.8050000071525574,0.8050000071525574,0.8069999814033508,0.8050000071525574,0.8309999704360962,0.8180000185966492,0.8199999928474426,0.8019999861717224,0.8149999976158142,0.8209999799728394,0.8199999928474426,0.8159999847412109,0.8289999961853027,0.8230000138282776,0.8240000009536743,0.8320000171661377,0.8109999895095825,0.8209999799728394,0.8180000185966492,0.8180000185966492,0.8199999928474426,0.8100000023841858,0.8299999833106995,0.824999988079071,0.8090000152587891,0.8180000185966492,0.828000009059906,0.8140000104904175,0.8149999976158142,0.8140000104904175,0.8259999752044678,0.8140000104904175,0.8240000009536743,0.8209999799728394,0.8149999976158142,0.8169999718666077,0.8109999895095825,0.8240000009536743,0.8159999847412109,0.8109999895095825,0.8270000219345093,0.8119999766349792,0.8230000138282776,0.8019999861717224],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.202000007033348,0.5149999856948853,0.5960000157356262,0.6209999918937683,0.6119999885559082,0.6380000114440918,0.656000018119812,0.6520000100135803,0.6859999895095825,0.6769999861717224,0.6690000295639038,0.6740000247955322,0.6800000071525574,0.6650000214576721,0.6930000185966492,0.6899999976158142,0.699999988079071,0.7059999704360962,0.7089999914169312,0.7160000205039978,0.7089999914169312,0.7329999804496765,0.7360000014305115,0.7269999980926514,0.7059999704360962,0.7279999852180481,0.734000027179718,0.718999981880188,0.7419999837875366,0.7369999885559082,0.7300000190734863,0.7549999952316284,0.7350000143051147,0.7179999947547913,0.7160000205039978,0.7379999756813049,0.7490000128746033,0.7680000066757202,0.7360000014305115,0.7260000109672546,0.7620000243186951,0.7400000095367432,0.7300000190734863,0.7559999823570251,0.7739999890327454,0.7620000243186951,0.7509999871253967,0.7860000133514404,0.7680000066757202,0.7860000133514404,0.7480000257492065,0.7519999742507935,0.7630000114440918,0.7549999952316284,0.7710000276565552,0.746999979019165,0.7599999904632568,0.7670000195503235,0.7799999713897705,0.7860000133514404,0.7630000114440918,0.7369999885559082,0.7400000095367432,0.7730000019073486,0.7620000243186951,0.7630000114440918,0.7509999871253967,0.7409999966621399,0.7549999952316284,0.734000027179718,0.7749999761581421,0.7739999890327454,0.7519999742507935,0.7570000290870667,0.7760000228881836,0.7630000114440918,0.7300000190734863,0.7590000033378601,0.7689999938011169,0.7450000047683716,0.7680000066757202,0.7440000176429749,0.765999972820282,0.781000018119812,0.7599999904632568,0.7620000243186951,0.7549999952316284,0.7739999890327454,0.7639999985694885,0.7609999775886536,0.765999972820282,0.7730000019073486,0.8009999990463257,0.7870000004768372,0.7829999923706055,0.7689999938011169,0.796999990940094,0.7789999842643738,0.7670000195503235,0.7689999938011169,0.7760000228881836,0.7670000195503235,0.7839999794960022,0.7720000147819519,0.7730000019073486,0.7670000195503235,0.7839999794960022,0.7910000085830688,0.7649999856948853,0.7730000019073486,0.7760000228881836,0.7639999985694885,0.7670000195503235,0.7720000147819519,0.7559999823570251,0.7749999761581421,0.7639999985694885,0.7839999794960022,0.777999997138977,0.7649999856948853,0.7680000066757202,0.796999990940094,0.7739999890327454,0.7789999842643738,0.8109999895095825,0.7889999747276306,0.796999990940094,0.7960000038146973,0.7789999842643738,0.7839999794960022,0.7929999828338623,0.7799999713897705,0.7929999828338623,0.7919999957084656,0.7850000262260437,0.7919999957084656,0.8040000200271606,0.7879999876022339,0.7940000295639038,0.7839999794960022,0.796999990940094,0.7929999828338623,0.7950000166893005,0.7879999876022339,0.8029999732971191,0.8040000200271606,0.7919999957084656,0.7889999747276306,0.7889999747276306,0.8009999990463257,0.7919999957084656,0.8069999814033508,0.7829999923706055,0.7910000085830688,0.7910000085830688,0.7839999794960022,0.7929999828338623,0.7919999957084656,0.8029999732971191,0.7799999713897705,0.781000018119812,0.7979999780654907,0.7929999828338623,0.8080000281333923,0.800000011920929,0.7950000166893005,0.8119999766349792,0.8029999732971191],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2029999941587448,0.5210000276565552,0.5929999947547913,0.5950000286102295,0.6320000290870667,0.6539999842643738,0.6510000228881836,0.6909999847412109,0.6700000166893005,0.7099999785423279,0.7009999752044678,0.6840000152587891,0.7129999995231628,0.703000009059906,0.7170000076293945,0.722000002861023,0.7390000224113464,0.7459999918937683,0.7279999852180481,0.7289999723434448,0.7229999899864197,0.7480000257492065,0.7160000205039978,0.7440000176429749,0.7689999938011169,0.7609999775886536,0.7720000147819519,0.7839999794960022,0.734000027179718,0.7390000224113464,0.765999972820282,0.753000020980835,0.7710000276565552,0.7609999775886536,0.7760000228881836,0.7829999923706055,0.7739999890327454,0.7900000214576721,0.777999997138977,0.7639999985694885,0.7689999938011169,0.765999972820282,0.7490000128746033,0.7929999828338623,0.7839999794960022,0.7870000004768372,0.7649999856948853,0.7940000295639038,0.7490000128746033,0.8090000152587891,0.8009999990463257,0.796999990940094,0.7979999780654907,0.7950000166893005,0.8019999861717224,0.796999990940094,0.7670000195503235,0.7829999923706055,0.777999997138977,0.7870000004768372,0.8029999732971191,0.7929999828338623,0.8080000281333923,0.7850000262260437,0.7929999828338623,0.7960000038146973,0.8050000071525574,0.781000018119812,0.7889999747276306,0.777999997138977,0.8100000023841858,0.7829999923706055,0.7910000085830688,0.7850000262260437,0.7850000262260437,0.7850000262260437,0.7910000085830688,0.7990000247955322,0.7870000004768372,0.800000011920929,0.7839999794960022,0.7979999780654907,0.7789999842643738,0.7860000133514404,0.781000018119812,0.7929999828338623,0.8040000200271606,0.800000011920929,0.7870000004768372,0.7889999747276306,0.7900000214576721,0.7929999828338623,0.7829999923706055,0.8100000023841858,0.8069999814033508,0.8069999814033508,0.7979999780654907,0.7940000295639038,0.7960000038146973,0.8149999976158142,0.8220000267028809,0.8050000071525574,0.8090000152587891,0.8090000152587891,0.8050000071525574,0.8090000152587891,0.824999988079071,0.824999988079071,0.8029999732971191,0.8169999718666077,0.8220000267028809,0.8119999766349792,0.8209999799728394,0.8230000138282776,0.824999988079071,0.8149999976158142,0.8240000009536743,0.8220000267028809,0.8140000104904175,0.8059999942779541,0.8080000281333923,0.8190000057220459,0.8230000138282776,0.8190000057220459,0.8059999942779541,0.8050000071525574,0.8240000009536743,0.8199999928474426,0.8050000071525574,0.8320000171661377,0.8309999704360962,0.824999988079071,0.8309999704360962,0.824999988079071,0.8240000009536743,0.8040000200271606,0.7990000247955322,0.8230000138282776,0.824999988079071,0.8270000219345093,0.8090000152587891,0.8259999752044678,0.824999988079071,0.8190000057220459,0.824999988079071,0.8299999833106995,0.8349999785423279,0.8420000076293945,0.8320000171661377,0.8429999947547913,0.8299999833106995,0.8320000171661377,0.8190000057220459,0.8289999961853027,0.8309999704360962,0.8299999833106995,0.8199999928474426,0.8289999961853027,0.8270000219345093,0.8360000252723694,0.8230000138282776,0.828000009059906,0.8299999833106995,0.8349999785423279,0.8140000104904175,0.8330000042915344,0.8230000138282776,0.8220000267028809],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.202000007033348,0.5109999775886536,0.6019999980926514,0.6240000128746033,0.6349999904632568,0.6710000038146973,0.6830000281333923,0.6639999747276306,0.6970000267028809,0.6990000009536743,0.7089999914169312,0.7269999980926514,0.7099999785423279,0.6940000057220459,0.7239999771118164,0.7419999837875366,0.7310000061988831,0.7250000238418579,0.7350000143051147,0.7699999809265137,0.7450000047683716,0.7519999742507935,0.7300000190734863,0.7739999890327454,0.7390000224113464,0.7440000176429749,0.7570000290870667,0.7590000033378601,0.7649999856948853,0.7409999966621399,0.7580000162124634,0.7639999985694885,0.7739999890327454,0.7590000033378601,0.7680000066757202,0.7639999985694885,0.7590000033378601,0.7770000100135803,0.7350000143051147,0.7820000052452087,0.7739999890327454,0.7799999713897705,0.7820000052452087,0.7770000100135803,0.7570000290870667,0.777999997138977,0.7889999747276306,0.7960000038146973,0.7680000066757202,0.7979999780654907,0.7760000228881836,0.7829999923706055,0.7850000262260437,0.7910000085830688,0.7770000100135803,0.8040000200271606,0.8109999895095825,0.781000018119812,0.7879999876022339,0.7649999856948853,0.800000011920929,0.7680000066757202,0.7680000066757202,0.7940000295639038,0.8220000267028809,0.8080000281333923,0.7879999876022339,0.800000011920929,0.8190000057220459,0.7950000166893005,0.7919999957084656,0.8090000152587891,0.7839999794960022,0.8159999847412109,0.7870000004768372,0.8130000233650208,0.7929999828338623,0.7870000004768372,0.8180000185966492,0.800000011920929,0.7979999780654907,0.7919999957084656,0.8180000185966492,0.8209999799728394,0.8069999814033508,0.7919999957084656,0.8040000200271606,0.7979999780654907,0.7870000004768372,0.796999990940094,0.7910000085830688,0.7960000038146973,0.8159999847412109,0.8119999766349792,0.800000011920929,0.8270000219345093,0.8050000071525574,0.8379999995231628,0.8240000009536743,0.8100000023841858,0.8330000042915344,0.8050000071525574,0.8009999990463257,0.7910000085830688,0.8059999942779541,0.8149999976158142,0.8080000281333923,0.8199999928474426,0.8230000138282776,0.8140000104904175,0.8100000023841858,0.824999988079071,0.8140000104904175,0.8050000071525574,0.7990000247955322,0.828000009059906,0.8220000267028809,0.8090000152587891,0.8330000042915344,0.8220000267028809,0.8119999766349792,0.8140000104904175,0.8130000233650208,0.8220000267028809,0.8090000152587891,0.7929999828338623,0.8169999718666077,0.8140000104904175,0.8019999861717224,0.8059999942779541,0.8190000057220459,0.8190000057220459,0.8149999976158142,0.8330000042915344,0.8050000071525574,0.8230000138282776,0.8040000200271606,0.8180000185966492,0.8230000138282776,0.800000011920929,0.8069999814033508,0.8259999752044678,0.824999988079071,0.8059999942779541,0.8159999847412109,0.8209999799728394,0.8190000057220459,0.8270000219345093,0.8230000138282776,0.8140000104904175,0.8230000138282776,0.8159999847412109,0.8149999976158142,0.8309999704360962,0.8299999833106995,0.8320000171661377,0.8199999928474426,0.8080000281333923,0.8119999766349792,0.8159999847412109,0.8240000009536743,0.8169999718666077,0.8169999718666077,0.8090000152587891,0.8270000219345093,0.8289999961853027,0.8169999718666077,0.8320000171661377],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.202000007033348,0.5170000195503235,0.574999988079071,0.640999972820282,0.6269999742507935,0.6499999761581421,0.6850000023841858,0.6679999828338623,0.699999988079071,0.6880000233650208,0.7059999704360962,0.7039999961853027,0.7139999866485596,0.7229999899864197,0.7149999737739563,0.7260000109672546,0.6930000185966492,0.7020000219345093,0.7049999833106995,0.7300000190734863,0.7289999723434448,0.7089999914169312,0.7390000224113464,0.7250000238418579,0.7210000157356262,0.7049999833106995,0.7519999742507935,0.718999981880188,0.7379999756813049,0.753000020980835,0.7409999966621399,0.7639999985694885,0.7419999837875366,0.734000027179718,0.722000002861023,0.7260000109672546,0.7400000095367432,0.7459999918937683,0.753000020980835,0.7450000047683716,0.7450000047683716,0.7450000047683716,0.7590000033378601,0.7400000095367432,0.7609999775886536,0.7310000061988831,0.7329999804496765,0.722000002861023,0.7440000176429749,0.7519999742507935,0.7450000047683716,0.7599999904632568,0.734000027179718,0.7379999756813049,0.7749999761581421,0.7310000061988831,0.7429999709129333,0.7440000176429749,0.7480000257492065,0.7649999856948853,0.7440000176429749,0.7609999775886536,0.7549999952316284,0.7749999761581421,0.7720000147819519,0.7549999952316284,0.7639999985694885,0.7889999747276306,0.7870000004768372,0.7710000276565552,0.7570000290870667,0.781000018119812,0.7749999761581421,0.7609999775886536,0.7639999985694885,0.7599999904632568,0.7829999923706055,0.7760000228881836,0.7799999713897705,0.7599999904632568,0.7870000004768372,0.7950000166893005,0.7580000162124634,0.7900000214576721,0.7879999876022339,0.7639999985694885,0.8040000200271606,0.7900000214576721,0.7820000052452087,0.7770000100135803,0.7919999957084656,0.781000018119812,0.7799999713897705,0.796999990940094,0.7799999713897705,0.7879999876022339,0.7910000085830688,0.7699999809265137,0.7739999890327454,0.7889999747276306,0.7730000019073486,0.7739999890327454,0.7820000052452087,0.8029999732971191,0.7789999842643738,0.8029999732971191,0.7990000247955322,0.7990000247955322,0.8109999895095825,0.7910000085830688,0.7720000147819519,0.7770000100135803,0.777999997138977,0.7960000038146973,0.7919999957084656,0.7940000295639038,0.8069999814033508,0.7770000100135803,0.7749999761581421,0.7870000004768372,0.781000018119812,0.8009999990463257,0.7979999780654907,0.8040000200271606,0.7940000295639038,0.7770000100135803,0.7879999876022339,0.7910000085830688,0.8059999942779541,0.7900000214576721,0.7900000214576721,0.8090000152587891,0.7749999761581421,0.7749999761581421,0.7860000133514404,0.7960000038146973,0.8159999847412109,0.8240000009536743,0.7919999957084656,0.781000018119812,0.8140000104904175,0.8109999895095825,0.8040000200271606,0.7919999957084656,0.7850000262260437,0.7820000052452087,0.8109999895095825,0.8029999732971191,0.8059999942779541,0.8069999814033508,0.8090000152587891,0.796999990940094,0.8080000281333923,0.824999988079071,0.7770000100135803,0.8080000281333923,0.7919999957084656,0.8029999732971191,0.8040000200271606,0.8059999942779541,0.7979999780654907,0.8019999861717224,0.8140000104904175,0.8040000200271606,0.8040000200271606,0.8029999732971191,0.8130000233650208,0.8159999847412109],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.202000007033348,0.5320000052452087,0.5849999785423279,0.6150000095367432,0.6690000295639038,0.6570000052452087,0.6990000009536743,0.6790000200271606,0.6850000023841858,0.7049999833106995,0.6990000009536743,0.6899999976158142,0.6819999814033508,0.6899999976158142,0.6880000233650208,0.6980000138282776,0.6949999928474426,0.7210000157356262,0.718999981880188,0.7400000095367432,0.722000002861023,0.7059999704360962,0.7200000286102295,0.7459999918937683,0.7429999709129333,0.722000002861023,0.7519999742507935,0.7590000033378601,0.7720000147819519,0.7689999938011169,0.7649999856948853,0.7749999761581421,0.7390000224113464,0.753000020980835,0.7519999742507935,0.777999997138977,0.7879999876022339,0.7900000214576721,0.7390000224113464,0.7749999761581421,0.7789999842643738,0.7559999823570251,0.7450000047683716,0.7889999747276306,0.781000018119812,0.7699999809265137,0.781000018119812,0.7639999985694885,0.7649999856948853,0.7739999890327454,0.7879999876022339,0.8009999990463257,0.800000011920929,0.8220000267028809,0.8059999942779541,0.7950000166893005,0.8130000233650208,0.8029999732971191,0.8040000200271606,0.8069999814033508,0.7929999828338623,0.8040000200271606,0.8080000281333923,0.7490000128746033,0.7910000085830688,0.800000011920929,0.8090000152587891,0.7760000228881836,0.8159999847412109,0.7950000166893005,0.800000011920929,0.7979999780654907,0.7870000004768372,0.8019999861717224,0.7910000085830688,0.7839999794960022,0.7990000247955322,0.8100000023841858,0.8080000281333923,0.8090000152587891,0.8190000057220459,0.8059999942779541,0.796999990940094,0.7760000228881836,0.7870000004768372,0.8069999814033508,0.8009999990463257,0.8050000071525574,0.7889999747276306,0.8100000023841858,0.7879999876022339,0.8180000185966492,0.7960000038146973,0.824999988079071,0.8209999799728394,0.8050000071525574,0.8159999847412109,0.7879999876022339,0.8029999732971191,0.7879999876022339,0.7940000295639038,0.7979999780654907,0.8159999847412109,0.8119999766349792,0.8090000152587891,0.824999988079071,0.800000011920929,0.8259999752044678,0.8450000286102295,0.8140000104904175,0.8339999914169312,0.7860000133514404,0.8090000152587891,0.7960000038146973,0.7960000038146973,0.8199999928474426,0.8199999928474426,0.7910000085830688,0.8240000009536743,0.8240000009536743,0.8029999732971191,0.8309999704360962,0.8270000219345093,0.8130000233650208,0.8240000009536743,0.8209999799728394,0.7889999747276306,0.8220000267028809,0.8040000200271606,0.8209999799728394,0.8169999718666077,0.8080000281333923,0.8199999928474426,0.8240000009536743,0.8230000138282776,0.8149999976158142,0.8299999833106995,0.8289999961853027,0.8069999814033508,0.8230000138282776,0.8270000219345093,0.8320000171661377,0.8270000219345093,0.828000009059906,0.8220000267028809,0.8460000157356262,0.8270000219345093,0.8379999995231628,0.8330000042915344,0.8289999961853027,0.847000002861023,0.8240000009536743,0.8209999799728394,0.8309999704360962,0.8270000219345093,0.8339999914169312,0.8330000042915344,0.8130000233650208,0.8199999928474426,0.8230000138282776,0.8339999914169312,0.8230000138282776,0.8190000057220459,0.8320000171661377,0.8240000009536743,0.8149999976158142,0.8140000104904175,0.8169999718666077],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2029999941587448,0.5220000147819519,0.5870000123977661,0.6110000014305115,0.6439999938011169,0.6650000214576721,0.6830000281333923,0.6600000262260437,0.6859999895095825,0.7099999785423279,0.7179999947547913,0.7049999833106995,0.6959999799728394,0.7129999995231628,0.7120000123977661,0.675000011920929,0.7160000205039978,0.7279999852180481,0.7350000143051147,0.7429999709129333,0.7429999709129333,0.7440000176429749,0.7379999756813049,0.722000002861023,0.7490000128746033,0.7400000095367432,0.7319999933242798,0.7480000257492065,0.7350000143051147,0.753000020980835,0.718999981880188,0.7459999918937683,0.7229999899864197,0.7540000081062317,0.7490000128746033,0.7580000162124634,0.7540000081062317,0.7379999756813049,0.7590000033378601,0.734000027179718,0.7440000176429749,0.7580000162124634,0.7519999742507935,0.7940000295639038,0.7450000047683716,0.7300000190734863,0.781000018119812,0.7710000276565552,0.75,0.7409999966621399,0.7440000176429749,0.7620000243186951,0.7900000214576721,0.7739999890327454,0.7760000228881836,0.7459999918937683,0.7990000247955322,0.777999997138977,0.7870000004768372,0.7770000100135803,0.7720000147819519,0.7879999876022339,0.7789999842643738,0.800000011920929,0.7730000019073486,0.7820000052452087,0.7799999713897705,0.7839999794960022,0.8320000171661377,0.7979999780654907,0.8050000071525574,0.781000018119812,0.7829999923706055,0.7900000214576721,0.8169999718666077,0.8069999814033508,0.7870000004768372,0.7850000262260437,0.7900000214576721,0.7950000166893005,0.8009999990463257,0.7979999780654907,0.8009999990463257,0.7950000166893005,0.8040000200271606,0.7749999761581421,0.8130000233650208,0.796999990940094,0.8119999766349792,0.8059999942779541,0.8169999718666077,0.8009999990463257,0.7929999828338623,0.796999990940094,0.7919999957084656,0.8019999861717224,0.824999988079071,0.8100000023841858,0.8069999814033508,0.7979999780654907,0.8069999814033508,0.7990000247955322,0.7979999780654907,0.8069999814033508,0.8100000023841858,0.8159999847412109,0.8019999861717224,0.8050000071525574,0.828000009059906,0.8169999718666077,0.8230000138282776,0.8040000200271606,0.8159999847412109,0.800000011920929,0.8029999732971191,0.8090000152587891,0.8090000152587891,0.8040000200271606,0.8019999861717224,0.8100000023841858,0.8069999814033508,0.7990000247955322,0.7850000262260437,0.796999990940094,0.8140000104904175,0.7990000247955322,0.8059999942779541,0.8180000185966492,0.8009999990463257,0.824999988079071,0.8169999718666077,0.8090000152587891,0.8140000104904175,0.8240000009536743,0.8149999976158142,0.8309999704360962,0.8220000267028809,0.8130000233650208,0.8059999942779541,0.8159999847412109,0.8140000104904175,0.8180000185966492,0.800000011920929,0.8240000009536743,0.8029999732971191,0.8119999766349792,0.8050000071525574,0.8050000071525574,0.8140000104904175,0.8119999766349792,0.8040000200271606,0.8140000104904175,0.8339999914169312,0.8180000185966492,0.8320000171661377,0.8130000233650208,0.8190000057220459,0.8289999961853027,0.824999988079071,0.8199999928474426,0.8209999799728394,0.8169999718666077,0.8230000138282776,0.8169999718666077,0.8270000219345093,0.8259999752044678,0.8309999704360962,0.824999988079071],"label":"FineWeb URL dedup"}},"arc/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2195000052452087,0.2649999856948852,0.3055000007152557,0.3210000097751617,0.3305000066757202,0.3330000042915344,0.3555000126361847,0.3485000133514404,0.3529999852180481,0.359499990940094,0.3549999892711639,0.3634999990463257,0.3659999966621399,0.3684999942779541,0.3759999871253967,0.3819999992847442,0.3714999854564667,0.3799999952316284,0.3899999856948852,0.3759999871253967,0.3844999969005584,0.3930000066757202,0.3925000131130218,0.3930000066757202,0.3970000147819519,0.3975000083446502,0.3944999873638153,0.4034999907016754,0.4070000052452087,0.4074999988079071,0.4065000116825104,0.4124999940395355,0.4095000028610229,0.4090000092983246,0.4180000126361847,0.4180000126361847,0.4070000052452087,0.4239999949932098,0.414000004529953,0.4144999980926513,0.4235000014305115,0.4160000085830688,0.418500006198883,0.4259999990463257,0.4180000126361847,0.4169999957084656,0.4210000038146972,0.4210000038146972,0.4269999861717224,0.4239999949932098,0.4239999949932098,0.4305000007152557,0.418500006198883,0.4259999990463257,0.429500013589859,0.4230000078678131,0.4259999990463257,0.4154999852180481,0.4280000030994415,0.4320000112056732,0.4194999933242798,0.4235000014305115,0.4259999990463257,0.4300000071525574,0.4314999878406524,0.4269999861717224,0.4379999935626983,0.4289999902248382,0.4339999854564667,0.429500013589859,0.4429999887943268,0.4415000081062317,0.4329999983310699,0.4440000057220459,0.4329999983310699,0.4410000145435333,0.4390000104904175,0.4320000112056732,0.4415000081062317,0.449999988079071,0.4444999992847442,0.4309999942779541,0.4329999983310699,0.4469999969005584,0.4384999871253967,0.4449999928474426,0.4535000026226043,0.4435000121593475,0.4399999976158142,0.4399999976158142,0.4474999904632568,0.4469999969005584,0.4460000097751617,0.4460000097751617,0.4395000040531158,0.4514999985694885,0.4494999945163727,0.4595000147819519,0.4485000073909759,0.4474999904632568,0.4514999985694885,0.457500010728836,0.4514999985694885,0.4465000033378601,0.4524999856948852,0.4490000009536743,0.4564999938011169,0.4544999897480011,0.4614999890327453,0.4485000073909759,0.4569999873638153,0.4480000138282776,0.4550000131130218,0.4535000026226043,0.4480000138282776,0.4564999938011169,0.4625000059604645,0.4564999938011169,0.4595000147819519,0.453000009059906,0.4589999914169311,0.4580000042915344,0.4605000019073486,0.4620000123977661,0.4634999930858612,0.4620000123977661,0.4605000019073486,0.4605000019073486,0.4560000002384186,0.460999995470047,0.4665000140666961,0.4645000100135803,0.4564999938011169,0.4614999890327453,0.4629999995231628,0.4639999866485595,0.4564999938011169,0.4659999907016754,0.4555000066757202,0.4634999930858612,0.4584999978542328,0.4634999930858612,0.4584999978542328,0.4704999923706054,0.465499997138977,0.4645000100135803,0.4679999947547912,0.4605000019073486,0.4670000076293945,0.4634999930858612,0.4634999930858612,0.4629999995231628,0.4665000140666961,0.4715000092983246,0.4735000133514404,0.4639999866485595,0.4629999995231628,0.4675000011920929,0.4695000052452087,0.4670000076293945,0.4639999866485595,0.4740000069141388,0.4715000092983246,0.4684999883174896,0.4709999859333038,0.4690000116825104,0.4699999988079071,0.4695000052452087],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2195000052452087,0.2730000019073486,0.3025000095367431,0.3174999952316284,0.3350000083446502,0.3199999928474426,0.3389999866485595,0.3470000028610229,0.3495000004768371,0.3499999940395355,0.3574999868869781,0.3704999983310699,0.3625000119209289,0.3695000112056732,0.3695000112056732,0.3664999902248382,0.3910000026226043,0.37950000166893,0.3819999992847442,0.3804999887943268,0.3914999961853027,0.3860000073909759,0.3860000073909759,0.3804999887943268,0.3865000009536743,0.3925000131130218,0.3935000002384186,0.3790000081062317,0.3964999914169311,0.395000010728836,0.3964999914169311,0.4014999866485595,0.3919999897480011,0.3919999897480011,0.3894999921321869,0.4099999964237213,0.390500009059906,0.4050000011920929,0.4050000011920929,0.3955000042915344,0.3959999978542328,0.3964999914169311,0.4000000059604645,0.4045000076293945,0.402999997138977,0.4110000133514404,0.4079999923706054,0.4115000069141388,0.4079999923706054,0.4115000069141388,0.4135000109672546,0.4169999957084656,0.4059999883174896,0.4189999997615814,0.4135000109672546,0.4154999852180481,0.4084999859333038,0.4165000021457672,0.4104999899864197,0.4074999988079071,0.418500006198883,0.4199999868869781,0.4174999892711639,0.4194999933242798,0.4189999997615814,0.4165000021457672,0.4099999964237213,0.4214999973773956,0.4065000116825104,0.429500013589859,0.4189999997615814,0.4070000052452087,0.4110000133514404,0.4095000028610229,0.4210000038146972,0.4120000004768371,0.4280000030994415,0.4230000078678131,0.4199999868869781,0.4199999868869781,0.4250000119209289,0.4129999876022339,0.4225000143051147,0.4269999861717224,0.4199999868869781,0.4329999983310699,0.426499992609024,0.4390000104904175,0.4275000095367431,0.4255000054836273,0.4239999949932098,0.4225000143051147,0.4284999966621399,0.4255000054836273,0.4305000007152557,0.4314999878406524,0.4235000014305115,0.4210000038146972,0.4289999902248382,0.4275000095367431,0.4345000088214874,0.4375,0.4339999854564667,0.4334999918937683,0.4384999871253967,0.4415000081062317,0.426499992609024,0.4305000007152557,0.4375,0.4289999902248382,0.44200000166893,0.4314999878406524,0.4320000112056732,0.4255000054836273,0.4379999935626983,0.4314999878406524,0.4230000078678131,0.4395000040531158,0.4404999911785126,0.4424999952316284,0.4354999959468841,0.4329999983310699,0.4415000081062317,0.4424999952316284,0.4375,0.4435000121593475,0.4399999976158142,0.4415000081062317,0.449999988079071,0.44200000166893,0.445499986410141,0.4404999911785126,0.4435000121593475,0.4424999952316284,0.4359999895095825,0.4390000104904175,0.453000009059906,0.445499986410141,0.4354999959468841,0.4465000033378601,0.4444999992847442,0.449999988079071,0.4424999952316284,0.4539999961853027,0.449999988079071,0.4480000138282776,0.4524999856948852,0.4474999904632568,0.453000009059906,0.4524999856948852,0.4440000057220459,0.4474999904632568,0.4485000073909759,0.4435000121593475,0.4485000073909759,0.44200000166893,0.4564999938011169,0.4390000104904175,0.4390000104904175,0.4505000114440918,0.4485000073909759,0.4510000050067901,0.4505000114440918,0.4460000097751617,0.4539999961853027,0.4494999945163727,0.4480000138282776,0.4424999952316284],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2195000052452087,0.2675000131130218,0.3075000047683716,0.3219999969005584,0.3100000023841858,0.324999988079071,0.3445000052452087,0.3345000147819519,0.3524999916553497,0.359499990940094,0.3655000030994415,0.3569999933242798,0.3625000119209289,0.3659999966621399,0.3630000054836273,0.3765000104904175,0.3729999959468841,0.3804999887943268,0.3785000145435333,0.3704999983310699,0.3740000128746032,0.3774999976158142,0.3810000121593475,0.390500009059906,0.3899999856948852,0.3899999856948852,0.3840000033378601,0.3955000042915344,0.3844999969005584,0.3849999904632568,0.398499995470047,0.3964999914169311,0.3889999985694885,0.3944999873638153,0.3869999945163727,0.3865000009536743,0.3935000002384186,0.3955000042915344,0.3989999890327453,0.3989999890327453,0.3944999873638153,0.3964999914169311,0.4025000035762787,0.4004999995231628,0.3989999890327453,0.3919999897480011,0.4045000076293945,0.4174999892711639,0.3975000083446502,0.4054999947547912,0.4074999988079071,0.4034999907016754,0.4050000011920929,0.4034999907016754,0.3980000019073486,0.4180000126361847,0.4214999973773956,0.4129999876022339,0.414000004529953,0.4074999988079071,0.4025000035762787,0.4020000100135803,0.3980000019073486,0.4045000076293945,0.3980000019073486,0.4120000004768371,0.4225000143051147,0.4165000021457672,0.4169999957084656,0.4050000011920929,0.4124999940395355,0.4169999957084656,0.4154999852180481,0.4194999933242798,0.429500013589859,0.4120000004768371,0.4210000038146972,0.402999997138977,0.4214999973773956,0.4180000126361847,0.4154999852180481,0.4144999980926513,0.4115000069141388,0.4154999852180481,0.4189999997615814,0.4235000014305115,0.4180000126361847,0.4194999933242798,0.429500013589859,0.4194999933242798,0.4255000054836273,0.4169999957084656,0.4180000126361847,0.4144999980926513,0.421999990940094,0.4194999933242798,0.4214999973773956,0.421999990940094,0.4255000054836273,0.4275000095367431,0.4255000054836273,0.4205000102519989,0.4180000126361847,0.4300000071525574,0.4250000119209289,0.4225000143051147,0.4329999983310699,0.4210000038146972,0.4350000023841858,0.4359999895095825,0.4404999911785126,0.4415000081062317,0.4309999942779541,0.4309999942779541,0.426499992609024,0.4334999918937683,0.429500013589859,0.4300000071525574,0.4384999871253967,0.4305000007152557,0.4370000064373016,0.4379999935626983,0.4259999990463257,0.4210000038146972,0.4280000030994415,0.4350000023841858,0.4300000071525574,0.4359999895095825,0.4365000128746032,0.4225000143051147,0.4194999933242798,0.4284999966621399,0.4275000095367431,0.4314999878406524,0.4350000023841858,0.426499992609024,0.4379999935626983,0.4300000071525574,0.4300000071525574,0.4269999861717224,0.4320000112056732,0.4334999918937683,0.4320000112056732,0.4339999854564667,0.4379999935626983,0.4345000088214874,0.4485000073909759,0.4379999935626983,0.4399999976158142,0.4329999983310699,0.4354999959468841,0.4465000033378601,0.4424999952316284,0.4350000023841858,0.4370000064373016,0.4359999895095825,0.4384999871253967,0.4365000128746032,0.4415000081062317,0.4494999945163727,0.4410000145435333,0.4375,0.4424999952316284,0.4460000097751617,0.4449999928474426,0.4435000121593475,0.4365000128746032,0.4429999887943268],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2195000052452087,0.273499995470047,0.304500013589859,0.324999988079071,0.3440000116825104,0.3330000042915344,0.3429999947547912,0.3564999997615814,0.356000006198883,0.3630000054836273,0.3734999895095825,0.3840000033378601,0.3765000104904175,0.3745000064373016,0.37950000166893,0.382999986410141,0.3889999985694885,0.3939999938011169,0.3824999928474426,0.398499995470047,0.4000000059604645,0.3980000019073486,0.3995000123977661,0.4095000028610229,0.4004999995231628,0.4095000028610229,0.4165000021457672,0.4129999876022339,0.4020000100135803,0.4165000021457672,0.4124999940395355,0.4149999916553497,0.4174999892711639,0.4169999957084656,0.4129999876022339,0.4165000021457672,0.4149999916553497,0.4129999876022339,0.421999990940094,0.429500013589859,0.4099999964237213,0.4225000143051147,0.4235000014305115,0.4239999949932098,0.4205000102519989,0.4235000014305115,0.4284999966621399,0.4350000023841858,0.4334999918937683,0.4350000023841858,0.4135000109672546,0.4275000095367431,0.4235000014305115,0.4365000128746032,0.4309999942779541,0.4259999990463257,0.4250000119209289,0.4244999885559082,0.4350000023841858,0.4325000047683716,0.4305000007152557,0.4314999878406524,0.4410000145435333,0.4395000040531158,0.4334999918937683,0.4300000071525574,0.4379999935626983,0.4314999878406524,0.4309999942779541,0.4359999895095825,0.4474999904632568,0.4429999887943268,0.4384999871253967,0.4404999911785126,0.4390000104904175,0.4255000054836273,0.4309999942779541,0.4404999911785126,0.4289999902248382,0.4429999887943268,0.4460000097751617,0.4399999976158142,0.4379999935626983,0.4424999952316284,0.4404999911785126,0.4535000026226043,0.4410000145435333,0.4444999992847442,0.4494999945163727,0.4514999985694885,0.4510000050067901,0.4480000138282776,0.4560000002384186,0.449999988079071,0.4560000002384186,0.4510000050067901,0.4474999904632568,0.4505000114440918,0.4444999992847442,0.4440000057220459,0.4605000019073486,0.4560000002384186,0.4614999890327453,0.4480000138282776,0.4550000131130218,0.4620000123977661,0.4675000011920929,0.4670000076293945,0.4665000140666961,0.4600000083446502,0.4595000147819519,0.4650000035762787,0.4645000100135803,0.4605000019073486,0.4614999890327453,0.4580000042915344,0.4564999938011169,0.4724999964237213,0.4699999988079071,0.4625000059604645,0.449999988079071,0.4595000147819519,0.4519999921321869,0.4564999938011169,0.4584999978542328,0.4550000131130218,0.4519999921321869,0.4614999890327453,0.4659999907016754,0.4645000100135803,0.4614999890327453,0.4550000131130218,0.4595000147819519,0.4690000116825104,0.4724999964237213,0.4589999914169311,0.4595000147819519,0.4735000133514404,0.4699999988079071,0.465499997138977,0.4634999930858612,0.4620000123977661,0.4605000019073486,0.4690000116825104,0.4675000011920929,0.4729999899864197,0.4659999907016754,0.4724999964237213,0.4709999859333038,0.4754999876022339,0.4720000028610229,0.4740000069141388,0.4600000083446502,0.4684999883174896,0.4724999964237213,0.4779999852180481,0.4600000083446502,0.4740000069141388,0.4724999964237213,0.4709999859333038,0.4650000035762787,0.4720000028610229,0.4754999876022339,0.4774999916553497,0.4699999988079071,0.481000006198883,0.4679999947547912,0.4690000116825104],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2195000052452087,0.2709999978542328,0.3165000081062317,0.3244999945163727,0.3330000042915344,0.3429999947547912,0.3495000004768371,0.3709999918937683,0.3524999916553497,0.3574999868869781,0.363999992609024,0.3709999918937683,0.3759999871253967,0.3634999990463257,0.3860000073909759,0.3815000057220459,0.398499995470047,0.3889999985694885,0.3919999897480011,0.3925000131130218,0.4034999907016754,0.4009999930858612,0.4000000059604645,0.4045000076293945,0.402999997138977,0.4115000069141388,0.3970000147819519,0.4065000116825104,0.4034999907016754,0.4025000035762787,0.4160000085830688,0.4050000011920929,0.4129999876022339,0.4189999997615814,0.4160000085830688,0.4124999940395355,0.4205000102519989,0.4199999868869781,0.4189999997615814,0.4104999899864197,0.4259999990463257,0.4154999852180481,0.4199999868869781,0.4169999957084656,0.4239999949932098,0.426499992609024,0.4339999854564667,0.4275000095367431,0.4325000047683716,0.4300000071525574,0.4210000038146972,0.4189999997615814,0.426499992609024,0.4350000023841858,0.4329999983310699,0.4280000030994415,0.4250000119209289,0.4284999966621399,0.4199999868869781,0.4305000007152557,0.4154999852180481,0.426499992609024,0.429500013589859,0.4269999861717224,0.4480000138282776,0.4334999918937683,0.4415000081062317,0.4309999942779541,0.44200000166893,0.4365000128746032,0.4379999935626983,0.4415000081062317,0.4474999904632568,0.4384999871253967,0.4334999918937683,0.445499986410141,0.4404999911785126,0.4465000033378601,0.4354999959468841,0.4384999871253967,0.445499986410141,0.4505000114440918,0.4350000023841858,0.4555000066757202,0.4410000145435333,0.453000009059906,0.4480000138282776,0.4580000042915344,0.4460000097751617,0.4505000114440918,0.4510000050067901,0.4480000138282776,0.4535000026226043,0.4544999897480011,0.4440000057220459,0.4490000009536743,0.4535000026226043,0.4589999914169311,0.4625000059604645,0.4625000059604645,0.4569999873638153,0.4539999961853027,0.4560000002384186,0.4584999978542328,0.4510000050067901,0.4650000035762787,0.457500010728836,0.4614999890327453,0.4569999873638153,0.4695000052452087,0.4539999961853027,0.4560000002384186,0.4629999995231628,0.4560000002384186,0.4539999961853027,0.4645000100135803,0.4519999921321869,0.449999988079071,0.4580000042915344,0.4494999945163727,0.4555000066757202,0.4550000131130218,0.4519999921321869,0.4550000131130218,0.4539999961853027,0.4569999873638153,0.4659999907016754,0.4550000131130218,0.4564999938011169,0.4560000002384186,0.4465000033378601,0.4595000147819519,0.4665000140666961,0.4659999907016754,0.4569999873638153,0.4665000140666961,0.4614999890327453,0.4650000035762787,0.4645000100135803,0.4665000140666961,0.4665000140666961,0.4695000052452087,0.4709999859333038,0.4679999947547912,0.4684999883174896,0.4639999866485595,0.4704999923706054,0.4740000069141388,0.4699999988079071,0.4690000116825104,0.4665000140666961,0.476500004529953,0.4679999947547912,0.4715000092983246,0.4709999859333038,0.4724999964237213,0.4684999883174896,0.4704999923706054,0.4709999859333038,0.4695000052452087,0.4760000109672546,0.4799999892711639,0.4709999859333038,0.4760000109672546,0.4745000004768371,0.4675000011920929,0.4659999907016754,0.4760000109672546],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2195000052452087,0.2714999914169311,0.3084999918937683,0.3285000026226043,0.3300000131130218,0.3619999885559082,0.3409999907016754,0.3689999878406524,0.3619999885559082,0.3729999959468841,0.3700000047683716,0.37950000166893,0.3779999911785126,0.3704999983310699,0.3835000097751617,0.3810000121593475,0.3759999871253967,0.3725000023841858,0.3925000131130218,0.3955000042915344,0.3955000042915344,0.3925000131130218,0.3930000066757202,0.3959999978542328,0.3970000147819519,0.3935000002384186,0.4034999907016754,0.4004999995231628,0.4000000059604645,0.3899999856948852,0.4099999964237213,0.4014999866485595,0.4020000100135803,0.3894999921321869,0.4059999883174896,0.4090000092983246,0.4095000028610229,0.4034999907016754,0.4004999995231628,0.4070000052452087,0.402999997138977,0.4065000116825104,0.4070000052452087,0.3964999914169311,0.4230000078678131,0.4070000052452087,0.4099999964237213,0.4199999868869781,0.4154999852180481,0.4154999852180481,0.4165000021457672,0.4050000011920929,0.4095000028610229,0.4154999852180481,0.4149999916553497,0.4099999964237213,0.421999990940094,0.4070000052452087,0.4160000085830688,0.429500013589859,0.4235000014305115,0.429500013589859,0.4255000054836273,0.418500006198883,0.4154999852180481,0.4269999861717224,0.4180000126361847,0.4284999966621399,0.4135000109672546,0.4165000021457672,0.429500013589859,0.4169999957084656,0.429500013589859,0.4189999997615814,0.4189999997615814,0.4289999902248382,0.4350000023841858,0.4305000007152557,0.4325000047683716,0.4354999959468841,0.4440000057220459,0.4339999854564667,0.4370000064373016,0.426499992609024,0.4370000064373016,0.4345000088214874,0.4410000145435333,0.4384999871253967,0.4300000071525574,0.4280000030994415,0.4275000095367431,0.4255000054836273,0.4375,0.4350000023841858,0.4345000088214874,0.4390000104904175,0.445499986410141,0.4325000047683716,0.4350000023841858,0.4305000007152557,0.4275000095367431,0.4284999966621399,0.4320000112056732,0.44200000166893,0.4379999935626983,0.4429999887943268,0.4435000121593475,0.4480000138282776,0.4424999952316284,0.4465000033378601,0.4410000145435333,0.4449999928474426,0.4370000064373016,0.4429999887943268,0.4404999911785126,0.4424999952316284,0.4524999856948852,0.4345000088214874,0.4390000104904175,0.4390000104904175,0.4395000040531158,0.4469999969005584,0.4505000114440918,0.4550000131130218,0.4415000081062317,0.4404999911785126,0.4474999904632568,0.4415000081062317,0.4384999871253967,0.4429999887943268,0.4469999969005584,0.4519999921321869,0.4435000121593475,0.4539999961853027,0.4449999928474426,0.4444999992847442,0.4550000131130218,0.4474999904632568,0.4535000026226043,0.4560000002384186,0.4514999985694885,0.4474999904632568,0.4539999961853027,0.4494999945163727,0.4449999928474426,0.4444999992847442,0.4510000050067901,0.4589999914169311,0.4494999945163727,0.4490000009536743,0.4600000083446502,0.4539999961853027,0.4519999921321869,0.4494999945163727,0.4460000097751617,0.4505000114440918,0.453000009059906,0.4524999856948852,0.4514999985694885,0.4485000073909759,0.4494999945163727,0.4490000009536743,0.4544999897480011,0.445499986410141,0.4469999969005584,0.4480000138282776,0.4584999978542328,0.4519999921321869],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2195000052452087,0.2849999964237213,0.3134999871253967,0.3140000104904175,0.3334999978542328,0.3339999914169311,0.3540000021457672,0.3504999876022339,0.3585000038146972,0.3504999876022339,0.3574999868869781,0.3585000038146972,0.3589999973773956,0.3720000088214874,0.3709999918937683,0.3745000064373016,0.3659999966621399,0.3849999904632568,0.3774999976158142,0.3785000145435333,0.3844999969005584,0.3964999914169311,0.3935000002384186,0.3869999945163727,0.3980000019073486,0.3824999928474426,0.3939999938011169,0.4050000011920929,0.3980000019073486,0.4034999907016754,0.3964999914169311,0.4110000133514404,0.4014999866485595,0.3989999890327453,0.3980000019073486,0.3995000123977661,0.4135000109672546,0.4165000021457672,0.3970000147819519,0.4040000140666961,0.4084999859333038,0.4115000069141388,0.4040000140666961,0.4160000085830688,0.414000004529953,0.4135000109672546,0.4079999923706054,0.4210000038146972,0.4205000102519989,0.4165000021457672,0.4169999957084656,0.4165000021457672,0.4275000095367431,0.4269999861717224,0.4329999983310699,0.4334999918937683,0.4255000054836273,0.4300000071525574,0.4305000007152557,0.4280000030994415,0.4339999854564667,0.4244999885559082,0.4305000007152557,0.4225000143051147,0.4404999911785126,0.4320000112056732,0.4284999966621399,0.4214999973773956,0.426499992609024,0.4149999916553497,0.4289999902248382,0.4384999871253967,0.4289999902248382,0.4354999959468841,0.4345000088214874,0.4314999878406524,0.4395000040531158,0.4435000121593475,0.4410000145435333,0.44200000166893,0.4410000145435333,0.4444999992847442,0.4384999871253967,0.4210000038146972,0.4365000128746032,0.4435000121593475,0.4390000104904175,0.4415000081062317,0.4354999959468841,0.4424999952316284,0.4244999885559082,0.4444999992847442,0.4365000128746032,0.4429999887943268,0.4469999969005584,0.4379999935626983,0.4345000088214874,0.4314999878406524,0.4384999871253967,0.4350000023841858,0.4415000081062317,0.4329999983310699,0.4379999935626983,0.4494999945163727,0.4345000088214874,0.4395000040531158,0.4404999911785126,0.4435000121593475,0.4465000033378601,0.4435000121593475,0.4560000002384186,0.4510000050067901,0.4490000009536743,0.4490000009536743,0.4490000009536743,0.4555000066757202,0.4469999969005584,0.4505000114440918,0.4494999945163727,0.4474999904632568,0.4384999871253967,0.4440000057220459,0.4505000114440918,0.4480000138282776,0.4589999914169311,0.4569999873638153,0.44200000166893,0.4474999904632568,0.4510000050067901,0.4485000073909759,0.4629999995231628,0.457500010728836,0.4535000026226043,0.4514999985694885,0.453000009059906,0.4560000002384186,0.453000009059906,0.457500010728836,0.4514999985694885,0.4539999961853027,0.457500010728836,0.4614999890327453,0.453000009059906,0.4490000009536743,0.4514999985694885,0.4560000002384186,0.4535000026226043,0.4589999914169311,0.457500010728836,0.4510000050067901,0.4605000019073486,0.4494999945163727,0.4474999904632568,0.4535000026226043,0.457500010728836,0.457500010728836,0.4560000002384186,0.4560000002384186,0.4535000026226043,0.4564999938011169,0.4625000059604645,0.4645000100135803,0.4580000042915344,0.4639999866485595,0.457500010728836,0.4539999961853027,0.4564999938011169,0.4564999938011169],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2189999967813491,0.2840000092983246,0.3050000071525574,0.3244999945163727,0.3244999945163727,0.332500010728836,0.3474999964237213,0.3544999957084656,0.3650000095367431,0.3589999973773956,0.3675000071525574,0.3700000047683716,0.3574999868869781,0.3680000007152557,0.3734999895095825,0.3614999949932098,0.3774999976158142,0.3855000138282776,0.3894999921321869,0.3810000121593475,0.3930000066757202,0.3989999890327453,0.390500009059906,0.395000010728836,0.4004999995231628,0.3975000083446502,0.4000000059604645,0.4054999947547912,0.3889999985694885,0.4009999930858612,0.3959999978542328,0.402999997138977,0.3975000083446502,0.4054999947547912,0.4009999930858612,0.4070000052452087,0.4095000028610229,0.4065000116825104,0.4174999892711639,0.4115000069141388,0.4189999997615814,0.421999990940094,0.4084999859333038,0.4239999949932098,0.414000004529953,0.4289999902248382,0.4115000069141388,0.4120000004768371,0.4180000126361847,0.4144999980926513,0.4169999957084656,0.4144999980926513,0.4345000088214874,0.4165000021457672,0.421999990940094,0.4189999997615814,0.4104999899864197,0.4065000116825104,0.4189999997615814,0.4144999980926513,0.4180000126361847,0.4205000102519989,0.4305000007152557,0.4259999990463257,0.4289999902248382,0.4225000143051147,0.4289999902248382,0.426499992609024,0.4325000047683716,0.4289999902248382,0.4189999997615814,0.4230000078678131,0.4284999966621399,0.4079999923706054,0.4329999983310699,0.426499992609024,0.4354999959468841,0.429500013589859,0.4280000030994415,0.4309999942779541,0.4305000007152557,0.4314999878406524,0.4334999918937683,0.4280000030994415,0.421999990940094,0.4339999854564667,0.44200000166893,0.421999990940094,0.4320000112056732,0.4325000047683716,0.4359999895095825,0.4280000030994415,0.4259999990463257,0.4194999933242798,0.4250000119209289,0.4424999952316284,0.4435000121593475,0.4474999904632568,0.4370000064373016,0.429500013589859,0.4390000104904175,0.4280000030994415,0.4329999983310699,0.4320000112056732,0.4314999878406524,0.4485000073909759,0.4539999961853027,0.445499986410141,0.4580000042915344,0.4560000002384186,0.449999988079071,0.4424999952316284,0.4465000033378601,0.453000009059906,0.4485000073909759,0.4440000057220459,0.4544999897480011,0.4560000002384186,0.4510000050067901,0.4524999856948852,0.4480000138282776,0.4460000097751617,0.4480000138282776,0.4465000033378601,0.4435000121593475,0.4535000026226043,0.4544999897480011,0.4514999985694885,0.4480000138282776,0.4595000147819519,0.4560000002384186,0.4410000145435333,0.4614999890327453,0.4595000147819519,0.4544999897480011,0.4580000042915344,0.4514999985694885,0.4490000009536743,0.4539999961853027,0.4544999897480011,0.4550000131130218,0.4589999914169311,0.4584999978542328,0.4595000147819519,0.4469999969005584,0.4684999883174896,0.4589999914169311,0.4614999890327453,0.4555000066757202,0.4620000123977661,0.4584999978542328,0.4614999890327453,0.4614999890327453,0.4569999873638153,0.4639999866485595,0.4659999907016754,0.4634999930858612,0.4539999961853027,0.4629999995231628,0.457500010728836,0.4634999930858612,0.4555000066757202,0.460999995470047,0.465499997138977,0.4600000083446502,0.4544999897480011,0.4625000059604645,0.4659999907016754],"label":"FineWeb URL dedup"}},"arc/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2509999871253967,0.2899999916553497,0.31700000166893,0.3409999907016754,0.3425000011920929,0.3485000133514404,0.3555000126361847,0.3574999868869781,0.3585000038146972,0.363999992609024,0.3619999885559082,0.3675000071525574,0.3865000009536743,0.3810000121593475,0.3810000121593475,0.3810000121593475,0.3860000073909759,0.3810000121593475,0.3894999921321869,0.3849999904632568,0.3855000138282776,0.3989999890327453,0.3980000019073486,0.3995000123977661,0.395000010728836,0.4084999859333038,0.4040000140666961,0.4004999995231628,0.3955000042915344,0.4135000109672546,0.4070000052452087,0.4104999899864197,0.4014999866485595,0.4099999964237213,0.4199999868869781,0.414000004529953,0.402999997138977,0.4214999973773956,0.4095000028610229,0.4059999883174896,0.4090000092983246,0.4074999988079071,0.4120000004768371,0.4154999852180481,0.4189999997615814,0.4149999916553497,0.429500013589859,0.4154999852180481,0.4214999973773956,0.4244999885559082,0.4205000102519989,0.4269999861717224,0.4214999973773956,0.4180000126361847,0.4415000081062317,0.4320000112056732,0.4350000023841858,0.4259999990463257,0.4300000071525574,0.4259999990463257,0.4189999997615814,0.4269999861717224,0.4199999868869781,0.426499992609024,0.4350000023841858,0.4289999902248382,0.4345000088214874,0.4259999990463257,0.426499992609024,0.4395000040531158,0.4395000040531158,0.4359999895095825,0.4280000030994415,0.4370000064373016,0.4329999983310699,0.4309999942779541,0.4490000009536743,0.4399999976158142,0.4339999854564667,0.4399999976158142,0.4345000088214874,0.429500013589859,0.4370000064373016,0.4379999935626983,0.4284999966621399,0.4309999942779541,0.4350000023841858,0.4399999976158142,0.4314999878406524,0.4300000071525574,0.4410000145435333,0.4345000088214874,0.4410000145435333,0.4345000088214874,0.4339999854564667,0.4460000097751617,0.4410000145435333,0.4469999969005584,0.4480000138282776,0.4435000121593475,0.4375,0.4519999921321869,0.4480000138282776,0.4429999887943268,0.4519999921321869,0.4435000121593475,0.4334999918937683,0.4460000097751617,0.4564999938011169,0.4469999969005584,0.453000009059906,0.4485000073909759,0.4410000145435333,0.4444999992847442,0.4485000073909759,0.457500010728836,0.4469999969005584,0.4535000026226043,0.4535000026226043,0.4485000073909759,0.4490000009536743,0.4505000114440918,0.4595000147819519,0.4544999897480011,0.453000009059906,0.4605000019073486,0.4620000123977661,0.457500010728836,0.453000009059906,0.4550000131130218,0.460999995470047,0.4449999928474426,0.4474999904632568,0.457500010728836,0.4584999978542328,0.4494999945163727,0.4474999904632568,0.4625000059604645,0.4639999866485595,0.4555000066757202,0.4469999969005584,0.4600000083446502,0.453000009059906,0.4629999995231628,0.4589999914169311,0.4614999890327453,0.4555000066757202,0.4560000002384186,0.4580000042915344,0.4584999978542328,0.4560000002384186,0.4605000019073486,0.4595000147819519,0.4639999866485595,0.4614999890327453,0.4564999938011169,0.4634999930858612,0.4625000059604645,0.4614999890327453,0.4679999947547912,0.4584999978542328,0.4595000147819519,0.4505000114440918,0.4544999897480011,0.4595000147819519,0.4620000123977661,0.4670000076293945,0.4555000066757202],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2515000104904175,0.2784999907016754,0.3149999976158142,0.3305000066757202,0.3334999978542328,0.3440000116825104,0.3600000143051147,0.3495000004768371,0.3680000007152557,0.3695000112056732,0.367000013589859,0.3745000064373016,0.3650000095367431,0.3664999902248382,0.3650000095367431,0.367000013589859,0.3844999969005584,0.3765000104904175,0.3860000073909759,0.3810000121593475,0.3910000026226043,0.3824999928474426,0.3759999871253967,0.3919999897480011,0.3935000002384186,0.4000000059604645,0.4014999866485595,0.3849999904632568,0.4009999930858612,0.398499995470047,0.402999997138977,0.4050000011920929,0.387499988079071,0.3980000019073486,0.3889999985694885,0.4059999883174896,0.4104999899864197,0.414000004529953,0.4084999859333038,0.3869999945163727,0.3955000042915344,0.4009999930858612,0.4079999923706054,0.4074999988079071,0.4090000092983246,0.4149999916553497,0.4129999876022339,0.418500006198883,0.4104999899864197,0.4025000035762787,0.4074999988079071,0.4199999868869781,0.4110000133514404,0.4074999988079071,0.4199999868869781,0.4165000021457672,0.414000004529953,0.4165000021457672,0.4160000085830688,0.426499992609024,0.4235000014305115,0.4214999973773956,0.4194999933242798,0.4189999997615814,0.4160000085830688,0.4180000126361847,0.4120000004768371,0.421999990940094,0.4169999957084656,0.4305000007152557,0.426499992609024,0.4099999964237213,0.4250000119209289,0.4110000133514404,0.4230000078678131,0.4255000054836273,0.4275000095367431,0.4259999990463257,0.426499992609024,0.4259999990463257,0.4269999861717224,0.4154999852180481,0.4314999878406524,0.4359999895095825,0.4250000119209289,0.4354999959468841,0.4235000014305115,0.4314999878406524,0.4300000071525574,0.4404999911785126,0.4239999949932098,0.4239999949932098,0.4339999854564667,0.4284999966621399,0.4334999918937683,0.4329999983310699,0.4314999878406524,0.4189999997615814,0.4329999983310699,0.4210000038146972,0.4314999878406524,0.4370000064373016,0.4399999976158142,0.4399999976158142,0.4325000047683716,0.4399999976158142,0.4300000071525574,0.4239999949932098,0.4199999868869781,0.4399999976158142,0.429500013589859,0.4399999976158142,0.4320000112056732,0.4269999861717224,0.4370000064373016,0.4390000104904175,0.4345000088214874,0.4460000097751617,0.4375,0.4365000128746032,0.445499986410141,0.4395000040531158,0.4469999969005584,0.4399999976158142,0.4424999952316284,0.4494999945163727,0.4494999945163727,0.4544999897480011,0.4580000042915344,0.4539999961853027,0.457500010728836,0.445499986410141,0.4569999873638153,0.4564999938011169,0.449999988079071,0.453000009059906,0.4595000147819519,0.4614999890327453,0.449999988079071,0.4539999961853027,0.4510000050067901,0.4569999873638153,0.4555000066757202,0.4550000131130218,0.4584999978542328,0.4595000147819519,0.4639999866485595,0.457500010728836,0.4535000026226043,0.4560000002384186,0.4645000100135803,0.4634999930858612,0.4584999978542328,0.4589999914169311,0.4555000066757202,0.457500010728836,0.4595000147819519,0.4580000042915344,0.449999988079071,0.4629999995231628,0.4625000059604645,0.4659999907016754,0.4600000083446502,0.4620000123977661,0.4695000052452087,0.460999995470047,0.4645000100135803,0.4550000131130218],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2509999871253967,0.2894999980926513,0.3235000073909759,0.3389999866485595,0.3384999930858612,0.3459999859333038,0.359499990940094,0.3429999947547912,0.3619999885559082,0.3564999997615814,0.3625000119209289,0.363999992609024,0.3680000007152557,0.3680000007152557,0.3684999942779541,0.375,0.3734999895095825,0.3849999904632568,0.3944999873638153,0.3865000009536743,0.395000010728836,0.3935000002384186,0.3980000019073486,0.3910000026226043,0.3885000050067901,0.3914999961853027,0.3815000057220459,0.395000010728836,0.3894999921321869,0.395000010728836,0.3935000002384186,0.4034999907016754,0.4004999995231628,0.3970000147819519,0.3975000083446502,0.3995000123977661,0.3980000019073486,0.4034999907016754,0.3959999978542328,0.3989999890327453,0.402999997138977,0.3880000114440918,0.3980000019073486,0.4040000140666961,0.3989999890327453,0.3970000147819519,0.3925000131130218,0.4120000004768371,0.3935000002384186,0.395000010728836,0.4070000052452087,0.3935000002384186,0.4034999907016754,0.4189999997615814,0.4129999876022339,0.4160000085830688,0.4149999916553497,0.418500006198883,0.4225000143051147,0.4174999892711639,0.4210000038146972,0.4045000076293945,0.4079999923706054,0.4124999940395355,0.4144999980926513,0.4169999957084656,0.4194999933242798,0.4154999852180481,0.4169999957084656,0.4225000143051147,0.4225000143051147,0.4230000078678131,0.4160000085830688,0.4325000047683716,0.4325000047683716,0.4199999868869781,0.4199999868869781,0.4189999997615814,0.4269999861717224,0.4259999990463257,0.4230000078678131,0.4144999980926513,0.4329999983310699,0.4275000095367431,0.4305000007152557,0.4289999902248382,0.4235000014305115,0.4235000014305115,0.4325000047683716,0.4244999885559082,0.4314999878406524,0.4194999933242798,0.4350000023841858,0.4269999861717224,0.4235000014305115,0.4300000071525574,0.4284999966621399,0.4255000054836273,0.4280000030994415,0.4345000088214874,0.4225000143051147,0.4334999918937683,0.4300000071525574,0.4350000023841858,0.429500013589859,0.4325000047683716,0.4384999871253967,0.4345000088214874,0.4354999959468841,0.4359999895095825,0.4354999959468841,0.4424999952316284,0.4424999952316284,0.4320000112056732,0.4280000030994415,0.4390000104904175,0.4480000138282776,0.4415000081062317,0.4384999871253967,0.4390000104904175,0.4494999945163727,0.4449999928474426,0.4384999871253967,0.4424999952316284,0.4359999895095825,0.445499986410141,0.4399999976158142,0.4375,0.4410000145435333,0.4384999871253967,0.4375,0.4329999983310699,0.4370000064373016,0.4354999959468841,0.4440000057220459,0.4384999871253967,0.4384999871253967,0.4390000104904175,0.4424999952316284,0.4379999935626983,0.4345000088214874,0.4354999959468841,0.4440000057220459,0.4395000040531158,0.4465000033378601,0.4404999911785126,0.4505000114440918,0.4480000138282776,0.4449999928474426,0.445499986410141,0.4410000145435333,0.4485000073909759,0.4460000097751617,0.4480000138282776,0.4465000033378601,0.4460000097751617,0.4460000097751617,0.4395000040531158,0.4474999904632568,0.4469999969005584,0.4404999911785126,0.4440000057220459,0.4435000121593475,0.4435000121593475,0.4514999985694885,0.4474999904632568,0.4474999904632568,0.445499986410141],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2515000104904175,0.2964999973773956,0.3255000114440918,0.3400000035762787,0.3465000092983246,0.3504999876022339,0.3600000143051147,0.3709999918937683,0.359499990940094,0.363999992609024,0.3840000033378601,0.3910000026226043,0.37950000166893,0.3980000019073486,0.3885000050067901,0.3894999921321869,0.3959999978542328,0.4004999995231628,0.390500009059906,0.3959999978542328,0.4034999907016754,0.4009999930858612,0.4045000076293945,0.4025000035762787,0.4160000085830688,0.4120000004768371,0.4065000116825104,0.4025000035762787,0.4014999866485595,0.402999997138977,0.4070000052452087,0.4079999923706054,0.4084999859333038,0.4120000004768371,0.4065000116825104,0.4115000069141388,0.4199999868869781,0.4235000014305115,0.4169999957084656,0.4174999892711639,0.4090000092983246,0.4099999964237213,0.4120000004768371,0.4214999973773956,0.4210000038146972,0.4314999878406524,0.4214999973773956,0.4280000030994415,0.4329999983310699,0.4214999973773956,0.4180000126361847,0.4309999942779541,0.4309999942779541,0.4390000104904175,0.4415000081062317,0.4339999854564667,0.4305000007152557,0.429500013589859,0.4329999983310699,0.4365000128746032,0.4289999902248382,0.4395000040531158,0.4424999952316284,0.4259999990463257,0.421999990940094,0.4284999966621399,0.4345000088214874,0.4339999854564667,0.4359999895095825,0.4305000007152557,0.4399999976158142,0.4424999952316284,0.4354999959468841,0.4370000064373016,0.4339999854564667,0.4239999949932098,0.4269999861717224,0.4460000097751617,0.4359999895095825,0.4339999854564667,0.4370000064373016,0.4404999911785126,0.4365000128746032,0.4510000050067901,0.4415000081062317,0.445499986410141,0.4460000097751617,0.4480000138282776,0.453000009059906,0.4535000026226043,0.4399999976158142,0.4490000009536743,0.4379999935626983,0.4480000138282776,0.4485000073909759,0.4404999911785126,0.4435000121593475,0.4424999952316284,0.4440000057220459,0.445499986410141,0.445499986410141,0.4524999856948852,0.4560000002384186,0.4544999897480011,0.4490000009536743,0.4589999914169311,0.4675000011920929,0.4684999883174896,0.4510000050067901,0.457500010728836,0.4519999921321869,0.457500010728836,0.453000009059906,0.4524999856948852,0.4600000083446502,0.4544999897480011,0.4560000002384186,0.4494999945163727,0.4514999985694885,0.4535000026226043,0.4474999904632568,0.4519999921321869,0.4460000097751617,0.457500010728836,0.4535000026226043,0.4519999921321869,0.445499986410141,0.4505000114440918,0.4595000147819519,0.4524999856948852,0.4524999856948852,0.457500010728836,0.460999995470047,0.4510000050067901,0.4584999978542328,0.4505000114440918,0.4505000114440918,0.4589999914169311,0.4605000019073486,0.4460000097751617,0.4560000002384186,0.4595000147819519,0.457500010728836,0.460999995470047,0.4659999907016754,0.4589999914169311,0.4645000100135803,0.4605000019073486,0.460999995470047,0.4625000059604645,0.4569999873638153,0.4600000083446502,0.4560000002384186,0.4589999914169311,0.4584999978542328,0.4695000052452087,0.4544999897480011,0.4629999995231628,0.4589999914169311,0.4595000147819519,0.4560000002384186,0.4580000042915344,0.4620000123977661,0.4629999995231628,0.453000009059906,0.4720000028610229,0.4629999995231628,0.460999995470047],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2509999871253967,0.2939999997615814,0.3174999952316284,0.3294999897480011,0.3510000109672546,0.3485000133514404,0.3634999990463257,0.3700000047683716,0.3524999916553497,0.375,0.3804999887943268,0.37950000166893,0.3824999928474426,0.3799999952316284,0.395000010728836,0.3844999969005584,0.3894999921321869,0.3855000138282776,0.3955000042915344,0.3995000123977661,0.4009999930858612,0.3939999938011169,0.3970000147819519,0.3955000042915344,0.3955000042915344,0.4079999923706054,0.3959999978542328,0.4090000092983246,0.4045000076293945,0.3930000066757202,0.4099999964237213,0.4054999947547912,0.4124999940395355,0.4160000085830688,0.4149999916553497,0.4070000052452087,0.4110000133514404,0.4144999980926513,0.4120000004768371,0.4050000011920929,0.4165000021457672,0.4180000126361847,0.4050000011920929,0.4120000004768371,0.4135000109672546,0.4320000112056732,0.4284999966621399,0.4269999861717224,0.414000004529953,0.4255000054836273,0.4165000021457672,0.4144999980926513,0.4079999923706054,0.4205000102519989,0.4180000126361847,0.4244999885559082,0.4235000014305115,0.4244999885559082,0.4300000071525574,0.4160000085830688,0.4205000102519989,0.4329999983310699,0.4280000030994415,0.4244999885559082,0.4375,0.4244999885559082,0.4365000128746032,0.4329999983310699,0.4424999952316284,0.4390000104904175,0.4449999928474426,0.445499986410141,0.4320000112056732,0.4365000128746032,0.4244999885559082,0.429500013589859,0.4395000040531158,0.4284999966621399,0.44200000166893,0.4370000064373016,0.4399999976158142,0.4334999918937683,0.4429999887943268,0.44200000166893,0.4334999918937683,0.4384999871253967,0.4365000128746032,0.4390000104904175,0.4354999959468841,0.44200000166893,0.4350000023841858,0.4390000104904175,0.4404999911785126,0.4410000145435333,0.4305000007152557,0.4490000009536743,0.4510000050067901,0.4605000019073486,0.4490000009536743,0.449999988079071,0.4595000147819519,0.4514999985694885,0.4490000009536743,0.4474999904632568,0.4444999992847442,0.4524999856948852,0.4465000033378601,0.4519999921321869,0.4550000131130218,0.4524999856948852,0.4429999887943268,0.4550000131130218,0.4510000050067901,0.4560000002384186,0.4465000033378601,0.4485000073909759,0.4524999856948852,0.4440000057220459,0.457500010728836,0.4544999897480011,0.4480000138282776,0.4584999978542328,0.4544999897480011,0.4569999873638153,0.4584999978542328,0.4444999992847442,0.4629999995231628,0.457500010728836,0.4555000066757202,0.4569999873638153,0.4474999904632568,0.4564999938011169,0.4595000147819519,0.4634999930858612,0.4555000066757202,0.453000009059906,0.457500010728836,0.4614999890327453,0.460999995470047,0.4539999961853027,0.4595000147819519,0.4629999995231628,0.4670000076293945,0.4580000042915344,0.4639999866485595,0.457500010728836,0.4595000147819519,0.4665000140666961,0.4584999978542328,0.4629999995231628,0.4595000147819519,0.4659999907016754,0.4645000100135803,0.4675000011920929,0.4690000116825104,0.4715000092983246,0.4634999930858612,0.4634999930858612,0.4639999866485595,0.465499997138977,0.4675000011920929,0.4670000076293945,0.4600000083446502,0.4595000147819519,0.4625000059604645,0.4600000083446502,0.4645000100135803,0.4715000092983246],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2509999871253967,0.2854999899864197,0.3240000009536743,0.3400000035762787,0.3379999995231628,0.3659999966621399,0.3499999940395355,0.3544999957084656,0.3700000047683716,0.3689999878406524,0.3844999969005584,0.3720000088214874,0.3840000033378601,0.3910000026226043,0.398499995470047,0.3774999976158142,0.3855000138282776,0.382999986410141,0.3880000114440918,0.3939999938011169,0.4059999883174896,0.3930000066757202,0.4059999883174896,0.4059999883174896,0.3975000083446502,0.4004999995231628,0.4059999883174896,0.4050000011920929,0.3959999978542328,0.4050000011920929,0.4034999907016754,0.4065000116825104,0.4074999988079071,0.3989999890327453,0.4079999923706054,0.4059999883174896,0.3989999890327453,0.4084999859333038,0.3935000002384186,0.4004999995231628,0.398499995470047,0.3914999961853027,0.4124999940395355,0.4040000140666961,0.4180000126361847,0.4079999923706054,0.414000004529953,0.4065000116825104,0.426499992609024,0.4054999947547912,0.4104999899864197,0.4054999947547912,0.4004999995231628,0.4074999988079071,0.421999990940094,0.4099999964237213,0.4149999916553497,0.4034999907016754,0.4239999949932098,0.4239999949932098,0.4225000143051147,0.4244999885559082,0.426499992609024,0.4239999949932098,0.4214999973773956,0.4339999854564667,0.4269999861717224,0.4375,0.4214999973773956,0.4194999933242798,0.4325000047683716,0.426499992609024,0.4339999854564667,0.4305000007152557,0.4169999957084656,0.426499992609024,0.4255000054836273,0.4235000014305115,0.4284999966621399,0.4339999854564667,0.4435000121593475,0.4379999935626983,0.429500013589859,0.4379999935626983,0.44200000166893,0.4350000023841858,0.4410000145435333,0.4365000128746032,0.4309999942779541,0.4325000047683716,0.429500013589859,0.4259999990463257,0.44200000166893,0.4365000128746032,0.4359999895095825,0.44200000166893,0.4384999871253967,0.4465000033378601,0.4289999902248382,0.4365000128746032,0.4325000047683716,0.4305000007152557,0.4480000138282776,0.4435000121593475,0.4325000047683716,0.4480000138282776,0.4469999969005584,0.4390000104904175,0.4474999904632568,0.445499986410141,0.4375,0.4390000104904175,0.4365000128746032,0.4584999978542328,0.4390000104904175,0.4390000104904175,0.4429999887943268,0.4490000009536743,0.4275000095367431,0.4370000064373016,0.4510000050067901,0.4589999914169311,0.4564999938011169,0.4564999938011169,0.4435000121593475,0.4444999992847442,0.4424999952316284,0.4440000057220459,0.4449999928474426,0.4505000114440918,0.4395000040531158,0.4539999961853027,0.4505000114440918,0.4494999945163727,0.4519999921321869,0.4474999904632568,0.4584999978542328,0.4550000131130218,0.4550000131130218,0.4465000033378601,0.4625000059604645,0.4605000019073486,0.4600000083446502,0.449999988079071,0.4494999945163727,0.4519999921321869,0.4569999873638153,0.4584999978542328,0.449999988079071,0.4605000019073486,0.4620000123977661,0.4564999938011169,0.4564999938011169,0.460999995470047,0.4519999921321869,0.4605000019073486,0.4480000138282776,0.4589999914169311,0.4600000083446502,0.4539999961853027,0.4480000138282776,0.457500010728836,0.4539999961853027,0.4555000066757202,0.4485000073909759,0.4535000026226043,0.4505000114440918,0.4614999890327453],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2509999871253967,0.2915000021457672,0.3194999992847442,0.3289999961853027,0.3470000028610229,0.3555000126361847,0.3544999957084656,0.3684999942779541,0.3675000071525574,0.3675000071525574,0.3664999902248382,0.3725000023841858,0.3659999966621399,0.3714999854564667,0.3759999871253967,0.3790000081062317,0.3644999861717224,0.3810000121593475,0.3855000138282776,0.3914999961853027,0.3849999904632568,0.387499988079071,0.3844999969005584,0.3930000066757202,0.4065000116825104,0.3819999992847442,0.3894999921321869,0.3995000123977661,0.395000010728836,0.3980000019073486,0.4025000035762787,0.4124999940395355,0.4065000116825104,0.4000000059604645,0.4065000116825104,0.3970000147819519,0.4189999997615814,0.4169999957084656,0.4034999907016754,0.4070000052452087,0.4154999852180481,0.4045000076293945,0.4040000140666961,0.4250000119209289,0.4110000133514404,0.4099999964237213,0.4084999859333038,0.4169999957084656,0.4095000028610229,0.4214999973773956,0.4120000004768371,0.418500006198883,0.414000004529953,0.4305000007152557,0.4280000030994415,0.4259999990463257,0.4255000054836273,0.4354999959468841,0.4314999878406524,0.4239999949932098,0.4280000030994415,0.4334999918937683,0.4300000071525574,0.4214999973773956,0.4325000047683716,0.4225000143051147,0.4329999983310699,0.4230000078678131,0.4325000047683716,0.4239999949932098,0.4250000119209289,0.4314999878406524,0.4289999902248382,0.4280000030994415,0.4329999983310699,0.4244999885559082,0.4350000023841858,0.4325000047683716,0.4359999895095825,0.4325000047683716,0.4305000007152557,0.4370000064373016,0.4404999911785126,0.4339999854564667,0.4314999878406524,0.4424999952316284,0.4370000064373016,0.4339999854564667,0.4379999935626983,0.4404999911785126,0.426499992609024,0.4404999911785126,0.4325000047683716,0.449999988079071,0.4505000114440918,0.4359999895095825,0.4410000145435333,0.4350000023841858,0.44200000166893,0.4334999918937683,0.4429999887943268,0.4339999854564667,0.445499986410141,0.4440000057220459,0.4449999928474426,0.4514999985694885,0.453000009059906,0.4589999914169311,0.457500010728836,0.4569999873638153,0.4580000042915344,0.4510000050067901,0.4569999873638153,0.4474999904632568,0.449999988079071,0.4555000066757202,0.4510000050067901,0.4580000042915344,0.4555000066757202,0.457500010728836,0.4555000066757202,0.4539999961853027,0.4580000042915344,0.4514999985694885,0.4614999890327453,0.4704999923706054,0.4480000138282776,0.4659999907016754,0.4589999914169311,0.465499997138977,0.4625000059604645,0.465499997138977,0.4595000147819519,0.4625000059604645,0.4665000140666961,0.4620000123977661,0.4670000076293945,0.4684999883174896,0.460999995470047,0.4745000004768371,0.4665000140666961,0.4690000116825104,0.4720000028610229,0.4679999947547912,0.4614999890327453,0.4704999923706054,0.4650000035762787,0.4629999995231628,0.4629999995231628,0.4634999930858612,0.4699999988079071,0.4699999988079071,0.4620000123977661,0.4715000092983246,0.4729999899864197,0.4679999947547912,0.4650000035762787,0.4639999866485595,0.4699999988079071,0.4620000123977661,0.4690000116825104,0.4729999899864197,0.465499997138977,0.4720000028610229,0.4690000116825104,0.4695000052452087,0.4724999964237213,0.4720000028610229],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2515000104904175,0.2989999949932098,0.3219999969005584,0.3334999978542328,0.3449999988079071,0.3485000133514404,0.3650000095367431,0.3614999949932098,0.363999992609024,0.3659999966621399,0.3720000088214874,0.3770000040531158,0.3610000014305115,0.3600000143051147,0.3709999918937683,0.3524999916553497,0.3680000007152557,0.3819999992847442,0.3799999952316284,0.3855000138282776,0.3865000009536743,0.3880000114440918,0.3799999952316284,0.3894999921321869,0.3914999961853027,0.398499995470047,0.398499995470047,0.3925000131130218,0.3914999961853027,0.398499995470047,0.3975000083446502,0.402999997138977,0.4000000059604645,0.4054999947547912,0.4115000069141388,0.4054999947547912,0.4115000069141388,0.4040000140666961,0.4090000092983246,0.4040000140666961,0.402999997138977,0.4115000069141388,0.4000000059604645,0.429500013589859,0.4025000035762787,0.4124999940395355,0.4115000069141388,0.4050000011920929,0.4070000052452087,0.4104999899864197,0.3980000019073486,0.4095000028610229,0.4269999861717224,0.4210000038146972,0.4235000014305115,0.4124999940395355,0.4225000143051147,0.4090000092983246,0.4230000078678131,0.4180000126361847,0.4244999885559082,0.4235000014305115,0.4235000014305115,0.4269999861717224,0.4154999852180481,0.4259999990463257,0.4225000143051147,0.4169999957084656,0.4359999895095825,0.4275000095367431,0.4235000014305115,0.4169999957084656,0.4235000014305115,0.4174999892711639,0.4305000007152557,0.4280000030994415,0.4359999895095825,0.418500006198883,0.4275000095367431,0.4259999990463257,0.4244999885559082,0.4269999861717224,0.4334999918937683,0.4300000071525574,0.4250000119209289,0.4255000054836273,0.4339999854564667,0.4289999902248382,0.4284999966621399,0.4259999990463257,0.4390000104904175,0.4250000119209289,0.4289999902248382,0.4269999861717224,0.4300000071525574,0.4345000088214874,0.44200000166893,0.4524999856948852,0.4460000097751617,0.4384999871253967,0.4325000047683716,0.426499992609024,0.4329999983310699,0.4320000112056732,0.4320000112056732,0.4444999992847442,0.453000009059906,0.445499986410141,0.4480000138282776,0.4449999928474426,0.4415000081062317,0.4390000104904175,0.4424999952316284,0.4494999945163727,0.4415000081062317,0.4460000097751617,0.4539999961853027,0.449999988079071,0.4449999928474426,0.4524999856948852,0.4465000033378601,0.4334999918937683,0.4490000009536743,0.4404999911785126,0.4485000073909759,0.4494999945163727,0.4539999961853027,0.4490000009536743,0.4410000145435333,0.4539999961853027,0.4584999978542328,0.4440000057220459,0.4600000083446502,0.4505000114440918,0.4580000042915344,0.457500010728836,0.4539999961853027,0.4449999928474426,0.4465000033378601,0.4564999938011169,0.4510000050067901,0.4555000066757202,0.4514999985694885,0.4524999856948852,0.4460000097751617,0.4600000083446502,0.4555000066757202,0.4465000033378601,0.4535000026226043,0.4539999961853027,0.457500010728836,0.4494999945163727,0.4550000131130218,0.4510000050067901,0.457500010728836,0.4514999985694885,0.4505000114440918,0.4535000026226043,0.449999988079071,0.4485000073909759,0.4494999945163727,0.449999988079071,0.4560000002384186,0.4539999961853027,0.4569999873638153,0.4465000033378601,0.4564999938011169,0.4564999938011169],"label":"FineWeb URL dedup"}},"mmlu/acc":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2302941530942917,0.2405829578638076,0.2450667917728424,0.250267893075943,0.2507315576076507,0.2576118409633636,0.2574253976345062,0.2628722488880157,0.2644384205341339,0.2702414989471435,0.2663867175579071,0.2689258158206939,0.2687146663665771,0.2676065266132355,0.2691615521907806,0.2706006467342376,0.2736584544181824,0.2746991813182831,0.2741798460483551,0.272423505783081,0.2805862426757812,0.2777875959873199,0.2752496600151062,0.2757043540477752,0.2761420309543609,0.2791363298892975,0.2797969877719879,0.2797309160232544,0.2755179107189178,0.2844363152980804,0.2820940613746643,0.283543199300766,0.2858954668045044,0.2816318869590759,0.2813069224357605,0.2818962335586548,0.2825306355953216,0.282880574464798,0.2810108065605163,0.2815119624137878,0.2832073867321014,0.2825962007045746,0.2820583581924438,0.2821622192859649,0.2786605358123779,0.2883289456367492,0.2807977795600891,0.2859970033168793,0.2870381772518158,0.2897791266441345,0.2796809375286102,0.2866620719432831,0.2845649123191833,0.2880626618862152,0.2874505817890167,0.2857808172702789,0.2867595553398132,0.2869653403759002,0.2860348522663116,0.2906606197357178,0.2821574509143829,0.289130836725235,0.2875072360038757,0.2884832322597503,0.2856673896312713,0.2871889770030975,0.2922988533973694,0.2935270965099334,0.2890375852584839,0.2862584292888641,0.2951976060867309,0.291631817817688,0.2929330170154571,0.2893630862236023,0.2878957092761993,0.2923579514026642,0.2913581430912018,0.2918873131275177,0.2926721572875976,0.2958362400531769,0.2955732345581054,0.2919157743453979,0.2908507585525512,0.2951728701591491,0.2940085828304291,0.296534389257431,0.2939820885658264,0.2948720157146454,0.2942836880683899,0.2921408414840698,0.2975771427154541,0.2972725927829742,0.293838769197464,0.2960700392723083,0.2971054315567016,0.2961299121379852,0.296864777803421,0.2978164553642273,0.2989802062511444,0.2968626916408539,0.2994182407855987,0.2990803122520447,0.2927748560905456,0.298820436000824,0.299898087978363,0.2952330708503723,0.2962251603603363,0.2951344549655914,0.2973354160785675,0.2973885536193847,0.2975764274597168,0.2971931993961334,0.2980869114398956,0.2979022562503814,0.2991840839385986,0.2984327673912048,0.2986229062080383,0.2955830991268158,0.2992549240589142,0.2967789471149444,0.2991774380207062,0.3031741976737976,0.2985482513904571,0.2986876964569092,0.3048456907272339,0.3001897633075714,0.3018456101417541,0.3032538294792175,0.3006997108459472,0.2999642193317413,0.3040018379688263,0.3004764914512634,0.2979345023632049,0.3039732873439789,0.3006691038608551,0.2995238900184631,0.2986087501049042,0.3038967847824096,0.3025071918964386,0.3029733002185821,0.3044440448284149,0.3004992604255676,0.305156260728836,0.3029279410839081,0.3027839660644531,0.3039737045764923,0.3021354973316192,0.3067358732223511,0.3016842603683471,0.3042422831058502,0.3052462935447693,0.3033320605754852,0.3031117022037506,0.3053246438503265,0.3034772276878357,0.3030612468719482,0.3051216900348663,0.2965869605541229,0.3025960028171539,0.3012389540672302,0.3032596409320831,0.3031393587589264,0.3052072525024414,0.3047348856925964,0.303049623966217,0.3001274168491363,0.3033583760261535,0.3040348291397095],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2301375120878219,0.2404979169368744,0.2487602680921554,0.2516559064388275,0.2606706619262695,0.2623841762542724,0.2604553997516632,0.2622999846935272,0.2647940218448639,0.2653771042823791,0.2683143615722656,0.2704180181026459,0.2687296867370605,0.2680672109127044,0.2687917947769165,0.2730067074298858,0.2721324265003204,0.270932525396347,0.2750434577465057,0.2698492109775543,0.2735810279846191,0.2747453153133392,0.2734541594982147,0.2757095992565155,0.2761601507663727,0.2747097313404083,0.2744422852993011,0.2749250829219818,0.2753488719463348,0.2768447697162628,0.2769301235675812,0.2761522531509399,0.2751984596252441,0.2800737619400024,0.277464896440506,0.2798367142677307,0.2811125516891479,0.279954195022583,0.2840792536735534,0.2800381779670715,0.2774267196655273,0.2829022705554962,0.2788951694965362,0.2855189740657806,0.2817118763923645,0.2798790037631988,0.2832670211791992,0.2823235988616943,0.2820709645748138,0.2844878435134887,0.2864419221878052,0.2873905897140503,0.283490926027298,0.2842352092266083,0.2787314355373382,0.2835323214530945,0.2833520472049713,0.2843783795833587,0.2848454117774963,0.2867993712425232,0.2833679616451263,0.2855691015720367,0.2830132246017456,0.2841243147850036,0.2809899747371673,0.2869817614555359,0.2794113755226135,0.2840205132961273,0.2825760543346405,0.2855633199214935,0.2886479198932647,0.2850384414196014,0.2829202711582184,0.2864995896816253,0.2838490009307861,0.2830989360809326,0.2860795259475708,0.2822003960609436,0.286266416311264,0.2801854908466339,0.2850552201271057,0.2831469774246216,0.2881248593330383,0.2852837443351745,0.2822920382022857,0.2886355519294739,0.286035418510437,0.2892711460590362,0.2887631952762604,0.2860815525054931,0.2869010269641876,0.2869570553302765,0.2867247760295868,0.2849505245685577,0.2856247723102569,0.2894046604633331,0.2885980904102325,0.2901588976383209,0.2844109833240509,0.2885493040084839,0.2887346446514129,0.2878243029117584,0.2873888313770294,0.2896631360054016,0.2898592054843902,0.2908548414707184,0.2898348569869995,0.2907491028308868,0.2875790596008301,0.288995087146759,0.2940312027931213,0.2899711430072784,0.2915889322757721,0.2917147576808929,0.2910755276679992,0.2915754914283752,0.2909590005874634,0.2916752099990845,0.2936562895774841,0.2939815521240234,0.2947404384613037,0.2905757427215576,0.2921632528305053,0.2936954200267792,0.2923091650009155,0.2917549014091491,0.2935185134410858,0.2912152409553528,0.2954114973545074,0.2934858500957489,0.2948988974094391,0.2928310036659241,0.2939939200878143,0.2976680994033813,0.2975406944751739,0.2984499335289001,0.2976469397544861,0.2982706725597381,0.2950336635112762,0.2936302125453949,0.2994522750377655,0.2958781123161316,0.2948693633079529,0.2964819669723511,0.2957675457000732,0.2961378693580627,0.2986456751823425,0.2965773940086365,0.2971347272396087,0.2979784905910492,0.2960640490055084,0.2963202893733978,0.2964765429496765,0.2955825328826904,0.2960845828056335,0.2962913811206817,0.297202855348587,0.2973734140396118,0.2963671684265136,0.2956562340259552,0.2961090505123138,0.2997306883335113,0.2954737246036529,0.2955188453197479,0.2986056506633758,0.2961571514606476,0.2995993494987488,0.296417236328125],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2302941530942917,0.2394891679286956,0.2503184080123901,0.2556455731391907,0.253048300743103,0.2535789608955383,0.2549353539943695,0.2566771805286407,0.2623271644115448,0.2609411180019378,0.2578624784946441,0.2614805698394775,0.2605361342430115,0.2652340233325958,0.2619531750679016,0.270562082529068,0.2670970559120178,0.2664526104927063,0.266819030046463,0.2683889269828796,0.2680206894874573,0.2757416367530823,0.2774391770362854,0.2746606171131134,0.2770424485206604,0.271879106760025,0.2707585990428924,0.2712187170982361,0.2728039920330047,0.2749942243099212,0.2732555270195007,0.276515781879425,0.2748349606990814,0.2744706273078918,0.2774482667446136,0.2771708071231842,0.278818279504776,0.2794012129306793,0.2771688103675842,0.2806626260280609,0.2767289280891418,0.2752445638179779,0.2794993221759796,0.2787448167800903,0.2791335582733154,0.2845953106880188,0.285821795463562,0.2835574150085449,0.2810848653316498,0.2827566564083099,0.2799965143203735,0.2829867005348205,0.2818765938282013,0.2831662595272064,0.2812851965427398,0.2809430658817291,0.2845199406147003,0.2810761034488678,0.280548632144928,0.2843766808509826,0.2836973965167999,0.2816115319728851,0.2813279032707214,0.2831666767597198,0.289567083120346,0.2827740609645843,0.2853868007659912,0.2859958112239837,0.2849586009979248,0.2829121947288513,0.2878905236721039,0.2904602885246277,0.2833390831947326,0.2841251194477081,0.2823526859283447,0.286386489868164,0.2867838144302368,0.2879679501056671,0.289354145526886,0.287205308675766,0.2860118150711059,0.2881567776203155,0.2898057699203491,0.2845668792724609,0.2820063829421997,0.2879539728164673,0.2910474836826324,0.29256671667099,0.2911987900733948,0.2911952137947082,0.2891197204589844,0.2894909679889679,0.2945535480976105,0.292443186044693,0.2922341823577881,0.2958264946937561,0.2897793650627136,0.2953986227512359,0.2889650464057922,0.2916810512542724,0.2924517393112182,0.2911387085914612,0.2910221815109253,0.2896819710731506,0.2910731434822082,0.2926735877990722,0.2947866320610046,0.2912710309028625,0.2928700745105743,0.2902169823646545,0.2913528084754944,0.2931830883026123,0.288572609424591,0.2932479381561279,0.2927209436893463,0.2933314144611358,0.294957548379898,0.2944406569004059,0.292906254529953,0.2974542081356048,0.28949174284935,0.2940118312835693,0.2939378619194031,0.2899948358535766,0.2916503548622131,0.2933265566825866,0.2923474609851837,0.2926449179649353,0.2939247488975525,0.2955576777458191,0.2945278882980346,0.2925565838813782,0.2975679039955139,0.2975771427154541,0.2975721061229706,0.2964449226856231,0.2963431775569916,0.2957415282726288,0.294972151517868,0.2952609956264496,0.2951166331768036,0.295406699180603,0.2954263091087341,0.2938945293426513,0.2970178127288818,0.2952383458614349,0.2960261702537536,0.2939098477363586,0.2990855574607849,0.2983920276165008,0.2962434887886047,0.2976707518100738,0.2962033450603485,0.2950758635997772,0.2956030964851379,0.2977538108825683,0.29536834359169,0.2968058288097381,0.299165278673172,0.2938053607940674,0.2983893454074859,0.2968741953372955,0.2985494136810303,0.2971247434616089,0.3027064800262451,0.2975856065750122,0.2972559630870819,0.2974089086055755],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2302852720022201,0.2423893511295318,0.2480557113885879,0.2496711313724517,0.2483558505773544,0.2569639086723327,0.2565478086471557,0.2618249952793121,0.2595195472240448,0.2643540203571319,0.2681331634521484,0.2635236978530884,0.2708289623260498,0.2684795260429382,0.268822431564331,0.2737374007701874,0.2747245132923126,0.2706727385520935,0.2765767276287079,0.2689609229564667,0.2750284969806671,0.2725656926631927,0.2786419093608856,0.2721802890300751,0.2771309614181518,0.2776786684989929,0.2784741520881653,0.2768192887306213,0.2722735106945038,0.279404878616333,0.2738591730594635,0.2735618352890014,0.2760910093784332,0.282706618309021,0.2802526354789734,0.280755341053009,0.279806911945343,0.2803169190883636,0.2802790105342865,0.2823083400726318,0.2791097164154053,0.2799264788627624,0.2810145616531372,0.2830551564693451,0.2767517268657684,0.2817390263080597,0.2797431051731109,0.2812069058418274,0.2839132845401764,0.280527800321579,0.2841951847076416,0.2821594178676605,0.2839535772800445,0.2827078700065613,0.2871818840503692,0.2862685620784759,0.2831906080245971,0.2893101572990417,0.2836923003196716,0.2853714525699615,0.2832745611667633,0.2869344651699066,0.2909739315509796,0.287185788154602,0.2904500663280487,0.2907691895961761,0.2879318594932556,0.2846351265907287,0.2876160442829132,0.2900785803794861,0.2894342243671417,0.2902654111385345,0.2904077172279358,0.2896934151649475,0.2896896600723266,0.288019984960556,0.2897504866123199,0.2864451110363006,0.2828132212162018,0.2877678573131561,0.2854636907577514,0.2947789430618286,0.2900680601596832,0.2904808521270752,0.2902005910873413,0.2898910045623779,0.2883723378181457,0.2907931804656982,0.289756178855896,0.2877400815486908,0.2894744873046875,0.287464439868927,0.294312447309494,0.2916102409362793,0.2905359268188476,0.2923611402511596,0.2934006750583648,0.2902256548404693,0.2923925220966339,0.2913002967834472,0.2938213348388672,0.2950030863285064,0.2941963374614715,0.2952739894390106,0.2916943430900574,0.2959964573383331,0.292758584022522,0.2986407876014709,0.294997364282608,0.296364814043045,0.2930647730827331,0.2949731945991516,0.2958677113056183,0.2944487035274505,0.2928292155265808,0.2940362989902496,0.2987499535083771,0.2980126142501831,0.2952496111392975,0.2935928404331207,0.295001357793808,0.2969489395618438,0.2924657464027405,0.2973984479904175,0.2949175536632538,0.2935470938682556,0.2948426008224487,0.2992851138114929,0.2992587685585022,0.2984158098697662,0.2967890501022339,0.2971494197845459,0.2999038398265838,0.2980946600437164,0.2980411648750305,0.2972898185253143,0.2941733598709106,0.3000704646110534,0.2996682822704315,0.2965673208236694,0.2985780537128448,0.2985095381736755,0.2977069318294525,0.2959935069084167,0.3000862896442413,0.2987641990184784,0.2984014451503753,0.300053596496582,0.2969347536563873,0.3001846671104431,0.2977829575538635,0.2977830469608307,0.2958649396896362,0.3001670837402344,0.3014028370380401,0.3023911416530609,0.3001483678817749,0.3008536994457245,0.3015736639499664,0.2965351939201355,0.2985740303993225,0.2997780740261078,0.2985914647579193,0.3003082871437073,0.2993003129959106,0.3037322759628296,0.3000002801418304,0.2982830703258514],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2302941530942917,0.2425713837146759,0.2531454265117645,0.2537876963615417,0.2551585733890533,0.2630817592144012,0.2590664327144623,0.2628366947174072,0.2701342403888702,0.2698567509651184,0.271359920501709,0.2727656662464142,0.2754974663257599,0.2764639556407928,0.2763088345527649,0.2768554091453552,0.2772888541221618,0.2821019887924194,0.2798008024692535,0.2795673012733459,0.2807479798793793,0.2834879159927368,0.2836300134658813,0.2781426012516022,0.2808595299720764,0.2884292304515838,0.2846161127090454,0.2882022559642792,0.2798523306846618,0.2833814024925232,0.2899111211299896,0.2866390347480774,0.2880376279354095,0.2878502905368805,0.2910982966423034,0.2891170382499695,0.2878516912460327,0.2887516915798187,0.2885439991950989,0.2882349789142608,0.2928331792354584,0.2946663200855255,0.2949031591415405,0.2920069396495819,0.2924359738826751,0.290930837392807,0.293034166097641,0.2966321110725403,0.2919987440109253,0.2924461662769317,0.2912311255931854,0.2928816676139831,0.2924420535564422,0.2932154536247253,0.2947424054145813,0.2945475578308105,0.2935222089290619,0.294662207365036,0.295950710773468,0.2920311093330383,0.2915212213993072,0.2947100698947906,0.2916833460330963,0.2941240966320038,0.2964881658554077,0.2978979051113128,0.2917112410068512,0.2940752804279327,0.2992609441280365,0.2978897094726562,0.2970111072063446,0.2954381704330444,0.2933490872383117,0.299363225698471,0.2922609746456146,0.2961671948432922,0.2965226173400879,0.2974887192249298,0.2948525846004486,0.2986953854560852,0.2982926368713379,0.3001065552234649,0.2970279455184936,0.2948827743530273,0.2972462773323059,0.2986973524093628,0.302126407623291,0.2985441088676452,0.3023014366626739,0.2973113656044006,0.2982563078403473,0.2950666844844818,0.2980487942695617,0.3008447885513305,0.2989610433578491,0.301068365573883,0.3022592663764953,0.299753189086914,0.2994685769081116,0.2996334731578827,0.3049249649047851,0.3035067319869995,0.3010409772396087,0.299841970205307,0.2963119149208069,0.2975607812404632,0.3001983761787414,0.3019936382770538,0.2994698882102966,0.3028704822063446,0.3017867803573608,0.302071064710617,0.3033528625965118,0.3001683056354522,0.30193692445755,0.3014234602451324,0.3008273243904114,0.306147426366806,0.2973030209541321,0.3003686368465423,0.3036256730556488,0.3054963648319244,0.3041203916072845,0.299890786409378,0.3041128814220428,0.3024519681930542,0.3039655685424804,0.3017177283763885,0.3039222657680511,0.306195467710495,0.3029496073722839,0.3023946583271026,0.3038596510887146,0.3035906255245209,0.3072469830513,0.305474191904068,0.3046322464942932,0.3048957586288452,0.3062893450260162,0.3037531077861786,0.3028694093227386,0.3044112920761108,0.3069455027580261,0.3019899427890777,0.3069635331630707,0.305140882730484,0.3064731061458587,0.3043522238731384,0.3063851594924927,0.3055339753627777,0.3054327368736267,0.3066801428794861,0.304499089717865,0.3043224513530731,0.3086932897567749,0.3066151142120361,0.3063015937805176,0.3042306900024414,0.3038672804832458,0.3038462996482849,0.3068911433219909,0.3072203993797302,0.3089776933193207,0.3058432340621948,0.3073770105838775,0.3080585896968841,0.3049748837947845,0.3095029592514038],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2302941530942917,0.2430401891469955,0.2501300871372223,0.2531542181968689,0.2523926198482513,0.2592448592185974,0.2574552297592163,0.2620232403278351,0.2590152025222778,0.2709018290042877,0.2668121755123138,0.2678887844085693,0.2660391926765442,0.2678857147693634,0.2694567739963531,0.2697669267654419,0.2674907445907593,0.2735385298728943,0.2718805372714996,0.2689968049526214,0.2740245163440704,0.2700002789497375,0.2726375460624695,0.2759962379932403,0.2779688239097595,0.2753633260726928,0.2783536314964294,0.2737064957618713,0.2791479527950287,0.2809297442436218,0.2782776653766632,0.278923362493515,0.2775233387947082,0.2794313132762909,0.2787668704986572,0.278833657503128,0.2841731011867523,0.2791468501091003,0.2789521217346191,0.2810447812080383,0.2848342657089233,0.2855708599090576,0.2871818244457245,0.2828938663005829,0.2835574448108673,0.284085601568222,0.286235898733139,0.2841546833515167,0.2847932279109955,0.2820126414299011,0.2835133075714111,0.2899715900421142,0.2850905358791351,0.2865831553936004,0.2848269939422607,0.2836639583110809,0.2842272818088531,0.2851946651935577,0.285736620426178,0.2875486016273498,0.2864581644535064,0.2838688790798187,0.2846946120262146,0.2860409915447235,0.2877615094184875,0.285281240940094,0.2882268130779266,0.2871605157852173,0.2876625955104828,0.2861424088478088,0.2848456799983978,0.2898689806461334,0.2885682582855224,0.2869403064250946,0.2863434255123138,0.2862505316734314,0.2896080017089844,0.2911330461502075,0.2936855852603912,0.2861319780349731,0.294349730014801,0.2926821410655975,0.2893033921718597,0.2921136915683746,0.2925426065921783,0.2931935787200928,0.2924295663833618,0.2945552468299866,0.2909598648548126,0.2918527126312256,0.291136771440506,0.2911294102668762,0.2927017211914062,0.2918365001678467,0.2908338010311126,0.2924268841743469,0.2950882017612457,0.2957153618335724,0.2958950400352478,0.2959841191768646,0.2956998348236084,0.2948305010795593,0.2948802709579468,0.2980543375015259,0.2918694615364074,0.2966636717319488,0.294614166021347,0.3001791834831238,0.2917566895484924,0.2952867448329925,0.2908158302307129,0.2925814986228943,0.2956191599369049,0.2975310385227203,0.2948774695396423,0.2982760071754455,0.2980831265449524,0.2983511686325073,0.299521267414093,0.2953948974609375,0.2988253235816955,0.2984384000301361,0.2952634990215301,0.3001562058925628,0.2967326641082763,0.2967140078544616,0.2967191040515899,0.298566997051239,0.2994621098041534,0.2993804812431335,0.2980446815490722,0.2990546822547912,0.3000186085700989,0.2978760302066803,0.2970815300941467,0.299174040555954,0.3012072145938873,0.2990481257438659,0.2981095612049103,0.2942902147769928,0.300515353679657,0.2975022792816162,0.2971253097057342,0.300593227148056,0.2985393702983856,0.2991617918014526,0.3011792600154876,0.3017111718654632,0.3028576672077179,0.2998140454292297,0.298651784658432,0.2986940145492553,0.3035962283611297,0.2973863482475281,0.3004998564720154,0.3013047277927398,0.3005253970623016,0.3018082678318023,0.3016049563884735,0.2999689280986786,0.3007806837558746,0.2995651960372925,0.2991808652877807,0.3001604080200195,0.3014689683914184,0.3005554676055908,0.3028019964694977,0.2996771335601806],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2302941530942917,0.2431725859642028,0.2491973936557769,0.2513575553894043,0.2576150596141815,0.2597958743572235,0.2623288631439209,0.2675388157367706,0.2641738355159759,0.2658170461654663,0.2673129141330719,0.2696804404258728,0.2681093215942383,0.2691816389560699,0.2686139047145843,0.2678294479846954,0.2713833749294281,0.2762300074100494,0.2732318937778473,0.2729426920413971,0.2753361165523529,0.2753785252571106,0.280246376991272,0.2739307880401611,0.2789853811264038,0.2787064015865326,0.2796043753623962,0.2807347178459167,0.2822284698486328,0.2793554663658142,0.282518059015274,0.2813326418399811,0.2811921238899231,0.2786293029785156,0.2810405492782593,0.2832583487033844,0.2827111184597015,0.284210741519928,0.2834082543849945,0.2825364172458648,0.2892339527606964,0.2851271331310272,0.2830458581447601,0.2917155623435974,0.2880749404430389,0.2852968573570251,0.2838859260082245,0.2858217358589172,0.2935910522937774,0.2913962304592132,0.2856296002864837,0.2863002717494964,0.2919958531856537,0.291260153055191,0.2888869345188141,0.2917166948318481,0.2928083837032318,0.291592001914978,0.2900373041629791,0.290350079536438,0.2896054983139038,0.2898766994476318,0.2912257313728332,0.2880926728248596,0.2868898510932922,0.2884824573993683,0.284532368183136,0.2907828688621521,0.2900049388408661,0.2904351949691772,0.2923563718795776,0.2881825268268585,0.2893885970115661,0.289294958114624,0.2924051880836487,0.2906378805637359,0.2903206944465637,0.293033242225647,0.2953883111476898,0.2920814156532287,0.289974570274353,0.2927417457103729,0.2930914163589477,0.2902568876743316,0.2877192497253418,0.2917113900184631,0.2915734350681305,0.2927587330341339,0.2900062203407287,0.2924955189228058,0.2922729253768921,0.2898525893688202,0.2919672429561615,0.2957657277584076,0.2943678796291351,0.2920540273189544,0.2966239154338836,0.2951430380344391,0.295727789402008,0.2966287434101105,0.2920288145542145,0.2970482409000397,0.2979781031608581,0.2971825301647186,0.2937128841876983,0.2962508499622345,0.294025719165802,0.2964968085289001,0.297142744064331,0.2964718341827392,0.2968791127204895,0.2926413416862488,0.2983491122722626,0.2954694032669067,0.2939556539058685,0.2922001183032989,0.2973969578742981,0.3004654049873352,0.297024518251419,0.2975258827209472,0.2950786352157593,0.2990403771400451,0.2983780205249786,0.2971011400222778,0.3002420663833618,0.2965699136257171,0.2974638342857361,0.2963720262050628,0.2978213131427765,0.298618882894516,0.2997609078884125,0.3001005351543426,0.29981130361557,0.300857812166214,0.2990098893642425,0.2975635826587677,0.3019692003726959,0.2997107207775116,0.2983364164829254,0.3031535148620605,0.3006802499294281,0.3008413314819336,0.3019627630710602,0.3016014099121094,0.3020424544811249,0.3014797270298004,0.3027486205101013,0.3009576499462127,0.3012239933013916,0.3003258109092712,0.3007867634296417,0.3023083806037903,0.3037638366222381,0.3023600280284881,0.3018107116222381,0.3005677163600921,0.3035200834274292,0.2990438342094421,0.3007476031780243,0.3002508282661438,0.2997041940689087,0.2986632585525512,0.2988404631614685,0.3013385236263275,0.3014250099658966,0.2997684478759765,0.301797479391098,0.3019861876964569],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2302852720022201,0.2423906475305557,0.2502092123031616,0.2505890429019928,0.2529841065406799,0.2554414272308349,0.2611663043498993,0.2613391578197479,0.2650775909423828,0.2682546079158783,0.2657448053359985,0.2674783170223236,0.2659584283828735,0.2683353722095489,0.2702054679393768,0.2628171741962433,0.2723247408866882,0.2712653875350952,0.2729564607143402,0.2731359601020813,0.2764972746372223,0.2786749303340912,0.2764124870300293,0.2775228917598724,0.2761183679103851,0.279299795627594,0.2813723087310791,0.2789660692214966,0.2782142758369446,0.2796961963176727,0.2800929844379425,0.2787646949291229,0.2777774930000305,0.2819646894931793,0.2847686111927032,0.2836755812168121,0.2790846824645996,0.282106876373291,0.2828855216503143,0.2784262895584106,0.2819558084011078,0.2849562168121338,0.2804000675678253,0.2828144133090973,0.2818105816841125,0.2849446535110473,0.2875114977359772,0.2840888798236847,0.2846514582633972,0.2834798097610473,0.287195473909378,0.2857663631439209,0.2875427007675171,0.2870612144470215,0.2880852818489074,0.2871463596820831,0.2877984344959259,0.2851130962371826,0.2902863621711731,0.2881656587123871,0.2936716973781585,0.2918212711811065,0.2906697690486908,0.2896789312362671,0.2869586646556854,0.2882633507251739,0.2910521924495697,0.2885527908802032,0.2891169488430023,0.2913079857826233,0.2881745100021362,0.2896412312984466,0.2872377932071686,0.2869805991649627,0.2921048402786255,0.2906677424907684,0.292618066072464,0.2909645140171051,0.2928961217403412,0.2893120050430298,0.2929781377315521,0.2915225028991699,0.2911928296089172,0.297902762889862,0.2904660403728485,0.2956863045692444,0.2981660366058349,0.292925089597702,0.290527194738388,0.2947019636631012,0.2895756363868713,0.2916719317436218,0.2926284074783325,0.2949083745479584,0.2942789793014526,0.2993685007095337,0.297613114118576,0.2969610691070556,0.2962918281555176,0.2979336977005005,0.2956188917160034,0.2927440702915191,0.2944952249526977,0.2994117438793182,0.2967657148838043,0.3014810681343078,0.2971532046794891,0.2984380424022674,0.301511287689209,0.3001125752925873,0.30377858877182,0.2953903675079345,0.2993964254856109,0.2970738708972931,0.2972185015678406,0.2976145446300506,0.2956169545650482,0.2981896996498108,0.2994268834590912,0.3015474677085876,0.3008508086204529,0.2983271181583404,0.301815927028656,0.2991032898426056,0.2992735207080841,0.2983767688274383,0.300561249256134,0.2975876331329345,0.3007292151451111,0.3046475946903229,0.303261250257492,0.3013674020767212,0.2963277697563171,0.3028241097927093,0.2996001243591308,0.3011476099491119,0.3009052276611328,0.2999244928359985,0.3012984991073608,0.2981511652469635,0.30339115858078,0.3028028905391693,0.3014983832836151,0.3077113032341003,0.3054217100143432,0.3055659234523773,0.303210437297821,0.3052520453929901,0.3068914115428924,0.3077176511287689,0.3058249056339264,0.3049653172492981,0.3068315684795379,0.3056458830833435,0.3053306937217712,0.3048221468925476,0.3084690272808075,0.3027506172657013,0.3033172786235809,0.3082787692546844,0.3066763579845428,0.3061989247798919,0.3057523965835571,0.3036724030971527,0.3064056038856506,0.3041214942932129,0.3058549165725708,0.3079395294189453],"label":"FineWeb URL dedup"}},"mmlu/acc_norm":{"big-run-refinedweb":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501466572284698,0.2528519630432129,0.2616856694221496,0.2665999829769134,0.2683407664299011,0.2742894291877746,0.2762066125869751,0.2807516455650329,0.2767378389835357,0.2807380557060241,0.2788906991481781,0.2844051718711853,0.2856102883815765,0.2883394360542297,0.2890409529209137,0.2894668281078338,0.2883355319499969,0.2872501015663147,0.291619062423706,0.2900333702564239,0.2962473034858703,0.2962896525859833,0.297355443239212,0.2932226359844208,0.2886744439601898,0.29665008187294,0.2976542115211487,0.2991503179073334,0.3004479110240936,0.3044549524784088,0.2976194322109222,0.3014707863330841,0.3048252463340759,0.3039425611495971,0.303354948759079,0.3027459383010864,0.2999922931194305,0.3050121665000915,0.2998814284801483,0.2978588044643402,0.3041949570178985,0.3010904192924499,0.3022017180919647,0.2997751235961914,0.3015910983085632,0.3096485137939453,0.3012076020240783,0.3065535724163055,0.3042872548103332,0.3104783594608307,0.2997980415821075,0.3051296770572662,0.303458571434021,0.3088337182998657,0.3145398199558258,0.3032208085060119,0.310806930065155,0.3075874149799347,0.3101692199707031,0.310107946395874,0.3066047430038452,0.3109066784381866,0.3081336915493011,0.3084586262702942,0.3086149394512176,0.3085348606109619,0.3136637806892395,0.3110873103141784,0.31076380610466,0.3084572553634643,0.3133681714534759,0.3125792145729065,0.3124453127384186,0.3097185790538788,0.3106793165206909,0.3089564740657806,0.3111244142055511,0.3123694658279419,0.3144859969615936,0.3135123550891876,0.311982125043869,0.3142133951187134,0.3122903704643249,0.3147654831409454,0.3078767359256744,0.314947634935379,0.3171303570270538,0.3129573762416839,0.3154936134815216,0.3158208429813385,0.3153132200241089,0.3141326904296875,0.3163397014141083,0.3166318237781524,0.3168410360813141,0.3198235332965851,0.3201336860656738,0.3212967813014984,0.3191385567188263,0.3178017139434814,0.3192791938781738,0.323061466217041,0.320336639881134,0.3165886104106903,0.3206393420696258,0.3167395293712616,0.3135207295417785,0.315539002418518,0.3191742599010467,0.321073055267334,0.3222262561321258,0.3193058371543884,0.3213480710983276,0.3198905289173126,0.3219239711761474,0.3211614489555359,0.318855881690979,0.3177095353603363,0.324197381734848,0.3208906352519989,0.3264936804771423,0.3245965242385864,0.3231639564037323,0.3221887946128845,0.3277338445186615,0.3227696120738983,0.3263820111751556,0.3258577883243561,0.3264622390270233,0.3222362995147705,0.3286814987659454,0.3235024213790893,0.32446950674057,0.3311836123466491,0.328130304813385,0.3271634578704834,0.3250012993812561,0.3309800624847412,0.3274554014205932,0.3273015916347503,0.3261759579181671,0.32697594165802,0.3303172886371612,0.3282814025878906,0.3289586305618286,0.3260826468467712,0.3258011937141418,0.3297208249568939,0.3254813551902771,0.3287739753723144,0.3287097811698913,0.3275279700756073,0.3293041586875915,0.3314100801944732,0.3287808299064636,0.3251930773258209,0.3288172781467438,0.3265027701854706,0.3275215625762939,0.3290774822235107,0.3261331617832184,0.3299777805805206,0.331955999135971,0.3305029273033142,0.3274719417095184,0.3235560953617096,0.3269940316677093,0.3323083519935608],"label":"RefinedWeb"},"big-run-sampled_cross_minhash_dump":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501466572284698,0.2544876635074615,0.2636238932609558,0.2635596990585327,0.2753011584281921,0.276723712682724,0.2776635885238647,0.2790510952472687,0.2780559957027435,0.2842589914798736,0.2803126275539398,0.2806592285633087,0.2843835055828094,0.2832211852073669,0.2839561700820923,0.2892738282680511,0.2865834534168243,0.286511093378067,0.2889319062232971,0.2891861796379089,0.290885180234909,0.2850055992603302,0.2917909622192383,0.2899129688739776,0.2898374497890472,0.2910006940364837,0.2872054278850555,0.2907578349113464,0.2926150560379028,0.2880342006683349,0.2901965379714966,0.2952837347984314,0.2859585881233215,0.2937746942043304,0.2954647243022918,0.2966125607490539,0.2966502606868744,0.297608733177185,0.2967801690101623,0.2954789400100708,0.291534274816513,0.2982968688011169,0.2948050796985626,0.2971893846988678,0.2985599935054779,0.3000908493995666,0.3015654385089874,0.3026306331157684,0.2969894111156463,0.295008510351181,0.3051140904426574,0.3011809289455414,0.301148384809494,0.30084028840065,0.3000010251998901,0.2981067597866058,0.2965763211250305,0.2994557917118072,0.299673318862915,0.302642285823822,0.2997134327888489,0.3017182052135467,0.2968311905860901,0.3011281490325928,0.3021756708621979,0.3043635487556457,0.2973764538764953,0.3025802671909332,0.2972780764102936,0.3005335927009582,0.3014411330223083,0.3007441163063049,0.298946738243103,0.2994847297668457,0.3046847283840179,0.3010449707508087,0.3046635091304779,0.302239179611206,0.306140124797821,0.298642635345459,0.3050216436386108,0.3010282516479492,0.304199755191803,0.3069856762886047,0.3023611009120941,0.3038834035396576,0.3043374717235565,0.3029325902462005,0.3067526221275329,0.3038187325000763,0.3058615326881408,0.3053784370422363,0.3040686249732971,0.3057010769844055,0.3075809180736542,0.3058017790317535,0.3063019514083862,0.3042554259300232,0.3066894114017486,0.3059817552566528,0.31159707903862,0.3104826211929321,0.3057895004749298,0.3096732795238495,0.308764636516571,0.3081749975681305,0.3074744343757629,0.3111171126365661,0.3071461021900177,0.3081350028514862,0.30860435962677,0.3113418519496918,0.312028169631958,0.3068177998065948,0.3104725778102875,0.3109223246574402,0.3129202127456665,0.3100030422210693,0.3143675029277801,0.3113570511341095,0.3117307424545288,0.3134656250476837,0.3128443658351898,0.3097193837165832,0.3132749795913696,0.3155365586280823,0.3150430917739868,0.3125199973583221,0.3146211802959442,0.3124625384807586,0.3148326575756073,0.3140344321727752,0.3188642859458923,0.3200671076774597,0.3202098309993744,0.3182824552059173,0.3144026398658752,0.3155149817466736,0.3157094419002533,0.3168105185031891,0.3165365159511566,0.3145294785499573,0.3134921789169311,0.3159840404987335,0.3180464506149292,0.3156932294368744,0.3171059191226959,0.3154203295707702,0.3152349889278412,0.3141801059246063,0.3131091594696045,0.3181729018688202,0.3161401152610779,0.3146364092826843,0.3182015419006347,0.3157785534858703,0.3172916769981384,0.3164207339286804,0.3199963867664337,0.3189407289028168,0.3206113576889038,0.3212437927722931,0.3190592527389526,0.3212800323963165,0.3199907541275024,0.3186413943767547,0.3241027593612671,0.3206748366355896],"label":"FineWeb full MinHash"},"big-run-sampled_full_filtered_no_dedup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501466572284698,0.2516599297523498,0.2610189318656921,0.2666046619415283,0.2667981088161468,0.2667821645736694,0.2708088159561157,0.2738403379917145,0.2726235687732696,0.2762763500213623,0.2768311202526092,0.2809228301048279,0.2836140990257263,0.2822815179824829,0.2797218561172485,0.286342591047287,0.2855269610881805,0.2847287058830261,0.2888180613517761,0.286526083946228,0.2865165770053863,0.294582188129425,0.2925947606563568,0.2947863042354584,0.2892930805683136,0.2903610467910766,0.288201242685318,0.2873396277427673,0.2916238009929657,0.2908017039299011,0.2907920777797699,0.2952797412872314,0.2941452264785766,0.2921333611011505,0.2925891280174255,0.2968584895133972,0.2980035543441772,0.2964116632938385,0.2962304651737213,0.2950254380702972,0.2977516651153564,0.2944138348102569,0.3003402054309845,0.2976303696632385,0.3013098239898681,0.302829384803772,0.3018766045570373,0.305361807346344,0.2971298694610595,0.3014816343784332,0.3019805550575256,0.3037064969539642,0.2970167994499206,0.2995208501815796,0.2970106601715088,0.2990955114364624,0.3027818500995636,0.3048534691333771,0.2993872463703155,0.2986327707767486,0.3015393316745758,0.3003426790237427,0.3003274798393249,0.3017795085906982,0.3019182682037353,0.3015450537204742,0.3046211004257202,0.3031167984008789,0.3020436763763428,0.3011128306388855,0.3029948472976684,0.3045558631420135,0.301642894744873,0.3029441833496094,0.3035804331302643,0.3004390001296997,0.3021787703037262,0.306041270494461,0.3064048886299133,0.3087956011295318,0.3070018291473388,0.3065581619739532,0.3093871772289276,0.3060930073261261,0.3033313155174255,0.3072777390480041,0.306413859128952,0.3104493916034698,0.3056999444961548,0.3077532052993774,0.309231549501419,0.3070645034313202,0.3117790520191192,0.3114112913608551,0.312661737203598,0.3181777000427246,0.3117201030254364,0.3099702894687652,0.3074746131896972,0.3064963519573211,0.3105958700180053,0.3111456036567688,0.3084964454174042,0.3087405860424042,0.3121673166751861,0.3121528625488281,0.3100416660308838,0.3142979145050049,0.3129935264587402,0.3112611472606659,0.3119436800479889,0.3154115974903106,0.3091593086719513,0.3103814721107483,0.3130497634410858,0.3133455514907837,0.3152708411216736,0.3137963414192199,0.3099324703216553,0.3164172768592834,0.3133907914161682,0.3128255009651184,0.3134104907512665,0.3106969892978668,0.3130004107952118,0.3131391704082489,0.3130116462707519,0.3143952488899231,0.3143975436687469,0.3143710494041443,0.3163396418094635,0.3166862726211548,0.3184126019477844,0.3178988993167877,0.317479133605957,0.3184944093227386,0.316694974899292,0.3176258206367492,0.3182629346847534,0.3200214207172394,0.3181648552417755,0.320680022239685,0.3178716897964477,0.3182425796985626,0.3182984292507171,0.3158398568630218,0.3152642548084259,0.3132680356502533,0.3178914785385132,0.3156660795211792,0.3161703050136566,0.3176451921463012,0.3173815906047821,0.3194171786308288,0.3193057179450989,0.3172560334205627,0.317656546831131,0.3155770003795624,0.3199106156826019,0.3170182108879089,0.3156754970550537,0.3180731236934662,0.3205638229846954,0.3175432682037353,0.3184471428394317,0.3192788958549499,0.3197042346000671,0.3177168369293213],"label":"FineWeb filtered only"},"big-run-sampled_full_imh_linededup":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501466572284698,0.253999799489975,0.2583010494709015,0.269153743982315,0.2707667946815491,0.2717087566852569,0.2736553251743316,0.2758435606956482,0.2778100669384002,0.2814604938030243,0.2868002951145172,0.2827531099319458,0.2838069796562195,0.2848111987113952,0.2881324887275696,0.2899852097034454,0.288834810256958,0.2855388522148132,0.2903755009174347,0.2859087288379669,0.286707192659378,0.2928432524204254,0.2948739528656006,0.2832534611225128,0.2934349179267883,0.2905211448669433,0.295222669839859,0.29123255610466,0.2889701426029205,0.2944531738758087,0.2919276058673858,0.2897505760192871,0.2937909960746765,0.2939953207969665,0.2948339879512787,0.2973888516426086,0.2988723516464233,0.2959459722042084,0.2978571951389313,0.2987410128116607,0.2943701148033142,0.3009988367557525,0.2991230487823486,0.2992964088916778,0.2981067895889282,0.3001026511192322,0.2982764840126037,0.2994687259197235,0.3011341691017151,0.3028860092163086,0.3003491461277008,0.2989377677440643,0.3023573756217956,0.3063880503177643,0.3044538795948028,0.3035243451595306,0.3003852665424347,0.302204430103302,0.2988624274730682,0.3033603131771087,0.2980654537677765,0.3027355670928955,0.3041884303092956,0.3046613335609436,0.3049206435680389,0.3040647804737091,0.3053110539913177,0.3015013635158539,0.3050790131092071,0.3055492341518402,0.3106111586093902,0.3116686344146728,0.304739236831665,0.3043427765369415,0.304662674665451,0.3055848479270935,0.3095492422580719,0.3075328767299652,0.3046663999557495,0.3070131838321686,0.3052798807621002,0.310669481754303,0.3065283000469208,0.3076212704181671,0.3061128854751587,0.30768883228302,0.3123957514762878,0.313648521900177,0.3068180084228515,0.3100768029689789,0.3143931329250335,0.3057041764259338,0.3121876120567322,0.3097154200077057,0.3098792433738708,0.3116051256656647,0.310238629579544,0.3088849484920501,0.3070208132266998,0.3095521926879883,0.3128596842288971,0.315104991197586,0.3098082840442657,0.3137387633323669,0.3135212957859039,0.3119608759880066,0.3123177587985992,0.3123584687709808,0.3123020827770233,0.3156505823135376,0.3147969245910644,0.3167971968650818,0.3161757290363312,0.3147077262401581,0.3128670156002044,0.3146953582763672,0.3170470297336578,0.3193329870700836,0.3174440562725067,0.3133153319358825,0.3175253570079803,0.316369891166687,0.3154952228069305,0.3167658150196075,0.3139858841896057,0.3135108947753906,0.3178616762161255,0.3165631294250488,0.3164533972740173,0.3176324367523193,0.317125141620636,0.3161855041980743,0.3160880208015442,0.3186675608158111,0.3159597814083099,0.3184659481048584,0.3191149234771728,0.3208386898040771,0.3176317512989044,0.3166281580924988,0.3184658586978912,0.3182388842105865,0.3204719126224518,0.3183542490005493,0.3210960924625397,0.3198772072792053,0.3213189542293548,0.3197827935218811,0.3216342031955719,0.3246194422245025,0.3220229744911194,0.3178151845932007,0.3214964270591736,0.3223589956760406,0.3244864344596863,0.3241894841194153,0.3217694163322449,0.3197280764579773,0.3211534321308136,0.3182283639907837,0.320689857006073,0.3222837746143341,0.3229076564311981,0.3252326548099518,0.322723776102066,0.3235912024974823,0.3184932470321655,0.3200807273387909],"label":"FineWeb line dedup"},"big-run-sampled_full_ind_minhash":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501466572284698,0.2558934390544891,0.2618628144264221,0.2683217823505401,0.2699837982654571,0.2738722860813141,0.2744417488574981,0.2740873992443084,0.2807216048240661,0.2820421457290649,0.2891400754451751,0.2879075407981872,0.2881667613983154,0.2892490327358246,0.2935869693756103,0.2870290875434875,0.2911452651023865,0.2949125170707702,0.2916406095027923,0.2981449663639068,0.2953989207744598,0.2946988642215729,0.297021746635437,0.3001497685909271,0.3010218441486358,0.2977036237716675,0.2992585003376007,0.2986803948879242,0.2994338274002075,0.2989781498908996,0.3041955828666687,0.3030496537685394,0.303806334733963,0.3036351203918457,0.3058845102787018,0.300450712442398,0.3025284707546234,0.3072526752948761,0.3039065897464752,0.3073755502700805,0.3070493042469024,0.3083153367042541,0.3123056292533874,0.307761400938034,0.3053378164768219,0.3116358816623688,0.3080427348613739,0.308482676744461,0.307318776845932,0.3083004653453827,0.3089516758918762,0.3088736236095428,0.3077724277973175,0.3126304149627685,0.3101697862148285,0.3159398734569549,0.314792275428772,0.3103811144828796,0.3111368715763092,0.3129658997058868,0.311605304479599,0.3118223249912262,0.3133279979228973,0.3146496713161468,0.3195074200630188,0.3142614662647247,0.3125102519989013,0.3115333616733551,0.3183117806911468,0.3168580532073974,0.3187012672424316,0.3179306983947754,0.3157722651958465,0.3214826583862304,0.3145081698894501,0.3172421753406524,0.3151432573795318,0.3181649446487427,0.3180212080478668,0.3171605765819549,0.3212067782878876,0.3180184066295624,0.3209905624389648,0.319052129983902,0.3212707936763763,0.3196887373924255,0.3188316226005554,0.3164899051189422,0.3241994678974151,0.3179469406604767,0.3214083909988403,0.3206575512886047,0.3263285160064697,0.3219505250453949,0.3181525468826294,0.3219776451587677,0.3259726762771606,0.3197665512561798,0.3236161768436432,0.3177970349788666,0.3258080780506134,0.3208407461643219,0.3251138925552368,0.3242645859718323,0.3229723274707794,0.3227455914020538,0.3206316232681274,0.3256695866584778,0.3241210877895355,0.3224890530109405,0.3263737261295318,0.3214233517646789,0.3240345120429992,0.3222567737102508,0.3242291808128357,0.3257078528404236,0.3278365731239319,0.3277338743209839,0.3253948092460632,0.3232105076313019,0.3267974853515625,0.3263654410839081,0.3262891769409179,0.3238334357738495,0.3294911682605743,0.3261866867542267,0.3243315815925598,0.3250119090080261,0.326727420091629,0.3268802464008331,0.3269768059253692,0.3257980346679687,0.3280686736106872,0.3274897634983063,0.3282252252101898,0.3272863030433655,0.328346699476242,0.325562834739685,0.3301684856414795,0.3284023404121399,0.3268299400806427,0.3286610245704651,0.3291078805923462,0.324972927570343,0.3314772248268127,0.3278062343597412,0.326839417219162,0.3277239501476288,0.330414742231369,0.3271744549274444,0.3279334008693695,0.3288575112819671,0.3285425007343292,0.3282454907894134,0.3296376466751098,0.3305942714214325,0.3276287615299225,0.3292438983917236,0.329515129327774,0.3281475007534027,0.3282177448272705,0.3333999514579773,0.3302631080150604,0.330238401889801,0.3323166668415069,0.3313035368919372,0.32961106300354,0.3321967124938965],"label":"FineWeb independent MinHash"},"big-run-sampled_line_dedup_3lines2":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501466572284698,0.2519457042217254,0.2616576254367828,0.2658758163452148,0.2679929733276367,0.2748787999153137,0.2722893059253692,0.2727676928043365,0.2729955911636352,0.2822930216789245,0.2800237536430359,0.2829027771949768,0.2829135060310364,0.2898730635643005,0.2846636474132538,0.2839370965957641,0.2861545979976654,0.2896808981895447,0.2867587506771087,0.2898013889789581,0.294308990240097,0.2903220653533935,0.2936711013317108,0.2989178001880646,0.2917765974998474,0.2910472750663757,0.2990753650665283,0.2938545048236847,0.295077919960022,0.2974505126476288,0.2954602241516113,0.2991233468055725,0.2987752854824066,0.2968650162220001,0.2968560755252838,0.293784499168396,0.3008463978767395,0.2980752885341644,0.2968375384807586,0.2989378273487091,0.3031772673130035,0.2982144057750702,0.3072997033596039,0.3009755611419678,0.3018175363540649,0.2972880899906158,0.3021102547645569,0.2980607748031616,0.3018033504486084,0.3023277521133423,0.300980657339096,0.3057446777820587,0.3020549416542053,0.3060078024864197,0.3068509101867676,0.3020707070827484,0.3008501827716827,0.29716557264328,0.302139401435852,0.3058683276176452,0.3006373047828674,0.3022995293140411,0.301407903432846,0.3064575493335724,0.303903192281723,0.3047733604907989,0.3033999502658844,0.3063433170318603,0.303598016500473,0.3049065470695495,0.3019661605358124,0.3097213208675384,0.3073177337646484,0.3025659918785095,0.3060482144355774,0.3043042421340942,0.3042346537113189,0.3050568997859955,0.3085763156414032,0.3084185421466827,0.3137410581111908,0.3108421564102173,0.3040379583835602,0.3115585446357727,0.3095895648002624,0.3092672228813171,0.3157180249691009,0.3095114827156067,0.3092750906944275,0.312365710735321,0.3091018795967102,0.305467814207077,0.3066084682941437,0.3131795823574066,0.3122726380825043,0.3114704191684723,0.3103253245353699,0.3097927272319793,0.3119098246097564,0.3089095056056976,0.3157062232494354,0.3098137676715851,0.3152211308479309,0.3178564608097076,0.3106072545051574,0.3152905702590942,0.3110293745994568,0.3181415498256683,0.3124554455280304,0.3141775727272033,0.3106608688831329,0.3153694272041321,0.3164840936660766,0.3161872029304504,0.3145796358585357,0.3129156231880188,0.3179356455802917,0.3162539005279541,0.3172806203365326,0.3169152438640594,0.315283328294754,0.3183337450027466,0.3184880316257477,0.3185418248176574,0.3173484802246094,0.3167769014835357,0.3173246681690216,0.3174279034137726,0.3163758516311645,0.3178513050079345,0.3180612027645111,0.3173169791698456,0.3186269700527191,0.3139888346195221,0.3200428187847137,0.3192640244960785,0.3197024464607239,0.3211536407470703,0.3195748925209045,0.3156979978084564,0.3221191167831421,0.3171336948871612,0.3193728923797607,0.3215304613113403,0.3195070922374725,0.3209142386913299,0.3222731053829193,0.323394238948822,0.3211849927902221,0.3216917812824249,0.3207966089248657,0.31895911693573,0.3225454092025757,0.3228538036346435,0.3228538334369659,0.3240528106689453,0.3232811093330383,0.3257603347301483,0.3250167369842529,0.3232788741588592,0.3213972151279449,0.3212160468101501,0.3239104747772217,0.322483479976654,0.3179150223731994,0.3196662366390228,0.3223597407341003,0.3219237923622131],"label":"FineWeb 3-line dedup"},"big-run-sampled_line_dedup_min_words":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501466572284698,0.2545117735862732,0.2621592879295349,0.2663872838020324,0.2735494375228882,0.2750547230243683,0.2745842039585113,0.2804706394672394,0.2774804532527923,0.2806868255138397,0.2805372774600982,0.2818433940410614,0.2860418856143951,0.2857778966426849,0.2832511961460113,0.2857283651828766,0.2871247231960296,0.2976761162281036,0.291380375623703,0.2948584854602813,0.2915708124637604,0.2921579778194427,0.2946071922779083,0.293646365404129,0.2965326607227325,0.2922790348529815,0.2949602603912353,0.2975448966026306,0.2989871203899383,0.2986166477203369,0.2999732196331024,0.2998775541782379,0.2963463366031647,0.2952789962291717,0.2985642850399017,0.3006074130535126,0.3027309477329254,0.3005261421203613,0.300907164812088,0.3029783368110657,0.3044944405555725,0.2981569766998291,0.2956142127513885,0.299979031085968,0.305809885263443,0.3034764528274536,0.3013955950736999,0.3041820526123047,0.3046390116214752,0.3076345920562744,0.3025684952735901,0.302787572145462,0.3042838275432586,0.3087618947029114,0.3073809146881103,0.3083157241344452,0.309103399515152,0.3066750168800354,0.3067053854465484,0.3106936514377594,0.3109026551246643,0.3106796741485595,0.3055593967437744,0.3090705275535583,0.3055923879146576,0.3087252378463745,0.3072529137134552,0.3051963150501251,0.3050454556941986,0.3084619641304016,0.306672602891922,0.3049459159374237,0.3070027530193329,0.3086561560630798,0.308915913105011,0.3056142330169678,0.3065256178379059,0.3072161078453064,0.3122203350067138,0.3062950074672699,0.3103486597537994,0.3102059662342071,0.3119488358497619,0.3082771897315979,0.3100796043872833,0.3124868273735046,0.3110047280788421,0.3118720054626465,0.3041315376758575,0.3115057647228241,0.3088001906871795,0.3168577551841736,0.3113644421100616,0.3124366104602813,0.3168828785419464,0.3092926144599914,0.3121701180934906,0.3163682520389557,0.3150610029697418,0.3114746809005737,0.3134048581123352,0.3160704970359802,0.3136301040649414,0.3169615864753723,0.3144893646240234,0.3145791292190552,0.3127212226390838,0.3167306184768677,0.3172886669635772,0.3168951570987701,0.3155937790870666,0.3135920763015747,0.3156870603561401,0.3176205158233642,0.3117742240428924,0.3131571114063263,0.3150772750377655,0.3159766495227813,0.3157162070274353,0.3173562586307525,0.3140435516834259,0.3161553144454956,0.3147145509719848,0.317251056432724,0.3186215758323669,0.3167826533317566,0.314603179693222,0.3149664998054504,0.3215184211730957,0.3178073167800903,0.3187208175659179,0.317701518535614,0.3186627030372619,0.3185585141181946,0.3173464238643646,0.3165761530399322,0.3158655762672424,0.3201327919960022,0.3181135058403015,0.3217732012271881,0.3195838332176208,0.3207148909568786,0.3191827833652496,0.3201151490211487,0.3208780586719513,0.3220908343791961,0.3213065266609192,0.3219057321548462,0.3219298720359802,0.3216041922569275,0.321382611989975,0.3205022811889648,0.3241901993751526,0.3208385705947876,0.3208568692207336,0.3225097060203552,0.3254899382591247,0.3231809437274933,0.3233455717563629,0.3200404942035675,0.3185034096240997,0.3179292380809784,0.3200477659702301,0.3212410807609558,0.3217600584030151,0.3198374509811401,0.3197197318077087,0.3201925456523895],"label":"FineWeb line dedup w/ min words"},"big-run-url_dedups_lowercase_char_length":{"x":[0.0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.2501270473003387,0.2601193785667419,0.2603300809860229,0.2651051580905914,0.2728359699249267,0.2695354223251343,0.2739534378051758,0.273395299911499,0.2795966863632202,0.284147173166275,0.2829134464263916,0.2859565317630768,0.2828491330146789,0.2857730388641357,0.2869693040847778,0.2732402086257934,0.2847454845905304,0.2865219116210937,0.2886554598808288,0.2892797291278839,0.291290283203125,0.2916518449783325,0.2931891679763794,0.2898360192775726,0.2938919961452484,0.2971687614917755,0.3001134991645813,0.294775515794754,0.2936112582683563,0.295440137386322,0.2940499782562256,0.2959242463111877,0.2958227396011352,0.2964979708194732,0.2992638945579529,0.297306627035141,0.3005943894386291,0.2951188385486603,0.2941581606864929,0.293078601360321,0.2979267835617065,0.3031066656112671,0.3003516793251037,0.2999812364578247,0.3004582524299621,0.2986674308776855,0.3050016462802887,0.3036046326160431,0.3008712530136108,0.3021310865879059,0.2994182109832763,0.3020281195640564,0.3047858774662018,0.3041724264621734,0.3056511282920837,0.301408976316452,0.3070854544639587,0.3071627020835876,0.306472510099411,0.3035155236721039,0.3071917593479156,0.3056483864784241,0.3062016367912292,0.308484673500061,0.3041844666004181,0.3077157437801361,0.3091868460178375,0.3021266460418701,0.3123455643653869,0.3037546277046203,0.3053824007511139,0.3085947334766388,0.3063064217567444,0.3060091733932495,0.3091322183609009,0.3121630549430847,0.3081730604171753,0.3094003200531006,0.3113689124584198,0.3081904053688049,0.3116835951805115,0.3110847771167755,0.3124465942382812,0.3175485730171203,0.3095638453960418,0.3100215196609497,0.3138969242572784,0.3140412271022796,0.3111719191074371,0.3088774979114532,0.3125203847885132,0.3101697266101837,0.3074556291103363,0.3127395212650299,0.3137616813182831,0.3123770952224731,0.3175848126411438,0.3179801702499389,0.3177808821201324,0.3152839839458465,0.3149872720241546,0.3162716925144195,0.313893973827362,0.3169337511062622,0.3194557428359985,0.320783257484436,0.3173812925815582,0.3184501230716705,0.3196139335632324,0.3192282319068908,0.3193719089031219,0.3167150914669037,0.3165983259677887,0.3183095753192901,0.3176077306270599,0.3150804936885834,0.3173128664493561,0.3199821710586548,0.3199923634529114,0.3177184164524078,0.3217757642269134,0.3218257427215576,0.3207743465900421,0.3207042217254638,0.3210084140300751,0.320665568113327,0.3229833245277405,0.3163409233093261,0.3208892941474914,0.3266535699367523,0.3246155977249145,0.3205644786357879,0.3224078416824341,0.3222611546516418,0.3225222527980804,0.3242463171482086,0.3233701586723327,0.3194558620452881,0.3234175741672516,0.3216695189476013,0.3188563883304596,0.3213144540786743,0.3217793107032776,0.32503741979599,0.3196976482868194,0.3221116364002228,0.3204020261764526,0.321814477443695,0.3251912891864776,0.3248582780361175,0.3253252208232879,0.3280388116836548,0.3276797235012054,0.3250380158424377,0.326240211725235,0.3244286477565765,0.3302447497844696,0.3256846368312835,0.3278273046016693,0.3264793753623962,0.3292208611965179,0.3291683495044708,0.3294762372970581,0.325553834438324,0.3297241032123565,0.3272131681442261,0.3282396793365478,0.3285378813743591],"label":"FineWeb URL dedup"}}},"layout":{"xaxis":{"title":{"text":"Training tokens (billions)"}},"title":{"text":"Attempting to further globally dedup worsened perf"}},"defaultWindowSize":5}
\ No newline at end of file