blogpost-fineweb-v1 / data /plots /dedup_attempts /winogrande_acc_norm.json
hynky's picture
hynky HF staff
new plotting code (JIT)
0932e7b
raw
history blame
44.8 kB
{"data":{"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"}},"layout":{"xaxis":{"title":{"text":"Training tokens (billions)"}},"title":{"text":"Attempting to further globally dedup worsened perf"}}}