thomwolf HF staff commited on
Commit
a86ca18
·
1 Parent(s): 0af560f

update build

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. dist/0108e89c9003e8c14ea3.woff +0 -0
  2. dist/02271ec5cb9f5b4588ac.woff +0 -0
  3. dist/073b3402d036714b4370.woff +0 -0
  4. dist/0c3b8929d377c0e9b2f3.woff +0 -0
  5. dist/172d3529b26f8cedef6b.woff2 +0 -0
  6. dist/20f389c4120be058d80a.woff2 +0 -0
  7. dist/2960900c4f271311eb36.woff2 +0 -0
  8. dist/2f7bc363fc5424ebda59.ttf +0 -0
  9. dist/354501bac435c3264834.woff +0 -0
  10. dist/39890742bc957b368704.woff2 +0 -0
  11. dist/3a99e70aee4076660d38.woff +0 -0
  12. dist/3f07ed67f06c720120ce.woff +0 -0
  13. dist/428978dc7837d46de091.woff +0 -0
  14. dist/4ad7c7e8bb8d10a34bb7.ttf +0 -0
  15. dist/4c6b94fd1d07f8beff7c.woff +0 -0
  16. dist/4c761b3711973ab04edf.ttf +0 -0
  17. dist/4f35fbcc9ee8614c2bcc.woff +0 -0
  18. dist/57f5c1837853986ea1db.ttf +0 -0
  19. dist/5b49f4993ae22d7975b4.ttf +0 -0
  20. dist/6d3d25f4820d0da8f01f.woff2 +0 -0
  21. dist/6de7d4b539221a49e9e2.ttf +0 -0
  22. dist/6eec866c69313624be60.woff2 +0 -0
  23. dist/6fdf0ac577be0ba82a4c.woff +0 -0
  24. dist/73ea273a72f4aca30ca5.woff2 +0 -0
  25. dist/7489a2fbfb9bfe704420.ttf +0 -0
  26. dist/7947224e8a9914fa332b.woff +0 -0
  27. dist/7d393d382f3e7fb1c637.woff2 +0 -0
  28. dist/7e873d3833eb108a0758.ttf +0 -0
  29. dist/8169508bf58f8bd92ad8.ttf +0 -0
  30. dist/828abcb200061cffbaae.ttf +0 -0
  31. dist/853be92419a6c3766b9a.ttf +0 -0
  32. dist/8a5f936332e8028c7278.ttf +0 -0
  33. dist/8d593cfaa96238d5e2f8.woff +0 -0
  34. dist/8d6b6822586eea3d3b20.ttf +0 -0
  35. dist/931d67ea207ab37ee693.woff2 +0 -0
  36. dist/95591a929f0d32aa282a.woff2 +0 -0
  37. dist/96759856b4e70f3a8338.woff +0 -0
  38. dist/9eba1d77abcf2aa6e94e.ttf +0 -0
  39. dist/a1abf90dfd72792a577a.woff2 +0 -0
  40. dist/aeffd8025cba3647f1a6.woff +0 -0
  41. dist/assets/data/clustering/data.csv +0 -0
  42. dist/assets/data/clustering/info.csv +106 -0
  43. dist/assets/data/plots/all_dumps_bad/agg_score.json +1 -0
  44. dist/assets/images/IMG_7537D08D7F41-1.jpeg +3 -0
  45. dist/assets/images/IMG_A95961668B3F-1.jpeg +3 -0
  46. dist/assets/images/IMG_C4260C5C58DC-1.jpeg +3 -0
  47. dist/assets/images/IMG_DA188FF29F45-1.jpeg +3 -0
  48. dist/assets/images/image 1.png +3 -0
  49. dist/assets/images/image 10.png +3 -0
  50. dist/assets/images/image 11.png +3 -0
dist/0108e89c9003e8c14ea3.woff ADDED
Binary file (6.5 kB). View file
 
dist/02271ec5cb9f5b4588ac.woff ADDED
Binary file (12.3 kB). View file
 
dist/073b3402d036714b4370.woff ADDED
Binary file (10.6 kB). View file
 
dist/0c3b8929d377c0e9b2f3.woff ADDED
Binary file (29.9 kB). View file
 
dist/172d3529b26f8cedef6b.woff2 ADDED
Binary file (11.3 kB). View file
 
dist/20f389c4120be058d80a.woff2 ADDED
Binary file (16.8 kB). View file
 
dist/2960900c4f271311eb36.woff2 ADDED
Binary file (5.21 kB). View file
 
dist/2f7bc363fc5424ebda59.ttf ADDED
Binary file (19.4 kB). View file
 
dist/354501bac435c3264834.woff ADDED
Binary file (13.3 kB). View file
 
dist/39890742bc957b368704.woff2 ADDED
Binary file (25.3 kB). View file
 
dist/3a99e70aee4076660d38.woff ADDED
Binary file (6.19 kB). View file
 
dist/3f07ed67f06c720120ce.woff ADDED
Binary file (18.7 kB). View file
 
dist/428978dc7837d46de091.woff ADDED
Binary file (19.4 kB). View file
 
dist/4ad7c7e8bb8d10a34bb7.ttf ADDED
Binary file (10.4 kB). View file
 
dist/4c6b94fd1d07f8beff7c.woff ADDED
Binary file (16 kB). View file
 
dist/4c761b3711973ab04edf.ttf ADDED
Binary file (19.6 kB). View file
 
dist/4f35fbcc9ee8614c2bcc.woff ADDED
Binary file (30.8 kB). View file
 
dist/57f5c1837853986ea1db.ttf ADDED
Binary file (11.5 kB). View file
 
dist/5b49f4993ae22d7975b4.ttf ADDED
Binary file (24.5 kB). View file
 
dist/6d3d25f4820d0da8f01f.woff2 ADDED
Binary file (16.4 kB). View file
 
dist/6de7d4b539221a49e9e2.ttf ADDED
Binary file (12.2 kB). View file
 
dist/6eec866c69313624be60.woff2 ADDED
Binary file (5.47 kB). View file
 
dist/6fdf0ac577be0ba82a4c.woff ADDED
Binary file (13.2 kB). View file
 
dist/73ea273a72f4aca30ca5.woff2 ADDED
Binary file (28.1 kB). View file
 
dist/7489a2fbfb9bfe704420.ttf ADDED
Binary file (12.4 kB). View file
 
dist/7947224e8a9914fa332b.woff ADDED
Binary file (4.42 kB). View file
 
dist/7d393d382f3e7fb1c637.woff2 ADDED
Binary file (12 kB). View file
 
dist/7e873d3833eb108a0758.ttf ADDED
Binary file (12.3 kB). View file
 
dist/8169508bf58f8bd92ad8.ttf ADDED
Binary file (51.3 kB). View file
 
dist/828abcb200061cffbaae.ttf ADDED
Binary file (33 kB). View file
 
dist/853be92419a6c3766b9a.ttf ADDED
Binary file (63.6 kB). View file
 
dist/8a5f936332e8028c7278.ttf ADDED
Binary file (31.3 kB). View file
 
dist/8d593cfaa96238d5e2f8.woff ADDED
Binary file (14.1 kB). View file
 
dist/8d6b6822586eea3d3b20.ttf ADDED
Binary file (7.59 kB). View file
 
dist/931d67ea207ab37ee693.woff2 ADDED
Binary file (11.3 kB). View file
 
dist/95591a929f0d32aa282a.woff2 ADDED
Binary file (12.2 kB). View file
 
dist/96759856b4e70f3a8338.woff ADDED
Binary file (18.7 kB). View file
 
dist/9eba1d77abcf2aa6e94e.ttf ADDED
Binary file (53.6 kB). View file
 
dist/a1abf90dfd72792a577a.woff2 ADDED
Binary file (6.91 kB). View file
 
dist/aeffd8025cba3647f1a6.woff ADDED
Binary file (5.98 kB). View file
 
dist/assets/data/clustering/data.csv ADDED
The diff for this file is too large to render. See raw diff
 
dist/assets/data/clustering/info.csv ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ,cluster_id,cluster_summaries,cluster_position_x,cluster_position_y
2
+ 0,-1,None,9.926462,4.7121987
3
+ 1,0,Philosophical/Spiritual Introspection,10.312462,1.2666532
4
+ 2,1,"Scholarships,",8.167274,4.8995786
5
+ 3,2,Politics,8.81142,2.4859838
6
+ 4,3,Theology,9.615214,0.3783942
7
+ 5,4,Dating,4.985182,1.8439052
8
+ 6,5,Accommodation,11.457769,5.080919
9
+ 7,6,Football,6.6154537,-1.6859366
10
+ 8,7,Film Festival,6.9734483,1.4548192
11
+ 9,8,Culinary,13.426296,4.5412893
12
+ 10,9,Music,6.0653744,0.7536916
13
+ 11,10,Gambling,3.124241,3.2533677
14
+ 12,11,Baseball,7.133596,-2.4256644
15
+ 13,12,Technology,6.4929094,6.768577
16
+ 14,13,Website Policies,4.873843,5.771508
17
+ 15,14,Weddings,11.815845,3.7894728
18
+ 16,15,Gaming,5.529167,2.9530518
19
+ 17,16,Commodities/Services Provision,10.453564,5.8489122
20
+ 18,17,Crafts,13.287651,6.4237967
21
+ 19,18,Automobiles,9.9531145,8.840178
22
+ 20,19,Watches,13.893139,9.859185
23
+ 21,20,Dogs,12.595798,3.5351615
24
+ 22,21,Photography,10.7942295,3.5504062
25
+ 23,22,Legalities,8.942016,4.72733
26
+ 24,23,Consumer Electronics,7.078649,8.338984
27
+ 25,24,Insulation,10.520957,7.914946
28
+ 26,25,Cannabis,14.317424,3.2114828
29
+ 27,26,Footwear,15.052116,7.6956415
30
+ 28,27,Real Estate,9.536316,6.103533
31
+ 29,28,Relocation,10.205071,7.1883316
32
+ 30,29,Sports betting,3.2779586,2.443366
33
+ 31,30,Narratives,7.613535,1.8300554
34
+ 32,31,Dating,4.788838,2.1900373
35
+ 33,32,Apparel/Clothing,14.394226,7.3073387
36
+ 34,33,User Authentication,5.265638,6.4014487
37
+ 35,34,Academicwriting,6.9187264,3.4357684
38
+ 36,35,Sports,7.4969172,-2.086585
39
+ 37,36,Fashion/Lifestyle Products,13.821669,7.7150764
40
+ 38,37,Diverse events,9.437052,2.2438836
41
+ 39,38,Blockchain/Cryptocurrency,7.7586045,6.9439344
42
+ 40,39,Online Businesses/Marketing,6.522259,5.219268
43
+ 41,40,Healthcare,11.425277,2.3801014
44
+ 42,41,Home Decor,12.878046,7.2632184
45
+ 43,42,Biomedicine,12.789575,2.3376262
46
+ 44,43,Jewelry,14.259997,8.653363
47
+ 45,44,Addiction,11.561383,1.3774762
48
+ 46,45,Products,11.711758,8.423251
49
+ 47,46,Multi-purposefulness,11.080702,7.4574013
50
+ 48,47,"Mass transit,",9.910158,5.4402313
51
+ 49,48,Ethernet,6.9763823,7.7909245
52
+ 50,49,Legal,9.516912,4.636553
53
+ 51,50,E-commerce,13.263438,8.6548195
54
+ 52,51,Audio,7.717162,8.903019
55
+ 53,52,Infrastructure,10.52904,5.369669
56
+ 54,53,Firearms,11.062812,9.268473
57
+ 55,54,Freight/Logistics,9.551044,7.0336204
58
+ 56,55,Products,12.073747,7.645973
59
+ 57,56,Vaccinations,11.9387045,2.7824683
60
+ 58,57,Artwork,11.019163,4.1677165
61
+ 59,58,Viticulture,14.223523,5.0761614
62
+ 60,59,WordPress,5.9597983,5.824579
63
+ 61,60,Cosmetics/Dermatology,15.093273,3.4669027
64
+ 62,61,Software,6.375921,6.4298844
65
+ 63,62,Dentistry,14.76626,1.1620314
66
+ 64,63,Pest Control,13.201735,3.6806118
67
+ 65,64,SEO,5.720493,5.238112
68
+ 66,65,Lottery,1.7142816,2.9782674
69
+ 67,66,Narratives,8.460977,1.0804662
70
+ 68,67,Waste Reduction & Recycling,10.634534,6.959523
71
+ 69,68,Communication,6.438943,5.9467845
72
+ 70,69,Orthopedics,13.005415,1.1908791
73
+ 71,70,Home Decor & Furniture,12.732457,7.876862
74
+ 72,71,Education,7.6568975,3.4944353
75
+ 73,72,Sports,7.295141,-0.7343214
76
+ 74,73,Social Media Advertising,6.133886,4.8547883
77
+ 75,74,Privacy,4.756733,6.3598356
78
+ 76,75,Website design,6.1168823,5.465095
79
+ 77,76,Roofing,11.389448,8.080609
80
+ 78,77,Nutrition/Supplements,13.631578,2.5334294
81
+ 79,78,Haircare/Hairstyling,15.544645,4.54254
82
+ 80,79,Cookies,4.341592,6.819268
83
+ 81,80,International Trade,8.993828,6.4757586
84
+ 82,81,Entrepreneurial Resources,9.435777,5.3340797
85
+ 83,82,Cricket,6.5171986,-1.245905
86
+ 84,83,Crafts,13.852216,7.049825
87
+ 85,84,Floristry,13.407425,5.8741536
88
+ 86,85,Genealogy,9.530803,1.6548243
89
+ 87,86,Mental Health,11.074349,1.6069281
90
+ 88,87,Volunteerism,10.145443,3.6734574
91
+ 89,88,Lighting,11.385381,8.93693
92
+ 90,89,Artificial Intelligence,6.5306387,6.2178063
93
+ 91,90,Business,7.471462,6.4142885
94
+ 92,91,E-commerce,13.638669,6.5098934
95
+ 93,92,Urbanization/Over-tourism,10.221115,6.100654
96
+ 94,93,Events,10.8449,3.9822264
97
+ 95,94,Pharmaceuticals/Biotechnology,12.318266,2.4331784
98
+ 96,95,Professional Wrestling,6.856304,-0.65598303
99
+ 97,96,Various,9.3211975,3.4894605
100
+ 98,97,Medicine,13.17882,2.1281319
101
+ 99,98,Community Engagement,9.848856,3.5187004
102
+ 100,99,Fitness,12.504849,0.9134393
103
+ 101,100,Bathroom Design & Toilet Engineering,11.779076,7.2920136
104
+ 102,101,Business Development,7.328447,5.659843
105
+ 103,102,Sports,7.6370654,-1.0701839
106
+ 104,103,Sexuality,13.817207,1.6510898
dist/assets/data/plots/all_dumps_bad/agg_score.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"data":{"big-run-refinedweb":{"x":[0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,28.311552000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308933284133672,0.3534814938902855,0.3764607086777687,0.38782499730587,0.3981050960719585,0.4028486795723438,0.4125883243978023,0.4117814563214779,0.414029736071825,0.4197172522544861,0.4211113378405571,0.4279881417751312,0.4280137903988361,0.4280424378812313,0.4291964024305343,0.4326301179826259,0.4371833503246307,0.4346669465303421,0.4336562640964985,0.4432648755609989,0.4401291646063328,0.4394684173166752,0.4476612061262131,0.4465444348752498,0.4472153298556804,0.4433343075215816,0.4510187618434429,0.4459567815065384,0.4460812956094742,0.4498684890568256,0.4529943652451038,0.4528274349868297,0.4551213420927524,0.4549156539142132,0.4564928151667118,0.4576693661510944,0.4557182416319847,0.4536240361630916,0.457439012825489,0.4570476822555065,0.4589823484420776,0.462024375796318,0.4540738053619861,0.4550252184271812,0.4576593860983848,0.4573238864541054,0.4575810581445694,0.4622134491801262,0.4592566937208175,0.4614734016358852,0.4637473002076149,0.4625372551381588,0.4613912180066108,0.4597448222339153,0.4594792164862156,0.4662549719214439,0.4634026065468788,0.4633508697152138,0.4635734222829342,0.4628961533308029,0.4670135043561458,0.4639505892992019,0.4631133340299129,0.4665167145431041,0.4672448337078094,0.4693268723785877,0.4630668573081493,0.4676454700529575,0.4646359197795391,0.4621579721570015,0.4692446552217006,0.4704835228621959,0.4663223996758461,0.4680556617677212,0.466339822858572,0.4682099223136902,0.4711195565760135,0.4722655527293682,0.4727961830794811,0.4676857478916645,0.4719390422105789,0.4713102728128433,0.4712141714990139,0.4721613004803657,0.4713456854224205,0.4682970903813839,0.4679934531450271,0.4685162976384163,0.4679946713149547,0.4681242071092129,0.4702276065945625,0.472664151340723,0.4730790853500366,0.4731674715876579,0.4718914777040481,0.4719801284372806,0.4761029370129108,0.4735167175531387,0.4730370938777923,0.4730173237621784,0.4735377207398414,0.4777223989367485,0.4796326830983162,0.4734170883893966,0.4739485755562782,0.4748299159109592,0.4765299335122108,0.4745025858283043,0.4754423759877682,0.4784592799842357,0.4761341325938701,0.4760282784700393,0.4769757278263569,0.47154351323843,0.4786738082766533,0.4804279990494251,0.4777076803147793,0.4798569902777672,0.4759011939167976,0.4784621745347976,0.479673832654953,0.4780617095530033,0.48076206818223,0.47995800152421,0.4790860973298549,0.4817167408764362,0.4811586998403072,0.482547752559185,0.4816697351634502,0.4809327870607376,0.4816545359790325,0.4804601892828941,0.4776877984404564,0.4813711903989315,0.4844604581594467,0.4819537848234176,0.4820829331874847,0.4778126627206802,0.482935007661581,0.48230691999197,0.4826001971960068,0.4823969900608063,0.4811219945549965,0.4789146520197391,0.484035175293684,0.4848698377609253,0.4855728335678577,0.4825376532971859,0.485215101391077,0.4824351668357849,0.4835342466831207,0.4822137206792831,0.4838785007596016,0.4837255179882049,0.4853012599050998,0.4857851006090641,0.4863366298377514,0.4856646582484245,0.4842503517866134,0.4838776960968971,0.4846346862614155,0.4837041422724724,0.4813097268342972,0.4873070046305656,0.4841253720223903,0.4837464913725853,0.483069509267807,0.4851242564618587,0.4861010462045669],"label":"RefinedWeb"},"big-run-sampled_full_filtered_no_dedup":{"x":[0,2.0971520000000003,4.194304000000001,6.291456,8.388608000000001,10.48576,12.582912,14.680064000000002,16.777216000000003,18.874368,20.97152,23.068672000000003,25.165824,27.262976000000002,28.311552000000002,29.360128000000003,31.45728,33.554432000000006,35.651584,37.748736,39.845888,41.94304,44.040192000000005,46.137344000000006,48.234496,50.331648,52.4288,54.525952000000004,56.623104000000005,58.720256000000006,60.817408,62.91456,65.011712,67.10886400000001,69.206016,71.303168,73.40032000000001,75.497472,77.59462400000001,79.691776,81.788928,83.88608,85.983232,88.08038400000001,90.177536,92.27468800000001,94.37184,96.468992,98.56614400000001,100.663296,102.76044800000001,104.8576,106.95475200000001,109.05190400000001,111.149056,113.24620800000001,115.34336,117.44051200000001,119.537664,121.634816,123.73196800000001,125.82912,127.92627200000001,130.023424,132.120576,134.21772800000002,136.31488000000002,138.412032,140.509184,142.606336,144.70348800000002,146.80064000000002,148.897792,150.994944,153.092096,155.18924800000002,157.28640000000001,159.383552,161.480704,163.577856,165.67500800000002,167.77216,169.869312,171.966464,174.06361600000002,176.16076800000002,178.25792,180.355072,182.452224,184.54937600000002,186.64652800000002,188.74368,190.840832,192.937984,195.03513600000002,197.13228800000002,199.22944,201.326592,203.423744,205.52089600000002,207.61804800000002,209.7152,211.812352,213.90950400000003,216.00665600000002,218.10380800000001,220.20096,222.298112,224.39526400000003,226.49241600000002,228.589568,230.68672,232.783872,234.88102400000002,236.97817600000002,239.075328,241.17248,243.269632,245.36678400000002,247.46393600000002,249.561088,251.65824,253.75539200000003,255.85254400000002,257.949696,260.046848,262.144,264.241152,266.338304,268.43545600000004,270.53260800000004,272.62976000000003,274.726912,276.824064,278.921216,281.018368,283.11552,285.212672,287.309824,289.40697600000004,291.50412800000004,293.60128000000003,295.698432,297.795584,299.892736,301.989888,304.08704,306.184192,308.28134400000005,310.37849600000004,312.47564800000004,314.57280000000003,316.669952,318.767104,320.864256,322.961408,325.05856,327.155712,329.25286400000005,331.35001600000004,333.44716800000003,335.54432,337.641472,339.738624,341.835776,343.932928,346.03008,348.12723200000005,350.22438400000004],"y":[0.3308933284133672,0.3605199865996837,0.3733148723840713,0.3882005847990513,0.3934122696518898,0.3947227671742439,0.4042885974049568,0.3974800482392311,0.4055779427289963,0.4133470430970192,0.4117913842201233,0.4113653488457203,0.4149517640471458,0.4187851920723915,0.4252083078026771,0.4206527359783649,0.4240428246557712,0.422003373503685,0.4280910938978195,0.4244147576391697,0.4316282644867897,0.4295645765960216,0.4310102686285972,0.4360743537545204,0.4313482865691185,0.4350991360843181,0.4378576353192329,0.4335876516997814,0.4347924515604973,0.4348904751241207,0.436600212007761,0.430036511272192,0.4350974671542644,0.4399556629359722,0.4371416717767715,0.4363861419260502,0.4376698136329651,0.4405004419386387,0.4373639523983001,0.4379038028419018,0.4371281825006008,0.4393439553678036,0.440426729619503,0.4401675276458263,0.4429537951946258,0.4449137263000011,0.4434786736965179,0.4450470842421055,0.4454202279448509,0.4394537284970283,0.442185215651989,0.4461225643754005,0.4427758157253265,0.4430646039545536,0.4476901069283485,0.4478763341903686,0.4493869319558143,0.4448477327823639,0.450044184923172,0.4498609118163585,0.4457665979862213,0.4506924152374267,0.449855338782072,0.448790930211544,0.4474099352955818,0.4546772800385952,0.4529431238770485,0.452015146613121,0.4502020999789238,0.4493804536759853,0.4523266032338142,0.4551868587732315,0.4501944817602634,0.4493303671479225,0.4526805207133293,0.4533850513398647,0.4518048763275146,0.4518973492085933,0.4531301632523536,0.4518006071448326,0.4553494565188885,0.4528752230107784,0.4536322727799415,0.4561733976006508,0.4549491256475448,0.4574789106845855,0.4577847123146057,0.4563642293214798,0.4578686729073524,0.4561499990522861,0.4537816494703293,0.4542164430022239,0.4559455662965774,0.4554723873734474,0.4575514122843742,0.4575202167034149,0.4592722058296203,0.4585275091230869,0.4580587856471538,0.456934317946434,0.4577495418488979,0.4540119916200638,0.4570806957781315,0.4608120545744896,0.4588425755500793,0.4578334167599678,0.4610816091299057,0.4598177038133144,0.461849745362997,0.4631866924464702,0.4601576402783394,0.4646804705262184,0.4632389545440674,0.4604574106633663,0.4602976888418197,0.4581312239170074,0.4654182009398937,0.4655338563024997,0.4616620391607284,0.461054053157568,0.4613021649420261,0.4658613465726375,0.4633531905710697,0.4613638147711754,0.4643996246159076,0.462500050663948,0.4650798961520195,0.4648764543235302,0.4639869071543216,0.4634246975183487,0.46585888043046,0.4639799632132053,0.4630857892334461,0.4644265696406364,0.4642998576164245,0.4686848931014538,0.4687492996454239,0.4650243632495403,0.4627032242715359,0.4665953740477562,0.4660026729106903,0.4664581045508384,0.4676475040614605,0.4657339677214622,0.4664678275585174,0.4673498086631298,0.4676674827933311,0.4680955372750759,0.4681585058569908,0.4659864418208599,0.4686457589268684,0.4661462865769863,0.4658931568264961,0.4674226939678192,0.46805215254426,0.4682257212698459,0.4689070098102093,0.4699570722877979,0.4655096270143986,0.4688013233244419,0.4707522802054882,0.4661469310522079,0.4688841328024864,0.4671329781413078,0.4662554152309894,0.4697433896362781,0.4698473587632179,0.4676505327224731,0.4696521013975143],"label":"FineWeb filtered only"},"big-run-fineweb-cross-dedup-fixed":{"x":[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":[0.3308933284133672,0.3551952373236418,0.3736435137689113,0.3814037963747978,0.3948809280991554,0.3996850810945034,0.4089604057371616,0.4100853353738785,0.4119834117591381,0.4168377220630646,0.4186493046581745,0.4169826358556747,0.4234288297593593,0.4229162000119686,0.4273439794778824,0.4290364980697632,0.4291782416403293,0.4296907968819141,0.4311576783657074,0.4326641112565994,0.430318683385849,0.430436260998249,0.4339037239551544,0.4363459683954716,0.4357402548193931,0.4342963136732578,0.4366712383925915,0.4363959729671478,0.436981026083231,0.4447868093848228,0.4411709941923618,0.4406092017889023,0.4424176625907421,0.4423875361680984,0.4422253370285034,0.4410557933151722,0.4447037056088447,0.4454837813973427,0.4435960277915001,0.4468514993786812,0.4479999616742134,0.4428562931716442,0.445764634758234,0.4456562362611294,0.4488007053732872,0.4475954286754131,0.4468922987580299,0.4548408314585686,0.4511027485132217,0.4530330970883369,0.4483681954443455,0.4531726539134979,0.45334542542696,0.4544384703040123,0.4530758671462536,0.4540613554418087,0.4510113634169101,0.4538320265710354,0.4518541917204857,0.4536847211420536,0.4532708041369915,0.4552236869931221,0.455034039914608,0.4562875479459762,0.4532428197562694,0.4574853852391243,0.4517738744616508,0.4579889141023159,0.4538268558681011,0.456730306148529,0.4526018649339676,0.4562746733427048,0.4560015797615051,0.4555426277220249,0.4561501257121563,0.4524396173655987,0.4557023830711841,0.4589769169688225,0.4581078588962555,0.4620813727378845,0.4586601965129375,0.4568093195557594,0.4569808952510357,0.4567535072565079,0.4575250148773193,0.4606908001005649,0.4603964723646641,0.4622848592698574,0.4594669193029403,0.4640629850327968,0.4604269936680794,0.4634841009974479,0.4644578285515308,0.4642514958977699,0.4666304066777229,0.4616626128554344,0.4588956907391548,0.4620226770639419,0.4628621749579906,0.4595407098531723,0.4635516740381717,0.46005355194211,0.4601523540914058,0.4644204638898372,0.4620639197528362,0.46614545956254,0.4636696502566337,0.4610077403485775,0.4640897810459137,0.4636163525283336,0.4630545899271965,0.466012816876173,0.4650349207222461,0.4613720141351223,0.4644323363900184,0.4647249802947044,0.4656480401754379,0.4651664271950722,0.4622530452907085,0.4655019529163837,0.4650313258171081,0.466718140989542,0.4661559611558914,0.4661237150430679,0.4664223715662956,0.4640601389110088,0.4642657749354839,0.4633881188929081,0.4629989042878151,0.4685831367969513,0.4675870984792709,0.467183344066143,0.4678030684590339,0.4660939238965511,0.4691914953291416,0.4670972637832165,0.468262892216444,0.4672016054391861,0.4676182121038437,0.4698677137494087,0.4658828042447567,0.4701816700398922,0.4684622809290886,0.466015312820673,0.4675401039421558,0.4693200923502445,0.4702670983970165,0.4679145030677318,0.4676233418285846,0.4674933589994907,0.4678357951343059,0.4669915996491909,0.4657857678830623,0.4666901864111423,0.4669371582567692,0.4672787226736545,0.4684535376727581,0.4685697965323925,0.4694835692644119,0.4683254994451999,0.4712230190634727,0.4683987610042095,0.4707653746008873,0.4663059376180172,0.4683133698999882,0.4686385430395603,0.4657671600580215,0.4692615270614624],"label":"FineWeb full MinHash"}},"layout":{"title":{"text":"Dedup across all dumps does not improve performance"}}}
dist/assets/images/IMG_7537D08D7F41-1.jpeg ADDED

Git LFS Details

  • SHA256: 9b3f86eaa830c3496db3dec914dfc5b107dd5ce65c4faa372753ce39ef39bb50
  • Pointer size: 131 Bytes
  • Size of remote file: 368 kB
dist/assets/images/IMG_A95961668B3F-1.jpeg ADDED

Git LFS Details

  • SHA256: e37655584c5c2118065c95cb88bc4acf6d2326bdafe732d397edb853d226757d
  • Pointer size: 131 Bytes
  • Size of remote file: 762 kB
dist/assets/images/IMG_C4260C5C58DC-1.jpeg ADDED

Git LFS Details

  • SHA256: 0c7775946b4ef616e1483bdfc9df5e582147f637db2ecb61d8abe68cf6b3bf36
  • Pointer size: 131 Bytes
  • Size of remote file: 562 kB
dist/assets/images/IMG_DA188FF29F45-1.jpeg ADDED

Git LFS Details

  • SHA256: 434ba8f17a4bc1923a52c2bf09632c297e1971fb66008df03f432ad86d5a5b21
  • Pointer size: 131 Bytes
  • Size of remote file: 607 kB
dist/assets/images/image 1.png ADDED

Git LFS Details

  • SHA256: ddeda70dbd64341c246a1a8027dc660103ba8d865ed14e778add1aec312f641c
  • Pointer size: 130 Bytes
  • Size of remote file: 82.4 kB
dist/assets/images/image 10.png ADDED

Git LFS Details

  • SHA256: 94b3664d2f13e123ba40d922464bdfb6f2e0ab9dd966c91e52ee7c4a5c89a281
  • Pointer size: 132 Bytes
  • Size of remote file: 1.14 MB
dist/assets/images/image 11.png ADDED

Git LFS Details

  • SHA256: 5ae427f06760810d0188dd879f39e2fc0c0e15fe0fd938d640bce45715ae6e8c
  • Pointer size: 131 Bytes
  • Size of remote file: 892 kB