feat: Graphs checkpoint

This commit is contained in:
Tibo De Peuter 2025-12-18 16:06:26 +01:00
parent 2f869a8a7a
commit 15062d8884
Signed by: tdpeuter
GPG key ID: 38297DE43F75FFE2
4 changed files with 453 additions and 4 deletions

49
results/measurements.csv Normal file
View file

@ -0,0 +1,49 @@
compressor,training_dataset,context_size,input_filename,input_size,compressed_size,compression_time,decompressed_size,decompression_time,mse_loss
gzip,,,genome.fna,4699745,1424004,.681197994,4699745,.015465955,0.0
gzip,,,genome_large.fna,23498433,7118154,3.384480370,23498433,.067414798,0.0
gzip,,,genome_small.fna,1367,589,.001937446,1367,.001983156,0.0
gzip,,,genome_xlarge.fna,46996793,14235842,6.775190783,46996793,.131633333,0.0
gzip,,,genome_xsmall.fna,1043,475,.002007016,1043,.002012775,0.0
gzip,,,genome_xxsmall.fna,800,393,.002071485,800,.001958195,0.0
gzip,,,text_large.txt,12977332,4770044,.613155078,12977332,.043915520,0.0
gzip,,,text_small.txt,1022,590,.002070305,1022,.001903226,0.0
gzip,,,text.txt,6488666,2385264,.308393934,6488666,.023656716,0.0
gzip,,,text_xlarge.txt,25954664,9539638,1.229028819,25954664,.085925486,0.0
gzip,,,text_xsmall.txt,825,473,.002110205,825,.001980535,0.0
gzip,,,text_xxsmall.txt,492,325,.001867306,492,.002114055,0.0
LZ4,,,genome.fna,4699745,2655438,.012701161,4699745,.009190410,0.0
LZ4,,,genome_large.fna,23498433,13275544,.020719873,23498433,.025022334,0.0
LZ4,,,genome_small.fna,1367,1041,.001883076,1367,.002144425,0.0
LZ4,,,genome_xlarge.fna,46996793,26551229,.031734579,46996793,.043495412,0.0
LZ4,,,genome_xsmall.fna,1043,814,.001954316,1043,.002085566,0.0
LZ4,,,genome_xxsmall.fna,800,641,.001893416,800,.001943666,0.0
LZ4,,,text_large.txt,12977332,7879136,.017927300,12977332,.015065196,0.0
LZ4,,,text_small.txt,1022,857,.001967146,1022,.002040285,0.0
LZ4,,,text.txt,6488666,3939378,.014891266,6488666,.009709618,0.0
LZ4,,,text_xlarge.txt,25954664,15758785,.023613977,25954664,.023486747,0.0
LZ4,,,text_xsmall.txt,825,678,.001757717,825,.002191075,0.0
LZ4,,,text_xxsmall.txt,492,438,.001869646,492,.002134206,0.0
Autoencoder,genome,256,genome.fna,4699745,4259288,636915773,,27887947,83.62875366210938
Autoencoder,genome,256,genome_large.fna,23498433,21295512,1932602305,,7778175,83.59369659423828
Autoencoder,genome,256,genome_xlarge.fna,46996793,42591024,3850901316,,10996509,83.58621215820312
Autoencoder,genome,128,genome.fna,4699745,9399552,390656081,,5804539,83.01229095458984
Autoencoder,genome,128,genome_large.fna,23498433,46996992,1932561312,,10575739,83.01190185546875
Autoencoder,genome,128,genome_xlarge.fna,46996793,93993728,3873777067,,18670984,83.00253295898438
Autoencoder,enwik9,256,text.txt,6488666,6184668,551986635,,10536259,786.6799926757812
Autoencoder,enwik9,256,text_large.txt,12977332,12369092,1065897991,,5763879,786.6173706054688
Autoencoder,enwik9,256,text_xlarge.txt,25954664,24738184,2139223055,,8369164,786.6337890625
Autoencoder,enwik9,128,text.txt,6488666,12774636,545577194,,20624030,206.2792510986328
Autoencoder,enwik9,128,text_large.txt,12977332,25549272,1073396133,,60871642,206.24131774902344
Autoencoder,enwik9,128,text_xlarge.txt,25954664,51098292,2145601924,,59481825,206.33023071289062
CNN,genome,256,genome_small.fna,1367,1743,1029290599,,890595665,0.0
CNN,genome,256,genome_xsmall.fna,1043,1343,686878467,,683701323,0.0
CNN,genome,256,genome_xxsmall.fna,800,1038,531354486,,527072394,0.0
CNN,genome,128,genome_small.fna,1367,1682,829554150,,851934528,0.0
CNN,genome,128,genome_xsmall.fna,1043,1300,654742547,,637221301,0.0
CNN,genome,128,genome_xxsmall.fna,800,1006,483840337,,488870786,0.0
CNN,enwik9,256,text_small.txt,1022,1561,693378115,,671294958,0.0
CNN,enwik9,256,text_xsmall.txt,825,1268,550333502,,550062973,0.0
CNN,enwik9,256,text_xxsmall.txt,492,790,333745012,,332073466,0.0
CNN,enwik9,128,text_small.txt,1022,1129,629310179,,621317553,0.0
CNN,enwik9,128,text_xsmall.txt,825,882,504538600,,504907940,0.0
CNN,enwik9,128,text_xxsmall.txt,492,571,305443187,,308964670,0.0
1 compressor training_dataset context_size input_filename input_size compressed_size compression_time decompressed_size decompression_time mse_loss
2 gzip genome.fna 4699745 1424004 .681197994 4699745 .015465955 0.0
3 gzip genome_large.fna 23498433 7118154 3.384480370 23498433 .067414798 0.0
4 gzip genome_small.fna 1367 589 .001937446 1367 .001983156 0.0
5 gzip genome_xlarge.fna 46996793 14235842 6.775190783 46996793 .131633333 0.0
6 gzip genome_xsmall.fna 1043 475 .002007016 1043 .002012775 0.0
7 gzip genome_xxsmall.fna 800 393 .002071485 800 .001958195 0.0
8 gzip text_large.txt 12977332 4770044 .613155078 12977332 .043915520 0.0
9 gzip text_small.txt 1022 590 .002070305 1022 .001903226 0.0
10 gzip text.txt 6488666 2385264 .308393934 6488666 .023656716 0.0
11 gzip text_xlarge.txt 25954664 9539638 1.229028819 25954664 .085925486 0.0
12 gzip text_xsmall.txt 825 473 .002110205 825 .001980535 0.0
13 gzip text_xxsmall.txt 492 325 .001867306 492 .002114055 0.0
14 LZ4 genome.fna 4699745 2655438 .012701161 4699745 .009190410 0.0
15 LZ4 genome_large.fna 23498433 13275544 .020719873 23498433 .025022334 0.0
16 LZ4 genome_small.fna 1367 1041 .001883076 1367 .002144425 0.0
17 LZ4 genome_xlarge.fna 46996793 26551229 .031734579 46996793 .043495412 0.0
18 LZ4 genome_xsmall.fna 1043 814 .001954316 1043 .002085566 0.0
19 LZ4 genome_xxsmall.fna 800 641 .001893416 800 .001943666 0.0
20 LZ4 text_large.txt 12977332 7879136 .017927300 12977332 .015065196 0.0
21 LZ4 text_small.txt 1022 857 .001967146 1022 .002040285 0.0
22 LZ4 text.txt 6488666 3939378 .014891266 6488666 .009709618 0.0
23 LZ4 text_xlarge.txt 25954664 15758785 .023613977 25954664 .023486747 0.0
24 LZ4 text_xsmall.txt 825 678 .001757717 825 .002191075 0.0
25 LZ4 text_xxsmall.txt 492 438 .001869646 492 .002134206 0.0
26 Autoencoder genome 256 genome.fna 4699745 4259288 636915773 27887947 83.62875366210938
27 Autoencoder genome 256 genome_large.fna 23498433 21295512 1932602305 7778175 83.59369659423828
28 Autoencoder genome 256 genome_xlarge.fna 46996793 42591024 3850901316 10996509 83.58621215820312
29 Autoencoder genome 128 genome.fna 4699745 9399552 390656081 5804539 83.01229095458984
30 Autoencoder genome 128 genome_large.fna 23498433 46996992 1932561312 10575739 83.01190185546875
31 Autoencoder genome 128 genome_xlarge.fna 46996793 93993728 3873777067 18670984 83.00253295898438
32 Autoencoder enwik9 256 text.txt 6488666 6184668 551986635 10536259 786.6799926757812
33 Autoencoder enwik9 256 text_large.txt 12977332 12369092 1065897991 5763879 786.6173706054688
34 Autoencoder enwik9 256 text_xlarge.txt 25954664 24738184 2139223055 8369164 786.6337890625
35 Autoencoder enwik9 128 text.txt 6488666 12774636 545577194 20624030 206.2792510986328
36 Autoencoder enwik9 128 text_large.txt 12977332 25549272 1073396133 60871642 206.24131774902344
37 Autoencoder enwik9 128 text_xlarge.txt 25954664 51098292 2145601924 59481825 206.33023071289062
38 CNN genome 256 genome_small.fna 1367 1743 1029290599 890595665 0.0
39 CNN genome 256 genome_xsmall.fna 1043 1343 686878467 683701323 0.0
40 CNN genome 256 genome_xxsmall.fna 800 1038 531354486 527072394 0.0
41 CNN genome 128 genome_small.fna 1367 1682 829554150 851934528 0.0
42 CNN genome 128 genome_xsmall.fna 1043 1300 654742547 637221301 0.0
43 CNN genome 128 genome_xxsmall.fna 800 1006 483840337 488870786 0.0
44 CNN enwik9 256 text_small.txt 1022 1561 693378115 671294958 0.0
45 CNN enwik9 256 text_xsmall.txt 825 1268 550333502 550062973 0.0
46 CNN enwik9 256 text_xxsmall.txt 492 790 333745012 332073466 0.0
47 CNN enwik9 128 text_small.txt 1022 1129 629310179 621317553 0.0
48 CNN enwik9 128 text_xsmall.txt 825 882 504538600 504907940 0.0
49 CNN enwik9 128 text_xxsmall.txt 492 571 305443187 308964670 0.0