FineVision / app /src /content /assets /data /ss_vs_s1.csv
lusxvr's picture
new plots
a024e38
raw
history blame
28 kB
run,step,metric,value,stderr
Single Stage,1000,ai2d_exact_match,0.2548575129533679,0.007843322436924496
Single Stage,1000,average,0.27120689295763617,
Single Stage,1000,average_rank,2.0,
Single Stage,1000,chartqa_relaxed_overall,0.3308,0.009411906161401973
Single Stage,1000,docvqa_val_anls,0.3528553494243383,0.005852289239342309
Single Stage,1000,infovqa_val_anls,0.17320578642581314,0.006297063452679795
Single Stage,1000,mme_total_score,977.4280712284914,
Single Stage,1000,mmmu_val_mmmu_acc,0.25222,
Single Stage,1000,mmstar_average,0.23215874078908072,
Single Stage,1000,ocrbench_ocrbench_accuracy,0.286,
Single Stage,1000,seedbench_seed_all,0.2563646470261256,
Single Stage,1000,textvqa_val_exact_match,0.3024,0.00628900296642181
Single Stage,2000,ai2d_exact_match,0.26295336787564766,0.007923526907377255
Single Stage,2000,average,0.3202068275596269,
Single Stage,2000,average_rank,1.8,
Single Stage,2000,chartqa_relaxed_overall,0.4688,0.009982508912777261
Single Stage,2000,docvqa_val_anls,0.4452261510942785,0.00614755494712251
Single Stage,2000,infovqa_val_anls,0.1820547866557169,0.006217861455795791
Single Stage,2000,mme_total_score,1049.3036214485794,
Single Stage,2000,mmmu_val_mmmu_acc,0.24556,
Single Stage,2000,mmstar_average,0.21305462434540698,
Single Stage,2000,ocrbench_ocrbench_accuracy,0.395,
Single Stage,2000,seedbench_seed_all,0.258532518065592,
Single Stage,2000,textvqa_val_exact_match,0.41068000000000005,0.006697862330024289
Single Stage,3000,ai2d_exact_match,0.25226683937823835,0.007816909588794397
Single Stage,3000,average,0.3507423834414229,
Single Stage,3000,average_rank,1.7,
Single Stage,3000,chartqa_relaxed_overall,0.5028,0.010001843767601082
Single Stage,3000,docvqa_val_anls,0.502653993831009,0.006267072346683124
Single Stage,3000,infovqa_val_anls,0.21728617578189535,0.006796941784959762
Single Stage,3000,mme_total_score,1170.2383953581434,
Single Stage,3000,mmmu_val_mmmu_acc,0.27556,
Single Stage,3000,mmstar_average,0.25432376938577683,
Single Stage,3000,ocrbench_ocrbench_accuracy,0.436,
Single Stage,3000,seedbench_seed_all,0.2792106725958866,
Single Stage,3000,textvqa_val_exact_match,0.43658,0.006766885462882726
Single Stage,4000,ai2d_exact_match,0.2645725388601036,0.007939149662089447
Single Stage,4000,average,0.36961781722974835,
Single Stage,4000,average_rank,1.8,
Single Stage,4000,chartqa_relaxed_overall,0.5312,0.009982508912777261
Single Stage,4000,docvqa_val_anls,0.5374434618615119,0.0062905728113059655
Single Stage,4000,infovqa_val_anls,0.2287924838861707,0.006994568698639919
Single Stage,4000,mme_total_score,1155.203781512605,
Single Stage,4000,mmmu_val_mmmu_acc,0.25556,
Single Stage,4000,mmstar_average,0.2575590188757354,
Single Stage,4000,ocrbench_ocrbench_accuracy,0.453,
Single Stage,4000,seedbench_seed_all,0.33913285158421347,
Single Stage,4000,textvqa_val_exact_match,0.4593,0.006791695475025738
Single Stage,5000,ai2d_exact_match,0.3125,0.008342439145556371
Single Stage,5000,average,0.3974627910380972,
Single Stage,5000,average_rank,1.8,
Single Stage,5000,chartqa_relaxed_overall,0.5488,0.00995424828018316
Single Stage,5000,docvqa_val_anls,0.552360266782429,0.006300308519952055
Single Stage,5000,infovqa_val_anls,0.23425555286643698,0.007002254622066442
Single Stage,5000,mme_total_score,1181.4653861544618,
Single Stage,5000,mmmu_val_mmmu_acc,0.26667,
Single Stage,5000,mmstar_average,0.29596648146165705,
Single Stage,5000,ocrbench_ocrbench_accuracy,0.462,
Single Stage,5000,seedbench_seed_all,0.43107281823235133,
Single Stage,5000,textvqa_val_exact_match,0.47354000000000007,0.0068172185364497985
Single Stage,6000,ai2d_exact_match,0.358160621761658,0.008629463221867162
Single Stage,6000,average,0.4161227404571003,
Single Stage,6000,average_rank,1.6,
Single Stage,6000,chartqa_relaxed_overall,0.5628,0.00992279440175477
Single Stage,6000,docvqa_val_anls,0.5747451497228876,0.00625495440870239
Single Stage,6000,infovqa_val_anls,0.22152017368968838,0.006604546680525351
Single Stage,6000,mme_total_score,1284.1648659463785,
Single Stage,6000,mmmu_val_mmmu_acc,0.27111,
Single Stage,6000,mmstar_average,0.2978489412854164,
Single Stage,6000,ocrbench_ocrbench_accuracy,0.495,
Single Stage,6000,seedbench_seed_all,0.4795997776542524,
Single Stage,6000,textvqa_val_exact_match,0.48432,0.006800535050670284
Single Stage,7000,ai2d_exact_match,0.3707901554404145,0.00869347755587734
Single Stage,7000,average,0.4291083177345374,
Single Stage,7000,average_rank,1.6,
Single Stage,7000,chartqa_relaxed_overall,0.5656,0.009915542506251351
Single Stage,7000,docvqa_val_anls,0.5940907049431567,0.006224236305767187
Single Stage,7000,infovqa_val_anls,0.2515675215816963,0.007105097396092786
Single Stage,7000,mme_total_score,1185.875650260104,
Single Stage,7000,mmmu_val_mmmu_acc,0.26556,
Single Stage,7000,mmstar_average,0.31372400960777047,
Single Stage,7000,ocrbench_ocrbench_accuracy,0.504,
Single Stage,7000,seedbench_seed_all,0.4964424680377988,
Single Stage,7000,textvqa_val_exact_match,0.5002,0.006794794025220267
Single Stage,8000,ai2d_exact_match,0.37759067357512954,0.008725299846043883
Single Stage,8000,average,0.43846759477995995,
Single Stage,8000,average_rank,1.5,
Single Stage,8000,chartqa_relaxed_overall,0.5832,0.009862556058385773
Single Stage,8000,docvqa_val_anls,0.6017336419437208,0.006231612198089698
Single Stage,8000,infovqa_val_anls,0.2449256624147254,0.006992518502948913
Single Stage,8000,mme_total_score,1199.2409963985594,
Single Stage,8000,mmmu_val_mmmu_acc,0.28111,
Single Stage,8000,mmstar_average,0.33512257186205047,
Single Stage,8000,ocrbench_ocrbench_accuracy,0.51,
Single Stage,8000,seedbench_seed_all,0.5024458032240133,
Single Stage,8000,textvqa_val_exact_match,0.51008,0.006796301690135059
Single Stage,9000,ai2d_exact_match,0.4067357512953368,0.008841214921078996
Single Stage,9000,average,0.4422510732201056,
Single Stage,9000,average_rank,1.6,
Single Stage,9000,chartqa_relaxed_overall,0.5912,0.009834211136815875
Single Stage,9000,docvqa_val_anls,0.6170968481662739,0.00617235763542544
Single Stage,9000,infovqa_val_anls,0.23537031288570615,0.00670318154156447
Single Stage,9000,mme_total_score,1231.5195078031213,
Single Stage,9000,mmmu_val_mmmu_acc,0.25889,
Single Stage,9000,mmstar_average,0.3216444898242951,
Single Stage,9000,ocrbench_ocrbench_accuracy,0.515,
Single Stage,9000,seedbench_seed_all,0.5120622568093385,
Single Stage,9000,textvqa_val_exact_match,0.52226,0.006792711289708482
Single Stage,10000,ai2d_exact_match,0.39993523316062174,0.008817096257082848
Single Stage,10000,average,0.4523875703250908,
Single Stage,10000,average_rank,1.3,
Single Stage,10000,chartqa_relaxed_overall,0.5996,0.00980154906867574
Single Stage,10000,docvqa_val_anls,0.6262613496433054,0.006147756371688175
Single Stage,10000,infovqa_val_anls,0.263290074230132,0.007186788766942786
Single Stage,10000,mme_total_score,1240.8218287314926,
Single Stage,10000,mmmu_val_mmmu_acc,0.28778,
Single Stage,10000,mmstar_average,0.32972717906018517,
Single Stage,10000,ocrbench_ocrbench_accuracy,0.517,
Single Stage,10000,seedbench_seed_all,0.5217342968315731,
Single Stage,10000,textvqa_val_exact_match,0.5261600000000001,0.006785774843600811
Single Stage,11000,ai2d_exact_match,0.422279792746114,0.008889771831066474
Single Stage,11000,average,0.4561398159525099,
Single Stage,11000,average_rank,1.2,
Single Stage,11000,chartqa_relaxed_overall,0.6104,0.009755142291143075
Single Stage,11000,docvqa_val_anls,0.6373130149166712,0.006128022584995044
Single Stage,11000,infovqa_val_anls,0.24419378339723755,0.006897644885887063
Single Stage,11000,mme_total_score,1322.9488795518205,
Single Stage,11000,mmmu_val_mmmu_acc,0.27778,
Single Stage,11000,mmstar_average,0.3298563439522548,
Single Stage,11000,ocrbench_ocrbench_accuracy,0.521,
Single Stage,11000,seedbench_seed_all,0.5237354085603113,
Single Stage,11000,textvqa_val_exact_match,0.5387,0.006770851562852138
Single Stage,12000,ai2d_exact_match,0.42001295336787564,0.008883255931688034
Single Stage,12000,average,0.4582751140055433,
Single Stage,12000,average_rank,1.4,
Single Stage,12000,chartqa_relaxed_overall,0.618,0.009719474639861454
Single Stage,12000,docvqa_val_anls,0.6393961983751871,0.0061228747388476674
Single Stage,12000,infovqa_val_anls,0.24798874058574302,0.006855374548993139
Single Stage,12000,mme_total_score,1225.6453581432572,
Single Stage,12000,mmmu_val_mmmu_acc,0.27889,
Single Stage,12000,mmstar_average,0.34010867846816534,
Single Stage,12000,ocrbench_ocrbench_accuracy,0.512,
Single Stage,12000,seedbench_seed_all,0.5350194552529183,
Single Stage,12000,textvqa_val_exact_match,0.5330600000000001,0.006777713092109446
Single Stage,13000,ai2d_exact_match,0.4375,0.008928571428571428
Single Stage,13000,average,0.4692868662590049,
Single Stage,13000,average_rank,1.2,
Single Stage,13000,chartqa_relaxed_overall,0.6148,0.00973479791861169
Single Stage,13000,docvqa_val_anls,0.6511374872549951,0.006086953065248391
Single Stage,13000,infovqa_val_anls,0.24465055100441893,0.006808432538374664
Single Stage,13000,mme_total_score,1281.7122849139657,
Single Stage,13000,mmmu_val_mmmu_acc,0.28222,
Single Stage,13000,mmstar_average,0.3453069542917521,
Single Stage,13000,ocrbench_ocrbench_accuracy,0.549,
Single Stage,13000,seedbench_seed_all,0.5442468037798777,
Single Stage,13000,textvqa_val_exact_match,0.55472,0.0067416788982325
Single Stage,14000,ai2d_exact_match,0.4572538860103627,0.00896620675297095
Single Stage,14000,average,0.47352486841689195,
Single Stage,14000,average_rank,1.4,
Single Stage,14000,chartqa_relaxed_overall,0.6172,0.009723347231923635
Single Stage,14000,docvqa_val_anls,0.6502269393708169,0.006057950730638126
Single Stage,14000,infovqa_val_anls,0.25805460837190913,0.007037735231659539
Single Stage,14000,mme_total_score,1309.1444577831132,
Single Stage,14000,mmmu_val_mmmu_acc,0.28111,
Single Stage,14000,mmstar_average,0.34575818188776586,
Single Stage,14000,ocrbench_ocrbench_accuracy,0.551,
Single Stage,14000,seedbench_seed_all,0.5483602001111729,
Single Stage,14000,textvqa_val_exact_match,0.55276,0.006751206724612103
Single Stage,15000,ai2d_exact_match,0.45045336787564766,0.008954861634252399
Single Stage,15000,average,0.47878665012878824,
Single Stage,15000,average_rank,1.2,
Single Stage,15000,chartqa_relaxed_overall,0.612,0.009747841205275417
Single Stage,15000,docvqa_val_anls,0.6621413031955148,0.006056838050222495
Single Stage,15000,infovqa_val_anls,0.2706898598157733,0.007200315730154543
Single Stage,15000,mme_total_score,1384.2171868747498,
Single Stage,15000,mmmu_val_mmmu_acc,0.30222,
Single Stage,15000,mmstar_average,0.35408135695920684,
Single Stage,15000,ocrbench_ocrbench_accuracy,0.558,
Single Stage,15000,seedbench_seed_all,0.5411339633129516,
Single Stage,15000,textvqa_val_exact_match,0.5583600000000001,0.0067279027203879065
Single Stage,16000,ai2d_exact_match,0.45077720207253885,0.008955440137395838
Single Stage,16000,average,0.47665128022935843,
Single Stage,16000,average_rank,1.3,
Single Stage,16000,chartqa_relaxed_overall,0.632,0.00964715642305132
Single Stage,16000,docvqa_val_anls,0.6709415729142987,0.005999818105621502
Single Stage,16000,infovqa_val_anls,0.26050032542402035,0.006997451875879188
Single Stage,16000,mme_total_score,1317.8491396558625,
Single Stage,16000,mmmu_val_mmmu_acc,0.27556,
Single Stage,16000,mmstar_average,0.33214333327093315,
Single Stage,16000,ocrbench_ocrbench_accuracy,0.56,
Single Stage,16000,seedbench_seed_all,0.5463590883824346,
Single Stage,16000,textvqa_val_exact_match,0.56158,0.006723854754867398
Single Stage,17000,ai2d_exact_match,0.45919689119170987,0.008969138793675545
Single Stage,17000,average,0.4777141780162423,
Single Stage,17000,average_rank,1.3,
Single Stage,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
Single Stage,17000,docvqa_val_anls,0.6796338519136422,0.005948761388267941
Single Stage,17000,infovqa_val_anls,0.28070956072505215,0.007298333094144192
Single Stage,17000,mme_total_score,1381.9161664665867,
Single Stage,17000,mmmu_val_mmmu_acc,0.27667,
Single Stage,17000,mmstar_average,0.3370289492329521,
Single Stage,17000,ocrbench_ocrbench_accuracy,0.519,
Single Stage,17000,seedbench_seed_all,0.5510283490828238,
Single Stage,17000,textvqa_val_exact_match,0.56416,0.006724830373229479
Single Stage,18000,ai2d_exact_match,0.46567357512953367,0.008977921602780726
Single Stage,18000,average,0.4819834595278701,
Single Stage,18000,average_rank,1.3,
Single Stage,18000,chartqa_relaxed_overall,0.6376,0.009615793331418735
Single Stage,18000,docvqa_val_anls,0.6775884603912571,0.005972234236435759
Single Stage,18000,infovqa_val_anls,0.27154318420389256,0.007164903131667027
Single Stage,18000,mme_total_score,1336.922769107643,
Single Stage,18000,mmmu_val_mmmu_acc,0.28667,
Single Stage,18000,mmstar_average,0.34482796716566916,
Single Stage,18000,ocrbench_ocrbench_accuracy,0.533,
Single Stage,18000,seedbench_seed_all,0.5543079488604781,
Single Stage,18000,textvqa_val_exact_match,0.5666399999999999,0.006713392287599574
Single Stage,19000,ai2d_exact_match,0.4682642487046632,0.008981008686994101
Single Stage,19000,average,0.4899006713916878,
Single Stage,19000,average_rank,1.1,
Single Stage,19000,chartqa_relaxed_overall,0.6444,0.009575809858898698
Single Stage,19000,docvqa_val_anls,0.678226526479947,0.005970619221588814
Single Stage,19000,infovqa_val_anls,0.26993847247278,0.0071348470764911525
Single Stage,19000,mme_total_score,1406.6628651460583,
Single Stage,19000,mmmu_val_mmmu_acc,0.28333,
Single Stage,19000,mmstar_average,0.356220913822775,
Single Stage,19000,ocrbench_ocrbench_accuracy,0.577,
Single Stage,19000,seedbench_seed_all,0.554585881045025,
Single Stage,19000,textvqa_val_exact_match,0.57714,0.0066918487914812905
Single Stage,20000,ai2d_exact_match,0.47571243523316065,0.00898853090258662
Single Stage,20000,average,0.4873169067639118,
Single Stage,20000,average_rank,1.2,
Single Stage,20000,chartqa_relaxed_overall,0.6336,0.009638338810708618
Single Stage,20000,docvqa_val_anls,0.6895214454380043,0.005896462073053767
Single Stage,20000,infovqa_val_anls,0.2655657550458317,0.007033265532032538
Single Stage,20000,mme_total_score,1324.6738695478193,
Single Stage,20000,mmmu_val_mmmu_acc,0.30111,
Single Stage,20000,mmstar_average,0.33806766134497995,
Single Stage,20000,ocrbench_ocrbench_accuracy,0.555,
Single Stage,20000,seedbench_seed_all,0.5587548638132296,
Single Stage,20000,textvqa_val_exact_match,0.56852,0.006720151338087659
Two Stage,1000,ai2d_exact_match,0.25906735751295334,0.007885466610693084
Two Stage,1000,average,0.31368848609084204,
Two Stage,1000,average_rank,1.0,
Two Stage,1000,chartqa_relaxed_overall,0.4436,0.009938164963872337
Two Stage,1000,docvqa_val_anls,0.42857906272393714,0.00617017051120098
Two Stage,1000,infovqa_val_anls,0.19144447578161194,0.006593728313201272
Two Stage,1000,mme_total_score,998.7869147659063,
Two Stage,1000,mmmu_val_mmmu_acc,0.25889,
Two Stage,1000,mmstar_average,0.2467637945300377,
Two Stage,1000,ocrbench_ocrbench_accuracy,0.368,
Two Stage,1000,seedbench_seed_all,0.25703168426903833,
Two Stage,1000,textvqa_val_exact_match,0.36982,0.006597131039140386
Two Stage,2000,ai2d_exact_match,0.26327720207253885,0.007926662492947052
Two Stage,2000,average,0.3358130433652279,
Two Stage,2000,average_rank,1.2,
Two Stage,2000,chartqa_relaxed_overall,0.4992,0.010001987797631107
Two Stage,2000,docvqa_val_anls,0.4932752040405314,0.006286364089099095
Two Stage,2000,infovqa_val_anls,0.19095428252193772,0.006391194919224349
Two Stage,2000,mme_total_score,1062.8957583033214,
Two Stage,2000,mmmu_val_mmmu_acc,0.23333,
Two Stage,2000,mmstar_average,0.22051867830573926,
Two Stage,2000,ocrbench_ocrbench_accuracy,0.435,
Two Stage,2000,seedbench_seed_all,0.2556420233463035,
Two Stage,2000,textvqa_val_exact_match,0.43112,0.006756288819146318
Two Stage,3000,ai2d_exact_match,0.2655440414507772,0.007948457289013515
Two Stage,3000,average,0.3636919255920759,
Two Stage,3000,average_rank,1.3,
Two Stage,3000,chartqa_relaxed_overall,0.5348,0.009977745545085072
Two Stage,3000,docvqa_val_anls,0.5283823835512687,0.006261305725762883
Two Stage,3000,infovqa_val_anls,0.2064005153919739,0.00660395026420985
Two Stage,3000,mme_total_score,1152.5195078031213,
Two Stage,3000,mmmu_val_mmmu_acc,0.26667,
Two Stage,3000,mmstar_average,0.26072557614922737,
Two Stage,3000,ocrbench_ocrbench_accuracy,0.455,
Two Stage,3000,seedbench_seed_all,0.29666481378543635,
Two Stage,3000,textvqa_val_exact_match,0.45903999999999995,0.006792178031860127
Two Stage,4000,ai2d_exact_match,0.30343264248704666,0.008274550183857863
Two Stage,4000,average,0.386738207804619,
Two Stage,4000,average_rank,1.2,
Two Stage,4000,chartqa_relaxed_overall,0.5464,0.00995883966107287
Two Stage,4000,docvqa_val_anls,0.5513347609587042,0.006295149714671814
Two Stage,4000,infovqa_val_anls,0.209061566918142,0.006630816594060217
Two Stage,4000,mme_total_score,1092.9095638255303,
Two Stage,4000,mmmu_val_mmmu_acc,0.26889,
Two Stage,4000,mmstar_average,0.26686799048357046,
Two Stage,4000,ocrbench_ocrbench_accuracy,0.477,
Two Stage,4000,seedbench_seed_all,0.38643690939410785,
Two Stage,4000,textvqa_val_exact_match,0.47121999999999997,0.006809171409434235
Two Stage,5000,ai2d_exact_match,0.34617875647668395,0.008562713351618975
Two Stage,5000,average,0.41048271276999254,
Two Stage,5000,average_rank,1.2,
Two Stage,5000,chartqa_relaxed_overall,0.5568,0.009937253322797029
Two Stage,5000,docvqa_val_anls,0.5616928036954175,0.006281333847375657
Two Stage,5000,infovqa_val_anls,0.21417615930558564,0.006470237976804916
Two Stage,5000,mme_total_score,1113.2024809923969,
Two Stage,5000,mmmu_val_mmmu_acc,0.28889,
Two Stage,5000,mmstar_average,0.3048769900603613,
Two Stage,5000,ocrbench_ocrbench_accuracy,0.501,
Two Stage,5000,seedbench_seed_all,0.4454697053918844,
Two Stage,5000,textvqa_val_exact_match,0.47525999999999996,0.006811465752181289
Two Stage,6000,ai2d_exact_match,0.3853626943005181,0.008759432661868542
Two Stage,6000,average,0.4256324408073156,
Two Stage,6000,average_rank,1.4,
Two Stage,6000,chartqa_relaxed_overall,0.574,0.009891852177211218
Two Stage,6000,docvqa_val_anls,0.5959624206334873,0.006223948314975518
Two Stage,6000,infovqa_val_anls,0.21910870056052556,0.00650522330852698
Two Stage,6000,mme_total_score,1166.5228091236495,
Two Stage,6000,mmmu_val_mmmu_acc,0.28333,
Two Stage,6000,mmstar_average,0.28797389940888596,
Two Stage,6000,ocrbench_ocrbench_accuracy,0.512,
Two Stage,6000,seedbench_seed_all,0.4776542523624236,
Two Stage,6000,textvqa_val_exact_match,0.4953,0.006792791061270795
Two Stage,7000,ai2d_exact_match,0.3915155440414508,0.008784780895708935
Two Stage,7000,average,0.4301306852910006,
Two Stage,7000,average_rank,1.4,
Two Stage,7000,chartqa_relaxed_overall,0.5776,0.009880807059104824
Two Stage,7000,docvqa_val_anls,0.5986163103423551,0.0062031909815058375
Two Stage,7000,infovqa_val_anls,0.22133856274121264,0.006604073748499083
Two Stage,7000,mme_total_score,1191.3954581832734,
Two Stage,7000,mmmu_val_mmmu_acc,0.28667,
Two Stage,7000,mmstar_average,0.2999043663917079,
Two Stage,7000,ocrbench_ocrbench_accuracy,0.501,
Two Stage,7000,seedbench_seed_all,0.48449138410227904,
Two Stage,7000,textvqa_val_exact_match,0.51004,0.006807782962299279
Two Stage,8000,ai2d_exact_match,0.4106217616580311,0.008854207883828033
Two Stage,8000,average,0.4460743520389214,
Two Stage,8000,average_rank,1.5,
Two Stage,8000,chartqa_relaxed_overall,0.6044,0.009781540134915584
Two Stage,8000,docvqa_val_anls,0.6026263625222106,0.006221681650022778
Two Stage,8000,infovqa_val_anls,0.25653488200256863,0.007114496312902602
Two Stage,8000,mme_total_score,1122.452581032413,
Two Stage,8000,mmmu_val_mmmu_acc,0.30556,
Two Stage,8000,mmstar_average,0.3287554228678711,
Two Stage,8000,ocrbench_ocrbench_accuracy,0.502,
Two Stage,8000,seedbench_seed_all,0.4953307392996109,
Two Stage,8000,textvqa_val_exact_match,0.5088400000000001,0.006790286627123755
Two Stage,9000,ai2d_exact_match,0.40900259067357514,0.00884886365109852
Two Stage,9000,average,0.4448373661618862,
Two Stage,9000,average_rank,1.4,
Two Stage,9000,chartqa_relaxed_overall,0.602,0.00979166741164548
Two Stage,9000,docvqa_val_anls,0.6230206474600885,0.006150742264825986
Two Stage,9000,infovqa_val_anls,0.22695214706156083,0.0066522293148095326
Two Stage,9000,mme_total_score,1123.2771108443376,
Two Stage,9000,mmmu_val_mmmu_acc,0.28444,
Two Stage,9000,mmstar_average,0.31337399530900006,
Two Stage,9000,ocrbench_ocrbench_accuracy,0.516,
Two Stage,9000,seedbench_seed_all,0.5044469149527515,
Two Stage,9000,textvqa_val_exact_match,0.5243,0.006775919466531711
Two Stage,10000,ai2d_exact_match,0.4167746113989637,0.008873613803189363
Two Stage,10000,average,0.45019708387432694,
Two Stage,10000,average_rank,1.7,
Two Stage,10000,chartqa_relaxed_overall,0.6008,0.00979663889573671
Two Stage,10000,docvqa_val_anls,0.625559493523932,0.006163808988970625
Two Stage,10000,infovqa_val_anls,0.2484394159425024,0.006960467307383163
Two Stage,10000,mme_total_score,1175.7940176070429,
Two Stage,10000,mmmu_val_mmmu_acc,0.28444,
Two Stage,10000,mmstar_average,0.3201372990396749,
Two Stage,10000,ocrbench_ocrbench_accuracy,0.523,
Two Stage,10000,seedbench_seed_all,0.5092829349638688,
Two Stage,10000,textvqa_val_exact_match,0.52334,0.006775531746371587
Two Stage,11000,ai2d_exact_match,0.4219559585492228,0.008888852746011196
Two Stage,11000,average,0.4544831873326875,
Two Stage,11000,average_rank,1.8,
Two Stage,11000,chartqa_relaxed_overall,0.6128,0.009744149186940382
Two Stage,11000,docvqa_val_anls,0.6332812103643084,0.006140691371662128
Two Stage,11000,infovqa_val_anls,0.23863681037743975,0.006726839163261667
Two Stage,11000,mme_total_score,1205.7752100840335,
Two Stage,11000,mmmu_val_mmmu_acc,0.27667,
Two Stage,11000,mmstar_average,0.3207287756303977,
Two Stage,11000,ocrbench_ocrbench_accuracy,0.542,
Two Stage,11000,seedbench_seed_all,0.5166759310728183,
Two Stage,11000,textvqa_val_exact_match,0.5276,0.006779501480792346
Two Stage,12000,ai2d_exact_match,0.43005181347150256,0.00891065778843896
Two Stage,12000,average,0.4603231834457321,
Two Stage,12000,average_rank,1.6,
Two Stage,12000,chartqa_relaxed_overall,0.612,0.009747841205275417
Two Stage,12000,docvqa_val_anls,0.6395985301346107,0.006113052714689484
Two Stage,12000,infovqa_val_anls,0.2439170659215255,0.006865310277271596
Two Stage,12000,mme_total_score,1157.484293717487,
Two Stage,12000,mmmu_val_mmmu_acc,0.29556,
Two Stage,12000,mmstar_average,0.33444157500257155,
Two Stage,12000,ocrbench_ocrbench_accuracy,0.539,
Two Stage,12000,seedbench_seed_all,0.5193996664813786,
Two Stage,12000,textvqa_val_exact_match,0.52894,0.006785904875622425
Two Stage,13000,ai2d_exact_match,0.4339378238341969,0.00892025987527176
Two Stage,13000,average,0.46490664749620997,
Two Stage,13000,average_rank,1.8,
Two Stage,13000,chartqa_relaxed_overall,0.6224,0.009697675699134625
Two Stage,13000,docvqa_val_anls,0.6462803017356844,0.0061027748005307945
Two Stage,13000,infovqa_val_anls,0.24426636134362278,0.006797247018813037
Two Stage,13000,mme_total_score,1191.0042016806724,
Two Stage,13000,mmmu_val_mmmu_acc,0.3,
Two Stage,13000,mmstar_average,0.33993002648901727,
Two Stage,13000,ocrbench_ocrbench_accuracy,0.545,
Two Stage,13000,seedbench_seed_all,0.5175653140633686,
Two Stage,13000,textvqa_val_exact_match,0.5347799999999999,0.0067635803775740536
Two Stage,14000,ai2d_exact_match,0.44332901554404147,0.008941163900483138
Two Stage,14000,average,0.47155104399726233,
Two Stage,14000,average_rank,1.6,
Two Stage,14000,chartqa_relaxed_overall,0.6268,0.009675026948726469
Two Stage,14000,docvqa_val_anls,0.6586021078894133,0.006060927182389954
Two Stage,14000,infovqa_val_anls,0.2553127836308732,0.0069494972189920795
Two Stage,14000,mme_total_score,1219.156662665066,
Two Stage,14000,mmmu_val_mmmu_acc,0.30444,
Two Stage,14000,mmstar_average,0.32252187023399065,
Two Stage,14000,ocrbench_ocrbench_accuracy,0.564,
Two Stage,14000,seedbench_seed_all,0.5245136186770428,
Two Stage,14000,textvqa_val_exact_match,0.54444,0.006760159556655915
Two Stage,15000,ai2d_exact_match,0.44527202072538863,0.008945084019331405
Two Stage,15000,average,0.47506404899487137,
Two Stage,15000,average_rank,1.8,
Two Stage,15000,chartqa_relaxed_overall,0.628,0.009668701749325345
Two Stage,15000,docvqa_val_anls,0.6614266719753668,0.006055793707421594
Two Stage,15000,infovqa_val_anls,0.25669760055121127,0.006992050333066725
Two Stage,15000,mme_total_score,1198.7210884353742,
Two Stage,15000,mmmu_val_mmmu_acc,0.31222,
Two Stage,15000,mmstar_average,0.34599838005318234,
Two Stage,15000,ocrbench_ocrbench_accuracy,0.553,
Two Stage,15000,seedbench_seed_all,0.5271817676486937,
Two Stage,15000,textvqa_val_exact_match,0.5457799999999999,0.006751174267547695
Two Stage,16000,ai2d_exact_match,0.452720207253886,0.008958830742136086
Two Stage,16000,average,0.4756900312291722,
Two Stage,16000,average_rank,1.7,
Two Stage,16000,chartqa_relaxed_overall,0.6228,0.009695651925812239
Two Stage,16000,docvqa_val_anls,0.6636227651335681,0.006049765989250173
Two Stage,16000,infovqa_val_anls,0.2545981800588258,0.0069034382302033005
Two Stage,16000,mme_total_score,1211.0271108443376,
Two Stage,16000,mmmu_val_mmmu_acc,0.30778,
Two Stage,16000,mmstar_average,0.3441840591332238,
Two Stage,16000,ocrbench_ocrbench_accuracy,0.558,
Two Stage,16000,seedbench_seed_all,0.5251250694830462,
Two Stage,16000,textvqa_val_exact_match,0.55238,0.006735691577574321
Two Stage,17000,ai2d_exact_match,0.45142487046632124,0.008956585653027465
Two Stage,17000,average,0.478877157951835,
Two Stage,17000,average_rank,1.7,
Two Stage,17000,chartqa_relaxed_overall,0.632,0.00964715642305132
Two Stage,17000,docvqa_val_anls,0.6682822523143818,0.006027291004964481
Two Stage,17000,infovqa_val_anls,0.2566899031113292,0.006984361605936137
Two Stage,17000,mme_total_score,1157.7550020008005,
Two Stage,17000,mmmu_val_mmmu_acc,0.31556,
Two Stage,17000,mmstar_average,0.3413821094043331,
Two Stage,17000,ocrbench_ocrbench_accuracy,0.563,
Two Stage,17000,seedbench_seed_all,0.5275152862701501,
Two Stage,17000,textvqa_val_exact_match,0.55404,0.006743665997528143
Two Stage,18000,ai2d_exact_match,0.45077720207253885,0.008955440137395842
Two Stage,18000,average,0.48011960096968553,
Two Stage,18000,average_rank,1.7,
Two Stage,18000,chartqa_relaxed_overall,0.6324,0.00964496273307725
Two Stage,18000,docvqa_val_anls,0.6669938909662756,0.006030949772272312
Two Stage,18000,infovqa_val_anls,0.26114082779542375,0.006997258882360672
Two Stage,18000,mme_total_score,1199.3700480192078,
Two Stage,18000,mmmu_val_mmmu_acc,0.30222,
Two Stage,18000,mmstar_average,0.34746272024423847,
Two Stage,18000,ocrbench_ocrbench_accuracy,0.579,
Two Stage,18000,seedbench_seed_all,0.5271817676486937,
Two Stage,18000,textvqa_val_exact_match,0.5539,0.0067478933611137175
Two Stage,19000,ai2d_exact_match,0.44559585492227977,0.00894572391435784
Two Stage,19000,average,0.48026929849849115,
Two Stage,19000,average_rank,1.9,
Two Stage,19000,chartqa_relaxed_overall,0.6372,0.00961808021316077
Two Stage,19000,docvqa_val_anls,0.6688318561206944,0.006022351017420005
Two Stage,19000,infovqa_val_anls,0.2646354907091152,0.007027671735260141
Two Stage,19000,mme_total_score,1170.1806722689075,
Two Stage,19000,mmmu_val_mmmu_acc,0.29778,
Two Stage,19000,mmstar_average,0.35086201891999,
Two Stage,19000,ocrbench_ocrbench_accuracy,0.574,
Two Stage,19000,seedbench_seed_all,0.5292384658143413,
Two Stage,19000,textvqa_val_exact_match,0.55428,0.006746127657232224
Two Stage,20000,ai2d_exact_match,0.44721502590673573,0.008948865761421001
Two Stage,20000,average,0.4807284005437735,
Two Stage,20000,average_rank,1.8,
Two Stage,20000,chartqa_relaxed_overall,0.632,0.00964715642305132
Two Stage,20000,docvqa_val_anls,0.6696120046502304,0.0060246464192922275
Two Stage,20000,infovqa_val_anls,0.2643335615077466,0.007024758501317731
Two Stage,20000,mme_total_score,1187.4589835934376,
Two Stage,20000,mmmu_val_mmmu_acc,0.29778,
Two Stage,20000,mmstar_average,0.34891710287927624,
Two Stage,20000,ocrbench_ocrbench_accuracy,0.582,
Two Stage,20000,seedbench_seed_all,0.5282379099499722,
Two Stage,20000,textvqa_val_exact_match,0.5564600000000001,0.006728915911338792