kind,file,step,n,k,acc,n_success,n_failure,raw_monotone_adjacent_fraction,raw_col0_is_sample_max_fraction,raw_col0_success_mean,raw_col0_failure_mean,raw_col0_delta_failure_minus_success,raw_col0_auc_failure,lambda_max_success_mean,lambda_max_failure_mean,lambda_max_delta_failure_minus_success,lambda_max_auc_failure,mean8_success_mean,mean8_failure_mean,mean8_delta_failure_minus_success,mean8_auc_failure,tail_mean_5_8_success_mean,tail_mean_5_8_failure_mean,tail_mean_5_8_delta_failure_minus_success,tail_mean_5_8_auc_failure,positive_sum_success_mean,positive_sum_failure_mean,positive_sum_delta_failure_minus_success,positive_sum_auc_failure,positive_count_success_mean,positive_count_failure_mean,positive_count_delta_failure_minus_success,positive_count_auc_failure,spread_success_mean,spread_failure_mean,spread_delta_failure_minus_success,spread_auc_failure,gap12_success_mean,gap12_failure_mean,gap12_delta_failure_minus_success,gap12_auc_failure,lambda_max_corr_token_acc,mean8_corr_token_acc,tail_mean_5_8_corr_token_acc,positive_sum_corr_token_acc,positive_count_corr_token_acc HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_2604_512.npz,2604,512,8,0.015625,8,504,0.6551339285714286,0.62890625,-0.12265677284449339,-0.0977591768882814,0.024897595956211993,0.6889880952380952,-0.1213220115751028,-0.0949796658704087,0.026342345704694112,0.6932043650793651,-0.19951309508178383,-0.11536999984130648,0.08414309524047735,0.9992559523809523,-0.23467964679002762,-0.12418151276171326,0.11049813402831436,1.0,0.0,7.118396313181e-05,7.118396313181e-05,0.5009920634920635,0.0,0.001984126984126984,0.001984126984126984,0.5009920634920635,0.13017353788018227,0.034761710632001126,-0.09541182724818115,0.019345238095238096,0.03395136073231697,0.01004286463712416,-0.023908496095192813,0.12177579365079365,0.11864046173536506,-0.24317640561416,-0.364745516214904,0.01654115981917942,0.01654115981917943 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_5208_512.npz,5208,512,8,0.048828125,25,487,0.7368861607142857,0.798828125,-0.18248083293437958,-0.1252742203170514,0.05720661261732818,0.8788501026694046,-0.18110741019248963,-0.12377287614975867,0.057334534042730964,0.8758110882956879,-0.22203324407339095,-0.16840960289919615,0.0536236411741948,0.9536755646817249,-0.24040259554982185,-0.1877109366994986,0.05269165885032326,0.9394661190965092,0.0,0.0,0.0,0.5,0.0,0.0,0.0,0.5,0.06972571730613708,0.07497160217019078,0.005245884864053696,0.5605749486652978,0.01896007537841797,0.0215270076581952,0.00256693227977723,0.5172073921971253,-0.19170281345239037,-0.3935742986571875,-0.44039154437692224,nan,nan HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_7812_512.npz,7812,512,8,0.15234375,78,434,0.7536272321428571,0.826171875,-0.19744304562799442,-0.09758298332957993,0.09986006229841449,0.9227519792035921,-0.19638217866229704,-0.09583942211473957,0.10054275654755747,0.9273307337823467,-0.2626351442558166,-0.15164301766584318,0.1109921265899734,0.9941214699279215,-0.2882901179866913,-0.1752684197264127,0.11302169826027861,0.9917582417582418,0.0,0.0003272232148648253,0.0003272232148648253,0.5138248847926268,0.0,0.027649769585253458,0.027649769585253458,0.5138248847926268,0.10413952138370429,0.09246484074762525,-0.011674680636079043,0.4651719248493442,0.03829955409925718,0.028275593728860324,-0.010023960370396854,0.4361928394186459,-0.538963951651198,-0.6951799773061379,-0.6975383575513661,-0.06688266082458418,-0.07401140024719328 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_10416_512.npz,10416,512,8,0.1796875,92,420,0.7572544642857143,0.841796875,-0.1734262867020848,-0.0592695716998562,0.1141567150022286,0.9278985507246377,-0.1725775988408081,-0.05791120557031328,0.1146663932704948,0.9305900621118013,-0.22779642522547636,-0.11871804687665038,0.10907837834882597,0.9611024844720497,-0.25038242412974004,-0.1428806266010118,0.10750179752872824,0.9642857142857143,0.0,0.005729037300833235,0.005729037300833235,0.580952380952381,0.0,0.20476190476190476,0.20476190476190476,0.580952380952381,0.09030715536083216,0.09668695457983717,0.006379799219005014,0.555667701863354,0.028749073491148327,0.03182062698594693,0.003071553494798606,0.5320393374741201,-0.4191290312385547,-0.47253422425178293,-0.4888621923983516,-0.0452883997405569,-0.059274922302819555 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_13020_512.npz,13020,512,8,0.30078125,154,358,0.7329799107142857,0.779296875,-0.16317386656331334,-0.012345420176165918,0.15082844638714743,0.9784879924544729,-0.16130138939328179,-0.010260718098612039,0.15104067129466975,0.9784698541681782,-0.20199005053763794,-0.06562561695864545,0.13636443357899247,0.9897337299571937,-0.21928635291610057,-0.08840406447549293,0.13088228844060765,0.9910578248567076,0.0,0.03084314924092586,0.03084314924092586,0.7067039106145251,0.0,0.9134078212290503,0.9134078212290503,0.7067039106145251,0.06808332314294485,0.08949387786655578,0.021410554723610933,0.6710440397591235,0.020334010348842756,0.02894391759471739,0.008609907245874633,0.5919248349415948,-0.6439558752057271,-0.6897349633120721,-0.6989600499840098,-0.14942778693878858,-0.20197511884575872 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_15624_512.npz,15624,512,8,0.333984375,171,341,0.7368861607142857,0.78515625,-0.17926316590140962,0.013238977896144526,0.19250214379755415,0.9800209222959647,-0.1768394878504482,0.015099927341163328,0.19193941519161153,0.9809298417108264,-0.2279172917539989,-0.04059797345319265,0.18731931830080625,0.9898475416302241,-0.24842964750796295,-0.06421948799691395,0.18421015951104902,0.9895731508634734,0.0007992622970837598,0.054435018036423026,0.053635755739339264,0.7755826516437722,0.023391812865497075,1.5073313782991202,1.4839395654336232,0.7767059388451578,0.08114021638005275,0.0924473905291844,0.01130717414913164,0.5924782631064465,0.026074302491693818,0.027355855661720895,0.001281553170027077,0.5126305499819931,-0.7050637096452648,-0.7549696612898014,-0.758163657007401,-0.24676472967716626,-0.2994831724010142 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_18228_512.npz,18228,512,8,0.474609375,243,269,0.7474888392857143,0.818359375,-0.07771555354618448,0.016638744400673956,0.09435429794685843,0.8841617329845335,-0.07614383449056474,0.018023035920062363,0.0941668704106271,0.8879250998210106,-0.14575748546156192,-0.03353973620840138,0.11221774925316054,0.9716523628130402,-0.1721063231313486,-0.05434106856267585,0.11776525456867276,0.9799899031621461,0.00525456639471437,0.050987723279165634,0.045733156884451266,0.749567824743372,0.13580246913580246,1.4981412639405205,1.362338794804718,0.7569645233833586,0.10785400053824455,0.0830327885870487,-0.024821211951195854,0.35938623464439245,0.03951045055418571,0.027345439433070017,-0.01216501112111569,0.4258111891321309,-0.6086543875688578,-0.7665403099919734,-0.786002777751629,-0.3211841461864595,-0.4146342203458471 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_20832_512.npz,20832,512,8,0.45703125,234,278,0.7497209821428571,0.80078125,-0.0847591630423951,0.011107698112080065,0.09586686115447517,0.9046762589928058,-0.08308592252134799,0.012636878445990327,0.09572280096733832,0.9064287031912931,-0.14093293187680603,-0.044163071447564366,0.09676986042924166,0.9825831642378405,-0.16335714651812983,-0.06769531056555371,0.09566183595257612,0.9836438541474513,0.002644224575935648,0.04743396344555085,0.0447897388696152,0.7440432269568961,0.0811965811965812,1.2589928057553956,1.1777962245588145,0.747501998401279,0.0904661258792059,0.09196829576401849,0.0015021698848125958,0.5366168603578676,0.03158770251569426,0.029151334776909496,-0.0024363677387847643,0.49451208264157903,-0.5961668167415688,-0.7490505096842796,-0.7670744302809093,-0.25827536960316083,-0.3352751212871484 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_23436_512.npz,23436,512,8,0.505859375,259,253,0.7444196428571429,0.8125,-0.1396155291305258,-0.002783365376173506,0.13683216375435228,0.9710501014848841,-0.1384992553999928,-0.0009893162803058476,0.13750993911968695,0.9724541028888855,-0.2008695753030298,-0.05231515268090541,0.14855442262212437,0.9922932531628184,-0.22361706499433173,-0.07373835104911058,0.14987871394522115,0.9920032963511224,0.0005239612893938558,0.02692777939243448,0.026403818103040624,0.7254032688815297,0.019305019305019305,0.8932806324110671,0.8739756131060479,0.7251133120698338,0.09569484527981534,0.08370462378894082,-0.011990221490874517,0.4474338822164909,0.0377779275387468,0.025563243349588635,-0.012214684189158165,0.42294016207059687,-0.735475615818423,-0.8331365987869843,-0.8388368318549599,-0.2844985120608491,-0.35566859763323194 HRM,/home/yurenh2/rrm/research/flossing/diag_hrm_step_26040_512.npz,26040,512,8,0.5,256,256,0.748046875,0.787109375,-0.14642834789538028,0.03254939207545249,0.17897773997083277,0.9890289306640625,-0.14456235250236205,0.034372387226426326,0.17893473972878837,0.9896240234375,-0.18957092847483636,-0.025070655147768406,0.16450027332706796,0.997589111328125,-0.21117772247089306,-0.04990981457450516,0.1612679078963879,0.9984893798828125,0.00045363006938714534,0.074183922140719,0.07373029207133186,0.865997314453125,0.01953125,1.94140625,1.921875,0.8662796020507812,0.07883575186588132,0.09741729416225553,0.01858154229637421,0.62774658203125,0.01608559737815085,0.02983991140987996,0.013754314031729109,0.631378173828125,-0.8022434699246608,-0.8493972056528871,-0.8567110926525265,-0.37718525164073874,-0.4879767533856408 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step26041_512.npz,26041,512,8,0.576171875,295,217,0.7438616071428571,0.791015625,-0.03554810737259686,0.034024751214321254,0.06957285858691811,0.9836132156525814,-0.03484145596473462,0.034498983389517714,0.06934043935425233,0.9838475357338123,-0.044594623737682894,0.011831644308724274,0.05642626804640717,0.9900960712333047,-0.04878217898325509,0.002079399892583064,0.050861578875838157,0.9916582051081778,0.002200093488031367,0.11402314361281402,0.11182305012478265,0.9693353120362415,0.1694915254237288,5.539170506912442,5.369678981488713,0.9706006404748887,0.01622369096148759,0.03719716329264318,0.02097347233115559,0.8946653128173084,0.004580460641320037,0.010477446547843793,0.005896985906523756,0.7136608607357651,-0.8221535026414836,-0.8532299277645251,-0.8618572814599218,-0.6425677667973041,-0.7985750358664757 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step52082_512.npz,52082,512,8,0.6484375,332,180,0.7435825892857143,0.78125,-0.0007075830156292839,0.05957649097674423,0.06028407399237352,0.981425702811245,-0.00011202936298378704,0.059987526981987886,0.060099556344971675,0.9824129852744311,-0.00932737177132882,0.03324007580221304,0.04256744757354186,0.993591030789826,-0.01301439359083114,0.02160164021022663,0.034616033801057766,0.9948627844712182,0.011575991871503936,0.26611879217404444,0.2545428003025405,0.9932730923694779,0.9879518072289156,7.916666666666667,6.9287148594377514,0.9850485274431058,0.014868822472832896,0.04419851013889355,0.029329687666060658,0.9461680053547523,0.0048919110970939116,0.01239234626862324,0.007500435171529329,0.7928547523427042,-0.822862756235417,-0.8543835399263785,-0.8502975145711263,-0.83615142839377,-0.8756439805499547 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step78123_512.npz,78123,512,8,0.6875,352,160,0.7522321428571429,0.94921875,-0.0022565727597132286,0.08176288979593664,0.08401946255564988,0.9937144886363637,-0.002104297534184628,0.08205510303378105,0.08415940056796568,0.99375,-0.03085258081190225,0.04898583621179568,0.07983841702369793,0.9991299715909091,-0.03740866408387236,0.03495748526038369,0.07236614934425606,0.9993607954545455,0.011536654059641065,0.39188668969436546,0.3803500356347244,0.9991299715909091,0.6619318181818182,8.0,7.338068181818182,0.9900568181818182,0.037154979946411586,0.05358391968184151,0.016428939735429922,0.8060191761363636,0.026502143868418152,0.015829400252550842,-0.01067274361586731,0.2559303977272727,-0.8695160653352085,-0.9167732333138554,-0.9212713093750954,-0.9333667142066921,-0.916788261375625 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step104164_512.npz,104164,512,8,0.7109375,364,148,0.7659040178571429,0.873046875,0.0007209903823832564,0.09478743761979244,0.09406644723740919,0.9850942975942976,0.0011589818968986748,0.0948834198753576,0.09372443797845893,0.9852242352242352,-0.013257209616115657,0.05609436892523632,0.06935157854135197,0.9912013662013662,-0.018433471481510245,0.04002377992288235,0.05845725140439259,0.9914241164241164,0.024264690904521637,0.44875495140189053,0.4244902604973689,0.9912013662013662,1.0631868131868132,8.0,6.936813186813187,0.9766483516483516,0.02201517710918679,0.06216927877048383,0.04015410166129704,0.9606660231660231,0.008753806905887968,0.020252479617861478,0.01149867271197351,0.8213171963171964,-0.8714207860201784,-0.8978503025935065,-0.9018662195261188,-0.9164290683745636,-0.8552081309221397 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step130205_512.npz,130205,512,8,0.755859375,387,125,0.7661830357142857,0.83203125,0.013444696512909148,0.10679112273454666,0.09334642622163751,0.988857881136951,0.014031398803655426,0.10683381146192551,0.09280241265827009,0.9889198966408269,0.0006696076976612102,0.05997022696118802,0.05930061926352681,0.9935503875968992,-0.004693869635777962,0.04096000522933901,0.04565387486511697,0.9943152454780362,0.04017261892318711,0.47976181568950416,0.439589196766317,0.9935503875968992,2.4108527131782944,8.0,5.589147286821706,0.9521963824289406,0.021535266655820777,0.07427249775826932,0.05273723110244854,0.9726511627906976,0.007057571094765433,0.02309795269370079,0.016040381598935356,0.8932093023255814,-0.868494410453853,-0.8995673015890842,-0.9101679267135595,-0.9091943845695494,-0.7232326485538275 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step156246_512.npz,156246,512,8,0.7578125,388,124,0.8465401785714286,0.984375,0.033355438992845106,0.1080104663006721,0.074655027307827,0.9934527768540073,0.03340256920781724,0.10808430672172577,0.07468173751390852,0.9935359161955437,-0.01719525050584332,0.059510113856841566,0.07670536436268488,0.9990646824077153,-0.03258687625807819,0.03992759636434306,0.07251447262242125,0.9987944795477219,0.0501136147264783,0.47608091085473253,0.42596729612825424,0.9990646824077153,1.7268041237113403,8.0,6.27319587628866,0.9806701030927835,0.07044461364565689,0.07696695457167563,0.006522340926018735,0.5740563684735617,0.03767048126359648,0.024864713691415324,-0.012805767572181152,0.30377036913867644,-0.8015386582153512,-0.8887892447157182,-0.8908349686685592,-0.9311284896491179,-0.8411922875634292 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step182287_512.npz,182287,512,8,0.7421875,380,132,0.7837611607142857,0.9296875,0.00821161610291902,0.10131858266664273,0.0931069665637237,0.9476076555023923,0.008431412303494461,0.10132696061874881,0.09289554831525434,0.9476275917065391,-0.018691345271909503,0.049928791549256966,0.06862013682116647,0.993122009569378,-0.026891200006043378,0.029759585490286223,0.0566507854963296,0.993421052631579,0.027419095844602212,0.3994350857048465,0.37201598986024426,0.993122009569378,0.8973684210526316,7.992424242424242,7.095055821371611,0.9867125199362041,0.03768573965873513,0.07997999362255954,0.04229425396382441,0.8919258373205742,0.019669575117656057,0.027337144778081864,0.007667569660425807,0.7587121212121212,-0.7443356021278564,-0.8907098916862968,-0.9075392398447194,-0.9063416990478439,-0.8813795117907826 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step208328_512.npz,208328,512,8,0.75,384,128,0.8138950892857143,0.970703125,0.03753090985757505,0.10676543856970966,0.06923452871213462,0.9824422200520834,0.037651085844269495,0.10677664534887299,0.0691255595046035,0.9825439453125,-0.003334924222756793,0.0556086836418217,0.058943607864578494,0.997314453125,-0.015420041531266785,0.03501016539212287,0.050430206923389655,0.9977620442708334,0.0587247395355727,0.4448694691345736,0.38614472959900087,0.997314453125,2.3385416666666665,8.0,5.661458333333334,0.97265625,0.05609253943835787,0.08039409609409631,0.024301556655738445,0.8315836588541666,0.029487703329541166,0.026957579655572772,-0.0025301236739683937,0.4844767252604167,-0.7847679828439686,-0.9025430240366568,-0.9116696180830379,-0.918178990916473,-0.8241555473543875 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step234369_512.npz,234369,512,8,0.7734375,396,116,0.7837611607142857,0.943359375,0.017852102687761037,0.10551282866247769,0.08766072597471665,0.9871125043538836,0.018100257435352516,0.10551282866247769,0.08741257122712517,0.9871125043538836,-0.011827684605397524,0.05244761205414824,0.06427529665954576,0.9948624172762104,-0.020207434739923615,0.03131334408957126,0.05152077882949488,0.995276036224312,0.03539385316928405,0.4195808964331859,0.38418704326390185,0.9948624172762104,1.4595959595959596,8.0,6.540404040404041,0.976010101010101,0.04073868896878162,0.08256442746115399,0.041825738492372366,0.9344740508533612,0.022704324246853612,0.026842519994182832,0.00413819574732922,0.6134839777081157,-0.8095679410757006,-0.8841140003061905,-0.8897475061573502,-0.9111627943782784,-0.8264057387186906 TRM,/home/yurenh2/rrm/research/flossing/diag_trm_singleGPU_step260410_512.npz,260410,512,8,0.76953125,394,118,0.7299107142857143,0.767578125,0.012635910749513134,0.10288177159125522,0.09024586084174209,0.9893530069689409,0.013151870022697326,0.10296485964524543,0.0898129896225481,0.9894175341994321,0.0016685908707722002,0.05065993657996641,0.04899134570919421,0.9931170954142648,-0.002553942017630222,0.030341437701096412,0.032895379718726636,0.9938484040264992,0.030020373667639433,0.40529236062114143,0.375271986953502,0.9931170954142648,3.182741116751269,7.991525423728813,4.808784306977544,0.9728770541168373,0.01786690075157378,0.08103766449001003,0.06317076373843625,0.9816742665404801,0.006782306742966769,0.028344342895483567,0.021562036152516798,0.9238363589434742,-0.8797240829367476,-0.9146835924338959,-0.9119410149316228,-0.9168566073790785,-0.6899483781164985