summaryrefslogtreecommitdiff
path: root/results/diag_nuis_low_rho0p2_res0_s0.json
blob: 7aa42f965b17818a94f126530865bf8f1a835c7e (plain)
1
{"args": {"mode": "sdil", "dataset": "mnist", "depth": 3, "width": 256, "act": "tanh", "residual": 0, "epochs": 15, "batch_size": 128, "eta": 0.05, "eta_A": 0.02, "eta_P": 0.002, "momentum": 0.9, "w_scale": 1.0, "a_scale": 1.0, "pert_sigma": 0.01, "pert_every": 4, "pert_ndirs": 8, "use_residual": 0, "learn_A": 1, "learn_P": 1, "p_neutral": 1, "p_warmup_steps": 200, "p_warmup_eta": 0.05, "nuis_rho": 0.2, "predictor_mode": "diagonal", "normalize_delta": 0, "settle_steps": 0, "kappa": 0.0, "feedback": "error", "seed": 0, "device": "cuda", "log_every": 100, "max_steps": 0, "probe_bs": 512, "outdir": "results", "tag": "diag_nuis_low_rho0p2_res0_s0", "n_in": 784}, "provenance": {"git_commit": "54633b2e0f51a8f48d4ba627d778c87927f54ca1", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.3603768348693848, "cos_r_negg": [-0.01658112369477749, -0.02675408124923706, 0.03309158980846405], "cos_apical_negg": [-0.01647482067346573, -0.02632959932088852, 0.029919130727648735], "cos_Ac_negg": [-0.016581138595938683, -0.02675417996942997, 0.03309144824743271], "r_norm": [4.897111415863037, 4.8262786865234375, 4.823426723480225], "ldr": {"dL_sdil": -0.0021238327026367188, "dL_bp": -0.21677780151367188, "ratio": 0.009797279462227462}}, {"step": 100, "epoch": 0, "train_loss": 0.354571670293808, "cos_r_negg": [0.40948987007141113, 0.4940800368785858, 0.7221688032150269], "cos_apical_negg": [0.1771671026945114, 0.2853664755821228, 0.6299550533294678], "cos_Ac_negg": [0.4092680811882019, 0.4940105378627777, 0.72206711769104], "r_norm": [1.181720495223999, 1.1689503192901611, 1.1525987386703491]}, {"step": 200, "epoch": 0, "train_loss": 0.4218946099281311, "cos_r_negg": [0.4224170446395874, 0.4905916750431061, 0.7656741738319397], "cos_apical_negg": [0.12543192505836487, 0.20883363485336304, 0.679609477519989], "cos_Ac_negg": [0.42178788781166077, 0.4902670979499817, 0.7654527425765991], "r_norm": [0.9258381128311157, 0.9121930599212646, 0.9058879017829895]}, {"step": 300, "epoch": 0, "train_loss": 0.41522276401519775, "cos_r_negg": [0.4006715416908264, 0.46267831325531006, 0.8000354766845703], "cos_apical_negg": [0.12734946608543396, 0.25871264934539795, 0.6939327716827393], "cos_Ac_negg": [0.4005220830440521, 0.4625197649002075, 0.7999415993690491], "r_norm": [0.7790969610214233, 0.7675883769989014, 0.7631418704986572]}, {"step": 400, "epoch": 0, "train_loss": 0.22118234634399414, "cos_r_negg": [0.41696903109550476, 0.4606304168701172, 0.6738429069519043], "cos_apical_negg": [0.11484207212924957, 0.1932595819234848, 0.602165162563324], "cos_Ac_negg": [0.4168544411659241, 0.4607000946998596, 0.6736845970153809], "r_norm": [0.6956605911254883, 0.6850021481513977, 0.6820066571235657]}, {"epoch_end": 0, "step": 469, "test_acc": 0.9206, "test_loss": 0.311843473815918}, {"step": 500, "epoch": 1, "train_loss": 0.3052837550640106, "cos_r_negg": [0.3626522123813629, 0.4173111617565155, 0.5963093042373657], "cos_apical_negg": [0.07664995640516281, 0.18701238930225372, 0.6576422452926636], "cos_Ac_negg": [0.36269712448120117, 0.41732293367385864, 0.5960298776626587], "r_norm": [0.6405333280563354, 0.6288838386535645, 0.6260596513748169], "ldr": {"dL_sdil": -0.014568626880645752, "dL_bp": -0.014336705207824707, "ratio": 1.0161767762857024}}, {"step": 600, "epoch": 1, "train_loss": 0.16827498376369476, "cos_r_negg": [0.37631213665008545, 0.44294190406799316, 0.5625686645507812], "cos_apical_negg": [0.10781636089086533, 0.1685357689857483, 0.5388386845588684], "cos_Ac_negg": [0.3762630224227905, 0.442885160446167, 0.5623227953910828], "r_norm": [0.6341857314109802, 0.6270827651023865, 0.624110758304596]}, {"step": 700, "epoch": 1, "train_loss": 0.21706843376159668, "cos_r_negg": [0.38124769926071167, 0.43224507570266724, 0.6496527194976807], "cos_apical_negg": [0.1277361810207367, 0.16795147955417633, 0.5623214244842529], "cos_Ac_negg": [0.3811199963092804, 0.4322311282157898, 0.6495639085769653], "r_norm": [0.6162890195846558, 0.6032637357711792, 0.6019018888473511]}, {"step": 800, "epoch": 1, "train_loss": 0.229483500123024, "cos_r_negg": [0.3993667960166931, 0.4717196226119995, 0.6010404825210571], "cos_apical_negg": [0.10239509493112564, 0.16297876834869385, 0.546845555305481], "cos_Ac_negg": [0.3992767930030823, 0.4717075824737549, 0.6010348796844482], "r_norm": [0.5413546562194824, 0.5288864970207214, 0.5284166932106018]}, {"step": 900, "epoch": 1, "train_loss": 0.32718586921691895, "cos_r_negg": [0.39117228984832764, 0.4628865420818329, 0.6911308765411377], "cos_apical_negg": [0.111225426197052, 0.17997516691684723, 0.6296118497848511], "cos_Ac_negg": [0.39112961292266846, 0.4628659784793854, 0.6910473108291626], "r_norm": [0.5905939936637878, 0.579919695854187, 0.5788048505783081]}, {"epoch_end": 1, "step": 938, "test_acc": 0.9394, "test_loss": 0.23626662445068358}, {"step": 1000, "epoch": 2, "train_loss": 0.07668660581111908, "cos_r_negg": [0.3927341103553772, 0.5061125755310059, 0.5423319339752197], "cos_apical_negg": [0.09865610301494598, 0.18970930576324463, 0.4494820237159729], "cos_Ac_negg": [0.3927924335002899, 0.5060699582099915, 0.5423330664634705], "r_norm": [0.5557097792625427, 0.5447742938995361, 0.5418888330459595], "ldr": {"dL_sdil": -0.013394027948379517, "dL_bp": -0.013386756181716919, "ratio": 1.0005432060286965}}, {"step": 1100, "epoch": 2, "train_loss": 0.3958793878555298, "cos_r_negg": [0.3528103530406952, 0.4424353539943695, 0.5622879862785339], "cos_apical_negg": [0.09641429036855698, 0.1834137737751007, 0.5174195170402527], "cos_Ac_negg": [0.35279470682144165, 0.44244295358657837, 0.5621176958084106], "r_norm": [0.5224853754043579, 0.5165130496025085, 0.5115327835083008]}, {"step": 1200, "epoch": 2, "train_loss": 0.28291386365890503, "cos_r_negg": [0.36777395009994507, 0.45954036712646484, 0.629369854927063], "cos_apical_negg": [0.08748626708984375, 0.20882287621498108, 0.5821536779403687], "cos_Ac_negg": [0.36777278780937195, 0.45949238538742065, 0.6293504238128662], "r_norm": [0.48233214020729065, 0.4738706350326538, 0.4739091396331787]}, {"step": 1300, "epoch": 2, "train_loss": 0.23181961476802826, "cos_r_negg": [0.3398638963699341, 0.4273473620414734, 0.49137306213378906], "cos_apical_negg": [0.07635918259620667, 0.1942366063594818, 0.5700696706771851], "cos_Ac_negg": [0.3398456275463104, 0.4272955060005188, 0.4912376403808594], "r_norm": [0.5011234283447266, 0.4903164505958557, 0.49216747283935547]}, {"step": 1400, "epoch": 2, "train_loss": 0.24559831619262695, "cos_r_negg": [0.3553113639354706, 0.4113725423812866, 0.48809611797332764], "cos_apical_negg": [0.08183115720748901, 0.16185510158538818, 0.5142189860343933], "cos_Ac_negg": [0.3552836775779724, 0.41137421131134033, 0.4880104064941406], "r_norm": [0.4710192084312439, 0.46069324016571045, 0.46100401878356934]}, {"epoch_end": 2, "step": 1407, "test_acc": 0.9468, "test_loss": 0.21931175231933595}, {"step": 1500, "epoch": 3, "train_loss": 0.15713244676589966, "cos_r_negg": [0.3175938129425049, 0.39262649416923523, 0.4930814504623413], "cos_apical_negg": [0.09748604893684387, 0.15574148297309875, 0.5159343481063843], "cos_Ac_negg": [0.317560076713562, 0.3925871253013611, 0.49292829632759094], "r_norm": [0.4714347720146179, 0.46116870641708374, 0.4615328311920166], "ldr": {"dL_sdil": -0.010026350617408752, "dL_bp": -0.010028526186943054, "ratio": 0.9997830618882828}}, {"step": 1600, "epoch": 3, "train_loss": 0.14471080899238586, "cos_r_negg": [0.3618842661380768, 0.43481770157814026, 0.5564713478088379], "cos_apical_negg": [0.053075097501277924, 0.146455779671669, 0.5378377437591553], "cos_Ac_negg": [0.36187559366226196, 0.43482112884521484, 0.5563569068908691], "r_norm": [0.45724189281463623, 0.4426780045032501, 0.44519713521003723]}, {"step": 1700, "epoch": 3, "train_loss": 0.1199292540550232, "cos_r_negg": [0.3346858024597168, 0.41836243867874146, 0.5202815532684326], "cos_apical_negg": [0.086707204580307, 0.21298858523368835, 0.5306088924407959], "cos_Ac_negg": [0.3346349596977234, 0.4182862341403961, 0.5201213359832764], "r_norm": [0.4878188669681549, 0.4770936965942383, 0.4752395451068878]}, {"step": 1800, "epoch": 3, "train_loss": 0.06115349382162094, "cos_r_negg": [0.3116943836212158, 0.37237071990966797, 0.4174896478652954], "cos_apical_negg": [0.09862097352743149, 0.17975583672523499, 0.4274527430534363], "cos_Ac_negg": [0.3116356432437897, 0.37228354811668396, 0.41747552156448364], "r_norm": [0.5187429189682007, 0.5102837681770325, 0.5100627541542053]}, {"epoch_end": 3, "step": 1876, "test_acc": 0.9507, "test_loss": 0.19927916564941406}, {"step": 1900, "epoch": 4, "train_loss": 0.08558028936386108, "cos_r_negg": [0.3055054545402527, 0.3636631369590759, 0.5528383255004883], "cos_apical_negg": [0.06964286416769028, 0.16293182969093323, 0.4555685818195343], "cos_Ac_negg": [0.3055107593536377, 0.3636547923088074, 0.552701473236084], "r_norm": [0.39640918374061584, 0.38864558935165405, 0.3887024521827698]}, {"step": 2000, "epoch": 4, "train_loss": 0.20863178372383118, "cos_r_negg": [0.2909287214279175, 0.36311227083206177, 0.4310835003852844], "cos_apical_negg": [0.08341501653194427, 0.1085396558046341, 0.4226093590259552], "cos_Ac_negg": [0.2908599376678467, 0.36305713653564453, 0.43094033002853394], "r_norm": [0.4183720052242279, 0.40805768966674805, 0.40764540433883667], "ldr": {"dL_sdil": -0.008532971143722534, "dL_bp": -0.010096043348312378, "ratio": 0.8451797252979186}}, {"step": 2100, "epoch": 4, "train_loss": 0.11507221311330795, "cos_r_negg": [0.3011534810066223, 0.3769491910934448, 0.45562195777893066], "cos_apical_negg": [0.07453006505966187, 0.11422134935855865, 0.4654961824417114], "cos_Ac_negg": [0.3011004626750946, 0.3769018054008484, 0.4554436206817627], "r_norm": [0.4303979277610779, 0.4184738099575043, 0.42080533504486084]}, {"step": 2200, "epoch": 4, "train_loss": 0.07536563277244568, "cos_r_negg": [0.2964628040790558, 0.3720691502094269, 0.4125217795372009], "cos_apical_negg": [0.054394520819187164, 0.12011854350566864, 0.4078434705734253], "cos_Ac_negg": [0.2964456379413605, 0.3720472455024719, 0.4124046564102173], "r_norm": [0.39150893688201904, 0.3806436061859131, 0.3817109763622284]}, {"step": 2300, "epoch": 4, "train_loss": 0.3441089987754822, "cos_r_negg": [0.314182311296463, 0.395413339138031, 0.48691341280937195], "cos_apical_negg": [0.0562342144548893, 0.15732164680957794, 0.5054457187652588], "cos_Ac_negg": [0.31417709589004517, 0.39541733264923096, 0.4867471158504486], "r_norm": [0.37638723850250244, 0.3671910762786865, 0.36852917075157166]}, {"epoch_end": 4, "step": 2345, "test_acc": 0.949, "test_loss": 0.2120886833190918}, {"step": 2400, "epoch": 5, "train_loss": 0.24819013476371765, "cos_r_negg": [0.29006025195121765, 0.38233426213264465, 0.4226503372192383], "cos_apical_negg": [0.05794958770275116, 0.16952604055404663, 0.43387433886528015], "cos_Ac_negg": [0.2900320291519165, 0.3822912573814392, 0.42244622111320496], "r_norm": [0.3746529519557953, 0.3633244037628174, 0.36511343717575073]}, {"step": 2500, "epoch": 5, "train_loss": 0.06795045733451843, "cos_r_negg": [0.28351694345474243, 0.36523333191871643, 0.4373854398727417], "cos_apical_negg": [0.06256628781557083, 0.16245101392269135, 0.44031962752342224], "cos_Ac_negg": [0.2835214138031006, 0.3652125597000122, 0.4372408092021942], "r_norm": [0.360385537147522, 0.3505025804042816, 0.3515985906124115], "ldr": {"dL_sdil": -0.007574334740638733, "dL_bp": -0.008766129612922668, "ratio": 0.8640454881562508}}, {"step": 2600, "epoch": 5, "train_loss": 0.1351993978023529, "cos_r_negg": [0.2961367964744568, 0.3669757843017578, 0.4170069098472595], "cos_apical_negg": [0.03270693123340607, 0.17077741026878357, 0.39031481742858887], "cos_Ac_negg": [0.29616183042526245, 0.36695927381515503, 0.4168417453765869], "r_norm": [0.3558770418167114, 0.34683164954185486, 0.3465604782104492]}, {"step": 2700, "epoch": 5, "train_loss": 0.1533799171447754, "cos_r_negg": [0.30687782168388367, 0.3699445128440857, 0.46407997608184814], "cos_apical_negg": [0.05205798149108887, 0.16318313777446747, 0.41084709763526917], "cos_Ac_negg": [0.3069007396697998, 0.36995577812194824, 0.46401360630989075], "r_norm": [0.3477948009967804, 0.3397001624107361, 0.33910202980041504]}, {"step": 2800, "epoch": 5, "train_loss": 0.23239493370056152, "cos_r_negg": [0.28342458605766296, 0.3175637125968933, 0.372060626745224], "cos_apical_negg": [0.05275917798280716, 0.09765138477087021, 0.31998056173324585], "cos_Ac_negg": [0.2833825945854187, 0.3175467848777771, 0.3720134496688843], "r_norm": [0.3499724268913269, 0.34066063165664673, 0.340814471244812]}, {"epoch_end": 5, "step": 2814, "test_acc": 0.9519, "test_loss": 0.20544991683959962}, {"step": 2900, "epoch": 6, "train_loss": 0.10849648714065552, "cos_r_negg": [0.2878199517726898, 0.3436349630355835, 0.47417017817497253], "cos_apical_negg": [0.05432596802711487, 0.11443020403385162, 0.3455365300178528], "cos_Ac_negg": [0.28781020641326904, 0.34365424513816833, 0.4741502106189728], "r_norm": [0.35208290815353394, 0.34019559621810913, 0.34312278032302856]}, {"step": 3000, "epoch": 6, "train_loss": 0.3311569392681122, "cos_r_negg": [0.28052449226379395, 0.35894688963890076, 0.40502479672431946], "cos_apical_negg": [0.035240545868873596, 0.14896342158317566, 0.42349112033843994], "cos_Ac_negg": [0.2805261015892029, 0.3588980436325073, 0.40476810932159424], "r_norm": [0.35302913188934326, 0.3448631763458252, 0.3449799418449402], "ldr": {"dL_sdil": -0.006956323981285095, "dL_bp": -0.00735849142074585, "ratio": 0.9453464825239966}}, {"step": 3100, "epoch": 6, "train_loss": 0.18019261956214905, "cos_r_negg": [0.2721954882144928, 0.33980417251586914, 0.4479500651359558], "cos_apical_negg": [0.02852373942732811, 0.17295899987220764, 0.35839468240737915], "cos_Ac_negg": [0.27219918370246887, 0.33978500962257385, 0.4477222263813019], "r_norm": [0.35866016149520874, 0.351005882024765, 0.34970420598983765]}, {"step": 3200, "epoch": 6, "train_loss": 0.199020117521286, "cos_r_negg": [0.25762081146240234, 0.3294498026371002, 0.42619872093200684], "cos_apical_negg": [0.04191029444336891, 0.1414119303226471, 0.40176644921302795], "cos_Ac_negg": [0.25764650106430054, 0.3294360637664795, 0.4260782301425934], "r_norm": [0.3657132685184479, 0.3539370894432068, 0.3553954064846039]}, {"epoch_end": 6, "step": 3283, "test_acc": 0.9549, "test_loss": 0.187177938079834}, {"step": 3300, "epoch": 7, "train_loss": 0.13309548795223236, "cos_r_negg": [0.27109068632125854, 0.3110350966453552, 0.3231617212295532], "cos_apical_negg": [0.023300375789403915, 0.11186415702104568, 0.3350473642349243], "cos_Ac_negg": [0.271141916513443, 0.3110065162181854, 0.3226667046546936], "r_norm": [0.3055375814437866, 0.29615113139152527, 0.2990162968635559]}, {"step": 3400, "epoch": 7, "train_loss": 0.25961431860923767, "cos_r_negg": [0.2954622507095337, 0.3442643880844116, 0.3928048610687256], "cos_apical_negg": [0.03685184568166733, 0.1230539083480835, 0.39098864793777466], "cos_Ac_negg": [0.29547008872032166, 0.34424111247062683, 0.3924611210823059], "r_norm": [0.31034815311431885, 0.30178070068359375, 0.3029753267765045]}, {"step": 3500, "epoch": 7, "train_loss": 0.11480915546417236, "cos_r_negg": [0.2152632176876068, 0.28108400106430054, 0.31355172395706177], "cos_apical_negg": [0.031719353049993515, 0.08576257526874542, 0.28526777029037476], "cos_Ac_negg": [0.21533070504665375, 0.28105199337005615, 0.3134344816207886], "r_norm": [0.3102531433105469, 0.302903413772583, 0.3034309148788452], "ldr": {"dL_sdil": -0.004531398415565491, "dL_bp": -0.006715118885040283, "ratio": 0.674805389620188}}, {"step": 3600, "epoch": 7, "train_loss": 0.0902668908238411, "cos_r_negg": [0.2389834225177765, 0.29262611269950867, 0.3521190881729126], "cos_apical_negg": [0.04988425225019455, 0.08719882369041443, 0.36276113986968994], "cos_Ac_negg": [0.2389843910932541, 0.29260218143463135, 0.3519917130470276], "r_norm": [0.3253469467163086, 0.313697874546051, 0.31717634201049805]}, {"step": 3700, "epoch": 7, "train_loss": 0.08515805006027222, "cos_r_negg": [0.2504104971885681, 0.32089632749557495, 0.3823220133781433], "cos_apical_negg": [0.024581369012594223, 0.08212266117334366, 0.3741797208786011], "cos_Ac_negg": [0.250422865152359, 0.32092148065567017, 0.3821236789226532], "r_norm": [0.33187663555145264, 0.3216373920440674, 0.3234902024269104]}, {"epoch_end": 7, "step": 3752, "test_acc": 0.9547, "test_loss": 0.19444280395507813}, {"step": 3800, "epoch": 8, "train_loss": 0.17694689333438873, "cos_r_negg": [0.25899192690849304, 0.31005844473838806, 0.3392488956451416], "cos_apical_negg": [0.03858417272567749, 0.0742853581905365, 0.3315388560295105], "cos_Ac_negg": [0.25906404852867126, 0.31005531549453735, 0.3390854001045227], "r_norm": [0.3168758153915405, 0.30747151374816895, 0.30865925550460815]}, {"step": 3900, "epoch": 8, "train_loss": 0.22353720664978027, "cos_r_negg": [0.22583681344985962, 0.2957781255245209, 0.31162646412849426], "cos_apical_negg": [0.029736997559666634, 0.1047627180814743, 0.21787340939044952], "cos_Ac_negg": [0.2258198857307434, 0.2957325577735901, 0.31153881549835205], "r_norm": [0.3253486156463623, 0.31517934799194336, 0.3172367215156555]}, {"step": 4000, "epoch": 8, "train_loss": 0.17737451195716858, "cos_r_negg": [0.2658914029598236, 0.31257694959640503, 0.3707655668258667], "cos_apical_negg": [0.02327217161655426, 0.09213034063577652, 0.3644936680793762], "cos_Ac_negg": [0.26588621735572815, 0.31257036328315735, 0.3706303536891937], "r_norm": [0.316942423582077, 0.30696213245391846, 0.3082296550273895], "ldr": {"dL_sdil": -0.005902528762817383, "dL_bp": -0.007494226098060608, "ratio": 0.7876101795680901}}, {"step": 4100, "epoch": 8, "train_loss": 0.10142381489276886, "cos_r_negg": [0.24553251266479492, 0.29517728090286255, 0.3253936171531677], "cos_apical_negg": [0.05160326510667801, 0.1083495244383812, 0.3625643253326416], "cos_Ac_negg": [0.24549433588981628, 0.2951638698577881, 0.3251679837703705], "r_norm": [0.312822550535202, 0.3023613691329956, 0.30564385652542114]}, {"step": 4200, "epoch": 8, "train_loss": 0.2199912816286087, "cos_r_negg": [0.21222490072250366, 0.2799052596092224, 0.3014346659183502], "cos_apical_negg": [0.028287524357438087, 0.08523555099964142, 0.2326328158378601], "cos_Ac_negg": [0.21220120787620544, 0.27988097071647644, 0.30123424530029297], "r_norm": [0.29305383563041687, 0.2860552668571472, 0.2874717116355896]}, {"epoch_end": 8, "step": 4221, "test_acc": 0.9564, "test_loss": 0.18425435104370116}, {"step": 4300, "epoch": 9, "train_loss": 0.06437113136053085, "cos_r_negg": [0.2358243763446808, 0.28641313314437866, 0.35599151253700256], "cos_apical_negg": [0.013880165293812752, 0.11917011439800262, 0.40688377618789673], "cos_Ac_negg": [0.23583494126796722, 0.28636664152145386, 0.3556973934173584], "r_norm": [0.31460991501808167, 0.3027815818786621, 0.3047682046890259]}, {"step": 4400, "epoch": 9, "train_loss": 0.06619978696107864, "cos_r_negg": [0.22984090447425842, 0.28721553087234497, 0.3278498947620392], "cos_apical_negg": [-0.011740047484636307, 0.06577267497777939, 0.32726940512657166], "cos_Ac_negg": [0.22985759377479553, 0.2872340679168701, 0.32772067189216614], "r_norm": [0.27921512722969055, 0.27059951424598694, 0.2719123363494873]}, {"step": 4500, "epoch": 9, "train_loss": 0.21131262183189392, "cos_r_negg": [0.2579497694969177, 0.3100973963737488, 0.30231156945228577], "cos_apical_negg": [0.04233098775148392, 0.08674807846546173, 0.28760814666748047], "cos_Ac_negg": [0.25795358419418335, 0.310102254152298, 0.30227792263031006], "r_norm": [0.3042036294937134, 0.2929670512676239, 0.29672420024871826], "ldr": {"dL_sdil": -0.004691421985626221, "dL_bp": -0.006736353039741516, "ratio": 0.6964335090439734}}, {"step": 4600, "epoch": 9, "train_loss": 0.05833065137267113, "cos_r_negg": [0.23096181452274323, 0.28671765327453613, 0.3423420190811157], "cos_apical_negg": [0.03894319757819176, 0.08784064650535583, 0.22024700045585632], "cos_Ac_negg": [0.2309252768754959, 0.28670844435691833, 0.34227150678634644], "r_norm": [0.2815912961959839, 0.2706446051597595, 0.2737721800804138]}, {"epoch_end": 9, "step": 4690, "test_acc": 0.9552, "test_loss": 0.19371358871459962}, {"step": 4700, "epoch": 10, "train_loss": 0.15056955814361572, "cos_r_negg": [0.23341451585292816, 0.275524377822876, 0.30159619450569153], "cos_apical_negg": [0.045774202793836594, 0.07596422731876373, 0.25025731325149536], "cos_Ac_negg": [0.23339876532554626, 0.27553778886795044, 0.3014761209487915], "r_norm": [0.29377245903015137, 0.28158220648765564, 0.28575533628463745]}, {"step": 4800, "epoch": 10, "train_loss": 0.09141849726438522, "cos_r_negg": [0.22750751674175262, 0.2827100157737732, 0.3121715784072876], "cos_apical_negg": [0.040812667459249496, 0.06755371391773224, 0.2866986393928528], "cos_Ac_negg": [0.22749042510986328, 0.2826702296733856, 0.3121235966682434], "r_norm": [0.2803487777709961, 0.2702489197254181, 0.274594247341156]}, {"step": 4900, "epoch": 10, "train_loss": 0.0935787707567215, "cos_r_negg": [0.23496471345424652, 0.27388620376586914, 0.3047889769077301], "cos_apical_negg": [0.03285589814186096, 0.08217950165271759, 0.22296622395515442], "cos_Ac_negg": [0.2349862903356552, 0.2738833725452423, 0.30466389656066895], "r_norm": [0.27926450967788696, 0.26818063855171204, 0.2710397243499756]}, {"step": 5000, "epoch": 10, "train_loss": 0.038625895977020264, "cos_r_negg": [0.23448936641216278, 0.29541683197021484, 0.3449649512767792], "cos_apical_negg": [0.026775607839226723, 0.07217676937580109, 0.31250983476638794], "cos_Ac_negg": [0.23451963067054749, 0.295479953289032, 0.3446601927280426], "r_norm": [0.28283730149269104, 0.2720959186553955, 0.2745661735534668], "ldr": {"dL_sdil": -0.005496546626091003, "dL_bp": -0.009115532040596008, "ratio": 0.6029869240338513}}, {"step": 5100, "epoch": 10, "train_loss": 0.21542933583259583, "cos_r_negg": [0.22495007514953613, 0.27443286776542664, 0.28965920209884644], "cos_apical_negg": [0.0038940533995628357, 0.06687778979539871, 0.28868257999420166], "cos_Ac_negg": [0.22494767606258392, 0.2744307219982147, 0.28959786891937256], "r_norm": [0.2665850520133972, 0.2567015588283539, 0.2595881223678589]}, {"epoch_end": 10, "step": 5159, "test_acc": 0.9589, "test_loss": 0.18391245193481445}, {"step": 5200, "epoch": 11, "train_loss": 0.03786221891641617, "cos_r_negg": [0.22902637720108032, 0.27354294061660767, 0.3025188446044922], "cos_apical_negg": [0.051290445029735565, 0.06759743392467499, 0.20606330037117004], "cos_Ac_negg": [0.22904717922210693, 0.2735593914985657, 0.3024744987487793], "r_norm": [0.26560336351394653, 0.25717055797576904, 0.2590850591659546]}, {"step": 5300, "epoch": 11, "train_loss": 0.10808123648166656, "cos_r_negg": [0.22896569967269897, 0.2585393786430359, 0.2974613308906555], "cos_apical_negg": [0.0072798095643520355, 0.06636877357959747, 0.2188795506954193], "cos_Ac_negg": [0.22902745008468628, 0.2586253881454468, 0.2974051833152771], "r_norm": [0.2733529806137085, 0.26100292801856995, 0.26502537727355957]}, {"step": 5400, "epoch": 11, "train_loss": 0.199072927236557, "cos_r_negg": [0.2233084738254547, 0.26314419507980347, 0.2899826467037201], "cos_apical_negg": [0.00771000050008297, 0.07246391475200653, 0.22055357694625854], "cos_Ac_negg": [0.22329072654247284, 0.2631770372390747, 0.2899090647697449], "r_norm": [0.30120620131492615, 0.28904008865356445, 0.2931087613105774]}, {"step": 5500, "epoch": 11, "train_loss": 0.20055337250232697, "cos_r_negg": [0.21133768558502197, 0.23950855433940887, 0.2701360583305359], "cos_apical_negg": [0.04376184940338135, 0.03876647353172302, 0.18125934898853302], "cos_Ac_negg": [0.21131333708763123, 0.2395479828119278, 0.27007484436035156], "r_norm": [0.29053816199302673, 0.2780545949935913, 0.2816965579986572], "ldr": {"dL_sdil": -0.004450201988220215, "dL_bp": -0.00824826955795288, "ratio": 0.5395315898629167}}, {"step": 5600, "epoch": 11, "train_loss": 0.126506969332695, "cos_r_negg": [0.23953893780708313, 0.2824479639530182, 0.30662205815315247], "cos_apical_negg": [0.03706660866737366, 0.10186675935983658, 0.2106373906135559], "cos_Ac_negg": [0.23959125578403473, 0.28245654702186584, 0.30653202533721924], "r_norm": [0.30468881130218506, 0.2926936447620392, 0.29458853602409363]}, {"epoch_end": 11, "step": 5628, "test_acc": 0.9579, "test_loss": 0.19195390396118164}, {"step": 5700, "epoch": 12, "train_loss": 0.08967877179384232, "cos_r_negg": [0.21077533066272736, 0.23948656022548676, 0.2750556766986847], "cos_apical_negg": [0.02860533446073532, 0.0595209114253521, 0.21731853485107422], "cos_Ac_negg": [0.21073806285858154, 0.23946264386177063, 0.2751821279525757], "r_norm": [0.28939589858055115, 0.27771109342575073, 0.28099897503852844]}, {"step": 5800, "epoch": 12, "train_loss": 0.05890396609902382, "cos_r_negg": [0.21447233855724335, 0.24529846012592316, 0.30949723720550537], "cos_apical_negg": [0.0038862908259034157, 0.04426558315753937, 0.28895819187164307], "cos_Ac_negg": [0.21441778540611267, 0.24530361592769623, 0.30945920944213867], "r_norm": [0.25535374879837036, 0.2450881004333496, 0.24786671996116638]}, {"step": 5900, "epoch": 12, "train_loss": 0.05154634267091751, "cos_r_negg": [0.19446277618408203, 0.22660233080387115, 0.2689710259437561], "cos_apical_negg": [0.010688330978155136, 0.042043544352054596, 0.2132973074913025], "cos_Ac_negg": [0.1944444626569748, 0.22659774124622345, 0.2688741683959961], "r_norm": [0.24351239204406738, 0.23183901607990265, 0.23559917509555817]}, {"step": 6000, "epoch": 12, "train_loss": 0.026518069207668304, "cos_r_negg": [0.22935675084590912, 0.2517244517803192, 0.26853829622268677], "cos_apical_negg": [0.012940449640154839, 0.04862320423126221, 0.22226621210575104], "cos_Ac_negg": [0.2293858379125595, 0.25175678730010986, 0.2686704397201538], "r_norm": [0.264340341091156, 0.2518172264099121, 0.25426769256591797], "ldr": {"dL_sdil": -0.006428390741348267, "dL_bp": -0.010369852185249329, "ratio": 0.619911511418878}}, {"epoch_end": 12, "step": 6097, "test_acc": 0.9584, "test_loss": 0.1835839588165283}, {"step": 6100, "epoch": 13, "train_loss": 0.06954273581504822, "cos_r_negg": [0.194825679063797, 0.24101389944553375, 0.30091187357902527], "cos_apical_negg": [0.00934390164911747, 0.07383058220148087, 0.25413602590560913], "cos_Ac_negg": [0.19485333561897278, 0.241000697016716, 0.3010340631008148], "r_norm": [0.2561012804508209, 0.2447504848241806, 0.24863633513450623]}, {"step": 6200, "epoch": 13, "train_loss": 0.04477343335747719, "cos_r_negg": [0.1878224015235901, 0.2199847251176834, 0.24407532811164856], "cos_apical_negg": [0.02219512313604355, 0.01871546171605587, 0.2027413696050644], "cos_Ac_negg": [0.1878327578306198, 0.21998947858810425, 0.2440405786037445], "r_norm": [0.25637736916542053, 0.2448316216468811, 0.2472589612007141]}, {"step": 6300, "epoch": 13, "train_loss": 0.06889718770980835, "cos_r_negg": [0.200616717338562, 0.24257710576057434, 0.28241243958473206], "cos_apical_negg": [0.06119794026017189, 0.045447248965501785, 0.23216712474822998], "cos_Ac_negg": [0.20062166452407837, 0.24265258014202118, 0.2824299931526184], "r_norm": [0.26680195331573486, 0.2550649046897888, 0.25872063636779785]}, {"step": 6400, "epoch": 13, "train_loss": 0.05969580262899399, "cos_r_negg": [0.210836261510849, 0.23148703575134277, 0.2838355004787445], "cos_apical_negg": [0.018764115869998932, 0.05549445375800133, 0.20234736800193787], "cos_Ac_negg": [0.21076911687850952, 0.2315089851617813, 0.28407302498817444], "r_norm": [0.2894783020019531, 0.27576225996017456, 0.27874502539634705]}, {"step": 6500, "epoch": 13, "train_loss": 0.042694855481386185, "cos_r_negg": [0.22249245643615723, 0.2611536681652069, 0.29595276713371277], "cos_apical_negg": [0.011676089838147163, 0.04506925493478775, 0.2274012267589569], "cos_Ac_negg": [0.22252732515335083, 0.26120078563690186, 0.2958718538284302], "r_norm": [0.2742013931274414, 0.26220232248306274, 0.26537418365478516], "ldr": {"dL_sdil": -0.005292832851409912, "dL_bp": -0.008661419153213501, "ratio": 0.6110814818892816}}, {"epoch_end": 13, "step": 6566, "test_acc": 0.9584, "test_loss": 0.194653182220459}, {"step": 6600, "epoch": 14, "train_loss": 0.04261435940861702, "cos_r_negg": [0.1855010986328125, 0.21898628771305084, 0.287163108587265], "cos_apical_negg": [0.00647738017141819, 0.046435341238975525, 0.21486365795135498], "cos_Ac_negg": [0.18545223772525787, 0.21898266673088074, 0.2869402766227722], "r_norm": [0.2575647234916687, 0.24623623490333557, 0.24928104877471924]}, {"step": 6700, "epoch": 14, "train_loss": 0.07799383997917175, "cos_r_negg": [0.1735231578350067, 0.18533873558044434, 0.30120450258255005], "cos_apical_negg": [0.04645295441150665, 0.053029824048280716, 0.24667207896709442], "cos_Ac_negg": [0.17348648607730865, 0.1852864772081375, 0.3009122610092163], "r_norm": [0.2859070599079132, 0.2738664150238037, 0.2766638994216919]}, {"step": 6800, "epoch": 14, "train_loss": 0.192641943693161, "cos_r_negg": [0.1949756145477295, 0.24111878871917725, 0.2974018454551697], "cos_apical_negg": [0.0397103875875473, 0.0335024930536747, 0.16501350700855255], "cos_Ac_negg": [0.19497132301330566, 0.24115285277366638, 0.2973495125770569], "r_norm": [0.27731722593307495, 0.26534324884414673, 0.26979339122772217]}, {"step": 6900, "epoch": 14, "train_loss": 0.05707872658967972, "cos_r_negg": [0.17775830626487732, 0.23034465312957764, 0.2533235549926758], "cos_apical_negg": [0.005555080249905586, 0.06054583191871643, 0.1894989162683487], "cos_Ac_negg": [0.1777692586183548, 0.23038877546787262, 0.25332021713256836], "r_norm": [0.2580033242702484, 0.24572646617889404, 0.24875102937221527]}, {"step": 7000, "epoch": 14, "train_loss": 0.13115863502025604, "cos_r_negg": [0.19121834635734558, 0.23183977603912354, 0.26908716559410095], "cos_apical_negg": [0.02594858966767788, 0.0576966255903244, 0.20463576912879944], "cos_Ac_negg": [0.1912306696176529, 0.23184677958488464, 0.269147664308548], "r_norm": [0.2929958403110504, 0.2797738015651703, 0.2834494113922119], "ldr": {"dL_sdil": -0.004326134920120239, "dL_bp": -0.009723544120788574, "ratio": 0.4449133840891537}}, {"epoch_end": 14, "step": 7035, "test_acc": 0.956, "test_loss": 0.2118159149169922}], "final": {"test_acc": 0.956, "test_loss": 0.2118159149169922, "wall_s": 41.38318920135498, "cos_r_negg": [0.19462116062641144, 0.23295272886753082, 0.27229419350624084], "cos_apical_negg": [0.04181640222668648, 0.08553440868854523, 0.18258577585220337], "cos_Ac_negg": [0.19462744891643524, 0.232876718044281, 0.2721676826477051]}}