summaryrefslogtreecommitdiff
path: root/results/diag_nuis_v2_rho1_res1_s0.json
blob: 9e1258eba4c958dda002ac7bdbf982d31f1704be (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": 1, "learn_A": 1, "learn_P": 1, "p_neutral": 1, "p_warmup_steps": 200, "p_warmup_eta": 0.05, "nuis_rho": 1.0, "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_v2_rho1_res1_s0", "n_in": 784}, "provenance": {"git_commit": "54633b2e0f51a8f48d4ba627d778c87927f54ca1", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.3603768348693848, "cos_r_negg": [-0.01952069252729416, -0.025523580610752106, 0.03376835584640503], "cos_apical_negg": [-0.013020750135183334, -0.01925305277109146, 0.015020018443465233], "cos_Ac_negg": [-0.019519753754138947, -0.025523563846945763, 0.033768195658922195], "r_norm": [4.898232936859131, 4.8268141746521, 4.823862075805664], "ldr": {"dL_sdil": -0.009217500686645508, "dL_bp": -0.24074769020080566, "ratio": 0.03828697454566341}}, {"step": 100, "epoch": 0, "train_loss": 0.20820632576942444, "cos_r_negg": [0.45247799158096313, 0.3730752468109131, 0.3574973940849304], "cos_apical_negg": [0.05355706810951233, 0.05912838876247406, 0.11560722440481186], "cos_Ac_negg": [0.45980772376060486, 0.3796604573726654, 0.3623949885368347], "r_norm": [0.8269623517990112, 0.8108935356140137, 0.8083734512329102]}, {"step": 200, "epoch": 0, "train_loss": 0.3125769793987274, "cos_r_negg": [0.4705178439617157, 0.39170902967453003, 0.3797178864479065], "cos_apical_negg": [0.035528019070625305, 0.05168655514717102, 0.11112870275974274], "cos_Ac_negg": [0.48269566893577576, 0.4057140648365021, 0.394461989402771], "r_norm": [0.7476809620857239, 0.7304548621177673, 0.7294222116470337]}, {"step": 300, "epoch": 0, "train_loss": 0.17788541316986084, "cos_r_negg": [0.48671621084213257, 0.45401448011398315, 0.42767101526260376], "cos_apical_negg": [0.0389477014541626, 0.05002295598387718, 0.09516053646802902], "cos_Ac_negg": [0.4957050085067749, 0.4590369462966919, 0.43208760023117065], "r_norm": [0.5665696263313293, 0.5552384257316589, 0.5545287132263184]}, {"step": 400, "epoch": 0, "train_loss": 0.20246447622776031, "cos_r_negg": [0.5172643065452576, 0.46812668442726135, 0.4462651312351227], "cos_apical_negg": [0.03872915729880333, 0.05281463637948036, 0.10063380002975464], "cos_Ac_negg": [0.5260440111160278, 0.47443151473999023, 0.4496137499809265], "r_norm": [0.6011828780174255, 0.5863693952560425, 0.5862574577331543]}, {"epoch_end": 0, "step": 469, "test_acc": 0.9489, "test_loss": 0.17657186698913574}, {"step": 500, "epoch": 1, "train_loss": 0.21730077266693115, "cos_r_negg": [0.4987039268016815, 0.48760223388671875, 0.4558370113372803], "cos_apical_negg": [0.026488296687602997, 0.05769956856966019, 0.10587222874164581], "cos_Ac_negg": [0.5154716968536377, 0.49703219532966614, 0.46710073947906494], "r_norm": [0.48388803005218506, 0.4662487506866455, 0.4681951105594635], "ldr": {"dL_sdil": -0.013195529580116272, "dL_bp": -0.012036949396133423, "ratio": 1.096251977627738}}, {"step": 600, "epoch": 1, "train_loss": 0.09636817872524261, "cos_r_negg": [0.49540555477142334, 0.4749462306499481, 0.4424026310443878], "cos_apical_negg": [0.024980027228593826, 0.045220229774713516, 0.1072184145450592], "cos_Ac_negg": [0.5133594274520874, 0.490916907787323, 0.456206738948822], "r_norm": [0.4222860336303711, 0.4137040376663208, 0.4124385714530945]}, {"step": 700, "epoch": 1, "train_loss": 0.20269888639450073, "cos_r_negg": [0.49148184061050415, 0.49356609582901, 0.46042340993881226], "cos_apical_negg": [0.023850711062550545, 0.05214633047580719, 0.10163506865501404], "cos_Ac_negg": [0.5164077281951904, 0.5084192752838135, 0.472796231508255], "r_norm": [0.5059418082237244, 0.4928421080112457, 0.49228620529174805]}, {"step": 800, "epoch": 1, "train_loss": 0.18580462038516998, "cos_r_negg": [0.5189096927642822, 0.5152329206466675, 0.476398229598999], "cos_apical_negg": [0.018776943907141685, 0.04151133447885513, 0.10171951353549957], "cos_Ac_negg": [0.5330885648727417, 0.5233570337295532, 0.4799470901489258], "r_norm": [0.35999131202697754, 0.34983736276626587, 0.34987181425094604]}, {"step": 900, "epoch": 1, "train_loss": 0.21851953864097595, "cos_r_negg": [0.5527595281600952, 0.5378736257553101, 0.47609639167785645], "cos_apical_negg": [0.020225191488862038, 0.03783454746007919, 0.09986966848373413], "cos_Ac_negg": [0.5599428415298462, 0.5394718050956726, 0.47620391845703125], "r_norm": [0.43943318724632263, 0.430154949426651, 0.42856162786483765]}, {"epoch_end": 1, "step": 938, "test_acc": 0.9527, "test_loss": 0.15849240112304688}, {"step": 1000, "epoch": 2, "train_loss": 0.048953793942928314, "cos_r_negg": [0.5406612157821655, 0.5401836633682251, 0.4945063591003418], "cos_apical_negg": [0.00684305839240551, 0.03470243513584137, 0.1051340103149414], "cos_Ac_negg": [0.5539208054542542, 0.5516437888145447, 0.4969608783721924], "r_norm": [0.32489970326423645, 0.31662869453430176, 0.3150239884853363], "ldr": {"dL_sdil": -0.007094234228134155, "dL_bp": -0.006320945918560028, "ratio": 1.1223374348613775}}, {"step": 1100, "epoch": 2, "train_loss": 0.15747609734535217, "cos_r_negg": [0.5204079151153564, 0.5393697023391724, 0.4994724988937378], "cos_apical_negg": [0.01675550267100334, 0.03992713242769241, 0.10017327964305878], "cos_Ac_negg": [0.5327305793762207, 0.5504438877105713, 0.5013687014579773], "r_norm": [0.3689071536064148, 0.35580331087112427, 0.35768550634384155]}, {"step": 1200, "epoch": 2, "train_loss": 0.11255984008312225, "cos_r_negg": [0.5356619954109192, 0.5522195100784302, 0.5070484280586243], "cos_apical_negg": [0.020492661744356155, 0.02906835451722145, 0.0979154109954834], "cos_Ac_negg": [0.5454577207565308, 0.5596871376037598, 0.5072890520095825], "r_norm": [0.33136746287345886, 0.32186439633369446, 0.32262858748435974]}, {"step": 1300, "epoch": 2, "train_loss": 0.10070528090000153, "cos_r_negg": [0.5401700735092163, 0.5643941164016724, 0.49811404943466187], "cos_apical_negg": [0.014834541827440262, 0.04274377226829529, 0.11134599894285202], "cos_Ac_negg": [0.5524884462356567, 0.5701723694801331, 0.49451586604118347], "r_norm": [0.3253134489059448, 0.3205445110797882, 0.3168211281299591]}, {"step": 1400, "epoch": 2, "train_loss": 0.12846702337265015, "cos_r_negg": [0.5300706028938293, 0.5501449108123779, 0.4875084459781647], "cos_apical_negg": [0.022953219711780548, 0.03865577653050423, 0.10092078149318695], "cos_Ac_negg": [0.5395514369010925, 0.556358277797699, 0.48264631628990173], "r_norm": [0.3233911097049713, 0.3172415494918823, 0.3122522830963135]}, {"epoch_end": 2, "step": 1407, "test_acc": 0.9646, "test_loss": 0.11960855293273925}, {"step": 1500, "epoch": 3, "train_loss": 0.04802365228533745, "cos_r_negg": [0.5132083892822266, 0.5398122072219849, 0.48653846979141235], "cos_apical_negg": [0.004868463613092899, 0.04425199329853058, 0.09690235555171967], "cos_Ac_negg": [0.5291253328323364, 0.5514917969703674, 0.48411718010902405], "r_norm": [0.2663966417312622, 0.25964945554733276, 0.2593282163143158], "ldr": {"dL_sdil": -0.006809838116168976, "dL_bp": -0.007302872836589813, "ratio": 0.9324875659958681}}, {"step": 1600, "epoch": 3, "train_loss": 0.06981910765171051, "cos_r_negg": [0.5092813968658447, 0.5406162142753601, 0.5145689845085144], "cos_apical_negg": [0.007913642562925816, 0.04007811099290848, 0.10188837349414825], "cos_Ac_negg": [0.5224987864494324, 0.5543344020843506, 0.5140657424926758], "r_norm": [0.28141167759895325, 0.2739402651786804, 0.27224165201187134]}, {"step": 1700, "epoch": 3, "train_loss": 0.026035308837890625, "cos_r_negg": [0.50555419921875, 0.5345337390899658, 0.48899438977241516], "cos_apical_negg": [0.011308996006846428, 0.03269694000482559, 0.0982828140258789], "cos_Ac_negg": [0.5196442604064941, 0.5508270859718323, 0.49150747060775757], "r_norm": [0.2902778089046478, 0.2821534276008606, 0.28198111057281494]}, {"step": 1800, "epoch": 3, "train_loss": 0.04488299414515495, "cos_r_negg": [0.4855574071407318, 0.5212392807006836, 0.4940805435180664], "cos_apical_negg": [0.006815566681325436, 0.027186643332242966, 0.1029171422123909], "cos_Ac_negg": [0.5005114674568176, 0.5404747724533081, 0.4900423288345337], "r_norm": [0.24610629677772522, 0.23986393213272095, 0.23803485929965973]}, {"epoch_end": 3, "step": 1876, "test_acc": 0.9686, "test_loss": 0.11410523509979248}, {"step": 1900, "epoch": 4, "train_loss": 0.03720477595925331, "cos_r_negg": [0.48969316482543945, 0.5347305536270142, 0.5098276138305664], "cos_apical_negg": [0.006092734634876251, 0.03636404126882553, 0.10486426949501038], "cos_Ac_negg": [0.5025357604026794, 0.547871470451355, 0.5085148811340332], "r_norm": [0.2381521463394165, 0.2338624894618988, 0.23269914090633392]}, {"step": 2000, "epoch": 4, "train_loss": 0.09376846253871918, "cos_r_negg": [0.4365556240081787, 0.4885815978050232, 0.47137346863746643], "cos_apical_negg": [0.0021592299453914165, 0.03594357147812843, 0.10092498362064362], "cos_Ac_negg": [0.4539882242679596, 0.5067046284675598, 0.4683157801628113], "r_norm": [0.21684274077415466, 0.21048754453659058, 0.2079436033964157], "ldr": {"dL_sdil": -0.005363352596759796, "dL_bp": -0.00588611513376236, "ratio": 0.9111871709739361}}, {"step": 2100, "epoch": 4, "train_loss": 0.01795094832777977, "cos_r_negg": [0.4665408730506897, 0.5193837881088257, 0.49605539441108704], "cos_apical_negg": [0.010030766949057579, 0.04343145340681076, 0.10490712523460388], "cos_Ac_negg": [0.48169970512390137, 0.5332257747650146, 0.49485909938812256], "r_norm": [0.29260313510894775, 0.284512996673584, 0.28386205434799194]}, {"step": 2200, "epoch": 4, "train_loss": 0.008237517438828945, "cos_r_negg": [0.43938398361206055, 0.46865034103393555, 0.44824403524398804], "cos_apical_negg": [0.012633603997528553, 0.04007020592689514, 0.09947294741868973], "cos_Ac_negg": [0.4531918168067932, 0.4835525155067444, 0.44038569927215576], "r_norm": [0.2399400770664215, 0.2317260056734085, 0.23124423623085022]}, {"step": 2300, "epoch": 4, "train_loss": 0.11108306795358658, "cos_r_negg": [0.4207015633583069, 0.4533999562263489, 0.4320896863937378], "cos_apical_negg": [0.006102248094975948, 0.0322481133043766, 0.09669387340545654], "cos_Ac_negg": [0.433410108089447, 0.4679757356643677, 0.4283112585544586], "r_norm": [0.21574358642101288, 0.2103872150182724, 0.20982559025287628]}, {"epoch_end": 4, "step": 2345, "test_acc": 0.9693, "test_loss": 0.11552863693237304}, {"step": 2400, "epoch": 5, "train_loss": 0.08832602202892303, "cos_r_negg": [0.45157134532928467, 0.4912949204444885, 0.4594407379627228], "cos_apical_negg": [-0.0022061672061681747, 0.03439273312687874, 0.09876271337270737], "cos_Ac_negg": [0.46504831314086914, 0.5073860287666321, 0.45602723956108093], "r_norm": [0.20758934319019318, 0.202786386013031, 0.20093324780464172]}, {"step": 2500, "epoch": 5, "train_loss": 0.03226463124155998, "cos_r_negg": [0.3894649147987366, 0.429095983505249, 0.4108053147792816], "cos_apical_negg": [0.0025818003341555595, 0.031595081090927124, 0.10596092790365219], "cos_Ac_negg": [0.40533214807510376, 0.45035403966903687, 0.4087473452091217], "r_norm": [0.21533071994781494, 0.20972885191440582, 0.2089804708957672], "ldr": {"dL_sdil": -0.006639398634433746, "dL_bp": -0.008147932589054108, "ratio": 0.8148568439745171}}, {"step": 2600, "epoch": 5, "train_loss": 0.032373085618019104, "cos_r_negg": [0.40147143602371216, 0.4475758969783783, 0.43539121747016907], "cos_apical_negg": [-0.0051475162617862225, 0.023986084386706352, 0.1003330647945404], "cos_Ac_negg": [0.41641348600387573, 0.4666827619075775, 0.4289860725402832], "r_norm": [0.19734030961990356, 0.19379596412181854, 0.19054484367370605]}, {"step": 2700, "epoch": 5, "train_loss": 0.015110287815332413, "cos_r_negg": [0.4128378629684448, 0.4559454321861267, 0.4345250725746155], "cos_apical_negg": [0.01075565442442894, 0.034593287855386734, 0.09787613153457642], "cos_Ac_negg": [0.426885187625885, 0.477386474609375, 0.4317507743835449], "r_norm": [0.17885702848434448, 0.1742594689130783, 0.17370907962322235]}, {"step": 2800, "epoch": 5, "train_loss": 0.0966603234410286, "cos_r_negg": [0.3848547041416168, 0.4462057948112488, 0.42858922481536865], "cos_apical_negg": [-0.006684037856757641, 0.02884947508573532, 0.09844431281089783], "cos_Ac_negg": [0.40319156646728516, 0.46496981382369995, 0.4250919818878174], "r_norm": [0.2119465321302414, 0.20669062435626984, 0.2052062451839447]}, {"epoch_end": 5, "step": 2814, "test_acc": 0.971, "test_loss": 0.11315425815582275}, {"step": 2900, "epoch": 6, "train_loss": 0.0055389562621712685, "cos_r_negg": [0.37317758798599243, 0.4125456213951111, 0.40699535608291626], "cos_apical_negg": [0.00035977899096906185, 0.02745770663022995, 0.10108094662427902], "cos_Ac_negg": [0.39138713479042053, 0.43325045704841614, 0.40558862686157227], "r_norm": [0.1856657862663269, 0.17919275164604187, 0.1803833544254303]}, {"step": 3000, "epoch": 6, "train_loss": 0.059122078120708466, "cos_r_negg": [0.35192257165908813, 0.3903104364871979, 0.38647234439849854], "cos_apical_negg": [0.00892309844493866, 0.03370555490255356, 0.10920710861682892], "cos_Ac_negg": [0.3734910488128662, 0.41287851333618164, 0.3839004635810852], "r_norm": [0.19960160553455353, 0.19387799501419067, 0.19266298413276672], "ldr": {"dL_sdil": -0.006923303008079529, "dL_bp": -0.009040042757987976, "ratio": 0.7658484803030328}}, {"step": 3100, "epoch": 6, "train_loss": 0.018755115568637848, "cos_r_negg": [0.3402131199836731, 0.3875967264175415, 0.3798831105232239], "cos_apical_negg": [0.00945977121591568, 0.036882299929857254, 0.10735878348350525], "cos_Ac_negg": [0.35401809215545654, 0.4052842855453491, 0.37230491638183594], "r_norm": [0.19227050244808197, 0.1867617517709732, 0.1859717220067978]}, {"step": 3200, "epoch": 6, "train_loss": 0.01891898550093174, "cos_r_negg": [0.31876227259635925, 0.35685282945632935, 0.36091458797454834], "cos_apical_negg": [0.0017555095255374908, 0.038343850523233414, 0.11688633263111115], "cos_Ac_negg": [0.3413740396499634, 0.38378798961639404, 0.35758328437805176], "r_norm": [0.20571985840797424, 0.2018389105796814, 0.19833488762378693]}, {"epoch_end": 6, "step": 3283, "test_acc": 0.9692, "test_loss": 0.130955908203125}, {"step": 3300, "epoch": 7, "train_loss": 0.006738610565662384, "cos_r_negg": [0.31167787313461304, 0.3542804718017578, 0.3547123074531555], "cos_apical_negg": [0.010213890112936497, 0.03309930860996246, 0.10646143555641174], "cos_Ac_negg": [0.33059394359588623, 0.3761446475982666, 0.3523675799369812], "r_norm": [0.21223412454128265, 0.20840251445770264, 0.2042357176542282]}, {"step": 3400, "epoch": 7, "train_loss": 0.021810583770275116, "cos_r_negg": [0.27874547243118286, 0.3243314027786255, 0.3212192952632904], "cos_apical_negg": [-0.004605062305927277, 0.03871099278330803, 0.11275854706764221], "cos_Ac_negg": [0.3016117215156555, 0.3479066491127014, 0.32066595554351807], "r_norm": [0.23009563982486725, 0.2254328429698944, 0.2223561853170395]}, {"step": 3500, "epoch": 7, "train_loss": 0.008282961323857307, "cos_r_negg": [0.26876071095466614, 0.3095095753669739, 0.31059515476226807], "cos_apical_negg": [0.009344077669084072, 0.04012364149093628, 0.11219605803489685], "cos_Ac_negg": [0.28943419456481934, 0.330199658870697, 0.30517202615737915], "r_norm": [0.20065978169441223, 0.19628766179084778, 0.1945386677980423], "ldr": {"dL_sdil": -0.006579555571079254, "dL_bp": -0.009318768978118896, "ratio": 0.7060541565660119}}, {"step": 3600, "epoch": 7, "train_loss": 0.007229046430438757, "cos_r_negg": [0.27966195344924927, 0.3219839334487915, 0.320639967918396], "cos_apical_negg": [0.001273922622203827, 0.034568898379802704, 0.11067237704992294], "cos_Ac_negg": [0.30297043919563293, 0.3484964668750763, 0.32118597626686096], "r_norm": [0.20084795355796814, 0.1961166262626648, 0.19354857504367828]}, {"step": 3700, "epoch": 7, "train_loss": 0.0032357717864215374, "cos_r_negg": [0.2889690399169922, 0.3235850930213928, 0.32603615522384644], "cos_apical_negg": [0.005334996152669191, 0.030190210789442062, 0.1029483824968338], "cos_Ac_negg": [0.3125620186328888, 0.3513339161872864, 0.32547399401664734], "r_norm": [0.1978764533996582, 0.19294148683547974, 0.19131165742874146]}, {"epoch_end": 7, "step": 3752, "test_acc": 0.9718, "test_loss": 0.12202647438049316}, {"step": 3800, "epoch": 8, "train_loss": 0.004304760135710239, "cos_r_negg": [0.25752127170562744, 0.28930535912513733, 0.28976207971572876], "cos_apical_negg": [0.004450488369911909, 0.036352045834064484, 0.10605746507644653], "cos_Ac_negg": [0.27779683470726013, 0.3127424120903015, 0.28937214612960815], "r_norm": [0.19058868288993835, 0.1862567961215973, 0.18404096364974976]}, {"step": 3900, "epoch": 8, "train_loss": 0.021304629743099213, "cos_r_negg": [0.23813478648662567, 0.27522072196006775, 0.2766387462615967], "cos_apical_negg": [-0.00306108221411705, 0.041349273175001144, 0.10692794620990753], "cos_Ac_negg": [0.2591044008731842, 0.2974087595939636, 0.27524787187576294], "r_norm": [0.18729475140571594, 0.18307757377624512, 0.18050262331962585]}, {"step": 4000, "epoch": 8, "train_loss": 0.009143074974417686, "cos_r_negg": [0.22320961952209473, 0.26025712490081787, 0.26596689224243164], "cos_apical_negg": [-0.0003281468525528908, 0.03821016848087311, 0.108045294880867], "cos_Ac_negg": [0.24703139066696167, 0.28710439801216125, 0.26665085554122925], "r_norm": [0.17665278911590576, 0.17257598042488098, 0.17093247175216675], "ldr": {"dL_sdil": -0.007727883756160736, "dL_bp": -0.012262985110282898, "ratio": 0.6301796574539312}}, {"step": 4100, "epoch": 8, "train_loss": 0.015190917067229748, "cos_r_negg": [0.2306123524904251, 0.26366978883743286, 0.26940739154815674], "cos_apical_negg": [-0.0059013147838413715, 0.033381711691617966, 0.11045115441083908], "cos_Ac_negg": [0.24856306612491608, 0.2868881821632385, 0.26694488525390625], "r_norm": [0.17268167436122894, 0.1689237803220749, 0.16698026657104492]}, {"step": 4200, "epoch": 8, "train_loss": 0.02685653418302536, "cos_r_negg": [0.22369186580181122, 0.2567075490951538, 0.2605605721473694], "cos_apical_negg": [-0.0075320592150092125, 0.039410971105098724, 0.10670064389705658], "cos_Ac_negg": [0.2400529682636261, 0.2787850499153137, 0.25893548130989075], "r_norm": [0.18252675235271454, 0.17883211374282837, 0.17642846703529358]}, {"epoch_end": 8, "step": 4221, "test_acc": 0.971, "test_loss": 0.13368471832275391}, {"step": 4300, "epoch": 9, "train_loss": 0.0005877374787814915, "cos_r_negg": [0.2049940526485443, 0.23769736289978027, 0.24234871566295624], "cos_apical_negg": [-0.016194412484765053, 0.040163516998291016, 0.09907465428113937], "cos_Ac_negg": [0.22388851642608643, 0.25845858454704285, 0.24186840653419495], "r_norm": [0.17549756169319153, 0.1730770766735077, 0.17001581192016602]}, {"step": 4400, "epoch": 9, "train_loss": 0.0025541128125041723, "cos_r_negg": [0.19466310739517212, 0.22876086831092834, 0.23361460864543915], "cos_apical_negg": [0.0013437815941870213, 0.039167940616607666, 0.10058873146772385], "cos_Ac_negg": [0.21199488639831543, 0.24881887435913086, 0.23262274265289307], "r_norm": [0.18421109020709991, 0.18011777102947235, 0.17842558026313782]}, {"step": 4500, "epoch": 9, "train_loss": 0.051683250814676285, "cos_r_negg": [0.18345549702644348, 0.2146534025669098, 0.21782127022743225], "cos_apical_negg": [0.0018967902287840843, 0.035548027604818344, 0.09891831129789352], "cos_Ac_negg": [0.20243990421295166, 0.23397545516490936, 0.21833869814872742], "r_norm": [0.19130754470825195, 0.18803565204143524, 0.1849699169397354], "ldr": {"dL_sdil": -0.00911315530538559, "dL_bp": -0.015487857162952423, "ratio": 0.5884064664016029}}, {"step": 4600, "epoch": 9, "train_loss": 0.0008189650252461433, "cos_r_negg": [0.20114709436893463, 0.23408544063568115, 0.2405523657798767], "cos_apical_negg": [-0.0015496102860197425, 0.032105863094329834, 0.10387919843196869], "cos_Ac_negg": [0.21795222163200378, 0.2518981993198395, 0.23951667547225952], "r_norm": [0.1851329207420349, 0.18125633895397186, 0.17906734347343445]}, {"epoch_end": 9, "step": 4690, "test_acc": 0.9718, "test_loss": 0.13972204494476317}, {"step": 4700, "epoch": 10, "train_loss": 0.001482734689489007, "cos_r_negg": [0.1834557205438614, 0.2140897661447525, 0.21974290907382965], "cos_apical_negg": [-0.0054072001948952675, 0.03423908352851868, 0.10417235642671585], "cos_Ac_negg": [0.19527043402194977, 0.2277383655309677, 0.21551403403282166], "r_norm": [0.18676964938640594, 0.1832066774368286, 0.18067359924316406]}, {"step": 4800, "epoch": 10, "train_loss": 0.023686068132519722, "cos_r_negg": [0.1680445671081543, 0.1973242163658142, 0.2018754482269287], "cos_apical_negg": [-0.008865216746926308, 0.03213939443230629, 0.09961983561515808], "cos_Ac_negg": [0.18008953332901, 0.21299338340759277, 0.20032998919487], "r_norm": [0.18621967732906342, 0.18277020752429962, 0.1804094910621643]}, {"step": 4900, "epoch": 10, "train_loss": 0.001245332881808281, "cos_r_negg": [0.1673194319009781, 0.19736751914024353, 0.20521703362464905], "cos_apical_negg": [-0.010764362290501595, 0.031070401892066002, 0.0963827520608902], "cos_Ac_negg": [0.18175038695335388, 0.21430855989456177, 0.2036517858505249], "r_norm": [0.18096566200256348, 0.17740479111671448, 0.17531053721904755]}, {"step": 5000, "epoch": 10, "train_loss": 0.0007794614648446441, "cos_r_negg": [0.16641497611999512, 0.1961652934551239, 0.20308934152126312], "cos_apical_negg": [-0.016297809779644012, 0.032492853701114655, 0.08998872339725494], "cos_Ac_negg": [0.18078342080116272, 0.21298450231552124, 0.20286217331886292], "r_norm": [0.18811345100402832, 0.1850011646747589, 0.18199634552001953], "ldr": {"dL_sdil": -0.00875924527645111, "dL_bp": -0.01467636227607727, "ratio": 0.596826728018893}}, {"step": 5100, "epoch": 10, "train_loss": 0.0015728764701634645, "cos_r_negg": [0.16495142877101898, 0.19899164140224457, 0.20289763808250427], "cos_apical_negg": [-0.008439348079264164, 0.0319247767329216, 0.09133325517177582], "cos_Ac_negg": [0.1828022301197052, 0.21493475139141083, 0.20316603779792786], "r_norm": [0.1848369538784027, 0.18157362937927246, 0.17898453772068024]}, {"epoch_end": 10, "step": 5159, "test_acc": 0.9719, "test_loss": 0.143025297164917}, {"step": 5200, "epoch": 11, "train_loss": 0.000945753650739789, "cos_r_negg": [0.15467843413352966, 0.1876443475484848, 0.19079965353012085], "cos_apical_negg": [-0.011053524911403656, 0.03400162607431412, 0.09057056903839111], "cos_Ac_negg": [0.17329344153404236, 0.2058325707912445, 0.19291263818740845], "r_norm": [0.18525457382202148, 0.18178372085094452, 0.17939798533916473]}, {"step": 5300, "epoch": 11, "train_loss": 0.0022470694966614246, "cos_r_negg": [0.15511254966259003, 0.18624407052993774, 0.19023746252059937], "cos_apical_negg": [-0.011065485887229443, 0.033132266253232956, 0.08913247287273407], "cos_Ac_negg": [0.16942650079727173, 0.2010449916124344, 0.1902359426021576], "r_norm": [0.18756461143493652, 0.18395178020000458, 0.18160291016101837]}, {"step": 5400, "epoch": 11, "train_loss": 0.0011650138767436147, "cos_r_negg": [0.15109407901763916, 0.18032802641391754, 0.18431201577186584], "cos_apical_negg": [-0.013389652594923973, 0.03147890791296959, 0.08431592583656311], "cos_Ac_negg": [0.16673095524311066, 0.19649699330329895, 0.18609780073165894], "r_norm": [0.18785886466503143, 0.18459686636924744, 0.1818501353263855]}, {"step": 5500, "epoch": 11, "train_loss": 0.0018065053736791015, "cos_r_negg": [0.15043359994888306, 0.18242962658405304, 0.18673600256443024], "cos_apical_negg": [-0.014000916853547096, 0.030169501900672913, 0.08574439585208893], "cos_Ac_negg": [0.16805027425289154, 0.1979711353778839, 0.18760564923286438], "r_norm": [0.18511494994163513, 0.18156656622886658, 0.17925119400024414], "ldr": {"dL_sdil": -0.009377487003803253, "dL_bp": -0.017397858202457428, "ratio": 0.5390023814815719}}, {"step": 5600, "epoch": 11, "train_loss": 0.0006028296193107963, "cos_r_negg": [0.14368405938148499, 0.1736426204442978, 0.17885416746139526], "cos_apical_negg": [-0.015546198934316635, 0.02911526709794998, 0.08045763522386551], "cos_Ac_negg": [0.15943577885627747, 0.1888650506734848, 0.17996357381343842], "r_norm": [0.17845308780670166, 0.17523901164531708, 0.17302536964416504]}, {"epoch_end": 11, "step": 5628, "test_acc": 0.9729, "test_loss": 0.1467744659423828}, {"step": 5700, "epoch": 12, "train_loss": 0.0018712173914536834, "cos_r_negg": [0.14311768114566803, 0.17202642560005188, 0.17876039445400238], "cos_apical_negg": [-0.013300701044499874, 0.028201447799801826, 0.07995752990245819], "cos_Ac_negg": [0.1575838029384613, 0.18676859140396118, 0.17903093993663788], "r_norm": [0.17752739787101746, 0.17435607314109802, 0.1720159649848938]}, {"step": 5800, "epoch": 12, "train_loss": 0.00026226392947137356, "cos_r_negg": [0.1410803496837616, 0.16962942481040955, 0.1758478432893753], "cos_apical_negg": [-0.016142388805747032, 0.029463719576597214, 0.08082856237888336], "cos_Ac_negg": [0.15645548701286316, 0.1850406527519226, 0.17691221833229065], "r_norm": [0.1738947331905365, 0.17098966240882874, 0.1685534417629242]}, {"step": 5900, "epoch": 12, "train_loss": 0.0019302917644381523, "cos_r_negg": [0.14157713949680328, 0.16993315517902374, 0.17557750642299652], "cos_apical_negg": [-0.01328299194574356, 0.029809674248099327, 0.07963322848081589], "cos_Ac_negg": [0.15610143542289734, 0.18432550132274628, 0.17637214064598083], "r_norm": [0.1819217950105667, 0.17911165952682495, 0.1762874722480774]}, {"step": 6000, "epoch": 12, "train_loss": 0.0006428231718018651, "cos_r_negg": [0.13808372616767883, 0.16538561880588531, 0.17137032747268677], "cos_apical_negg": [-0.014472590759396553, 0.02844945341348648, 0.07746273279190063], "cos_Ac_negg": [0.15271863341331482, 0.18086877465248108, 0.17349126935005188], "r_norm": [0.17917108535766602, 0.17625850439071655, 0.1736314296722412], "ldr": {"dL_sdil": -0.009854309260845184, "dL_bp": -0.018573276698589325, "ratio": 0.5305638536895129}}, {"epoch_end": 12, "step": 6097, "test_acc": 0.9727, "test_loss": 0.1511538637161255}, {"step": 6100, "epoch": 13, "train_loss": 0.0010399093152955174, "cos_r_negg": [0.13761809468269348, 0.16418057680130005, 0.16989046335220337], "cos_apical_negg": [-0.015085707418620586, 0.027884524315595627, 0.0746118426322937], "cos_Ac_negg": [0.15187600255012512, 0.17952817678451538, 0.17225655913352966], "r_norm": [0.18038342893123627, 0.17778252065181732, 0.17469583451747894]}, {"step": 6200, "epoch": 13, "train_loss": 0.0007959031499922276, "cos_r_negg": [0.1321205198764801, 0.15859249234199524, 0.16480687260627747], "cos_apical_negg": [-0.015651533380150795, 0.02816075086593628, 0.07136611640453339], "cos_Ac_negg": [0.14719578623771667, 0.17477412521839142, 0.16768872737884521], "r_norm": [0.17893503606319427, 0.1755964756011963, 0.17348116636276245]}, {"step": 6300, "epoch": 13, "train_loss": 0.0006927199428901076, "cos_r_negg": [0.13134489953517914, 0.15783515572547913, 0.16386264562606812], "cos_apical_negg": [-0.016916628926992416, 0.027650490403175354, 0.0720038115978241], "cos_Ac_negg": [0.14617937803268433, 0.1732787936925888, 0.16604876518249512], "r_norm": [0.18042808771133423, 0.17756028473377228, 0.1749606728553772]}, {"step": 6400, "epoch": 13, "train_loss": 0.0002556143736001104, "cos_r_negg": [0.13152113556861877, 0.15837058424949646, 0.16415289044380188], "cos_apical_negg": [-0.014501968398690224, 0.02755911275744438, 0.07234740257263184], "cos_Ac_negg": [0.14663293957710266, 0.1733982414007187, 0.16639921069145203], "r_norm": [0.18087442219257355, 0.17796151340007782, 0.17527058720588684]}, {"step": 6500, "epoch": 13, "train_loss": 3.9401020330842584e-05, "cos_r_negg": [0.12811042368412018, 0.15400443971157074, 0.15969786047935486], "cos_apical_negg": [-0.014461074024438858, 0.02677958272397518, 0.06982248276472092], "cos_Ac_negg": [0.14337000250816345, 0.16995283961296082, 0.1628904640674591], "r_norm": [0.17826606333255768, 0.1752840280532837, 0.17260578274726868], "ldr": {"dL_sdil": -0.01027720421552658, "dL_bp": -0.019783921539783478, "ratio": 0.5194725522369342}}, {"epoch_end": 13, "step": 6566, "test_acc": 0.9732, "test_loss": 0.15409321250915528}, {"step": 6600, "epoch": 14, "train_loss": 0.00021599166211672127, "cos_r_negg": [0.12744799256324768, 0.1532696783542633, 0.15923601388931274], "cos_apical_negg": [-0.014625275507569313, 0.026122236624360085, 0.06785876303911209], "cos_Ac_negg": [0.1434287577867508, 0.1701580137014389, 0.16322126984596252], "r_norm": [0.1740453839302063, 0.17141611874103546, 0.16868329048156738]}, {"step": 6700, "epoch": 14, "train_loss": 0.0005370760336518288, "cos_r_negg": [0.1292593777179718, 0.1553119719028473, 0.1612003743648529], "cos_apical_negg": [-0.014544112607836723, 0.02638331800699234, 0.06908605992794037], "cos_Ac_negg": [0.14379610121250153, 0.1703704297542572, 0.1642872393131256], "r_norm": [0.17507882416248322, 0.17225655913352966, 0.16960997879505157]}, {"step": 6800, "epoch": 14, "train_loss": 0.0007449829136021435, "cos_r_negg": [0.12631851434707642, 0.1522466540336609, 0.15829485654830933], "cos_apical_negg": [-0.014272957108914852, 0.02619188092648983, 0.06658457219600677], "cos_Ac_negg": [0.14164145290851593, 0.1677858680486679, 0.16174274682998657], "r_norm": [0.1792091578245163, 0.17650106549263, 0.17361101508140564]}, {"step": 6900, "epoch": 14, "train_loss": 0.00038480397779494524, "cos_r_negg": [0.12308157235383987, 0.14831876754760742, 0.1546904444694519], "cos_apical_negg": [-0.015797391533851624, 0.026111885905265808, 0.06552687287330627], "cos_Ac_negg": [0.13904376327991486, 0.16539886593818665, 0.15902471542358398], "r_norm": [0.1767159253358841, 0.17383286356925964, 0.17140065133571625]}, {"step": 7000, "epoch": 14, "train_loss": 0.0010645879665389657, "cos_r_negg": [0.12115307152271271, 0.14677995443344116, 0.15252578258514404], "cos_apical_negg": [-0.015390787273645401, 0.025602485984563828, 0.06431327015161514], "cos_Ac_negg": [0.13721109926700592, 0.16398105025291443, 0.15706533193588257], "r_norm": [0.17232541739940643, 0.16934022307395935, 0.16710829734802246], "ldr": {"dL_sdil": -0.009419582784175873, "dL_bp": -0.017572030425071716, "ratio": 0.5360554561034702}}, {"epoch_end": 14, "step": 7035, "test_acc": 0.9729, "test_loss": 0.15747193183898925}], "final": {"test_acc": 0.9729, "test_loss": 0.15747193183898925, "wall_s": 44.96389436721802, "cos_r_negg": [0.12099438905715942, 0.14610928297042847, 0.15199074149131775], "cos_apical_negg": [-0.015345013700425625, 0.025703568011522293, 0.0641845166683197], "cos_Ac_negg": [0.13689438998699188, 0.1636166274547577, 0.1564505398273468]}}