{"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": 0.02, "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_rho0p02_res1_s0", "n_in": 784}, "provenance": {"git_commit": "54633b2e0f51a8f48d4ba627d778c87927f54ca1", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.3603768348693848, "cos_r_negg": [-0.019516076892614365, -0.02552611567080021, 0.03376470506191254], "cos_apical_negg": [-0.019525274634361267, -0.025608714669942856, 0.033514510840177536], "cos_Ac_negg": [-0.019516058266162872, -0.02552611753344536, 0.03376470133662224], "r_norm": [4.898172378540039, 4.826802730560303, 4.823856353759766], "ldr": {"dL_sdil": -0.009198188781738281, "dL_bp": -0.2406764030456543, "ratio": 0.03821807483134714}}, {"step": 100, "epoch": 0, "train_loss": 0.20666691660881042, "cos_r_negg": [0.45621293783187866, 0.3815845847129822, 0.3604835271835327], "cos_apical_negg": [0.2548171281814575, 0.2229165881872177, 0.2502298951148987], "cos_Ac_negg": [0.4563215970993042, 0.38170552253723145, 0.3605661392211914], "r_norm": [0.8244898319244385, 0.8078850507736206, 0.8057104349136353]}, {"step": 200, "epoch": 0, "train_loss": 0.3330998122692108, "cos_r_negg": [0.47436001896858215, 0.4069191813468933, 0.3816928565502167], "cos_apical_negg": [0.24737149477005005, 0.22371184825897217, 0.2461678683757782], "cos_Ac_negg": [0.47450393438339233, 0.4071381986141205, 0.3819814622402191], "r_norm": [0.7478988766670227, 0.730629563331604, 0.72956383228302]}, {"step": 300, "epoch": 0, "train_loss": 0.17292667925357819, "cos_r_negg": [0.500956654548645, 0.47095879912376404, 0.42712223529815674], "cos_apical_negg": [0.2329605221748352, 0.2119992971420288, 0.23979687690734863], "cos_Ac_negg": [0.50104820728302, 0.4710274934768677, 0.4271710515022278], "r_norm": [0.5720133781433105, 0.5613110065460205, 0.5610545873641968]}, {"step": 400, "epoch": 0, "train_loss": 0.12120312452316284, "cos_r_negg": [0.5187759399414062, 0.48503759503364563, 0.4563548266887665], "cos_apical_negg": [0.2260979413986206, 0.2193305790424347, 0.24290788173675537], "cos_Ac_negg": [0.5188868045806885, 0.48505544662475586, 0.4563472270965576], "r_norm": [0.5730111002922058, 0.5584796667098999, 0.5582184195518494]}, {"epoch_end": 0, "step": 469, "test_acc": 0.9455, "test_loss": 0.1858793228149414}, {"step": 500, "epoch": 1, "train_loss": 0.22908438742160797, "cos_r_negg": [0.5118932723999023, 0.4822896122932434, 0.47202080488204956], "cos_apical_negg": [0.19514621794223785, 0.18528658151626587, 0.22929653525352478], "cos_Ac_negg": [0.5121138691902161, 0.4823378920555115, 0.47203999757766724], "r_norm": [0.4961223006248474, 0.478294312953949, 0.4794073700904846], "ldr": {"dL_sdil": -0.012139663100242615, "dL_bp": -0.010848388075828552, "ratio": 1.1190292064948497}}, {"step": 600, "epoch": 1, "train_loss": 0.09079079329967499, "cos_r_negg": [0.5184227228164673, 0.5019474029541016, 0.4570058584213257], "cos_apical_negg": [0.1823062300682068, 0.19016176462173462, 0.2272079885005951], "cos_Ac_negg": [0.518621563911438, 0.5019934177398682, 0.45703262090682983], "r_norm": [0.43909209966659546, 0.42774102091789246, 0.4260190725326538]}, {"step": 700, "epoch": 1, "train_loss": 0.21720203757286072, "cos_r_negg": [0.5171608924865723, 0.5006321668624878, 0.468919575214386], "cos_apical_negg": [0.16877971589565277, 0.17867717146873474, 0.22401881217956543], "cos_Ac_negg": [0.5175011157989502, 0.5006343126296997, 0.4689297080039978], "r_norm": [0.4626578092575073, 0.44650548696517944, 0.4488585889339447]}, {"step": 800, "epoch": 1, "train_loss": 0.13265103101730347, "cos_r_negg": [0.5302672386169434, 0.5384685397148132, 0.4882376790046692], "cos_apical_negg": [0.15258991718292236, 0.17883214354515076, 0.21039175987243652], "cos_Ac_negg": [0.5305817127227783, 0.5384242534637451, 0.48820960521698], "r_norm": [0.37950968742370605, 0.3676168918609619, 0.36676251888275146]}, {"step": 900, "epoch": 1, "train_loss": 0.20370136201381683, "cos_r_negg": [0.5451664924621582, 0.5469822883605957, 0.47349900007247925], "cos_apical_negg": [0.16239389777183533, 0.18302062153816223, 0.21378210186958313], "cos_Ac_negg": [0.5452289581298828, 0.5469443202018738, 0.47342297434806824], "r_norm": [0.37063032388687134, 0.3622225522994995, 0.36039620637893677]}, {"epoch_end": 1, "step": 938, "test_acc": 0.9529, "test_loss": 0.15865937118530274}, {"step": 1000, "epoch": 2, "train_loss": 0.029328424483537674, "cos_r_negg": [0.5289598703384399, 0.5364674925804138, 0.4905230700969696], "cos_apical_negg": [0.13371966779232025, 0.1510743498802185, 0.19319716095924377], "cos_Ac_negg": [0.5291118025779724, 0.5364547967910767, 0.4904087781906128], "r_norm": [0.3019307851791382, 0.2927197813987732, 0.29203489422798157], "ldr": {"dL_sdil": -0.006969355046749115, "dL_bp": -0.005919985473155975, "ratio": 1.177258808885846}}, {"step": 1100, "epoch": 2, "train_loss": 0.10531969368457794, "cos_r_negg": [0.5412123203277588, 0.5536156892776489, 0.5019960403442383], "cos_apical_negg": [0.13393628597259521, 0.15139706432819366, 0.20108921825885773], "cos_Ac_negg": [0.5413720607757568, 0.5536148548126221, 0.5018433928489685], "r_norm": [0.37149864435195923, 0.3579740822315216, 0.3603286147117615]}, {"step": 1200, "epoch": 2, "train_loss": 0.18178343772888184, "cos_r_negg": [0.5275225639343262, 0.5536405444145203, 0.5052825212478638], "cos_apical_negg": [0.1327957957983017, 0.14455966651439667, 0.18889185786247253], "cos_Ac_negg": [0.527618408203125, 0.5536795854568481, 0.5051732063293457], "r_norm": [0.2758646309375763, 0.26887577772140503, 0.2693221867084503]}, {"step": 1300, "epoch": 2, "train_loss": 0.13751375675201416, "cos_r_negg": [0.5319006443023682, 0.5425025820732117, 0.48974841833114624], "cos_apical_negg": [0.12245390564203262, 0.14747200906276703, 0.19146475195884705], "cos_Ac_negg": [0.5320289134979248, 0.5424505472183228, 0.4895438253879547], "r_norm": [0.2822554111480713, 0.27503806352615356, 0.27348774671554565]}, {"step": 1400, "epoch": 2, "train_loss": 0.1919175386428833, "cos_r_negg": [0.4942934811115265, 0.5211362242698669, 0.469143271446228], "cos_apical_negg": [0.13863955438137054, 0.15377335250377655, 0.1846141815185547], "cos_Ac_negg": [0.49437832832336426, 0.520835280418396, 0.4687177538871765], "r_norm": [0.2955261170864105, 0.28647202253341675, 0.2861825227737427]}, {"epoch_end": 2, "step": 1407, "test_acc": 0.9637, "test_loss": 0.12490827331542968}, {"step": 1500, "epoch": 3, "train_loss": 0.09113158285617828, "cos_r_negg": [0.49388402700424194, 0.5273165702819824, 0.4769553244113922], "cos_apical_negg": [0.10814551264047623, 0.13171860575675964, 0.1783793568611145], "cos_Ac_negg": [0.49401742219924927, 0.5272470116615295, 0.4765438735485077], "r_norm": [0.2476242333650589, 0.24017561972141266, 0.24017147719860077], "ldr": {"dL_sdil": -0.0050140321254730225, "dL_bp": -0.0049041807651519775, "ratio": 1.0223995332924154}}, {"step": 1600, "epoch": 3, "train_loss": 0.09694245457649231, "cos_r_negg": [0.503745436668396, 0.5409880876541138, 0.5105512142181396], "cos_apical_negg": [0.12057998776435852, 0.13434819877147675, 0.18615035712718964], "cos_Ac_negg": [0.5037381052970886, 0.5408003330230713, 0.5100628137588501], "r_norm": [0.30542612075805664, 0.295025497674942, 0.2949987053871155]}, {"step": 1700, "epoch": 3, "train_loss": 0.042790692299604416, "cos_r_negg": [0.4831027686595917, 0.5262888073921204, 0.4767081141471863], "cos_apical_negg": [0.12841689586639404, 0.14515358209609985, 0.19567400217056274], "cos_Ac_negg": [0.4830111265182495, 0.5262072086334229, 0.4762493669986725], "r_norm": [0.2926684617996216, 0.2838863134384155, 0.2848629951477051]}, {"step": 1800, "epoch": 3, "train_loss": 0.025837283581495285, "cos_r_negg": [0.49439430236816406, 0.5511816740036011, 0.48297521471977234], "cos_apical_negg": [0.08975066989660263, 0.12552043795585632, 0.1713440716266632], "cos_Ac_negg": [0.4943971037864685, 0.5510495901107788, 0.48242872953414917], "r_norm": [0.2425144612789154, 0.23646119236946106, 0.23406532406806946]}, {"epoch_end": 3, "step": 1876, "test_acc": 0.9674, "test_loss": 0.11496790046691895}, {"step": 1900, "epoch": 4, "train_loss": 0.04518939554691315, "cos_r_negg": [0.48827606439590454, 0.5391676425933838, 0.4935782551765442], "cos_apical_negg": [0.11472448706626892, 0.1402273178100586, 0.1942419409751892], "cos_Ac_negg": [0.48823282122612, 0.5389991998672485, 0.49292588233947754], "r_norm": [0.3024155795574188, 0.2952362298965454, 0.2935969829559326]}, {"step": 2000, "epoch": 4, "train_loss": 0.09094434231519699, "cos_r_negg": [0.4285632073879242, 0.48903414607048035, 0.4430459141731262], "cos_apical_negg": [0.0712447464466095, 0.10120940208435059, 0.15749140083789825], "cos_Ac_negg": [0.4285363256931305, 0.4889431893825531, 0.4423690438270569], "r_norm": [0.19939634203910828, 0.19333955645561218, 0.19306454062461853], "ldr": {"dL_sdil": -0.004258647561073303, "dL_bp": -0.004662469029426575, "ratio": 0.9133889220915776}}, {"step": 2100, "epoch": 4, "train_loss": 0.04867567867040634, "cos_r_negg": [0.4485446512699127, 0.5176587104797363, 0.4661404490470886], "cos_apical_negg": [0.09516894072294235, 0.1227864995598793, 0.18243567645549774], "cos_Ac_negg": [0.4484497308731079, 0.5175020098686218, 0.4654655158519745], "r_norm": [0.2640710473060608, 0.2580794394016266, 0.25592613220214844]}, {"step": 2200, "epoch": 4, "train_loss": 0.005549731198698282, "cos_r_negg": [0.4341243505477905, 0.49059516191482544, 0.4355831444263458], "cos_apical_negg": [0.08100329339504242, 0.10584701597690582, 0.1655983179807663], "cos_Ac_negg": [0.43403735756874084, 0.49035704135894775, 0.43483299016952515], "r_norm": [0.25272154808044434, 0.24526101350784302, 0.24376076459884644]}, {"step": 2300, "epoch": 4, "train_loss": 0.11908858269453049, "cos_r_negg": [0.41476237773895264, 0.4658155143260956, 0.42012280225753784], "cos_apical_negg": [0.08445233106613159, 0.11838938295841217, 0.16716186702251434], "cos_Ac_negg": [0.4147198796272278, 0.46558678150177, 0.41937845945358276], "r_norm": [0.21195140480995178, 0.20710352063179016, 0.20612670481204987]}, {"epoch_end": 4, "step": 2345, "test_acc": 0.9706, "test_loss": 0.11300087585449219}, {"step": 2400, "epoch": 5, "train_loss": 0.09114673733711243, "cos_r_negg": [0.41651755571365356, 0.47811898589134216, 0.4303111433982849], "cos_apical_negg": [0.07098812609910965, 0.09009087085723877, 0.16010312736034393], "cos_Ac_negg": [0.41635245084762573, 0.4779331684112549, 0.4294087290763855], "r_norm": [0.20994238555431366, 0.2038857340812683, 0.20224055647850037]}, {"step": 2500, "epoch": 5, "train_loss": 0.0506490059196949, "cos_r_negg": [0.38574618101119995, 0.4409067928791046, 0.397209107875824], "cos_apical_negg": [0.07910504192113876, 0.08861284703016281, 0.16518300771713257], "cos_Ac_negg": [0.38568058609962463, 0.44085222482681274, 0.3965015113353729], "r_norm": [0.21368306875228882, 0.20854078233242035, 0.20763856172561646], "ldr": {"dL_sdil": -0.00640907883644104, "dL_bp": -0.007272765040397644, "ratio": 0.8812437636635954}}, {"step": 2600, "epoch": 5, "train_loss": 0.049843236804008484, "cos_r_negg": [0.39549702405929565, 0.44585907459259033, 0.403192937374115], "cos_apical_negg": [0.07233475893735886, 0.09070632606744766, 0.16163372993469238], "cos_Ac_negg": [0.395357221364975, 0.44567298889160156, 0.40239015221595764], "r_norm": [0.19365227222442627, 0.18826515972614288, 0.18756335973739624]}, {"step": 2700, "epoch": 5, "train_loss": 0.011957159265875816, "cos_r_negg": [0.41444921493530273, 0.4680020213127136, 0.42595210671424866], "cos_apical_negg": [0.06405209004878998, 0.09268269687891006, 0.15636903047561646], "cos_Ac_negg": [0.41426366567611694, 0.46777641773223877, 0.42501968145370483], "r_norm": [0.1665506362915039, 0.16178865730762482, 0.16212913393974304]}, {"step": 2800, "epoch": 5, "train_loss": 0.0497964546084404, "cos_r_negg": [0.3917809724807739, 0.45230811834335327, 0.41274556517601013], "cos_apical_negg": [0.07781335711479187, 0.1003563329577446, 0.17138859629631042], "cos_Ac_negg": [0.3917839825153351, 0.45210278034210205, 0.4119354784488678], "r_norm": [0.20583036541938782, 0.20006787776947021, 0.19989202916622162]}, {"epoch_end": 5, "step": 2814, "test_acc": 0.9697, "test_loss": 0.11425394191741943}, {"step": 2900, "epoch": 6, "train_loss": 0.016345564275979996, "cos_r_negg": [0.3668573498725891, 0.4212730824947357, 0.3867816627025604], "cos_apical_negg": [0.05176198109984398, 0.09197431057691574, 0.1654084324836731], "cos_Ac_negg": [0.3670150935649872, 0.42115360498428345, 0.3859657645225525], "r_norm": [0.18884789943695068, 0.1829959899187088, 0.18494556844234467]}, {"step": 3000, "epoch": 6, "train_loss": 0.06740796566009521, "cos_r_negg": [0.35739368200302124, 0.41632911562919617, 0.3758406341075897], "cos_apical_negg": [0.04749305546283722, 0.07950197160243988, 0.1474684327840805], "cos_Ac_negg": [0.35742366313934326, 0.41612905263900757, 0.37502217292785645], "r_norm": [0.1672361195087433, 0.16116869449615479, 0.1613539755344391], "ldr": {"dL_sdil": -0.004773199558258057, "dL_bp": -0.006503865122795105, "ratio": 0.7339019902993812}}, {"step": 3100, "epoch": 6, "train_loss": 0.015779832378029823, "cos_r_negg": [0.33921587467193604, 0.401305615901947, 0.3627150058746338], "cos_apical_negg": [0.04513528570532799, 0.08053319901227951, 0.14738032221794128], "cos_Ac_negg": [0.33924078941345215, 0.40108269453048706, 0.36195629835128784], "r_norm": [0.19078296422958374, 0.1855381280183792, 0.18521305918693542]}, {"step": 3200, "epoch": 6, "train_loss": 0.014715760946273804, "cos_r_negg": [0.323300838470459, 0.3751212954521179, 0.3425447344779968], "cos_apical_negg": [0.04321293905377388, 0.07752640545368195, 0.14486974477767944], "cos_Ac_negg": [0.3232835829257965, 0.37487027049064636, 0.34174519777297974], "r_norm": [0.15650531649589539, 0.15346120297908783, 0.15262295305728912]}, {"epoch_end": 6, "step": 3283, "test_acc": 0.9684, "test_loss": 0.13092685871124268}, {"step": 3300, "epoch": 7, "train_loss": 0.010674525052309036, "cos_r_negg": [0.30907344818115234, 0.35837921500205994, 0.32657375931739807], "cos_apical_negg": [0.05170029401779175, 0.08447684347629547, 0.1447277069091797], "cos_Ac_negg": [0.3089962899684906, 0.3581080436706543, 0.32574689388275146], "r_norm": [0.18258851766586304, 0.1787324845790863, 0.17720270156860352]}, {"step": 3400, "epoch": 7, "train_loss": 0.033174771815538406, "cos_r_negg": [0.28079208731651306, 0.32952362298965454, 0.2979621887207031], "cos_apical_negg": [0.04452217370271683, 0.08559951931238174, 0.1455911248922348], "cos_Ac_negg": [0.2807585299015045, 0.3293297290802002, 0.29722511768341064], "r_norm": [0.1638374626636505, 0.1596226990222931, 0.15870176255702972]}, {"step": 3500, "epoch": 7, "train_loss": 0.001852021785452962, "cos_r_negg": [0.2659572958946228, 0.3107095956802368, 0.28311192989349365], "cos_apical_negg": [0.031097523868083954, 0.07743818312883377, 0.14182418584823608], "cos_Ac_negg": [0.26604214310646057, 0.31052032113075256, 0.28239208459854126], "r_norm": [0.1802939772605896, 0.17595365643501282, 0.17571572959423065], "ldr": {"dL_sdil": -0.006213486194610596, "dL_bp": -0.00846630334854126, "ratio": 0.7339078153490893}}, {"step": 3600, "epoch": 7, "train_loss": 0.011132667772471905, "cos_r_negg": [0.29550132155418396, 0.34680211544036865, 0.3192564845085144], "cos_apical_negg": [0.052166856825351715, 0.08566244691610336, 0.1426910012960434], "cos_Ac_negg": [0.2954166531562805, 0.34657326340675354, 0.3185856342315674], "r_norm": [0.216933012008667, 0.21131376922130585, 0.21031340956687927]}, {"step": 3700, "epoch": 7, "train_loss": 0.009207136929035187, "cos_r_negg": [0.2779083549976349, 0.3308279514312744, 0.30681318044662476], "cos_apical_negg": [0.04207058250904083, 0.0821167528629303, 0.13696354627609253], "cos_Ac_negg": [0.27785173058509827, 0.33055371046066284, 0.306132972240448], "r_norm": [0.18489482998847961, 0.18016967177391052, 0.1788412630558014]}, {"epoch_end": 7, "step": 3752, "test_acc": 0.9723, "test_loss": 0.12359478569030762}, {"step": 3800, "epoch": 8, "train_loss": 0.002723423996940255, "cos_r_negg": [0.2539207339286804, 0.3019651174545288, 0.2805212438106537], "cos_apical_negg": [0.023168187588453293, 0.07803573459386826, 0.1375126987695694], "cos_Ac_negg": [0.25397467613220215, 0.30177628993988037, 0.2798832654953003], "r_norm": [0.17767879366874695, 0.17325571179389954, 0.1724102795124054]}, {"step": 3900, "epoch": 8, "train_loss": 0.018768351525068283, "cos_r_negg": [0.24070538580417633, 0.2874033451080322, 0.2684459090232849], "cos_apical_negg": [0.029751447960734367, 0.07550971955060959, 0.1321178376674652], "cos_Ac_negg": [0.2406652569770813, 0.2872641682624817, 0.26789575815200806], "r_norm": [0.1703643500804901, 0.1662348061800003, 0.1656225025653839]}, {"step": 4000, "epoch": 8, "train_loss": 0.013924628496170044, "cos_r_negg": [0.2321178913116455, 0.2789957523345947, 0.2601158022880554], "cos_apical_negg": [0.02238772250711918, 0.07014966011047363, 0.12876828014850616], "cos_Ac_negg": [0.23211203515529633, 0.2788405418395996, 0.25953006744384766], "r_norm": [0.15361139178276062, 0.15028171241283417, 0.14933691918849945], "ldr": {"dL_sdil": -0.005793191492557526, "dL_bp": -0.009559974074363708, "ratio": 0.6059840170584467}}, {"step": 4100, "epoch": 8, "train_loss": 0.016691818833351135, "cos_r_negg": [0.2363642156124115, 0.2781643271446228, 0.26152127981185913], "cos_apical_negg": [0.0323525071144104, 0.06793119758367538, 0.1332402378320694], "cos_Ac_negg": [0.236360564827919, 0.2779131531715393, 0.26090848445892334], "r_norm": [0.14785313606262207, 0.1430557668209076, 0.1428561955690384]}, {"step": 4200, "epoch": 8, "train_loss": 0.007424125913530588, "cos_r_negg": [0.22033420205116272, 0.2601127326488495, 0.24122940003871918], "cos_apical_negg": [0.03079233691096306, 0.07190176844596863, 0.1316319853067398], "cos_Ac_negg": [0.22028687596321106, 0.2598786950111389, 0.24067524075508118], "r_norm": [0.16593816876411438, 0.16193701326847076, 0.16203181445598602]}, {"epoch_end": 8, "step": 4221, "test_acc": 0.9722, "test_loss": 0.13240455589294434}, {"step": 4300, "epoch": 9, "train_loss": 0.006326611153781414, "cos_r_negg": [0.2145157754421234, 0.2527114450931549, 0.23701094090938568], "cos_apical_negg": [0.033963993191719055, 0.06959258019924164, 0.13042381405830383], "cos_Ac_negg": [0.2144797146320343, 0.2525511085987091, 0.23643437027931213], "r_norm": [0.18063950538635254, 0.17672720551490784, 0.175909161567688]}, {"step": 4400, "epoch": 9, "train_loss": 0.0011063176207244396, "cos_r_negg": [0.20485961437225342, 0.24688483774662018, 0.2341856062412262], "cos_apical_negg": [0.03402389958500862, 0.06971719115972519, 0.12852472066879272], "cos_Ac_negg": [0.20482957363128662, 0.2466934621334076, 0.23364372551441193], "r_norm": [0.17688536643981934, 0.17364048957824707, 0.17277860641479492]}, {"step": 4500, "epoch": 9, "train_loss": 0.027883945032954216, "cos_r_negg": [0.19688260555267334, 0.2351025640964508, 0.22025971114635468], "cos_apical_negg": [0.029540207237005234, 0.06613779067993164, 0.12443678081035614], "cos_Ac_negg": [0.19691920280456543, 0.23485177755355835, 0.21967586874961853], "r_norm": [0.1727409064769745, 0.16848939657211304, 0.1681206375360489], "ldr": {"dL_sdil": -0.007039323449134827, "dL_bp": -0.01283390074968338, "ratio": 0.5484944590450016}}, {"step": 4600, "epoch": 9, "train_loss": 0.0004145799030084163, "cos_r_negg": [0.2012549340724945, 0.2405065894126892, 0.2255883812904358], "cos_apical_negg": [0.02580380253493786, 0.06926220655441284, 0.12946876883506775], "cos_Ac_negg": [0.20122212171554565, 0.24027664959430695, 0.22505322098731995], "r_norm": [0.18977829813957214, 0.18521910905838013, 0.1842881292104721]}, {"epoch_end": 9, "step": 4690, "test_acc": 0.9718, "test_loss": 0.13522891788482666}, {"step": 4700, "epoch": 10, "train_loss": 0.002352712443098426, "cos_r_negg": [0.1847139596939087, 0.21888308227062225, 0.20647931098937988], "cos_apical_negg": [0.018549814820289612, 0.0614742785692215, 0.11759516596794128], "cos_Ac_negg": [0.1847943663597107, 0.2187812477350235, 0.20605726540088654], "r_norm": [0.14868712425231934, 0.1454245150089264, 0.14488908648490906]}, {"step": 4800, "epoch": 10, "train_loss": 0.0063841980881989, "cos_r_negg": [0.1894565224647522, 0.222882479429245, 0.21073979139328003], "cos_apical_negg": [0.02503601834177971, 0.06502237915992737, 0.12016555666923523], "cos_Ac_negg": [0.1895405650138855, 0.22279232740402222, 0.21032766997814178], "r_norm": [0.16727523505687714, 0.16356618702411652, 0.16298474371433258]}, {"step": 4900, "epoch": 10, "train_loss": 0.0010623340494930744, "cos_r_negg": [0.18027281761169434, 0.21277551352977753, 0.20070210099220276], "cos_apical_negg": [0.021039476618170738, 0.06321974098682404, 0.11654315888881683], "cos_Ac_negg": [0.18037821352481842, 0.21267223358154297, 0.20031720399856567], "r_norm": [0.1639031171798706, 0.15994615852832794, 0.1595858931541443]}, {"step": 5000, "epoch": 10, "train_loss": 0.00036228657700121403, "cos_r_negg": [0.18431438505649567, 0.21687689423561096, 0.20406456291675568], "cos_apical_negg": [0.024427860975265503, 0.06379403173923492, 0.1138601005077362], "cos_Ac_negg": [0.18437957763671875, 0.21679972112178802, 0.20367948710918427], "r_norm": [0.17233991622924805, 0.16849377751350403, 0.1679506003856659], "ldr": {"dL_sdil": -0.007889904081821442, "dL_bp": -0.01465548574924469, "ratio": 0.5383584151912583}}, {"step": 5100, "epoch": 10, "train_loss": 0.004313663579523563, "cos_r_negg": [0.1769174039363861, 0.21067111194133759, 0.19968238472938538], "cos_apical_negg": [0.020369667559862137, 0.06167798861861229, 0.11909909546375275], "cos_Ac_negg": [0.1769578456878662, 0.21049445867538452, 0.19923339784145355], "r_norm": [0.1595233976840973, 0.1564694046974182, 0.15605463087558746]}, {"epoch_end": 10, "step": 5159, "test_acc": 0.9725, "test_loss": 0.14078899154663085}, {"step": 5200, "epoch": 11, "train_loss": 0.0012677351478487253, "cos_r_negg": [0.16810822486877441, 0.19922301173210144, 0.18810823559761047], "cos_apical_negg": [0.023612264543771744, 0.06200932711362839, 0.11799322813749313], "cos_Ac_negg": [0.16817978024482727, 0.1990954726934433, 0.18768227100372314], "r_norm": [0.16747885942459106, 0.16378852725028992, 0.16306960582733154]}, {"step": 5300, "epoch": 11, "train_loss": 0.002009693067520857, "cos_r_negg": [0.1719294935464859, 0.20394322276115417, 0.1956622302532196], "cos_apical_negg": [0.023588884621858597, 0.06294385343790054, 0.11028198897838593], "cos_Ac_negg": [0.17197218537330627, 0.20385082066059113, 0.19527961313724518], "r_norm": [0.16482827067375183, 0.16162650287151337, 0.16074684262275696]}, {"step": 5400, "epoch": 11, "train_loss": 0.0034146991092711687, "cos_r_negg": [0.16919755935668945, 0.19766053557395935, 0.18918699026107788], "cos_apical_negg": [0.022576574236154556, 0.05874956399202347, 0.10831654816865921], "cos_Ac_negg": [0.16924500465393066, 0.19753403961658478, 0.18878859281539917], "r_norm": [0.16575463116168976, 0.16234257817268372, 0.16134923696517944]}, {"step": 5500, "epoch": 11, "train_loss": 0.0017908771988004446, "cos_r_negg": [0.16837087273597717, 0.19721250236034393, 0.187839075922966], "cos_apical_negg": [0.026299742981791496, 0.05963471531867981, 0.11012455821037292], "cos_Ac_negg": [0.16840282082557678, 0.19710946083068848, 0.18743689358234406], "r_norm": [0.1873452216386795, 0.1830121874809265, 0.18206292390823364], "ldr": {"dL_sdil": -0.009683892130851746, "dL_bp": -0.018616408109664917, "ratio": 0.5201804813155253}}, {"step": 5600, "epoch": 11, "train_loss": 0.0013754954561591148, "cos_r_negg": [0.1636376976966858, 0.19207163155078888, 0.18392041325569153], "cos_apical_negg": [0.02321229875087738, 0.057002753019332886, 0.10404518246650696], "cos_Ac_negg": [0.1637110710144043, 0.19200128316879272, 0.18356746435165405], "r_norm": [0.1753554493188858, 0.1717456877231598, 0.17066563665866852]}, {"epoch_end": 11, "step": 5628, "test_acc": 0.9729, "test_loss": 0.14531429138183594}, {"step": 5700, "epoch": 12, "train_loss": 0.0009287337306886911, "cos_r_negg": [0.16079433262348175, 0.18868830800056458, 0.18174007534980774], "cos_apical_negg": [0.02139887399971485, 0.057885367423295975, 0.10542373359203339], "cos_Ac_negg": [0.16087688505649567, 0.18858040869235992, 0.18139316141605377], "r_norm": [0.16926921904087067, 0.16593024134635925, 0.16500943899154663]}, {"step": 5800, "epoch": 12, "train_loss": 0.00030310082365758717, "cos_r_negg": [0.15898418426513672, 0.1867973506450653, 0.1785888373851776], "cos_apical_negg": [0.02138589508831501, 0.05659627914428711, 0.10516968369483948], "cos_Ac_negg": [0.15908759832382202, 0.18671759963035583, 0.1782454252243042], "r_norm": [0.17852672934532166, 0.17494000494480133, 0.1738014966249466]}, {"step": 5900, "epoch": 12, "train_loss": 0.001459339284338057, "cos_r_negg": [0.1598544418811798, 0.1872079074382782, 0.17989645898342133], "cos_apical_negg": [0.023842452093958855, 0.05727141723036766, 0.10314548015594482], "cos_Ac_negg": [0.15993618965148926, 0.18710944056510925, 0.17956651747226715], "r_norm": [0.1763380616903305, 0.17273308336734772, 0.17151713371276855]}, {"step": 6000, "epoch": 12, "train_loss": 0.00025371171068400145, "cos_r_negg": [0.1550983190536499, 0.1812928020954132, 0.17431369423866272], "cos_apical_negg": [0.02227218635380268, 0.05576448142528534, 0.10111168771982193], "cos_Ac_negg": [0.1551620364189148, 0.18118974566459656, 0.17398272454738617], "r_norm": [0.1751830279827118, 0.17173755168914795, 0.17048761248588562], "ldr": {"dL_sdil": -0.008753687143325806, "dL_bp": -0.01805989444255829, "ratio": 0.4847031177932951}}, {"epoch_end": 12, "step": 6097, "test_acc": 0.9725, "test_loss": 0.14830777206420898}, {"step": 6100, "epoch": 13, "train_loss": 0.0012382576242089272, "cos_r_negg": [0.1526487171649933, 0.1792762279510498, 0.17127978801727295], "cos_apical_negg": [0.019318794831633568, 0.055017780512571335, 0.09939050674438477], "cos_Ac_negg": [0.15276604890823364, 0.17921492457389832, 0.1709662675857544], "r_norm": [0.17004649341106415, 0.1664789319038391, 0.16549012064933777]}, {"step": 6200, "epoch": 13, "train_loss": 0.00042536837281659245, "cos_r_negg": [0.15009625256061554, 0.17631268501281738, 0.16910406947135925], "cos_apical_negg": [0.02108912542462349, 0.05487648397684097, 0.09703240543603897], "cos_Ac_negg": [0.150213360786438, 0.17624229192733765, 0.16879916191101074], "r_norm": [0.1764199584722519, 0.1728973090648651, 0.1716037541627884]}, {"step": 6300, "epoch": 13, "train_loss": 0.001201061299070716, "cos_r_negg": [0.1477968692779541, 0.1737002432346344, 0.16652484238147736], "cos_apical_negg": [0.020455854013562202, 0.054728034883737564, 0.09616195410490036], "cos_Ac_negg": [0.14792168140411377, 0.1736440360546112, 0.1662227213382721], "r_norm": [0.172653928399086, 0.1693204641342163, 0.16836033761501312]}, {"step": 6400, "epoch": 13, "train_loss": 0.00039902038406580687, "cos_r_negg": [0.1479041576385498, 0.17350591719150543, 0.1664724051952362], "cos_apical_negg": [0.018904881551861763, 0.054554253816604614, 0.09641586244106293], "cos_Ac_negg": [0.14803674817085266, 0.17345182597637177, 0.1661784052848816], "r_norm": [0.17616300284862518, 0.17270249128341675, 0.17161139845848083]}, {"step": 6500, "epoch": 13, "train_loss": 0.00016758985293563455, "cos_r_negg": [0.14824876189231873, 0.1737014353275299, 0.16627953946590424], "cos_apical_negg": [0.018250765278935432, 0.05398929864168167, 0.09398175776004791], "cos_Ac_negg": [0.14837145805358887, 0.17363858222961426, 0.16598375141620636], "r_norm": [0.17000073194503784, 0.1666126400232315, 0.16557259857654572], "ldr": {"dL_sdil": -0.00859159231185913, "dL_bp": -0.018522031605243683, "ratio": 0.4638579878800556}}, {"epoch_end": 13, "step": 6566, "test_acc": 0.973, "test_loss": 0.15130350227355957}, {"step": 6600, "epoch": 14, "train_loss": 0.00037631491431966424, "cos_r_negg": [0.14674055576324463, 0.17132018506526947, 0.1644669622182846], "cos_apical_negg": [0.01886620745062828, 0.05378362163901329, 0.0943530723452568], "cos_Ac_negg": [0.14686821401119232, 0.17125654220581055, 0.1641768217086792], "r_norm": [0.17951610684394836, 0.17604151368141174, 0.17475900053977966]}, {"step": 6700, "epoch": 14, "train_loss": 0.00028938663308508694, "cos_r_negg": [0.14904211461544037, 0.17376399040222168, 0.1669040471315384], "cos_apical_negg": [0.020278243348002434, 0.054608870297670364, 0.09475350379943848], "cos_Ac_negg": [0.14918139576911926, 0.17369869351387024, 0.1666075885295868], "r_norm": [0.1792440116405487, 0.17569801211357117, 0.17455503344535828]}, {"step": 6800, "epoch": 14, "train_loss": 0.0005413379985839128, "cos_r_negg": [0.1450190544128418, 0.16897258162498474, 0.1624162793159485], "cos_apical_negg": [0.019038885831832886, 0.05303763598203659, 0.09342364966869354], "cos_Ac_negg": [0.1451721489429474, 0.16892066597938538, 0.1621500551700592], "r_norm": [0.17567753791809082, 0.17228949069976807, 0.1711525321006775]}, {"step": 6900, "epoch": 14, "train_loss": 0.0007388935191556811, "cos_r_negg": [0.142916738986969, 0.16697654128074646, 0.1604384183883667], "cos_apical_negg": [0.019763367250561714, 0.052394505590200424, 0.09278304874897003], "cos_Ac_negg": [0.14305640757083893, 0.1669260412454605, 0.16018031537532806], "r_norm": [0.1767953783273697, 0.1734650731086731, 0.1722719371318817]}, {"step": 7000, "epoch": 14, "train_loss": 0.000649950176011771, "cos_r_negg": [0.1411450058221817, 0.16502931714057922, 0.15865254402160645], "cos_apical_negg": [0.01981346309185028, 0.053107645362615585, 0.09194252640008926], "cos_Ac_negg": [0.14126035571098328, 0.16497738659381866, 0.15838924050331116], "r_norm": [0.1810358315706253, 0.17778807878494263, 0.17635104060173035], "ldr": {"dL_sdil": -0.01009424775838852, "dL_bp": -0.02193962037563324, "ratio": 0.460092179607605}}, {"epoch_end": 14, "step": 7035, "test_acc": 0.9727, "test_loss": 0.15496361064910888}], "final": {"test_acc": 0.9727, "test_loss": 0.15496361064910888, "wall_s": 59.02428102493286, "cos_r_negg": [0.14169630408287048, 0.1655777096748352, 0.1592366099357605], "cos_apical_negg": [0.018531912937760353, 0.052661314606666565, 0.09144338220357895], "cos_Ac_negg": [0.14182420074939728, 0.1655307412147522, 0.15897312760353088]}}