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": 0.1, "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_rho0p1_res0_s0", "n_in": 784}, "provenance": {"git_commit": "54633b2e0f51a8f48d4ba627d778c87927f54ca1", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.3603768348693848, "cos_r_negg": [-0.018149716779589653, -0.026159491389989853, 0.03341463953256607], "cos_apical_negg": [-0.01817035675048828, -0.026294099166989326, 0.03202316164970398], "cos_Ac_negg": [-0.018149685114622116, -0.026159506291151047, 0.03341459482908249], "r_norm": [4.897443771362305, 4.8264689445495605, 4.823726177215576], "ldr": {"dL_sdil": -0.007371425628662109, "dL_bp": -0.22916293144226074, "ratio": 0.032166745216031564}}, {"step": 100, "epoch": 0, "train_loss": 0.2762371301651001, "cos_r_negg": [0.44541698694229126, 0.44750165939331055, 0.4498120844364166], "cos_apical_negg": [0.1863493025302887, 0.22645536065101624, 0.29871681332588196], "cos_Ac_negg": [0.44527506828308105, 0.4474462866783142, 0.4496145248413086], "r_norm": [0.8935065865516663, 0.8772377371788025, 0.8749199509620667]}, {"step": 200, "epoch": 0, "train_loss": 0.37479275465011597, "cos_r_negg": [0.44363704323768616, 0.4628668427467346, 0.5308301448822021], "cos_apical_negg": [0.17599457502365112, 0.20544520020484924, 0.33132797479629517], "cos_Ac_negg": [0.4437377452850342, 0.4631724953651428, 0.5308259129524231], "r_norm": [0.759809136390686, 0.744493842124939, 0.7407262325286865]}, {"step": 300, "epoch": 0, "train_loss": 0.2960105538368225, "cos_r_negg": [0.49565568566322327, 0.5042164325714111, 0.4768705368041992], "cos_apical_negg": [0.16109946370124817, 0.23191282153129578, 0.2783460319042206], "cos_Ac_negg": [0.49555158615112305, 0.5041651725769043, 0.47681987285614014], "r_norm": [0.7143169641494751, 0.7000225782394409, 0.6968193650245667]}, {"step": 400, "epoch": 0, "train_loss": 0.156812384724617, "cos_r_negg": [0.46017366647720337, 0.44548624753952026, 0.4824177622795105], "cos_apical_negg": [0.140870600938797, 0.16781483590602875, 0.2878004312515259], "cos_Ac_negg": [0.4601784944534302, 0.44544240832328796, 0.48233509063720703], "r_norm": [0.6665322780609131, 0.6561061143875122, 0.6546273231506348]}, {"epoch_end": 0, "step": 469, "test_acc": 0.9386, "test_loss": 0.24025605010986328}, {"step": 500, "epoch": 1, "train_loss": 0.1977778971195221, "cos_r_negg": [0.46847325563430786, 0.48639601469039917, 0.4975510835647583], "cos_apical_negg": [0.12961715459823608, 0.19412121176719666, 0.29938745498657227], "cos_Ac_negg": [0.468395471572876, 0.4863022565841675, 0.4973657727241516], "r_norm": [0.5680610537528992, 0.555564284324646, 0.5551686882972717], "ldr": {"dL_sdil": -0.009178996086120605, "dL_bp": -0.007929801940917969, "ratio": 1.1575315694527961}}, {"step": 600, "epoch": 1, "train_loss": 0.12994696199893951, "cos_r_negg": [0.40892812609672546, 0.44459545612335205, 0.49697914719581604], "cos_apical_negg": [0.1473712921142578, 0.18131253123283386, 0.28280460834503174], "cos_Ac_negg": [0.4088168442249298, 0.44452303647994995, 0.4969891905784607], "r_norm": [0.5339714288711548, 0.5249640345573425, 0.519861102104187]}, {"step": 700, "epoch": 1, "train_loss": 0.16491901874542236, "cos_r_negg": [0.4256364703178406, 0.440668523311615, 0.5330575704574585], "cos_apical_negg": [0.11386850476264954, 0.18758568167686462, 0.35666579008102417], "cos_Ac_negg": [0.42566782236099243, 0.4405771493911743, 0.5329521894454956], "r_norm": [0.5536546111106873, 0.5378513336181641, 0.5388550162315369]}, {"step": 800, "epoch": 1, "train_loss": 0.17110717296600342, "cos_r_negg": [0.4351373016834259, 0.43780046701431274, 0.576678454875946], "cos_apical_negg": [0.10322420299053192, 0.1988857090473175, 0.3974878191947937], "cos_Ac_negg": [0.43509441614151, 0.43770116567611694, 0.5765353441238403], "r_norm": [0.48688948154449463, 0.475961834192276, 0.4741421639919281]}, {"step": 900, "epoch": 1, "train_loss": 0.29496675729751587, "cos_r_negg": [0.48740899562835693, 0.47181832790374756, 0.5963932275772095], "cos_apical_negg": [0.10475624352693558, 0.2022893726825714, 0.4589501619338989], "cos_Ac_negg": [0.48739027976989746, 0.4717230498790741, 0.5962759852409363], "r_norm": [0.48102694749832153, 0.46774303913116455, 0.46749189496040344]}, {"epoch_end": 1, "step": 938, "test_acc": 0.9467, "test_loss": 0.21232797012329102}, {"step": 1000, "epoch": 2, "train_loss": 0.05081885680556297, "cos_r_negg": [0.4261878430843353, 0.4687647819519043, 0.5351234078407288], "cos_apical_negg": [0.08882705867290497, 0.14287811517715454, 0.41190072894096375], "cos_Ac_negg": [0.42612844705581665, 0.4686488211154938, 0.5350337028503418], "r_norm": [0.4382684528827667, 0.4267258942127228, 0.4252968430519104], "ldr": {"dL_sdil": -0.0077686309814453125, "dL_bp": -0.007604062557220459, "ratio": 1.021642171271801}}, {"step": 1100, "epoch": 2, "train_loss": 0.17293067276477814, "cos_r_negg": [0.42635345458984375, 0.436636745929718, 0.43410253524780273], "cos_apical_negg": [0.11521389335393906, 0.1451309621334076, 0.29686006903648376], "cos_Ac_negg": [0.42632269859313965, 0.43655574321746826, 0.4340246021747589], "r_norm": [0.4487457871437073, 0.4393031597137451, 0.43677783012390137]}, {"step": 1200, "epoch": 2, "train_loss": 0.20848479866981506, "cos_r_negg": [0.442474901676178, 0.45517247915267944, 0.5386346578598022], "cos_apical_negg": [0.09892383217811584, 0.16177767515182495, 0.4463983178138733], "cos_Ac_negg": [0.4423860013484955, 0.4550597071647644, 0.5385562181472778], "r_norm": [0.39272546768188477, 0.38346344232559204, 0.3823698163032532]}, {"step": 1300, "epoch": 2, "train_loss": 0.16447065770626068, "cos_r_negg": [0.4026065468788147, 0.4427296817302704, 0.4520164430141449], "cos_apical_negg": [0.1049981638789177, 0.16617241501808167, 0.43328726291656494], "cos_Ac_negg": [0.4025520086288452, 0.44268229603767395, 0.45195090770721436], "r_norm": [0.45160338282585144, 0.4402342140674591, 0.43770354986190796]}, {"step": 1400, "epoch": 2, "train_loss": 0.20390990376472473, "cos_r_negg": [0.3993721306324005, 0.4542754590511322, 0.4953177571296692], "cos_apical_negg": [0.06672823429107666, 0.1392410546541214, 0.37507134675979614], "cos_Ac_negg": [0.3993054926395416, 0.4541670083999634, 0.49529051780700684], "r_norm": [0.3890014886856079, 0.37828296422958374, 0.37614405155181885]}, {"epoch_end": 2, "step": 1407, "test_acc": 0.9554, "test_loss": 0.169120894241333}, {"step": 1500, "epoch": 3, "train_loss": 0.16671910881996155, "cos_r_negg": [0.4117174744606018, 0.4330917298793793, 0.48378750681877136], "cos_apical_negg": [0.0925174355506897, 0.15199881792068481, 0.3734169602394104], "cos_Ac_negg": [0.4117169976234436, 0.4330543875694275, 0.483761191368103], "r_norm": [0.3958891034126282, 0.38500869274139404, 0.38426539301872253], "ldr": {"dL_sdil": -0.005747601389884949, "dL_bp": -0.006682336330413818, "ratio": 0.8601185432294779}}, {"step": 1600, "epoch": 3, "train_loss": 0.12549501657485962, "cos_r_negg": [0.39289334416389465, 0.44915440678596497, 0.4579179883003235], "cos_apical_negg": [0.06114117428660393, 0.16337698698043823, 0.3305564522743225], "cos_Ac_negg": [0.39274075627326965, 0.4489688277244568, 0.45787423849105835], "r_norm": [0.3441646695137024, 0.334293395280838, 0.33339497447013855]}, {"step": 1700, "epoch": 3, "train_loss": 0.10290870815515518, "cos_r_negg": [0.35971707105636597, 0.4149544835090637, 0.41636937856674194], "cos_apical_negg": [0.10031169652938843, 0.17306800186634064, 0.3904416561126709], "cos_Ac_negg": [0.3596198856830597, 0.4148382544517517, 0.41626545786857605], "r_norm": [0.37432676553726196, 0.3625507652759552, 0.3613091707229614]}, {"step": 1800, "epoch": 3, "train_loss": 0.05377885699272156, "cos_r_negg": [0.3381999135017395, 0.39523470401763916, 0.40547239780426025], "cos_apical_negg": [0.07854337990283966, 0.1191946268081665, 0.3450331389904022], "cos_Ac_negg": [0.33815616369247437, 0.3951526880264282, 0.4054502546787262], "r_norm": [0.34665098786354065, 0.33539432287216187, 0.3357474207878113]}, {"epoch_end": 3, "step": 1876, "test_acc": 0.9568, "test_loss": 0.1756272834777832}, {"step": 1900, "epoch": 4, "train_loss": 0.053782038390636444, "cos_r_negg": [0.37742263078689575, 0.43863987922668457, 0.4813166856765747], "cos_apical_negg": [0.07947307825088501, 0.18122676014900208, 0.36060473322868347], "cos_Ac_negg": [0.3773921728134155, 0.4385415315628052, 0.4813358783721924], "r_norm": [0.3479138910770416, 0.34022289514541626, 0.3393150269985199]}, {"step": 2000, "epoch": 4, "train_loss": 0.1693098545074463, "cos_r_negg": [0.302074134349823, 0.36862003803253174, 0.3845616579055786], "cos_apical_negg": [0.05067247152328491, 0.09565144032239914, 0.30579322576522827], "cos_Ac_negg": [0.30201858282089233, 0.36856329441070557, 0.3845508396625519], "r_norm": [0.3478071987628937, 0.3374285101890564, 0.3365751802921295], "ldr": {"dL_sdil": -0.00672970712184906, "dL_bp": -0.007786288857460022, "ratio": 0.8643022683908453}}, {"step": 2100, "epoch": 4, "train_loss": 0.08755938708782196, "cos_r_negg": [0.36371514201164246, 0.3920271098613739, 0.4279513955116272], "cos_apical_negg": [0.10892920196056366, 0.14157618582248688, 0.35677605867385864], "cos_Ac_negg": [0.3636758625507355, 0.39195653796195984, 0.4279196560382843], "r_norm": [0.38288623094558716, 0.37204116582870483, 0.3697913885116577]}, {"step": 2200, "epoch": 4, "train_loss": 0.032282549887895584, "cos_r_negg": [0.32277482748031616, 0.37331444025039673, 0.4008542001247406], "cos_apical_negg": [0.05109245330095291, 0.10842463374137878, 0.3036212921142578], "cos_Ac_negg": [0.3227275311946869, 0.3732089698314667, 0.40080153942108154], "r_norm": [0.3336029350757599, 0.3244991898536682, 0.32251161336898804]}, {"step": 2300, "epoch": 4, "train_loss": 0.31710344552993774, "cos_r_negg": [0.3238556683063507, 0.3977438509464264, 0.4312130808830261], "cos_apical_negg": [0.08798874914646149, 0.1668751835823059, 0.30054429173469543], "cos_Ac_negg": [0.3237970471382141, 0.39765965938568115, 0.4312444031238556], "r_norm": [0.3623567819595337, 0.35056763887405396, 0.3507392406463623]}, {"epoch_end": 4, "step": 2345, "test_acc": 0.9556, "test_loss": 0.18188404693603516}, {"step": 2400, "epoch": 5, "train_loss": 0.10923928767442703, "cos_r_negg": [0.3178540766239166, 0.37013620138168335, 0.4150301218032837], "cos_apical_negg": [0.03521845489740372, 0.1222638338804245, 0.2965596914291382], "cos_Ac_negg": [0.3178318738937378, 0.3700489103794098, 0.4150121510028839], "r_norm": [0.3304583728313446, 0.3197857141494751, 0.3196999132633209]}, {"step": 2500, "epoch": 5, "train_loss": 0.04513147100806236, "cos_r_negg": [0.29577139019966125, 0.36760804057121277, 0.3441578447818756], "cos_apical_negg": [0.06950408965349197, 0.13895860314369202, 0.2978608012199402], "cos_Ac_negg": [0.29578518867492676, 0.3675388991832733, 0.3440762162208557], "r_norm": [0.3791693150997162, 0.368236243724823, 0.36595118045806885], "ldr": {"dL_sdil": -0.009107112884521484, "dL_bp": -0.009832099080085754, "ratio": 0.9262633350560228}}, {"step": 2600, "epoch": 5, "train_loss": 0.0934981182217598, "cos_r_negg": [0.3214896321296692, 0.39022743701934814, 0.3800325393676758], "cos_apical_negg": [0.05411633104085922, 0.14016154408454895, 0.3429078757762909], "cos_Ac_negg": [0.32152223587036133, 0.390146404504776, 0.37996140122413635], "r_norm": [0.3271043300628662, 0.31700441241264343, 0.31523042917251587]}, {"step": 2700, "epoch": 5, "train_loss": 0.0971001386642456, "cos_r_negg": [0.3392976224422455, 0.38967713713645935, 0.39619553089141846], "cos_apical_negg": [0.0893879234790802, 0.1420595794916153, 0.2971969246864319], "cos_Ac_negg": [0.33929216861724854, 0.3896039128303528, 0.39616307616233826], "r_norm": [0.35043787956237793, 0.33896341919898987, 0.34025537967681885]}, {"step": 2800, "epoch": 5, "train_loss": 0.1256164312362671, "cos_r_negg": [0.3236563801765442, 0.37178584933280945, 0.42420494556427], "cos_apical_negg": [0.0778699517250061, 0.1484702229499817, 0.3644770681858063], "cos_Ac_negg": [0.32358455657958984, 0.3716598153114319, 0.4241813123226166], "r_norm": [0.3412046432495117, 0.32874637842178345, 0.32860463857650757]}, {"epoch_end": 5, "step": 2814, "test_acc": 0.9564, "test_loss": 0.1780750129699707}, {"step": 2900, "epoch": 6, "train_loss": 0.041379958391189575, "cos_r_negg": [0.27906250953674316, 0.34929847717285156, 0.4314815402030945], "cos_apical_negg": [0.0627644956111908, 0.17768119275569916, 0.3501538634300232], "cos_Ac_negg": [0.2790553569793701, 0.34919771552085876, 0.4314073622226715], "r_norm": [0.34956032037734985, 0.3371644616127014, 0.3382599353790283]}, {"step": 3000, "epoch": 6, "train_loss": 0.34214505553245544, "cos_r_negg": [0.27627718448638916, 0.3222602605819702, 0.3395204544067383], "cos_apical_negg": [0.053199075162410736, 0.09846411645412445, 0.2411688268184662], "cos_Ac_negg": [0.2762613296508789, 0.32217276096343994, 0.3394371271133423], "r_norm": [0.30777665972709656, 0.2951382100582123, 0.295731782913208], "ldr": {"dL_sdil": -0.004803195595741272, "dL_bp": -0.006155624985694885, "ratio": 0.7802937324647722}}, {"step": 3100, "epoch": 6, "train_loss": 0.1299528181552887, "cos_r_negg": [0.2844964563846588, 0.2894437909126282, 0.4082588255405426], "cos_apical_negg": [0.07756244391202927, 0.11715252697467804, 0.1790253221988678], "cos_Ac_negg": [0.28450191020965576, 0.2893946170806885, 0.40820980072021484], "r_norm": [0.35087454319000244, 0.3400832414627075, 0.3381013572216034]}, {"step": 3200, "epoch": 6, "train_loss": 0.14603891968727112, "cos_r_negg": [0.30431196093559265, 0.3414464592933655, 0.3532407879829407], "cos_apical_negg": [0.05583346262574196, 0.08824919164180756, 0.1684969961643219], "cos_Ac_negg": [0.30429357290267944, 0.34138715267181396, 0.3532252013683319], "r_norm": [0.2956363558769226, 0.28516098856925964, 0.28568029403686523]}, {"epoch_end": 6, "step": 3283, "test_acc": 0.9572, "test_loss": 0.1773396816253662}, {"step": 3300, "epoch": 7, "train_loss": 0.060805972665548325, "cos_r_negg": [0.28383898735046387, 0.3337588310241699, 0.36710286140441895], "cos_apical_negg": [0.043250832706689835, 0.1290111243724823, 0.23789039254188538], "cos_Ac_negg": [0.2838148772716522, 0.33361512422561646, 0.3670954704284668], "r_norm": [0.2922723889350891, 0.2817229926586151, 0.2819357216358185]}, {"step": 3400, "epoch": 7, "train_loss": 0.2055455446243286, "cos_r_negg": [0.27874404191970825, 0.3272626996040344, 0.3254462778568268], "cos_apical_negg": [0.08251073956489563, 0.10467558354139328, 0.20164358615875244], "cos_Ac_negg": [0.2786571681499481, 0.3271692991256714, 0.32538002729415894], "r_norm": [0.31691062450408936, 0.3045899569988251, 0.30485498905181885]}, {"step": 3500, "epoch": 7, "train_loss": 0.10245728492736816, "cos_r_negg": [0.26824331283569336, 0.32757097482681274, 0.3487533926963806], "cos_apical_negg": [0.0619991160929203, 0.09457815438508987, 0.21863090991973877], "cos_Ac_negg": [0.2682163417339325, 0.32750052213668823, 0.34871795773506165], "r_norm": [0.3403148651123047, 0.32707229256629944, 0.32713019847869873], "ldr": {"dL_sdil": -0.006241738796234131, "dL_bp": -0.0080699622631073, "ratio": 0.7734532817791367}}, {"step": 3600, "epoch": 7, "train_loss": 0.03638872131705284, "cos_r_negg": [0.27593857049942017, 0.31196749210357666, 0.32632380723953247], "cos_apical_negg": [0.032105714082717896, 0.08662648499011993, 0.23128540813922882], "cos_Ac_negg": [0.27592968940734863, 0.31189513206481934, 0.32622987031936646], "r_norm": [0.3004930019378662, 0.2896602153778076, 0.28952687978744507]}, {"step": 3700, "epoch": 7, "train_loss": 0.06841079145669937, "cos_r_negg": [0.27148646116256714, 0.33184802532196045, 0.3303089737892151], "cos_apical_negg": [0.04844781011343002, 0.10810357332229614, 0.2396182119846344], "cos_Ac_negg": [0.27147847414016724, 0.33177340030670166, 0.3302474319934845], "r_norm": [0.31027713418006897, 0.29871368408203125, 0.2979956269264221]}, {"epoch_end": 7, "step": 3752, "test_acc": 0.9594, "test_loss": 0.17211565971374512}, {"step": 3800, "epoch": 8, "train_loss": 0.055494487285614014, "cos_r_negg": [0.2379501610994339, 0.28925734758377075, 0.3242334723472595], "cos_apical_negg": [0.04948269948363304, 0.10142925381660461, 0.28163570165634155], "cos_Ac_negg": [0.23792357742786407, 0.28920406103134155, 0.32419145107269287], "r_norm": [0.2887183427810669, 0.27809247374534607, 0.2782195508480072]}, {"step": 3900, "epoch": 8, "train_loss": 0.2021137773990631, "cos_r_negg": [0.2594875991344452, 0.31504377722740173, 0.312594473361969], "cos_apical_negg": [0.026851417496800423, 0.09658454358577728, 0.21139296889305115], "cos_Ac_negg": [0.2594544291496277, 0.31502121686935425, 0.3125804662704468], "r_norm": [0.31115344166755676, 0.2986151874065399, 0.2989969253540039]}, {"step": 4000, "epoch": 8, "train_loss": 0.09608633816242218, "cos_r_negg": [0.2210184931755066, 0.26909708976745605, 0.27979251742362976], "cos_apical_negg": [0.037123903632164, 0.07577767968177795, 0.1690133959054947], "cos_Ac_negg": [0.22095856070518494, 0.2690652310848236, 0.2797449827194214], "r_norm": [0.2945510149002075, 0.2837965488433838, 0.2839779853820801], "ldr": {"dL_sdil": -0.004758194088935852, "dL_bp": -0.0057487934827804565, "ratio": 0.8276856879949196}}, {"step": 4100, "epoch": 8, "train_loss": 0.04448690265417099, "cos_r_negg": [0.24987395107746124, 0.3037770092487335, 0.3241797089576721], "cos_apical_negg": [0.03907449543476105, 0.0750594288110733, 0.2098713219165802], "cos_Ac_negg": [0.24984955787658691, 0.30371013283729553, 0.3241608738899231], "r_norm": [0.28570955991744995, 0.2731584310531616, 0.27527064085006714]}, {"step": 4200, "epoch": 8, "train_loss": 0.21926257014274597, "cos_r_negg": [0.2690197825431824, 0.3184193968772888, 0.30807825922966003], "cos_apical_negg": [0.051653966307640076, 0.09576829522848129, 0.22929464280605316], "cos_Ac_negg": [0.2690441608428955, 0.31837600469589233, 0.308036744594574], "r_norm": [0.30632734298706055, 0.295185387134552, 0.29503560066223145]}, {"epoch_end": 8, "step": 4221, "test_acc": 0.9591, "test_loss": 0.18215001335144043}, {"step": 4300, "epoch": 9, "train_loss": 0.06056637316942215, "cos_r_negg": [0.2375640720129013, 0.2759319543838501, 0.3089990019798279], "cos_apical_negg": [0.03297046944499016, 0.09315337240695953, 0.19694852828979492], "cos_Ac_negg": [0.2375570833683014, 0.2758650481700897, 0.3090273141860962], "r_norm": [0.28082606196403503, 0.26998332142829895, 0.27087530493736267]}, {"step": 4400, "epoch": 9, "train_loss": 0.057083841413259506, "cos_r_negg": [0.2541005611419678, 0.308647096157074, 0.3306451439857483], "cos_apical_negg": [0.03590516746044159, 0.07734210789203644, 0.20197394490242004], "cos_Ac_negg": [0.2541109323501587, 0.3086484670639038, 0.3306594491004944], "r_norm": [0.32942909002304077, 0.31473660469055176, 0.317359983921051]}, {"step": 4500, "epoch": 9, "train_loss": 0.17264485359191895, "cos_r_negg": [0.20887184143066406, 0.26254981756210327, 0.2650260925292969], "cos_apical_negg": [0.029389288276433945, 0.09439267218112946, 0.2195759117603302], "cos_Ac_negg": [0.20885686576366425, 0.2624436318874359, 0.2650618553161621], "r_norm": [0.3040929138660431, 0.29136353731155396, 0.2927548289299011], "ldr": {"dL_sdil": -0.005173087120056152, "dL_bp": -0.00791679322719574, "ratio": 0.6534321374323105}}, {"step": 4600, "epoch": 9, "train_loss": 0.0752175971865654, "cos_r_negg": [0.22289590537548065, 0.2698022127151489, 0.28208571672439575], "cos_apical_negg": [0.03619851917028427, 0.085477314889431, 0.24939176440238953], "cos_Ac_negg": [0.2228788584470749, 0.2697603702545166, 0.2820448577404022], "r_norm": [0.31468111276626587, 0.3012823462486267, 0.3018352687358856]}, {"epoch_end": 9, "step": 4690, "test_acc": 0.9591, "test_loss": 0.18390218124389648}, {"step": 4700, "epoch": 10, "train_loss": 0.07721929252147675, "cos_r_negg": [0.1966843456029892, 0.23706476390361786, 0.2741895318031311], "cos_apical_negg": [0.04599922522902489, 0.06404320150613785, 0.14993104338645935], "cos_Ac_negg": [0.1966865360736847, 0.23700743913650513, 0.2741366922855377], "r_norm": [0.27993515133857727, 0.26831120252609253, 0.2700636386871338]}, {"step": 4800, "epoch": 10, "train_loss": 0.04933841526508331, "cos_r_negg": [0.22418658435344696, 0.26583805680274963, 0.3130151033401489], "cos_apical_negg": [0.046518005430698395, 0.0524347648024559, 0.1983204036951065], "cos_Ac_negg": [0.22416317462921143, 0.26579636335372925, 0.3130127489566803], "r_norm": [0.2925627827644348, 0.2816404104232788, 0.28210076689720154]}, {"step": 4900, "epoch": 10, "train_loss": 0.03420368582010269, "cos_r_negg": [0.18807004392147064, 0.23366165161132812, 0.27562859654426575], "cos_apical_negg": [0.03951200097799301, 0.09651213139295578, 0.17248132824897766], "cos_Ac_negg": [0.1880582720041275, 0.23363134264945984, 0.27558690309524536], "r_norm": [0.2823236584663391, 0.27097827196121216, 0.27296847105026245]}, {"step": 5000, "epoch": 10, "train_loss": 0.04745296761393547, "cos_r_negg": [0.2138243317604065, 0.2755025625228882, 0.3482120633125305], "cos_apical_negg": [0.037016212940216064, 0.0758054107427597, 0.25266584753990173], "cos_Ac_negg": [0.21386215090751648, 0.27552640438079834, 0.3482104539871216], "r_norm": [0.3235507309436798, 0.30904749035835266, 0.3109239935874939], "ldr": {"dL_sdil": -0.0061250776052474976, "dL_bp": -0.00871327519416809, "ratio": 0.7029592740680441}}, {"step": 5100, "epoch": 10, "train_loss": 0.07249965518712997, "cos_r_negg": [0.22767964005470276, 0.26825857162475586, 0.2804119884967804], "cos_apical_negg": [0.04583592712879181, 0.08559513092041016, 0.15423330664634705], "cos_Ac_negg": [0.22763952612876892, 0.268194317817688, 0.28042399883270264], "r_norm": [0.291387677192688, 0.28049182891845703, 0.28076058626174927]}, {"epoch_end": 10, "step": 5159, "test_acc": 0.9587, "test_loss": 0.18065969924926759}, {"step": 5200, "epoch": 11, "train_loss": 0.017667211592197418, "cos_r_negg": [0.2213592827320099, 0.27206921577453613, 0.29410693049430847], "cos_apical_negg": [0.056591518223285675, 0.08806470781564713, 0.14317181706428528], "cos_Ac_negg": [0.22131603956222534, 0.2720063626766205, 0.2940799593925476], "r_norm": [0.2979279160499573, 0.2849676012992859, 0.28668737411499023]}, {"step": 5300, "epoch": 11, "train_loss": 0.07039394974708557, "cos_r_negg": [0.21036005020141602, 0.2557890713214874, 0.3030744791030884], "cos_apical_negg": [0.047831885516643524, 0.1077776849269867, 0.1418984830379486], "cos_Ac_negg": [0.21038542687892914, 0.25579971075057983, 0.303048312664032], "r_norm": [0.29446399211883545, 0.28210651874542236, 0.28310051560401917]}, {"step": 5400, "epoch": 11, "train_loss": 0.1389809548854828, "cos_r_negg": [0.18942250311374664, 0.24828064441680908, 0.2568184733390808], "cos_apical_negg": [0.017937052994966507, 0.07540638744831085, 0.16169123351573944], "cos_Ac_negg": [0.1894456148147583, 0.2482515573501587, 0.256881982088089], "r_norm": [0.26323065161705017, 0.25284603238105774, 0.25425899028778076]}, {"step": 5500, "epoch": 11, "train_loss": 0.07426370680332184, "cos_r_negg": [0.21561381220817566, 0.24225088953971863, 0.28007450699806213], "cos_apical_negg": [0.044352926313877106, 0.07818645238876343, 0.1871023327112198], "cos_Ac_negg": [0.21556456387043, 0.24218611419200897, 0.28008145093917847], "r_norm": [0.2965092360973358, 0.2840360999107361, 0.2850237786769867], "ldr": {"dL_sdil": -0.006513118743896484, "dL_bp": -0.010754704475402832, "ratio": 0.6056064821485972}}, {"step": 5600, "epoch": 11, "train_loss": 0.010568395256996155, "cos_r_negg": [0.21170857548713684, 0.24074894189834595, 0.26868629455566406], "cos_apical_negg": [0.03770392760634422, 0.0757589116692543, 0.16171687841415405], "cos_Ac_negg": [0.2116708755493164, 0.24069292843341827, 0.26865971088409424], "r_norm": [0.2969200611114502, 0.28489241003990173, 0.28569772839546204]}, {"epoch_end": 11, "step": 5628, "test_acc": 0.9601, "test_loss": 0.18408200645446776}, {"step": 5700, "epoch": 12, "train_loss": 0.05423484742641449, "cos_r_negg": [0.20610107481479645, 0.250031054019928, 0.26989874243736267], "cos_apical_negg": [0.03498787060379982, 0.08079690486192703, 0.2153046429157257], "cos_Ac_negg": [0.20606306195259094, 0.25000301003456116, 0.2700352668762207], "r_norm": [0.26945945620536804, 0.2579163908958435, 0.2595214247703552]}, {"step": 5800, "epoch": 12, "train_loss": 0.03092847391963005, "cos_r_negg": [0.20888328552246094, 0.2365681380033493, 0.29691624641418457], "cos_apical_negg": [0.04725015163421631, 0.08541767299175262, 0.17507749795913696], "cos_Ac_negg": [0.2088392674922943, 0.2365473508834839, 0.29690492153167725], "r_norm": [0.27622243762016296, 0.2644508481025696, 0.2654731273651123]}, {"step": 5900, "epoch": 12, "train_loss": 0.034352608025074005, "cos_r_negg": [0.17960354685783386, 0.2192736566066742, 0.26465660333633423], "cos_apical_negg": [0.04020436108112335, 0.06893104314804077, 0.16025002300739288], "cos_Ac_negg": [0.17960572242736816, 0.21927610039710999, 0.2646784782409668], "r_norm": [0.2822814881801605, 0.2698795795440674, 0.2713061571121216]}, {"step": 6000, "epoch": 12, "train_loss": 0.030067335814237595, "cos_r_negg": [0.19201797246932983, 0.2104051113128662, 0.30097487568855286], "cos_apical_negg": [0.055199034512043, 0.08216610550880432, 0.16139814257621765], "cos_Ac_negg": [0.1920022815465927, 0.21032708883285522, 0.30093929171562195], "r_norm": [0.31174176931381226, 0.2978854477405548, 0.2987750172615051], "ldr": {"dL_sdil": -0.00710730254650116, "dL_bp": -0.009356006979942322, "ratio": 0.7596512659447562}}, {"epoch_end": 12, "step": 6097, "test_acc": 0.9615, "test_loss": 0.18627358894348145}, {"step": 6100, "epoch": 13, "train_loss": 0.04072863608598709, "cos_r_negg": [0.17546366155147552, 0.21122168004512787, 0.24398577213287354], "cos_apical_negg": [0.0411820262670517, 0.05403941124677658, 0.17221496999263763], "cos_Ac_negg": [0.1754714548587799, 0.21115264296531677, 0.24401018023490906], "r_norm": [0.270816832780838, 0.25968310236930847, 0.26091817021369934]}, {"step": 6200, "epoch": 13, "train_loss": 0.0243786983191967, "cos_r_negg": [0.1795467734336853, 0.21211552619934082, 0.24943940341472626], "cos_apical_negg": [0.016638685017824173, 0.06957788020372391, 0.18678492307662964], "cos_Ac_negg": [0.17955666780471802, 0.2120814323425293, 0.24953234195709229], "r_norm": [0.25884437561035156, 0.2469954490661621, 0.2491001933813095]}, {"step": 6300, "epoch": 13, "train_loss": 0.08152099698781967, "cos_r_negg": [0.1668044626712799, 0.19989478588104248, 0.2628723680973053], "cos_apical_negg": [0.028372405096888542, 0.05827978998422623, 0.15671584010124207], "cos_Ac_negg": [0.16669470071792603, 0.1998569369316101, 0.2628690004348755], "r_norm": [0.27642008662223816, 0.2646355628967285, 0.26592689752578735]}, {"step": 6400, "epoch": 13, "train_loss": 0.0580926239490509, "cos_r_negg": [0.19312119483947754, 0.22229841351509094, 0.2774145305156708], "cos_apical_negg": [0.032133400440216064, 0.0813821405172348, 0.1635916829109192], "cos_Ac_negg": [0.19315162301063538, 0.22226916253566742, 0.2774478495121002], "r_norm": [0.30658918619155884, 0.2912878692150116, 0.2935417890548706]}, {"step": 6500, "epoch": 13, "train_loss": 0.005591629538685083, "cos_r_negg": [0.1965150237083435, 0.23062925040721893, 0.24952132999897003], "cos_apical_negg": [0.047904156148433685, 0.0537736751139164, 0.12270792573690414], "cos_Ac_negg": [0.19651466608047485, 0.23068967461585999, 0.2494906634092331], "r_norm": [0.2683509290218353, 0.2550716698169708, 0.2575607895851135], "ldr": {"dL_sdil": -0.005764961242675781, "dL_bp": -0.009291961789131165, "ratio": 0.6204245533401863}}, {"epoch_end": 13, "step": 6566, "test_acc": 0.9602, "test_loss": 0.1887426570892334}, {"step": 6600, "epoch": 14, "train_loss": 0.033564284443855286, "cos_r_negg": [0.15905055403709412, 0.21370354294776917, 0.24354621767997742], "cos_apical_negg": [0.037060972303152084, 0.04435315728187561, 0.1333831399679184], "cos_Ac_negg": [0.1589794009923935, 0.2136426568031311, 0.243565171957016], "r_norm": [0.2601277828216553, 0.2484085112810135, 0.24964506924152374]}, {"step": 6700, "epoch": 14, "train_loss": 0.057931434363126755, "cos_r_negg": [0.17561273276805878, 0.21444493532180786, 0.26210662722587585], "cos_apical_negg": [0.026238270103931427, 0.05927834287285805, 0.17970684170722961], "cos_Ac_negg": [0.17562194168567657, 0.2144266963005066, 0.26206517219543457], "r_norm": [0.28001832962036133, 0.26702648401260376, 0.2682105302810669]}, {"step": 6800, "epoch": 14, "train_loss": 0.08162819594144821, "cos_r_negg": [0.1556033492088318, 0.20279154181480408, 0.2468697875738144], "cos_apical_negg": [0.04083441197872162, 0.07081535458564758, 0.10019386559724808], "cos_Ac_negg": [0.15570971369743347, 0.20281541347503662, 0.2469877153635025], "r_norm": [0.275912344455719, 0.26399606466293335, 0.2650752663612366]}, {"step": 6900, "epoch": 14, "train_loss": 0.043335363268852234, "cos_r_negg": [0.15936440229415894, 0.20607733726501465, 0.23480677604675293], "cos_apical_negg": [0.025776928290724754, 0.06425251811742783, 0.13836276531219482], "cos_Ac_negg": [0.15931743383407593, 0.20606312155723572, 0.23489713668823242], "r_norm": [0.26348352432250977, 0.25113725662231445, 0.25322505831718445]}, {"step": 7000, "epoch": 14, "train_loss": 0.07403210550546646, "cos_r_negg": [0.1728387176990509, 0.22299912571907043, 0.2353971302509308], "cos_apical_negg": [0.046100541949272156, 0.07392027974128723, 0.13622358441352844], "cos_Ac_negg": [0.17284350097179413, 0.2229929268360138, 0.23542022705078125], "r_norm": [0.27658048272132874, 0.264566034078598, 0.2655790448188782], "ldr": {"dL_sdil": -0.004432976245880127, "dL_bp": -0.0077589452266693115, "ratio": 0.5713374842037742}}, {"epoch_end": 14, "step": 7035, "test_acc": 0.9587, "test_loss": 0.1950464973449707}], "final": {"test_acc": 0.9587, "test_loss": 0.1950464973449707, "wall_s": 43.170592069625854, "cos_r_negg": [0.15515871345996857, 0.19200049340724945, 0.23033785820007324], "cos_apical_negg": [0.04083329066634178, 0.06870468705892563, 0.09320558607578278], "cos_Ac_negg": [0.15518587827682495, 0.19202908873558044, 0.23038293421268463]}}
|