{"args": {"mode": "bp", "dataset": "mnist", "depth": 2, "width": 500, "act": "tanh", "residual": 0, "epochs": 60, "batch_size": 128, "train_examples": 50000, "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": 16, "pert_mode": "simultaneous", "use_residual": 1, "raw_scale_control": "none", "learn_A": 1, "learn_P": 1, "p_neutral": 1, "p_warmup_steps": 200, "p_warmup_eta": 0.05, "nuis_rho": 0.0, "predictor_mode": "diagonal", "normalize_delta": 0, "settle_steps": 0, "kappa": 0.0, "feedback": "error", "seed": 4, "device": "cuda", "log_every": 50, "max_steps": 0, "probe_bs": 512, "outdir": "results", "tag": "ep_depth2_v1_mnist_bp_w500_d2_s4", "n_in": 784}, "provenance": {"git_commit": "f2b6107e20975aa649c4ab36b3faab21d1e3c281", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.291302442550659}, {"step": 50, "epoch": 0, "train_loss": 0.39364296197891235}, {"step": 100, "epoch": 0, "train_loss": 0.1469763070344925}, {"step": 150, "epoch": 0, "train_loss": 0.2302943766117096}, {"step": 200, "epoch": 0, "train_loss": 0.21935664117336273}, {"step": 250, "epoch": 0, "train_loss": 0.25212544202804565}, {"step": 300, "epoch": 0, "train_loss": 0.1246330663561821}, {"step": 350, "epoch": 0, "train_loss": 0.18833714723587036}, {"epoch_end": 0, "step": 391, "test_acc": 0.9601, "test_loss": 0.13104409790039062}, {"step": 400, "epoch": 1, "train_loss": 0.10538937896490097}, {"step": 450, "epoch": 1, "train_loss": 0.09758008271455765}, {"step": 500, "epoch": 1, "train_loss": 0.14763130247592926}, {"step": 550, "epoch": 1, "train_loss": 0.051217399537563324}, {"step": 600, "epoch": 1, "train_loss": 0.035290010273456573}, {"step": 650, "epoch": 1, "train_loss": 0.04214641824364662}, {"step": 700, "epoch": 1, "train_loss": 0.07102253288030624}, {"step": 750, "epoch": 1, "train_loss": 0.12612642347812653}, {"epoch_end": 1, "step": 782, "test_acc": 0.9545, "test_loss": 0.14070011444091796}, {"step": 800, "epoch": 2, "train_loss": 0.03583225980401039}, {"step": 850, "epoch": 2, "train_loss": 0.04256102442741394}, {"step": 900, "epoch": 2, "train_loss": 0.03639531880617142}, {"step": 950, "epoch": 2, "train_loss": 0.08152765035629272}, {"step": 1000, "epoch": 2, "train_loss": 0.05228731781244278}, {"step": 1050, "epoch": 2, "train_loss": 0.01867414079606533}, {"step": 1100, "epoch": 2, "train_loss": 0.0894116684794426}, {"step": 1150, "epoch": 2, "train_loss": 0.08133216947317123}, {"epoch_end": 2, "step": 1173, "test_acc": 0.9732, "test_loss": 0.08426325883865357}, {"step": 1200, "epoch": 3, "train_loss": 0.022250648587942123}, {"step": 1250, "epoch": 3, "train_loss": 0.04134953022003174}, {"step": 1300, "epoch": 3, "train_loss": 0.002860091859474778}, {"step": 1350, "epoch": 3, "train_loss": 0.02243887074291706}, {"step": 1400, "epoch": 3, "train_loss": 0.03783981502056122}, {"step": 1450, "epoch": 3, "train_loss": 0.019108053296804428}, {"step": 1500, "epoch": 3, "train_loss": 0.04740138351917267}, {"step": 1550, "epoch": 3, "train_loss": 0.007123575545847416}, {"epoch_end": 3, "step": 1564, "test_acc": 0.9753, "test_loss": 0.08500791492462158}, {"step": 1600, "epoch": 4, "train_loss": 0.011419685557484627}, {"step": 1650, "epoch": 4, "train_loss": 0.03584011644124985}, {"step": 1700, "epoch": 4, "train_loss": 0.02678517811000347}, {"step": 1750, "epoch": 4, "train_loss": 0.008792899549007416}, {"step": 1800, "epoch": 4, "train_loss": 0.013370592147111893}, {"step": 1850, "epoch": 4, "train_loss": 0.0402667373418808}, {"step": 1900, "epoch": 4, "train_loss": 0.017590802162885666}, {"step": 1950, "epoch": 4, "train_loss": 0.029321851208806038}, {"epoch_end": 4, "step": 1955, "test_acc": 0.9775, "test_loss": 0.07419840393066406}, {"step": 2000, "epoch": 5, "train_loss": 0.02428915537893772}, {"step": 2050, "epoch": 5, "train_loss": 0.01204412616789341}, {"step": 2100, "epoch": 5, "train_loss": 0.0032445755787193775}, {"step": 2150, "epoch": 5, "train_loss": 0.001119991997256875}, {"step": 2200, "epoch": 5, "train_loss": 0.006751333829015493}, {"step": 2250, "epoch": 5, "train_loss": 0.00258468184620142}, {"step": 2300, "epoch": 5, "train_loss": 0.002865246031433344}, {"epoch_end": 5, "step": 2346, "test_acc": 0.9816, "test_loss": 0.06624412927627564}, {"step": 2350, "epoch": 6, "train_loss": 0.001674018451012671}, {"step": 2400, "epoch": 6, "train_loss": 0.0016474288422614336}, {"step": 2450, "epoch": 6, "train_loss": 0.0033407381270080805}, {"step": 2500, "epoch": 6, "train_loss": 0.0022942584473639727}, {"step": 2550, "epoch": 6, "train_loss": 0.004713284317404032}, {"step": 2600, "epoch": 6, "train_loss": 0.0009024733444675803}, {"step": 2650, "epoch": 6, "train_loss": 0.0016742912121117115}, {"step": 2700, "epoch": 6, "train_loss": 0.0017572323558852077}, {"epoch_end": 6, "step": 2737, "test_acc": 0.982, "test_loss": 0.06408412280082702}, {"step": 2750, "epoch": 7, "train_loss": 0.00019542236987035722}, {"step": 2800, "epoch": 7, "train_loss": 0.0002920048136729747}, {"step": 2850, "epoch": 7, "train_loss": 0.0005332455621100962}, {"step": 2900, "epoch": 7, "train_loss": 0.0009066697675734758}, {"step": 2950, "epoch": 7, "train_loss": 0.0004573145997710526}, {"step": 3000, "epoch": 7, "train_loss": 0.0005032937624491751}, {"step": 3050, "epoch": 7, "train_loss": 0.0014907000586390495}, {"step": 3100, "epoch": 7, "train_loss": 0.0003606841783039272}, {"epoch_end": 7, "step": 3128, "test_acc": 0.9821, "test_loss": 0.0636427788734436}, {"step": 3150, "epoch": 8, "train_loss": 0.0008699899190105498}, {"step": 3200, "epoch": 8, "train_loss": 0.0008689676178619266}, {"step": 3250, "epoch": 8, "train_loss": 0.0006030146032571793}, {"step": 3300, "epoch": 8, "train_loss": 0.0007159017841331661}, {"step": 3350, "epoch": 8, "train_loss": 0.0016930368728935719}, {"step": 3400, "epoch": 8, "train_loss": 0.0007102179806679487}, {"step": 3450, "epoch": 8, "train_loss": 0.0011278390884399414}, {"step": 3500, "epoch": 8, "train_loss": 0.0010142205283045769}, {"epoch_end": 8, "step": 3519, "test_acc": 0.9821, "test_loss": 0.06381717040538788}, {"step": 3550, "epoch": 9, "train_loss": 0.0004911221330985427}, {"step": 3600, "epoch": 9, "train_loss": 0.00043511827243492007}, {"step": 3650, "epoch": 9, "train_loss": 0.0010022508213296533}, {"step": 3700, "epoch": 9, "train_loss": 0.0009125139913521707}, {"step": 3750, "epoch": 9, "train_loss": 0.0006748156156390905}, {"step": 3800, "epoch": 9, "train_loss": 0.0003099168825428933}, {"step": 3850, "epoch": 9, "train_loss": 0.0010234840447083116}, {"step": 3900, "epoch": 9, "train_loss": 0.00039469084003940225}, {"epoch_end": 9, "step": 3910, "test_acc": 0.9822, "test_loss": 0.0643073212146759}, {"step": 3950, "epoch": 10, "train_loss": 0.00044396251905709505}, {"step": 4000, "epoch": 10, "train_loss": 0.0007221153355203569}, {"step": 4050, "epoch": 10, "train_loss": 0.0005764525267295539}, {"step": 4100, "epoch": 10, "train_loss": 0.00047138077206909657}, {"step": 4150, "epoch": 10, "train_loss": 0.00027936589322052896}, {"step": 4200, "epoch": 10, "train_loss": 0.00046803729492239654}, {"step": 4250, "epoch": 10, "train_loss": 0.0008994791423901916}, {"step": 4300, "epoch": 10, "train_loss": 0.0007740232395008206}, {"epoch_end": 10, "step": 4301, "test_acc": 0.9824, "test_loss": 0.06478251147270203}, {"step": 4350, "epoch": 11, "train_loss": 0.00036745742545463145}, {"step": 4400, "epoch": 11, "train_loss": 0.0004546194104477763}, {"step": 4450, "epoch": 11, "train_loss": 0.0005450356984511018}, {"step": 4500, "epoch": 11, "train_loss": 0.00014803778321947902}, {"step": 4550, "epoch": 11, "train_loss": 0.0005247935187071562}, {"step": 4600, "epoch": 11, "train_loss": 0.00030437277746386826}, {"step": 4650, "epoch": 11, "train_loss": 0.0003501830797176808}, {"epoch_end": 11, "step": 4692, "test_acc": 0.9829, "test_loss": 0.06549244931936264}, {"step": 4700, "epoch": 12, "train_loss": 0.0007662368007004261}, {"step": 4750, "epoch": 12, "train_loss": 0.00036546328919939697}, {"step": 4800, "epoch": 12, "train_loss": 0.0002221220638602972}, {"step": 4850, "epoch": 12, "train_loss": 0.00040096830343827605}, {"step": 4900, "epoch": 12, "train_loss": 0.00037509918911382556}, {"step": 4950, "epoch": 12, "train_loss": 0.0002631846582517028}, {"step": 5000, "epoch": 12, "train_loss": 0.00027531120576895773}, {"step": 5050, "epoch": 12, "train_loss": 0.0003029878716915846}, {"epoch_end": 12, "step": 5083, "test_acc": 0.9826, "test_loss": 0.06601939859390259}, {"step": 5100, "epoch": 13, "train_loss": 0.00018406816525384784}, {"step": 5150, "epoch": 13, "train_loss": 0.00034745721495710313}, {"step": 5200, "epoch": 13, "train_loss": 0.00040767184691503644}, {"step": 5250, "epoch": 13, "train_loss": 0.00019829867233056575}, {"step": 5300, "epoch": 13, "train_loss": 0.0002809641882777214}, {"step": 5350, "epoch": 13, "train_loss": 0.00045263301581144333}, {"step": 5400, "epoch": 13, "train_loss": 0.00037783136940561235}, {"step": 5450, "epoch": 13, "train_loss": 0.0002749054692685604}, {"epoch_end": 13, "step": 5474, "test_acc": 0.9823, "test_loss": 0.06665702311992645}, {"step": 5500, "epoch": 14, "train_loss": 0.00014197223936207592}, {"step": 5550, "epoch": 14, "train_loss": 0.00022185442503541708}, {"step": 5600, "epoch": 14, "train_loss": 0.0002671891706995666}, {"step": 5650, "epoch": 14, "train_loss": 0.00027945602778345346}, {"step": 5700, "epoch": 14, "train_loss": 8.680299652041867e-05}, {"step": 5750, "epoch": 14, "train_loss": 0.0005022325785830617}, {"step": 5800, "epoch": 14, "train_loss": 0.0006272653699852526}, {"step": 5850, "epoch": 14, "train_loss": 0.0004376774304546416}, {"epoch_end": 14, "step": 5865, "test_acc": 0.9826, "test_loss": 0.06660801872015}, {"step": 5900, "epoch": 15, "train_loss": 0.0004325751797296107}, {"step": 5950, "epoch": 15, "train_loss": 0.00042664443026296794}, {"step": 6000, "epoch": 15, "train_loss": 0.0006674003088846803}, {"step": 6050, "epoch": 15, "train_loss": 0.0005708972457796335}, {"step": 6100, "epoch": 15, "train_loss": 0.0004023154906462878}, {"step": 6150, "epoch": 15, "train_loss": 0.0002655570860952139}, {"step": 6200, "epoch": 15, "train_loss": 0.0002641330938786268}, {"step": 6250, "epoch": 15, "train_loss": 0.0001795770222088322}, {"epoch_end": 15, "step": 6256, "test_acc": 0.9827, "test_loss": 0.06706198364496231}, {"step": 6300, "epoch": 16, "train_loss": 0.00026549084577709436}, {"step": 6350, "epoch": 16, "train_loss": 0.00018756416102405638}, {"step": 6400, "epoch": 16, "train_loss": 0.0002497814130038023}, {"step": 6450, "epoch": 16, "train_loss": 0.00010118693899130449}, {"step": 6500, "epoch": 16, "train_loss": 0.0001925670076161623}, {"step": 6550, "epoch": 16, "train_loss": 0.0003133576246909797}, {"step": 6600, "epoch": 16, "train_loss": 0.00018717642524279654}, {"epoch_end": 16, "step": 6647, "test_acc": 0.9829, "test_loss": 0.06766105650663376}, {"step": 6650, "epoch": 17, "train_loss": 0.00013850888353772461}, {"step": 6700, "epoch": 17, "train_loss": 9.444526949664578e-05}, {"step": 6750, "epoch": 17, "train_loss": 0.0004659938276745379}, {"step": 6800, "epoch": 17, "train_loss": 0.0005299951299093664}, {"step": 6850, "epoch": 17, "train_loss": 0.0002655761200003326}, {"step": 6900, "epoch": 17, "train_loss": 0.0003144824877381325}, {"step": 6950, "epoch": 17, "train_loss": 0.00041616472299210727}, {"step": 7000, "epoch": 17, "train_loss": 0.00026933770277537405}, {"epoch_end": 17, "step": 7038, "test_acc": 0.9828, "test_loss": 0.06781046007871627}, {"step": 7050, "epoch": 18, "train_loss": 0.00010141458915313706}, {"step": 7100, "epoch": 18, "train_loss": 0.00040044402703642845}, {"step": 7150, "epoch": 18, "train_loss": 9.53858980210498e-05}, {"step": 7200, "epoch": 18, "train_loss": 0.00025199653464369476}, {"step": 7250, "epoch": 18, "train_loss": 0.00028149218996986747}, {"step": 7300, "epoch": 18, "train_loss": 0.00011935819202335551}, {"step": 7350, "epoch": 18, "train_loss": 0.000322213105391711}, {"step": 7400, "epoch": 18, "train_loss": 0.00017448156722821295}, {"epoch_end": 18, "step": 7429, "test_acc": 0.9827, "test_loss": 0.06812874274253845}, {"step": 7450, "epoch": 19, "train_loss": 0.00013095830217935145}, {"step": 7500, "epoch": 19, "train_loss": 0.00019298159168101847}, {"step": 7550, "epoch": 19, "train_loss": 0.00013883333303965628}, {"step": 7600, "epoch": 19, "train_loss": 9.751130710355937e-05}, {"step": 7650, "epoch": 19, "train_loss": 0.0003284781996626407}, {"step": 7700, "epoch": 19, "train_loss": 0.0003798116522375494}, {"step": 7750, "epoch": 19, "train_loss": 0.0002911537594627589}, {"step": 7800, "epoch": 19, "train_loss": 0.00047479799832217395}, {"epoch_end": 19, "step": 7820, "test_acc": 0.9832, "test_loss": 0.0686237362742424}, {"step": 7850, "epoch": 20, "train_loss": 0.000262435176409781}, {"step": 7900, "epoch": 20, "train_loss": 0.00017210340593010187}, {"step": 7950, "epoch": 20, "train_loss": 0.00022939936025068164}, {"step": 8000, "epoch": 20, "train_loss": 0.00016162444080691785}, {"step": 8050, "epoch": 20, "train_loss": 0.00034435666748322546}, {"step": 8100, "epoch": 20, "train_loss": 0.0002227916120318696}, {"step": 8150, "epoch": 20, "train_loss": 0.00022021980839781463}, {"step": 8200, "epoch": 20, "train_loss": 0.0001410331024089828}, {"epoch_end": 20, "step": 8211, "test_acc": 0.9827, "test_loss": 0.06876816350221635}, {"step": 8250, "epoch": 21, "train_loss": 0.0002480137627571821}, {"step": 8300, "epoch": 21, "train_loss": 0.0002917578676715493}, {"step": 8350, "epoch": 21, "train_loss": 0.00026102998526766896}, {"step": 8400, "epoch": 21, "train_loss": 0.00021005557209718972}, {"step": 8450, "epoch": 21, "train_loss": 0.00018647372780833393}, {"step": 8500, "epoch": 21, "train_loss": 0.00029030395671725273}, {"step": 8550, "epoch": 21, "train_loss": 0.00015452875231858343}, {"step": 8600, "epoch": 21, "train_loss": 0.00032065584673546255}, {"epoch_end": 21, "step": 8602, "test_acc": 0.9828, "test_loss": 0.06907096277475357}, {"step": 8650, "epoch": 22, "train_loss": 9.971997496904805e-05}, {"step": 8700, "epoch": 22, "train_loss": 0.00011137694673379883}, {"step": 8750, "epoch": 22, "train_loss": 0.0001790395617717877}, {"step": 8800, "epoch": 22, "train_loss": 0.0002891529002226889}, {"step": 8850, "epoch": 22, "train_loss": 0.00017149662016890943}, {"step": 8900, "epoch": 22, "train_loss": 0.00030390775646083057}, {"step": 8950, "epoch": 22, "train_loss": 0.00023020363005343825}, {"epoch_end": 22, "step": 8993, "test_acc": 0.9828, "test_loss": 0.06926261469125748}, {"step": 9000, "epoch": 23, "train_loss": 0.00010755974653875455}, {"step": 9050, "epoch": 23, "train_loss": 0.00016214927018154413}, {"step": 9100, "epoch": 23, "train_loss": 0.00015555917343590409}, {"step": 9150, "epoch": 23, "train_loss": 0.00030072193476371467}, {"step": 9200, "epoch": 23, "train_loss": 0.0002867585571948439}, {"step": 9250, "epoch": 23, "train_loss": 0.00015199989138636738}, {"step": 9300, "epoch": 23, "train_loss": 0.00018440891290083528}, {"step": 9350, "epoch": 23, "train_loss": 0.00014685756468679756}, {"epoch_end": 23, "step": 9384, "test_acc": 0.9827, "test_loss": 0.06959138736724854}, {"step": 9400, "epoch": 24, "train_loss": 0.00017987762112170458}, {"step": 9450, "epoch": 24, "train_loss": 9.863806189969182e-05}, {"step": 9500, "epoch": 24, "train_loss": 0.0001399952598148957}, {"step": 9550, "epoch": 24, "train_loss": 0.00024029231281019747}, {"step": 9600, "epoch": 24, "train_loss": 0.0001379798341076821}, {"step": 9650, "epoch": 24, "train_loss": 0.00029427872505038977}, {"step": 9700, "epoch": 24, "train_loss": 0.00015636003809049726}, {"step": 9750, "epoch": 24, "train_loss": 0.0003558069874998182}, {"epoch_end": 24, "step": 9775, "test_acc": 0.9827, "test_loss": 0.06997076139450073}, {"step": 9800, "epoch": 25, "train_loss": 0.00025066445232369006}, {"step": 9850, "epoch": 25, "train_loss": 5.935924855293706e-05}, {"step": 9900, "epoch": 25, "train_loss": 9.24157357076183e-05}, {"step": 9950, "epoch": 25, "train_loss": 0.00020199880236759782}, {"step": 10000, "epoch": 25, "train_loss": 0.00014164895401336253}, {"step": 10050, "epoch": 25, "train_loss": 0.0001403556962031871}, {"step": 10100, "epoch": 25, "train_loss": 9.340759424958378e-05}, {"step": 10150, "epoch": 25, "train_loss": 7.353860564762726e-05}, {"epoch_end": 25, "step": 10166, "test_acc": 0.9827, "test_loss": 0.07019420676231385}, {"step": 10200, "epoch": 26, "train_loss": 0.00017907537403516471}, {"step": 10250, "epoch": 26, "train_loss": 0.00023682782193645835}, {"step": 10300, "epoch": 26, "train_loss": 0.0006407250184565783}, {"step": 10350, "epoch": 26, "train_loss": 7.847866072552279e-05}, {"step": 10400, "epoch": 26, "train_loss": 0.00021461807773448527}, {"step": 10450, "epoch": 26, "train_loss": 0.0001957369822775945}, {"step": 10500, "epoch": 26, "train_loss": 0.00020981807028874755}, {"step": 10550, "epoch": 26, "train_loss": 0.00018154186545871198}, {"epoch_end": 26, "step": 10557, "test_acc": 0.983, "test_loss": 0.07042285536527634}, {"step": 10600, "epoch": 27, "train_loss": 0.00016192550538107753}, {"step": 10650, "epoch": 27, "train_loss": 0.00011984848242718726}, {"step": 10700, "epoch": 27, "train_loss": 0.00018574055866338313}, {"step": 10750, "epoch": 27, "train_loss": 0.00013063932419754565}, {"step": 10800, "epoch": 27, "train_loss": 7.902872312115505e-05}, {"step": 10850, "epoch": 27, "train_loss": 0.00014823340461589396}, {"step": 10900, "epoch": 27, "train_loss": 0.0001323805918218568}, {"epoch_end": 27, "step": 10948, "test_acc": 0.9828, "test_loss": 0.07055745251178741}, {"step": 10950, "epoch": 28, "train_loss": 0.00013999415386933833}, {"step": 11000, "epoch": 28, "train_loss": 0.00013167144788894802}, {"step": 11050, "epoch": 28, "train_loss": 0.00023652937670703977}, {"step": 11100, "epoch": 28, "train_loss": 0.0001590998435858637}, {"step": 11150, "epoch": 28, "train_loss": 0.00018085594638250768}, {"step": 11200, "epoch": 28, "train_loss": 0.0002572239318396896}, {"step": 11250, "epoch": 28, "train_loss": 0.00022921555500943214}, {"step": 11300, "epoch": 28, "train_loss": 0.0001623511197976768}, {"epoch_end": 28, "step": 11339, "test_acc": 0.9829, "test_loss": 0.07073245130777359}, {"step": 11350, "epoch": 29, "train_loss": 6.0183036111993715e-05}, {"step": 11400, "epoch": 29, "train_loss": 0.0001452862488804385}, {"step": 11450, "epoch": 29, "train_loss": 0.00018772810290101916}, {"step": 11500, "epoch": 29, "train_loss": 0.00015524191258009523}, {"step": 11550, "epoch": 29, "train_loss": 0.0001450076961191371}, {"step": 11600, "epoch": 29, "train_loss": 0.00013192975893616676}, {"step": 11650, "epoch": 29, "train_loss": 0.00017911463510245085}, {"step": 11700, "epoch": 29, "train_loss": 8.096110832411796e-05}, {"epoch_end": 29, "step": 11730, "test_acc": 0.9828, "test_loss": 0.0710735158085823}, {"step": 11750, "epoch": 30, "train_loss": 0.00018626262317411602}, {"step": 11800, "epoch": 30, "train_loss": 0.00011235721467528492}, {"step": 11850, "epoch": 30, "train_loss": 0.00013739729183726013}, {"step": 11900, "epoch": 30, "train_loss": 0.000309840397676453}, {"step": 11950, "epoch": 30, "train_loss": 4.3881482270080596e-05}, {"step": 12000, "epoch": 30, "train_loss": 0.00010042562644230202}, {"step": 12050, "epoch": 30, "train_loss": 0.00024307618150487542}, {"step": 12100, "epoch": 30, "train_loss": 0.00014585760072804987}, {"epoch_end": 30, "step": 12121, "test_acc": 0.9828, "test_loss": 0.07133416588306427}, {"step": 12150, "epoch": 31, "train_loss": 0.00010490254499018192}, {"step": 12200, "epoch": 31, "train_loss": 0.00018824386643245816}, {"step": 12250, "epoch": 31, "train_loss": 0.00015146176156122237}, {"step": 12300, "epoch": 31, "train_loss": 0.00018209846166428179}, {"step": 12350, "epoch": 31, "train_loss": 0.00017051184840966016}, {"step": 12400, "epoch": 31, "train_loss": 0.00010881022171815857}, {"step": 12450, "epoch": 31, "train_loss": 9.747555304784328e-05}, {"step": 12500, "epoch": 31, "train_loss": 4.4246982724871486e-05}, {"epoch_end": 31, "step": 12512, "test_acc": 0.9829, "test_loss": 0.07150286313295365}, {"step": 12550, "epoch": 32, "train_loss": 0.0001309427316300571}, {"step": 12600, "epoch": 32, "train_loss": 4.038174301967956e-05}, {"step": 12650, "epoch": 32, "train_loss": 0.00013858421880286187}, {"step": 12700, "epoch": 32, "train_loss": 0.00018673465820029378}, {"step": 12750, "epoch": 32, "train_loss": 4.718443233286962e-05}, {"step": 12800, "epoch": 32, "train_loss": 0.00011681449541356415}, {"step": 12850, "epoch": 32, "train_loss": 8.042650006245822e-05}, {"step": 12900, "epoch": 32, "train_loss": 0.0001060528593370691}, {"epoch_end": 32, "step": 12903, "test_acc": 0.9829, "test_loss": 0.0716207631111145}, {"step": 12950, "epoch": 33, "train_loss": 0.00010537367779761553}, {"step": 13000, "epoch": 33, "train_loss": 2.341212166356854e-05}, {"step": 13050, "epoch": 33, "train_loss": 0.00010726689652074128}, {"step": 13100, "epoch": 33, "train_loss": 8.977043762570247e-05}, {"step": 13150, "epoch": 33, "train_loss": 0.00010445379302836955}, {"step": 13200, "epoch": 33, "train_loss": 8.590897778049111e-05}, {"step": 13250, "epoch": 33, "train_loss": 0.00013528352428693324}, {"epoch_end": 33, "step": 13294, "test_acc": 0.9829, "test_loss": 0.07184869918823242}, {"step": 13300, "epoch": 34, "train_loss": 9.671041334513575e-05}, {"step": 13350, "epoch": 34, "train_loss": 9.210796270053834e-05}, {"step": 13400, "epoch": 34, "train_loss": 5.007109575672075e-05}, {"step": 13450, "epoch": 34, "train_loss": 0.00017027083958964795}, {"step": 13500, "epoch": 34, "train_loss": 0.0001093901737476699}, {"step": 13550, "epoch": 34, "train_loss": 0.00015354107017628849}, {"step": 13600, "epoch": 34, "train_loss": 0.00010531790758250281}, {"step": 13650, "epoch": 34, "train_loss": 0.0001556281204102561}, {"epoch_end": 34, "step": 13685, "test_acc": 0.9828, "test_loss": 0.07201017322540283}, {"step": 13700, "epoch": 35, "train_loss": 7.158467633416876e-05}, {"step": 13750, "epoch": 35, "train_loss": 0.000131442749989219}, {"step": 13800, "epoch": 35, "train_loss": 7.188840390881523e-05}, {"step": 13850, "epoch": 35, "train_loss": 0.00010079280764330178}, {"step": 13900, "epoch": 35, "train_loss": 7.857014861656353e-05}, {"step": 13950, "epoch": 35, "train_loss": 0.00010487205145182088}, {"step": 14000, "epoch": 35, "train_loss": 0.00010084121458930895}, {"step": 14050, "epoch": 35, "train_loss": 0.00010616760118864477}, {"epoch_end": 35, "step": 14076, "test_acc": 0.9828, "test_loss": 0.07213304411172866}, {"step": 14100, "epoch": 36, "train_loss": 0.00010604792623780668}, {"step": 14150, "epoch": 36, "train_loss": 0.00012253977183718234}, {"step": 14200, "epoch": 36, "train_loss": 0.00011153498780913651}, {"step": 14250, "epoch": 36, "train_loss": 6.328873860184103e-05}, {"step": 14300, "epoch": 36, "train_loss": 6.750795000698417e-05}, {"step": 14350, "epoch": 36, "train_loss": 0.0001201903069159016}, {"step": 14400, "epoch": 36, "train_loss": 8.218447328545153e-05}, {"step": 14450, "epoch": 36, "train_loss": 8.728015382075682e-05}, {"epoch_end": 36, "step": 14467, "test_acc": 0.9827, "test_loss": 0.07248274369239807}, {"step": 14500, "epoch": 37, "train_loss": 0.00014759984333068132}, {"step": 14550, "epoch": 37, "train_loss": 0.0001590204774402082}, {"step": 14600, "epoch": 37, "train_loss": 6.788943574065343e-05}, {"step": 14650, "epoch": 37, "train_loss": 0.00010148985165869817}, {"step": 14700, "epoch": 37, "train_loss": 9.584690997144207e-05}, {"step": 14750, "epoch": 37, "train_loss": 0.00010318477143300697}, {"step": 14800, "epoch": 37, "train_loss": 9.15433483896777e-05}, {"step": 14850, "epoch": 37, "train_loss": 0.00010804944031406194}, {"epoch_end": 37, "step": 14858, "test_acc": 0.9828, "test_loss": 0.0725913555264473}, {"step": 14900, "epoch": 38, "train_loss": 0.00011363031808286905}, {"step": 14950, "epoch": 38, "train_loss": 7.316612027352676e-05}, {"step": 15000, "epoch": 38, "train_loss": 0.00012711422459688038}, {"step": 15050, "epoch": 38, "train_loss": 9.515023702988401e-05}, {"step": 15100, "epoch": 38, "train_loss": 5.41004010301549e-05}, {"step": 15150, "epoch": 38, "train_loss": 0.0001311997475568205}, {"step": 15200, "epoch": 38, "train_loss": 0.0001264335442101583}, {"epoch_end": 38, "step": 15249, "test_acc": 0.9828, "test_loss": 0.07275794246196747}, {"step": 15250, "epoch": 39, "train_loss": 7.916390313766897e-05}, {"step": 15300, "epoch": 39, "train_loss": 6.303977716015652e-05}, {"step": 15350, "epoch": 39, "train_loss": 0.00010753333481261507}, {"step": 15400, "epoch": 39, "train_loss": 5.613376197288744e-05}, {"step": 15450, "epoch": 39, "train_loss": 8.814284956315532e-05}, {"step": 15500, "epoch": 39, "train_loss": 0.00012389598123263568}, {"step": 15550, "epoch": 39, "train_loss": 9.387684258399531e-05}, {"step": 15600, "epoch": 39, "train_loss": 0.00013791322999168187}, {"epoch_end": 39, "step": 15640, "test_acc": 0.9827, "test_loss": 0.07280995452404022}, {"step": 15650, "epoch": 40, "train_loss": 0.00015040443395264447}, {"step": 15700, "epoch": 40, "train_loss": 0.00011892919428646564}, {"step": 15750, "epoch": 40, "train_loss": 0.00011485738650662825}, {"step": 15800, "epoch": 40, "train_loss": 8.597267878940329e-05}, {"step": 15850, "epoch": 40, "train_loss": 5.744921145378612e-05}, {"step": 15900, "epoch": 40, "train_loss": 2.497171954018995e-05}, {"step": 15950, "epoch": 40, "train_loss": 0.00010481806384632364}, {"step": 16000, "epoch": 40, "train_loss": 4.542177703115158e-05}, {"epoch_end": 40, "step": 16031, "test_acc": 0.9828, "test_loss": 0.07291598691940307}, {"step": 16050, "epoch": 41, "train_loss": 5.804003740195185e-05}, {"step": 16100, "epoch": 41, "train_loss": 7.803454354871064e-05}, {"step": 16150, "epoch": 41, "train_loss": 0.00010424356878502294}, {"step": 16200, "epoch": 41, "train_loss": 7.65346412663348e-05}, {"step": 16250, "epoch": 41, "train_loss": 9.972842963179573e-05}, {"step": 16300, "epoch": 41, "train_loss": 7.333554094657302e-05}, {"step": 16350, "epoch": 41, "train_loss": 8.410644659306854e-05}, {"step": 16400, "epoch": 41, "train_loss": 4.3914493289776146e-05}, {"epoch_end": 41, "step": 16422, "test_acc": 0.9829, "test_loss": 0.07329654378890992}, {"step": 16450, "epoch": 42, "train_loss": 7.477890903828666e-05}, {"step": 16500, "epoch": 42, "train_loss": 0.00010876964370254427}, {"step": 16550, "epoch": 42, "train_loss": 0.0001440050546079874}, {"step": 16600, "epoch": 42, "train_loss": 0.00010400739847682416}, {"step": 16650, "epoch": 42, "train_loss": 8.164148312062025e-05}, {"step": 16700, "epoch": 42, "train_loss": 9.552264236845076e-05}, {"step": 16750, "epoch": 42, "train_loss": 6.490955274784938e-05}, {"step": 16800, "epoch": 42, "train_loss": 4.8331763537134975e-05}, {"epoch_end": 42, "step": 16813, "test_acc": 0.9827, "test_loss": 0.07325140186548233}, {"step": 16850, "epoch": 43, "train_loss": 0.00020717710140161216}, {"step": 16900, "epoch": 43, "train_loss": 4.88253754156176e-05}, {"step": 16950, "epoch": 43, "train_loss": 0.0001094538820325397}, {"step": 17000, "epoch": 43, "train_loss": 9.297055657953024e-05}, {"step": 17050, "epoch": 43, "train_loss": 8.100207196548581e-05}, {"step": 17100, "epoch": 43, "train_loss": 6.675608892692253e-05}, {"step": 17150, "epoch": 43, "train_loss": 0.00011117687972728163}, {"step": 17200, "epoch": 43, "train_loss": 9.731025056680664e-05}, {"epoch_end": 43, "step": 17204, "test_acc": 0.9827, "test_loss": 0.07347131382226944}, {"step": 17250, "epoch": 44, "train_loss": 0.00012624828377738595}, {"step": 17300, "epoch": 44, "train_loss": 0.00010055005986941978}, {"step": 17350, "epoch": 44, "train_loss": 0.00010853242565644905}, {"step": 17400, "epoch": 44, "train_loss": 8.109281770884991e-05}, {"step": 17450, "epoch": 44, "train_loss": 0.00010525665857130662}, {"step": 17500, "epoch": 44, "train_loss": 6.758339441148564e-05}, {"step": 17550, "epoch": 44, "train_loss": 5.5307424190687016e-05}, {"epoch_end": 44, "step": 17595, "test_acc": 0.9828, "test_loss": 0.07361960085630417}, {"step": 17600, "epoch": 45, "train_loss": 7.508299313485622e-05}, {"step": 17650, "epoch": 45, "train_loss": 3.460294828983024e-05}, {"step": 17700, "epoch": 45, "train_loss": 3.7753194192191586e-05}, {"step": 17750, "epoch": 45, "train_loss": 0.00011935871589230374}, {"step": 17800, "epoch": 45, "train_loss": 0.0001599396055098623}, {"step": 17850, "epoch": 45, "train_loss": 2.6760671971715055e-05}, {"step": 17900, "epoch": 45, "train_loss": 9.723626135382801e-05}, {"step": 17950, "epoch": 45, "train_loss": 0.00010464312799740583}, {"epoch_end": 45, "step": 17986, "test_acc": 0.9828, "test_loss": 0.07373019757270813}, {"step": 18000, "epoch": 46, "train_loss": 9.535747085465118e-05}, {"step": 18050, "epoch": 46, "train_loss": 0.00012193090515211225}, {"step": 18100, "epoch": 46, "train_loss": 0.0001474238815717399}, {"step": 18150, "epoch": 46, "train_loss": 4.6285953430924565e-05}, {"step": 18200, "epoch": 46, "train_loss": 5.4947340686339885e-05}, {"step": 18250, "epoch": 46, "train_loss": 0.0001035458772093989}, {"step": 18300, "epoch": 46, "train_loss": 8.287168748211116e-05}, {"step": 18350, "epoch": 46, "train_loss": 6.271224992815405e-05}, {"epoch_end": 46, "step": 18377, "test_acc": 0.9827, "test_loss": 0.07384136906862258}, {"step": 18400, "epoch": 47, "train_loss": 0.00014558206021320075}, {"step": 18450, "epoch": 47, "train_loss": 8.075837831711397e-05}, {"step": 18500, "epoch": 47, "train_loss": 8.775796595728025e-05}, {"step": 18550, "epoch": 47, "train_loss": 0.00010419484897283837}, {"step": 18600, "epoch": 47, "train_loss": 4.51750929642003e-05}, {"step": 18650, "epoch": 47, "train_loss": 7.000344339758158e-05}, {"step": 18700, "epoch": 47, "train_loss": 0.00011124822776764631}, {"step": 18750, "epoch": 47, "train_loss": 5.0685732276178896e-05}, {"epoch_end": 47, "step": 18768, "test_acc": 0.9827, "test_loss": 0.07406444592475891}, {"step": 18800, "epoch": 48, "train_loss": 6.244525138754398e-05}, {"step": 18850, "epoch": 48, "train_loss": 0.00011041232210118324}, {"step": 18900, "epoch": 48, "train_loss": 6.429747736547142e-05}, {"step": 18950, "epoch": 48, "train_loss": 0.00011146260658279061}, {"step": 19000, "epoch": 48, "train_loss": 6.242367817321792e-05}, {"step": 19050, "epoch": 48, "train_loss": 0.00012988198432140052}, {"step": 19100, "epoch": 48, "train_loss": 0.00010444399231346324}, {"step": 19150, "epoch": 48, "train_loss": 7.496113539673388e-05}, {"epoch_end": 48, "step": 19159, "test_acc": 0.9828, "test_loss": 0.07409962644577027}, {"step": 19200, "epoch": 49, "train_loss": 5.9086447436129674e-05}, {"step": 19250, "epoch": 49, "train_loss": 3.858268973999657e-05}, {"step": 19300, "epoch": 49, "train_loss": 0.00013192933693062514}, {"step": 19350, "epoch": 49, "train_loss": 5.958638575975783e-05}, {"step": 19400, "epoch": 49, "train_loss": 6.459596625063568e-05}, {"step": 19450, "epoch": 49, "train_loss": 6.46376793156378e-05}, {"step": 19500, "epoch": 49, "train_loss": 6.745515565853566e-05}, {"epoch_end": 49, "step": 19550, "test_acc": 0.9827, "test_loss": 0.07433605736494064}, {"step": 19550, "epoch": 50, "train_loss": 4.810602331417613e-05}, {"step": 19600, "epoch": 50, "train_loss": 7.360464223893359e-05}, {"step": 19650, "epoch": 50, "train_loss": 5.190850788494572e-05}, {"step": 19700, "epoch": 50, "train_loss": 9.974428394343704e-05}, {"step": 19750, "epoch": 50, "train_loss": 0.0001208674002555199}, {"step": 19800, "epoch": 50, "train_loss": 0.00010319567809347063}, {"step": 19850, "epoch": 50, "train_loss": 0.00011552356590982527}, {"step": 19900, "epoch": 50, "train_loss": 9.888026397675276e-05}, {"epoch_end": 50, "step": 19941, "test_acc": 0.9827, "test_loss": 0.07437540879249573}, {"step": 19950, "epoch": 51, "train_loss": 5.120566129335202e-05}, {"step": 20000, "epoch": 51, "train_loss": 9.813077485887334e-05}, {"step": 20050, "epoch": 51, "train_loss": 5.393240280682221e-05}, {"step": 20100, "epoch": 51, "train_loss": 6.487981590908021e-05}, {"step": 20150, "epoch": 51, "train_loss": 5.521741695702076e-05}, {"step": 20200, "epoch": 51, "train_loss": 5.386405246099457e-05}, {"step": 20250, "epoch": 51, "train_loss": 8.661358879180625e-05}, {"step": 20300, "epoch": 51, "train_loss": 4.425274164532311e-05}, {"epoch_end": 51, "step": 20332, "test_acc": 0.9828, "test_loss": 0.07456666195392608}, {"step": 20350, "epoch": 52, "train_loss": 9.800515545066446e-05}, {"step": 20400, "epoch": 52, "train_loss": 7.165116403484717e-05}, {"step": 20450, "epoch": 52, "train_loss": 6.73231334076263e-05}, {"step": 20500, "epoch": 52, "train_loss": 8.043954585446045e-05}, {"step": 20550, "epoch": 52, "train_loss": 4.4579461246030405e-05}, {"step": 20600, "epoch": 52, "train_loss": 5.553072696784511e-05}, {"step": 20650, "epoch": 52, "train_loss": 9.160779882222414e-05}, {"step": 20700, "epoch": 52, "train_loss": 8.100656850729138e-05}, {"epoch_end": 52, "step": 20723, "test_acc": 0.9826, "test_loss": 0.07456368848085404}, {"step": 20750, "epoch": 53, "train_loss": 4.115768751944415e-05}, {"step": 20800, "epoch": 53, "train_loss": 5.6075103202601895e-05}, {"step": 20850, "epoch": 53, "train_loss": 9.512992255622521e-05}, {"step": 20900, "epoch": 53, "train_loss": 0.00010725550964707509}, {"step": 20950, "epoch": 53, "train_loss": 5.069637700216845e-05}, {"step": 21000, "epoch": 53, "train_loss": 5.5351782066281885e-05}, {"step": 21050, "epoch": 53, "train_loss": 3.221587758162059e-05}, {"step": 21100, "epoch": 53, "train_loss": 7.68420723034069e-05}, {"epoch_end": 53, "step": 21114, "test_acc": 0.9828, "test_loss": 0.07473356870412827}, {"step": 21150, "epoch": 54, "train_loss": 6.664243119303137e-05}, {"step": 21200, "epoch": 54, "train_loss": 7.824272324796766e-05}, {"step": 21250, "epoch": 54, "train_loss": 3.521521284710616e-05}, {"step": 21300, "epoch": 54, "train_loss": 5.91998323216103e-05}, {"step": 21350, "epoch": 54, "train_loss": 9.841067367233336e-05}, {"step": 21400, "epoch": 54, "train_loss": 0.00012085437629139051}, {"step": 21450, "epoch": 54, "train_loss": 5.1676408475032076e-05}, {"step": 21500, "epoch": 54, "train_loss": 3.9956856198841706e-05}, {"epoch_end": 54, "step": 21505, "test_acc": 0.9827, "test_loss": 0.07485537580251694}, {"step": 21550, "epoch": 55, "train_loss": 7.726886542513967e-05}, {"step": 21600, "epoch": 55, "train_loss": 6.194297748152167e-05}, {"step": 21650, "epoch": 55, "train_loss": 4.471097781788558e-05}, {"step": 21700, "epoch": 55, "train_loss": 6.0620288422796875e-05}, {"step": 21750, "epoch": 55, "train_loss": 8.302717469632626e-05}, {"step": 21800, "epoch": 55, "train_loss": 8.460906246909872e-05}, {"step": 21850, "epoch": 55, "train_loss": 5.056637019151822e-05}, {"epoch_end": 55, "step": 21896, "test_acc": 0.9828, "test_loss": 0.0749716695189476}, {"step": 21900, "epoch": 56, "train_loss": 4.9003374442690983e-05}, {"step": 21950, "epoch": 56, "train_loss": 0.0001372849364997819}, {"step": 22000, "epoch": 56, "train_loss": 6.623547233175486e-05}, {"step": 22050, "epoch": 56, "train_loss": 3.6256544262869284e-05}, {"step": 22100, "epoch": 56, "train_loss": 5.8672398154158145e-05}, {"step": 22150, "epoch": 56, "train_loss": 7.292251393664628e-05}, {"step": 22200, "epoch": 56, "train_loss": 0.00012510147644206882}, {"step": 22250, "epoch": 56, "train_loss": 9.870545181911439e-05}, {"epoch_end": 56, "step": 22287, "test_acc": 0.9828, "test_loss": 0.07504557712078094}, {"step": 22300, "epoch": 57, "train_loss": 7.574549817945808e-05}, {"step": 22350, "epoch": 57, "train_loss": 8.143819286487997e-05}, {"step": 22400, "epoch": 57, "train_loss": 8.443746628472582e-05}, {"step": 22450, "epoch": 57, "train_loss": 2.1128664229763672e-05}, {"step": 22500, "epoch": 57, "train_loss": 3.902858225046657e-05}, {"step": 22550, "epoch": 57, "train_loss": 0.00010016425949288532}, {"step": 22600, "epoch": 57, "train_loss": 5.250710091786459e-05}, {"step": 22650, "epoch": 57, "train_loss": 8.624679321656004e-05}, {"epoch_end": 57, "step": 22678, "test_acc": 0.9827, "test_loss": 0.07510928243398667}, {"step": 22700, "epoch": 58, "train_loss": 3.725526767084375e-05}, {"step": 22750, "epoch": 58, "train_loss": 8.389033610001206e-05}, {"step": 22800, "epoch": 58, "train_loss": 7.700687274336815e-05}, {"step": 22850, "epoch": 58, "train_loss": 5.887016232009046e-05}, {"step": 22900, "epoch": 58, "train_loss": 3.5315526474732906e-05}, {"step": 22950, "epoch": 58, "train_loss": 7.719283894402906e-05}, {"step": 23000, "epoch": 58, "train_loss": 3.745256253750995e-05}, {"step": 23050, "epoch": 58, "train_loss": 5.576364856096916e-05}, {"epoch_end": 58, "step": 23069, "test_acc": 0.9826, "test_loss": 0.07524532930850983}, {"step": 23100, "epoch": 59, "train_loss": 7.28686063666828e-05}, {"step": 23150, "epoch": 59, "train_loss": 3.918320726370439e-05}, {"step": 23200, "epoch": 59, "train_loss": 2.389540895819664e-05}, {"step": 23250, "epoch": 59, "train_loss": 7.385655771940947e-05}, {"step": 23300, "epoch": 59, "train_loss": 6.201702490216121e-05}, {"step": 23350, "epoch": 59, "train_loss": 3.861414370476268e-05}, {"step": 23400, "epoch": 59, "train_loss": 0.00016701521235518157}, {"step": 23450, "epoch": 59, "train_loss": 5.1557410188252106e-05}, {"epoch_end": 59, "step": 23460, "test_acc": 0.9827, "test_loss": 0.07536257346868515}], "final": {"test_acc": 0.9827, "test_loss": 0.07536257346868515, "wall_s": 44.190484046936035}}