# Note: In this checkpoint, we use total batch size 1536 instead of default total batch size 2048. {"train_lr": 1.0000000000000165e-06, "train_loss": 6.910937792224755, "epoch": 0, "n_parameters": 5498844} {"train_lr": 1.0000000000000165e-06, "train_loss": 6.909439640817977, "epoch": 1, "n_parameters": 5498844} {"train_lr": 0.00030079999999999566, "train_loss": 6.747292511254478, "epoch": 2, "n_parameters": 5498844} {"train_lr": 0.0006006000000000057, "train_loss": 6.425523795955758, "epoch": 3, "n_parameters": 5498844} {"train_lr": 0.0009004000000000146, "train_loss": 6.092398541389133, "epoch": 4, "n_parameters": 5498844} {"train_lr": 0.00120019999999999, "train_loss": 5.803467009922297, "epoch": 5, "n_parameters": 5498844} {"train_lr": 0.0014989790033921367, "train_loss": 5.555222965199217, "epoch": 6, "n_parameters": 5498844} {"train_lr": 0.001498529912679069, "train_loss": 5.323510034073838, "epoch": 7, "n_parameters": 5498844} {"train_lr": 0.001497999285532199, "train_loss": 5.146562053859949, "epoch": 8, "n_parameters": 5498844} {"train_lr": 0.0014973871801409009, "train_loss": 5.0277680171122086, "test_loss": 2.5280604393948978, "test_acc1": 46.64600139953613, "test_acc5": 72.52600221679687, "epoch": 9, "n_parameters": 5498844} {"train_lr": 0.001496693663629296, "train_loss": 4.9193477949959865, "epoch": 10, "n_parameters": 5498844} {"train_lr": 0.0014959188120493578, "train_loss": 4.8299283757865386, "epoch": 11, "n_parameters": 5498844} {"train_lr": 0.0014950627103722735, "train_loss": 4.766627801753444, "epoch": 12, "n_parameters": 5498844} {"train_lr": 0.001494125452479267, "train_loss": 4.700829539474824, "epoch": 13, "n_parameters": 5498844} {"train_lr": 0.0014931071411512452, "train_loss": 4.6549373077903144, "epoch": 14, "n_parameters": 5498844} {"train_lr": 0.0014920078880574345, "train_loss": 4.610939756690931, "epoch": 15, "n_parameters": 5498844} {"train_lr": 0.0014908278137433452, "train_loss": 4.558225347436399, "epoch": 16, "n_parameters": 5498844} {"train_lr": 0.0014895670476175297, "train_loss": 4.5358294702881725, "epoch": 17, "n_parameters": 5498844} {"train_lr": 0.0014882257279370923, "train_loss": 4.494899381205237, "epoch": 18, "n_parameters": 5498844} {"train_lr": 0.0014868040017928692, "train_loss": 4.4703150727003695, "test_loss": 1.8361137442991509, "test_acc1": 59.84000184570313, "test_acc5": 83.40000249511719, "epoch": 19, "n_parameters": 5498844} {"train_lr": 0.0014853020250931849, "train_loss": 4.433649067708152, "epoch": 20, "n_parameters": 5498844} {"train_lr": 0.0014837199625466779, "train_loss": 4.408274005893037, "epoch": 21, "n_parameters": 5498844} {"train_lr": 0.0014820579876443744, "train_loss": 4.3936516453417465, "epoch": 22, "n_parameters": 5498844} {"train_lr": 0.0014803162826405153, "train_loss": 4.369779003085755, "epoch": 23, "n_parameters": 5498844} {"train_lr": 0.0014784950385326957, "train_loss": 4.35560642412717, "epoch": 24, "n_parameters": 5498844} {"train_lr": 0.0014765944550408027, "train_loss": 4.330139206670267, "epoch": 25, "n_parameters": 5498844} {"train_lr": 0.001474614740585323, "train_loss": 4.319557490108682, "epoch": 26, "n_parameters": 5498844} {"train_lr": 0.001472556112264245, "train_loss": 4.296143399106322, "epoch": 27, "n_parameters": 5498844} {"train_lr": 0.0014704187958293408, "train_loss": 4.276464555201104, "epoch": 28, "n_parameters": 5498844} {"train_lr": 0.0014682030256614013, "train_loss": 4.265460023324457, "test_loss": 1.6236450756808847, "test_acc1": 63.79000185668945, "test_acc5": 86.05600256591796, "epoch": 29, "n_parameters": 5498844} {"train_lr": 0.0014659090447446384, "train_loss": 4.248843861128882, "epoch": 30, "n_parameters": 5498844} {"train_lr": 0.0014635371046398723, "train_loss": 4.232300464126418, "epoch": 31, "n_parameters": 5498844} {"train_lr": 0.0014610874654571253, "train_loss": 4.229726163674887, "epoch": 32, "n_parameters": 5498844} {"train_lr": 0.0014585603958269045, "train_loss": 4.211376681280651, "epoch": 33, "n_parameters": 5498844} {"train_lr": 0.0014559561728708823, "train_loss": 4.202582645032713, "epoch": 34, "n_parameters": 5498844} {"train_lr": 0.0014532750821714343, "train_loss": 4.189444161016497, "epoch": 35, "n_parameters": 5498844} {"train_lr": 0.0014505174177404001, "train_loss": 4.178470503249995, "epoch": 36, "n_parameters": 5498844} {"train_lr": 0.00144768348198676, "train_loss": 4.162863575404496, "epoch": 37, "n_parameters": 5498844} {"train_lr": 0.0014447735856834417, "train_loss": 4.16514378607416, "epoch": 38, "n_parameters": 5498844} {"train_lr": 0.001441788047933402, "train_loss": 4.157880783521777, "test_loss": 1.5357450562566806, "test_acc1": 65.4000018701172, "test_acc5": 87.1660025415039, "epoch": 39, "n_parameters": 5498844} {"train_lr": 0.0014387271961345588, "train_loss": 4.13958386764776, "epoch": 40, "n_parameters": 5498844} {"train_lr": 0.001435591365943752, "train_loss": 4.133316471076888, "epoch": 41, "n_parameters": 5498844} {"train_lr": 0.0014323809012400694, "train_loss": 4.121563448287029, "epoch": 42, "n_parameters": 5498844} {"train_lr": 0.0014290961540871859, "train_loss": 4.12090629806145, "epoch": 43, "n_parameters": 5498844} {"train_lr": 0.0014257374846946504, "train_loss": 4.114854791765209, "epoch": 44, "n_parameters": 5498844} {"train_lr": 0.0014223052613783597, "train_loss": 4.095949862750886, "epoch": 45, "n_parameters": 5498844} {"train_lr": 0.0014187998605203313, "train_loss": 4.098161561943168, "epoch": 46, "n_parameters": 5498844} {"train_lr": 0.001415221666527278, "train_loss": 4.090290810957515, "epoch": 47, "n_parameters": 5498844} {"train_lr": 0.0014115710717884254, "train_loss": 4.085967622953448, "epoch": 48, "n_parameters": 5498844} {"train_lr": 0.0014078484766326686, "train_loss": 4.0699818298446955, "test_loss": 1.4823833420272066, "test_acc1": 66.81200198730468, "test_acc5": 88.09600245605469, "epoch": 49, "n_parameters": 5498844} {"train_lr": 0.0014040542892845619, "train_loss": 4.0732231953685325, "epoch": 50, "n_parameters": 5498844} {"train_lr": 0.0014001889258194106, "train_loss": 4.064996620102657, "epoch": 51, "n_parameters": 5498844} {"train_lr": 0.0013962528101179224, "train_loss": 4.062493424549949, "epoch": 52, "n_parameters": 5498844} {"train_lr": 0.0013922463738196042, "train_loss": 4.046356149214349, "epoch": 53, "n_parameters": 5498844} {"train_lr": 0.001388170056275224, "train_loss": 4.042181439239154, "epoch": 54, "n_parameters": 5498844} {"train_lr": 0.001384024304499001, "train_loss": 4.035469881731639, "epoch": 55, "n_parameters": 5498844} {"train_lr": 0.0013798095731193541, "train_loss": 4.031900358285835, "epoch": 56, "n_parameters": 5498844} {"train_lr": 0.0013755263243290382, "train_loss": 4.029868579870887, "epoch": 57, "n_parameters": 5498844} {"train_lr": 0.0013711750278345505, "train_loss": 4.017277608898809, "epoch": 58, "n_parameters": 5498844} {"train_lr": 0.0013667561608046155, "train_loss": 4.019141199717895, "test_loss": 1.4441334869490934, "test_acc1": 67.68600188598633, "test_acc5": 88.67000250732421, "epoch": 59, "n_parameters": 5498844} {"train_lr": 0.0013622702078177633, "train_loss": 4.010788615527961, "epoch": 60, "n_parameters": 5498844} {"train_lr": 0.0013577176608093506, "train_loss": 4.005627782594004, "epoch": 61, "n_parameters": 5498844} {"train_lr": 0.001353099019017369, "train_loss": 3.9956299950845904, "epoch": 62, "n_parameters": 5498844} {"train_lr": 0.0013484147889280046, "train_loss": 3.997681376090248, "epoch": 63, "n_parameters": 5498844} {"train_lr": 0.0013436654842199, "train_loss": 3.9983489816065885, "epoch": 64, "n_parameters": 5498844} {"train_lr": 0.0013388516257077697, "train_loss": 3.9904197592982094, "epoch": 65, "n_parameters": 5498844} {"train_lr": 0.0013339737412854293, "train_loss": 3.982907855479742, "epoch": 66, "n_parameters": 5498844} {"train_lr": 0.0013290323658679758, "train_loss": 3.97614231411454, "epoch": 67, "n_parameters": 5498844} {"train_lr": 0.0013240280413328142, "train_loss": 3.9682510000505418, "epoch": 68, "n_parameters": 5498844} {"train_lr": 0.0013189613164605683, "train_loss": 3.9615138575708646, "test_loss": 1.385747451185036, "test_acc1": 68.51000202636719, "test_acc5": 89.17000243652343, "epoch": 69, "n_parameters": 5498844} {"train_lr": 0.0013138327468746884, "train_loss": 3.9660281921081024, "epoch": 70, "n_parameters": 5498844} {"train_lr": 0.00130864289498067, "train_loss": 3.9617457265952987, "epoch": 71, "n_parameters": 5498844} {"train_lr": 0.001303392329904193, "train_loss": 3.963760824071513, "epoch": 72, "n_parameters": 5498844} {"train_lr": 0.001298081627428957, "train_loss": 3.9464029743731452, "epoch": 73, "n_parameters": 5498844} {"train_lr": 0.001292711369933259, "train_loss": 3.950758880455431, "epoch": 74, "n_parameters": 5498844} {"train_lr": 0.0012872821463264423, "train_loss": 3.944981151061664, "epoch": 75, "n_parameters": 5498844} {"train_lr": 0.0012817945519839737, "train_loss": 3.943939899440578, "epoch": 76, "n_parameters": 5498844} {"train_lr": 0.001276249188682435, "train_loss": 3.935706566718461, "epoch": 77, "n_parameters": 5498844} {"train_lr": 0.001270646664533459, "train_loss": 3.932512060820246, "epoch": 78, "n_parameters": 5498844} {"train_lr": 0.001264987593916884, "train_loss": 3.9293258234108093, "test_loss": 1.346250995564598, "test_acc1": 69.50400204956054, "test_acc5": 89.52000260253907, "epoch": 79, "n_parameters": 5498844} {"train_lr": 0.0012592725974135677, "train_loss": 3.924008738949335, "epoch": 80, "n_parameters": 5498844} {"train_lr": 0.0012535023017373635, "train_loss": 3.9214575792745436, "epoch": 81, "n_parameters": 5498844} {"train_lr": 0.0012476773396661296, "train_loss": 3.914579840348684, "epoch": 82, "n_parameters": 5498844} {"train_lr": 0.0012417983499726233, "train_loss": 3.9229775620855207, "epoch": 83, "n_parameters": 5498844} {"train_lr": 0.00123586597735436, "train_loss": 3.9131740274951516, "epoch": 84, "n_parameters": 5498844} {"train_lr": 0.0012298808723627598, "train_loss": 3.906996764486833, "epoch": 85, "n_parameters": 5498844} {"train_lr": 0.0012238436913321116, "train_loss": 3.8981066047311494, "epoch": 86, "n_parameters": 5498844} {"train_lr": 0.0012177550963073647, "train_loss": 3.906924739348993, "epoch": 87, "n_parameters": 5498844} {"train_lr": 0.0012116157549714461, "train_loss": 3.9012015066344103, "epoch": 88, "n_parameters": 5498844} {"train_lr": 0.001205426340572496, "train_loss": 3.896031111806369, "test_loss": 1.3414034480783166, "test_acc1": 69.80800220458984, "test_acc5": 89.80800271484375, "epoch": 89, "n_parameters": 5498844} {"train_lr": 0.0011991875318493601, "train_loss": 3.8858622524092237, "epoch": 90, "n_parameters": 5498844} {"train_lr": 0.0011929000129579043, "train_loss": 3.882509019044187, "epoch": 91, "n_parameters": 5498844} {"train_lr": 0.0011865644733952759, "train_loss": 3.8796053596085116, "epoch": 92, "n_parameters": 5498844} {"train_lr": 0.001180181607924886, "train_loss": 3.879936546265936, "epoch": 93, "n_parameters": 5498844} {"train_lr": 0.0011737521164998377, "train_loss": 3.8730925780406102, "epoch": 94, "n_parameters": 5498844} {"train_lr": 0.0011672767041862814, "train_loss": 3.8760491377539297, "epoch": 95, "n_parameters": 5498844} {"train_lr": 0.0011607560810862106, "train_loss": 3.862193223872154, "epoch": 96, "n_parameters": 5498844} {"train_lr": 0.0011541909622593347, "train_loss": 3.8730857798771607, "epoch": 97, "n_parameters": 5498844} {"train_lr": 0.0011475820676450082, "train_loss": 3.867871627938166, "epoch": 98, "n_parameters": 5498844} {"train_lr": 0.0011409301219829958, "train_loss": 3.8589554413629, "test_loss": 1.3135940388502865, "test_acc1": 70.08400204956055, "test_acc5": 90.27400243652343, "epoch": 99, "n_parameters": 5498844} {"train_lr": 0.001134235854734039, "train_loss": 3.8571838044303117, "epoch": 100, "n_parameters": 5498844} {"train_lr": 0.0011274999999999775, "train_loss": 3.8549131311529834, "epoch": 101, "n_parameters": 5498844} {"train_lr": 0.0011207232964432971, "train_loss": 3.853709993888434, "epoch": 102, "n_parameters": 5498844} {"train_lr": 0.0011139064872057738, "train_loss": 3.8546773978798603, "epoch": 103, "n_parameters": 5498844} {"train_lr": 0.0011070503198274664, "train_loss": 3.8490693541668017, "epoch": 104, "n_parameters": 5498844} {"train_lr": 0.0011001555461642792, "train_loss": 3.8437943555277694, "epoch": 105, "n_parameters": 5498844} {"train_lr": 0.001093222922305959, "train_loss": 3.840830476223517, "epoch": 106, "n_parameters": 5498844} {"train_lr": 0.001086253208492762, "train_loss": 3.8379682683341985, "epoch": 107, "n_parameters": 5498844} {"train_lr": 0.0010792471690323983, "train_loss": 3.8272704805592173, "epoch": 108, "n_parameters": 5498844} {"train_lr": 0.0010722055722159876, "train_loss": 3.82143851034909, "test_loss": 1.3000001975419195, "test_acc1": 70.7340021484375, "test_acc5": 90.41400235351563, "epoch": 109, "n_parameters": 5498844} {"train_lr": 0.001065129190234018, "train_loss": 3.8219242063190917, "epoch": 110, "n_parameters": 5498844} {"train_lr": 0.001058018799091484, "train_loss": 3.821737274467993, "epoch": 111, "n_parameters": 5498844} {"train_lr": 0.0010508751785228995, "train_loss": 3.816403063426582, "epoch": 112, "n_parameters": 5498844} {"train_lr": 0.0010436991119068247, "train_loss": 3.8195201531290817, "epoch": 113, "n_parameters": 5498844} {"train_lr": 0.0010364913861797749, "train_loss": 3.806987988800525, "epoch": 114, "n_parameters": 5498844} {"train_lr": 0.0010292527917500668, "train_loss": 3.7981878269454845, "epoch": 115, "n_parameters": 5498844} {"train_lr": 0.0010219841224112544, "train_loss": 3.7956381547722597, "epoch": 116, "n_parameters": 5498844} {"train_lr": 0.0010146861752547667, "train_loss": 3.7980670520334505, "epoch": 117, "n_parameters": 5498844} {"train_lr": 0.0010073597505827476, "train_loss": 3.7865280270647945, "epoch": 118, "n_parameters": 5498844} {"train_lr": 0.0010000056518202367, "train_loss": 3.7968130762592778, "test_loss": 1.2790934403223553, "test_acc1": 71.01000078430175, "test_acc5": 90.5300008959961, "epoch": 119, "n_parameters": 5498844} {"train_lr": 0.0009926246854270522, "train_loss": 3.799956298864288, "epoch": 120, "n_parameters": 5498844} {"train_lr": 0.000985217660809356, "train_loss": 3.7945215356149835, "epoch": 121, "n_parameters": 5498844} {"train_lr": 0.0009777853902307732, "train_loss": 3.780289442562085, "epoch": 122, "n_parameters": 5498844} {"train_lr": 0.0009703286887236247, "train_loss": 3.789252082560417, "epoch": 123, "n_parameters": 5498844} {"train_lr": 0.0009628483739992136, "train_loss": 3.7783618216498867, "epoch": 124, "n_parameters": 5498844} {"train_lr": 0.0009553452663583552, "train_loss": 3.7664619382444045, "epoch": 125, "n_parameters": 5498844} {"train_lr": 0.0009478201886013921, "train_loss": 3.77271912761515, "epoch": 126, "n_parameters": 5498844} {"train_lr": 0.0009402739659378006, "train_loss": 3.7664139807688817, "epoch": 127, "n_parameters": 5498844} {"train_lr": 0.0009327074258960266, "train_loss": 3.7653131183120703, "epoch": 128, "n_parameters": 5498844} {"train_lr": 0.0009251213982324276, "train_loss": 3.765110251009107, "test_loss": 1.2838377905474312, "test_acc1": 71.66000059570312, "test_acc5": 90.77200083496093, "epoch": 129, "n_parameters": 5498844} {"train_lr": 0.0009175167148404178, "train_loss": 3.750675491952925, "epoch": 130, "n_parameters": 5498844} {"train_lr": 0.0009098942096592476, "train_loss": 3.755403560110562, "epoch": 131, "n_parameters": 5498844} {"train_lr": 0.0009022547185824416, "train_loss": 3.7527787177343304, "epoch": 132, "n_parameters": 5498844} {"train_lr": 0.0008945990793663697, "train_loss": 3.7519919104355988, "epoch": 133, "n_parameters": 5498844} {"train_lr": 0.0008869281315380942, "train_loss": 3.7446248832759528, "epoch": 134, "n_parameters": 5498844} {"train_lr": 0.000879242716303492, "train_loss": 3.7404202338960246, "epoch": 135, "n_parameters": 5498844} {"train_lr": 0.0008715436764549598, "train_loss": 3.7435885757315073, "epoch": 136, "n_parameters": 5498844} {"train_lr": 0.0008638318562789997, "train_loss": 3.73603052108122, "epoch": 137, "n_parameters": 5498844} {"train_lr": 0.0008561081014635556, "train_loss": 3.743284126229995, "epoch": 138, "n_parameters": 5498844} {"train_lr": 0.0008483732590054102, "train_loss": 3.728909273281229, "test_loss": 1.2490950651552486, "test_acc1": 71.90000086181641, "test_acc5": 90.79800079101562, "epoch": 139, "n_parameters": 5498844} {"train_lr": 0.0008406281771171736, "train_loss": 3.7340847254514125, "epoch": 140, "n_parameters": 5498844} {"train_lr": 0.0008328737051344065, "train_loss": 3.7308800127937927, "epoch": 141, "n_parameters": 5498844} {"train_lr": 0.0008251106934222841, "train_loss": 3.7246765077596518, "epoch": 142, "n_parameters": 5498844} {"train_lr": 0.0008173399932825871, "train_loss": 3.722353571217409, "epoch": 143, "n_parameters": 5498844} {"train_lr": 0.0008095624568600761, "train_loss": 3.718812854616619, "epoch": 144, "n_parameters": 5498844} {"train_lr": 0.0008017789370493495, "train_loss": 3.701064998306316, "epoch": 145, "n_parameters": 5498844} {"train_lr": 0.0007939902874010041, "train_loss": 3.7138173235691996, "epoch": 146, "n_parameters": 5498844} {"train_lr": 0.0007861973620282396, "train_loss": 3.7040819877968563, "epoch": 147, "n_parameters": 5498844} {"train_lr": 0.0007784010155131946, "train_loss": 3.703808527430899, "epoch": 148, "n_parameters": 5498844} {"train_lr": 0.0007706021028131006, "train_loss": 3.706329107856293, "test_loss": 1.2459246362077778, "test_acc1": 72.39600063110352, "test_acc5": 91.22000107421874, "epoch": 149, "n_parameters": 5498844} {"train_lr": 0.0007628014791666195, "train_loss": 3.6987964799292654, "epoch": 150, "n_parameters": 5498844} {"train_lr": 0.0007549999999999935, "train_loss": 3.6925297841358242, "epoch": 151, "n_parameters": 5498844} {"train_lr": 0.0007471985208333895, "train_loss": 3.6956688823531287, "epoch": 152, "n_parameters": 5498844} {"train_lr": 0.000739397897186908, "train_loss": 3.69344286225754, "epoch": 153, "n_parameters": 5498844} {"train_lr": 0.000731598984486791, "train_loss": 3.682867795193224, "epoch": 154, "n_parameters": 5498844} {"train_lr": 0.0007238026379717457, "train_loss": 3.6833250251926963, "epoch": 155, "n_parameters": 5498844} {"train_lr": 0.0007160097125989996, "train_loss": 3.6750083920195236, "epoch": 156, "n_parameters": 5498844} {"train_lr": 0.0007082210629506558, "train_loss": 3.682098651085969, "epoch": 157, "n_parameters": 5498844} {"train_lr": 0.0007004375431399113, "train_loss": 3.6761153169798195, "epoch": 158, "n_parameters": 5498844} {"train_lr": 0.0006926600067174185, "train_loss": 3.667432326796672, "test_loss": 1.204009929265099, "test_acc1": 72.85200077514648, "test_acc5": 91.3760007861328, "epoch": 159, "n_parameters": 5498844} {"train_lr": 0.0006848893065777179, "train_loss": 3.6711226558888987, "epoch": 160, "n_parameters": 5498844} {"train_lr": 0.0006771262948656035, "train_loss": 3.6737190320980635, "epoch": 161, "n_parameters": 5498844} {"train_lr": 0.0006693718228828092, "train_loss": 3.6673100199059046, "epoch": 162, "n_parameters": 5498844} {"train_lr": 0.0006616267409945818, "train_loss": 3.646079399960218, "epoch": 163, "n_parameters": 5498844} {"train_lr": 0.0006538918985364373, "train_loss": 3.6573219183358927, "epoch": 164, "n_parameters": 5498844} {"train_lr": 0.0006461681437209942, "train_loss": 3.6507730412897734, "epoch": 165, "n_parameters": 5498844} {"train_lr": 0.0006384563235450294, "train_loss": 3.6611718890174543, "epoch": 166, "n_parameters": 5498844} {"train_lr": 0.0006307572836964984, "train_loss": 3.6407101328710287, "epoch": 167, "n_parameters": 5498844} {"train_lr": 0.0006230718684619012, "train_loss": 3.648871107174338, "epoch": 168, "n_parameters": 5498844} {"train_lr": 0.0006154009206336259, "train_loss": 3.6367619933305884, "test_loss": 1.183149312333814, "test_acc1": 73.49000072387695, "test_acc5": 91.65200086425781, "epoch": 169, "n_parameters": 5498844} {"train_lr": 0.0006077452814175498, "train_loss": 3.634190063039176, "epoch": 170, "n_parameters": 5498844} {"train_lr": 0.0006001057903407651, "train_loss": 3.636305921458655, "epoch": 171, "n_parameters": 5498844} {"train_lr": 0.0005924832851595839, "train_loss": 3.6233131219264414, "epoch": 172, "n_parameters": 5498844} {"train_lr": 0.0005848786017675498, "train_loss": 3.6250863526847295, "epoch": 173, "n_parameters": 5498844} {"train_lr": 0.0005772925741039497, "train_loss": 3.618952938487275, "epoch": 174, "n_parameters": 5498844} {"train_lr": 0.0005697260340621892, "train_loss": 3.620528883624563, "epoch": 175, "n_parameters": 5498844} {"train_lr": 0.0005621798113986145, "train_loss": 3.6158324370442108, "epoch": 176, "n_parameters": 5498844} {"train_lr": 0.0005546547336416323, "train_loss": 3.6087577740976706, "epoch": 177, "n_parameters": 5498844} {"train_lr": 0.0005471516260007746, "train_loss": 3.6159909839431443, "epoch": 178, "n_parameters": 5498844} {"train_lr": 0.0005396713112763611, "train_loss": 3.6069587326700168, "test_loss": 1.1734828325523727, "test_acc1": 73.89200068786622, "test_acc5": 91.81800093505859, "epoch": 179, "n_parameters": 5498844} {"train_lr": 0.0005322146097692112, "train_loss": 3.598576982699924, "epoch": 180, "n_parameters": 5498844} {"train_lr": 0.000524782339190673, "train_loss": 3.606162816786366, "epoch": 181, "n_parameters": 5498844} {"train_lr": 0.0005173753145729492, "train_loss": 3.595703967773228, "epoch": 182, "n_parameters": 5498844} {"train_lr": 0.0005099943481797611, "train_loss": 3.590661280821982, "epoch": 183, "n_parameters": 5498844} {"train_lr": 0.0005026402494172623, "train_loss": 3.593627157641186, "epoch": 184, "n_parameters": 5498844} {"train_lr": 0.0004953138247452536, "train_loss": 3.583563294315295, "epoch": 185, "n_parameters": 5498844} {"train_lr": 0.000488015877588746, "train_loss": 3.5911460063047262, "epoch": 186, "n_parameters": 5498844} {"train_lr": 0.0004807472082499199, "train_loss": 3.573364341921872, "epoch": 187, "n_parameters": 5498844} {"train_lr": 0.0004735086138202327, "train_loss": 3.5809171747961206, "epoch": 188, "n_parameters": 5498844} {"train_lr": 0.0004663008880931849, "train_loss": 3.567919843113251, "test_loss": 1.1505533562138164, "test_acc1": 74.39400067138672, "test_acc5": 92.12400068359375, "epoch": 189, "n_parameters": 5498844} {"train_lr": 0.0004591248214770862, "train_loss": 3.576948427432161, "epoch": 190, "n_parameters": 5498844} {"train_lr": 0.0004519812009085206, "train_loss": 3.561402995362699, "epoch": 191, "n_parameters": 5498844} {"train_lr": 0.00044487080976600375, "train_loss": 3.561582712496785, "epoch": 192, "n_parameters": 5498844} {"train_lr": 0.00043779442778402167, "train_loss": 3.561353889005862, "epoch": 193, "n_parameters": 5498844} {"train_lr": 0.00043075283096761065, "train_loss": 3.5570983135407204, "epoch": 194, "n_parameters": 5498844} {"train_lr": 0.00042374679150723277, "train_loss": 3.550980493229785, "epoch": 195, "n_parameters": 5498844} {"train_lr": 0.0004167770776940377, "train_loss": 3.540118515705891, "epoch": 196, "n_parameters": 5498844} {"train_lr": 0.0004098444538357002, "train_loss": 3.5528664282775466, "epoch": 197, "n_parameters": 5498844} {"train_lr": 0.000402949680172555, "train_loss": 3.5490181797431957, "epoch": 198, "n_parameters": 5498844} {"train_lr": 0.0003960935127942217, "train_loss": 3.5351181791411888, "test_loss": 1.1208571727419723, "test_acc1": 74.72000078491212, "test_acc5": 92.47800084228516, "epoch": 199, "n_parameters": 5498844} {"train_lr": 0.00038927670355671216, "train_loss": 3.5292301379072724, "epoch": 200, "n_parameters": 5498844} {"train_lr": 0.0003825000000000037, "train_loss": 3.534933429470451, "epoch": 201, "n_parameters": 5498844} {"train_lr": 0.000375764145265968, "train_loss": 3.5306026937721446, "epoch": 202, "n_parameters": 5498844} {"train_lr": 0.00036906987801701454, "train_loss": 3.52688211073085, "epoch": 203, "n_parameters": 5498844} {"train_lr": 0.0003624179323549748, "train_loss": 3.5159562045811033, "epoch": 204, "n_parameters": 5498844} {"train_lr": 0.00035580903774064737, "train_loss": 3.5106779455745536, "epoch": 205, "n_parameters": 5498844} {"train_lr": 0.00034924391891380123, "train_loss": 3.5070145489018167, "epoch": 206, "n_parameters": 5498844} {"train_lr": 0.0003427232958137021, "train_loss": 3.5151845101329635, "epoch": 207, "n_parameters": 5498844} {"train_lr": 0.0003362478835001678, "train_loss": 3.5042536601299146, "epoch": 208, "n_parameters": 5498844} {"train_lr": 0.0003298183920751001, "train_loss": 3.501142034740399, "test_loss": 1.1101681669296204, "test_acc1": 75.07600104125977, "test_acc5": 92.51200083984375, "epoch": 209, "n_parameters": 5498844} {"train_lr": 0.00032343552660470695, "train_loss": 3.4931489965773457, "epoch": 210, "n_parameters": 5498844} {"train_lr": 0.00031709998704210364, "train_loss": 3.499601492591256, "epoch": 211, "n_parameters": 5498844} {"train_lr": 0.00031081246815062134, "train_loss": 3.5019966828362117, "epoch": 212, "n_parameters": 5498844} {"train_lr": 0.00030457365942753627, "train_loss": 3.4862291213187526, "epoch": 213, "n_parameters": 5498844} {"train_lr": 0.0002983842450285365, "train_loss": 3.483109030345504, "epoch": 214, "n_parameters": 5498844} {"train_lr": 0.0002922449036926526, "train_loss": 3.485362630587616, "epoch": 215, "n_parameters": 5498844} {"train_lr": 0.0002861563086678732, "train_loss": 3.477959041544002, "epoch": 216, "n_parameters": 5498844} {"train_lr": 0.00028011912763722897, "train_loss": 3.4737565908268344, "epoch": 217, "n_parameters": 5498844} {"train_lr": 0.00027413402264565205, "train_loss": 3.47571116370513, "epoch": 218, "n_parameters": 5498844} {"train_lr": 0.0002682016500273682, "train_loss": 3.4691688080164167, "test_loss": 1.0763107322413346, "test_acc1": 75.90000086669922, "test_acc5": 92.83800093261719, "epoch": 219, "n_parameters": 5498844} {"train_lr": 0.00026232266033388013, "train_loss": 3.4564698655470956, "epoch": 220, "n_parameters": 5498844} {"train_lr": 0.00025649769826265625, "train_loss": 3.4574228351314864, "epoch": 221, "n_parameters": 5498844} {"train_lr": 0.0002507274025864154, "train_loss": 3.4514319565441967, "epoch": 222, "n_parameters": 5498844} {"train_lr": 0.00024501240608312813, "train_loss": 3.4486838541656946, "epoch": 223, "n_parameters": 5498844} {"train_lr": 0.00023935333546654323, "train_loss": 3.441871205268861, "epoch": 224, "n_parameters": 5498844} {"train_lr": 0.00023375081131754512, "train_loss": 3.4412261355462834, "epoch": 225, "n_parameters": 5498844} {"train_lr": 0.00022820544801602227, "train_loss": 3.434967328461526, "epoch": 226, "n_parameters": 5498844} {"train_lr": 0.00022271785367356016, "train_loss": 3.4356830655831656, "epoch": 227, "n_parameters": 5498844} {"train_lr": 0.00021728863006672194, "train_loss": 3.426836194483925, "epoch": 228, "n_parameters": 5498844} {"train_lr": 0.00021191837257104475, "train_loss": 3.4297244270785536, "test_loss": 1.053340161240649, "test_acc1": 76.42400083984376, "test_acc5": 93.11000077636719, "epoch": 229, "n_parameters": 5498844} {"train_lr": 0.00020660767009580017, "train_loss": 3.4273269955846044, "epoch": 230, "n_parameters": 5498844} {"train_lr": 0.00020135710501933987, "train_loss": 3.407505639317296, "epoch": 231, "n_parameters": 5498844} {"train_lr": 0.0001961672531253057, "train_loss": 3.417496662774532, "epoch": 232, "n_parameters": 5498844} {"train_lr": 0.00019103868353944288, "train_loss": 3.419695227355551, "epoch": 233, "n_parameters": 5498844} {"train_lr": 0.0001859719586671909, "train_loss": 3.40697601299992, "epoch": 234, "n_parameters": 5498844} {"train_lr": 0.00018096763413203755, "train_loss": 3.3992043205802673, "epoch": 235, "n_parameters": 5498844} {"train_lr": 0.00017602625871455667, "train_loss": 3.397608393405696, "epoch": 236, "n_parameters": 5498844} {"train_lr": 0.0001711483742922467, "train_loss": 3.3943316863148474, "epoch": 237, "n_parameters": 5498844} {"train_lr": 0.00016633451578011268, "train_loss": 3.3860102975272017, "epoch": 238, "n_parameters": 5498844} {"train_lr": 0.00016158521107197287, "train_loss": 3.391723998212557, "test_loss": 1.033976229014753, "test_acc1": 76.81800090209961, "test_acc5": 93.33200087646485, "epoch": 239, "n_parameters": 5498844} {"train_lr": 0.00015690098098261856, "train_loss": 3.390645173706597, "epoch": 240, "n_parameters": 5498844} {"train_lr": 0.00015228233919066484, "train_loss": 3.3805394829284374, "epoch": 241, "n_parameters": 5498844} {"train_lr": 0.0001477297921822251, "train_loss": 3.37865626954918, "epoch": 242, "n_parameters": 5498844} {"train_lr": 0.00014324383919539206, "train_loss": 3.372644835399638, "epoch": 243, "n_parameters": 5498844} {"train_lr": 0.00013882497216545218, "train_loss": 3.3659167044061267, "epoch": 244, "n_parameters": 5498844} {"train_lr": 0.00013447367567097436, "train_loss": 3.359964396813505, "epoch": 245, "n_parameters": 5498844} {"train_lr": 0.00013019042688065826, "train_loss": 3.363326682193245, "epoch": 246, "n_parameters": 5498844} {"train_lr": 0.0001259756955010005, "train_loss": 3.3554827800864797, "epoch": 247, "n_parameters": 5498844} {"train_lr": 0.00012182994372478594, "train_loss": 3.355530333899551, "epoch": 248, "n_parameters": 5498844} {"train_lr": 0.00011775362618042428, "train_loss": 3.351437228894848, "test_loss": 1.0310108689912434, "test_acc1": 77.11400085083008, "test_acc5": 93.51200069335937, "epoch": 249, "n_parameters": 5498844} {"train_lr": 0.00011374718988206232, "train_loss": 3.3500945948564604, "epoch": 250, "n_parameters": 5498844} {"train_lr": 0.00010981107418059352, "train_loss": 3.348843896310392, "epoch": 251, "n_parameters": 5498844} {"train_lr": 0.00010594571071545856, "train_loss": 3.344284920169295, "epoch": 252, "n_parameters": 5498844} {"train_lr": 0.0001021515233673206, "train_loss": 3.340828749809048, "epoch": 253, "n_parameters": 5498844} {"train_lr": 9.842892821157986e-05, "train_loss": 3.330344907457022, "epoch": 254, "n_parameters": 5498844} {"train_lr": 9.477833347274443e-05, "train_loss": 3.3329234104648195, "epoch": 255, "n_parameters": 5498844} {"train_lr": 9.12001394796647e-05, "train_loss": 3.331772677877324, "epoch": 256, "n_parameters": 5498844} {"train_lr": 8.769473862163653e-05, "train_loss": 3.322286539619489, "epoch": 257, "n_parameters": 5498844} {"train_lr": 8.426251530536481e-05, "train_loss": 3.3213807869193364, "epoch": 258, "n_parameters": 5498844} {"train_lr": 8.090384591281436e-05, "train_loss": 3.319420635593023, "test_loss": 1.0005149342034054, "test_acc1": 77.52200100585938, "test_acc5": 93.77000092041015, "epoch": 259, "n_parameters": 5498844} {"train_lr": 7.761909875993307e-05, "train_loss": 3.313142391676597, "epoch": 260, "n_parameters": 5498844} {"train_lr": 7.440863405626344e-05, "train_loss": 3.3114134452039963, "epoch": 261, "n_parameters": 5498844} {"train_lr": 7.127280386543524e-05, "train_loss": 3.306579649895072, "epoch": 262, "n_parameters": 5498844} {"train_lr": 6.821195206656816e-05, "train_loss": 3.3125476918810848, "epoch": 263, "n_parameters": 5498844} {"train_lr": 6.522641431655447e-05, "train_loss": 3.2939331122814752, "epoch": 264, "n_parameters": 5498844} {"train_lr": 6.231651801325206e-05, "train_loss": 3.2957491507257917, "epoch": 265, "n_parameters": 5498844} {"train_lr": 5.948258225958532e-05, "train_loss": 3.2972074094579087, "epoch": 266, "n_parameters": 5498844} {"train_lr": 5.672491782854153e-05, "train_loss": 3.295253487540592, "epoch": 267, "n_parameters": 5498844} {"train_lr": 5.404382712910265e-05, "train_loss": 3.2918315168193204, "epoch": 268, "n_parameters": 5498844} {"train_lr": 5.1439604173077446e-05, "train_loss": 3.300519437893189, "test_loss": 0.9885661878633774, "test_acc1": 77.9140007788086, "test_acc5": 93.74800100341797, "epoch": 269, "n_parameters": 5498844} {"train_lr": 4.8912534542859366e-05, "train_loss": 3.2869416272325767, "epoch": 270, "n_parameters": 5498844} {"train_lr": 4.64628953601101e-05, "train_loss": 3.2867780881945037, "epoch": 271, "n_parameters": 5498844} {"train_lr": 4.40909552553738e-05, "train_loss": 3.28100550705366, "epoch": 272, "n_parameters": 5498844} {"train_lr": 4.179697433860962e-05, "train_loss": 3.2832619231238924, "epoch": 273, "n_parameters": 5498844} {"train_lr": 3.958120417067726e-05, "train_loss": 3.2846109431138713, "epoch": 274, "n_parameters": 5498844} {"train_lr": 3.744388773574431e-05, "train_loss": 3.28260659520253, "epoch": 275, "n_parameters": 5498844} {"train_lr": 3.5385259414644674e-05, "train_loss": 3.2770800881570192, "epoch": 276, "n_parameters": 5498844} {"train_lr": 3.3405544959169265e-05, "train_loss": 3.27500902693406, "epoch": 277, "n_parameters": 5498844} {"train_lr": 3.150496146732081e-05, "train_loss": 3.2738929341772764, "epoch": 278, "n_parameters": 5498844} {"train_lr": 2.9683717359496194e-05, "train_loss": 3.2678264006078956, "test_loss": 0.9847472103248383, "test_acc1": 78.13800084228515, "test_acc5": 93.8960008227539, "epoch": 279, "n_parameters": 5498844} {"train_lr": 2.7942012355633404e-05, "train_loss": 3.263109210494468, "epoch": 280, "n_parameters": 5498844} {"train_lr": 2.6280037453314815e-05, "train_loss": 3.2618429808022023, "epoch": 281, "n_parameters": 5498844} {"train_lr": 2.4697974906816924e-05, "train_loss": 3.2698948190634627, "epoch": 282, "n_parameters": 5498844} {"train_lr": 2.319599820712709e-05, "train_loss": 3.260701488346147, "epoch": 283, "n_parameters": 5498844} {"train_lr": 2.177427206291483e-05, "train_loss": 3.2527646625356423, "epoch": 284, "n_parameters": 5498844} {"train_lr": 2.0432952382473795e-05, "train_loss": 3.258609218384436, "epoch": 285, "n_parameters": 5498844} {"train_lr": 1.9172186256622544e-05, "train_loss": 3.258166954698537, "epoch": 286, "n_parameters": 5498844} {"train_lr": 1.7992111942573368e-05, "train_loss": 3.2512748807990293, "epoch": 287, "n_parameters": 5498844} {"train_lr": 1.689285884877437e-05, "train_loss": 3.2623684651595797, "epoch": 288, "n_parameters": 5498844} {"train_lr": 1.5874547520713972e-05, "train_loss": 3.252865689639136, "test_loss": 0.9797613292333038, "test_acc1": 78.20800069946289, "test_acc5": 93.93600080078124, "epoch": 289, "n_parameters": 5498844} {"train_lr": 1.493728962770468e-05, "train_loss": 3.247846332599791, "epoch": 290, "n_parameters": 5498844} {"train_lr": 1.4081187950636669e-05, "train_loss": 3.252932017646748, "epoch": 291, "n_parameters": 5498844} {"train_lr": 1.3306336370705135e-05, "train_loss": 3.246301533953606, "epoch": 292, "n_parameters": 5498844} {"train_lr": 1.2612819859119116e-05, "train_loss": 3.250600523532009, "epoch": 293, "n_parameters": 5498844} {"train_lr": 1.2000714467778719e-05, "train_loss": 3.2469807530550074, "epoch": 294, "n_parameters": 5498844} {"train_lr": 1.1470087320937668e-05, "train_loss": 3.243682384526701, "epoch": 295, "n_parameters": 5498844} {"train_lr": 1.1020996607842462e-05, "train_loss": 3.24823594008454, "epoch": 296, "n_parameters": 5498844} {"train_lr": 1.0653491576350343e-05, "train_loss": 3.248996904401256, "epoch": 297, "n_parameters": 5498844} {"train_lr": 1.036761252753003e-05, "train_loss": 3.2443617321908187, "epoch": 298, "n_parameters": 5498844} {"train_lr": 1.0163390811239968e-05, "train_loss": 3.25708865840658, "test_loss": 0.9709683276884172, "test_acc1": 78.28000100219727, "test_acc5": 93.99000075683594, "epoch": 299, "n_parameters": 5498844}