Soptq's picture
Upload main results checkpoints and logs
a66e0d7 verified
{"train_lr": 5.796761823604603e-06, "train_min_lr": 4.3623151888942615e-09, "train_loss": 2.766492031601925, "train_loss_scale": 65536.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.052987583909934, "val_loss": 1.1287840834030738, "val_acc1": 73.91348525464282, "val_acc5": 91.30281241783017, "epoch": 0, "n_parameters": 7033744}
{"train_lr": 1.3398380911802301e-05, "train_min_lr": 1.0082863905179636e-08, "train_loss": 2.7523064762353897, "train_loss_scale": 65536.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.1467811728691775, "val_loss": 1.1280001293366344, "val_acc1": 74.12068174187526, "val_acc5": 91.42409786041611, "epoch": 1, "n_parameters": 7033744}
{"train_lr": 2.1e-05, "train_min_lr": 1.580341262146501e-08, "train_loss": 2.7505678130002322, "train_loss_scale": 122592.10223642172, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.157926769937062, "val_loss": 1.128691458537315, "val_acc1": 73.9235924026184, "val_acc5": 91.23711595598895, "epoch": 2, "n_parameters": 7033744}
{"train_lr": 2.8601619088197708e-05, "train_min_lr": 2.1523961337750373e-08, "train_loss": 2.75004669057485, "train_loss_scale": 131072.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.187909469563867, "val_loss": 1.1297500137812817, "val_acc1": 73.67091411963024, "val_acc5": 91.4139907679607, "epoch": 3, "n_parameters": 7033744}
{"train_lr": 3.620323817639542e-05, "train_min_lr": 2.7244510054035785e-08, "train_loss": 2.748580263731198, "train_loss_scale": 228154.6155484558, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.194184198674049, "val_loss": 1.1309940941775074, "val_acc1": 73.72650322992199, "val_acc5": 91.28765156631978, "epoch": 4, "n_parameters": 7033744}
{"train_lr": 3.995011322111233e-05, "train_min_lr": 3.00641963574992e-08, "train_loss": 2.7458091202222756, "train_loss_scale": 262144.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.20612795030474, "val_loss": 1.1234162330197601, "val_acc1": 73.85284240380282, "val_acc5": 91.4695800448129, "epoch": 5, "n_parameters": 7033744}
{"train_lr": 3.965141816880098e-05, "train_min_lr": 2.9839415349896006e-08, "train_loss": 2.756216258175584, "train_loss_scale": 422250.0532481363, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.234621368404141, "val_loss": 1.127847880536977, "val_acc1": 73.95896738351945, "val_acc5": 91.22195525253231, "epoch": 6, "n_parameters": 7033744}
{"train_lr": 3.9058579110150524e-05, "train_min_lr": 2.939327819456398e-08, "train_loss": 2.736829403744211, "train_loss_scale": 524288.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.190921060574321, "val_loss": 1.1265247498209088, "val_acc1": 74.06509235398273, "val_acc5": 91.27249085129645, "epoch": 7, "n_parameters": 7033744}
{"train_lr": 3.818094547126076e-05, "train_min_lr": 2.873282074095189e-08, "train_loss": 2.7454542378806712, "train_loss_scale": 776381.750798722, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.257847345929049, "val_loss": 1.1216933087875636, "val_acc1": 73.93369955059396, "val_acc5": 91.38872297204864, "epoch": 8, "n_parameters": 7033744}
{"train_lr": 3.703235805888975e-05, "train_min_lr": 2.7868458797641472e-08, "train_loss": 2.735197303981319, "train_loss_scale": 1048576.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.203770769543795, "val_loss": 1.1213409971230879, "val_acc1": 73.90843163438824, "val_acc5": 91.44936554528786, "epoch": 9, "n_parameters": 7033744}
{"train_lr": 3.56309307826638e-05, "train_min_lr": 2.6813823868823523e-08, "train_loss": 2.7304389027678293, "train_loss_scale": 1416526.790202343, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.2953459284683895, "val_loss": 1.1244759876639223, "val_acc1": 74.08530656665364, "val_acc5": 91.3634551946433, "epoch": 10, "n_parameters": 7033744}
{"train_lr": 3.3998764987900644e-05, "train_min_lr": 2.5585548177333914e-08, "train_loss": 2.7344873623567394, "train_loss_scale": 2097152.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.310826039542786, "val_loss": 1.1359453071266985, "val_acc1": 73.66586059190925, "val_acc5": 91.26743730738208, "epoch": 11, "n_parameters": 7033744}
{"train_lr": 3.216160090419244e-05, "train_min_lr": 2.4203002364563575e-08, "train_loss": 2.727030398762518, "train_loss_scale": 2560580.1576144835, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.270268705325385, "val_loss": 1.1166783234534354, "val_acc1": 73.98423507764457, "val_acc5": 91.4493657858752, "epoch": 12, "n_parameters": 7033744}
{"train_lr": 3.014841170660801e-05, "train_min_lr": 2.268799000387303e-08, "train_loss": 2.7199884558193728, "train_loss_scale": 4194304.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.3104823669051715, "val_loss": 1.1240628100573444, "val_acc1": 74.00444954940953, "val_acc5": 91.25227649288513, "epoch": 13, "n_parameters": 7033744}
{"train_lr": 2.7990946591414164e-05, "train_min_lr": 2.106440374521459e-08, "train_loss": 2.7214455872742387, "train_loss_scale": 4576213.469648562, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.362951320327255, "val_loss": 1.1239129707503777, "val_acc1": 73.7568247201155, "val_acc5": 91.36345506509628, "epoch": 14, "n_parameters": 7033744}
{"train_lr": 2.5723230072284647e-05, "train_min_lr": 1.935784851377099e-08, "train_loss": 2.7111076358566906, "train_loss_scale": 8388608.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.4035205109812585, "val_loss": 1.1190634060364504, "val_acc1": 73.90337814368068, "val_acc5": 91.47463367432084, "epoch": 15, "n_parameters": 7033744}
{"train_lr": 2.3381025393394265e-05, "train_min_lr": 1.759523770498859e-08, "train_loss": 2.722221492467343, "train_loss_scale": 8388608.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.409071534332503, "val_loss": 1.1222793073393404, "val_acc1": 74.19143149085014, "val_acc5": 91.37861573153947, "epoch": 16, "n_parameters": 7033744}
{"train_lr": 2.1001270521694432e-05, "train_min_lr": 1.5804368744254613e-08, "train_loss": 2.7124379699666914, "train_loss_scale": 16451141.248136315, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.405713900971336, "val_loss": 1.1212108970906298, "val_acc1": 74.13584236205166, "val_acc5": 91.42915141589718, "epoch": 17, "n_parameters": 7033744}
{"train_lr": 1.8621495613108523e-05, "train_min_lr": 1.4013484704893083e-08, "train_loss": 2.705171400111831, "train_loss_scale": 16777216.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.393888255658622, "val_loss": 1.1152486553630576, "val_acc1": 74.26218143414555, "val_acc5": 91.31797278816589, "epoch": 18, "n_parameters": 7033744}
{"train_lr": 1.6279231139553547e-05, "train_min_lr": 1.2250828898026982e-08, "train_loss": 2.695304168806797, "train_loss_scale": 30722495.113951012, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.422047192042374, "val_loss": 1.1174136872331684, "val_acc1": 74.01455663261159, "val_acc5": 91.36345497256268, "epoch": 19, "n_parameters": 7033744}
{"train_lr": 1.4011416010978406e-05, "train_min_lr": 1.0544199458690121e-08, "train_loss": 2.6973604507212694, "train_loss_scale": 33554432.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.448751109349715, "val_loss": 1.1172529654935575, "val_acc1": 74.17627082440693, "val_acc5": 91.40893721247963, "epoch": 20, "n_parameters": 7033744}
{"train_lr": 1.1853815026687832e-05, "train_min_lr": 8.920510952631953e-09, "train_loss": 2.702480722444888, "train_loss_scale": 57085415.46325879, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.408106899870851, "val_loss": 1.115336077968375, "val_acc1": 74.28239581337692, "val_acc5": 91.4089371939729, "epoch": 21, "n_parameters": 7033744}
{"train_lr": 9.84045484309253e-06, "train_min_lr": 7.405369917537388e-09, "train_loss": 2.6873067954001715, "train_loss_scale": 67108864.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.480403551278404, "val_loss": 1.1171580284045866, "val_acc1": 74.18637800014258, "val_acc5": 91.36345515762986, "epoch": 22, "n_parameters": 7033744}
{"train_lr": 8.0030873530108e-06, "train_min_lr": 6.02267103263132e-09, "train_loss": 2.695888483359283, "train_loss_scale": 105451681.3972311, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.493371952329073, "val_loss": 1.1151480245977068, "val_acc1": 74.3733599138231, "val_acc5": 91.31291956580574, "epoch": 23, "n_parameters": 7033744}
{"train_lr": 6.370688939351329e-06, "train_min_lr": 4.79422028531298e-09, "train_loss": 2.6928711958840506, "train_loss_scale": 134217728.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.4894860900375155, "val_loss": 1.1161840702407062, "val_acc1": 74.47948480100614, "val_acc5": 91.31291934372513, "epoch": 24, "n_parameters": 7033744}
{"train_lr": 4.9690035002451514e-06, "train_min_lr": 3.739391077708465e-09, "train_loss": 2.6981368632362295, "train_loss_scale": 193465063.73588926, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.503132145244854, "val_loss": 1.115710699572586, "val_acc1": 74.35819926588661, "val_acc5": 91.31797288069947, "epoch": 25, "n_parameters": 7033744}
{"train_lr": 3.820136452393189e-06, "train_min_lr": 2.8748186965461473e-09, "train_loss": 2.6885893122710613, "train_loss_scale": 268435456.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.526718641876286, "val_loss": 1.1131801881397574, "val_acc1": 74.17627093544723, "val_acc5": 91.44431215636726, "epoch": 26, "n_parameters": 7033744}
{"train_lr": 2.942206115440049e-06, "train_min_lr": 2.2141379647474633e-09, "train_loss": 2.693267487283078, "train_loss_scale": 352053529.3546326, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.516044377518919, "val_loss": 1.113148590979668, "val_acc1": 74.37841343229073, "val_acc5": 91.37356232411216, "epoch": 27, "n_parameters": 7033744}
{"train_lr": 2.349057975249593e-06, "train_min_lr": 1.7677682121243997e-09, "train_loss": 2.682887580003728, "train_loss_scale": 536870912.0, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.491146889484474, "val_loss": 1.1139164198046694, "val_acc1": 74.3531456548854, "val_acc5": 91.39883012002421, "epoch": 28, "n_parameters": 7033744}
{"train_lr": 2.0500463323221688e-06, "train_min_lr": 1.5427489563242004e-09, "train_loss": 2.682087733627508, "train_loss_scale": 634353862.4749733, "train_weight_decay": 0.0999999999999966, "train_grad_norm": 5.537904883091188, "val_loss": 1.11356991998708, "val_acc1": 74.28239587815044, "val_acc5": 91.40893726799978, "epoch": 29, "n_parameters": 7033744}
{"Final top-1": 76.5350988022439, "Final Top-5": 92.86905544044069}