SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.4442058801651001, "lr": 1e-05, "grad_norm": 0.26566195487976074, "tokens": 146, "tok_per_s": 142.6038668042789, "t": 1.61}2{"step": 50, "loss": 0.3302801251411438, "lr": 0.00051, "grad_norm": 0.12795601785182953, "tokens": 8382, "tok_per_s": 115.26923182435175, "t": 73.3}3{"step": 100, "loss": 0.45227131247520447, "lr": 0.001, "grad_norm": 0.07484367489814758, "tokens": 16548, "tok_per_s": 114.00094680417554, "t": 145.74}4{"step": 150, "loss": 0.3129723072052002, "lr": 0.0009993400362330058, "grad_norm": 0.08788355439901352, "tokens": 24812, "tok_per_s": 114.53308215759476, "t": 217.22}5{"step": 200, "loss": 0.4257463812828064, "lr": 0.0009973620807194618, "grad_norm": 0.10304352641105652, "tokens": 33400, "tok_per_s": 115.85383846092705, "t": 288.87}6{"step": 250, "loss": 0.3977409601211548, "lr": 0.000994071935143687, "grad_norm": 0.15990205109119415, "tokens": 41583, "tok_per_s": 115.66768776120531, "t": 360.09}7{"step": 300, "loss": 0.34691986441612244, "lr": 0.000989479250069539, "grad_norm": 0.046245746314525604, "tokens": 49989, "tok_per_s": 115.83250566898845, "t": 432.14}8{"step": 350, "loss": 0.4594186842441559, "lr": 0.0009835974966336503, "grad_norm": 0.11592946201562881, "tokens": 58214, "tok_per_s": 115.79196977986399, "t": 503.33}9{"step": 400, "loss": 0.40671858191490173, "lr": 0.0009764439270322612, "grad_norm": 0.10639804601669312, "tokens": 66391, "tok_per_s": 115.63506143863032, "t": 574.72}10{"step": 450, "loss": 0.29914480447769165, "lr": 0.0009680395239175562, "grad_norm": 0.04916009679436684, "tokens": 74699, "tok_per_s": 115.60729014803182, "t": 646.72}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.46037233163712354, "val_loss_b2": 0.4587469895289061, "val_loss_b4": 0.4570851577450455, "val_loss_b8": 0.45723892539049266, "t": 734.2}12{"step": 500, "loss": 0.5816026926040649, "lr": 0.0009584089388519307, "grad_norm": 0.09193511307239532, "tokens": 83038, "tok_per_s": 112.97457022257555, "t": 735.6}13{"step": 550, "loss": 0.39662158489227295, "lr": 0.0009475804200007103, "grad_norm": 0.03103887289762497, "tokens": 91441, "tok_per_s": 113.5680009104975, "t": 805.75}14{"step": 600, "loss": 0.4760717749595642, "lr": 0.0009355857292754152, "grad_norm": 0.07478009909391403, "tokens": 99553, "tok_per_s": 113.52580062536418, "t": 877.5}15{"step": 650, "loss": 0.41480961441993713, "lr": 0.0009224600491706008, "grad_norm": 0.208595871925354, "tokens": 107666, "tok_per_s": 113.46486137026837, "t": 949.47}16{"step": 700, "loss": 0.4368736743927002, "lr": 0.0009082418795675396, "grad_norm": 0.05104822665452957, "tokens": 115959, "tok_per_s": 113.57652221787296, "t": 1021.56}17{"step": 750, "loss": 0.40659040212631226, "lr": 0.0008929729248074364, "grad_norm": 0.1446484923362732, "tokens": 124302, "tok_per_s": 113.6920726322617, "t": 1093.9}18{"step": 800, "loss": 0.4863240420818329, "lr": 0.0008766979713654089, "grad_norm": 0.07468735426664352, "tokens": 132734, "tok_per_s": 114.05675798064564, "t": 1164.33}19{"step": 850, "loss": 0.49689337611198425, "lr": 0.0008594647564840406, "grad_norm": 0.09858051687479019, "tokens": 141025, "tok_per_s": 114.25206166723694, "t": 1234.91}20{"step": 900, "loss": 0.4579603970050812, "lr": 0.0008413238281518224, "grad_norm": 0.20093727111816406, "tokens": 149035, "tok_per_s": 114.21732899036809, "t": 1305.42}21{"step": 950, "loss": 0.403351753950119, "lr": 0.0008223283968371944, "grad_norm": 0.06825621426105499, "tokens": 157135, "tok_per_s": 114.29407845218333, "t": 1375.41}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45742617927201573, "val_loss_b2": 0.4545834110310772, "val_loss_b4": 0.4511198830639805, "val_loss_b8": 0.449984414639762, "t": 1462.02}23{"step": 1000, "loss": 0.4254775047302246, "lr": 0.000802534179413072, "grad_norm": 0.12758596241474152, "tokens": 165602, "tok_per_s": 113.21122383611645, "t": 1463.35}24{"step": 1050, "loss": 0.37501847743988037, "lr": 0.0007819992357296598, "grad_norm": 0.18022030591964722, "tokens": 173674, "tok_per_s": 113.16670335138896, "t": 1535.26}25{"step": 1100, "loss": 0.3768076002597809, "lr": 0.0007607837983149056, "grad_norm": 0.06416597217321396, "tokens": 181834, "tok_per_s": 113.23112931799395, "t": 1606.44}26{"step": 1150, "loss": 0.4205983877182007, "lr": 0.0007389500957021191, "grad_norm": 0.1021963581442833, "tokens": 190158, "tok_per_s": 114.28441023049137, "t": 1664.48}27{"step": 1200, "loss": 0.3997196555137634, "lr": 0.0007165621699029615, "grad_norm": 0.15934248268604279, "tokens": 198573, "tok_per_s": 115.33061231064146, "t": 1722.35}28{"step": 1250, "loss": 0.47409239411354065, "lr": 0.000693685688561191, "grad_norm": 0.11943033337593079, "tokens": 206880, "tok_per_s": 116.24228023282878, "t": 1780.31}29{"step": 1300, "loss": 0.3151923716068268, "lr": 0.0006703877523381495, "grad_norm": 0.11243133991956711, "tokens": 215095, "tok_per_s": 117.05188333899085, "t": 1838.18}30{"step": 1350, "loss": 0.4008791744709015, "lr": 0.0006467366980949609, "grad_norm": 0.16221584379673004, "tokens": 223349, "tok_per_s": 117.85082564820458, "t": 1895.76}31{"step": 1400, "loss": 0.4429158568382263, "lr": 0.0006228018984487442, "grad_norm": 0.08774591237306595, "tokens": 231716, "tok_per_s": 118.64879337748675, "t": 1953.54}32{"step": 1450, "loss": 0.5093106627464294, "lr": 0.0005986535582907738, "grad_norm": 0.16429488360881805, "tokens": 239960, "tok_per_s": 119.39434684928833, "t": 2010.39}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4570828151561874, "val_loss_b2": 0.45443070093477345, "val_loss_b4": 0.4524719742144664, "val_loss_b8": 0.45787258721620006, "t": 2080.56}34{"step": 1500, "loss": 0.4425789713859558, "lr": 0.000574362508863438, "grad_norm": 0.170491561293602, "tokens": 248357, "tok_per_s": 119.3333893978972, "t": 2081.78}35{"step": 1550, "loss": 0.5680528283119202, "lr": 0.00055, "grad_norm": 0.259628564119339, "tokens": 256793, "tok_per_s": 120.1686742803747, "t": 2137.52}36{"step": 1600, "loss": 0.4874943494796753, "lr": 0.0005256374911365621, "grad_norm": 0.13048462569713593, "tokens": 265023, "tok_per_s": 120.90437291647063, "t": 2192.58}37{"step": 1650, "loss": 0.5266953110694885, "lr": 0.0005013464417092262, "grad_norm": 0.18775279819965363, "tokens": 273283, "tok_per_s": 121.62191383764889, "t": 2247.57}38{"step": 1700, "loss": 0.4652155637741089, "lr": 0.00047719810155125587, "grad_norm": 0.17218419909477234, "tokens": 281671, "tok_per_s": 123.21417701385661, "t": 2286.61}39{"step": 1750, "loss": 0.4079532325267792, "lr": 0.0004532633019050392, "grad_norm": 0.08724191784858704, "tokens": 289799, "tok_per_s": 124.65161216940453, "t": 2325.45}40{"step": 1800, "loss": 0.36326223611831665, "lr": 0.0004296122476618507, "grad_norm": 0.12728826701641083, "tokens": 298140, "tok_per_s": 126.12334115973194, "t": 2364.46}41{"step": 1850, "loss": 0.4664868116378784, "lr": 0.00040631431143880916, "grad_norm": 0.15473872423171997, "tokens": 306518, "tok_per_s": 127.58493980585114, "t": 2403.04}42{"step": 1900, "loss": 0.34554028511047363, "lr": 0.00038343783009703845, "grad_norm": 0.09950820356607437, "tokens": 314885, "tok_per_s": 128.97587968518243, "t": 2442.0}43{"step": 1950, "loss": 0.32253697514533997, "lr": 0.000361049904297881, "grad_norm": 0.20983266830444336, "tokens": 322988, "tok_per_s": 130.25181574586648, "t": 2480.3}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4556730316447883, "val_loss_b2": 0.4522779708192994, "val_loss_b4": 0.4501180662904366, "val_loss_b8": 0.4546808446787331, "t": 2527.88}45{"step": 2000, "loss": 0.48750779032707214, "lr": 0.0003392162016850945, "grad_norm": 0.14171190559864044, "tokens": 331190, "tok_per_s": 131.00242203377758, "t": 2528.7}46{"step": 2050, "loss": 0.3983094394207001, "lr": 0.0003180007642703402, "grad_norm": 0.16070474684238434, "tokens": 339365, "tok_per_s": 132.2069667786942, "t": 2567.5}47{"step": 2100, "loss": 0.3568074703216553, "lr": 0.000297465820586928, "grad_norm": 0.1417226940393448, "tokens": 347821, "tok_per_s": 133.4743860263013, "t": 2606.48}48{"step": 2150, "loss": 0.4867430329322815, "lr": 0.0002776716031628058, "grad_norm": 0.09098409116268158, "tokens": 355802, "tok_per_s": 134.51639335211573, "t": 2645.62}49{"step": 2200, "loss": 0.34427204728126526, "lr": 0.00025867617184817756, "grad_norm": 0.1846030056476593, "tokens": 363932, "tok_per_s": 135.62400655190388, "t": 2683.97}50{"step": 2250, "loss": 0.30324769020080566, "lr": 0.00024053524351595949, "grad_norm": 0.1642894744873047, "tokens": 372235, "tok_per_s": 136.8552093987072, "t": 2720.5}51{"step": 2300, "loss": 0.3728746175765991, "lr": 0.0002233020286345913, "grad_norm": 0.12141154706478119, "tokens": 380617, "tok_per_s": 138.07301184133183, "t": 2757.21}52{"step": 2350, "loss": 0.3504433035850525, "lr": 0.00020702707519256364, "grad_norm": 0.1990635097026825, "tokens": 388820, "tok_per_s": 139.51268552063794, "t": 2787.57}53{"step": 2400, "loss": 0.3718884587287903, "lr": 0.00019175812043246033, "grad_norm": 0.24506865441799164, "tokens": 397013, "tok_per_s": 141.3620994601803, "t": 2809.06}54{"step": 2450, "loss": 0.41120845079421997, "lr": 0.00017753995082939931, "grad_norm": 0.24014084041118622, "tokens": 405444, "tok_per_s": 143.22846294662097, "t": 2831.33}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4535177737518506, "val_loss_b2": 0.4499597431933016, "val_loss_b4": 0.4489762422308774, "val_loss_b8": 0.4580538915612534, "t": 2857.41}56{"step": 2500, "loss": 0.46159517765045166, "lr": 0.00016441427072458494, "grad_norm": 0.21556061506271362, "tokens": 413920, "tok_per_s": 144.86615291744934, "t": 2857.84}57{"step": 2550, "loss": 0.3261321485042572, "lr": 0.0001524195799992897, "grad_norm": 0.15561074018478394, "tokens": 422230, "tok_per_s": 146.6387278742791, "t": 2879.97}58{"step": 2600, "loss": 0.4107820689678192, "lr": 0.0001415910611480694, "grad_norm": 0.1327059119939804, "tokens": 430404, "tok_per_s": 148.3539884702053, "t": 2901.77}59{"step": 2650, "loss": 0.3894215524196625, "lr": 0.00013196047608244387, "grad_norm": 0.20400525629520416, "tokens": 438498, "tok_per_s": 149.99253023327094, "t": 2924.04}60{"step": 2700, "loss": 0.33403095602989197, "lr": 0.00012355607296773896, "grad_norm": 0.13920696079730988, "tokens": 446658, "tok_per_s": 151.64974404152466, "t": 2945.9}61{"step": 2750, "loss": 0.34938904643058777, "lr": 0.00011640250336634969, "grad_norm": 0.1591184437274933, "tokens": 455155, "tok_per_s": 153.3470975772089, "t": 2968.71}62{"step": 2800, "loss": 0.43081972002983093, "lr": 0.00011052074993046101, "grad_norm": 0.20634661614894867, "tokens": 463083, "tok_per_s": 154.8619655071733, "t": 2990.87}63{"step": 2850, "loss": 0.37509167194366455, "lr": 0.00010592806485631325, "grad_norm": 0.18761345744132996, "tokens": 471665, "tok_per_s": 156.65087547460473, "t": 3011.51}64{"step": 2900, "loss": 0.4324471354484558, "lr": 0.00010263791928053818, "grad_norm": 0.18597878515720367, "tokens": 480193, "tok_per_s": 158.38796927295223, "t": 3032.33}65{"step": 2950, "loss": 0.3264772295951843, "lr": 0.0001006599637669943, "grad_norm": 0.21078287065029144, "tokens": 488284, "tok_per_s": 159.94192392254993, "t": 3053.46}66{"step": 2999, "loss": 0.4364827573299408, "lr": 0.0001000002640500325, "grad_norm": 0.2555046081542969, "tokens": 496298, "tok_per_s": 161.47019527969405, "t": 3074.2}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45305735727670216, "val_loss_b2": 0.4493508374179861, "val_loss_b4": 0.44867408210976245, "val_loss_b8": 0.45768629593940835, "t": 3078.78}68{"step": 2999, "checkpoint_sha256": "be647104dbbe6787efe407cab018fcfe59d716f23226a10ba6bd920d0e4afa1e", "t": 3078.82}69
Files · main
Menu

Theme