SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 6.126169204711914, "lr": 1e-05, "grad_norm": 22.459897994995117, "tokens": 8192, "tok_per_s": 19159.570081847007, "t": 1.2}2{"step": 20, "loss": 4.8716816902160645, "lr": 0.00021, "grad_norm": 3.611126661300659, "tokens": 172032, "tok_per_s": 21031.514071206133, "t": 8.95}3{"step": 40, "loss": 4.72945499420166, "lr": 0.00041, "grad_norm": 1.8112001419067383, "tokens": 335872, "tok_per_s": 21060.599843687287, "t": 16.72}4{"step": 60, "loss": 4.318785190582275, "lr": 0.00061, "grad_norm": 1.518459439277649, "tokens": 499712, "tok_per_s": 21072.455565997894, "t": 24.48}5{"step": 80, "loss": 4.133788585662842, "lr": 0.0008100000000000001, "grad_norm": 1.3122013807296753, "tokens": 663552, "tok_per_s": 21078.024613709178, "t": 32.25}6{"step": 100, "loss": 3.8849146366119385, "lr": 0.001, "grad_norm": 1.1216819286346436, "tokens": 827392, "tok_per_s": 21083.597835674766, "t": 40.01}7{"step": 120, "loss": 4.074357032775879, "lr": 0.000999894384108318, "grad_norm": 0.8756412267684937, "tokens": 991232, "tok_per_s": 21084.689673281333, "t": 47.78}8{"step": 140, "loss": 3.9606566429138184, "lr": 0.0009995775860097895, "grad_norm": 0.8356199860572815, "tokens": 1155072, "tok_per_s": 21086.45124730354, "t": 55.55}9{"step": 160, "loss": 4.0986528396606445, "lr": 0.000999049754410698, "grad_norm": 0.8302110433578491, "tokens": 1318912, "tok_per_s": 21089.4473782742, "t": 63.31}10{"step": 180, "loss": 4.090394020080566, "lr": 0.0009983111370772877, "grad_norm": 0.7752633690834045, "tokens": 1482752, "tok_per_s": 21091.795490383807, "t": 71.07}11{"step": 200, "loss": 3.8404526710510254, "lr": 0.0009973620807194618, "grad_norm": 0.5948396325111389, "tokens": 1646592, "tok_per_s": 21097.229656773066, "t": 78.82}12{"step": 220, "loss": 3.940852165222168, "lr": 0.0009962030308280363, "grad_norm": 0.6501525640487671, "tokens": 1810432, "tok_per_s": 21102.915381104813, "t": 86.56}13{"step": 240, "loss": 3.7750067710876465, "lr": 0.0009948345314656232, "grad_norm": 0.5302097201347351, "tokens": 1974272, "tok_per_s": 21107.126686139054, "t": 94.3}14{"step": 260, "loss": 3.697026014328003, "lr": 0.0009932572250112468, "grad_norm": 0.5430718660354614, "tokens": 2138112, "tok_per_s": 21107.188627904445, "t": 102.07}15{"step": 280, "loss": 3.739744186401367, "lr": 0.0009914718518588075, "grad_norm": 0.4621249735355377, "tokens": 2301952, "tok_per_s": 21106.59567666816, "t": 109.83}16{"step": 300, "loss": 4.02414608001709, "lr": 0.000989479250069539, "grad_norm": 0.4370909631252289, "tokens": 2465792, "tok_per_s": 21107.680000868284, "t": 117.59}17{"step": 320, "loss": 3.8102855682373047, "lr": 0.0009872803549786176, "grad_norm": 0.4399644434452057, "tokens": 2629632, "tok_per_s": 21111.876180248946, "t": 125.32}18{"step": 340, "loss": 3.832735538482666, "lr": 0.0009848761987561131, "grad_norm": 0.4151759445667267, "tokens": 2793472, "tok_per_s": 21110.95184738199, "t": 133.09}19{"step": 360, "loss": 3.626600980758667, "lr": 0.0009822679099224844, "grad_norm": 0.364500492811203, "tokens": 2957312, "tok_per_s": 21111.71261074574, "t": 140.85}20{"step": 380, "loss": 3.8548686504364014, "lr": 0.0009794567128188466, "grad_norm": 0.37897947430610657, "tokens": 3121152, "tok_per_s": 21112.906199626756, "t": 148.6}21{"step": 400, "loss": 3.727853775024414, "lr": 0.0009764439270322612, "grad_norm": 0.3435725271701813, "tokens": 3284992, "tok_per_s": 21115.922471332877, "t": 156.34}22{"step": 420, "loss": 3.829807996749878, "lr": 0.0009732309667763159, "grad_norm": 0.36790931224823, "tokens": 3448832, "tok_per_s": 21116.75817582348, "t": 164.09}23{"step": 440, "loss": 3.852527141571045, "lr": 0.0009698193402272879, "grad_norm": 0.3527315557003021, "tokens": 3612672, "tok_per_s": 21117.78130748966, "t": 171.84}24{"step": 460, "loss": 3.7055013179779053, "lr": 0.0009662106488162, "grad_norm": 0.37226602435112, "tokens": 3776512, "tok_per_s": 21120.383078309766, "t": 179.58}25{"step": 480, "loss": 3.6937286853790283, "lr": 0.0009624065864771017, "grad_norm": 0.3175200819969177, "tokens": 3940352, "tok_per_s": 21121.463581065476, "t": 187.32}26{"step": 499, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9894694805145265, "val_loss_b2": 3.992402124404907, "val_loss_b4": 4.003933787345886, "val_loss_b8": 4.049389839172363, "t": 206.19}27{"step": 500, "loss": 3.59987473487854, "lr": 0.0009584089388519307, "grad_norm": 0.33032384514808655, "tokens": 4104192, "tok_per_s": 19941.8637209553, "t": 206.58}28{"step": 520, "loss": 3.750821113586426, "lr": 0.0009542195824523249, "grad_norm": 0.3064441382884979, "tokens": 4268032, "tok_per_s": 19984.898122075596, "t": 214.33}29{"step": 540, "loss": 3.692033290863037, "lr": 0.0009498404837787811, "grad_norm": 0.320122629404068, "tokens": 4431872, "tok_per_s": 20026.113684464894, "t": 222.07}30{"step": 560, "loss": 3.8850107192993164, "lr": 0.0009452736983975708, "grad_norm": 0.3112269937992096, "tokens": 4595712, "tok_per_s": 20063.686484753223, "t": 229.82}31{"step": 580, "loss": 3.8188445568084717, "lr": 0.0009405213699758506, "grad_norm": 0.28276461362838745, "tokens": 4759552, "tok_per_s": 20099.4307069932, "t": 237.57}32{"step": 600, "loss": 3.8345580101013184, "lr": 0.0009355857292754152, "grad_norm": 0.28096383810043335, "tokens": 4923392, "tok_per_s": 20132.815964205005, "t": 245.31}33{"step": 620, "loss": 3.7093982696533203, "lr": 0.0009304690931055693, "grad_norm": 0.2515045702457428, "tokens": 5087232, "tok_per_s": 20164.545090887987, "t": 253.05}34{"step": 640, "loss": 3.8132317066192627, "lr": 0.0009251738632356086, "grad_norm": 0.27688807249069214, "tokens": 5251072, "tok_per_s": 20194.140991766715, "t": 260.8}35{"step": 660, "loss": 3.791135311126709, "lr": 0.0009197025252674192, "grad_norm": 0.27515342831611633, "tokens": 5414912, "tok_per_s": 20221.427005550144, "t": 268.55}36{"step": 680, "loss": 3.9602394104003906, "lr": 0.0009140576474687263, "grad_norm": 0.27827608585357666, "tokens": 5578752, "tok_per_s": 20245.936262055464, "t": 276.32}37{"step": 700, "loss": 3.7879137992858887, "lr": 0.0009082418795675396, "grad_norm": 0.23957505822181702, "tokens": 5742592, "tok_per_s": 20270.117248495346, "t": 284.07}38{"step": 720, "loss": 3.8342854976654053, "lr": 0.0009022579515083601, "grad_norm": 0.2529521882534027, "tokens": 5906432, "tok_per_s": 20293.09161556465, "t": 291.82}39{"step": 740, "loss": 3.789114475250244, "lr": 0.000896108672170733, "grad_norm": 0.2292860746383667, "tokens": 6070272, "tok_per_s": 20315.594895864164, "t": 299.57}40{"step": 760, "loss": 3.81569766998291, "lr": 0.0008897969280507493, "grad_norm": 0.24284496903419495, "tokens": 6234112, "tok_per_s": 20335.97964834195, "t": 307.32}41{"step": 780, "loss": 3.835716962814331, "lr": 0.0008833256819061126, "grad_norm": 0.22712063789367676, "tokens": 6397952, "tok_per_s": 20356.10289072659, "t": 315.07}42{"step": 800, "loss": 3.71336030960083, "lr": 0.0008766979713654089, "grad_norm": 0.24536189436912537, "tokens": 6561792, "tok_per_s": 20375.05429210699, "t": 322.82}43{"step": 820, "loss": 3.941588878631592, "lr": 0.0008699169075022318, "grad_norm": 0.22303837537765503, "tokens": 6725632, "tok_per_s": 20393.359958812696, "t": 330.56}44{"step": 840, "loss": 3.8339693546295166, "lr": 0.0008629856733748324, "grad_norm": 0.2281208485364914, "tokens": 6889472, "tok_per_s": 20411.04778506067, "t": 338.3}45{"step": 860, "loss": 3.8048322200775146, "lr": 0.0008559075225319786, "grad_norm": 0.2118220180273056, "tokens": 7053312, "tok_per_s": 20428.346432708793, "t": 346.04}46{"step": 880, "loss": 3.687807083129883, "lr": 0.000848685777485727, "grad_norm": 0.268770307302475, "tokens": 7217152, "tok_per_s": 20445.11248641459, "t": 353.77}47{"step": 900, "loss": 3.7973411083221436, "lr": 0.0008413238281518224, "grad_norm": 0.22056519985198975, "tokens": 7380992, "tok_per_s": 20459.598584371703, "t": 361.53}48{"step": 920, "loss": 3.708625316619873, "lr": 0.0008338251302584579, "grad_norm": 0.2216741442680359, "tokens": 7544832, "tok_per_s": 20473.749172788648, "t": 369.28}49{"step": 940, "loss": 3.837420701980591, "lr": 0.0008261932037241419, "grad_norm": 0.20800068974494934, "tokens": 7708672, "tok_per_s": 20487.340607417882, "t": 377.03}50{"step": 960, "loss": 3.770883083343506, "lr": 0.0008184316310054355, "grad_norm": 0.21802109479904175, "tokens": 7872512, "tok_per_s": 20500.81824575616, "t": 384.78}51{"step": 980, "loss": 3.816431999206543, "lr": 0.0008105440554153319, "grad_norm": 0.20279525220394135, "tokens": 8036352, "tok_per_s": 20513.690712858683, "t": 392.52}52{"step": 999, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9885369539260864, "val_loss_b2": 3.989286947250366, "val_loss_b4": 3.992767333984375, "val_loss_b8": 4.006371879577637, "t": 411.34}53{"step": 999, "checkpoint_sha256": "7f0da8009526d8fc08ea71b774f9caa4c9f2ec2d108b88ef56d61c857df4fff9", "t": 411.58}54{"step": 1000, "loss": 3.750763416290283, "lr": 0.000802534179413072, "grad_norm": 0.22864268720149994, "tokens": 8200192, "tok_per_s": 19942.16324513874, "t": 411.97}55{"step": 1020, "loss": 3.6501269340515137, "lr": 0.0007944057628661947, "grad_norm": 0.19888758659362793, "tokens": 8364032, "tok_per_s": 19964.14959768776, "t": 419.72}56{"step": 1040, "loss": 3.8121538162231445, "lr": 0.0007861626212856403, "grad_norm": 0.2171272486448288, "tokens": 8527872, "tok_per_s": 19985.43263588043, "t": 427.47}57{"step": 1060, "loss": 3.9051833152770996, "lr": 0.0007778086240347343, "grad_norm": 0.19203534722328186, "tokens": 8691712, "tok_per_s": 20006.31730570062, "t": 435.22}58{"step": 1080, "loss": 3.717747688293457, "lr": 0.0007693476925128937, "grad_norm": 0.1844388097524643, "tokens": 8855552, "tok_per_s": 20026.471421672482, "t": 442.96}59{"step": 1100, "loss": 3.8869900703430176, "lr": 0.0007607837983149056, "grad_norm": 0.19374239444732666, "tokens": 9019392, "tok_per_s": 20045.912058185117, "t": 450.7}60{"step": 1120, "loss": 3.863908290863037, "lr": 0.0007521209613666457, "grad_norm": 0.1999870389699936, "tokens": 9183232, "tok_per_s": 20063.995210986654, "t": 458.46}61{"step": 1140, "loss": 3.8573102951049805, "lr": 0.0007433632480381083, "grad_norm": 0.20228514075279236, "tokens": 9347072, "tok_per_s": 20082.348172526035, "t": 466.21}62{"step": 1160, "loss": 3.68766450881958, "lr": 0.0007345147692346373, "grad_norm": 0.20986148715019226, "tokens": 9510912, "tok_per_s": 20099.842512632164, "t": 473.95}63{"step": 1180, "loss": 3.784796953201294, "lr": 0.0007255796784672496, "grad_norm": 0.17604109644889832, "tokens": 9674752, "tok_per_s": 20116.630759310498, "t": 481.7}64{"step": 1200, "loss": 3.745537281036377, "lr": 0.0007165621699029615, "grad_norm": 0.17398570477962494, "tokens": 9838592, "tok_per_s": 20132.826175762733, "t": 489.45}65{"step": 1220, "loss": 3.6806092262268066, "lr": 0.0007074664763960298, "grad_norm": 0.18960657715797424, "tokens": 10002432, "tok_per_s": 20148.635471384598, "t": 497.2}66{"step": 1240, "loss": 3.8601021766662598, "lr": 0.0006982968675010332, "grad_norm": 0.18283644318580627, "tokens": 10166272, "tok_per_s": 20163.897834505216, "t": 504.95}67{"step": 1260, "loss": 3.815518379211426, "lr": 0.0006890576474687264, "grad_norm": 0.19706735014915466, "tokens": 10330112, "tok_per_s": 20178.700048080373, "t": 512.7}68{"step": 1280, "loss": 3.8219187259674072, "lr": 0.0006797531532256079, "grad_norm": 0.17206616699695587, "tokens": 10493952, "tok_per_s": 20193.23949113737, "t": 520.44}69{"step": 1300, "loss": 3.886626720428467, "lr": 0.0006703877523381495, "grad_norm": 0.1895555555820465, "tokens": 10657792, "tok_per_s": 20206.81607817688, "t": 528.2}70{"step": 1320, "loss": 3.783961057662964, "lr": 0.000660965840962643, "grad_norm": 0.1719844788312912, "tokens": 10821632, "tok_per_s": 20220.507792118013, "t": 535.95}71{"step": 1340, "loss": 3.9477076530456543, "lr": 0.0006514918417816275, "grad_norm": 0.1903124451637268, "tokens": 10985472, "tok_per_s": 20232.891667326534, "t": 543.72}72{"step": 1360, "loss": 3.812472343444824, "lr": 0.0006419702019278642, "grad_norm": 0.1686677634716034, "tokens": 11149312, "tok_per_s": 20244.79608284485, "t": 551.49}73{"step": 1380, "loss": 3.834444522857666, "lr": 0.0006324053908968352, "grad_norm": 0.1864556223154068, "tokens": 11313152, "tok_per_s": 20257.516328201422, "t": 559.23}74{"step": 1400, "loss": 3.872220039367676, "lr": 0.0006228018984487442, "grad_norm": 0.17829525470733643, "tokens": 11476992, "tok_per_s": 20270.50927715957, "t": 566.96}75{"step": 1420, "loss": 3.999208927154541, "lr": 0.0006131642325010049, "grad_norm": 0.17192476987838745, "tokens": 11640832, "tok_per_s": 20283.015449002134, "t": 574.69}76{"step": 1440, "loss": 3.853477954864502, "lr": 0.0006034969170122078, "grad_norm": 0.16637860238552094, "tokens": 11804672, "tok_per_s": 20295.355537634325, "t": 582.41}77{"step": 1460, "loss": 3.898850679397583, "lr": 0.0005938044898585555, "grad_norm": 0.1983206421136856, "tokens": 11968512, "tok_per_s": 20306.80967133359, "t": 590.15}78{"step": 1480, "loss": 3.632338047027588, "lr": 0.0005840915007037648, "grad_norm": 0.19351805746555328, "tokens": 12132352, "tok_per_s": 20318.415572608643, "t": 597.88}79{"step": 1499, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9883332014083863, "val_loss_b2": 3.9885011672973634, "val_loss_b4": 3.990019416809082, "val_loss_b8": 3.996551442146301, "t": 616.67}80{"step": 1500, "loss": 3.9075660705566406, "lr": 0.000574362508863438, "grad_norm": 0.1780702769756317, "tokens": 12296192, "tok_per_s": 19951.941952929767, "t": 617.06}81{"step": 1520, "loss": 3.7346367835998535, "lr": 0.0005646220811649013, "grad_norm": 0.16623790562152863, "tokens": 12460032, "tok_per_s": 19967.410669554505, "t": 624.79}82{"step": 1540, "loss": 3.715179920196533, "lr": 0.0005548747898035181, "grad_norm": 0.16164474189281464, "tokens": 12623872, "tok_per_s": 19982.723124173135, "t": 632.51}83{"step": 1560, "loss": 3.7581560611724854, "lr": 0.0005451252101964821, "grad_norm": 0.1829266995191574, "tokens": 12787712, "tok_per_s": 19997.50810251118, "t": 640.23}84{"step": 1580, "loss": 3.7185606956481934, "lr": 0.0005353779188350989, "grad_norm": 0.1619238555431366, "tokens": 12951552, "tok_per_s": 20011.831404432392, "t": 647.96}85{"step": 1600, "loss": 4.002614974975586, "lr": 0.0005256374911365621, "grad_norm": 0.1767655909061432, "tokens": 13115392, "tok_per_s": 20025.77092212467, "t": 655.69}86{"step": 1620, "loss": 3.76900577545166, "lr": 0.0005159084992962354, "grad_norm": 0.17787884175777435, "tokens": 13279232, "tok_per_s": 20039.422995251905, "t": 663.42}87{"step": 1640, "loss": 3.7815041542053223, "lr": 0.0005061955101414447, "grad_norm": 0.18058991432189941, "tokens": 13443072, "tok_per_s": 20052.714088790024, "t": 671.15}88{"step": 1660, "loss": 3.8960037231445312, "lr": 0.0004965030829877921, "grad_norm": 0.18848209083080292, "tokens": 13606912, "tok_per_s": 20066.03770949369, "t": 678.87}89{"step": 1680, "loss": 3.734178066253662, "lr": 0.00048683576749899505, "grad_norm": 0.15351198613643646, "tokens": 13770752, "tok_per_s": 20078.81570631483, "t": 686.6}90{"step": 1700, "loss": 3.5477917194366455, "lr": 0.00047719810155125587, "grad_norm": 0.16984161734580994, "tokens": 13934592, "tok_per_s": 20091.46403735785, "t": 694.33}91{"step": 1720, "loss": 3.770994186401367, "lr": 0.00046759460910316477, "grad_norm": 0.15741173923015594, "tokens": 14098432, "tok_per_s": 20103.675663226775, "t": 702.05}92{"step": 1740, "loss": 3.8800048828125, "lr": 0.00045802979807213587, "grad_norm": 0.16288399696350098, "tokens": 14262272, "tok_per_s": 20115.74082326937, "t": 709.78}93{"step": 1760, "loss": 3.5981998443603516, "lr": 0.00044850815821837267, "grad_norm": 0.15490977466106415, "tokens": 14426112, "tok_per_s": 20127.345534971482, "t": 717.51}94{"step": 1780, "loss": 3.8376967906951904, "lr": 0.0004390341590373572, "grad_norm": 0.17385722696781158, "tokens": 14589952, "tok_per_s": 20139.07010963785, "t": 725.23}95{"step": 1800, "loss": 3.757993221282959, "lr": 0.0004296122476618507, "grad_norm": 0.1688479632139206, "tokens": 14753792, "tok_per_s": 20150.19294815362, "t": 732.96}96{"step": 1820, "loss": 3.9143409729003906, "lr": 0.0004202468467743922, "grad_norm": 0.16462662816047668, "tokens": 14917632, "tok_per_s": 20161.211903966334, "t": 740.69}97{"step": 1840, "loss": 3.816563367843628, "lr": 0.0004109423525312738, "grad_norm": 0.16830846667289734, "tokens": 15081472, "tok_per_s": 20172.10910736733, "t": 748.41}98{"step": 1860, "loss": 3.7594363689422607, "lr": 0.00040170313249896693, "grad_norm": 0.16261203587055206, "tokens": 15245312, "tok_per_s": 20182.289434668623, "t": 756.15}99{"step": 1880, "loss": 3.7165236473083496, "lr": 0.0003925335236039702, "grad_norm": 0.18339066207408905, "tokens": 15409152, "tok_per_s": 20192.203796447877, "t": 763.89}100{"step": 1900, "loss": 3.732370376586914, "lr": 0.00038343783009703845, "grad_norm": 0.1566825807094574, "tokens": 15572992, "tok_per_s": 20202.162116519117, "t": 771.63}101{"step": 1920, "loss": 3.911724090576172, "lr": 0.0003744203215327505, "grad_norm": 0.17064091563224792, "tokens": 15736832, "tok_per_s": 20212.287594807913, "t": 779.35}102{"step": 1940, "loss": 3.6301357746124268, "lr": 0.0003654852307653628, "grad_norm": 0.1638231873512268, "tokens": 15900672, "tok_per_s": 20222.147256168635, "t": 787.07}103{"step": 1960, "loss": 4.000123023986816, "lr": 0.0003566367519618918, "grad_norm": 0.1858472377061844, "tokens": 16064512, "tok_per_s": 20231.75492530863, "t": 794.79}104{"step": 1980, "loss": 3.5589189529418945, "lr": 0.0003478790386333546, "grad_norm": 0.1453864425420761, "tokens": 16228352, "tok_per_s": 20241.34148686865, "t": 802.51}105{"step": 1999, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9877698183059693, "val_loss_b2": 3.987339735031128, "val_loss_b4": 3.987492895126343, "val_loss_b8": 3.9896637201309204, "t": 821.29}106{"step": 1999, "checkpoint_sha256": "a5609e74906c926e4347f3843e780d19ed543bf2fa0b24649102ec04268eefea", "t": 821.52}107{"step": 2000, "loss": 3.813103199005127, "lr": 0.0003392162016850945, "grad_norm": 0.16317197680473328, "tokens": 16392192, "tok_per_s": 19962.62147589013, "t": 821.91}108{"step": 2020, "loss": 3.7536630630493164, "lr": 0.00033065230748710643, "grad_norm": 0.15909479558467865, "tokens": 16556032, "tok_per_s": 19974.10202884544, "t": 829.64}109{"step": 2040, "loss": 3.844332456588745, "lr": 0.0003221913759652657, "grad_norm": 0.15411806106567383, "tokens": 16719872, "tok_per_s": 19985.69561080414, "t": 837.36}110{"step": 2060, "loss": 3.74894380569458, "lr": 0.0003138373787143598, "grad_norm": 0.16718031466007233, "tokens": 16883712, "tok_per_s": 19997.104726857455, "t": 845.08}111{"step": 2080, "loss": 3.8611268997192383, "lr": 0.0003055942371338052, "grad_norm": 0.17034530639648438, "tokens": 17047552, "tok_per_s": 20008.05704884555, "t": 852.8}112{"step": 2100, "loss": 3.765115976333618, "lr": 0.000297465820586928, "grad_norm": 0.15159408748149872, "tokens": 17211392, "tok_per_s": 20018.53073344119, "t": 860.54}113{"step": 2120, "loss": 4.089189052581787, "lr": 0.0002894559445846682, "grad_norm": 0.17298366129398346, "tokens": 17375232, "tok_per_s": 20029.18926831579, "t": 868.26}114{"step": 2140, "loss": 3.836331367492676, "lr": 0.0002815683689945647, "grad_norm": 0.1622205674648285, "tokens": 17539072, "tok_per_s": 20039.805342049553, "t": 875.98}115{"step": 2160, "loss": 3.9095306396484375, "lr": 0.00027380679627585816, "grad_norm": 0.158914253115654, "tokens": 17702912, "tok_per_s": 20050.105580576193, "t": 883.7}116{"step": 2180, "loss": 3.73299503326416, "lr": 0.0002661748697415423, "grad_norm": 0.15621504187583923, "tokens": 17866752, "tok_per_s": 20060.090250933445, "t": 891.43}117{"step": 2200, "loss": 3.837934732437134, "lr": 0.00025867617184817756, "grad_norm": 0.1473250389099121, "tokens": 18030592, "tok_per_s": 20070.085446889883, "t": 899.15}118{"step": 2220, "loss": 4.005699157714844, "lr": 0.00025131422251427305, "grad_norm": 0.15512457489967346, "tokens": 18194432, "tok_per_s": 20080.106930567712, "t": 906.86}119{"step": 2240, "loss": 3.845271348953247, "lr": 0.00024409247746802145, "grad_norm": 0.15060970187187195, "tokens": 18358272, "tok_per_s": 20089.6081075339, "t": 914.59}120{"step": 2260, "loss": 3.7056186199188232, "lr": 0.00023701432662516769, "grad_norm": 0.15680763125419617, "tokens": 18522112, "tok_per_s": 20099.200318026535, "t": 922.3}121{"step": 2280, "loss": 3.559237480163574, "lr": 0.0002300830924977683, "grad_norm": 0.15065070986747742, "tokens": 18685952, "tok_per_s": 20108.6692028769, "t": 930.02}122{"step": 2300, "loss": 3.9159555435180664, "lr": 0.0002233020286345913, "grad_norm": 0.16651766002178192, "tokens": 18849792, "tok_per_s": 20118.047411714015, "t": 937.73}123{"step": 2320, "loss": 3.7802019119262695, "lr": 0.00021667431809388747, "grad_norm": 0.14918780326843262, "tokens": 19013632, "tok_per_s": 20126.91752437407, "t": 945.45}124{"step": 2340, "loss": 3.8701388835906982, "lr": 0.00021020307194925082, "grad_norm": 0.15167640149593353, "tokens": 19177472, "tok_per_s": 20135.77269069399, "t": 953.18}125{"step": 2360, "loss": 3.5380337238311768, "lr": 0.000203891327829267, "grad_norm": 0.15401595830917358, "tokens": 19341312, "tok_per_s": 20144.54729953582, "t": 960.89}126{"step": 2380, "loss": 3.8055543899536133, "lr": 0.00019774204849164, "grad_norm": 0.1612010896205902, "tokens": 19505152, "tok_per_s": 20153.22975054963, "t": 968.61}127{"step": 2400, "loss": 3.9584109783172607, "lr": 0.00019175812043246033, "grad_norm": 0.1553308665752411, "tokens": 19668992, "tok_per_s": 20162.054064397944, "t": 976.31}128{"step": 2420, "loss": 3.797402858734131, "lr": 0.00018594235253127373, "grad_norm": 0.16736063361167908, "tokens": 19832832, "tok_per_s": 20170.986979957466, "t": 984.0}129{"step": 2440, "loss": 3.837085008621216, "lr": 0.0001802974747325809, "grad_norm": 0.1564146727323532, "tokens": 19996672, "tok_per_s": 20179.819480041282, "t": 991.69}130{"step": 2460, "loss": 3.830759286880493, "lr": 0.00017482613676439153, "grad_norm": 0.14325658977031708, "tokens": 20160512, "tok_per_s": 20188.54421671684, "t": 999.38}131{"step": 2480, "loss": 3.7485439777374268, "lr": 0.00016953090689443074, "grad_norm": 0.16542506217956543, "tokens": 20324352, "tok_per_s": 20196.81763779774, "t": 1007.08}132{"step": 2499, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.987573432922363, "val_loss_b2": 3.986850929260254, "val_loss_b4": 3.986389660835266, "val_loss_b8": 3.987432909011841, "t": 1025.83}133{"step": 2500, "loss": 3.910710334777832, "lr": 0.00016441427072458494, "grad_norm": 0.1484222412109375, "tokens": 20488192, "tok_per_s": 19979.773240637853, "t": 1026.21}134{"step": 2520, "loss": 3.9365949630737305, "lr": 0.00015947863002414937, "grad_norm": 0.15480661392211914, "tokens": 20652032, "tok_per_s": 19988.896213363285, "t": 1033.94}135{"step": 2540, "loss": 3.7896642684936523, "lr": 0.0001547263016024292, "grad_norm": 0.15083913505077362, "tokens": 20815872, "tok_per_s": 19997.90520478423, "t": 1041.67}136{"step": 2560, "loss": 3.7249796390533447, "lr": 0.00015015951622121895, "grad_norm": 0.14854873716831207, "tokens": 20979712, "tok_per_s": 20006.874948560082, "t": 1049.39}137{"step": 2580, "loss": 3.731898784637451, "lr": 0.0001457804175476751, "grad_norm": 0.14294327795505524, "tokens": 21143552, "tok_per_s": 20015.621567101072, "t": 1057.12}138{"step": 2600, "loss": 3.9330503940582275, "lr": 0.0001415910611480694, "grad_norm": 0.1628326028585434, "tokens": 21307392, "tok_per_s": 20024.545766005245, "t": 1064.83}139{"step": 2620, "loss": 3.8897671699523926, "lr": 0.0001375934135228983, "grad_norm": 0.1529216319322586, "tokens": 21471232, "tok_per_s": 20033.144620677278, "t": 1072.55}140{"step": 2640, "loss": 3.7286152839660645, "lr": 0.00013378935118380005, "grad_norm": 0.15187598764896393, "tokens": 21635072, "tok_per_s": 20041.69349541672, "t": 1080.27}141{"step": 2660, "loss": 3.6857709884643555, "lr": 0.00013018065977271216, "grad_norm": 0.1457250565290451, "tokens": 21798912, "tok_per_s": 20050.199914044973, "t": 1087.98}142{"step": 2680, "loss": 3.5857090950012207, "lr": 0.0001267690332236842, "grad_norm": 0.140897735953331, "tokens": 21962752, "tok_per_s": 20058.51634510263, "t": 1095.7}143{"step": 2700, "loss": 3.851405143737793, "lr": 0.00012355607296773896, "grad_norm": 0.16423779726028442, "tokens": 22126592, "tok_per_s": 20066.741382681077, "t": 1103.42}144{"step": 2720, "loss": 3.874582052230835, "lr": 0.00012054328718115336, "grad_norm": 0.14421683549880981, "tokens": 22290432, "tok_per_s": 20075.062259683444, "t": 1111.12}145{"step": 2740, "loss": 3.5842206478118896, "lr": 0.00011773209007751561, "grad_norm": 0.14662709832191467, "tokens": 22454272, "tok_per_s": 20082.858018918985, "t": 1118.85}146{"step": 2760, "loss": 3.761885166168213, "lr": 0.00011512380124388696, "grad_norm": 0.15166927874088287, "tokens": 22618112, "tok_per_s": 20090.55053695252, "t": 1126.58}147{"step": 2780, "loss": 3.7198662757873535, "lr": 0.0001127196450213825, "grad_norm": 0.17583592236042023, "tokens": 22781952, "tok_per_s": 20098.3898454846, "t": 1134.29}148{"step": 2800, "loss": 3.8337318897247314, "lr": 0.00011052074993046101, "grad_norm": 0.15117432177066803, "tokens": 22945792, "tok_per_s": 20106.200994193674, "t": 1142.0}149{"step": 2820, "loss": 3.7311487197875977, "lr": 0.00010852814814119239, "grad_norm": 0.13563314080238342, "tokens": 23109632, "tok_per_s": 20113.668546192555, "t": 1149.72}150{"step": 2840, "loss": 3.7886385917663574, "lr": 0.00010674277498875323, "grad_norm": 0.16122478246688843, "tokens": 23273472, "tok_per_s": 20121.092874871665, "t": 1157.44}151{"step": 2860, "loss": 3.8388917446136475, "lr": 0.00010516546853437686, "grad_norm": 0.15907351672649384, "tokens": 23437312, "tok_per_s": 20128.26115559017, "t": 1165.17}152{"step": 2880, "loss": 3.8185627460479736, "lr": 0.00010379696917196379, "grad_norm": 0.1412941813468933, "tokens": 23601152, "tok_per_s": 20135.368216714098, "t": 1172.89}153{"step": 2900, "loss": 3.7403621673583984, "lr": 0.00010263791928053818, "grad_norm": 0.15521971881389618, "tokens": 23764992, "tok_per_s": 20142.611721962156, "t": 1180.6}154{"step": 2920, "loss": 3.754521131515503, "lr": 0.00010168886292271246, "grad_norm": 0.15074467658996582, "tokens": 23928832, "tok_per_s": 20149.640351873582, "t": 1188.32}155{"step": 2940, "loss": 3.79710054397583, "lr": 0.00010095024558930203, "grad_norm": 0.14874565601348877, "tokens": 24092672, "tok_per_s": 20156.65187130967, "t": 1196.04}156{"step": 2960, "loss": 3.6774227619171143, "lr": 0.00010042241399021049, "grad_norm": 0.1491830050945282, "tokens": 24256512, "tok_per_s": 20163.274440417656, "t": 1203.77}157{"step": 2980, "loss": 3.8444924354553223, "lr": 0.00010010561589168215, "grad_norm": 0.14975227415561676, "tokens": 24420352, "tok_per_s": 20169.829268250734, "t": 1211.5}158{"step": 2999, "loss": 3.670819044113159, "lr": 0.0001000002640500325, "grad_norm": 0.14213569462299347, "tokens": 24576000, "tok_per_s": 20176.07306916722, "t": 1218.84}159{"step": 2999, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.987425208091736, "val_loss_b2": 3.986540651321411, "val_loss_b4": 3.985757327079773, "val_loss_b8": 3.986104154586792, "t": 1230.3}160{"step": 2999, "checkpoint_sha256": "1e3e5cdd103672376ad23bbfaafc50bcc68b937d808fae74308285a54564938a", "t": 1230.52}161
Files · main
Menu

Theme