SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.4461214244365692, "lr": 1e-05, "grad_norm": 0.09516235440969467, "tokens": 146, "tok_per_s": 241.09636950910496, "t": 1.12}2{"step": 50, "loss": 0.32782331109046936, "lr": 0.00051, "grad_norm": 0.050148751586675644, "tokens": 8382, "tok_per_s": 153.10953396485178, "t": 55.26}3{"step": 100, "loss": 0.4529685080051422, "lr": 0.001, "grad_norm": 0.06715001165866852, "tokens": 16548, "tok_per_s": 151.09942898121116, "t": 110.03}4{"step": 150, "loss": 0.314990371465683, "lr": 0.0009993400362330058, "grad_norm": 0.06396530568599701, "tokens": 24812, "tok_per_s": 151.09040502726734, "t": 164.74}5{"step": 200, "loss": 0.4230530858039856, "lr": 0.0009973620807194618, "grad_norm": 0.0592140257358551, "tokens": 33400, "tok_per_s": 151.99799881788772, "t": 220.26}6{"step": 250, "loss": 0.40603217482566833, "lr": 0.000994071935143687, "grad_norm": 0.09058233350515366, "tokens": 41583, "tok_per_s": 151.7502841980952, "t": 274.54}7{"step": 300, "loss": 0.3490418791770935, "lr": 0.000989479250069539, "grad_norm": 0.048476509749889374, "tokens": 49989, "tok_per_s": 151.430518988372, "t": 330.63}8{"step": 350, "loss": 0.4594109356403351, "lr": 0.0009835974966336503, "grad_norm": 0.06444650143384933, "tokens": 58214, "tok_per_s": 151.08869907713446, "t": 385.82}9{"step": 400, "loss": 0.4108210504055023, "lr": 0.0009764439270322612, "grad_norm": 0.13102994859218597, "tokens": 66391, "tok_per_s": 150.8676207722629, "t": 440.58}10{"step": 450, "loss": 0.299140065908432, "lr": 0.0009680395239175562, "grad_norm": 0.027036255225539207, "tokens": 74699, "tok_per_s": 150.81378545286304, "t": 495.83}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4607674479778322, "val_loss_b2": 0.4593917429300292, "val_loss_b4": 0.45790387375005775, "val_loss_b8": 0.457711939391037, "t": 564.18}12{"step": 500, "loss": 0.5773906707763672, "lr": 0.0009584089388519307, "grad_norm": 0.05966398864984512, "tokens": 83038, "tok_per_s": 147.03352363015463, "t": 565.27}13{"step": 550, "loss": 0.39798715710639954, "lr": 0.0009475804200007103, "grad_norm": 0.02683185786008835, "tokens": 91441, "tok_per_s": 147.63560541192336, "t": 619.89}14{"step": 600, "loss": 0.47835156321525574, "lr": 0.0009355857292754152, "grad_norm": 0.11388559639453888, "tokens": 99553, "tok_per_s": 147.62604774635665, "t": 674.88}15{"step": 650, "loss": 0.41516444087028503, "lr": 0.0009224600491706008, "grad_norm": 0.1538604348897934, "tokens": 107666, "tok_per_s": 147.63241874400677, "t": 729.8}16{"step": 700, "loss": 0.4394778907299042, "lr": 0.0009082418795675396, "grad_norm": 0.04718884453177452, "tokens": 115959, "tok_per_s": 147.92226673291162, "t": 784.44}17{"step": 750, "loss": 0.39850616455078125, "lr": 0.0008929729248074364, "grad_norm": 0.05520658940076828, "tokens": 124302, "tok_per_s": 148.2103043721468, "t": 839.21}18{"step": 800, "loss": 0.4861777424812317, "lr": 0.0008766979713654089, "grad_norm": 0.07380149513483047, "tokens": 132734, "tok_per_s": 148.57754893394056, "t": 893.88}19{"step": 850, "loss": 0.4959874749183655, "lr": 0.0008594647564840406, "grad_norm": 0.07644492387771606, "tokens": 141025, "tok_per_s": 148.81900094259115, "t": 948.14}20{"step": 900, "loss": 0.4589282274246216, "lr": 0.0008413238281518224, "grad_norm": 0.1329474300146103, "tokens": 149035, "tok_per_s": 148.79762014718276, "t": 1002.11}21{"step": 950, "loss": 0.4106466472148895, "lr": 0.0008223283968371944, "grad_norm": 0.1005278080701828, "tokens": 157135, "tok_per_s": 148.8234522988704, "t": 1056.37}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45725937604081635, "val_loss_b2": 0.4541209621814861, "val_loss_b4": 0.4517574817926323, "val_loss_b8": 0.45239582033566267, "t": 1123.72}23{"step": 1000, "loss": 0.4286046624183655, "lr": 0.000802534179413072, "grad_norm": 0.09162841737270355, "tokens": 165602, "tok_per_s": 147.31009743060457, "t": 1124.69}24{"step": 1050, "loss": 0.37365084886550903, "lr": 0.0007819992357296598, "grad_norm": 0.07550956308841705, "tokens": 173674, "tok_per_s": 147.30917708303664, "t": 1179.5}25{"step": 1100, "loss": 0.3745676279067993, "lr": 0.0007607837983149056, "grad_norm": 0.044421058148145676, "tokens": 181834, "tok_per_s": 147.44818843799757, "t": 1233.72}26{"step": 1150, "loss": 0.41067275404930115, "lr": 0.0007389500957021191, "grad_norm": 0.09208662062883377, "tokens": 190158, "tok_per_s": 147.70432714997625, "t": 1287.94}27{"step": 1200, "loss": 0.39671701192855835, "lr": 0.0007165621699029615, "grad_norm": 0.0735398605465889, "tokens": 198573, "tok_per_s": 147.92554552953348, "t": 1342.9}28{"step": 1250, "loss": 0.4679332375526428, "lr": 0.000693685688561191, "grad_norm": 0.09343890845775604, "tokens": 206880, "tok_per_s": 148.1327019956828, "t": 1397.1}29{"step": 1300, "loss": 0.3112703263759613, "lr": 0.0006703877523381495, "grad_norm": 0.10924684256315231, "tokens": 215095, "tok_per_s": 149.38936714740575, "t": 1440.34}30{"step": 1350, "loss": 0.40129825472831726, "lr": 0.0006467366980949609, "grad_norm": 0.11308054625988007, "tokens": 223349, "tok_per_s": 150.5417130108, "t": 1484.15}31{"step": 1400, "loss": 0.4358211159706116, "lr": 0.0006228018984487442, "grad_norm": 0.08415605127811432, "tokens": 231716, "tok_per_s": 151.67399773297623, "t": 1528.24}32{"step": 1450, "loss": 0.5053636431694031, "lr": 0.0005986535582907738, "grad_norm": 0.09213020652532578, "tokens": 239960, "tok_per_s": 153.2733008963444, "t": 1566.09}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45641542080295916, "val_loss_b2": 0.45360596300992784, "val_loss_b4": 0.45242518448018865, "val_loss_b8": 0.458873715877768, "t": 1605.55}34{"step": 1500, "loss": 0.43987947702407837, "lr": 0.000574362508863438, "grad_norm": 0.11156048625707626, "tokens": 248357, "tok_per_s": 154.6689664664522, "t": 1606.25}35{"step": 1550, "loss": 0.5688856840133667, "lr": 0.00055, "grad_norm": 0.20671619474887848, "tokens": 256793, "tok_per_s": 156.75573339214938, "t": 1638.69}36{"step": 1600, "loss": 0.4860112965106964, "lr": 0.0005256374911365621, "grad_norm": 0.11779836565256119, "tokens": 265023, "tok_per_s": 158.62792294418423, "t": 1671.24}37{"step": 1650, "loss": 0.5257750153541565, "lr": 0.0005013464417092262, "grad_norm": 0.1788065880537033, "tokens": 273283, "tok_per_s": 160.4361925604975, "t": 1703.89}38{"step": 1700, "loss": 0.46461063623428345, "lr": 0.00047719810155125587, "grad_norm": 0.1716850996017456, "tokens": 281671, "tok_per_s": 162.24305896133194, "t": 1736.62}39{"step": 1750, "loss": 0.40716487169265747, "lr": 0.0004532633019050392, "grad_norm": 0.08291112631559372, "tokens": 289799, "tok_per_s": 163.94233375679346, "t": 1768.21}40{"step": 1800, "loss": 0.3613208830356598, "lr": 0.0004296122476618507, "grad_norm": 0.09130488336086273, "tokens": 298140, "tok_per_s": 165.84219396825372, "t": 1798.25}41{"step": 1850, "loss": 0.46017178893089294, "lr": 0.00040631431143880916, "grad_norm": 0.12051569670438766, "tokens": 306518, "tok_per_s": 167.68741209336898, "t": 1828.43}42{"step": 1900, "loss": 0.34737125039100647, "lr": 0.00038343783009703845, "grad_norm": 0.08825219422578812, "tokens": 314885, "tok_per_s": 169.41838289629342, "t": 1859.14}43{"step": 1950, "loss": 0.3211873769760132, "lr": 0.000361049904297881, "grad_norm": 0.131572425365448, "tokens": 322988, "tok_per_s": 170.9765788728236, "t": 1889.59}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4550159552110246, "val_loss_b2": 0.45159991919083686, "val_loss_b4": 0.44931293109651266, "val_loss_b8": 0.4523804948034987, "t": 1927.26}45{"step": 2000, "loss": 0.4902324080467224, "lr": 0.0003392162016850945, "grad_norm": 0.13040460646152496, "tokens": 331190, "tok_per_s": 171.83678769789077, "t": 1927.87}46{"step": 2050, "loss": 0.40006566047668457, "lr": 0.0003180007642703402, "grad_norm": 0.18407990038394928, "tokens": 339365, "tok_per_s": 173.5102274022956, "t": 1956.39}47{"step": 2100, "loss": 0.35288283228874207, "lr": 0.000297465820586928, "grad_norm": 0.13266116380691528, "tokens": 347821, "tok_per_s": 175.27271276696285, "t": 1984.97}48{"step": 2150, "loss": 0.48831039667129517, "lr": 0.0002776716031628058, "grad_norm": 0.1096341609954834, "tokens": 355802, "tok_per_s": 176.9778108120158, "t": 2010.95}49{"step": 2200, "loss": 0.3428565263748169, "lr": 0.00025867617184817756, "grad_norm": 0.13877543807029724, "tokens": 363932, "tok_per_s": 179.37823043683542, "t": 2029.37}50{"step": 2250, "loss": 0.299686998128891, "lr": 0.00024053524351595949, "grad_norm": 0.10998736321926117, "tokens": 372235, "tok_per_s": 181.782744842022, "t": 2048.21}51{"step": 2300, "loss": 0.3777705132961273, "lr": 0.0002233020286345913, "grad_norm": 0.12887640297412872, "tokens": 380617, "tok_per_s": 184.14205374035762, "t": 2067.49}52{"step": 2350, "loss": 0.3582797348499298, "lr": 0.00020702707519256364, "grad_norm": 0.1376567780971527, "tokens": 388820, "tok_per_s": 186.40777866361185, "t": 2086.37}53{"step": 2400, "loss": 0.3737044930458069, "lr": 0.00019175812043246033, "grad_norm": 0.26164454221725464, "tokens": 397013, "tok_per_s": 188.656052674674, "t": 2104.94}54{"step": 2450, "loss": 0.40984028577804565, "lr": 0.00017753995082939931, "grad_norm": 0.15022003650665283, "tokens": 405444, "tok_per_s": 190.93829441308773, "t": 2123.95}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45343949255419225, "val_loss_b2": 0.45016375241343054, "val_loss_b4": 0.4495674526239041, "val_loss_b8": 0.4584270851432308, "t": 2146.6}56{"step": 2500, "loss": 0.46228790283203125, "lr": 0.00016441427072458494, "grad_norm": 0.18309006094932556, "tokens": 413920, "tok_per_s": 192.83879033985957, "t": 2146.97}57{"step": 2550, "loss": 0.3293818533420563, "lr": 0.0001524195799992897, "grad_norm": 0.10093899816274643, "tokens": 422230, "tok_per_s": 194.9818076506188, "t": 2166.0}58{"step": 2600, "loss": 0.4060114622116089, "lr": 0.0001415910611480694, "grad_norm": 0.1200878769159317, "tokens": 430404, "tok_per_s": 197.06611055554976, "t": 2184.57}59{"step": 2650, "loss": 0.39150142669677734, "lr": 0.00013196047608244387, "grad_norm": 0.14202018082141876, "tokens": 438498, "tok_per_s": 199.01164456703376, "t": 2203.89}60{"step": 2700, "loss": 0.332682341337204, "lr": 0.00012355607296773896, "grad_norm": 0.12434625625610352, "tokens": 446658, "tok_per_s": 200.99331434304528, "t": 2222.77}61{"step": 2750, "loss": 0.35336926579475403, "lr": 0.00011640250336634969, "grad_norm": 0.11305773258209229, "tokens": 455155, "tok_per_s": 203.104781987499, "t": 2241.5}62{"step": 2800, "loss": 0.43149587512016296, "lr": 0.00011052074993046101, "grad_norm": 0.16088692843914032, "tokens": 463083, "tok_per_s": 204.98805997116258, "t": 2259.59}63{"step": 2850, "loss": 0.3708423972129822, "lr": 0.00010592806485631325, "grad_norm": 0.13220471143722534, "tokens": 471665, "tok_per_s": 207.15263889306573, "t": 2277.41}64{"step": 2900, "loss": 0.42745962738990784, "lr": 0.00010263791928053818, "grad_norm": 0.13615313172340393, "tokens": 480193, "tok_per_s": 209.2472549194375, "t": 2295.38}65{"step": 2950, "loss": 0.31990453600883484, "lr": 0.0001006599637669943, "grad_norm": 0.1531381756067276, "tokens": 488284, "tok_per_s": 211.09546064598297, "t": 2313.61}66{"step": 2999, "loss": 0.4423004984855652, "lr": 0.0001000002640500325, "grad_norm": 0.16302490234375, "tokens": 496298, "tok_per_s": 212.91213492078708, "t": 2331.51}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45239370523737593, "val_loss_b2": 0.44897717945442933, "val_loss_b4": 0.44805410167981746, "val_loss_b8": 0.45787607101808925, "t": 2335.65}68{"step": 2999, "checkpoint_sha256": "ae474b44abeef345f7c67c986684edff2996bd0acb19b4d554a0afd2061ac4bb", "t": 2335.67}69
Files · main
Menu

Theme