SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.41377881169319153, "lr": 1e-05, "grad_norm": 0.32589152455329895, "tokens": 157, "tok_per_s": 61.88468066278903, "t": 3.36}2{"step": 50, "loss": 0.3895237147808075, "lr": 0.00051, "grad_norm": 0.13877931237220764, "tokens": 8616, "tok_per_s": 160.21602561780693, "t": 54.6}3{"step": 100, "loss": 0.40602242946624756, "lr": 0.001, "grad_norm": 0.09282264113426208, "tokens": 16635, "tok_per_s": 159.08570631823272, "t": 105.39}4{"step": 150, "loss": 0.5330981016159058, "lr": 0.0009993400362330058, "grad_norm": 0.05619408190250397, "tokens": 25042, "tok_per_s": 161.25173185958099, "t": 156.12}5{"step": 200, "loss": 0.46268630027770996, "lr": 0.0009973620807194618, "grad_norm": 0.1182842031121254, "tokens": 33661, "tok_per_s": 164.11870207156525, "t": 205.92}6{"step": 250, "loss": 0.4415181279182434, "lr": 0.000994071935143687, "grad_norm": 0.11809372901916504, "tokens": 42410, "tok_per_s": 166.04278737107842, "t": 256.24}7{"step": 300, "loss": 0.3940010964870453, "lr": 0.000989479250069539, "grad_norm": 0.11211973428726196, "tokens": 50771, "tok_per_s": 166.2438654851675, "t": 306.22}8{"step": 350, "loss": 0.41956377029418945, "lr": 0.0009835974966336503, "grad_norm": 0.14605280756950378, "tokens": 59133, "tok_per_s": 166.61739038383837, "t": 355.73}9{"step": 400, "loss": 0.5921702980995178, "lr": 0.0009764439270322612, "grad_norm": 0.14147312939167023, "tokens": 67299, "tok_per_s": 166.53724378679408, "t": 404.93}10{"step": 450, "loss": 0.4641536772251129, "lr": 0.0009680395239175562, "grad_norm": 0.016725623980164528, "tokens": 75575, "tok_per_s": 166.6311099345598, "t": 454.37}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.46034266573857535, "val_loss_b2": 0.4589685399641598, "val_loss_b4": 0.4578057689112122, "val_loss_b8": 0.4581116149436082, "t": 514.68}12{"step": 500, "loss": 0.4079206585884094, "lr": 0.0009584089388519307, "grad_norm": 0.07969986647367477, "tokens": 84036, "tok_per_s": 163.21910559753672, "t": 515.69}13{"step": 550, "loss": 0.2891760766506195, "lr": 0.0009475804200007103, "grad_norm": 0.1479167938232422, "tokens": 92359, "tok_per_s": 163.5730510728396, "t": 565.46}14{"step": 600, "loss": 0.31191176176071167, "lr": 0.0009355857292754152, "grad_norm": 0.06306462734937668, "tokens": 100627, "tok_per_s": 163.903513576079, "t": 614.76}15{"step": 650, "loss": 0.515059769153595, "lr": 0.0009224600491706008, "grad_norm": 0.08930547535419464, "tokens": 108981, "tok_per_s": 164.2998373092478, "t": 664.13}16{"step": 700, "loss": 0.3886401951313019, "lr": 0.0009082418795675396, "grad_norm": 0.11570568382740021, "tokens": 117352, "tok_per_s": 164.6603637917854, "t": 713.52}17{"step": 750, "loss": 0.5017507076263428, "lr": 0.0008929729248074364, "grad_norm": 0.0987381860613823, "tokens": 125499, "tok_per_s": 164.71069629569118, "t": 762.76}18{"step": 800, "loss": 0.3760119378566742, "lr": 0.0008766979713654089, "grad_norm": 0.0683303251862526, "tokens": 133880, "tok_per_s": 164.9549890095108, "t": 812.44}19{"step": 850, "loss": 0.4709320068359375, "lr": 0.0008594647564840406, "grad_norm": 0.09987472742795944, "tokens": 142063, "tok_per_s": 165.18682469615484, "t": 860.84}20{"step": 900, "loss": 0.3489229679107666, "lr": 0.0008413238281518224, "grad_norm": 0.07888219505548477, "tokens": 150436, "tok_per_s": 165.38166185239095, "t": 910.45}21{"step": 950, "loss": 0.4072759747505188, "lr": 0.0008223283968371944, "grad_norm": 0.07829706370830536, "tokens": 158527, "tok_per_s": 165.27623798382515, "t": 959.99}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45937989367940496, "val_loss_b2": 0.4575431235263123, "val_loss_b4": 0.45673000266130126, "val_loss_b8": 0.4624986681461099, "t": 1016.94}23{"step": 1000, "loss": 0.4026084840297699, "lr": 0.000802534179413072, "grad_norm": 0.13475772738456726, "tokens": 166917, "tok_per_s": 164.15685014497905, "t": 1017.64}24{"step": 1050, "loss": 0.4446007311344147, "lr": 0.0007819992357296598, "grad_norm": 0.09949758648872375, "tokens": 175091, "tok_per_s": 166.67192713010346, "t": 1051.34}25{"step": 1100, "loss": 0.3610053062438965, "lr": 0.0007607837983149056, "grad_norm": 0.1080545037984848, "tokens": 183159, "tok_per_s": 168.86812602214903, "t": 1085.45}26{"step": 1150, "loss": 0.2910768985748291, "lr": 0.0007389500957021191, "grad_norm": 0.0796373263001442, "tokens": 191581, "tok_per_s": 171.22145291462377, "t": 1119.73}27{"step": 1200, "loss": 0.509045422077179, "lr": 0.0007165621699029615, "grad_norm": 0.15310613811016083, "tokens": 200185, "tok_per_s": 173.58466978703638, "t": 1154.06}28{"step": 1250, "loss": 0.5962255597114563, "lr": 0.000693685688561191, "grad_norm": 0.14465220272541046, "tokens": 208401, "tok_per_s": 175.47885387982117, "t": 1188.44}29{"step": 1300, "loss": 0.43049100041389465, "lr": 0.0006703877523381495, "grad_norm": 0.10987836867570877, "tokens": 216624, "tok_per_s": 177.31546349746324, "t": 1222.51}30{"step": 1350, "loss": 0.5324873328208923, "lr": 0.0006467366980949609, "grad_norm": 0.21272416412830353, "tokens": 225093, "tok_per_s": 179.26075452488448, "t": 1256.5}31{"step": 1400, "loss": 0.3952127993106842, "lr": 0.0006228018984487442, "grad_norm": 0.1312004029750824, "tokens": 233304, "tok_per_s": 180.88421837919512, "t": 1290.62}32{"step": 1450, "loss": 0.4139695465564728, "lr": 0.0005986535582907738, "grad_norm": 0.33455613255500793, "tokens": 241497, "tok_per_s": 182.748978597057, "t": 1322.29}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45859495250387927, "val_loss_b2": 0.4556615208098899, "val_loss_b4": 0.45208282151088275, "val_loss_b8": 0.4501298017957752, "t": 1356.45}34{"step": 1500, "loss": 0.4523616433143616, "lr": 0.000574362508863438, "grad_norm": 0.12466985732316971, "tokens": 249582, "tok_per_s": 184.0514086791072, "t": 1356.87}35{"step": 1550, "loss": 0.3245019316673279, "lr": 0.00055, "grad_norm": 0.08476366847753525, "tokens": 257750, "tok_per_s": 187.13480812990522, "t": 1378.17}36{"step": 1600, "loss": 0.42608216404914856, "lr": 0.0005256374911365621, "grad_norm": 0.20363709330558777, "tokens": 266068, "tok_per_s": 190.21605178561012, "t": 1399.59}37{"step": 1650, "loss": 0.4637435972690582, "lr": 0.0005013464417092262, "grad_norm": 0.16455550491809845, "tokens": 274463, "tok_per_s": 193.18618992764792, "t": 1421.54}38{"step": 1700, "loss": 0.31812137365341187, "lr": 0.00047719810155125587, "grad_norm": 0.14841340482234955, "tokens": 282527, "tok_per_s": 195.92824998741816, "t": 1442.81}39{"step": 1750, "loss": 0.45544934272766113, "lr": 0.0004532633019050392, "grad_norm": 0.1827537566423416, "tokens": 290793, "tok_per_s": 198.65061791855652, "t": 1464.66}40{"step": 1800, "loss": 0.41542357206344604, "lr": 0.0004296122476618507, "grad_norm": 0.1110563799738884, "tokens": 299230, "tok_per_s": 201.4799162137614, "t": 1485.98}41{"step": 1850, "loss": 0.3915477693080902, "lr": 0.00040631431143880916, "grad_norm": 0.143265038728714, "tokens": 307566, "tok_per_s": 204.12279628381296, "t": 1507.59}42{"step": 1900, "loss": 0.4001297354698181, "lr": 0.00038343783009703845, "grad_norm": 0.15975813567638397, "tokens": 315780, "tok_per_s": 206.56299740801512, "t": 1529.56}43{"step": 1950, "loss": 0.4183209240436554, "lr": 0.000361049904297881, "grad_norm": 0.109605573117733, "tokens": 324229, "tok_per_s": 209.10890015013644, "t": 1551.35}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4558325608179686, "val_loss_b2": 0.45223948919109197, "val_loss_b4": 0.4498618367036732, "val_loss_b8": 0.4549521854677008, "t": 1576.36}45{"step": 2000, "loss": 0.4663313329219818, "lr": 0.0003392162016850945, "grad_norm": 0.1678052693605423, "tokens": 332550, "tok_per_s": 211.01336299741774, "t": 1576.79}46{"step": 2050, "loss": 0.5198301672935486, "lr": 0.0003180007642703402, "grad_norm": 0.18945680558681488, "tokens": 340880, "tok_per_s": 213.48011053590992, "t": 1597.6}47{"step": 2100, "loss": 0.3012462854385376, "lr": 0.000297465820586928, "grad_norm": 0.1794416457414627, "tokens": 349421, "tok_per_s": 216.00369799663127, "t": 1618.48}48{"step": 2150, "loss": 0.41065317392349243, "lr": 0.0002776716031628058, "grad_norm": 0.11587367206811905, "tokens": 357735, "tok_per_s": 218.33327392420912, "t": 1639.3}49{"step": 2200, "loss": 0.46054497361183167, "lr": 0.00025867617184817756, "grad_norm": 0.16278108954429626, "tokens": 366168, "tok_per_s": 220.635371679601, "t": 1660.43}50{"step": 2250, "loss": 0.37992358207702637, "lr": 0.00024053524351595949, "grad_norm": 0.14999039471149445, "tokens": 374489, "tok_per_s": 222.86814316840253, "t": 1681.14}51{"step": 2300, "loss": 0.3185075521469116, "lr": 0.0002233020286345913, "grad_norm": 0.113345667719841, "tokens": 382832, "tok_per_s": 225.05689472738257, "t": 1701.87}52{"step": 2350, "loss": 0.5366150736808777, "lr": 0.00020702707519256364, "grad_norm": 0.14083729684352875, "tokens": 391097, "tok_per_s": 227.15892529598239, "t": 1722.51}53{"step": 2400, "loss": 0.2769290506839752, "lr": 0.00019175812043246033, "grad_norm": 0.17433945834636688, "tokens": 399648, "tok_per_s": 229.36398170876802, "t": 1743.24}54{"step": 2450, "loss": 0.3580985963344574, "lr": 0.00017753995082939931, "grad_norm": 0.11281668394804001, "tokens": 407914, "tok_per_s": 231.31280289827802, "t": 1764.3}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.454425459251197, "val_loss_b2": 0.450600290838987, "val_loss_b4": 0.44763611877651976, "val_loss_b8": 0.45284086333641926, "t": 1789.21}56{"step": 2500, "loss": 0.2528717517852783, "lr": 0.00016441427072458494, "grad_norm": 0.15901102125644684, "tokens": 416524, "tok_per_s": 232.85095945181234, "t": 1789.62}57{"step": 2550, "loss": 0.3208119571208954, "lr": 0.0001524195799992897, "grad_norm": 0.10840102285146713, "tokens": 424563, "tok_per_s": 234.6427678209868, "t": 1810.22}58{"step": 2600, "loss": 0.28689998388290405, "lr": 0.0001415910611480694, "grad_norm": 0.1907479614019394, "tokens": 432991, "tok_per_s": 236.6094447109885, "t": 1830.8}59{"step": 2650, "loss": 0.3996273875236511, "lr": 0.00013196047608244387, "grad_norm": 0.19439655542373657, "tokens": 441165, "tok_per_s": 238.37121342881758, "t": 1851.57}60{"step": 2700, "loss": 0.3488006889820099, "lr": 0.00012355607296773896, "grad_norm": 0.0831410363316536, "tokens": 449578, "tok_per_s": 240.2240335312619, "t": 1872.32}61{"step": 2750, "loss": 0.3745587468147278, "lr": 0.00011640250336634969, "grad_norm": 0.14482615888118744, "tokens": 457759, "tok_per_s": 241.90082217882664, "t": 1893.16}62{"step": 2800, "loss": 0.3701288402080536, "lr": 0.00011052074993046101, "grad_norm": 0.13142140209674835, "tokens": 465905, "tok_per_s": 243.57611308709494, "t": 1913.59}63{"step": 2850, "loss": 0.4103100597858429, "lr": 0.00010592806485631325, "grad_norm": 0.23936885595321655, "tokens": 474059, "tok_per_s": 245.1898399615459, "t": 1934.26}64{"step": 2900, "loss": 0.5368825793266296, "lr": 0.00010263791928053818, "grad_norm": 0.1333414763212204, "tokens": 482466, "tok_per_s": 246.91453771332556, "t": 1954.8}65{"step": 2950, "loss": 0.3774418234825134, "lr": 0.0001006599637669943, "grad_norm": 0.20752447843551636, "tokens": 490971, "tok_per_s": 248.6493059377558, "t": 1975.37}66{"step": 2999, "loss": 0.36559033393859863, "lr": 0.0001000002640500325, "grad_norm": 0.17667441070079803, "tokens": 499017, "tok_per_s": 250.15001059032386, "t": 1995.69}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45277018051185064, "val_loss_b2": 0.4485527572519031, "val_loss_b4": 0.4473290281262875, "val_loss_b8": 0.4560615009366144, "t": 2000.32}68{"step": 2999, "checkpoint_sha256": "db179a778bde150a446381c1ada6c3b38d2e1bc4cab31656443ed784b0354b80", "t": 2000.35}69
Files · main
Menu

Theme