SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.6175040006637573, "lr": 1e-05, "grad_norm": 3.2414886951446533, "tokens": 163, "tok_per_s": 107.50353910024111, "t": 2.09}2{"step": 50, "loss": 0.4191346764564514, "lr": 0.00051, "grad_norm": 0.7941694259643555, "tokens": 8255, "tok_per_s": 148.2695947416678, "t": 56.25}3{"step": 100, "loss": 0.3450653553009033, "lr": 0.001, "grad_norm": 0.35149919986724854, "tokens": 16571, "tok_per_s": 152.14221717928712, "t": 109.49}4{"step": 150, "loss": 0.4997781813144684, "lr": 0.0009993400362330058, "grad_norm": 0.13594625890254974, "tokens": 25277, "tok_per_s": 152.8511239052867, "t": 165.94}5{"step": 200, "loss": 0.5539324879646301, "lr": 0.0009973620807194618, "grad_norm": 0.07752683758735657, "tokens": 33752, "tok_per_s": 152.235445260487, "t": 222.28}6{"step": 250, "loss": 0.401094913482666, "lr": 0.000994071935143687, "grad_norm": 0.03228667378425598, "tokens": 41944, "tok_per_s": 150.78721683530185, "t": 278.74}7{"step": 300, "loss": 0.5438956618309021, "lr": 0.000989479250069539, "grad_norm": 0.10028450191020966, "tokens": 49880, "tok_per_s": 149.13108931858764, "t": 335.04}8{"step": 350, "loss": 0.3841667175292969, "lr": 0.0009835974966336503, "grad_norm": 0.022541984915733337, "tokens": 58163, "tok_per_s": 149.91477999535186, "t": 388.55}9{"step": 400, "loss": 0.5042541027069092, "lr": 0.0009764439270322612, "grad_norm": 0.027701949700713158, "tokens": 66164, "tok_per_s": 152.15655466828863, "t": 435.41}10{"step": 450, "loss": 0.3880065977573395, "lr": 0.0009680395239175562, "grad_norm": 0.04414923116564751, "tokens": 74558, "tok_per_s": 157.22214885286112, "t": 474.79}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.46082406492877204, "val_loss_b2": 0.4615930469826914, "val_loss_b4": 0.46362703266021593, "val_loss_b8": 0.4671937294814785, "t": 521.12}12{"step": 500, "loss": 0.4668440520763397, "lr": 0.0009584089388519307, "grad_norm": 0.17547723650932312, "tokens": 82715, "tok_per_s": 158.6948931522783, "t": 521.79}13{"step": 550, "loss": 0.47662848234176636, "lr": 0.0009475804200007103, "grad_norm": 0.06315135210752487, "tokens": 91267, "tok_per_s": 163.13441163815702, "t": 560.03}14{"step": 600, "loss": 0.32247188687324524, "lr": 0.0009355857292754152, "grad_norm": 0.04472284018993378, "tokens": 99524, "tok_per_s": 166.43019237508528, "t": 598.56}15{"step": 650, "loss": 0.42376238107681274, "lr": 0.0009224600491706008, "grad_norm": 0.16782182455062866, "tokens": 107970, "tok_per_s": 169.70663182865576, "t": 636.79}16{"step": 700, "loss": 0.46679484844207764, "lr": 0.0009082418795675396, "grad_norm": 0.31452107429504395, "tokens": 116272, "tok_per_s": 172.37790513212076, "t": 675.09}17{"step": 750, "loss": 0.445706844329834, "lr": 0.0008929729248074364, "grad_norm": 0.05088164284825325, "tokens": 124586, "tok_per_s": 174.7128683128489, "t": 713.66}18{"step": 800, "loss": 0.35657286643981934, "lr": 0.0008766979713654089, "grad_norm": 0.07667183130979538, "tokens": 132471, "tok_per_s": 176.30648908834726, "t": 751.94}19{"step": 850, "loss": 0.43975961208343506, "lr": 0.0008594647564840406, "grad_norm": 0.04667941480875015, "tokens": 140749, "tok_per_s": 178.23069724877234, "t": 790.27}20{"step": 900, "loss": 0.2834239900112152, "lr": 0.0008413238281518224, "grad_norm": 0.10542237758636475, "tokens": 149107, "tok_per_s": 179.8776558950554, "t": 829.51}21{"step": 950, "loss": 0.36658424139022827, "lr": 0.0008223283968371944, "grad_norm": 0.17627085745334625, "tokens": 157427, "tok_per_s": 181.42233883631172, "t": 868.31}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45846444905949907, "val_loss_b2": 0.45833364856131503, "val_loss_b4": 0.46165743527475867, "val_loss_b8": 0.47278527005544846, "t": 915.01}23{"step": 1000, "loss": 0.40747031569480896, "lr": 0.000802534179413072, "grad_norm": 0.15712597966194153, "tokens": 165723, "tok_per_s": 181.07409234147943, "t": 915.79}24{"step": 1050, "loss": 0.38181960582733154, "lr": 0.0007819992357296598, "grad_norm": 0.07127010822296143, "tokens": 173820, "tok_per_s": 182.36220583855592, "t": 953.73}25{"step": 1100, "loss": 0.33967795968055725, "lr": 0.0007607837983149056, "grad_norm": 0.08439648151397705, "tokens": 182174, "tok_per_s": 183.82337209526167, "t": 991.6}26{"step": 1150, "loss": 0.43615493178367615, "lr": 0.0007389500957021191, "grad_norm": 0.15645818412303925, "tokens": 190590, "tok_per_s": 185.05597291964503, "t": 1030.48}27{"step": 1200, "loss": 0.33294913172721863, "lr": 0.0007165621699029615, "grad_norm": 0.11471361666917801, "tokens": 198577, "tok_per_s": 185.74317036324547, "t": 1069.67}28{"step": 1250, "loss": 0.3649960160255432, "lr": 0.000693685688561191, "grad_norm": 0.1403680294752121, "tokens": 206821, "tok_per_s": 186.7628732069694, "t": 1107.97}29{"step": 1300, "loss": 0.4480742812156677, "lr": 0.0006703877523381495, "grad_norm": 0.12956714630126953, "tokens": 214819, "tok_per_s": 187.49460414657085, "t": 1146.31}30{"step": 1350, "loss": 0.432046502828598, "lr": 0.0006467366980949609, "grad_norm": 0.08767837285995483, "tokens": 222971, "tok_per_s": 188.3496703235639, "t": 1184.39}31{"step": 1400, "loss": 0.38587379455566406, "lr": 0.0006228018984487442, "grad_norm": 0.04989991337060928, "tokens": 231317, "tok_per_s": 189.34714928528052, "t": 1222.23}32{"step": 1450, "loss": 0.5259009003639221, "lr": 0.0005986535582907738, "grad_norm": 0.1720942258834839, "tokens": 239557, "tok_per_s": 190.0972454125422, "t": 1260.75}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4578478593671187, "val_loss_b2": 0.45563309670904695, "val_loss_b4": 0.4542384149994152, "val_loss_b8": 0.45781593924381864, "t": 1306.81}34{"step": 1500, "loss": 0.4896051585674286, "lr": 0.000574362508863438, "grad_norm": 0.17245404422283173, "tokens": 247607, "tok_per_s": 189.44007362529467, "t": 1307.62}35{"step": 1550, "loss": 0.4309367835521698, "lr": 0.00055, "grad_norm": 0.23932434618473053, "tokens": 256272, "tok_per_s": 190.44017374283257, "t": 1346.25}36{"step": 1600, "loss": 0.3857293128967285, "lr": 0.0005256374911365621, "grad_norm": 0.208397775888443, "tokens": 264490, "tok_per_s": 191.0888573407758, "t": 1384.69}37{"step": 1650, "loss": 0.34531235694885254, "lr": 0.0005013464417092262, "grad_norm": 0.11431685090065002, "tokens": 272714, "tok_per_s": 191.73860410982658, "t": 1422.89}38{"step": 1700, "loss": 0.5485448241233826, "lr": 0.00047719810155125587, "grad_norm": 0.19971315562725067, "tokens": 280990, "tok_per_s": 192.31437547246244, "t": 1461.67}39{"step": 1750, "loss": 0.40110480785369873, "lr": 0.0004532633019050392, "grad_norm": 0.24384284019470215, "tokens": 289345, "tok_per_s": 192.84311910819943, "t": 1500.99}40{"step": 1800, "loss": 0.26500847935676575, "lr": 0.0004296122476618507, "grad_norm": 0.1481645256280899, "tokens": 297639, "tok_per_s": 193.39162080014972, "t": 1539.62}41{"step": 1850, "loss": 0.40097033977508545, "lr": 0.00040631431143880916, "grad_norm": 0.18518149852752686, "tokens": 305990, "tok_per_s": 193.89124979035623, "t": 1578.72}42{"step": 1900, "loss": 0.2959955334663391, "lr": 0.00038343783009703845, "grad_norm": 0.09370853751897812, "tokens": 313976, "tok_per_s": 194.23153749913536, "t": 1617.08}43{"step": 1950, "loss": 0.3586525321006775, "lr": 0.000361049904297881, "grad_norm": 0.08504636585712433, "tokens": 322226, "tok_per_s": 194.6972758168645, "t": 1655.58}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45386123469217826, "val_loss_b2": 0.4506356872438268, "val_loss_b4": 0.4501138586549115, "val_loss_b8": 0.45747592638372025, "t": 1701.76}45{"step": 2000, "loss": 0.3734626770019531, "lr": 0.0003392162016850945, "grad_norm": 0.27070653438568115, "tokens": 330697, "tok_per_s": 194.30516123812896, "t": 1702.52}46{"step": 2050, "loss": 0.4408971071243286, "lr": 0.0003180007642703402, "grad_norm": 0.15026015043258667, "tokens": 338821, "tok_per_s": 194.7272230413463, "t": 1740.55}47{"step": 2100, "loss": 0.44188392162323, "lr": 0.000297465820586928, "grad_norm": 0.14100410044193268, "tokens": 347181, "tok_per_s": 195.16493325122576, "t": 1779.48}48{"step": 2150, "loss": 0.4460934102535248, "lr": 0.0002776716031628058, "grad_norm": 0.1447376310825348, "tokens": 355319, "tok_per_s": 195.50464393677083, "t": 1818.02}49{"step": 2200, "loss": 0.35946232080459595, "lr": 0.00025867617184817756, "grad_norm": 0.12054786086082458, "tokens": 363537, "tok_per_s": 195.99050248408702, "t": 1855.44}50{"step": 2250, "loss": 0.4852771759033203, "lr": 0.00024053524351595949, "grad_norm": 0.22278863191604614, "tokens": 371638, "tok_per_s": 196.23741270222706, "t": 1894.39}51{"step": 2300, "loss": 0.3293868899345398, "lr": 0.0002233020286345913, "grad_norm": 0.1886606216430664, "tokens": 379727, "tok_per_s": 196.5623939374814, "t": 1932.41}52{"step": 2350, "loss": 0.3871571719646454, "lr": 0.00020702707519256364, "grad_norm": 0.20455144345760345, "tokens": 388116, "tok_per_s": 196.97037039229437, "t": 1971.0}53{"step": 2400, "loss": 0.27921193838119507, "lr": 0.00019175812043246033, "grad_norm": 0.18543168902397156, "tokens": 396308, "tok_per_s": 197.29923193949577, "t": 2009.24}54{"step": 2450, "loss": 0.38231372833251953, "lr": 0.00017753995082939931, "grad_norm": 0.27275392413139343, "tokens": 404717, "tok_per_s": 197.70359253743172, "t": 2047.66}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45227900674743804, "val_loss_b2": 0.4482950423961205, "val_loss_b4": 0.44645703890571575, "val_loss_b8": 0.45105067516795044, "t": 2093.68}56{"step": 2500, "loss": 0.483014851808548, "lr": 0.00016441427072458494, "grad_norm": 0.19232407212257385, "tokens": 413027, "tok_per_s": 197.27034888499787, "t": 2094.28}57{"step": 2550, "loss": 0.446356862783432, "lr": 0.0001524195799992897, "grad_norm": 0.17389285564422607, "tokens": 421798, "tok_per_s": 197.82747461204104, "t": 2132.72}58{"step": 2600, "loss": 0.29569846391677856, "lr": 0.0001415910611480694, "grad_norm": 0.1704888939857483, "tokens": 430295, "tok_per_s": 198.2333622548404, "t": 2171.22}59{"step": 2650, "loss": 0.5031952261924744, "lr": 0.00013196047608244387, "grad_norm": 0.24525725841522217, "tokens": 438698, "tok_per_s": 198.63542491111568, "t": 2209.13}60{"step": 2700, "loss": 0.43966037034988403, "lr": 0.00012355607296773896, "grad_norm": 0.20851770043373108, "tokens": 447187, "tok_per_s": 198.96505841186914, "t": 2248.14}61{"step": 2750, "loss": 0.39324167370796204, "lr": 0.00011640250336634969, "grad_norm": 0.18412964046001434, "tokens": 455379, "tok_per_s": 199.20498104314046, "t": 2286.55}62{"step": 2800, "loss": 0.4187619686126709, "lr": 0.00011052074993046101, "grad_norm": 0.2582833766937256, "tokens": 463791, "tok_per_s": 199.53339656676184, "t": 2324.95}63{"step": 2850, "loss": 0.44189223647117615, "lr": 0.00010592806485631325, "grad_norm": 0.21274004876613617, "tokens": 472187, "tok_per_s": 199.80592274062536, "t": 2363.8}64{"step": 2900, "loss": 0.439410537481308, "lr": 0.00010263791928053818, "grad_norm": 0.24176284670829773, "tokens": 480621, "tok_per_s": 200.18181486793563, "t": 2401.49}65{"step": 2950, "loss": 0.33981627225875854, "lr": 0.0001006599637669943, "grad_norm": 0.2049698382616043, "tokens": 488878, "tok_per_s": 200.4054014247851, "t": 2440.02}66{"step": 2999, "loss": 0.3931575119495392, "lr": 0.0001000002640500325, "grad_norm": 0.2162751704454422, "tokens": 497078, "tok_per_s": 200.7111849139665, "t": 2477.16}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.44912503892532885, "val_loss_b2": 0.4444847529953251, "val_loss_b4": 0.44287649994122097, "val_loss_b8": 0.4483173928747276, "t": 2485.99}68{"step": 2999, "checkpoint_sha256": "992e5fe53a5b3ec512151644bcdcf2a4cef2c691a566bc1cdccdfbd7ed65cfda", "t": 2486.03}69
Files · main
Menu

Theme