SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.41846907138824463, "lr": 1e-05, "grad_norm": 0.36108529567718506, "tokens": 157, "tok_per_s": 217.3555235383917, "t": 1.33}2{"step": 50, "loss": 0.388771116733551, "lr": 0.00051, "grad_norm": 0.2420598715543747, "tokens": 8616, "tok_per_s": 196.12355961364148, "t": 44.54}3{"step": 100, "loss": 0.39915910363197327, "lr": 0.001, "grad_norm": 0.1391167789697647, "tokens": 16635, "tok_per_s": 187.77332131845256, "t": 89.21}4{"step": 150, "loss": 0.5309883952140808, "lr": 0.0009993400362330058, "grad_norm": 0.05155426263809204, "tokens": 25042, "tok_per_s": 189.0310570649822, "t": 133.09}5{"step": 200, "loss": 0.46042296290397644, "lr": 0.0009973620807194618, "grad_norm": 0.08551902323961258, "tokens": 33661, "tok_per_s": 189.98897916310997, "t": 177.79}6{"step": 250, "loss": 0.4389230012893677, "lr": 0.000994071935143687, "grad_norm": 0.10805997997522354, "tokens": 42410, "tok_per_s": 192.40353039111562, "t": 221.05}7{"step": 300, "loss": 0.39704984426498413, "lr": 0.000989479250069539, "grad_norm": 0.11089330166578293, "tokens": 50771, "tok_per_s": 192.30607228409198, "t": 264.64}8{"step": 350, "loss": 0.42276087403297424, "lr": 0.0009835974966336503, "grad_norm": 0.1514595001935959, "tokens": 59133, "tok_per_s": 192.1915916947382, "t": 308.29}9{"step": 400, "loss": 0.5882344841957092, "lr": 0.0009764439270322612, "grad_norm": 0.07778030633926392, "tokens": 67299, "tok_per_s": 192.61808475835358, "t": 350.0}10{"step": 450, "loss": 0.4646863043308258, "lr": 0.0009680395239175562, "grad_norm": 0.019660362973809242, "tokens": 75575, "tok_per_s": 192.2060343214502, "t": 393.81}11{"step": 499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.46007884153889694, "val_loss_b2": 0.45837105571959275, "val_loss_b4": 0.45615302170950417, "val_loss_b8": 0.4546031594687697, "t": 446.58}12{"step": 500, "loss": 0.40814441442489624, "lr": 0.0009584089388519307, "grad_norm": 0.05026669055223465, "tokens": 84036, "tok_per_s": 188.04613396943554, "t": 447.5}13{"step": 550, "loss": 0.2865464389324188, "lr": 0.0009475804200007103, "grad_norm": 0.13275815546512604, "tokens": 92359, "tok_per_s": 188.4365765304433, "t": 490.75}14{"step": 600, "loss": 0.3117946684360504, "lr": 0.0009355857292754152, "grad_norm": 0.03057662956416607, "tokens": 100627, "tok_per_s": 188.75162749075153, "t": 533.73}15{"step": 650, "loss": 0.5158529877662659, "lr": 0.0009224600491706008, "grad_norm": 0.08472947031259537, "tokens": 108981, "tok_per_s": 189.70984668085177, "t": 575.08}16{"step": 700, "loss": 0.39397192001342773, "lr": 0.0009082418795675396, "grad_norm": 0.08564465492963791, "tokens": 117352, "tok_per_s": 190.2278714254416, "t": 617.52}17{"step": 750, "loss": 0.5006252527236938, "lr": 0.0008929729248074364, "grad_norm": 0.07506497204303741, "tokens": 125499, "tok_per_s": 190.60298625119302, "t": 659.04}18{"step": 800, "loss": 0.3831084966659546, "lr": 0.0008766979713654089, "grad_norm": 0.05614817515015602, "tokens": 133880, "tok_per_s": 190.71985676729471, "t": 702.59}19{"step": 850, "loss": 0.4713840186595917, "lr": 0.0008594647564840406, "grad_norm": 0.0841238722205162, "tokens": 142063, "tok_per_s": 190.46593953680284, "t": 746.48}20{"step": 900, "loss": 0.35030126571655273, "lr": 0.0008413238281518224, "grad_norm": 0.057008035480976105, "tokens": 150436, "tok_per_s": 190.733161029106, "t": 789.34}21{"step": 950, "loss": 0.4163607656955719, "lr": 0.0008223283968371944, "grad_norm": 0.16304853558540344, "tokens": 158527, "tok_per_s": 190.48949647451875, "t": 832.83}22{"step": 999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4593773753023782, "val_loss_b2": 0.45767565370487306, "val_loss_b4": 0.45732333849309525, "val_loss_b8": 0.4645223330840388, "t": 885.22}23{"step": 1000, "loss": 0.39599382877349854, "lr": 0.000802534179413072, "grad_norm": 0.09378430247306824, "tokens": 166917, "tok_per_s": 188.49415818596904, "t": 886.14}24{"step": 1050, "loss": 0.4469398558139801, "lr": 0.0007819992357296598, "grad_norm": 0.08505380153656006, "tokens": 175091, "tok_per_s": 188.80595444536831, "t": 927.97}25{"step": 1100, "loss": 0.36446577310562134, "lr": 0.0007607837983149056, "grad_norm": 0.09850195795297623, "tokens": 183159, "tok_per_s": 188.49870712283013, "t": 972.29}26{"step": 1150, "loss": 0.29299095273017883, "lr": 0.0007389500957021191, "grad_norm": 0.10912376642227173, "tokens": 191581, "tok_per_s": 188.87296197544012, "t": 1014.96}27{"step": 1200, "loss": 0.5148290991783142, "lr": 0.0007165621699029615, "grad_norm": 0.1272507607936859, "tokens": 200185, "tok_per_s": 189.19557646734046, "t": 1058.7}28{"step": 1250, "loss": 0.5890127420425415, "lr": 0.000693685688561191, "grad_norm": 0.19908148050308228, "tokens": 208401, "tok_per_s": 189.13874414743154, "t": 1102.46}29{"step": 1300, "loss": 0.4281315803527832, "lr": 0.0006703877523381495, "grad_norm": 0.10693594813346863, "tokens": 216624, "tok_per_s": 189.55360899877914, "t": 1143.42}30{"step": 1350, "loss": 0.5360256433486938, "lr": 0.0006467366980949609, "grad_norm": 0.23222783207893372, "tokens": 225093, "tok_per_s": 189.85956390460268, "t": 1186.21}31{"step": 1400, "loss": 0.3951980173587799, "lr": 0.0006228018984487442, "grad_norm": 0.15957921743392944, "tokens": 233304, "tok_per_s": 190.0167714780041, "t": 1228.42}32{"step": 1450, "loss": 0.4151223599910736, "lr": 0.0005986535582907738, "grad_norm": 0.25544270873069763, "tokens": 241497, "tok_per_s": 189.9976440582373, "t": 1271.67}33{"step": 1499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4582970677014347, "val_loss_b2": 0.4552533980247832, "val_loss_b4": 0.451894881397471, "val_loss_b8": 0.4509359136950858, "t": 1323.82}34{"step": 1500, "loss": 0.45399290323257446, "lr": 0.000574362508863438, "grad_norm": 0.11162404716014862, "tokens": 249582, "tok_per_s": 188.51008874341954, "t": 1324.6}35{"step": 1550, "loss": 0.32088905572891235, "lr": 0.00055, "grad_norm": 0.09440828114748001, "tokens": 257750, "tok_per_s": 188.60690290697005, "t": 1367.21}36{"step": 1600, "loss": 0.43825435638427734, "lr": 0.0005256374911365621, "grad_norm": 0.29277175664901733, "tokens": 266068, "tok_per_s": 188.75103895869194, "t": 1410.24}37{"step": 1650, "loss": 0.4631388783454895, "lr": 0.0005013464417092262, "grad_norm": 0.16344238817691803, "tokens": 274463, "tok_per_s": 188.95725364793932, "t": 1453.14}38{"step": 1700, "loss": 0.3125242590904236, "lr": 0.00047719810155125587, "grad_norm": 0.15245889127254486, "tokens": 282527, "tok_per_s": 188.91481815489274, "t": 1496.14}39{"step": 1750, "loss": 0.4575767517089844, "lr": 0.0004532633019050392, "grad_norm": 0.12754447758197784, "tokens": 290793, "tok_per_s": 189.12091408143863, "t": 1538.22}40{"step": 1800, "loss": 0.41113683581352234, "lr": 0.0004296122476618507, "grad_norm": 0.09663138538599014, "tokens": 299230, "tok_per_s": 189.33663297712025, "t": 1581.03}41{"step": 1850, "loss": 0.386082261800766, "lr": 0.00040631431143880916, "grad_norm": 0.12585628032684326, "tokens": 307566, "tok_per_s": 189.4122648061899, "t": 1624.41}42{"step": 1900, "loss": 0.39487528800964355, "lr": 0.00038343783009703845, "grad_norm": 0.1578918993473053, "tokens": 315780, "tok_per_s": 189.61297290563766, "t": 1666.01}43{"step": 1950, "loss": 0.4119558036327362, "lr": 0.000361049904297881, "grad_norm": 0.1361137181520462, "tokens": 324229, "tok_per_s": 189.9051788780983, "t": 1707.93}44{"step": 1999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.45461687564614844, "val_loss_b2": 0.45074231545874616, "val_loss_b4": 0.448824666767299, "val_loss_b8": 0.4546939770889846, "t": 1760.56}45{"step": 2000, "loss": 0.4633687734603882, "lr": 0.0003392162016850945, "grad_norm": 0.1985238641500473, "tokens": 332550, "tok_per_s": 188.8482494922474, "t": 1761.55}46{"step": 2050, "loss": 0.523091197013855, "lr": 0.0003180007642703402, "grad_norm": 0.20256252586841583, "tokens": 340880, "tok_per_s": 189.00773403164138, "t": 1804.16}47{"step": 2100, "loss": 0.3142109811306, "lr": 0.000297465820586928, "grad_norm": 0.27769017219543457, "tokens": 349421, "tok_per_s": 189.4734947511578, "t": 1844.78}48{"step": 2150, "loss": 0.41368094086647034, "lr": 0.0002776716031628058, "grad_norm": 0.15510377287864685, "tokens": 357735, "tok_per_s": 190.28499370701715, "t": 1880.62}49{"step": 2200, "loss": 0.4687657952308655, "lr": 0.00025867617184817756, "grad_norm": 0.1831185668706894, "tokens": 366168, "tok_per_s": 191.11236539557885, "t": 1916.6}50{"step": 2250, "loss": 0.38054609298706055, "lr": 0.00024053524351595949, "grad_norm": 0.1372220814228058, "tokens": 374489, "tok_per_s": 192.3756691869415, "t": 1947.27}51{"step": 2300, "loss": 0.318832129240036, "lr": 0.0002233020286345913, "grad_norm": 0.120822973549366, "tokens": 382832, "tok_per_s": 194.20835336048708, "t": 1971.86}52{"step": 2350, "loss": 0.5379577875137329, "lr": 0.00020702707519256364, "grad_norm": 0.1537543535232544, "tokens": 391097, "tok_per_s": 195.98887908690364, "t": 1996.12}53{"step": 2400, "loss": 0.28337565064430237, "lr": 0.00019175812043246033, "grad_norm": 0.21870733797550201, "tokens": 399648, "tok_per_s": 197.84687758448183, "t": 2020.6}54{"step": 2450, "loss": 0.36246389150619507, "lr": 0.00017753995082939931, "grad_norm": 0.14099475741386414, "tokens": 407914, "tok_per_s": 199.49038028147078, "t": 2045.39}55{"step": 2499, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4531072858168375, "val_loss_b2": 0.449115593366402, "val_loss_b4": 0.44687444462219206, "val_loss_b8": 0.4518818063298842, "t": 2074.23}56{"step": 2500, "loss": 0.2562374770641327, "lr": 0.00016441427072458494, "grad_norm": 0.1882106214761734, "tokens": 416524, "tok_per_s": 200.82242019291425, "t": 2074.7}57{"step": 2550, "loss": 0.3215468227863312, "lr": 0.0001524195799992897, "grad_norm": 0.11503736674785614, "tokens": 424563, "tok_per_s": 202.27737311652962, "t": 2099.53}58{"step": 2600, "loss": 0.28172174096107483, "lr": 0.0001415910611480694, "grad_norm": 0.15108425915241241, "tokens": 432991, "tok_per_s": 203.88602157912698, "t": 2124.3}59{"step": 2650, "loss": 0.3938547372817993, "lr": 0.00013196047608244387, "grad_norm": 0.24123036861419678, "tokens": 441165, "tok_per_s": 205.3597366043352, "t": 2148.87}60{"step": 2700, "loss": 0.3498060703277588, "lr": 0.00012355607296773896, "grad_norm": 0.07935789972543716, "tokens": 449578, "tok_per_s": 206.9109144845185, "t": 2173.42}61{"step": 2750, "loss": 0.3729216158390045, "lr": 0.00011640250336634969, "grad_norm": 0.18832242488861084, "tokens": 457759, "tok_per_s": 208.2697711670102, "t": 2198.53}62{"step": 2800, "loss": 0.378124475479126, "lr": 0.00011052074993046101, "grad_norm": 0.17141707241535187, "tokens": 465905, "tok_per_s": 209.66543984629382, "t": 2222.75}63{"step": 2850, "loss": 0.4000420868396759, "lr": 0.00010592806485631325, "grad_norm": 0.168649822473526, "tokens": 474059, "tok_per_s": 210.9874156090354, "t": 2247.47}64{"step": 2900, "loss": 0.5353509187698364, "lr": 0.00010263791928053818, "grad_norm": 0.1195419654250145, "tokens": 482466, "tok_per_s": 212.4026399357882, "t": 2272.08}65{"step": 2950, "loss": 0.37273770570755005, "lr": 0.0001006599637669943, "grad_norm": 0.19124028086662292, "tokens": 490971, "tok_per_s": 213.82317792696134, "t": 2296.77}66{"step": 2999, "loss": 0.364658921957016, "lr": 0.0001000002640500325, "grad_norm": 0.193694069981575, "tokens": 499017, "tok_per_s": 215.05789857390815, "t": 2321.0}67{"step": 2999, "val_loss_b0": 0.46212446495721704, "val_loss_b1": 0.4516305683750775, "val_loss_b2": 0.4474406385727267, "val_loss_b4": 0.44696345923862296, "val_loss_b8": 0.4555199257900939, "t": 2325.52}68{"step": 2999, "checkpoint_sha256": "e7094ff15274165fb76a2edcb046bab1616875a43108d60f4de4b687ea5a35f6", "t": 2325.58}69
Files · main
Menu

Theme