SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.8655945062637329, "lr": 1e-05, "grad_norm": 12.048591613769531, "tokens": 139, "tok_per_s": 96.54339083738365, "t": 2.06}2{"step": 50, "loss": 0.3399727940559387, "lr": 0.00051, "grad_norm": 0.7269741296768188, "tokens": 8357, "tok_per_s": 149.1151678253597, "t": 56.67}3{"step": 100, "loss": 0.3171934187412262, "lr": 0.001, "grad_norm": 0.19586065411567688, "tokens": 16659, "tok_per_s": 151.32462337255544, "t": 110.71}4{"step": 150, "loss": 0.4541836082935333, "lr": 0.0009993400362330058, "grad_norm": 0.0716216191649437, "tokens": 25169, "tok_per_s": 149.90418379145228, "t": 168.52}5{"step": 200, "loss": 0.480942040681839, "lr": 0.0009973620807194618, "grad_norm": 0.07926613092422485, "tokens": 33572, "tok_per_s": 148.77339224230175, "t": 226.28}6{"step": 250, "loss": 0.4172719120979309, "lr": 0.000994071935143687, "grad_norm": 0.058588795363903046, "tokens": 41743, "tok_per_s": 147.20441953992818, "t": 284.19}7{"step": 300, "loss": 0.39874881505966187, "lr": 0.000989479250069539, "grad_norm": 0.027894267812371254, "tokens": 49922, "tok_per_s": 148.07897969647084, "t": 337.75}8{"step": 350, "loss": 0.3876688778400421, "lr": 0.0009835974966336503, "grad_norm": 0.06466042995452881, "tokens": 58442, "tok_per_s": 149.55396427003848, "t": 391.4}9{"step": 400, "loss": 0.3570287823677063, "lr": 0.0009764439270322612, "grad_norm": 0.1428617388010025, "tokens": 66780, "tok_per_s": 155.4938619051402, "t": 430.09}10{"step": 450, "loss": 0.4955383539199829, "lr": 0.0009680395239175562, "grad_norm": 0.08507850021123886, "tokens": 74983, "tok_per_s": 160.16621731157574, "t": 468.78}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4604369417795, "val_loss_b2": 0.4592154236366268, "val_loss_b4": 0.4576377267024387, "val_loss_b8": 0.4563891512822376, "t": 514.89}12{"step": 500, "loss": 0.32608169317245483, "lr": 0.0009584089388519307, "grad_norm": 0.055683426558971405, "tokens": 83177, "tok_per_s": 161.4955422904968, "t": 515.66}13{"step": 550, "loss": 0.4463685154914856, "lr": 0.0009475804200007103, "grad_norm": 0.3191685676574707, "tokens": 91423, "tok_per_s": 165.29029195993874, "t": 553.73}14{"step": 600, "loss": 0.3830341696739197, "lr": 0.0009355857292754152, "grad_norm": 0.08180791884660721, "tokens": 99986, "tok_per_s": 168.97036106422584, "t": 592.36}15{"step": 650, "loss": 0.3474637269973755, "lr": 0.0009224600491706008, "grad_norm": 0.07271377742290497, "tokens": 108206, "tok_per_s": 171.56762340517923, "t": 631.31}16{"step": 700, "loss": 0.44002798199653625, "lr": 0.0009082418795675396, "grad_norm": 0.10826680064201355, "tokens": 116415, "tok_per_s": 173.9194454417135, "t": 669.98}17{"step": 750, "loss": 0.3435828685760498, "lr": 0.0008929729248074364, "grad_norm": 0.041411735117435455, "tokens": 124709, "tok_per_s": 176.13439719686343, "t": 708.65}18{"step": 800, "loss": 0.4373776316642761, "lr": 0.0008766979713654089, "grad_norm": 0.11360673606395721, "tokens": 132874, "tok_per_s": 178.13283477861236, "t": 746.55}19{"step": 850, "loss": 0.3737347424030304, "lr": 0.0008594647564840406, "grad_norm": 0.24829496443271637, "tokens": 141506, "tok_per_s": 180.3520432018977, "t": 785.23}20{"step": 900, "loss": 0.29486343264579773, "lr": 0.0008413238281518224, "grad_norm": 0.06879092752933502, "tokens": 149769, "tok_per_s": 182.05077413536222, "t": 823.3}21{"step": 950, "loss": 0.35829195380210876, "lr": 0.0008223283968371944, "grad_norm": 0.087185338139534, "tokens": 158176, "tok_per_s": 183.74701071074165, "t": 861.46}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45787572884218863, "val_loss_b2": 0.4561677926158952, "val_loss_b4": 0.456597868241131, "val_loss_b8": 0.4643479860022833, "t": 907.83}23{"step": 1000, "loss": 0.4176991581916809, "lr": 0.000802534179413072, "grad_norm": 0.08061283081769943, "tokens": 166573, "tok_per_s": 183.45071711887286, "t": 908.62}24{"step": 1050, "loss": 0.3641575574874878, "lr": 0.0007819992357296598, "grad_norm": 0.0686296820640564, "tokens": 174773, "tok_per_s": 184.78448032671236, "t": 946.44}25{"step": 1100, "loss": 0.4379884600639343, "lr": 0.0007607837983149056, "grad_norm": 0.05248786881566048, "tokens": 183200, "tok_per_s": 186.09277060482617, "t": 985.08}26{"step": 1150, "loss": 0.45660871267318726, "lr": 0.0007389500957021191, "grad_norm": 0.1266135424375534, "tokens": 191474, "tok_per_s": 187.1818950354158, "t": 1023.55}27{"step": 1200, "loss": 0.40806588530540466, "lr": 0.0007165621699029615, "grad_norm": 0.3347068428993225, "tokens": 200061, "tok_per_s": 188.50317266974437, "t": 1061.94}28{"step": 1250, "loss": 0.3856147825717926, "lr": 0.000693685688561191, "grad_norm": 0.1208675280213356, "tokens": 208455, "tok_per_s": 189.56374981885557, "t": 1100.28}29{"step": 1300, "loss": 0.38933703303337097, "lr": 0.0006703877523381495, "grad_norm": 0.1603798121213913, "tokens": 216814, "tok_per_s": 190.62830745741175, "t": 1137.99}30{"step": 1350, "loss": 0.34210237860679626, "lr": 0.0006467366980949609, "grad_norm": 0.18286241590976715, "tokens": 225136, "tok_per_s": 191.57990034681615, "t": 1175.78}31{"step": 1400, "loss": 0.345404714345932, "lr": 0.0006228018984487442, "grad_norm": 0.11985611170530319, "tokens": 233471, "tok_per_s": 192.3186226890698, "t": 1214.6}32{"step": 1450, "loss": 0.30971866846084595, "lr": 0.0005986535582907738, "grad_norm": 0.11268249154090881, "tokens": 241795, "tok_per_s": 192.9629846001505, "t": 1253.69}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45496321406018975, "val_loss_b2": 0.45169282652815906, "val_loss_b4": 0.45048721768457706, "val_loss_b8": 0.4564763769955398, "t": 1300.15}34{"step": 1500, "loss": 0.3161209523677826, "lr": 0.000574362508863438, "grad_norm": 0.11852918565273285, "tokens": 250085, "tok_per_s": 192.31729117447637, "t": 1301.0}35{"step": 1550, "loss": 0.391324520111084, "lr": 0.00055, "grad_norm": 0.12516531348228455, "tokens": 258187, "tok_per_s": 192.9049769600227, "t": 1339.04}36{"step": 1600, "loss": 0.3599947392940521, "lr": 0.0005256374911365621, "grad_norm": 0.27807214856147766, "tokens": 266247, "tok_per_s": 193.35903938392892, "t": 1377.58}37{"step": 1650, "loss": 0.3111146092414856, "lr": 0.0005013464417092262, "grad_norm": 0.21061010658740997, "tokens": 274738, "tok_per_s": 194.13623316514514, "t": 1415.8}38{"step": 1700, "loss": 0.37696588039398193, "lr": 0.00047719810155125587, "grad_norm": 0.07229266315698624, "tokens": 283093, "tok_per_s": 194.6884837741506, "t": 1454.7}39{"step": 1750, "loss": 0.3832671344280243, "lr": 0.0004532633019050392, "grad_norm": 0.08422736823558807, "tokens": 291261, "tok_per_s": 195.14685483372944, "t": 1493.14}40{"step": 1800, "loss": 0.3942514657974243, "lr": 0.0004296122476618507, "grad_norm": 0.1140027567744255, "tokens": 299555, "tok_per_s": 195.67926658749064, "t": 1531.47}41{"step": 1850, "loss": 0.41107434034347534, "lr": 0.00040631431143880916, "grad_norm": 0.1174962967634201, "tokens": 307521, "tok_per_s": 195.99367405846078, "t": 1569.66}42{"step": 1900, "loss": 0.39733079075813293, "lr": 0.00038343783009703845, "grad_norm": 0.12105542421340942, "tokens": 315892, "tok_per_s": 196.5308373927524, "t": 1607.96}43{"step": 1950, "loss": 0.3482963740825653, "lr": 0.000361049904297881, "grad_norm": 0.07223738729953766, "tokens": 324298, "tok_per_s": 196.99729131352814, "t": 1646.83}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45352128857518137, "val_loss_b2": 0.45063519466093693, "val_loss_b4": 0.4516505170420745, "val_loss_b8": 0.4623401184984473, "t": 1693.11}45{"step": 2000, "loss": 0.28482967615127563, "lr": 0.0003392162016850945, "grad_norm": 0.1879567950963974, "tokens": 332486, "tok_per_s": 196.3597366654131, "t": 1693.87}46{"step": 2050, "loss": 0.45000118017196655, "lr": 0.0003180007642703402, "grad_norm": 0.17789825797080994, "tokens": 340738, "tok_per_s": 196.75505223406296, "t": 1732.41}47{"step": 2100, "loss": 0.37656378746032715, "lr": 0.000297465820586928, "grad_norm": 0.1739136129617691, "tokens": 349148, "tok_per_s": 197.21077279276597, "t": 1771.05}48{"step": 2150, "loss": 0.34364545345306396, "lr": 0.0002776716031628058, "grad_norm": 0.14809828996658325, "tokens": 357576, "tok_per_s": 197.63057294007265, "t": 1809.94}49{"step": 2200, "loss": 0.35878118872642517, "lr": 0.00025867617184817756, "grad_norm": 0.2344849705696106, "tokens": 366097, "tok_per_s": 198.15122138412727, "t": 1848.19}50{"step": 2250, "loss": 0.2842257022857666, "lr": 0.00024053524351595949, "grad_norm": 0.17711761593818665, "tokens": 374285, "tok_per_s": 198.4178496779049, "t": 1886.97}51{"step": 2300, "loss": 0.37554076313972473, "lr": 0.0002233020286345913, "grad_norm": 0.12894129753112793, "tokens": 382864, "tok_per_s": 198.86365428938592, "t": 1925.88}52{"step": 2350, "loss": 0.44722574949264526, "lr": 0.00020702707519256364, "grad_norm": 0.1302153766155243, "tokens": 391427, "tok_per_s": 199.34400535558052, "t": 1964.2}53{"step": 2400, "loss": 0.6251325607299805, "lr": 0.00019175812043246033, "grad_norm": 0.21531735360622406, "tokens": 399797, "tok_per_s": 199.63811879415368, "t": 2003.23}54{"step": 2450, "loss": 0.3431641459465027, "lr": 0.00017753995082939931, "grad_norm": 0.1581304967403412, "tokens": 407948, "tok_per_s": 199.84328105588526, "t": 2041.96}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45283549568698933, "val_loss_b2": 0.44889017653148006, "val_loss_b4": 0.4465542469428877, "val_loss_b8": 0.44887843538587935, "t": 2088.03}56{"step": 2500, "loss": 0.4022432863712311, "lr": 0.00016441427072458494, "grad_norm": 0.17129039764404297, "tokens": 416019, "tok_per_s": 199.2259266364483, "t": 2088.8}57{"step": 2550, "loss": 0.32315266132354736, "lr": 0.0001524195799992897, "grad_norm": 0.13392019271850586, "tokens": 424449, "tok_per_s": 199.63873991732126, "t": 2126.71}58{"step": 2600, "loss": 0.3660646975040436, "lr": 0.0001415910611480694, "grad_norm": 0.1913999319076538, "tokens": 432494, "tok_per_s": 199.8245766378626, "t": 2164.99}59{"step": 2650, "loss": 0.2979769706726074, "lr": 0.00013196047608244387, "grad_norm": 0.161627396941185, "tokens": 440693, "tok_per_s": 200.03758587567327, "t": 2203.67}60{"step": 2700, "loss": 0.4123683571815491, "lr": 0.00012355607296773896, "grad_norm": 0.1975613534450531, "tokens": 449079, "tok_per_s": 200.38045421463764, "t": 2241.75}61{"step": 2750, "loss": 0.3076244592666626, "lr": 0.00011640250336634969, "grad_norm": 0.09679023176431656, "tokens": 457686, "tok_per_s": 200.80783035654713, "t": 2279.85}62{"step": 2800, "loss": 0.41053563356399536, "lr": 0.00011052074993046101, "grad_norm": 0.17802442610263824, "tokens": 466220, "tok_per_s": 201.13883253156507, "t": 2318.52}63{"step": 2850, "loss": 0.476248562335968, "lr": 0.00010592806485631325, "grad_norm": 0.2532316744327545, "tokens": 474198, "tok_per_s": 201.27194241849395, "t": 2356.63}64{"step": 2900, "loss": 0.45045414566993713, "lr": 0.00010263791928053818, "grad_norm": 0.25948673486709595, "tokens": 482297, "tok_per_s": 201.36717706673187, "t": 2395.73}65{"step": 2950, "loss": 0.4043290317058563, "lr": 0.0001006599637669943, "grad_norm": 0.2326698750257492, "tokens": 490516, "tok_per_s": 201.5243624866477, "t": 2434.65}66{"step": 2999, "loss": 0.5114490985870361, "lr": 0.0001000002640500325, "grad_norm": 0.26940447092056274, "tokens": 498543, "tok_per_s": 201.76689788180497, "t": 2471.51}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4512192137197886, "val_loss_b2": 0.4481554496693693, "val_loss_b4": 0.4485814849868556, "val_loss_b8": 0.45539801810515107, "t": 2480.33}68{"step": 2999, "checkpoint_sha256": "a7371f8c402f8a7fd98f784bb1c6750d70ccb46f53060656ba762df1166582b0", "t": 2480.36}69
Files · main
Menu

Theme