SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.41628074645996094, "lr": 1e-05, "grad_norm": 0.09441929310560226, "tokens": 157, "tok_per_s": 76.23368448373806, "t": 2.53}2{"step": 50, "loss": 0.3849809765815735, "lr": 0.00051, "grad_norm": 0.06585487723350525, "tokens": 8616, "tok_per_s": 178.92702301231424, "t": 48.62}3{"step": 100, "loss": 0.40517204999923706, "lr": 0.001, "grad_norm": 0.057480212301015854, "tokens": 16635, "tok_per_s": 181.81339836121228, "t": 91.96}4{"step": 150, "loss": 0.5333823561668396, "lr": 0.0009993400362330058, "grad_norm": 0.02902735397219658, "tokens": 25042, "tok_per_s": 167.2314615914325, "t": 150.21}5{"step": 200, "loss": 0.45932891964912415, "lr": 0.0009973620807194618, "grad_norm": 0.04262002557516098, "tokens": 33661, "tok_per_s": 133.38232732880203, "t": 252.84}6{"step": 250, "loss": 0.4389614164829254, "lr": 0.000994071935143687, "grad_norm": 0.08942517638206482, "tokens": 42410, "tok_per_s": 122.85604897960116, "t": 345.68}7{"step": 300, "loss": 0.40019649267196655, "lr": 0.000989479250069539, "grad_norm": 0.07559962570667267, "tokens": 50771, "tok_per_s": 86.11691710272953, "t": 590.06}8{"step": 350, "loss": 0.41981714963912964, "lr": 0.0009835974966336503, "grad_norm": 0.07638349384069443, "tokens": 59133, "tok_per_s": 84.77426026745736, "t": 698.0}9{"step": 400, "loss": 0.5899505615234375, "lr": 0.0009764439270322612, "grad_norm": 0.08170770853757858, "tokens": 67299, "tok_per_s": 91.50610246962272, "t": 735.93}10{"step": 450, "loss": 0.4660124182701111, "lr": 0.0009680395239175562, "grad_norm": 0.01963513344526291, "tokens": 75575, "tok_per_s": 97.89160269212493, "t": 772.5}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4598086711043146, "val_loss_b2": 0.4581131509749862, "val_loss_b4": 0.45654943155032063, "val_loss_b8": 0.45604746138420876, "t": 811.46}12{"step": 500, "loss": 0.4069359302520752, "lr": 0.0009584089388519307, "grad_norm": 0.06094549596309662, "tokens": 84036, "tok_per_s": 103.1174163252563, "t": 815.42}13{"step": 550, "loss": 0.27935779094696045, "lr": 0.0009475804200007103, "grad_norm": 0.05953722074627876, "tokens": 92359, "tok_per_s": 108.29517887786412, "t": 853.31}14{"step": 600, "loss": 0.3141501545906067, "lr": 0.0009355857292754152, "grad_norm": 0.05040886253118515, "tokens": 100627, "tok_per_s": 113.4706155031016, "t": 887.28}15{"step": 650, "loss": 0.5134652853012085, "lr": 0.0009224600491706008, "grad_norm": 0.057372983545064926, "tokens": 108981, "tok_per_s": 118.26541989413879, "t": 921.96}16{"step": 700, "loss": 0.3943898677825928, "lr": 0.0009082418795675396, "grad_norm": 0.07181911915540695, "tokens": 117352, "tok_per_s": 122.17729868864579, "t": 960.97}17{"step": 750, "loss": 0.5025733113288879, "lr": 0.0008929729248074364, "grad_norm": 0.05662066116929054, "tokens": 125499, "tok_per_s": 125.94347567035993, "t": 996.94}18{"step": 800, "loss": 0.37932491302490234, "lr": 0.0008766979713654089, "grad_norm": 0.04996273294091225, "tokens": 133880, "tok_per_s": 129.79364589560947, "t": 1031.96}19{"step": 850, "loss": 0.4697991609573364, "lr": 0.0008594647564840406, "grad_norm": 0.055067237466573715, "tokens": 142063, "tok_per_s": 133.56002545926628, "t": 1064.13}20{"step": 900, "loss": 0.35059595108032227, "lr": 0.0008413238281518224, "grad_norm": 0.05403149873018265, "tokens": 150436, "tok_per_s": 137.31161130513945, "t": 1096.05}21{"step": 950, "loss": 0.40549370646476746, "lr": 0.0008223283968371944, "grad_norm": 0.06161244958639145, "tokens": 158527, "tok_per_s": 140.32084815858366, "t": 1130.21}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4590382197621187, "val_loss_b2": 0.457376954824599, "val_loss_b4": 0.4583016936563987, "val_loss_b8": 0.4709075619400047, "t": 1162.97}23{"step": 1000, "loss": 0.39927181601524353, "lr": 0.000802534179413072, "grad_norm": 0.16384650766849518, "tokens": 166917, "tok_per_s": 143.23363743111332, "t": 1165.82}24{"step": 1050, "loss": 0.45086076855659485, "lr": 0.0007819992357296598, "grad_norm": 0.08820460736751556, "tokens": 175091, "tok_per_s": 134.22538883524174, "t": 1304.92}25{"step": 1100, "loss": 0.36108672618865967, "lr": 0.0007607837983149056, "grad_norm": 0.08024729043245316, "tokens": 183159, "tok_per_s": 129.37580655129057, "t": 1416.18}26{"step": 1150, "loss": 0.2917662262916565, "lr": 0.0007389500957021191, "grad_norm": 0.07970580458641052, "tokens": 191581, "tok_per_s": 129.12324796178197, "t": 1484.18}27{"step": 1200, "loss": 0.5199249386787415, "lr": 0.0007165621699029615, "grad_norm": 0.08367694169282913, "tokens": 200185, "tok_per_s": 130.2004657543515, "t": 1537.98}28{"step": 1250, "loss": 0.5937767624855042, "lr": 0.000693685688561191, "grad_norm": 0.12493769079446793, "tokens": 208401, "tok_per_s": 132.2752653506699, "t": 1575.98}29{"step": 1300, "loss": 0.42773929238319397, "lr": 0.0006703877523381495, "grad_norm": 0.10414895415306091, "tokens": 216624, "tok_per_s": 131.81521285562764, "t": 1643.86}30{"step": 1350, "loss": 0.5293939709663391, "lr": 0.0006467366980949609, "grad_norm": 0.14718231558799744, "tokens": 225093, "tok_per_s": 134.2808869122232, "t": 1676.75}31{"step": 1400, "loss": 0.40015003085136414, "lr": 0.0006228018984487442, "grad_norm": 0.11198031157255173, "tokens": 233304, "tok_per_s": 129.0880198822577, "t": 1807.79}32{"step": 1450, "loss": 0.40849366784095764, "lr": 0.0005986535582907738, "grad_norm": 0.13696350157260895, "tokens": 241497, "tok_per_s": 131.77192598779104, "t": 1833.16}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4587571796024298, "val_loss_b2": 0.4560935526660301, "val_loss_b4": 0.4532689535893966, "val_loss_b8": 0.4521760042810041, "t": 2029.15}34{"step": 1500, "loss": 0.4508856534957886, "lr": 0.000574362508863438, "grad_norm": 0.1173471063375473, "tokens": 249582, "tok_per_s": 122.9812705936426, "t": 2029.9}35{"step": 1550, "loss": 0.32820817828178406, "lr": 0.00055, "grad_norm": 0.05806326866149902, "tokens": 257750, "tok_per_s": 124.86232819496398, "t": 2064.74}36{"step": 1600, "loss": 0.43102556467056274, "lr": 0.0005256374911365621, "grad_norm": 0.18208174407482147, "tokens": 266068, "tok_per_s": 126.73265083347641, "t": 2099.91}37{"step": 1650, "loss": 0.46742770075798035, "lr": 0.0005013464417092262, "grad_norm": 0.15524812042713165, "tokens": 274463, "tok_per_s": 128.63472462211854, "t": 2134.14}38{"step": 1700, "loss": 0.3101527690887451, "lr": 0.00047719810155125587, "grad_norm": 0.12821900844573975, "tokens": 282527, "tok_per_s": 130.41887452236182, "t": 2166.78}39{"step": 1750, "loss": 0.4640965163707733, "lr": 0.0004532633019050392, "grad_norm": 0.15198944509029388, "tokens": 290793, "tok_per_s": 132.19487638182403, "t": 2200.2}40{"step": 1800, "loss": 0.4189888536930084, "lr": 0.0004296122476618507, "grad_norm": 0.08550280332565308, "tokens": 299230, "tok_per_s": 134.05332625864432, "t": 2232.64}41{"step": 1850, "loss": 0.38966259360313416, "lr": 0.00040631431143880916, "grad_norm": 0.08842860162258148, "tokens": 307566, "tok_per_s": 135.6854165192611, "t": 2267.23}42{"step": 1900, "loss": 0.39895954728126526, "lr": 0.00038343783009703845, "grad_norm": 0.0926157757639885, "tokens": 315780, "tok_per_s": 137.2314381149405, "t": 2301.54}43{"step": 1950, "loss": 0.4174782931804657, "lr": 0.000361049904297881, "grad_norm": 0.14346063137054443, "tokens": 324229, "tok_per_s": 138.98119411956768, "t": 2333.37}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45646335363035545, "val_loss_b2": 0.4533683293673016, "val_loss_b4": 0.452160370414512, "val_loss_b8": 0.4597365565932167, "t": 2373.09}45{"step": 2000, "loss": 0.46434611082077026, "lr": 0.0003392162016850945, "grad_norm": 0.10196118801832199, "tokens": 332550, "tok_per_s": 140.12519101506717, "t": 2373.7}46{"step": 2050, "loss": 0.5134860873222351, "lr": 0.0003180007642703402, "grad_norm": 0.14082075655460358, "tokens": 340880, "tok_per_s": 141.75737318234087, "t": 2405.14}47{"step": 2100, "loss": 0.3075798451900482, "lr": 0.000297465820586928, "grad_norm": 0.1813054382801056, "tokens": 349421, "tok_per_s": 143.30923109742986, "t": 2438.7}48{"step": 2150, "loss": 0.4070427715778351, "lr": 0.0002776716031628058, "grad_norm": 0.11349090933799744, "tokens": 357735, "tok_per_s": 144.7719233751314, "t": 2471.49}49{"step": 2200, "loss": 0.4638199508190155, "lr": 0.00025867617184817756, "grad_norm": 0.16088604927062988, "tokens": 366168, "tok_per_s": 146.19060647914947, "t": 2505.21}50{"step": 2250, "loss": 0.37473154067993164, "lr": 0.00024053524351595949, "grad_norm": 0.1478862762451172, "tokens": 374489, "tok_per_s": 147.59200227975717, "t": 2537.79}51{"step": 2300, "loss": 0.3179093301296234, "lr": 0.0002233020286345913, "grad_norm": 0.10336705297231674, "tokens": 382832, "tok_per_s": 148.81621483978682, "t": 2572.98}52{"step": 2350, "loss": 0.5466263294219971, "lr": 0.00020702707519256364, "grad_norm": 0.10759564489126205, "tokens": 391097, "tok_per_s": 150.15389057333724, "t": 2605.11}53{"step": 2400, "loss": 0.28178325295448303, "lr": 0.00019175812043246033, "grad_norm": 0.1071697473526001, "tokens": 399648, "tok_per_s": 151.4713617930621, "t": 2638.91}54{"step": 2450, "loss": 0.35788118839263916, "lr": 0.00017753995082939931, "grad_norm": 0.11532649397850037, "tokens": 407914, "tok_per_s": 152.52543818331955, "t": 2674.87}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.454885331441053, "val_loss_b2": 0.45128242601720847, "val_loss_b4": 0.4493378610549859, "val_loss_b8": 0.45634948143881493, "t": 2715.39}56{"step": 2500, "loss": 0.25389036536216736, "lr": 0.00016441427072458494, "grad_norm": 0.08990485966205597, "tokens": 416524, "tok_per_s": 153.37934494595504, "t": 2716.11}57{"step": 2550, "loss": 0.3264312446117401, "lr": 0.0001524195799992897, "grad_norm": 0.08565962314605713, "tokens": 424563, "tok_per_s": 154.41249769889347, "t": 2750.01}58{"step": 2600, "loss": 0.28204038739204407, "lr": 0.0001415910611480694, "grad_norm": 0.12292370945215225, "tokens": 432991, "tok_per_s": 155.58141120006212, "t": 2783.52}59{"step": 2650, "loss": 0.39607131481170654, "lr": 0.00013196047608244387, "grad_norm": 0.1578507125377655, "tokens": 441165, "tok_per_s": 156.63446713405443, "t": 2816.99}60{"step": 2700, "loss": 0.35214802622795105, "lr": 0.00012355607296773896, "grad_norm": 0.05702836439013481, "tokens": 449578, "tok_per_s": 157.78197134324517, "t": 2849.83}61{"step": 2750, "loss": 0.37589535117149353, "lr": 0.00011640250336634969, "grad_norm": 0.19739776849746704, "tokens": 457759, "tok_per_s": 158.74368095093567, "t": 2884.1}62{"step": 2800, "loss": 0.37203744053840637, "lr": 0.00011052074993046101, "grad_norm": 0.11156265437602997, "tokens": 465905, "tok_per_s": 159.81425264540462, "t": 2915.76}63{"step": 2850, "loss": 0.41233229637145996, "lr": 0.00010592806485631325, "grad_norm": 0.2024451345205307, "tokens": 474059, "tok_per_s": 160.80802583226986, "t": 2948.45}64{"step": 2900, "loss": 0.5339433550834656, "lr": 0.00010263791928053818, "grad_norm": 0.1096133142709732, "tokens": 482466, "tok_per_s": 161.8589674874603, "t": 2981.25}65{"step": 2950, "loss": 0.37303152680397034, "lr": 0.0001006599637669943, "grad_norm": 0.13276389241218567, "tokens": 490971, "tok_per_s": 162.8636104627615, "t": 3015.08}66{"step": 2999, "loss": 0.3692943751811981, "lr": 0.0001000002640500325, "grad_norm": 0.17356663942337036, "tokens": 499017, "tok_per_s": 163.69406469855696, "t": 3048.94}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4534133800207658, "val_loss_b2": 0.44958524671077965, "val_loss_b4": 0.44851532847262066, "val_loss_b8": 0.4585513466975559, "t": 3055.98}68{"step": 2999, "checkpoint_sha256": "3c18bd5fb450697410ab4a3a49556d8e371249f9afa443ef96f8cd91e3a0ceb6", "t": 3056.05}69
Files · main
Menu

Theme