SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.2574068307876587, "lr": 1e-05, "grad_norm": 0.02281644381582737, "tokens": 146, "tok_per_s": 201.8701259313982, "t": 1.5}2{"step": 50, "loss": 0.29632481932640076, "lr": 0.00051, "grad_norm": 0.019611647352576256, "tokens": 8382, "tok_per_s": 238.8615009625485, "t": 35.87}3{"step": 100, "loss": 0.2928289771080017, "lr": 0.001, "grad_norm": 0.03218043968081474, "tokens": 16548, "tok_per_s": 242.5809658060073, "t": 68.99}4{"step": 150, "loss": 0.27522939443588257, "lr": 0.0009993400362330058, "grad_norm": 0.035960081964731216, "tokens": 24812, "tok_per_s": 245.6446848604652, "t": 101.79}5{"step": 200, "loss": 0.2911725342273712, "lr": 0.0009973620807194618, "grad_norm": 0.03377067297697067, "tokens": 33400, "tok_per_s": 250.01054118680793, "t": 134.37}6{"step": 250, "loss": 0.26847678422927856, "lr": 0.000994071935143687, "grad_norm": 0.024587862193584442, "tokens": 41583, "tok_per_s": 248.14157141989233, "t": 168.36}7{"step": 300, "loss": 0.2520502805709839, "lr": 0.000989479250069539, "grad_norm": 0.02395401895046234, "tokens": 49989, "tok_per_s": 249.9883153529742, "t": 200.74}8{"step": 350, "loss": 0.3760474622249603, "lr": 0.0009835974966336503, "grad_norm": 0.0955885574221611, "tokens": 58214, "tok_per_s": 248.86359307777582, "t": 234.7}9{"step": 400, "loss": 0.2934175729751587, "lr": 0.0009764439270322612, "grad_norm": 0.03379363194108009, "tokens": 66391, "tok_per_s": 249.30502340683375, "t": 267.08}10{"step": 450, "loss": 0.20187416672706604, "lr": 0.0009680395239175562, "grad_norm": 0.05836236849427223, "tokens": 74699, "tok_per_s": 250.12985566998898, "t": 299.42}11{"step": 499, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.41388571598908874, "val_loss_b2": 0.41333505196876014, "val_loss_b4": 0.4130766558257467, "val_loss_b8": 0.4149458404813089, "t": 327.54}12{"step": 500, "loss": 0.3621078431606293, "lr": 0.0009584089388519307, "grad_norm": 0.03487864136695862, "tokens": 83038, "tok_per_s": 253.78134438509935, "t": 327.98}13{"step": 550, "loss": 0.2949325144290924, "lr": 0.0009475804200007103, "grad_norm": 0.039413344115018845, "tokens": 91441, "tok_per_s": 262.07085905576315, "t": 349.69}14{"step": 600, "loss": 0.36860066652297974, "lr": 0.0009355857292754152, "grad_norm": 0.06942126899957657, "tokens": 99553, "tok_per_s": 267.5088516205941, "t": 372.93}15{"step": 650, "loss": 0.3048055171966553, "lr": 0.0009224600491706008, "grad_norm": 0.033525556325912476, "tokens": 107666, "tok_per_s": 264.82925568339476, "t": 407.33}16{"step": 700, "loss": 0.3155032694339752, "lr": 0.0009082418795675396, "grad_norm": 0.035131558775901794, "tokens": 115959, "tok_per_s": 263.3350495385592, "t": 441.13}17{"step": 750, "loss": 0.25763794779777527, "lr": 0.0008929729248074364, "grad_norm": 0.01945130154490471, "tokens": 124302, "tok_per_s": 259.77709879773954, "t": 479.27}18{"step": 800, "loss": 0.34229332208633423, "lr": 0.0008766979713654089, "grad_norm": 0.042905353009700775, "tokens": 132734, "tok_per_s": 252.09902527133045, "t": 527.3}19{"step": 850, "loss": 0.3549925982952118, "lr": 0.0008594647564840406, "grad_norm": 0.06940905004739761, "tokens": 141025, "tok_per_s": 243.66067602748035, "t": 579.56}20{"step": 900, "loss": 0.34444135427474976, "lr": 0.0008413238281518224, "grad_norm": 0.05708182603120804, "tokens": 149035, "tok_per_s": 237.70578563676642, "t": 627.75}21{"step": 950, "loss": 0.3196276128292084, "lr": 0.0008223283968371944, "grad_norm": 0.04837086796760559, "tokens": 157135, "tok_per_s": 234.27442894491801, "t": 671.52}22{"step": 999, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.41292231079373637, "val_loss_b2": 0.4124131649068348, "val_loss_b4": 0.41228707867603953, "val_loss_b8": 0.4145959596222967, "t": 750.59}23{"step": 1000, "loss": 0.3006693422794342, "lr": 0.000802534179413072, "grad_norm": 0.05650242790579796, "tokens": 165602, "tok_per_s": 220.37104848179126, "t": 752.25}24{"step": 1050, "loss": 0.2752276062965393, "lr": 0.0007819992357296598, "grad_norm": 0.10306810587644577, "tokens": 173674, "tok_per_s": 211.8841533546052, "t": 820.45}25{"step": 1100, "loss": 0.24044103920459747, "lr": 0.0007607837983149056, "grad_norm": 0.07654126733541489, "tokens": 181834, "tok_per_s": 204.64523292063996, "t": 889.31}26{"step": 1150, "loss": 0.3453167676925659, "lr": 0.0007389500957021191, "grad_norm": 0.047272052615880966, "tokens": 190158, "tok_per_s": 200.69316957919511, "t": 948.28}27{"step": 1200, "loss": 0.3205467164516449, "lr": 0.0007165621699029615, "grad_norm": 0.07610572874546051, "tokens": 198573, "tok_per_s": 201.2703617479415, "t": 987.38}28{"step": 1250, "loss": 0.3766207695007324, "lr": 0.000693685688561191, "grad_norm": 0.11205436289310455, "tokens": 206880, "tok_per_s": 203.23875172387238, "t": 1018.69}29{"step": 1300, "loss": 0.25073426961898804, "lr": 0.0006703877523381495, "grad_norm": 0.02866116352379322, "tokens": 215095, "tok_per_s": 204.32399051367523, "t": 1053.49}30{"step": 1350, "loss": 0.2750009000301361, "lr": 0.0006467366980949609, "grad_norm": 0.08874290436506271, "tokens": 223349, "tok_per_s": 205.43970213727562, "t": 1087.95}31{"step": 1400, "loss": 0.26846012473106384, "lr": 0.0006228018984487442, "grad_norm": 0.08993160724639893, "tokens": 231716, "tok_per_s": 206.17248491969283, "t": 1124.67}32{"step": 1450, "loss": 0.37126070261001587, "lr": 0.0005986535582907738, "grad_norm": 0.09381195902824402, "tokens": 239960, "tok_per_s": 207.25213909026385, "t": 1158.59}33{"step": 1499, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.4119904505373996, "val_loss_b2": 0.41204987450836317, "val_loss_b4": 0.4140512712997278, "val_loss_b8": 0.4230532341513556, "t": 1196.93}34{"step": 1499, "checkpoint_sha256": "55a327447292a3b40730ece7a3c0c43fd5ac993486438745112a7545e8732f10", "t": 1197.03}35{"step": 1500, "loss": 0.26724329590797424, "lr": 0.000574362508863438, "grad_norm": 0.1111975610256195, "tokens": 248357, "tok_per_s": 207.49581380741336, "t": 1197.7}36{"step": 1550, "loss": 0.3123103976249695, "lr": 0.00055, "grad_norm": 0.09849677979946136, "tokens": 256793, "tok_per_s": 208.68812756438493, "t": 1231.29}37{"step": 1600, "loss": 0.28196197748184204, "lr": 0.0005256374911365621, "grad_norm": 0.08638253062963486, "tokens": 265023, "tok_per_s": 210.5317661187001, "t": 1259.6}38{"step": 1650, "loss": 0.347612589597702, "lr": 0.0005013464417092262, "grad_norm": 0.06267423927783966, "tokens": 273283, "tok_per_s": 212.0269164756034, "t": 1289.68}39{"step": 1700, "loss": 0.3768414855003357, "lr": 0.00047719810155125587, "grad_norm": 0.09401395171880722, "tokens": 281671, "tok_per_s": 213.709111042203, "t": 1318.79}40{"step": 1750, "loss": 0.26761454343795776, "lr": 0.0004532633019050392, "grad_norm": 0.05395130068063736, "tokens": 289799, "tok_per_s": 215.14359839898987, "t": 1347.78}41{"step": 1800, "loss": 0.24711786210536957, "lr": 0.0004296122476618507, "grad_norm": 0.049351055175065994, "tokens": 298140, "tok_per_s": 215.7011592696487, "t": 1382.97}42{"step": 1850, "loss": 0.2801760137081146, "lr": 0.00040631431143880916, "grad_norm": 0.09576767683029175, "tokens": 306518, "tok_per_s": 216.1789281953634, "t": 1418.67}43{"step": 1900, "loss": 0.28702354431152344, "lr": 0.00038343783009703845, "grad_norm": 0.06675335019826889, "tokens": 314885, "tok_per_s": 216.87856589520936, "t": 1452.67}44{"step": 1950, "loss": 0.21578460931777954, "lr": 0.000361049904297881, "grad_norm": 0.0865975022315979, "tokens": 322988, "tok_per_s": 217.08951165753467, "t": 1488.59}45{"step": 1999, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.41191016618068294, "val_loss_b2": 0.4128569975650328, "val_loss_b4": 0.4138939249568673, "val_loss_b8": 0.4240893042282399, "t": 1524.81}46{"step": 2000, "loss": 0.24176457524299622, "lr": 0.0003392162016850945, "grad_norm": 0.09138377755880356, "tokens": 331190, "tok_per_s": 217.25065171432246, "t": 1525.24}47{"step": 2050, "loss": 0.27041375637054443, "lr": 0.0003180007642703402, "grad_norm": 0.12077879160642624, "tokens": 339365, "tok_per_s": 218.53047166446817, "t": 1553.72}48{"step": 2100, "loss": 0.2858930826187134, "lr": 0.000297465820586928, "grad_norm": 0.15457485616207123, "tokens": 347821, "tok_per_s": 219.6558923585326, "t": 1584.26}49{"step": 2150, "loss": 0.2684478759765625, "lr": 0.0002776716031628058, "grad_norm": 0.05642038583755493, "tokens": 355802, "tok_per_s": 220.89252553601239, "t": 1611.52}50{"step": 2200, "loss": 0.2356978803873062, "lr": 0.00025867617184817756, "grad_norm": 0.11221145838499069, "tokens": 363932, "tok_per_s": 221.90883218965223, "t": 1640.78}51{"step": 2250, "loss": 0.23309443891048431, "lr": 0.00024053524351595949, "grad_norm": 0.06473631411790848, "tokens": 372235, "tok_per_s": 222.31644292615823, "t": 1675.12}52{"step": 2300, "loss": 0.27500903606414795, "lr": 0.0002233020286345913, "grad_norm": 0.0791851282119751, "tokens": 380617, "tok_per_s": 222.7510982833804, "t": 1709.49}53{"step": 2350, "loss": 0.20908822119235992, "lr": 0.00020702707519256364, "grad_norm": 0.10462427139282227, "tokens": 388820, "tok_per_s": 223.1480124449076, "t": 1743.21}54{"step": 2400, "loss": 0.18027986586093903, "lr": 0.00019175812043246033, "grad_norm": 0.08221527934074402, "tokens": 397013, "tok_per_s": 223.75909173491473, "t": 1775.07}55{"step": 2450, "loss": 0.3071126937866211, "lr": 0.00017753995082939931, "grad_norm": 0.09175784885883331, "tokens": 405444, "tok_per_s": 224.78321984200625, "t": 1804.49}56{"step": 2499, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.40995508423531746, "val_loss_b2": 0.409993490528033, "val_loss_b4": 0.41109113990817703, "val_loss_b8": 0.4188066938833886, "t": 1841.88}57{"step": 2500, "loss": 0.3278486132621765, "lr": 0.00016441427072458494, "grad_norm": 0.12872454524040222, "tokens": 413920, "tok_per_s": 224.74138191863418, "t": 1842.54}58{"step": 2550, "loss": 0.28487342596054077, "lr": 0.0001524195799992897, "grad_norm": 0.09486062824726105, "tokens": 422230, "tok_per_s": 224.9697021818197, "t": 1877.61}59{"step": 2600, "loss": 0.2684286832809448, "lr": 0.0001415910611480694, "grad_norm": 0.12426797300577164, "tokens": 430404, "tok_per_s": 225.21814513164202, "t": 1911.83}60{"step": 2650, "loss": 0.254168301820755, "lr": 0.00013196047608244387, "grad_norm": 0.16166745126247406, "tokens": 438498, "tok_per_s": 225.3601838181466, "t": 1946.54}61{"step": 2700, "loss": 0.1905134916305542, "lr": 0.00012355607296773896, "grad_norm": 0.07620202749967575, "tokens": 446658, "tok_per_s": 225.86205716807774, "t": 1978.35}62{"step": 2750, "loss": 0.26853248476982117, "lr": 0.00011640250336634969, "grad_norm": 0.13326406478881836, "tokens": 455155, "tok_per_s": 226.83726534529018, "t": 2007.3}63{"step": 2800, "loss": 0.2448510378599167, "lr": 0.00011052074993046101, "grad_norm": 0.10193030536174774, "tokens": 463083, "tok_per_s": 227.6757016091016, "t": 2034.74}64{"step": 2850, "loss": 0.2740918695926666, "lr": 0.00010592806485631325, "grad_norm": 0.17447443306446075, "tokens": 471665, "tok_per_s": 229.09464735586297, "t": 2059.6}65{"step": 2900, "loss": 0.2866029441356659, "lr": 0.00010263791928053818, "grad_norm": 0.12663234770298004, "tokens": 480193, "tok_per_s": 230.46142883895683, "t": 2084.39}66{"step": 2950, "loss": 0.20462633669376373, "lr": 0.0001006599637669943, "grad_norm": 0.06513027101755142, "tokens": 488284, "tok_per_s": 232.0436854411812, "t": 2105.05}67{"step": 2999, "loss": 0.31182020902633667, "lr": 0.0001000002640500325, "grad_norm": 0.07867877185344696, "tokens": 496298, "tok_per_s": 234.06802248820583, "t": 2121.09}68{"step": 2999, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.40932418262090586, "val_loss_b2": 0.4092105990178872, "val_loss_b4": 0.410994329920141, "val_loss_b8": 0.4191988424950156, "t": 2123.99}69{"step": 2999, "checkpoint_sha256": "a1f686a87bcbb5c3da1dbc90e3048b457a7dd541388accedd820e1be47fb21e1", "t": 2124.04}70
Files · 20e88d79efe28fb13610284e7be1ef0ef40c265d
Menu

Theme