SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.4976329803466797, "lr": 1e-05, "grad_norm": 0.22238093614578247, "tokens": 163, "tok_per_s": 84.61194668421103, "t": 4.6}2{"step": 50, "loss": 0.393350750207901, "lr": 0.00051, "grad_norm": 0.12063182145357132, "tokens": 8255, "tok_per_s": 393.4001218604864, "t": 23.66}3{"step": 100, "loss": 0.32887032628059387, "lr": 0.001, "grad_norm": 0.12225979566574097, "tokens": 16571, "tok_per_s": 425.77115276351276, "t": 41.59}4{"step": 150, "loss": 0.49287304282188416, "lr": 0.0009993400362330058, "grad_norm": 0.06844253838062286, "tokens": 25277, "tok_per_s": 442.711811480207, "t": 59.77}5{"step": 200, "loss": 0.5539912581443787, "lr": 0.0009973620807194618, "grad_norm": 0.04587992653250694, "tokens": 33752, "tok_per_s": 448.5288613758638, "t": 77.92}6{"step": 250, "loss": 0.3975309729576111, "lr": 0.000994071935143687, "grad_norm": 0.17492030560970306, "tokens": 41944, "tok_per_s": 449.3454260421667, "t": 96.02}7{"step": 300, "loss": 0.5402591824531555, "lr": 0.000989479250069539, "grad_norm": 0.08958450704813004, "tokens": 49880, "tok_per_s": 446.9670707703846, "t": 114.27}8{"step": 350, "loss": 0.37288999557495117, "lr": 0.0009835974966336503, "grad_norm": 0.08096161484718323, "tokens": 58163, "tok_per_s": 447.738754539614, "t": 132.58}9{"step": 400, "loss": 0.5008520483970642, "lr": 0.0009764439270322612, "grad_norm": 0.05884331092238426, "tokens": 66164, "tok_per_s": 447.1194584487338, "t": 150.65}10{"step": 450, "loss": 0.3860907256603241, "lr": 0.0009680395239175562, "grad_norm": 0.047043610364198685, "tokens": 74558, "tok_per_s": 447.9750347886294, "t": 169.11}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.460943504999047, "val_loss_b2": 0.45998056279197, "val_loss_b4": 0.46146853443670294, "val_loss_b8": 0.46851102961525654, "t": 192.06}12{"step": 500, "loss": 0.47134503722190857, "lr": 0.0009584089388519307, "grad_norm": 0.1635056585073471, "tokens": 82715, "tok_per_s": 435.9865188054314, "t": 192.39}13{"step": 550, "loss": 0.4755559265613556, "lr": 0.0009475804200007103, "grad_norm": 0.07261548191308975, "tokens": 91267, "tok_per_s": 441.151159636114, "t": 209.56}14{"step": 600, "loss": 0.32549944519996643, "lr": 0.0009355857292754152, "grad_norm": 0.15958034992218018, "tokens": 99524, "tok_per_s": 452.22242853377946, "t": 222.75}15{"step": 650, "loss": 0.427525132894516, "lr": 0.0009224600491706008, "grad_norm": 0.12561847269535065, "tokens": 107970, "tok_per_s": 462.96403318396017, "t": 235.89}16{"step": 700, "loss": 0.4624163806438446, "lr": 0.0009082418795675396, "grad_norm": 0.1625501960515976, "tokens": 116272, "tok_per_s": 472.1454317724133, "t": 248.93}17{"step": 750, "loss": 0.4421165883541107, "lr": 0.0008929729248074364, "grad_norm": 0.055073559284210205, "tokens": 124586, "tok_per_s": 480.1161781433963, "t": 262.16}18{"step": 800, "loss": 0.3564184904098511, "lr": 0.0008766979713654089, "grad_norm": 0.069588303565979, "tokens": 132471, "tok_per_s": 485.7095591876277, "t": 275.41}19{"step": 850, "loss": 0.4399373233318329, "lr": 0.0008594647564840406, "grad_norm": 0.048798490315675735, "tokens": 140749, "tok_per_s": 492.74489357477717, "t": 288.31}20{"step": 900, "loss": 0.2871304750442505, "lr": 0.0008413238281518224, "grad_norm": 0.08208801597356796, "tokens": 149107, "tok_per_s": 498.805048648141, "t": 301.6}21{"step": 950, "loss": 0.36441102623939514, "lr": 0.0008223283968371944, "grad_norm": 0.10770761966705322, "tokens": 157427, "tok_per_s": 504.579079056027, "t": 314.67}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45901470174925735, "val_loss_b2": 0.4565359062018096, "val_loss_b4": 0.45642252753320267, "val_loss_b8": 0.46655843479989373, "t": 331.05}23{"step": 1000, "loss": 0.4136921167373657, "lr": 0.000802534179413072, "grad_norm": 0.1121366024017334, "tokens": 165723, "tok_per_s": 504.29055672483537, "t": 331.3}24{"step": 1050, "loss": 0.38944146037101746, "lr": 0.0007819992357296598, "grad_norm": 0.12471265345811844, "tokens": 173820, "tok_per_s": 508.66829555000487, "t": 344.39}25{"step": 1100, "loss": 0.34300392866134644, "lr": 0.0007607837983149056, "grad_norm": 0.07694360613822937, "tokens": 182174, "tok_per_s": 513.3970568854626, "t": 357.51}26{"step": 1150, "loss": 0.43103283643722534, "lr": 0.0007389500957021191, "grad_norm": 0.11248519271612167, "tokens": 190590, "tok_per_s": 516.8553223621121, "t": 371.42}27{"step": 1200, "loss": 0.33171379566192627, "lr": 0.0007165621699029615, "grad_norm": 0.10738139599561691, "tokens": 198577, "tok_per_s": 521.8406337951326, "t": 383.2}28{"step": 1250, "loss": 0.34989044070243835, "lr": 0.000693685688561191, "grad_norm": 0.1391138732433319, "tokens": 206821, "tok_per_s": 527.4995280793381, "t": 394.75}29{"step": 1300, "loss": 0.4434140920639038, "lr": 0.0006703877523381495, "grad_norm": 0.07076703011989594, "tokens": 214819, "tok_per_s": 532.2010063807521, "t": 406.31}30{"step": 1350, "loss": 0.4238818883895874, "lr": 0.0006467366980949609, "grad_norm": 0.1108204573392868, "tokens": 222971, "tok_per_s": 537.0990517879787, "t": 417.81}31{"step": 1400, "loss": 0.3878036439418793, "lr": 0.0006228018984487442, "grad_norm": 0.06963787227869034, "tokens": 231317, "tok_per_s": 542.2675010833291, "t": 429.25}32{"step": 1450, "loss": 0.5305743217468262, "lr": 0.0005986535582907738, "grad_norm": 0.12191683799028397, "tokens": 239557, "tok_per_s": 546.6931289992312, "t": 440.86}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4570688404667959, "val_loss_b2": 0.4542083796636996, "val_loss_b4": 0.45302422543709475, "val_loss_b8": 0.46362494294310863, "t": 454.98}34{"step": 1500, "loss": 0.4861062467098236, "lr": 0.000574362508863438, "grad_norm": 0.12572044134140015, "tokens": 247607, "tok_per_s": 547.1369919490667, "t": 455.22}35{"step": 1550, "loss": 0.4167870581150055, "lr": 0.00055, "grad_norm": 0.22349806129932404, "tokens": 256272, "tok_per_s": 552.0812870285318, "t": 466.86}36{"step": 1600, "loss": 0.3853699862957001, "lr": 0.0005256374911365621, "grad_norm": 0.1026955395936966, "tokens": 264490, "tok_per_s": 555.8905913432582, "t": 478.47}37{"step": 1650, "loss": 0.3469164967536926, "lr": 0.0005013464417092262, "grad_norm": 0.13878987729549408, "tokens": 272714, "tok_per_s": 559.6118275612525, "t": 490.0}38{"step": 1700, "loss": 0.5522928237915039, "lr": 0.00047719810155125587, "grad_norm": 0.12124762684106827, "tokens": 280990, "tok_per_s": 563.1004586217838, "t": 501.68}39{"step": 1750, "loss": 0.4049311578273773, "lr": 0.0004532633019050392, "grad_norm": 0.1389528065919876, "tokens": 289345, "tok_per_s": 566.4312742629755, "t": 513.49}40{"step": 1800, "loss": 0.26083695888519287, "lr": 0.0004296122476618507, "grad_norm": 0.06856448948383331, "tokens": 297639, "tok_per_s": 569.686621044419, "t": 525.13}41{"step": 1850, "loss": 0.4003559350967407, "lr": 0.00040631431143880916, "grad_norm": 0.18578925728797913, "tokens": 305990, "tok_per_s": 572.7902641944992, "t": 536.88}42{"step": 1900, "loss": 0.29872119426727295, "lr": 0.00038343783009703845, "grad_norm": 0.12418847531080246, "tokens": 313976, "tok_per_s": 575.2914446100954, "t": 548.44}43{"step": 1950, "loss": 0.3592284023761749, "lr": 0.000361049904297881, "grad_norm": 0.08927774429321289, "tokens": 322226, "tok_per_s": 578.1103338419928, "t": 560.05}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4555240629223428, "val_loss_b2": 0.45274437443266485, "val_loss_b4": 0.45268278935086026, "val_loss_b8": 0.46107708896657645, "t": 574.22}45{"step": 2000, "loss": 0.3748653829097748, "lr": 0.0003392162016850945, "grad_norm": 0.14531075954437256, "tokens": 330697, "tok_per_s": 578.369695326598, "t": 574.45}46{"step": 2050, "loss": 0.4355790615081787, "lr": 0.0003180007642703402, "grad_norm": 0.09180943667888641, "tokens": 338821, "tok_per_s": 580.9159944745809, "t": 585.92}47{"step": 2100, "loss": 0.4499213397502899, "lr": 0.000297465820586928, "grad_norm": 0.11612505465745926, "tokens": 347181, "tok_per_s": 583.5497711926873, "t": 597.62}48{"step": 2150, "loss": 0.43951940536499023, "lr": 0.0002776716031628058, "grad_norm": 0.10938943922519684, "tokens": 355319, "tok_per_s": 585.7958879627946, "t": 609.23}49{"step": 2200, "loss": 0.36023643612861633, "lr": 0.00025867617184817756, "grad_norm": 0.07697799056768417, "tokens": 363537, "tok_per_s": 588.3555876687608, "t": 620.56}50{"step": 2250, "loss": 0.4750427305698395, "lr": 0.00024053524351595949, "grad_norm": 0.16163936257362366, "tokens": 371638, "tok_per_s": 590.2718894867074, "t": 632.28}51{"step": 2300, "loss": 0.33048737049102783, "lr": 0.0002233020286345913, "grad_norm": 0.1482601910829544, "tokens": 379727, "tok_per_s": 592.3218344205422, "t": 643.75}52{"step": 2350, "loss": 0.3855617940425873, "lr": 0.00020702707519256364, "grad_norm": 0.13034561276435852, "tokens": 388116, "tok_per_s": 594.6298999511741, "t": 655.37}53{"step": 2400, "loss": 0.2776845693588257, "lr": 0.00019175812043246033, "grad_norm": 0.15028749406337738, "tokens": 396308, "tok_per_s": 596.622382836719, "t": 666.92}54{"step": 2450, "loss": 0.39043331146240234, "lr": 0.00017753995082939931, "grad_norm": 0.17181925475597382, "tokens": 404717, "tok_per_s": 598.8408547269553, "t": 678.51}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45477955020549204, "val_loss_b2": 0.4509135867175708, "val_loss_b4": 0.4491357244018735, "val_loss_b8": 0.4568491146563309, "t": 692.6}56{"step": 2500, "loss": 0.4794559180736542, "lr": 0.00016441427072458494, "grad_norm": 0.1502954512834549, "tokens": 413027, "tok_per_s": 598.4870681200077, "t": 692.79}57{"step": 2550, "loss": 0.44730380177497864, "lr": 0.0001524195799992897, "grad_norm": 0.13818083703517914, "tokens": 421798, "tok_per_s": 601.0942805065821, "t": 704.39}58{"step": 2600, "loss": 0.3003736734390259, "lr": 0.0001415910611480694, "grad_norm": 0.16183654963970184, "tokens": 430295, "tok_per_s": 603.2339191920843, "t": 715.99}59{"step": 2650, "loss": 0.4860246479511261, "lr": 0.00013196047608244387, "grad_norm": 0.15019167959690094, "tokens": 438698, "tok_per_s": 605.2928798280242, "t": 727.44}60{"step": 2700, "loss": 0.4426535964012146, "lr": 0.00012355607296773896, "grad_norm": 0.16043521463871002, "tokens": 447187, "tok_per_s": 607.1716815993683, "t": 739.18}61{"step": 2750, "loss": 0.3921026587486267, "lr": 0.00011640250336634969, "grad_norm": 0.13376887142658234, "tokens": 455379, "tok_per_s": 608.7265928383379, "t": 750.76}62{"step": 2800, "loss": 0.4261237382888794, "lr": 0.00011052074993046101, "grad_norm": 0.1602645069360733, "tokens": 463791, "tok_per_s": 610.5258934800445, "t": 762.33}63{"step": 2850, "loss": 0.4478849768638611, "lr": 0.00010592806485631325, "grad_norm": 0.19411280751228333, "tokens": 472187, "tok_per_s": 612.157583824913, "t": 774.02}64{"step": 2900, "loss": 0.44169315695762634, "lr": 0.00010263791928053818, "grad_norm": 0.23864154517650604, "tokens": 480621, "tok_per_s": 614.0195706886982, "t": 785.42}65{"step": 2950, "loss": 0.3378205895423889, "lr": 0.0001006599637669943, "grad_norm": 0.13967959582805634, "tokens": 488878, "tok_per_s": 615.4441163307799, "t": 797.02}66{"step": 2999, "loss": 0.3887619972229004, "lr": 0.0001000002640500325, "grad_norm": 0.1735013872385025, "tokens": 497078, "tok_per_s": 617.0508431265438, "t": 808.24}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4529955823060737, "val_loss_b2": 0.44925534966075403, "val_loss_b4": 0.447848415421758, "val_loss_b8": 0.4567291500416808, "t": 811.12}68{"step": 2999, "checkpoint_sha256": "1a62de8a37bc40aa10e76c5a32052b4ad3638b4527a737a8b4d5c5d0460b44c2", "t": 811.16}69
Files · main
Menu

Theme