SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 3.8388280868530273, "lr": 2.9999999999999997e-06, "grad_norm": 0.16530217230319977, "tokens": 8192, "tok_per_s": 5555.570741903939, "t": 2.33}2{"step": 20, "loss": 3.683028221130371, "lr": 6.299999999999999e-05, "grad_norm": 0.14000000059604645, "tokens": 172032, "tok_per_s": 5153.812067721846, "t": 34.23}3{"step": 40, "loss": 4.018809795379639, "lr": 0.00012299999999999998, "grad_norm": 0.12102383375167847, "tokens": 335872, "tok_per_s": 5114.816955004463, "t": 66.52}4{"step": 60, "loss": 3.8221116065979004, "lr": 0.00018299999999999998, "grad_norm": 0.09996253252029419, "tokens": 499712, "tok_per_s": 4678.3844258352765, "t": 107.67}5{"step": 80, "loss": 3.7520482540130615, "lr": 0.000243, "grad_norm": 0.08119877427816391, "tokens": 663552, "tok_per_s": 4566.69780285139, "t": 146.16}6{"step": 100, "loss": 3.5873820781707764, "lr": 0.0003, "grad_norm": 0.05057114362716675, "tokens": 827392, "tok_per_s": 4404.052739043535, "t": 188.72}7{"step": 120, "loss": 3.880525827407837, "lr": 0.00029996831523249534, "grad_norm": 0.02119096927344799, "tokens": 991232, "tok_per_s": 4411.498032822185, "t": 225.55}8{"step": 140, "loss": 3.784116744995117, "lr": 0.00029987327580293684, "grad_norm": 0.012864955700933933, "tokens": 1155072, "tok_per_s": 4424.064223711705, "t": 261.94}9{"step": 160, "loss": 3.988798141479492, "lr": 0.00029971492632320935, "grad_norm": 0.015187021344900131, "tokens": 1318912, "tok_per_s": 4491.147841157171, "t": 294.52}10{"step": 180, "loss": 3.9943411350250244, "lr": 0.00029949334112318624, "grad_norm": 0.012424705550074577, "tokens": 1482752, "tok_per_s": 4375.225308050471, "t": 339.75}11{"step": 200, "loss": 3.7738120555877686, "lr": 0.00029920862421583855, "grad_norm": 0.015423587523400784, "tokens": 1646592, "tok_per_s": 4316.237828757673, "t": 382.34}12{"step": 220, "loss": 3.86301851272583, "lr": 0.00029886090924841085, "grad_norm": 0.01458093523979187, "tokens": 1810432, "tok_per_s": 4443.7918714043135, "t": 408.26}13{"step": 240, "loss": 3.718639373779297, "lr": 0.00029845035943968696, "grad_norm": 0.010044100694358349, "tokens": 1974272, "tok_per_s": 4483.892496917172, "t": 441.16}14{"step": 260, "loss": 3.63783860206604, "lr": 0.000297977167503374, "grad_norm": 0.01396073866635561, "tokens": 2138112, "tok_per_s": 4543.494007181648, "t": 471.44}15{"step": 280, "loss": 3.697767972946167, "lr": 0.0002974415555576423, "grad_norm": 0.014589798636734486, "tokens": 2301952, "tok_per_s": 4600.971590123155, "t": 501.17}16{"step": 300, "loss": 3.991833209991455, "lr": 0.00029684377502086165, "grad_norm": 0.006617589388042688, "tokens": 2465792, "tok_per_s": 4608.253979077773, "t": 535.93}17{"step": 320, "loss": 3.776200771331787, "lr": 0.0002961841064935852, "grad_norm": 0.009673132561147213, "tokens": 2629632, "tok_per_s": 4661.962361198249, "t": 564.91}18{"step": 340, "loss": 3.804020404815674, "lr": 0.0002954628596268339, "grad_norm": 0.008413425646722317, "tokens": 2793472, "tok_per_s": 4621.8243908042205, "t": 605.26}19{"step": 360, "loss": 3.6039321422576904, "lr": 0.00029468037297674526, "grad_norm": 0.011924357153475285, "tokens": 2957312, "tok_per_s": 4647.944307062156, "t": 637.12}20{"step": 380, "loss": 3.828267812728882, "lr": 0.000293837013845654, "grad_norm": 0.012362201698124409, "tokens": 3121152, "tok_per_s": 4671.112004620043, "t": 669.04}21{"step": 400, "loss": 3.7054331302642822, "lr": 0.0002929331781096783, "grad_norm": 0.013202954083681107, "tokens": 3284992, "tok_per_s": 4690.541827956888, "t": 701.2}22{"step": 420, "loss": 3.8094773292541504, "lr": 0.0002919692900328947, "grad_norm": 0.013429978862404823, "tokens": 3448832, "tok_per_s": 4650.34476065565, "t": 742.48}23{"step": 440, "loss": 3.832529306411743, "lr": 0.00029094580206818636, "grad_norm": 0.015276624821126461, "tokens": 3612672, "tok_per_s": 4700.278107237236, "t": 769.46}24{"step": 460, "loss": 3.6833889484405518, "lr": 0.00028986319464486, "grad_norm": 0.010125985369086266, "tokens": 3776512, "tok_per_s": 4592.850904398649, "t": 823.11}25{"step": 480, "loss": 3.6737911701202393, "lr": 0.0002887219759431305, "grad_norm": 0.013986553996801376, "tokens": 3940352, "tok_per_s": 4586.490897097214, "t": 859.97}26{"step": 499, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9885329008102417, "val_loss_b2": 3.988248109817505, "val_loss_b4": 3.988071346282959, "val_loss_b8": 3.989164853096008, "t": 918.99}27{"step": 500, "loss": 3.585740566253662, "lr": 0.00028752268165557917, "grad_norm": 0.015741195529699326, "tokens": 4104192, "tok_per_s": 4462.758202491632, "t": 920.51}28{"step": 520, "loss": 3.7321407794952393, "lr": 0.00028626587473569746, "grad_norm": 0.009654651395976543, "tokens": 4268032, "tok_per_s": 4392.5144225691865, "t": 972.52}29{"step": 540, "loss": 3.675868511199951, "lr": 0.00028495214513363427, "grad_norm": 0.012084590271115303, "tokens": 4431872, "tok_per_s": 4384.299847761102, "t": 1011.7}30{"step": 560, "loss": 3.8682422637939453, "lr": 0.0002835821095192712, "grad_norm": 0.012979291379451752, "tokens": 4595712, "tok_per_s": 4417.367114475134, "t": 1041.23}31{"step": 580, "loss": 3.8059096336364746, "lr": 0.00028215641099275517, "grad_norm": 0.014583375304937363, "tokens": 4759552, "tok_per_s": 4438.0271035006435, "t": 1073.3}32{"step": 600, "loss": 3.8229777812957764, "lr": 0.00028067571878262454, "grad_norm": 0.017459910362958908, "tokens": 4923392, "tok_per_s": 4466.848177326197, "t": 1103.06}33{"step": 620, "loss": 3.6982314586639404, "lr": 0.00027914072793167077, "grad_norm": 0.015852632001042366, "tokens": 5087232, "tok_per_s": 4492.692840303049, "t": 1133.19}34{"step": 640, "loss": 3.801331043243408, "lr": 0.00027755215897068257, "grad_norm": 0.012572171166539192, "tokens": 5251072, "tok_per_s": 4504.295626018583, "t": 1166.65}35{"step": 660, "loss": 3.7758383750915527, "lr": 0.0002759107575802257, "grad_norm": 0.014323781244456768, "tokens": 5414912, "tok_per_s": 4523.230886119979, "t": 1197.99}36{"step": 680, "loss": 3.9480979442596436, "lr": 0.00027421729424061787, "grad_norm": 0.013456886634230614, "tokens": 5578752, "tok_per_s": 4509.814087492459, "t": 1237.88}37{"step": 700, "loss": 3.779712438583374, "lr": 0.00027247256387026185, "grad_norm": 0.012655014172196388, "tokens": 5742592, "tok_per_s": 4532.351850816981, "t": 1267.88}38{"step": 720, "loss": 3.822575569152832, "lr": 0.000270677385452508, "grad_norm": 0.014358540996909142, "tokens": 5906432, "tok_per_s": 4547.740722835746, "t": 1299.61}39{"step": 740, "loss": 3.7792210578918457, "lr": 0.0002688326016512199, "grad_norm": 0.01548258401453495, "tokens": 6070272, "tok_per_s": 4553.915504804082, "t": 1333.83}40{"step": 760, "loss": 3.806464672088623, "lr": 0.0002669390784152248, "grad_norm": 0.013577770441770554, "tokens": 6234112, "tok_per_s": 4543.631112666273, "t": 1372.91}41{"step": 780, "loss": 3.8274717330932617, "lr": 0.00026499770457183376, "grad_norm": 0.013904247432947159, "tokens": 6397952, "tok_per_s": 4503.13781769418, "t": 1421.63}42{"step": 800, "loss": 3.7019476890563965, "lr": 0.0002630093914096226, "grad_norm": 0.03281262144446373, "tokens": 6561792, "tok_per_s": 4502.10486864367, "t": 1458.35}43{"step": 820, "loss": 3.932710647583008, "lr": 0.0002609750722506695, "grad_norm": 0.0163898766040802, "tokens": 6725632, "tok_per_s": 4502.591980769655, "t": 1494.58}44{"step": 840, "loss": 3.8267409801483154, "lr": 0.00025889570201244967, "grad_norm": 0.015150759369134903, "tokens": 6889472, "tok_per_s": 4514.623144027639, "t": 1526.89}45{"step": 860, "loss": 3.798384189605713, "lr": 0.00025677225675959357, "grad_norm": 0.016737058758735657, "tokens": 7053312, "tok_per_s": 4510.831425955238, "t": 1564.49}46{"step": 880, "loss": 3.679598808288574, "lr": 0.0002546057332457181, "grad_norm": 0.0183124803006649, "tokens": 7217152, "tok_per_s": 4463.914533024111, "t": 1617.63}47{"step": 900, "loss": 3.790926456451416, "lr": 0.00025239714844554667, "grad_norm": 0.014279105700552464, "tokens": 7380992, "tok_per_s": 4490.537276585615, "t": 1644.53}48{"step": 920, "loss": 3.7000484466552734, "lr": 0.00025014753907753737, "grad_norm": 0.01636924408376217, "tokens": 7544832, "tok_per_s": 4499.325213367083, "t": 1677.73}49{"step": 940, "loss": 3.832568645477295, "lr": 0.0002478579611172425, "grad_norm": 0.015563327819108963, "tokens": 7708672, "tok_per_s": 4515.3561128980455, "t": 1708.07}50{"step": 960, "loss": 3.7648119926452637, "lr": 0.0002455294893016306, "grad_norm": 0.014933220110833645, "tokens": 7872512, "tok_per_s": 4532.2022562195925, "t": 1737.87}51{"step": 980, "loss": 3.812920093536377, "lr": 0.00024316321662459957, "grad_norm": 0.01687745936214924, "tokens": 8036352, "tok_per_s": 4546.233485207428, "t": 1768.55}52{"step": 999, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.988364601135254, "val_loss_b2": 3.9879326105117796, "val_loss_b4": 3.987476348876953, "val_loss_b8": 3.9878592252731324, "t": 1836.47}53{"step": 999, "checkpoint_sha256": "d9484ed8cfaee2f2838a7cf1e817d290aa9a8e8ba1bd415bb2d6ab7bf774f7ae", "t": 1836.88}54{"step": 1000, "loss": 3.744023323059082, "lr": 0.0002407602538239216, "grad_norm": 0.01775466836988926, "tokens": 8200192, "tok_per_s": 4462.841607778254, "t": 1838.29}55{"step": 1020, "loss": 3.6456146240234375, "lr": 0.0002383217288598584, "grad_norm": 0.015043514780700207, "tokens": 8364032, "tok_per_s": 4473.138341334909, "t": 1870.69}56{"step": 1040, "loss": 3.8070361614227295, "lr": 0.00023584878638569206, "grad_norm": 0.017470480874180794, "tokens": 8527872, "tok_per_s": 4484.145318430601, "t": 1902.64}57{"step": 1060, "loss": 3.9012932777404785, "lr": 0.00023334258721042025, "grad_norm": 0.017150765284895897, "tokens": 8691712, "tok_per_s": 4489.887152572901, "t": 1936.69}58{"step": 1080, "loss": 3.713714599609375, "lr": 0.00023080430775386808, "grad_norm": 0.0152369299903512, "tokens": 8855552, "tok_per_s": 4483.223476622849, "t": 1976.12}59{"step": 1100, "loss": 3.8825254440307617, "lr": 0.00022823513949447166, "grad_norm": 0.01471775397658348, "tokens": 9019392, "tok_per_s": 4461.2083640179635, "t": 2022.59}60{"step": 1120, "loss": 3.8597702980041504, "lr": 0.00022563628840999367, "grad_norm": 0.020681019872426987, "tokens": 9183232, "tok_per_s": 4460.321539731326, "t": 2059.73}61{"step": 1140, "loss": 3.8525748252868652, "lr": 0.00022300897441143247, "grad_norm": 0.015108371153473854, "tokens": 9347072, "tok_per_s": 4464.914655275153, "t": 2094.3}62{"step": 1160, "loss": 3.6822214126586914, "lr": 0.00022035443077039114, "grad_norm": 0.021639063954353333, "tokens": 9510912, "tok_per_s": 4465.419732137452, "t": 2130.76}63{"step": 1180, "loss": 3.7807776927948, "lr": 0.00021767390354017485, "grad_norm": 0.015806611627340317, "tokens": 9674752, "tok_per_s": 4457.327421713042, "t": 2171.38}64{"step": 1200, "loss": 3.7414073944091797, "lr": 0.00021496865097088845, "grad_norm": 0.016911961138248444, "tokens": 9838592, "tok_per_s": 4427.218627377195, "t": 2223.15}65{"step": 1220, "loss": 3.6769042015075684, "lr": 0.00021223994291880895, "grad_norm": 0.02072557620704174, "tokens": 10002432, "tok_per_s": 4443.716994735264, "t": 2251.77}66{"step": 1240, "loss": 3.855714797973633, "lr": 0.00020948906025030994, "grad_norm": 0.015918290242552757, "tokens": 10166272, "tok_per_s": 4451.796183563373, "t": 2284.49}67{"step": 1260, "loss": 3.812335968017578, "lr": 0.00020671729424061788, "grad_norm": 0.016744321212172508, "tokens": 10330112, "tok_per_s": 4464.24219340855, "t": 2314.82}68{"step": 1280, "loss": 3.8199563026428223, "lr": 0.00020392594596768237, "grad_norm": 0.01638096384704113, "tokens": 10493952, "tok_per_s": 4477.386252961841, "t": 2344.62}69{"step": 1300, "loss": 3.883105516433716, "lr": 0.00020111632570144484, "grad_norm": 0.015294700860977173, "tokens": 10657792, "tok_per_s": 4488.659379768258, "t": 2375.24}70{"step": 1320, "loss": 3.7806808948516846, "lr": 0.00019828975228879288, "grad_norm": 0.01800672523677349, "tokens": 10821632, "tok_per_s": 4497.1409745956535, "t": 2407.19}71{"step": 1340, "loss": 3.943575859069824, "lr": 0.00019544755253448823, "grad_norm": 0.016109060496091843, "tokens": 10985472, "tok_per_s": 4488.721913806638, "t": 2448.2}72{"step": 1360, "loss": 3.810106039047241, "lr": 0.00019259106057835926, "grad_norm": 0.016049453988671303, "tokens": 11149312, "tok_per_s": 4496.089783517685, "t": 2480.63}73{"step": 1380, "loss": 3.831757068634033, "lr": 0.00018972161726905055, "grad_norm": 0.01839154213666916, "tokens": 11313152, "tok_per_s": 4507.67956947905, "t": 2510.6}74{"step": 1400, "loss": 3.8676252365112305, "lr": 0.00018684056953462326, "grad_norm": 0.014575948938727379, "tokens": 11476992, "tok_per_s": 4514.820483486525, "t": 2542.92}75{"step": 1420, "loss": 3.9963245391845703, "lr": 0.00018394926975030145, "grad_norm": 0.018497414886951447, "tokens": 11640832, "tok_per_s": 4508.077077213495, "t": 2583.07}76{"step": 1440, "loss": 3.851541757583618, "lr": 0.00018104907510366235, "grad_norm": 0.017899619415402412, "tokens": 11804672, "tok_per_s": 4518.3079856051445, "t": 2613.48}77{"step": 1460, "loss": 3.8959813117980957, "lr": 0.00017814134695756664, "grad_norm": 0.017883889377117157, "tokens": 11968512, "tok_per_s": 4490.001312349696, "t": 2666.45}78{"step": 1480, "loss": 3.6291708946228027, "lr": 0.00017522745021112944, "grad_norm": 0.01759996823966503, "tokens": 12132352, "tok_per_s": 4495.778668172852, "t": 2699.46}79{"step": 1499, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9881173849105833, "val_loss_b2": 3.987528657913208, "val_loss_b4": 3.9869588375091554, "val_loss_b8": 3.9877641439437865, "t": 2762.58}80{"step": 1500, "loss": 3.90535569190979, "lr": 0.00017230875265903138, "grad_norm": 0.02068295143544674, "tokens": 12296192, "tok_per_s": 4450.055997063979, "t": 2764.01}81{"step": 1520, "loss": 3.7332606315612793, "lr": 0.00016938662434947037, "grad_norm": 0.020495988428592682, "tokens": 12460032, "tok_per_s": 4447.8016000180505, "t": 2802.25}82{"step": 1540, "loss": 3.713611602783203, "lr": 0.0001664624369410554, "grad_norm": 0.023707536980509758, "tokens": 12623872, "tok_per_s": 4421.60151321603, "t": 2855.9}83{"step": 1560, "loss": 3.7561423778533936, "lr": 0.0001635375630589446, "grad_norm": 0.024348311126232147, "tokens": 12787712, "tok_per_s": 4437.488887229454, "t": 2882.6}84{"step": 1580, "loss": 3.717986583709717, "lr": 0.00016061337565052966, "grad_norm": 0.020553236827254295, "tokens": 12951552, "tok_per_s": 4443.512346135477, "t": 2915.56}85{"step": 1600, "loss": 4.001625061035156, "lr": 0.00015769124734096862, "grad_norm": 0.023473521694540977, "tokens": 13115392, "tok_per_s": 4453.408975739985, "t": 2945.88}86{"step": 1620, "loss": 3.767557144165039, "lr": 0.0001547725497888706, "grad_norm": 0.018059588968753815, "tokens": 13279232, "tok_per_s": 4463.92539012233, "t": 2975.64}87{"step": 1640, "loss": 3.778282880783081, "lr": 0.0001518586530424334, "grad_norm": 0.01947772316634655, "tokens": 13443072, "tok_per_s": 4472.883608072359, "t": 3006.31}88{"step": 1660, "loss": 3.89432430267334, "lr": 0.00014895092489633762, "grad_norm": 0.021466944366693497, "tokens": 13606912, "tok_per_s": 4479.628182152929, "t": 3038.36}89{"step": 1680, "loss": 3.732147216796875, "lr": 0.0001460507302496985, "grad_norm": 0.019685208797454834, "tokens": 13770752, "tok_per_s": 4473.219439602959, "t": 3079.34}90{"step": 1700, "loss": 3.5457446575164795, "lr": 0.00014315943046537674, "grad_norm": 0.021686526015400887, "tokens": 13934592, "tok_per_s": 4479.236540919507, "t": 3111.78}91{"step": 1720, "loss": 3.7694344520568848, "lr": 0.00014027838273094942, "grad_norm": 0.016095783561468124, "tokens": 14098432, "tok_per_s": 4488.6670721878445, "t": 3141.75}92{"step": 1740, "loss": 3.877885580062866, "lr": 0.00013740893942164073, "grad_norm": 0.02273871935904026, "tokens": 14262272, "tok_per_s": 4494.629376677128, "t": 3174.03}93{"step": 1760, "loss": 3.595947265625, "lr": 0.00013455244746551177, "grad_norm": 0.02010590210556984, "tokens": 14426112, "tok_per_s": 4496.748110435041, "t": 3208.97}94{"step": 1780, "loss": 3.834798574447632, "lr": 0.00013171024771120715, "grad_norm": 0.018496211618185043, "tokens": 14589952, "tok_per_s": 4497.2367868885385, "t": 3245.06}95{"step": 1800, "loss": 3.7569198608398438, "lr": 0.0001288836742985552, "grad_norm": 0.017011066898703575, "tokens": 14753792, "tok_per_s": 4480.462218534476, "t": 3293.77}96{"step": 1820, "loss": 3.9124388694763184, "lr": 0.00012607405403231763, "grad_norm": 0.01866631768643856, "tokens": 14917632, "tok_per_s": 4479.462464200471, "t": 3331.08}97{"step": 1840, "loss": 3.813666582107544, "lr": 0.00012328270575938212, "grad_norm": 0.021668385714292526, "tokens": 15081472, "tok_per_s": 4485.040926548531, "t": 3363.47}98{"step": 1860, "loss": 3.759260654449463, "lr": 0.00012051093974969008, "grad_norm": 0.02275138534605503, "tokens": 15245312, "tok_per_s": 4485.084879003477, "t": 3399.97}99{"step": 1880, "loss": 3.715264320373535, "lr": 0.00011776005708119105, "grad_norm": 0.019421957433223724, "tokens": 15409152, "tok_per_s": 4490.093760354635, "t": 3432.66}100{"step": 1900, "loss": 3.7311267852783203, "lr": 0.00011503134902911152, "grad_norm": 0.02526695653796196, "tokens": 15572992, "tok_per_s": 4479.445462219193, "t": 3477.4}101{"step": 1920, "loss": 3.9095945358276367, "lr": 0.00011232609645982515, "grad_norm": 0.024148497730493546, "tokens": 15736832, "tok_per_s": 4471.055353422084, "t": 3520.57}102{"step": 1940, "loss": 3.6274752616882324, "lr": 0.00010964556922960883, "grad_norm": 0.020813388749957085, "tokens": 15900672, "tok_per_s": 4482.81961524903, "t": 3547.88}103{"step": 1960, "loss": 3.9998321533203125, "lr": 0.00010699102558856754, "grad_norm": 0.02876809798181057, "tokens": 16064512, "tok_per_s": 4485.545783655364, "t": 3582.25}104{"step": 1980, "loss": 3.557504653930664, "lr": 0.00010436371159000636, "grad_norm": 0.019393693655729294, "tokens": 16228352, "tok_per_s": 4493.9490049562355, "t": 3612.01}105{"step": 1999, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9878397941589356, "val_loss_b2": 3.9870748281478883, "val_loss_b4": 3.986360287666321, "val_loss_b8": 3.98707230091095, "t": 3666.57}106{"step": 1999, "checkpoint_sha256": "61126d1f41c3d4e1c92ee1136a36663df20fa31da9ede0d2bd2fff0de7f35f58", "t": 3667.02}107{"step": 2000, "loss": 3.812525749206543, "lr": 0.00010176486050552833, "grad_norm": 0.0217677503824234, "tokens": 16392192, "tok_per_s": 4467.965500930371, "t": 3669.68}108{"step": 2020, "loss": 3.7536354064941406, "lr": 9.919569224613192e-05, "grad_norm": 0.024728665128350258, "tokens": 16556032, "tok_per_s": 4476.2916397518375, "t": 3699.46}109{"step": 2040, "loss": 3.8425941467285156, "lr": 9.66574127895797e-05, "grad_norm": 0.020093586295843124, "tokens": 16719872, "tok_per_s": 4470.964526245769, "t": 3740.51}110{"step": 2060, "loss": 3.7483816146850586, "lr": 9.415121361430792e-05, "grad_norm": 0.021629303693771362, "tokens": 16883712, "tok_per_s": 4475.814541392472, "t": 3773.06}111{"step": 2080, "loss": 3.8599843978881836, "lr": 9.167827114014155e-05, "grad_norm": 0.020756013691425323, "tokens": 17047552, "tok_per_s": 4483.60948095026, "t": 3803.05}112{"step": 2100, "loss": 3.764911651611328, "lr": 8.92397461760784e-05, "grad_norm": 0.02337750419974327, "tokens": 17211392, "tok_per_s": 4488.301240996396, "t": 3835.58}113{"step": 2120, "loss": 4.088828086853027, "lr": 8.683678337540044e-05, "grad_norm": 0.023548651486635208, "tokens": 17375232, "tok_per_s": 4480.20498913092, "t": 3879.08}114{"step": 2140, "loss": 3.833620548248291, "lr": 8.447051069836941e-05, "grad_norm": 0.0264931321144104, "tokens": 17539072, "tok_per_s": 4487.815032221786, "t": 3909.01}115{"step": 2160, "loss": 3.9101006984710693, "lr": 8.214203888275743e-05, "grad_norm": 0.02647393010556698, "tokens": 17702912, "tok_per_s": 4471.573481150476, "t": 3959.84}116{"step": 2180, "loss": 3.7312822341918945, "lr": 7.985246092246267e-05, "grad_norm": 0.02162903919816017, "tokens": 17866752, "tok_per_s": 4473.032397135901, "t": 3995.18}117{"step": 2200, "loss": 3.8372957706451416, "lr": 7.760285155445326e-05, "grad_norm": 0.02322702668607235, "tokens": 18030592, "tok_per_s": 4476.022609599988, "t": 4029.12}118{"step": 2220, "loss": 4.003998279571533, "lr": 7.53942667542819e-05, "grad_norm": 0.021999096497893333, "tokens": 18194432, "tok_per_s": 4475.795164253909, "t": 4065.93}119{"step": 2240, "loss": 3.845353841781616, "lr": 7.322774324040643e-05, "grad_norm": 0.02525237947702408, "tokens": 18358272, "tok_per_s": 4450.846319413955, "t": 4125.52}120{"step": 2260, "loss": 3.7047626972198486, "lr": 7.11042979875503e-05, "grad_norm": 0.022539757192134857, "tokens": 18522112, "tok_per_s": 4461.855021141051, "t": 4152.07}121{"step": 2280, "loss": 3.5579464435577393, "lr": 6.902492774933048e-05, "grad_norm": 0.02275800332427025, "tokens": 18685952, "tok_per_s": 4473.976878177679, "t": 4177.44}122{"step": 2300, "loss": 3.917072296142578, "lr": 6.699060859037737e-05, "grad_norm": 0.027450494468212128, "tokens": 18849792, "tok_per_s": 4475.6279215284585, "t": 4212.51}123{"step": 2320, "loss": 3.77860164642334, "lr": 6.500229542816624e-05, "grad_norm": 0.02635987289249897, "tokens": 19013632, "tok_per_s": 4483.243541117967, "t": 4241.9}124{"step": 2340, "loss": 3.8698670864105225, "lr": 6.306092158477523e-05, "grad_norm": 0.02103089541196823, "tokens": 19177472, "tok_per_s": 4490.565259161523, "t": 4271.47}125{"step": 2360, "loss": 3.538996696472168, "lr": 6.116739834878009e-05, "grad_norm": 0.027196239680051804, "tokens": 19341312, "tok_per_s": 4495.306164625844, "t": 4303.41}126{"step": 2380, "loss": 3.8050360679626465, "lr": 5.9322614547491995e-05, "grad_norm": 0.02367325685918331, "tokens": 19505152, "tok_per_s": 4500.932601813845, "t": 4334.43}127{"step": 2400, "loss": 3.9583663940429688, "lr": 5.752743612973809e-05, "grad_norm": 0.024019066244363785, "tokens": 19668992, "tok_per_s": 4495.994951515232, "t": 4375.63}128{"step": 2420, "loss": 3.797323226928711, "lr": 5.578270575938211e-05, "grad_norm": 0.022699503228068352, "tokens": 19832832, "tok_per_s": 4499.898642157829, "t": 4408.25}129{"step": 2440, "loss": 3.8363139629364014, "lr": 5.408924241977427e-05, "grad_norm": 0.026374451816082, "tokens": 19996672, "tok_per_s": 4506.4186044389835, "t": 4438.23}130{"step": 2460, "loss": 3.8300018310546875, "lr": 5.244784102931745e-05, "grad_norm": 0.024398434907197952, "tokens": 20160512, "tok_per_s": 4510.375946585783, "t": 4470.66}131{"step": 2480, "loss": 3.7476959228515625, "lr": 5.085927206832921e-05, "grad_norm": 0.04752561077475548, "tokens": 20324352, "tok_per_s": 4502.40608964813, "t": 4514.96}132{"step": 2499, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9876109838485716, "val_loss_b2": 3.9867547750473022, "val_loss_b4": 3.9860803127288817, "val_loss_b8": 3.9870404481887816, "t": 4585.73}133{"step": 2500, "loss": 3.910581588745117, "lr": 4.9324281217375474e-05, "grad_norm": 0.029107971116900444, "tokens": 20488192, "tok_per_s": 4466.885087320102, "t": 4587.54}134{"step": 2520, "loss": 3.935685157775879, "lr": 4.78435890072448e-05, "grad_norm": 0.02710035629570484, "tokens": 20652032, "tok_per_s": 4466.65847609691, "t": 4624.45}135{"step": 2540, "loss": 3.789839267730713, "lr": 4.641789048072876e-05, "grad_norm": 0.021377671509981155, "tokens": 20815872, "tok_per_s": 4470.856416233407, "t": 4656.76}136{"step": 2560, "loss": 3.72589111328125, "lr": 4.504785486636568e-05, "grad_norm": 0.026580851525068283, "tokens": 20979712, "tok_per_s": 4471.037158516677, "t": 4693.21}137{"step": 2580, "loss": 3.7323179244995117, "lr": 4.373412526430252e-05, "grad_norm": 0.023492466658353806, "tokens": 21143552, "tok_per_s": 4471.1057294862485, "t": 4729.78}138{"step": 2600, "loss": 3.9327902793884277, "lr": 4.247731834442082e-05, "grad_norm": 0.02387898974120617, "tokens": 21307392, "tok_per_s": 4452.449317383295, "t": 4786.4}139{"step": 2620, "loss": 3.8893706798553467, "lr": 4.1278024056869486e-05, "grad_norm": 0.022287946194410324, "tokens": 21471232, "tok_per_s": 4461.553316090243, "t": 4813.35}140{"step": 2640, "loss": 3.728363037109375, "lr": 4.013680535514001e-05, "grad_norm": 0.02374396100640297, "tokens": 21635072, "tok_per_s": 4472.0444321199775, "t": 4838.7}141{"step": 2660, "loss": 3.68619441986084, "lr": 3.905419793181364e-05, "grad_norm": 0.0230452548712492, "tokens": 21798912, "tok_per_s": 4473.988572940419, "t": 4873.22}142{"step": 2680, "loss": 3.5850837230682373, "lr": 3.803070996710526e-05, "grad_norm": 0.024549061432480812, "tokens": 21962752, "tok_per_s": 4480.588428195816, "t": 4902.61}143{"step": 2700, "loss": 3.84997820854187, "lr": 3.7066821890321684e-05, "grad_norm": 0.024593722075223923, "tokens": 22126592, "tok_per_s": 4486.424080994401, "t": 4932.75}144{"step": 2720, "loss": 3.8746180534362793, "lr": 3.6162986154346006e-05, "grad_norm": 0.026537152007222176, "tokens": 22290432, "tok_per_s": 4489.576178719199, "t": 4965.78}145{"step": 2740, "loss": 3.584238290786743, "lr": 3.531962702325468e-05, "grad_norm": 0.0271969772875309, "tokens": 22454272, "tok_per_s": 4495.755865530468, "t": 4995.4}146{"step": 2760, "loss": 3.762524127960205, "lr": 3.4537140373166085e-05, "grad_norm": 0.023005293682217598, "tokens": 22618112, "tok_per_s": 4501.789992555519, "t": 5025.1}147{"step": 2780, "loss": 3.71954345703125, "lr": 3.3815893506414745e-05, "grad_norm": 0.023993074893951416, "tokens": 22781952, "tok_per_s": 4507.663435271643, "t": 5054.9}148{"step": 2800, "loss": 3.8339943885803223, "lr": 3.3156224979138305e-05, "grad_norm": 0.024403758347034454, "tokens": 22945792, "tok_per_s": 4514.798911326871, "t": 5083.2}149{"step": 2820, "loss": 3.7308526039123535, "lr": 3.255844444235771e-05, "grad_norm": 0.022225676104426384, "tokens": 23109632, "tok_per_s": 4521.21005386317, "t": 5112.24}150{"step": 2840, "loss": 3.7879652976989746, "lr": 3.202283249662597e-05, "grad_norm": 0.023512132465839386, "tokens": 23273472, "tok_per_s": 4527.090194869152, "t": 5141.79}151{"step": 2860, "loss": 3.8382761478424072, "lr": 3.154964056031306e-05, "grad_norm": 0.024715004488825798, "tokens": 23437312, "tok_per_s": 4533.258005850404, "t": 5170.93}152{"step": 2880, "loss": 3.820117950439453, "lr": 3.113909075158913e-05, "grad_norm": 0.02976880595088005, "tokens": 23601152, "tok_per_s": 4540.142502210738, "t": 5199.18}153{"step": 2900, "loss": 3.740880250930786, "lr": 3.0791375784161455e-05, "grad_norm": 0.02943800948560238, "tokens": 23764992, "tok_per_s": 4545.708717545187, "t": 5228.86}154{"step": 2920, "loss": 3.7544302940368652, "lr": 3.0506658876813734e-05, "grad_norm": 0.026308447122573853, "tokens": 23928832, "tok_per_s": 4551.5054035111825, "t": 5258.2}155{"step": 2940, "loss": 3.797105312347412, "lr": 3.0285073676790606e-05, "grad_norm": 0.024099133908748627, "tokens": 24092672, "tok_per_s": 4557.647528247589, "t": 5287.06}156{"step": 2960, "loss": 3.6772618293762207, "lr": 3.0126724197063143e-05, "grad_norm": 0.024978075176477432, "tokens": 24256512, "tok_per_s": 4563.641464905187, "t": 5316.02}157{"step": 2980, "loss": 3.8443057537078857, "lr": 3.0031684767504643e-05, "grad_norm": 0.02494724839925766, "tokens": 24420352, "tok_per_s": 4568.869186978655, "t": 5345.8}158{"step": 2999, "loss": 3.670595645904541, "lr": 3.0000079215009746e-05, "grad_norm": 0.025034256279468536, "tokens": 24576000, "tok_per_s": 4574.156629459247, "t": 5373.65}159{"step": 2999, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9875057220458983, "val_loss_b2": 3.9866103887557984, "val_loss_b4": 3.985898995399475, "val_loss_b8": 3.986349606513977, "t": 5397.13}160{"step": 2999, "checkpoint_sha256": "1203ea2e786b258268ea56204e9676a6b900d41628d9fce32af5a01ab0181ea3", "t": 5397.54}161
Files · main
Menu

Theme