{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.989841527834214, "eval_steps": 500, "global_step": 1535, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.016253555465258026, "grad_norm": 2.077186346054077, "learning_rate": 4.9998691031433496e-05, "loss": 2.8778, "step": 5 }, { "epoch": 0.03250711093051605, "grad_norm": 2.073504686355591, "learning_rate": 4.999476426280588e-05, "loss": 2.6432, "step": 10 }, { "epoch": 0.048760666395774074, "grad_norm": 2.1281931400299072, "learning_rate": 4.998822010531848e-05, "loss": 2.3167, "step": 15 }, { "epoch": 0.0650142218610321, "grad_norm": 1.090219497680664, "learning_rate": 4.997905924425903e-05, "loss": 2.1533, "step": 20 }, { "epoch": 0.08126777732629012, "grad_norm": 1.007896900177002, "learning_rate": 4.996728263892985e-05, "loss": 2.0267, "step": 25 }, { "epoch": 0.09752133279154815, "grad_norm": 0.9982665777206421, "learning_rate": 4.995289152254744e-05, "loss": 1.9352, "step": 30 }, { "epoch": 0.11377488825680618, "grad_norm": 0.8844298720359802, "learning_rate": 4.9935887402113315e-05, "loss": 1.9486, "step": 35 }, { "epoch": 0.1300284437220642, "grad_norm": 0.9337536692619324, "learning_rate": 4.991627205825621e-05, "loss": 1.9228, "step": 40 }, { "epoch": 0.14628199918732224, "grad_norm": 0.9377800822257996, "learning_rate": 4.9894047545045605e-05, "loss": 1.835, "step": 45 }, { "epoch": 0.16253555465258024, "grad_norm": 0.8525241017341614, "learning_rate": 4.986921618977664e-05, "loss": 1.8157, "step": 50 }, { "epoch": 0.17878911011783827, "grad_norm": 0.872871458530426, "learning_rate": 4.984178059272638e-05, "loss": 1.8811, "step": 55 }, { "epoch": 0.1950426655830963, "grad_norm": 0.9125804305076599, "learning_rate": 4.981174362688158e-05, "loss": 1.8242, "step": 60 }, { "epoch": 0.21129622104835433, "grad_norm": 0.7474733591079712, "learning_rate": 4.977910843763777e-05, "loss": 1.7808, "step": 65 }, { "epoch": 0.22754977651361236, "grad_norm": 1.0248199701309204, "learning_rate": 4.974387844246987e-05, "loss": 1.8512, "step": 70 }, { "epoch": 0.24380333197887039, "grad_norm": 0.9032835960388184, "learning_rate": 4.970605733057441e-05, "loss": 1.8172, "step": 75 }, { "epoch": 0.2600568874441284, "grad_norm": 0.8550340533256531, "learning_rate": 4.9665649062483115e-05, "loss": 1.7418, "step": 80 }, { "epoch": 0.27631044290938644, "grad_norm": 0.9429016709327698, "learning_rate": 4.96226578696482e-05, "loss": 1.8265, "step": 85 }, { "epoch": 0.2925639983746445, "grad_norm": 0.975885272026062, "learning_rate": 4.957708825399927e-05, "loss": 1.7943, "step": 90 }, { "epoch": 0.3088175538399025, "grad_norm": 0.827629804611206, "learning_rate": 4.9528944987471884e-05, "loss": 1.8067, "step": 95 }, { "epoch": 0.3250711093051605, "grad_norm": 1.0019093751907349, "learning_rate": 4.9478233111507856e-05, "loss": 1.7874, "step": 100 }, { "epoch": 0.3413246647704185, "grad_norm": 1.0811312198638916, "learning_rate": 4.9424957936527295e-05, "loss": 1.7395, "step": 105 }, { "epoch": 0.35757822023567654, "grad_norm": 0.9461565613746643, "learning_rate": 4.936912504137257e-05, "loss": 1.7833, "step": 110 }, { "epoch": 0.37383177570093457, "grad_norm": 1.0386009216308594, "learning_rate": 4.9310740272724055e-05, "loss": 1.7569, "step": 115 }, { "epoch": 0.3900853311661926, "grad_norm": 0.9916568994522095, "learning_rate": 4.924980974448791e-05, "loss": 1.7584, "step": 120 }, { "epoch": 0.4063388866314506, "grad_norm": 1.240400791168213, "learning_rate": 4.918633983715581e-05, "loss": 1.7438, "step": 125 }, { "epoch": 0.42259244209670865, "grad_norm": 1.1441287994384766, "learning_rate": 4.912033719713687e-05, "loss": 1.7046, "step": 130 }, { "epoch": 0.4388459975619667, "grad_norm": 1.1687984466552734, "learning_rate": 4.905180873606157e-05, "loss": 1.738, "step": 135 }, { "epoch": 0.4550995530272247, "grad_norm": 0.9126319885253906, "learning_rate": 4.8980761630058014e-05, "loss": 1.7738, "step": 140 }, { "epoch": 0.47135310849248274, "grad_norm": 1.172781229019165, "learning_rate": 4.8907203319000495e-05, "loss": 1.6642, "step": 145 }, { "epoch": 0.48760666395774077, "grad_norm": 1.1217776536941528, "learning_rate": 4.883114150573037e-05, "loss": 1.7359, "step": 150 }, { "epoch": 0.5038602194229987, "grad_norm": 1.1024829149246216, "learning_rate": 4.8752584155249444e-05, "loss": 1.6707, "step": 155 }, { "epoch": 0.5201137748882568, "grad_norm": 1.042017936706543, "learning_rate": 4.8671539493885934e-05, "loss": 1.709, "step": 160 }, { "epoch": 0.5363673303535148, "grad_norm": 1.1834771633148193, "learning_rate": 4.8588016008432945e-05, "loss": 1.7282, "step": 165 }, { "epoch": 0.5526208858187729, "grad_norm": 1.0311099290847778, "learning_rate": 4.850202244525987e-05, "loss": 1.774, "step": 170 }, { "epoch": 0.5688744412840309, "grad_norm": 1.2995566129684448, "learning_rate": 4.8413567809396376e-05, "loss": 1.714, "step": 175 }, { "epoch": 0.585127996749289, "grad_norm": 1.23491370677948, "learning_rate": 4.8322661363589507e-05, "loss": 1.7717, "step": 180 }, { "epoch": 0.6013815522145469, "grad_norm": 1.1809489727020264, "learning_rate": 4.822931262733367e-05, "loss": 1.722, "step": 185 }, { "epoch": 0.617635107679805, "grad_norm": 0.988572359085083, "learning_rate": 4.813353137587377e-05, "loss": 1.7007, "step": 190 }, { "epoch": 0.633888663145063, "grad_norm": 1.0803310871124268, "learning_rate": 4.803532763918162e-05, "loss": 1.6824, "step": 195 }, { "epoch": 0.650142218610321, "grad_norm": 1.02713143825531, "learning_rate": 4.793471170090555e-05, "loss": 1.6453, "step": 200 }, { "epoch": 0.666395774075579, "grad_norm": 1.2023831605911255, "learning_rate": 4.783169409729362e-05, "loss": 1.6974, "step": 205 }, { "epoch": 0.682649329540837, "grad_norm": 1.0009326934814453, "learning_rate": 4.772628561609022e-05, "loss": 1.7094, "step": 210 }, { "epoch": 0.6989028850060951, "grad_norm": 1.269020438194275, "learning_rate": 4.761849729540643e-05, "loss": 1.6832, "step": 215 }, { "epoch": 0.7151564404713531, "grad_norm": 1.3129128217697144, "learning_rate": 4.7508340422564134e-05, "loss": 1.6847, "step": 220 }, { "epoch": 0.7314099959366112, "grad_norm": 1.0837377309799194, "learning_rate": 4.7395826532914054e-05, "loss": 1.7215, "step": 225 }, { "epoch": 0.7476635514018691, "grad_norm": 1.1211832761764526, "learning_rate": 4.728096740862778e-05, "loss": 1.7658, "step": 230 }, { "epoch": 0.7639171068671272, "grad_norm": 1.1422042846679688, "learning_rate": 4.716377507746397e-05, "loss": 1.7098, "step": 235 }, { "epoch": 0.7801706623323852, "grad_norm": 1.2925424575805664, "learning_rate": 4.704426181150884e-05, "loss": 1.7504, "step": 240 }, { "epoch": 0.7964242177976433, "grad_norm": 1.282771348953247, "learning_rate": 4.6922440125891064e-05, "loss": 1.72, "step": 245 }, { "epoch": 0.8126777732629012, "grad_norm": 1.2494529485702515, "learning_rate": 4.6798322777471216e-05, "loss": 1.6581, "step": 250 }, { "epoch": 0.8289313287281593, "grad_norm": 1.2736073732376099, "learning_rate": 4.667192276350591e-05, "loss": 1.6825, "step": 255 }, { "epoch": 0.8451848841934173, "grad_norm": 1.1477563381195068, "learning_rate": 4.654325332028676e-05, "loss": 1.6889, "step": 260 }, { "epoch": 0.8614384396586753, "grad_norm": 1.2415803670883179, "learning_rate": 4.641232792175428e-05, "loss": 1.6586, "step": 265 }, { "epoch": 0.8776919951239334, "grad_norm": 1.3159024715423584, "learning_rate": 4.6279160278086994e-05, "loss": 1.7102, "step": 270 }, { "epoch": 0.8939455505891913, "grad_norm": 1.2742581367492676, "learning_rate": 4.614376433426565e-05, "loss": 1.7476, "step": 275 }, { "epoch": 0.9101991060544494, "grad_norm": 1.34221351146698, "learning_rate": 4.6006154268613014e-05, "loss": 1.7497, "step": 280 }, { "epoch": 0.9264526615197074, "grad_norm": 1.1669361591339111, "learning_rate": 4.586634449130911e-05, "loss": 1.6693, "step": 285 }, { "epoch": 0.9427062169849655, "grad_norm": 1.2765443325042725, "learning_rate": 4.572434964288226e-05, "loss": 1.5862, "step": 290 }, { "epoch": 0.9589597724502235, "grad_norm": 1.2429810762405396, "learning_rate": 4.55801845926759e-05, "loss": 1.6875, "step": 295 }, { "epoch": 0.9752133279154815, "grad_norm": 1.2103233337402344, "learning_rate": 4.543386443729157e-05, "loss": 1.7294, "step": 300 }, { "epoch": 0.9914668833807395, "grad_norm": 1.3512628078460693, "learning_rate": 4.528540449900798e-05, "loss": 1.709, "step": 305 }, { "epoch": 1.0077204388459975, "grad_norm": 1.2039848566055298, "learning_rate": 4.513482032417656e-05, "loss": 1.6632, "step": 310 }, { "epoch": 1.0239739943112556, "grad_norm": 1.3805475234985352, "learning_rate": 4.498212768159341e-05, "loss": 1.695, "step": 315 }, { "epoch": 1.0402275497765137, "grad_norm": 1.3265151977539062, "learning_rate": 4.48273425608481e-05, "loss": 1.6653, "step": 320 }, { "epoch": 1.0564811052417715, "grad_norm": 1.015641212463379, "learning_rate": 4.4670481170649214e-05, "loss": 1.652, "step": 325 }, { "epoch": 1.0727346607070296, "grad_norm": 1.2359689474105835, "learning_rate": 4.451155993712711e-05, "loss": 1.6457, "step": 330 }, { "epoch": 1.0889882161722877, "grad_norm": 1.3188092708587646, "learning_rate": 4.435059550211371e-05, "loss": 1.6512, "step": 335 }, { "epoch": 1.1052417716375458, "grad_norm": 1.323879361152649, "learning_rate": 4.4187604721399877e-05, "loss": 1.6338, "step": 340 }, { "epoch": 1.1214953271028036, "grad_norm": 1.263047218322754, "learning_rate": 4.40226046629703e-05, "loss": 1.6508, "step": 345 }, { "epoch": 1.1377488825680617, "grad_norm": 1.265649676322937, "learning_rate": 4.3855612605216174e-05, "loss": 1.6447, "step": 350 }, { "epoch": 1.1540024380333198, "grad_norm": 1.2379087209701538, "learning_rate": 4.3686646035125855e-05, "loss": 1.6522, "step": 355 }, { "epoch": 1.170255993498578, "grad_norm": 1.200422763824463, "learning_rate": 4.351572264645366e-05, "loss": 1.6935, "step": 360 }, { "epoch": 1.1865095489638358, "grad_norm": 1.3982837200164795, "learning_rate": 4.334286033786704e-05, "loss": 1.6792, "step": 365 }, { "epoch": 1.2027631044290938, "grad_norm": 1.3108696937561035, "learning_rate": 4.3168077211072263e-05, "loss": 1.6498, "step": 370 }, { "epoch": 1.219016659894352, "grad_norm": 1.3713555335998535, "learning_rate": 4.2991391568918825e-05, "loss": 1.6675, "step": 375 }, { "epoch": 1.23527021535961, "grad_norm": 1.406441330909729, "learning_rate": 4.281282191348289e-05, "loss": 1.6328, "step": 380 }, { "epoch": 1.2515237708248679, "grad_norm": 1.3209528923034668, "learning_rate": 4.2632386944129707e-05, "loss": 1.7064, "step": 385 }, { "epoch": 1.267777326290126, "grad_norm": 1.4870327711105347, "learning_rate": 4.245010555555554e-05, "loss": 1.7161, "step": 390 }, { "epoch": 1.284030881755384, "grad_norm": 1.4530566930770874, "learning_rate": 4.2265996835809016e-05, "loss": 1.6267, "step": 395 }, { "epoch": 1.300284437220642, "grad_norm": 1.4400850534439087, "learning_rate": 4.2080080064292304e-05, "loss": 1.6029, "step": 400 }, { "epoch": 1.3165379926859, "grad_norm": 1.389769434928894, "learning_rate": 4.189237470974219e-05, "loss": 1.6298, "step": 405 }, { "epoch": 1.332791548151158, "grad_norm": 1.2579468488693237, "learning_rate": 4.1702900428191374e-05, "loss": 1.6965, "step": 410 }, { "epoch": 1.3490451036164162, "grad_norm": 1.4243718385696411, "learning_rate": 4.151167706091017e-05, "loss": 1.5955, "step": 415 }, { "epoch": 1.3652986590816742, "grad_norm": 1.395219087600708, "learning_rate": 4.131872463232872e-05, "loss": 1.6369, "step": 420 }, { "epoch": 1.3815522145469321, "grad_norm": 1.4617631435394287, "learning_rate": 4.1124063347940135e-05, "loss": 1.6105, "step": 425 }, { "epoch": 1.3978057700121902, "grad_norm": 1.1881122589111328, "learning_rate": 4.092771359218461e-05, "loss": 1.6372, "step": 430 }, { "epoch": 1.414059325477448, "grad_norm": 1.330495834350586, "learning_rate": 4.0729695926314815e-05, "loss": 1.5817, "step": 435 }, { "epoch": 1.4303128809427061, "grad_norm": 1.3312103748321533, "learning_rate": 4.053003108624276e-05, "loss": 1.6602, "step": 440 }, { "epoch": 1.4465664364079642, "grad_norm": 1.3933234214782715, "learning_rate": 4.03287399803684e-05, "loss": 1.63, "step": 445 }, { "epoch": 1.4628199918732223, "grad_norm": 1.600183129310608, "learning_rate": 4.0125843687390166e-05, "loss": 1.6614, "step": 450 }, { "epoch": 1.4790735473384804, "grad_norm": 1.4344749450683594, "learning_rate": 3.992136345409765e-05, "loss": 1.6492, "step": 455 }, { "epoch": 1.4953271028037383, "grad_norm": 1.4546074867248535, "learning_rate": 3.9715320693146655e-05, "loss": 1.6063, "step": 460 }, { "epoch": 1.5115806582689963, "grad_norm": 1.2904654741287231, "learning_rate": 3.9507736980817e-05, "loss": 1.6618, "step": 465 }, { "epoch": 1.5278342137342542, "grad_norm": 1.8645012378692627, "learning_rate": 3.9298634054753026e-05, "loss": 1.697, "step": 470 }, { "epoch": 1.5440877691995123, "grad_norm": 1.4428379535675049, "learning_rate": 3.908803381168732e-05, "loss": 1.6741, "step": 475 }, { "epoch": 1.5603413246647704, "grad_norm": 1.4418410062789917, "learning_rate": 3.887595830514775e-05, "loss": 1.7026, "step": 480 }, { "epoch": 1.5765948801300285, "grad_norm": 1.3783613443374634, "learning_rate": 3.8662429743148046e-05, "loss": 1.6692, "step": 485 }, { "epoch": 1.5928484355952865, "grad_norm": 1.3248358964920044, "learning_rate": 3.844747048586228e-05, "loss": 1.6315, "step": 490 }, { "epoch": 1.6091019910605446, "grad_norm": 1.3751637935638428, "learning_rate": 3.823110304328331e-05, "loss": 1.6716, "step": 495 }, { "epoch": 1.6253555465258025, "grad_norm": 1.3097206354141235, "learning_rate": 3.801335007286564e-05, "loss": 1.5766, "step": 500 }, { "epoch": 1.6416091019910606, "grad_norm": 1.402269959449768, "learning_rate": 3.779423437715274e-05, "loss": 1.6405, "step": 505 }, { "epoch": 1.6578626574563184, "grad_norm": 1.6543242931365967, "learning_rate": 3.757377890138927e-05, "loss": 1.6307, "step": 510 }, { "epoch": 1.6741162129215765, "grad_norm": 1.4377750158309937, "learning_rate": 3.7352006731118264e-05, "loss": 1.588, "step": 515 }, { "epoch": 1.6903697683868346, "grad_norm": 1.578800916671753, "learning_rate": 3.712894108976372e-05, "loss": 1.6307, "step": 520 }, { "epoch": 1.7066233238520927, "grad_norm": 1.4415676593780518, "learning_rate": 3.690460533619866e-05, "loss": 1.6854, "step": 525 }, { "epoch": 1.7228768793173508, "grad_norm": 1.5168665647506714, "learning_rate": 3.667902296229905e-05, "loss": 1.599, "step": 530 }, { "epoch": 1.7391304347826086, "grad_norm": 1.3709524869918823, "learning_rate": 3.645221759048384e-05, "loss": 1.6427, "step": 535 }, { "epoch": 1.7553839902478667, "grad_norm": 1.4154709577560425, "learning_rate": 3.622421297124122e-05, "loss": 1.5486, "step": 540 }, { "epoch": 1.7716375457131246, "grad_norm": 1.5655745267868042, "learning_rate": 3.599503298064154e-05, "loss": 1.6065, "step": 545 }, { "epoch": 1.7878911011783827, "grad_norm": 1.5691167116165161, "learning_rate": 3.576470161783712e-05, "loss": 1.6194, "step": 550 }, { "epoch": 1.8041446566436408, "grad_norm": 1.5229332447052002, "learning_rate": 3.5533243002549046e-05, "loss": 1.6312, "step": 555 }, { "epoch": 1.8203982121088988, "grad_norm": 2.0803072452545166, "learning_rate": 3.5300681372541476e-05, "loss": 1.5872, "step": 560 }, { "epoch": 1.836651767574157, "grad_norm": 1.4445246458053589, "learning_rate": 3.5067041081083496e-05, "loss": 1.6226, "step": 565 }, { "epoch": 1.852905323039415, "grad_norm": 1.559645652770996, "learning_rate": 3.483234659439889e-05, "loss": 1.5703, "step": 570 }, { "epoch": 1.8691588785046729, "grad_norm": 1.3045098781585693, "learning_rate": 3.459662248910411e-05, "loss": 1.5574, "step": 575 }, { "epoch": 1.885412433969931, "grad_norm": 1.410343050956726, "learning_rate": 3.435989344963471e-05, "loss": 1.6836, "step": 580 }, { "epoch": 1.9016659894351888, "grad_norm": 1.5801265239715576, "learning_rate": 3.41221842656604e-05, "loss": 1.6366, "step": 585 }, { "epoch": 1.917919544900447, "grad_norm": 1.440772533416748, "learning_rate": 3.3883519829489154e-05, "loss": 1.6395, "step": 590 }, { "epoch": 1.934173100365705, "grad_norm": 1.3845847845077515, "learning_rate": 3.3643925133460564e-05, "loss": 1.6139, "step": 595 }, { "epoch": 1.950426655830963, "grad_norm": 1.3879539966583252, "learning_rate": 3.3403425267328715e-05, "loss": 1.5887, "step": 600 }, { "epoch": 1.9666802112962212, "grad_norm": 1.3762508630752563, "learning_rate": 3.316204541563479e-05, "loss": 1.636, "step": 605 }, { "epoch": 1.982933766761479, "grad_norm": 1.6764074563980103, "learning_rate": 3.2919810855069864e-05, "loss": 1.6699, "step": 610 }, { "epoch": 1.9991873222267371, "grad_norm": 1.5237112045288086, "learning_rate": 3.267674695182798e-05, "loss": 1.6194, "step": 615 }, { "epoch": 2.015440877691995, "grad_norm": 1.7229068279266357, "learning_rate": 3.243287915894987e-05, "loss": 1.6077, "step": 620 }, { "epoch": 2.031694433157253, "grad_norm": 1.5503779649734497, "learning_rate": 3.218823301365754e-05, "loss": 1.6024, "step": 625 }, { "epoch": 2.047947988622511, "grad_norm": 1.584635853767395, "learning_rate": 3.1942834134680124e-05, "loss": 1.5911, "step": 630 }, { "epoch": 2.0642015440877692, "grad_norm": 1.4763562679290771, "learning_rate": 3.1696708219571126e-05, "loss": 1.6143, "step": 635 }, { "epoch": 2.0804550995530273, "grad_norm": 1.5131165981292725, "learning_rate": 3.144988104201745e-05, "loss": 1.6069, "step": 640 }, { "epoch": 2.0967086550182854, "grad_norm": 1.595162272453308, "learning_rate": 3.120237844914044e-05, "loss": 1.6128, "step": 645 }, { "epoch": 2.112962210483543, "grad_norm": 1.9360445737838745, "learning_rate": 3.095422635878923e-05, "loss": 1.6004, "step": 650 }, { "epoch": 2.129215765948801, "grad_norm": 1.4424818754196167, "learning_rate": 3.0705450756826706e-05, "loss": 1.6084, "step": 655 }, { "epoch": 2.145469321414059, "grad_norm": 1.6683636903762817, "learning_rate": 3.045607769440829e-05, "loss": 1.6063, "step": 660 }, { "epoch": 2.1617228768793173, "grad_norm": 1.9396454095840454, "learning_rate": 3.0206133285254017e-05, "loss": 1.6374, "step": 665 }, { "epoch": 2.1779764323445754, "grad_norm": 1.9183346033096313, "learning_rate": 2.9955643702913865e-05, "loss": 1.529, "step": 670 }, { "epoch": 2.1942299878098335, "grad_norm": 1.61932373046875, "learning_rate": 2.9704635178027012e-05, "loss": 1.5607, "step": 675 }, { "epoch": 2.2104835432750916, "grad_norm": 1.7259231805801392, "learning_rate": 2.9453133995574955e-05, "loss": 1.5854, "step": 680 }, { "epoch": 2.2267370987403496, "grad_norm": 1.675529956817627, "learning_rate": 2.9201166492129088e-05, "loss": 1.5563, "step": 685 }, { "epoch": 2.2429906542056073, "grad_norm": 1.628509283065796, "learning_rate": 2.8948759053092754e-05, "loss": 1.5781, "step": 690 }, { "epoch": 2.2592442096708654, "grad_norm": 1.5093809366226196, "learning_rate": 2.869593810993824e-05, "loss": 1.5759, "step": 695 }, { "epoch": 2.2754977651361235, "grad_norm": 1.8209433555603027, "learning_rate": 2.844273013743896e-05, "loss": 1.6089, "step": 700 }, { "epoch": 2.2917513206013815, "grad_norm": 2.2926626205444336, "learning_rate": 2.8189161650897045e-05, "loss": 1.578, "step": 705 }, { "epoch": 2.3080048760666396, "grad_norm": 1.6229182481765747, "learning_rate": 2.7935259203366777e-05, "loss": 1.5563, "step": 710 }, { "epoch": 2.3242584315318977, "grad_norm": 1.8527780771255493, "learning_rate": 2.7681049382873965e-05, "loss": 1.5463, "step": 715 }, { "epoch": 2.340511986997156, "grad_norm": 1.877462387084961, "learning_rate": 2.7426558809631748e-05, "loss": 1.5227, "step": 720 }, { "epoch": 2.356765542462414, "grad_norm": 1.5895532369613647, "learning_rate": 2.7171814133253015e-05, "loss": 1.6244, "step": 725 }, { "epoch": 2.3730190979276715, "grad_norm": 1.5113598108291626, "learning_rate": 2.691684202995966e-05, "loss": 1.5977, "step": 730 }, { "epoch": 2.3892726533929296, "grad_norm": 1.582775592803955, "learning_rate": 2.6661669199789174e-05, "loss": 1.6314, "step": 735 }, { "epoch": 2.4055262088581877, "grad_norm": 1.6638239622116089, "learning_rate": 2.6406322363798657e-05, "loss": 1.5892, "step": 740 }, { "epoch": 2.4217797643234458, "grad_norm": 1.538442850112915, "learning_rate": 2.6150828261266642e-05, "loss": 1.5512, "step": 745 }, { "epoch": 2.438033319788704, "grad_norm": 1.6044487953186035, "learning_rate": 2.589521364689308e-05, "loss": 1.5288, "step": 750 }, { "epoch": 2.454286875253962, "grad_norm": 1.8566341400146484, "learning_rate": 2.5639505287997583e-05, "loss": 1.6311, "step": 755 }, { "epoch": 2.47054043071922, "grad_norm": 1.7828178405761719, "learning_rate": 2.5383729961716483e-05, "loss": 1.5705, "step": 760 }, { "epoch": 2.4867939861844777, "grad_norm": 1.8720645904541016, "learning_rate": 2.512791445219876e-05, "loss": 1.5955, "step": 765 }, { "epoch": 2.5030475416497358, "grad_norm": 1.5776010751724243, "learning_rate": 2.487208554780125e-05, "loss": 1.6158, "step": 770 }, { "epoch": 2.519301097114994, "grad_norm": 1.802860140800476, "learning_rate": 2.461627003828352e-05, "loss": 1.5844, "step": 775 }, { "epoch": 2.535554652580252, "grad_norm": 1.8349519968032837, "learning_rate": 2.4360494712002423e-05, "loss": 1.5486, "step": 780 }, { "epoch": 2.55180820804551, "grad_norm": 1.77409029006958, "learning_rate": 2.4104786353106926e-05, "loss": 1.5918, "step": 785 }, { "epoch": 2.568061763510768, "grad_norm": 1.7446224689483643, "learning_rate": 2.384917173873336e-05, "loss": 1.5554, "step": 790 }, { "epoch": 2.584315318976026, "grad_norm": 1.7830730676651, "learning_rate": 2.359367763620135e-05, "loss": 1.6061, "step": 795 }, { "epoch": 2.600568874441284, "grad_norm": 1.542494773864746, "learning_rate": 2.3338330800210828e-05, "loss": 1.6328, "step": 800 }, { "epoch": 2.616822429906542, "grad_norm": 1.7287977933883667, "learning_rate": 2.3083157970040344e-05, "loss": 1.5585, "step": 805 }, { "epoch": 2.6330759853718, "grad_norm": 1.6727949380874634, "learning_rate": 2.282818586674699e-05, "loss": 1.6686, "step": 810 }, { "epoch": 2.649329540837058, "grad_norm": 1.8130536079406738, "learning_rate": 2.2573441190368255e-05, "loss": 1.606, "step": 815 }, { "epoch": 2.665583096302316, "grad_norm": 1.8258434534072876, "learning_rate": 2.2318950617126044e-05, "loss": 1.5736, "step": 820 }, { "epoch": 2.6818366517675742, "grad_norm": 1.8970004320144653, "learning_rate": 2.206474079663323e-05, "loss": 1.5835, "step": 825 }, { "epoch": 2.6980902072328323, "grad_norm": 1.6587392091751099, "learning_rate": 2.181083834910296e-05, "loss": 1.6072, "step": 830 }, { "epoch": 2.71434376269809, "grad_norm": 2.0163655281066895, "learning_rate": 2.1557269862561043e-05, "loss": 1.6178, "step": 835 }, { "epoch": 2.7305973181633485, "grad_norm": 1.669689416885376, "learning_rate": 2.1304061890061762e-05, "loss": 1.5864, "step": 840 }, { "epoch": 2.746850873628606, "grad_norm": 1.7801822423934937, "learning_rate": 2.105124094690725e-05, "loss": 1.5186, "step": 845 }, { "epoch": 2.7631044290938642, "grad_norm": 1.7704806327819824, "learning_rate": 2.0798833507870918e-05, "loss": 1.5555, "step": 850 }, { "epoch": 2.7793579845591223, "grad_norm": 1.954834222793579, "learning_rate": 2.0546866004425054e-05, "loss": 1.6356, "step": 855 }, { "epoch": 2.7956115400243804, "grad_norm": 1.6739940643310547, "learning_rate": 2.0295364821972997e-05, "loss": 1.5781, "step": 860 }, { "epoch": 2.8118650954896385, "grad_norm": 1.758725881576538, "learning_rate": 2.0044356297086134e-05, "loss": 1.6308, "step": 865 }, { "epoch": 2.828118650954896, "grad_norm": 1.7557764053344727, "learning_rate": 1.9793866714745978e-05, "loss": 1.5366, "step": 870 }, { "epoch": 2.8443722064201546, "grad_norm": 1.6240283250808716, "learning_rate": 1.9543922305591704e-05, "loss": 1.6104, "step": 875 }, { "epoch": 2.8606257618854123, "grad_norm": 1.7991812229156494, "learning_rate": 1.9294549243173303e-05, "loss": 1.6576, "step": 880 }, { "epoch": 2.8768793173506704, "grad_norm": 1.8438798189163208, "learning_rate": 1.904577364121077e-05, "loss": 1.5634, "step": 885 }, { "epoch": 2.8931328728159285, "grad_norm": 2.0317084789276123, "learning_rate": 1.879762155085956e-05, "loss": 1.5538, "step": 890 }, { "epoch": 2.9093864282811865, "grad_norm": 1.6778262853622437, "learning_rate": 1.8550118957982547e-05, "loss": 1.6398, "step": 895 }, { "epoch": 2.9256399837464446, "grad_norm": 1.8134307861328125, "learning_rate": 1.8303291780428876e-05, "loss": 1.4889, "step": 900 }, { "epoch": 2.9418935392117027, "grad_norm": 1.9006396532058716, "learning_rate": 1.8057165865319882e-05, "loss": 1.582, "step": 905 }, { "epoch": 2.958147094676961, "grad_norm": 1.8433765172958374, "learning_rate": 1.781176698634246e-05, "loss": 1.5856, "step": 910 }, { "epoch": 2.9744006501422184, "grad_norm": 1.6938343048095703, "learning_rate": 1.7567120841050135e-05, "loss": 1.599, "step": 915 }, { "epoch": 2.9906542056074765, "grad_norm": 1.868025302886963, "learning_rate": 1.7323253048172013e-05, "loss": 1.5799, "step": 920 }, { "epoch": 3.0069077610727346, "grad_norm": 1.767774224281311, "learning_rate": 1.7080189144930135e-05, "loss": 1.6014, "step": 925 }, { "epoch": 3.0231613165379927, "grad_norm": 1.7357462644577026, "learning_rate": 1.6837954584365216e-05, "loss": 1.5911, "step": 930 }, { "epoch": 3.039414872003251, "grad_norm": 1.7004544734954834, "learning_rate": 1.6596574732671287e-05, "loss": 1.5304, "step": 935 }, { "epoch": 3.055668427468509, "grad_norm": 1.7053595781326294, "learning_rate": 1.6356074866539435e-05, "loss": 1.548, "step": 940 }, { "epoch": 3.071921982933767, "grad_norm": 1.7751458883285522, "learning_rate": 1.6116480170510852e-05, "loss": 1.6273, "step": 945 }, { "epoch": 3.0881755383990246, "grad_norm": 1.8386896848678589, "learning_rate": 1.5877815734339608e-05, "loss": 1.5394, "step": 950 }, { "epoch": 3.1044290938642827, "grad_norm": 1.6355414390563965, "learning_rate": 1.5640106550365298e-05, "loss": 1.5259, "step": 955 }, { "epoch": 3.1206826493295408, "grad_norm": 1.7519521713256836, "learning_rate": 1.54033775108959e-05, "loss": 1.6105, "step": 960 }, { "epoch": 3.136936204794799, "grad_norm": 1.690624713897705, "learning_rate": 1.5167653405601124e-05, "loss": 1.5488, "step": 965 }, { "epoch": 3.153189760260057, "grad_norm": 1.7758216857910156, "learning_rate": 1.4932958918916513e-05, "loss": 1.5906, "step": 970 }, { "epoch": 3.169443315725315, "grad_norm": 1.7740142345428467, "learning_rate": 1.469931862745853e-05, "loss": 1.5361, "step": 975 }, { "epoch": 3.185696871190573, "grad_norm": 1.8564815521240234, "learning_rate": 1.446675699745097e-05, "loss": 1.5407, "step": 980 }, { "epoch": 3.2019504266558307, "grad_norm": 1.829458236694336, "learning_rate": 1.4235298382162899e-05, "loss": 1.5962, "step": 985 }, { "epoch": 3.218203982121089, "grad_norm": 1.9702229499816895, "learning_rate": 1.4004967019358469e-05, "loss": 1.5905, "step": 990 }, { "epoch": 3.234457537586347, "grad_norm": 1.8121120929718018, "learning_rate": 1.3775787028758799e-05, "loss": 1.5726, "step": 995 }, { "epoch": 3.250711093051605, "grad_norm": 2.0297420024871826, "learning_rate": 1.354778240951617e-05, "loss": 1.5484, "step": 1000 }, { "epoch": 3.266964648516863, "grad_norm": 1.9334895610809326, "learning_rate": 1.3320977037700952e-05, "loss": 1.5091, "step": 1005 }, { "epoch": 3.283218203982121, "grad_norm": 1.7220382690429688, "learning_rate": 1.3095394663801347e-05, "loss": 1.5658, "step": 1010 }, { "epoch": 3.2994717594473792, "grad_norm": 1.8911561965942383, "learning_rate": 1.2871058910236292e-05, "loss": 1.5774, "step": 1015 }, { "epoch": 3.315725314912637, "grad_norm": 1.8349742889404297, "learning_rate": 1.2647993268881745e-05, "loss": 1.5463, "step": 1020 }, { "epoch": 3.331978870377895, "grad_norm": 1.8155410289764404, "learning_rate": 1.2426221098610741e-05, "loss": 1.55, "step": 1025 }, { "epoch": 3.348232425843153, "grad_norm": 2.0373146533966064, "learning_rate": 1.2205765622847274e-05, "loss": 1.5677, "step": 1030 }, { "epoch": 3.364485981308411, "grad_norm": 1.8565573692321777, "learning_rate": 1.1986649927134372e-05, "loss": 1.594, "step": 1035 }, { "epoch": 3.3807395367736692, "grad_norm": 1.7318943738937378, "learning_rate": 1.1768896956716693e-05, "loss": 1.5615, "step": 1040 }, { "epoch": 3.3969930922389273, "grad_norm": 2.03358793258667, "learning_rate": 1.1552529514137733e-05, "loss": 1.5068, "step": 1045 }, { "epoch": 3.4132466477041854, "grad_norm": 1.943980097770691, "learning_rate": 1.1337570256851963e-05, "loss": 1.5696, "step": 1050 }, { "epoch": 3.4295002031694435, "grad_norm": 1.7781481742858887, "learning_rate": 1.1124041694852258e-05, "loss": 1.5515, "step": 1055 }, { "epoch": 3.4457537586347016, "grad_norm": 1.72038733959198, "learning_rate": 1.091196618831268e-05, "loss": 1.5536, "step": 1060 }, { "epoch": 3.462007314099959, "grad_norm": 1.7962324619293213, "learning_rate": 1.070136594524698e-05, "loss": 1.578, "step": 1065 }, { "epoch": 3.4782608695652173, "grad_norm": 2.4699037075042725, "learning_rate": 1.0492263019183002e-05, "loss": 1.5386, "step": 1070 }, { "epoch": 3.4945144250304754, "grad_norm": 1.756534218788147, "learning_rate": 1.0284679306853343e-05, "loss": 1.5757, "step": 1075 }, { "epoch": 3.5107679804957335, "grad_norm": 1.8124436140060425, "learning_rate": 1.0078636545902362e-05, "loss": 1.5579, "step": 1080 }, { "epoch": 3.5270215359609915, "grad_norm": 1.7683898210525513, "learning_rate": 9.874156312609836e-06, "loss": 1.5616, "step": 1085 }, { "epoch": 3.5432750914262496, "grad_norm": 1.870835542678833, "learning_rate": 9.671260019631604e-06, "loss": 1.5243, "step": 1090 }, { "epoch": 3.5595286468915077, "grad_norm": 1.8171908855438232, "learning_rate": 9.469968913757254e-06, "loss": 1.6215, "step": 1095 }, { "epoch": 3.5757822023567654, "grad_norm": 1.8751733303070068, "learning_rate": 9.270304073685193e-06, "loss": 1.5294, "step": 1100 }, { "epoch": 3.5920357578220234, "grad_norm": 1.6688753366470337, "learning_rate": 9.07228640781539e-06, "loss": 1.546, "step": 1105 }, { "epoch": 3.6082893132872815, "grad_norm": 1.7186001539230347, "learning_rate": 8.875936652059872e-06, "loss": 1.5659, "step": 1110 }, { "epoch": 3.6245428687525396, "grad_norm": 1.6870884895324707, "learning_rate": 8.681275367671287e-06, "loss": 1.5799, "step": 1115 }, { "epoch": 3.6407964242177977, "grad_norm": 1.8477848768234253, "learning_rate": 8.488322939089838e-06, "loss": 1.6147, "step": 1120 }, { "epoch": 3.657049979683056, "grad_norm": 1.7299193143844604, "learning_rate": 8.297099571808625e-06, "loss": 1.5244, "step": 1125 }, { "epoch": 3.673303535148314, "grad_norm": 1.8795167207717896, "learning_rate": 8.10762529025782e-06, "loss": 1.62, "step": 1130 }, { "epoch": 3.6895570906135715, "grad_norm": 2.0962882041931152, "learning_rate": 7.9199199357077e-06, "loss": 1.5168, "step": 1135 }, { "epoch": 3.7058106460788296, "grad_norm": 1.949979305267334, "learning_rate": 7.734003164190983e-06, "loss": 1.5378, "step": 1140 }, { "epoch": 3.7220642015440877, "grad_norm": 1.9429444074630737, "learning_rate": 7.549894444444469e-06, "loss": 1.5231, "step": 1145 }, { "epoch": 3.7383177570093458, "grad_norm": 2.2284860610961914, "learning_rate": 7.367613055870301e-06, "loss": 1.5921, "step": 1150 }, { "epoch": 3.754571312474604, "grad_norm": 1.9204776287078857, "learning_rate": 7.187178086517116e-06, "loss": 1.539, "step": 1155 }, { "epoch": 3.770824867939862, "grad_norm": 1.7024307250976562, "learning_rate": 7.008608431081179e-06, "loss": 1.58, "step": 1160 }, { "epoch": 3.78707842340512, "grad_norm": 2.035949945449829, "learning_rate": 6.831922788927744e-06, "loss": 1.5792, "step": 1165 }, { "epoch": 3.8033319788703777, "grad_norm": 1.947672963142395, "learning_rate": 6.657139662132961e-06, "loss": 1.5228, "step": 1170 }, { "epoch": 3.819585534335636, "grad_norm": 1.8621673583984375, "learning_rate": 6.4842773535463416e-06, "loss": 1.5181, "step": 1175 }, { "epoch": 3.835839089800894, "grad_norm": 1.968684434890747, "learning_rate": 6.313353964874155e-06, "loss": 1.5622, "step": 1180 }, { "epoch": 3.852092645266152, "grad_norm": 1.8336701393127441, "learning_rate": 6.14438739478383e-06, "loss": 1.5889, "step": 1185 }, { "epoch": 3.86834620073141, "grad_norm": 2.0393776893615723, "learning_rate": 5.977395337029701e-06, "loss": 1.5254, "step": 1190 }, { "epoch": 3.884599756196668, "grad_norm": 1.9161821603775024, "learning_rate": 5.8123952786001276e-06, "loss": 1.5271, "step": 1195 }, { "epoch": 3.900853311661926, "grad_norm": 2.1005172729492188, "learning_rate": 5.6494044978862906e-06, "loss": 1.553, "step": 1200 }, { "epoch": 3.917106867127184, "grad_norm": 2.095838785171509, "learning_rate": 5.488440062872891e-06, "loss": 1.5279, "step": 1205 }, { "epoch": 3.9333604225924423, "grad_norm": 2.2288739681243896, "learning_rate": 5.329518829350788e-06, "loss": 1.6242, "step": 1210 }, { "epoch": 3.9496139780577, "grad_norm": 1.9176870584487915, "learning_rate": 5.172657439151912e-06, "loss": 1.4934, "step": 1215 }, { "epoch": 3.965867533522958, "grad_norm": 1.945634126663208, "learning_rate": 5.017872318406594e-06, "loss": 1.5367, "step": 1220 }, { "epoch": 3.982121088988216, "grad_norm": 1.921211838722229, "learning_rate": 4.865179675823442e-06, "loss": 1.512, "step": 1225 }, { "epoch": 3.9983746444534742, "grad_norm": 2.0986344814300537, "learning_rate": 4.7145955009920195e-06, "loss": 1.5012, "step": 1230 }, { "epoch": 4.014628199918732, "grad_norm": 2.0708072185516357, "learning_rate": 4.5661355627084374e-06, "loss": 1.6165, "step": 1235 }, { "epoch": 4.03088175538399, "grad_norm": 1.9316012859344482, "learning_rate": 4.419815407324102e-06, "loss": 1.57, "step": 1240 }, { "epoch": 4.0471353108492485, "grad_norm": 1.8041713237762451, "learning_rate": 4.275650357117747e-06, "loss": 1.555, "step": 1245 }, { "epoch": 4.063388866314506, "grad_norm": 2.017209529876709, "learning_rate": 4.13365550869089e-06, "loss": 1.567, "step": 1250 }, { "epoch": 4.079642421779765, "grad_norm": 1.708092212677002, "learning_rate": 3.993845731386991e-06, "loss": 1.5679, "step": 1255 }, { "epoch": 4.095895977245022, "grad_norm": 1.8569332361221313, "learning_rate": 3.856235665734359e-06, "loss": 1.6, "step": 1260 }, { "epoch": 4.11214953271028, "grad_norm": 1.8322447538375854, "learning_rate": 3.720839721913011e-06, "loss": 1.568, "step": 1265 }, { "epoch": 4.1284030881755385, "grad_norm": 1.730568289756775, "learning_rate": 3.587672078245716e-06, "loss": 1.5105, "step": 1270 }, { "epoch": 4.144656643640796, "grad_norm": 2.135589361190796, "learning_rate": 3.456746679713238e-06, "loss": 1.5713, "step": 1275 }, { "epoch": 4.160910199106055, "grad_norm": 1.7022476196289062, "learning_rate": 3.328077236494087e-06, "loss": 1.614, "step": 1280 }, { "epoch": 4.177163754571312, "grad_norm": 1.968857765197754, "learning_rate": 3.2016772225287844e-06, "loss": 1.5023, "step": 1285 }, { "epoch": 4.193417310036571, "grad_norm": 2.244847536087036, "learning_rate": 3.0775598741089372e-06, "loss": 1.5558, "step": 1290 }, { "epoch": 4.2096708655018285, "grad_norm": 1.9722509384155273, "learning_rate": 2.955738188491167e-06, "loss": 1.495, "step": 1295 }, { "epoch": 4.225924420967086, "grad_norm": 2.2794189453125, "learning_rate": 2.836224922536035e-06, "loss": 1.4822, "step": 1300 }, { "epoch": 4.242177976432345, "grad_norm": 1.8010648488998413, "learning_rate": 2.7190325913722196e-06, "loss": 1.5623, "step": 1305 }, { "epoch": 4.258431531897602, "grad_norm": 2.321396589279175, "learning_rate": 2.6041734670859493e-06, "loss": 1.4989, "step": 1310 }, { "epoch": 4.274685087362861, "grad_norm": 1.797762393951416, "learning_rate": 2.4916595774358705e-06, "loss": 1.6575, "step": 1315 }, { "epoch": 4.290938642828118, "grad_norm": 1.9985977411270142, "learning_rate": 2.3815027045935774e-06, "loss": 1.5394, "step": 1320 }, { "epoch": 4.307192198293377, "grad_norm": 1.9368855953216553, "learning_rate": 2.273714383909789e-06, "loss": 1.5128, "step": 1325 }, { "epoch": 4.323445753758635, "grad_norm": 1.9567540884017944, "learning_rate": 2.1683059027063828e-06, "loss": 1.4683, "step": 1330 }, { "epoch": 4.339699309223893, "grad_norm": 1.9031387567520142, "learning_rate": 2.0652882990944534e-06, "loss": 1.5042, "step": 1335 }, { "epoch": 4.355952864689151, "grad_norm": 2.1097919940948486, "learning_rate": 1.964672360818387e-06, "loss": 1.5478, "step": 1340 }, { "epoch": 4.372206420154408, "grad_norm": 2.0269947052001953, "learning_rate": 1.8664686241262358e-06, "loss": 1.4658, "step": 1345 }, { "epoch": 4.388459975619667, "grad_norm": 1.8135507106781006, "learning_rate": 1.7706873726663381e-06, "loss": 1.5633, "step": 1350 }, { "epoch": 4.404713531084925, "grad_norm": 2.005018949508667, "learning_rate": 1.6773386364104971e-06, "loss": 1.535, "step": 1355 }, { "epoch": 4.420967086550183, "grad_norm": 1.8301798105239868, "learning_rate": 1.5864321906036262e-06, "loss": 1.524, "step": 1360 }, { "epoch": 4.437220642015441, "grad_norm": 2.0094285011291504, "learning_rate": 1.4979775547401376e-06, "loss": 1.5157, "step": 1365 }, { "epoch": 4.453474197480699, "grad_norm": 1.9530905485153198, "learning_rate": 1.4119839915670562e-06, "loss": 1.5491, "step": 1370 }, { "epoch": 4.469727752945957, "grad_norm": 2.0504391193389893, "learning_rate": 1.3284605061140764e-06, "loss": 1.5194, "step": 1375 }, { "epoch": 4.485981308411215, "grad_norm": 2.2431955337524414, "learning_rate": 1.2474158447505601e-06, "loss": 1.533, "step": 1380 }, { "epoch": 4.502234863876473, "grad_norm": 1.8665050268173218, "learning_rate": 1.1688584942696368e-06, "loss": 1.4757, "step": 1385 }, { "epoch": 4.518488419341731, "grad_norm": 1.950392246246338, "learning_rate": 1.0927966809995084e-06, "loss": 1.5358, "step": 1390 }, { "epoch": 4.534741974806989, "grad_norm": 2.056180000305176, "learning_rate": 1.0192383699419911e-06, "loss": 1.4977, "step": 1395 }, { "epoch": 4.550995530272247, "grad_norm": 1.7911049127578735, "learning_rate": 9.481912639384389e-07, "loss": 1.5788, "step": 1400 }, { "epoch": 4.567249085737505, "grad_norm": 2.2223970890045166, "learning_rate": 8.796628028631321e-07, "loss": 1.513, "step": 1405 }, { "epoch": 4.583502641202763, "grad_norm": 1.851468801498413, "learning_rate": 8.136601628441876e-07, "loss": 1.6059, "step": 1410 }, { "epoch": 4.599756196668022, "grad_norm": 1.991767406463623, "learning_rate": 7.501902555120982e-07, "loss": 1.5495, "step": 1415 }, { "epoch": 4.616009752133279, "grad_norm": 1.99836003780365, "learning_rate": 6.892597272759482e-07, "loss": 1.582, "step": 1420 }, { "epoch": 4.632263307598537, "grad_norm": 1.8228671550750732, "learning_rate": 6.308749586274309e-07, "loss": 1.587, "step": 1425 }, { "epoch": 4.648516863063795, "grad_norm": 2.050323009490967, "learning_rate": 5.750420634727082e-07, "loss": 1.6031, "step": 1430 }, { "epoch": 4.664770418529053, "grad_norm": 1.8385125398635864, "learning_rate": 5.217668884921506e-07, "loss": 1.5689, "step": 1435 }, { "epoch": 4.681023973994312, "grad_norm": 1.8687756061553955, "learning_rate": 4.7105501252811546e-07, "loss": 1.5067, "step": 1440 }, { "epoch": 4.697277529459569, "grad_norm": 1.8358879089355469, "learning_rate": 4.229117460007342e-07, "loss": 1.5941, "step": 1445 }, { "epoch": 4.713531084924828, "grad_norm": 2.0827765464782715, "learning_rate": 3.7734213035180435e-07, "loss": 1.593, "step": 1450 }, { "epoch": 4.729784640390085, "grad_norm": 1.8851794004440308, "learning_rate": 3.343509375168863e-07, "loss": 1.4914, "step": 1455 }, { "epoch": 4.746038195855343, "grad_norm": 1.9744462966918945, "learning_rate": 2.939426694255898e-07, "loss": 1.5901, "step": 1460 }, { "epoch": 4.762291751320602, "grad_norm": 1.7084238529205322, "learning_rate": 2.561215575301312e-07, "loss": 1.631, "step": 1465 }, { "epoch": 4.778545306785859, "grad_norm": 1.8658472299575806, "learning_rate": 2.2089156236224096e-07, "loss": 1.544, "step": 1470 }, { "epoch": 4.794798862251118, "grad_norm": 1.8390461206436157, "learning_rate": 1.8825637311841726e-07, "loss": 1.5495, "step": 1475 }, { "epoch": 4.811052417716375, "grad_norm": 2.16766619682312, "learning_rate": 1.5821940727361874e-07, "loss": 1.5227, "step": 1480 }, { "epoch": 4.827305973181634, "grad_norm": 2.022632122039795, "learning_rate": 1.3078381022336715e-07, "loss": 1.5021, "step": 1485 }, { "epoch": 4.8435595286468915, "grad_norm": 1.9457296133041382, "learning_rate": 1.0595245495439999e-07, "loss": 1.4985, "step": 1490 }, { "epoch": 4.859813084112149, "grad_norm": 2.0490968227386475, "learning_rate": 8.372794174379417e-08, "loss": 1.5625, "step": 1495 }, { "epoch": 4.876066639577408, "grad_norm": 2.0088553428649902, "learning_rate": 6.411259788668966e-08, "loss": 1.5457, "step": 1500 }, { "epoch": 4.892320195042665, "grad_norm": 2.013977289199829, "learning_rate": 4.7108477452562084e-08, "loss": 1.5011, "step": 1505 }, { "epoch": 4.908573750507924, "grad_norm": 1.8730751276016235, "learning_rate": 3.271736107015033e-08, "loss": 1.5281, "step": 1510 }, { "epoch": 4.9248273059731815, "grad_norm": 1.82501220703125, "learning_rate": 2.0940755740969652e-08, "loss": 1.5072, "step": 1515 }, { "epoch": 4.94108086143844, "grad_norm": 1.6899996995925903, "learning_rate": 1.1779894681515635e-08, "loss": 1.5403, "step": 1520 }, { "epoch": 4.957334416903698, "grad_norm": 1.7991502285003662, "learning_rate": 5.235737194120294e-09, "loss": 1.5469, "step": 1525 }, { "epoch": 4.973587972368955, "grad_norm": 1.9792165756225586, "learning_rate": 1.3089685665046426e-09, "loss": 1.4977, "step": 1530 }, { "epoch": 4.989841527834214, "grad_norm": 1.802415370941162, "learning_rate": 0.0, "loss": 1.5761, "step": 1535 }, { "epoch": 4.989841527834214, "step": 1535, "total_flos": 7.916227959595991e+17, "train_loss": 1.6256803264058763, "train_runtime": 27276.7889, "train_samples_per_second": 0.902, "train_steps_per_second": 0.056 } ], "logging_steps": 5, "max_steps": 1535, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7.916227959595991e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }