{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 2623, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0019063959584405682, "grad_norm": 1.2586055994033813, "learning_rate": 5.063291139240506e-06, "loss": 3.003311538696289, "step": 5 }, { "epoch": 0.0038127919168811364, "grad_norm": 1.5307438373565674, "learning_rate": 1.139240506329114e-05, "loss": 2.9366327285766602, "step": 10 }, { "epoch": 0.005719187875321705, "grad_norm": 0.592338502407074, "learning_rate": 1.7721518987341772e-05, "loss": 2.7316946029663085, "step": 15 }, { "epoch": 0.007625583833762273, "grad_norm": 0.36872273683547974, "learning_rate": 2.4050632911392405e-05, "loss": 2.587538719177246, "step": 20 }, { "epoch": 0.009531979792202841, "grad_norm": 0.2774277329444885, "learning_rate": 3.0379746835443042e-05, "loss": 2.4864227294921877, "step": 25 }, { "epoch": 0.01143837575064341, "grad_norm": 0.3261786997318268, "learning_rate": 3.670886075949367e-05, "loss": 2.456864929199219, "step": 30 }, { "epoch": 0.013344771709083977, "grad_norm": 0.2876887917518616, "learning_rate": 4.3037974683544305e-05, "loss": 2.372416877746582, "step": 35 }, { "epoch": 0.015251167667524546, "grad_norm": 0.2148808389902115, "learning_rate": 4.936708860759494e-05, "loss": 2.2838165283203127, "step": 40 }, { "epoch": 0.017157563625965114, "grad_norm": 0.24246512353420258, "learning_rate": 5.569620253164557e-05, "loss": 2.198516845703125, "step": 45 }, { "epoch": 0.019063959584405682, "grad_norm": 0.23023569583892822, "learning_rate": 6.20253164556962e-05, "loss": 2.1250381469726562, "step": 50 }, { "epoch": 0.02097035554284625, "grad_norm": 0.1854756623506546, "learning_rate": 6.835443037974683e-05, "loss": 2.082244873046875, "step": 55 }, { "epoch": 0.02287675150128682, "grad_norm": 0.19344080984592438, "learning_rate": 7.468354430379747e-05, "loss": 1.9703384399414063, "step": 60 }, { "epoch": 0.024783147459727387, "grad_norm": 0.2533968389034271, "learning_rate": 8.10126582278481e-05, "loss": 1.950678825378418, "step": 65 }, { "epoch": 0.026689543418167955, "grad_norm": 0.21384087204933167, "learning_rate": 8.734177215189874e-05, "loss": 1.9272956848144531, "step": 70 }, { "epoch": 0.028595939376608523, "grad_norm": 0.19282890856266022, "learning_rate": 9.367088607594936e-05, "loss": 1.8916118621826172, "step": 75 }, { "epoch": 0.03050233533504909, "grad_norm": 0.21983802318572998, "learning_rate": 0.0001, "loss": 1.8754505157470702, "step": 80 }, { "epoch": 0.03240873129348966, "grad_norm": 0.2724936008453369, "learning_rate": 9.999904688749192e-05, "loss": 1.854794692993164, "step": 85 }, { "epoch": 0.03431512725193023, "grad_norm": 0.26541006565093994, "learning_rate": 9.999618758630464e-05, "loss": 1.8259353637695312, "step": 90 }, { "epoch": 0.036221523210370796, "grad_norm": 0.1897761970758438, "learning_rate": 9.999142220544758e-05, "loss": 1.7403358459472655, "step": 95 }, { "epoch": 0.038127919168811364, "grad_norm": 0.26632198691368103, "learning_rate": 9.99847509265985e-05, "loss": 1.6990802764892579, "step": 100 }, { "epoch": 0.04003431512725193, "grad_norm": 0.2682671546936035, "learning_rate": 9.997617400409658e-05, "loss": 1.744873046875, "step": 105 }, { "epoch": 0.0419407110856925, "grad_norm": 0.2320956140756607, "learning_rate": 9.996569176493269e-05, "loss": 1.7325843811035155, "step": 110 }, { "epoch": 0.04384710704413307, "grad_norm": 0.24077412486076355, "learning_rate": 9.995330460873698e-05, "loss": 1.7279281616210938, "step": 115 }, { "epoch": 0.04575350300257364, "grad_norm": 0.23554739356040955, "learning_rate": 9.993901300776359e-05, "loss": 1.7739908218383789, "step": 120 }, { "epoch": 0.047659898961014205, "grad_norm": 0.274027943611145, "learning_rate": 9.992281750687265e-05, "loss": 1.730174446105957, "step": 125 }, { "epoch": 0.04956629491945477, "grad_norm": 0.25585317611694336, "learning_rate": 9.990471872350954e-05, "loss": 1.6933242797851562, "step": 130 }, { "epoch": 0.05147269087789534, "grad_norm": 0.25577089190483093, "learning_rate": 9.988471734768135e-05, "loss": 1.6811307907104491, "step": 135 }, { "epoch": 0.05337908683633591, "grad_norm": 0.305698037147522, "learning_rate": 9.986281414193051e-05, "loss": 1.6803890228271485, "step": 140 }, { "epoch": 0.05528548279477648, "grad_norm": 0.25642573833465576, "learning_rate": 9.983900994130583e-05, "loss": 1.6894367218017579, "step": 145 }, { "epoch": 0.057191878753217046, "grad_norm": 0.29189297556877136, "learning_rate": 9.981330565333054e-05, "loss": 1.6893959045410156, "step": 150 }, { "epoch": 0.059098274711657614, "grad_norm": 0.27010300755500793, "learning_rate": 9.978570225796777e-05, "loss": 1.635919189453125, "step": 155 }, { "epoch": 0.06100467067009818, "grad_norm": 0.232698455452919, "learning_rate": 9.97562008075832e-05, "loss": 1.6725154876708985, "step": 160 }, { "epoch": 0.06291106662853875, "grad_norm": 0.24709032475948334, "learning_rate": 9.972480242690488e-05, "loss": 1.6602203369140625, "step": 165 }, { "epoch": 0.06481746258697932, "grad_norm": 0.247094988822937, "learning_rate": 9.969150831298038e-05, "loss": 1.613349723815918, "step": 170 }, { "epoch": 0.06672385854541989, "grad_norm": 0.24072547256946564, "learning_rate": 9.965631973513115e-05, "loss": 1.6103199005126954, "step": 175 }, { "epoch": 0.06863025450386046, "grad_norm": 0.2545181214809418, "learning_rate": 9.961923803490412e-05, "loss": 1.6176319122314453, "step": 180 }, { "epoch": 0.07053665046230102, "grad_norm": 0.23141637444496155, "learning_rate": 9.958026462602062e-05, "loss": 1.6500850677490235, "step": 185 }, { "epoch": 0.07244304642074159, "grad_norm": 0.25008970499038696, "learning_rate": 9.953940099432238e-05, "loss": 1.5950878143310547, "step": 190 }, { "epoch": 0.07434944237918216, "grad_norm": 0.25782686471939087, "learning_rate": 9.949664869771491e-05, "loss": 1.5809452056884765, "step": 195 }, { "epoch": 0.07625583833762273, "grad_norm": 0.28598663210868835, "learning_rate": 9.94520093661082e-05, "loss": 1.5538606643676758, "step": 200 }, { "epoch": 0.0781622342960633, "grad_norm": 0.29584410786628723, "learning_rate": 9.940548470135444e-05, "loss": 1.6130935668945312, "step": 205 }, { "epoch": 0.08006863025450386, "grad_norm": 0.27961355447769165, "learning_rate": 9.935707647718322e-05, "loss": 1.599756908416748, "step": 210 }, { "epoch": 0.08197502621294443, "grad_norm": 0.23241564631462097, "learning_rate": 9.930678653913391e-05, "loss": 1.628369140625, "step": 215 }, { "epoch": 0.083881422171385, "grad_norm": 0.2561100423336029, "learning_rate": 9.925461680448526e-05, "loss": 1.624163818359375, "step": 220 }, { "epoch": 0.08578781812982557, "grad_norm": 0.26588836312294006, "learning_rate": 9.920056926218235e-05, "loss": 1.6177953720092773, "step": 225 }, { "epoch": 0.08769421408826614, "grad_norm": 0.27178075909614563, "learning_rate": 9.914464597276071e-05, "loss": 1.5150765419006347, "step": 230 }, { "epoch": 0.0896006100467067, "grad_norm": 0.26186487078666687, "learning_rate": 9.908684906826781e-05, "loss": 1.6010353088378906, "step": 235 }, { "epoch": 0.09150700600514727, "grad_norm": 0.23075440526008606, "learning_rate": 9.902718075218176e-05, "loss": 1.5511919021606446, "step": 240 }, { "epoch": 0.09341340196358784, "grad_norm": 0.278274267911911, "learning_rate": 9.896564329932727e-05, "loss": 1.5401070594787598, "step": 245 }, { "epoch": 0.09531979792202841, "grad_norm": 0.22299042344093323, "learning_rate": 9.890223905578901e-05, "loss": 1.5656064987182616, "step": 250 }, { "epoch": 0.09722619388046898, "grad_norm": 0.25387582182884216, "learning_rate": 9.883697043882209e-05, "loss": 1.6029573440551759, "step": 255 }, { "epoch": 0.09913258983890955, "grad_norm": 0.23146803677082062, "learning_rate": 9.876983993675989e-05, "loss": 1.5423292160034179, "step": 260 }, { "epoch": 0.10103898579735011, "grad_norm": 0.28828540444374084, "learning_rate": 9.870085010891927e-05, "loss": 1.612344741821289, "step": 265 }, { "epoch": 0.10294538175579068, "grad_norm": 0.2970161736011505, "learning_rate": 9.863000358550296e-05, "loss": 1.5890921592712401, "step": 270 }, { "epoch": 0.10485177771423125, "grad_norm": 0.289323627948761, "learning_rate": 9.855730306749922e-05, "loss": 1.5366689682006835, "step": 275 }, { "epoch": 0.10675817367267182, "grad_norm": 0.28991764783859253, "learning_rate": 9.848275132657903e-05, "loss": 1.475804901123047, "step": 280 }, { "epoch": 0.10866456963111239, "grad_norm": 0.2903752028942108, "learning_rate": 9.840635120499023e-05, "loss": 1.5855154991149902, "step": 285 }, { "epoch": 0.11057096558955296, "grad_norm": 0.3289552927017212, "learning_rate": 9.832810561544925e-05, "loss": 1.558029556274414, "step": 290 }, { "epoch": 0.11247736154799352, "grad_norm": 0.27089908719062805, "learning_rate": 9.824801754103016e-05, "loss": 1.5478031158447265, "step": 295 }, { "epoch": 0.11438375750643409, "grad_norm": 0.22977833449840546, "learning_rate": 9.816609003505073e-05, "loss": 1.544564437866211, "step": 300 }, { "epoch": 0.11629015346487466, "grad_norm": 0.23880314826965332, "learning_rate": 9.808232622095621e-05, "loss": 1.5019208908081054, "step": 305 }, { "epoch": 0.11819654942331523, "grad_norm": 0.2860472500324249, "learning_rate": 9.799672929220015e-05, "loss": 1.5145726203918457, "step": 310 }, { "epoch": 0.1201029453817558, "grad_norm": 0.24491359293460846, "learning_rate": 9.790930251212269e-05, "loss": 1.588730239868164, "step": 315 }, { "epoch": 0.12200934134019636, "grad_norm": 0.2457381784915924, "learning_rate": 9.782004921382612e-05, "loss": 1.5239738464355468, "step": 320 }, { "epoch": 0.12391573729863693, "grad_norm": 0.2565726339817047, "learning_rate": 9.772897280004787e-05, "loss": 1.5374886512756347, "step": 325 }, { "epoch": 0.1258221332570775, "grad_norm": 0.23986336588859558, "learning_rate": 9.763607674303068e-05, "loss": 1.534232997894287, "step": 330 }, { "epoch": 0.12772852921551806, "grad_norm": 0.2615854740142822, "learning_rate": 9.754136458439033e-05, "loss": 1.4485984802246095, "step": 335 }, { "epoch": 0.12963492517395864, "grad_norm": 0.30507153272628784, "learning_rate": 9.744483993498052e-05, "loss": 1.4952167510986327, "step": 340 }, { "epoch": 0.1315413211323992, "grad_norm": 0.2607581317424774, "learning_rate": 9.73465064747553e-05, "loss": 1.5398927688598634, "step": 345 }, { "epoch": 0.13344771709083977, "grad_norm": 0.33851197361946106, "learning_rate": 9.724636795262868e-05, "loss": 1.4469717025756836, "step": 350 }, { "epoch": 0.13535411304928033, "grad_norm": 0.24243547022342682, "learning_rate": 9.714442818633179e-05, "loss": 1.5158900260925292, "step": 355 }, { "epoch": 0.1372605090077209, "grad_norm": 0.25393182039260864, "learning_rate": 9.704069106226727e-05, "loss": 1.5190658569335938, "step": 360 }, { "epoch": 0.13916690496616146, "grad_norm": 0.237921342253685, "learning_rate": 9.693516053536117e-05, "loss": 1.4767440795898437, "step": 365 }, { "epoch": 0.14107330092460205, "grad_norm": 0.2758413553237915, "learning_rate": 9.682784062891209e-05, "loss": 1.4936092376708985, "step": 370 }, { "epoch": 0.1429796968830426, "grad_norm": 0.2373586744070053, "learning_rate": 9.671873543443783e-05, "loss": 1.4848154067993165, "step": 375 }, { "epoch": 0.14488609284148318, "grad_norm": 0.2621917128562927, "learning_rate": 9.66078491115194e-05, "loss": 1.4819945335388183, "step": 380 }, { "epoch": 0.14679248879992374, "grad_norm": 0.22313298285007477, "learning_rate": 9.649518588764247e-05, "loss": 1.5208452224731446, "step": 385 }, { "epoch": 0.14869888475836432, "grad_norm": 0.23852401971817017, "learning_rate": 9.638075005803616e-05, "loss": 1.494023036956787, "step": 390 }, { "epoch": 0.15060528071680487, "grad_norm": 0.26584136486053467, "learning_rate": 9.626454598550927e-05, "loss": 1.4752232551574707, "step": 395 }, { "epoch": 0.15251167667524546, "grad_norm": 0.24776215851306915, "learning_rate": 9.614657810028402e-05, "loss": 1.4930031776428223, "step": 400 }, { "epoch": 0.154418072633686, "grad_norm": 0.3163340985774994, "learning_rate": 9.602685089982708e-05, "loss": 1.4964912414550782, "step": 405 }, { "epoch": 0.1563244685921266, "grad_norm": 0.2543104887008667, "learning_rate": 9.590536894867814e-05, "loss": 1.5049744606018067, "step": 410 }, { "epoch": 0.15823086455056715, "grad_norm": 0.2678035497665405, "learning_rate": 9.578213687827591e-05, "loss": 1.461942195892334, "step": 415 }, { "epoch": 0.16013726050900773, "grad_norm": 0.2502294182777405, "learning_rate": 9.565715938678147e-05, "loss": 1.4835428237915038, "step": 420 }, { "epoch": 0.16204365646744828, "grad_norm": 0.2536308467388153, "learning_rate": 9.553044123889922e-05, "loss": 1.4969836235046388, "step": 425 }, { "epoch": 0.16395005242588886, "grad_norm": 0.2468816339969635, "learning_rate": 9.540198726569528e-05, "loss": 1.4650330543518066, "step": 430 }, { "epoch": 0.16585644838432942, "grad_norm": 0.27914702892303467, "learning_rate": 9.527180236441317e-05, "loss": 1.4838687896728515, "step": 435 }, { "epoch": 0.16776284434277, "grad_norm": 0.22599376738071442, "learning_rate": 9.513989149828718e-05, "loss": 1.4824600219726562, "step": 440 }, { "epoch": 0.16966924030121056, "grad_norm": 0.24725623428821564, "learning_rate": 9.50062596963532e-05, "loss": 1.4750584602355956, "step": 445 }, { "epoch": 0.17157563625965114, "grad_norm": 0.29999127984046936, "learning_rate": 9.487091205325687e-05, "loss": 1.4551380157470704, "step": 450 }, { "epoch": 0.1734820322180917, "grad_norm": 0.25167712569236755, "learning_rate": 9.47338537290595e-05, "loss": 1.495721435546875, "step": 455 }, { "epoch": 0.17538842817653227, "grad_norm": 0.24826137721538544, "learning_rate": 9.459508994904119e-05, "loss": 1.501543140411377, "step": 460 }, { "epoch": 0.17729482413497283, "grad_norm": 0.2614264190196991, "learning_rate": 9.44546260035017e-05, "loss": 1.5151371955871582, "step": 465 }, { "epoch": 0.1792012200934134, "grad_norm": 0.26163870096206665, "learning_rate": 9.431246724755877e-05, "loss": 1.4383647918701172, "step": 470 }, { "epoch": 0.18110761605185396, "grad_norm": 0.22550693154335022, "learning_rate": 9.416861910094397e-05, "loss": 1.5205669403076172, "step": 475 }, { "epoch": 0.18301401201029455, "grad_norm": 0.26660946011543274, "learning_rate": 9.402308704779599e-05, "loss": 1.436134147644043, "step": 480 }, { "epoch": 0.1849204079687351, "grad_norm": 0.24280768632888794, "learning_rate": 9.387587663645163e-05, "loss": 1.5114476203918457, "step": 485 }, { "epoch": 0.18682680392717568, "grad_norm": 0.25510141253471375, "learning_rate": 9.37269934792343e-05, "loss": 1.4367637634277344, "step": 490 }, { "epoch": 0.18873319988561624, "grad_norm": 0.2576332986354828, "learning_rate": 9.357644325223993e-05, "loss": 1.471407127380371, "step": 495 }, { "epoch": 0.19063959584405682, "grad_norm": 0.23395271599292755, "learning_rate": 9.342423169512071e-05, "loss": 1.4066363334655763, "step": 500 }, { "epoch": 0.19254599180249737, "grad_norm": 0.2984515428543091, "learning_rate": 9.327036461086622e-05, "loss": 1.468923854827881, "step": 505 }, { "epoch": 0.19445238776093796, "grad_norm": 0.24967055022716522, "learning_rate": 9.311484786558214e-05, "loss": 1.4417306900024414, "step": 510 }, { "epoch": 0.1963587837193785, "grad_norm": 0.2556474506855011, "learning_rate": 9.295768738826668e-05, "loss": 1.528633213043213, "step": 515 }, { "epoch": 0.1982651796778191, "grad_norm": 0.24390017986297607, "learning_rate": 9.279888917058452e-05, "loss": 1.4584775924682618, "step": 520 }, { "epoch": 0.20017157563625965, "grad_norm": 0.25844407081604004, "learning_rate": 9.263845926663835e-05, "loss": 1.4421388626098632, "step": 525 }, { "epoch": 0.20207797159470023, "grad_norm": 0.36213552951812744, "learning_rate": 9.247640379273811e-05, "loss": 1.4121234893798829, "step": 530 }, { "epoch": 0.20398436755314078, "grad_norm": 0.2492515742778778, "learning_rate": 9.231272892716774e-05, "loss": 1.4554323196411132, "step": 535 }, { "epoch": 0.20589076351158137, "grad_norm": 0.30490273237228394, "learning_rate": 9.214744090994973e-05, "loss": 1.4580575942993164, "step": 540 }, { "epoch": 0.20779715947002192, "grad_norm": 0.30119040608406067, "learning_rate": 9.198054604260714e-05, "loss": 1.4783581733703612, "step": 545 }, { "epoch": 0.2097035554284625, "grad_norm": 0.24260403215885162, "learning_rate": 9.181205068792339e-05, "loss": 1.4456222534179688, "step": 550 }, { "epoch": 0.21160995138690306, "grad_norm": 0.24098362028598785, "learning_rate": 9.164196126969969e-05, "loss": 1.4119773864746095, "step": 555 }, { "epoch": 0.21351634734534364, "grad_norm": 0.26129308342933655, "learning_rate": 9.14702842725101e-05, "loss": 1.4306962013244628, "step": 560 }, { "epoch": 0.2154227433037842, "grad_norm": 0.24792641401290894, "learning_rate": 9.129702624145438e-05, "loss": 1.4851024627685547, "step": 565 }, { "epoch": 0.21732913926222477, "grad_norm": 0.26257944107055664, "learning_rate": 9.112219378190837e-05, "loss": 1.4666027069091796, "step": 570 }, { "epoch": 0.21923553522066533, "grad_norm": 0.262560099363327, "learning_rate": 9.094579355927224e-05, "loss": 1.4559066772460938, "step": 575 }, { "epoch": 0.2211419311791059, "grad_norm": 0.2670407295227051, "learning_rate": 9.076783229871635e-05, "loss": 1.4089237213134767, "step": 580 }, { "epoch": 0.22304832713754646, "grad_norm": 0.25297465920448303, "learning_rate": 9.058831678492482e-05, "loss": 1.4622627258300782, "step": 585 }, { "epoch": 0.22495472309598705, "grad_norm": 0.2526761591434479, "learning_rate": 9.040725386183691e-05, "loss": 1.4129371643066406, "step": 590 }, { "epoch": 0.2268611190544276, "grad_norm": 0.30954116582870483, "learning_rate": 9.02246504323861e-05, "loss": 1.395735740661621, "step": 595 }, { "epoch": 0.22876751501286818, "grad_norm": 0.2452450692653656, "learning_rate": 9.004051345823689e-05, "loss": 1.4689098358154298, "step": 600 }, { "epoch": 0.23067391097130874, "grad_norm": 0.26220786571502686, "learning_rate": 8.98548499595194e-05, "loss": 1.4297904014587401, "step": 605 }, { "epoch": 0.23258030692974932, "grad_norm": 0.23016299307346344, "learning_rate": 8.966766701456177e-05, "loss": 1.4439301490783691, "step": 610 }, { "epoch": 0.23448670288818987, "grad_norm": 0.25978660583496094, "learning_rate": 8.947897175962021e-05, "loss": 1.4122808456420899, "step": 615 }, { "epoch": 0.23639309884663046, "grad_norm": 0.29846689105033875, "learning_rate": 8.928877138860707e-05, "loss": 1.380140209197998, "step": 620 }, { "epoch": 0.238299494805071, "grad_norm": 0.2431071400642395, "learning_rate": 8.909707315281644e-05, "loss": 1.4312551498413086, "step": 625 }, { "epoch": 0.2402058907635116, "grad_norm": 0.23043565452098846, "learning_rate": 8.890388436064775e-05, "loss": 1.4197410583496093, "step": 630 }, { "epoch": 0.24211228672195215, "grad_norm": 0.25711482763290405, "learning_rate": 8.870921237732721e-05, "loss": 1.4300183296203612, "step": 635 }, { "epoch": 0.24401868268039273, "grad_norm": 0.22921070456504822, "learning_rate": 8.851306462462688e-05, "loss": 1.4581551551818848, "step": 640 }, { "epoch": 0.24592507863883328, "grad_norm": 0.24076664447784424, "learning_rate": 8.831544858058183e-05, "loss": 1.4910277366638183, "step": 645 }, { "epoch": 0.24783147459727387, "grad_norm": 0.24699273705482483, "learning_rate": 8.8116371779205e-05, "loss": 1.4063929557800292, "step": 650 }, { "epoch": 0.24973787055571442, "grad_norm": 0.3326893150806427, "learning_rate": 8.791584181019996e-05, "loss": 1.4108802795410156, "step": 655 }, { "epoch": 0.251644266514155, "grad_norm": 0.3746221959590912, "learning_rate": 8.771386631867158e-05, "loss": 1.4183805465698243, "step": 660 }, { "epoch": 0.25355066247259556, "grad_norm": 0.2820988595485687, "learning_rate": 8.751045300483455e-05, "loss": 1.4383504867553711, "step": 665 }, { "epoch": 0.2554570584310361, "grad_norm": 0.28455182909965515, "learning_rate": 8.730560962371984e-05, "loss": 1.4205707550048827, "step": 670 }, { "epoch": 0.2573634543894767, "grad_norm": 0.2357279509305954, "learning_rate": 8.709934398487897e-05, "loss": 1.429055404663086, "step": 675 }, { "epoch": 0.2592698503479173, "grad_norm": 0.26164668798446655, "learning_rate": 8.689166395208636e-05, "loss": 1.4281024932861328, "step": 680 }, { "epoch": 0.26117624630635783, "grad_norm": 0.2792905271053314, "learning_rate": 8.668257744303952e-05, "loss": 1.4488028526306151, "step": 685 }, { "epoch": 0.2630826422647984, "grad_norm": 0.23465481400489807, "learning_rate": 8.647209242905708e-05, "loss": 1.393794631958008, "step": 690 }, { "epoch": 0.264989038223239, "grad_norm": 0.284840852022171, "learning_rate": 8.626021693477507e-05, "loss": 1.4296216011047362, "step": 695 }, { "epoch": 0.26689543418167955, "grad_norm": 0.2479892373085022, "learning_rate": 8.60469590378408e-05, "loss": 1.4239065170288085, "step": 700 }, { "epoch": 0.2688018301401201, "grad_norm": 0.3007226884365082, "learning_rate": 8.583232686860506e-05, "loss": 1.4247923851013184, "step": 705 }, { "epoch": 0.27070822609856066, "grad_norm": 0.2490592896938324, "learning_rate": 8.561632860981205e-05, "loss": 1.4240179061889648, "step": 710 }, { "epoch": 0.27261462205700127, "grad_norm": 0.25223028659820557, "learning_rate": 8.539897249628745e-05, "loss": 1.4027082443237304, "step": 715 }, { "epoch": 0.2745210180154418, "grad_norm": 0.2591800391674042, "learning_rate": 8.518026681462448e-05, "loss": 1.3855839729309083, "step": 720 }, { "epoch": 0.2764274139738824, "grad_norm": 0.29331284761428833, "learning_rate": 8.496021990286798e-05, "loss": 1.418544864654541, "step": 725 }, { "epoch": 0.27833380993232293, "grad_norm": 0.25057944655418396, "learning_rate": 8.473884015019648e-05, "loss": 1.4180222511291505, "step": 730 }, { "epoch": 0.28024020589076354, "grad_norm": 0.22133305668830872, "learning_rate": 8.451613599660249e-05, "loss": 1.3833829879760742, "step": 735 }, { "epoch": 0.2821466018492041, "grad_norm": 0.251863569021225, "learning_rate": 8.429211593257054e-05, "loss": 1.4573945999145508, "step": 740 }, { "epoch": 0.28405299780764465, "grad_norm": 0.2532324492931366, "learning_rate": 8.406678849875363e-05, "loss": 1.4017548561096191, "step": 745 }, { "epoch": 0.2859593937660852, "grad_norm": 0.2683808207511902, "learning_rate": 8.384016228564759e-05, "loss": 1.4019456863403321, "step": 750 }, { "epoch": 0.2878657897245258, "grad_norm": 0.2368578314781189, "learning_rate": 8.36122459332636e-05, "loss": 1.4322586059570312, "step": 755 }, { "epoch": 0.28977218568296637, "grad_norm": 0.24327214062213898, "learning_rate": 8.338304813079865e-05, "loss": 1.3828792572021484, "step": 760 }, { "epoch": 0.2916785816414069, "grad_norm": 0.26548320055007935, "learning_rate": 8.315257761630444e-05, "loss": 1.4083205223083497, "step": 765 }, { "epoch": 0.2935849775998475, "grad_norm": 0.25241178274154663, "learning_rate": 8.29208431763542e-05, "loss": 1.413995361328125, "step": 770 }, { "epoch": 0.2954913735582881, "grad_norm": 0.30916735529899597, "learning_rate": 8.268785364570767e-05, "loss": 1.3871379852294923, "step": 775 }, { "epoch": 0.29739776951672864, "grad_norm": 0.2495160698890686, "learning_rate": 8.245361790697426e-05, "loss": 1.3945639610290528, "step": 780 }, { "epoch": 0.2993041654751692, "grad_norm": 0.2700437605381012, "learning_rate": 8.221814489027447e-05, "loss": 1.4237943649291993, "step": 785 }, { "epoch": 0.30121056143360975, "grad_norm": 0.23574313521385193, "learning_rate": 8.19814435728994e-05, "loss": 1.385953998565674, "step": 790 }, { "epoch": 0.3031169573920503, "grad_norm": 0.24942244589328766, "learning_rate": 8.174352297896851e-05, "loss": 1.3988289833068848, "step": 795 }, { "epoch": 0.3050233533504909, "grad_norm": 0.280823677778244, "learning_rate": 8.150439217908556e-05, "loss": 1.3632831573486328, "step": 800 }, { "epoch": 0.30692974930893147, "grad_norm": 0.255289763212204, "learning_rate": 8.12640602899928e-05, "loss": 1.3655292510986328, "step": 805 }, { "epoch": 0.308836145267372, "grad_norm": 0.29499486088752747, "learning_rate": 8.102253647422341e-05, "loss": 1.3923774719238282, "step": 810 }, { "epoch": 0.3107425412258126, "grad_norm": 0.2698020339012146, "learning_rate": 8.077982993975221e-05, "loss": 1.471755027770996, "step": 815 }, { "epoch": 0.3126489371842532, "grad_norm": 0.29889410734176636, "learning_rate": 8.053594993964452e-05, "loss": 1.3912424087524413, "step": 820 }, { "epoch": 0.31455533314269374, "grad_norm": 0.22284908592700958, "learning_rate": 8.029090577170351e-05, "loss": 1.4176401138305663, "step": 825 }, { "epoch": 0.3164617291011343, "grad_norm": 0.2976219058036804, "learning_rate": 8.00447067781156e-05, "loss": 1.439077663421631, "step": 830 }, { "epoch": 0.31836812505957485, "grad_norm": 0.24919576942920685, "learning_rate": 7.979736234509444e-05, "loss": 1.408050537109375, "step": 835 }, { "epoch": 0.32027452101801546, "grad_norm": 0.2600626051425934, "learning_rate": 7.954888190252292e-05, "loss": 1.3918458938598632, "step": 840 }, { "epoch": 0.322180916976456, "grad_norm": 0.253104031085968, "learning_rate": 7.929927492359377e-05, "loss": 1.4648473739624024, "step": 845 }, { "epoch": 0.32408731293489657, "grad_norm": 0.22518160939216614, "learning_rate": 7.904855092444833e-05, "loss": 1.4031518936157226, "step": 850 }, { "epoch": 0.3259937088933371, "grad_norm": 0.28883233666419983, "learning_rate": 7.87967194638138e-05, "loss": 1.3993185043334961, "step": 855 }, { "epoch": 0.32790010485177773, "grad_norm": 0.28593140840530396, "learning_rate": 7.854379014263876e-05, "loss": 1.3652525901794434, "step": 860 }, { "epoch": 0.3298065008102183, "grad_norm": 0.22951166331768036, "learning_rate": 7.828977260372722e-05, "loss": 1.4364437103271483, "step": 865 }, { "epoch": 0.33171289676865884, "grad_norm": 0.29228949546813965, "learning_rate": 7.803467653137091e-05, "loss": 1.4088499069213867, "step": 870 }, { "epoch": 0.3336192927270994, "grad_norm": 0.2429066151380539, "learning_rate": 7.777851165098012e-05, "loss": 1.37188777923584, "step": 875 }, { "epoch": 0.33552568868554, "grad_norm": 0.33716997504234314, "learning_rate": 7.752128772871292e-05, "loss": 1.363558292388916, "step": 880 }, { "epoch": 0.33743208464398056, "grad_norm": 0.24004337191581726, "learning_rate": 7.726301457110282e-05, "loss": 1.4081727027893067, "step": 885 }, { "epoch": 0.3393384806024211, "grad_norm": 0.24102216958999634, "learning_rate": 7.700370202468489e-05, "loss": 1.3424272537231445, "step": 890 }, { "epoch": 0.34124487656086167, "grad_norm": 0.2801651656627655, "learning_rate": 7.674335997562043e-05, "loss": 1.3846661567687988, "step": 895 }, { "epoch": 0.3431512725193023, "grad_norm": 0.19731613993644714, "learning_rate": 7.648199834931992e-05, "loss": 1.438795280456543, "step": 900 }, { "epoch": 0.34505766847774283, "grad_norm": 0.2224002629518509, "learning_rate": 7.621962711006479e-05, "loss": 1.3394567489624023, "step": 905 }, { "epoch": 0.3469640644361834, "grad_norm": 0.30952727794647217, "learning_rate": 7.595625626062744e-05, "loss": 1.3653787612915038, "step": 910 }, { "epoch": 0.34887046039462394, "grad_norm": 0.2750058174133301, "learning_rate": 7.569189584188989e-05, "loss": 1.3910099029541017, "step": 915 }, { "epoch": 0.35077685635306455, "grad_norm": 0.2625235915184021, "learning_rate": 7.542655593246103e-05, "loss": 1.3822028160095214, "step": 920 }, { "epoch": 0.3526832523115051, "grad_norm": 0.2934473752975464, "learning_rate": 7.51602466482923e-05, "loss": 1.399022388458252, "step": 925 }, { "epoch": 0.35458964826994566, "grad_norm": 0.25218287110328674, "learning_rate": 7.48929781422921e-05, "loss": 1.394824504852295, "step": 930 }, { "epoch": 0.3564960442283862, "grad_norm": 0.28869032859802246, "learning_rate": 7.46247606039387e-05, "loss": 1.4306042671203614, "step": 935 }, { "epoch": 0.3584024401868268, "grad_norm": 0.24312981963157654, "learning_rate": 7.435560425889169e-05, "loss": 1.398825740814209, "step": 940 }, { "epoch": 0.3603088361452674, "grad_norm": 0.2509699761867523, "learning_rate": 7.408551936860224e-05, "loss": 1.3485726356506347, "step": 945 }, { "epoch": 0.36221523210370793, "grad_norm": 0.22470155358314514, "learning_rate": 7.381451622992184e-05, "loss": 1.3923337936401368, "step": 950 }, { "epoch": 0.3641216280621485, "grad_norm": 0.32364603877067566, "learning_rate": 7.354260517470975e-05, "loss": 1.334847640991211, "step": 955 }, { "epoch": 0.3660280240205891, "grad_norm": 0.2654114365577698, "learning_rate": 7.326979656943906e-05, "loss": 1.3885457992553711, "step": 960 }, { "epoch": 0.36793441997902965, "grad_norm": 0.3019956350326538, "learning_rate": 7.299610081480155e-05, "loss": 1.4311206817626954, "step": 965 }, { "epoch": 0.3698408159374702, "grad_norm": 0.25415265560150146, "learning_rate": 7.272152834531112e-05, "loss": 1.3751686096191407, "step": 970 }, { "epoch": 0.37174721189591076, "grad_norm": 0.30601051449775696, "learning_rate": 7.244608962890593e-05, "loss": 1.4377851486206055, "step": 975 }, { "epoch": 0.37365360785435137, "grad_norm": 0.24736209213733673, "learning_rate": 7.216979516654943e-05, "loss": 1.3647064208984374, "step": 980 }, { "epoch": 0.3755600038127919, "grad_norm": 0.26788419485092163, "learning_rate": 7.189265549182995e-05, "loss": 1.3745835304260254, "step": 985 }, { "epoch": 0.3774663997712325, "grad_norm": 0.2601538300514221, "learning_rate": 7.161468117055911e-05, "loss": 1.4127769470214844, "step": 990 }, { "epoch": 0.37937279572967303, "grad_norm": 0.2553812265396118, "learning_rate": 7.133588280036899e-05, "loss": 1.420806312561035, "step": 995 }, { "epoch": 0.38127919168811364, "grad_norm": 0.25586581230163574, "learning_rate": 7.105627101030817e-05, "loss": 1.3908451080322266, "step": 1000 }, { "epoch": 0.3831855876465542, "grad_norm": 0.25829628109931946, "learning_rate": 7.07758564604364e-05, "loss": 1.3931778907775878, "step": 1005 }, { "epoch": 0.38509198360499475, "grad_norm": 0.2720872163772583, "learning_rate": 7.04946498414183e-05, "loss": 1.3420132637023925, "step": 1010 }, { "epoch": 0.3869983795634353, "grad_norm": 0.23615601658821106, "learning_rate": 7.021266187411572e-05, "loss": 1.3387642860412599, "step": 1015 }, { "epoch": 0.3889047755218759, "grad_norm": 0.28808966279029846, "learning_rate": 6.992990330917896e-05, "loss": 1.3504127502441405, "step": 1020 }, { "epoch": 0.39081117148031647, "grad_norm": 0.25406962633132935, "learning_rate": 6.964638492663708e-05, "loss": 1.377500343322754, "step": 1025 }, { "epoch": 0.392717567438757, "grad_norm": 0.24571816623210907, "learning_rate": 6.93621175354867e-05, "loss": 1.3347816467285156, "step": 1030 }, { "epoch": 0.3946239633971976, "grad_norm": 0.253203809261322, "learning_rate": 6.907711197328011e-05, "loss": 1.4103373527526855, "step": 1035 }, { "epoch": 0.3965303593556382, "grad_norm": 0.37093397974967957, "learning_rate": 6.879137910571191e-05, "loss": 1.3626442909240724, "step": 1040 }, { "epoch": 0.39843675531407874, "grad_norm": 0.2757250666618347, "learning_rate": 6.850492982620494e-05, "loss": 1.3676484107971192, "step": 1045 }, { "epoch": 0.4003431512725193, "grad_norm": 0.23742161691188812, "learning_rate": 6.821777505549484e-05, "loss": 1.340796947479248, "step": 1050 }, { "epoch": 0.40224954723095985, "grad_norm": 0.24769580364227295, "learning_rate": 6.792992574121374e-05, "loss": 1.3983160972595214, "step": 1055 }, { "epoch": 0.40415594318940046, "grad_norm": 0.26636403799057007, "learning_rate": 6.764139285747292e-05, "loss": 1.330171489715576, "step": 1060 }, { "epoch": 0.406062339147841, "grad_norm": 0.24734552204608917, "learning_rate": 6.735218740444442e-05, "loss": 1.3838493347167968, "step": 1065 }, { "epoch": 0.40796873510628157, "grad_norm": 0.2548673748970032, "learning_rate": 6.706232040794161e-05, "loss": 1.388270378112793, "step": 1070 }, { "epoch": 0.4098751310647221, "grad_norm": 0.2421494573354721, "learning_rate": 6.677180291899892e-05, "loss": 1.3804280281066894, "step": 1075 }, { "epoch": 0.41178152702316273, "grad_norm": 0.33268406987190247, "learning_rate": 6.64806460134504e-05, "loss": 1.4276175498962402, "step": 1080 }, { "epoch": 0.4136879229816033, "grad_norm": 0.24848121404647827, "learning_rate": 6.618886079150764e-05, "loss": 1.3721673965454102, "step": 1085 }, { "epoch": 0.41559431894004384, "grad_norm": 0.21902380883693695, "learning_rate": 6.58964583773364e-05, "loss": 1.3873804092407227, "step": 1090 }, { "epoch": 0.4175007148984844, "grad_norm": 0.25105956196784973, "learning_rate": 6.56034499186326e-05, "loss": 1.3554351806640625, "step": 1095 }, { "epoch": 0.419407110856925, "grad_norm": 0.3022575080394745, "learning_rate": 6.530984658619734e-05, "loss": 1.3639636993408204, "step": 1100 }, { "epoch": 0.42131350681536556, "grad_norm": 0.27669885754585266, "learning_rate": 6.501565957351097e-05, "loss": 1.3871520042419434, "step": 1105 }, { "epoch": 0.4232199027738061, "grad_norm": 0.26725828647613525, "learning_rate": 6.472090009630634e-05, "loss": 1.2727947235107422, "step": 1110 }, { "epoch": 0.42512629873224667, "grad_norm": 0.26539531350135803, "learning_rate": 6.442557939214125e-05, "loss": 1.3116284370422364, "step": 1115 }, { "epoch": 0.4270326946906873, "grad_norm": 0.29391223192214966, "learning_rate": 6.412970871996995e-05, "loss": 1.3417422294616699, "step": 1120 }, { "epoch": 0.42893909064912783, "grad_norm": 0.27035921812057495, "learning_rate": 6.383329935971399e-05, "loss": 1.331747817993164, "step": 1125 }, { "epoch": 0.4308454866075684, "grad_norm": 0.2546106278896332, "learning_rate": 6.353636261183213e-05, "loss": 1.355039405822754, "step": 1130 }, { "epoch": 0.43275188256600894, "grad_norm": 0.23129746317863464, "learning_rate": 6.323890979688951e-05, "loss": 1.3793773651123047, "step": 1135 }, { "epoch": 0.43465827852444955, "grad_norm": 0.2750200033187866, "learning_rate": 6.294095225512603e-05, "loss": 1.2835375785827636, "step": 1140 }, { "epoch": 0.4365646744828901, "grad_norm": 0.2910929322242737, "learning_rate": 6.264250134602416e-05, "loss": 1.2731900215148926, "step": 1145 }, { "epoch": 0.43847107044133066, "grad_norm": 0.23885288834571838, "learning_rate": 6.234356844787563e-05, "loss": 1.3810148239135742, "step": 1150 }, { "epoch": 0.4403774663997712, "grad_norm": 0.2842715084552765, "learning_rate": 6.204416495734781e-05, "loss": 1.3476411819458007, "step": 1155 }, { "epoch": 0.4422838623582118, "grad_norm": 0.27236074209213257, "learning_rate": 6.174430228904919e-05, "loss": 1.3782694816589356, "step": 1160 }, { "epoch": 0.4441902583166524, "grad_norm": 0.2982919216156006, "learning_rate": 6.144399187509416e-05, "loss": 1.3414841651916505, "step": 1165 }, { "epoch": 0.44609665427509293, "grad_norm": 0.2682361304759979, "learning_rate": 6.11432451646672e-05, "loss": 1.3429731369018554, "step": 1170 }, { "epoch": 0.4480030502335335, "grad_norm": 0.29433199763298035, "learning_rate": 6.084207362358635e-05, "loss": 1.3581157684326173, "step": 1175 }, { "epoch": 0.4499094461919741, "grad_norm": 0.22920751571655273, "learning_rate": 6.054048873386613e-05, "loss": 1.3716768264770507, "step": 1180 }, { "epoch": 0.45181584215041465, "grad_norm": 0.2386595457792282, "learning_rate": 6.0238501993279784e-05, "loss": 1.297121238708496, "step": 1185 }, { "epoch": 0.4537222381088552, "grad_norm": 0.28741690516471863, "learning_rate": 5.993612491492088e-05, "loss": 1.3232603073120117, "step": 1190 }, { "epoch": 0.45562863406729576, "grad_norm": 0.2324090301990509, "learning_rate": 5.963336902676445e-05, "loss": 1.3853673934936523, "step": 1195 }, { "epoch": 0.45753503002573637, "grad_norm": 0.2917945683002472, "learning_rate": 5.9330245871227454e-05, "loss": 1.3603765487670898, "step": 1200 }, { "epoch": 0.4594414259841769, "grad_norm": 0.30369922518730164, "learning_rate": 5.902676700472873e-05, "loss": 1.3104385375976562, "step": 1205 }, { "epoch": 0.4613478219426175, "grad_norm": 0.29477372765541077, "learning_rate": 5.872294399724842e-05, "loss": 1.331740951538086, "step": 1210 }, { "epoch": 0.46325421790105803, "grad_norm": 0.2806938588619232, "learning_rate": 5.841878843188684e-05, "loss": 1.3606687545776368, "step": 1215 }, { "epoch": 0.46516061385949864, "grad_norm": 0.2490273416042328, "learning_rate": 5.8114311904423004e-05, "loss": 1.3449721336364746, "step": 1220 }, { "epoch": 0.4670670098179392, "grad_norm": 0.2897224426269531, "learning_rate": 5.780952602287233e-05, "loss": 1.3665520668029785, "step": 1225 }, { "epoch": 0.46897340577637975, "grad_norm": 0.24134814739227295, "learning_rate": 5.750444240704429e-05, "loss": 1.3601598739624023, "step": 1230 }, { "epoch": 0.4708798017348203, "grad_norm": 0.27711760997772217, "learning_rate": 5.7199072688099266e-05, "loss": 1.3746469497680665, "step": 1235 }, { "epoch": 0.4727861976932609, "grad_norm": 0.23725396394729614, "learning_rate": 5.6893428508105225e-05, "loss": 1.3549458503723144, "step": 1240 }, { "epoch": 0.47469259365170147, "grad_norm": 0.2515436112880707, "learning_rate": 5.65875215195938e-05, "loss": 1.372105026245117, "step": 1245 }, { "epoch": 0.476598989610142, "grad_norm": 0.2758740782737732, "learning_rate": 5.628136338511607e-05, "loss": 1.3271823883056642, "step": 1250 }, { "epoch": 0.4785053855685826, "grad_norm": 0.2380417436361313, "learning_rate": 5.597496577679793e-05, "loss": 1.2887084007263183, "step": 1255 }, { "epoch": 0.4804117815270232, "grad_norm": 0.34265971183776855, "learning_rate": 5.566834037589511e-05, "loss": 1.3523871421813964, "step": 1260 }, { "epoch": 0.48231817748546374, "grad_norm": 0.3290402591228485, "learning_rate": 5.5361498872347804e-05, "loss": 1.287813377380371, "step": 1265 }, { "epoch": 0.4842245734439043, "grad_norm": 0.2645690143108368, "learning_rate": 5.5054452964335004e-05, "loss": 1.3339000701904298, "step": 1270 }, { "epoch": 0.48613096940234485, "grad_norm": 0.2834484875202179, "learning_rate": 5.4747214357828535e-05, "loss": 1.3187914848327638, "step": 1275 }, { "epoch": 0.48803736536078546, "grad_norm": 0.25123342871665955, "learning_rate": 5.4439794766146746e-05, "loss": 1.3513497352600097, "step": 1280 }, { "epoch": 0.489943761319226, "grad_norm": 0.2649517357349396, "learning_rate": 5.413220590950796e-05, "loss": 1.3626354217529297, "step": 1285 }, { "epoch": 0.49185015727766657, "grad_norm": 0.24755874276161194, "learning_rate": 5.382445951458365e-05, "loss": 1.355795192718506, "step": 1290 }, { "epoch": 0.4937565532361071, "grad_norm": 0.24829553067684174, "learning_rate": 5.351656731405133e-05, "loss": 1.3056276321411133, "step": 1295 }, { "epoch": 0.49566294919454773, "grad_norm": 0.260469526052475, "learning_rate": 5.3208541046147306e-05, "loss": 1.328080940246582, "step": 1300 }, { "epoch": 0.4975693451529883, "grad_norm": 0.2671087086200714, "learning_rate": 5.290039245421914e-05, "loss": 1.3472344398498535, "step": 1305 }, { "epoch": 0.49947574111142884, "grad_norm": 0.29492273926734924, "learning_rate": 5.259213328627792e-05, "loss": 1.2832697868347167, "step": 1310 }, { "epoch": 0.5013821370698694, "grad_norm": 0.25961264967918396, "learning_rate": 5.228377529455039e-05, "loss": 1.3272671699523926, "step": 1315 }, { "epoch": 0.50328853302831, "grad_norm": 0.2618507742881775, "learning_rate": 5.197533023503089e-05, "loss": 1.3849388122558595, "step": 1320 }, { "epoch": 0.5051949289867506, "grad_norm": 0.27279746532440186, "learning_rate": 5.166680986703323e-05, "loss": 1.2919696807861327, "step": 1325 }, { "epoch": 0.5071013249451911, "grad_norm": 0.24809473752975464, "learning_rate": 5.1358225952742246e-05, "loss": 1.3210315704345703, "step": 1330 }, { "epoch": 0.5090077209036317, "grad_norm": 0.25010329484939575, "learning_rate": 5.104959025676548e-05, "loss": 1.2906679153442382, "step": 1335 }, { "epoch": 0.5109141168620722, "grad_norm": 0.298988938331604, "learning_rate": 5.074091454568464e-05, "loss": 1.3387374877929688, "step": 1340 }, { "epoch": 0.5128205128205128, "grad_norm": 0.27491581439971924, "learning_rate": 5.043221058760695e-05, "loss": 1.3015724182128907, "step": 1345 }, { "epoch": 0.5147269087789534, "grad_norm": 0.25862807035446167, "learning_rate": 5.012349015171659e-05, "loss": 1.3090481758117676, "step": 1350 }, { "epoch": 0.516633304737394, "grad_norm": 0.22323614358901978, "learning_rate": 4.981476500782591e-05, "loss": 1.2918867111206054, "step": 1355 }, { "epoch": 0.5185397006958345, "grad_norm": 0.2747284471988678, "learning_rate": 4.950604692592672e-05, "loss": 1.3748528480529785, "step": 1360 }, { "epoch": 0.5204460966542751, "grad_norm": 0.29153740406036377, "learning_rate": 4.919734767574167e-05, "loss": 1.3216867446899414, "step": 1365 }, { "epoch": 0.5223524926127157, "grad_norm": 0.2901960015296936, "learning_rate": 4.888867902627544e-05, "loss": 1.2926323890686036, "step": 1370 }, { "epoch": 0.5242588885711562, "grad_norm": 0.29376184940338135, "learning_rate": 4.8580052745365996e-05, "loss": 1.3518081665039063, "step": 1375 }, { "epoch": 0.5261652845295968, "grad_norm": 0.2881779074668884, "learning_rate": 4.827148059923614e-05, "loss": 1.3113883972167968, "step": 1380 }, { "epoch": 0.5280716804880373, "grad_norm": 0.23365597426891327, "learning_rate": 4.796297435204473e-05, "loss": 1.328169822692871, "step": 1385 }, { "epoch": 0.529978076446478, "grad_norm": 0.3102223575115204, "learning_rate": 4.76545457654383e-05, "loss": 1.2958507537841797, "step": 1390 }, { "epoch": 0.5318844724049185, "grad_norm": 0.3015563189983368, "learning_rate": 4.73462065981026e-05, "loss": 1.305961513519287, "step": 1395 }, { "epoch": 0.5337908683633591, "grad_norm": 0.24197225272655487, "learning_rate": 4.703796860531429e-05, "loss": 1.3416491508483888, "step": 1400 }, { "epoch": 0.5356972643217996, "grad_norm": 0.29191067814826965, "learning_rate": 4.6729843538492847e-05, "loss": 1.2949129104614259, "step": 1405 }, { "epoch": 0.5376036602802402, "grad_norm": 0.2928674519062042, "learning_rate": 4.642184314475249e-05, "loss": 1.3139276504516602, "step": 1410 }, { "epoch": 0.5395100562386808, "grad_norm": 0.26519039273262024, "learning_rate": 4.6113979166454295e-05, "loss": 1.3090953826904297, "step": 1415 }, { "epoch": 0.5414164521971213, "grad_norm": 0.27504435181617737, "learning_rate": 4.5806263340758645e-05, "loss": 1.3588967323303223, "step": 1420 }, { "epoch": 0.5433228481555619, "grad_norm": 0.2822822332382202, "learning_rate": 4.54987073991776e-05, "loss": 1.2958033561706543, "step": 1425 }, { "epoch": 0.5452292441140025, "grad_norm": 0.29674676060676575, "learning_rate": 4.519132306712778e-05, "loss": 1.266901969909668, "step": 1430 }, { "epoch": 0.5471356400724431, "grad_norm": 0.2783163785934448, "learning_rate": 4.488412206348325e-05, "loss": 1.3179558753967284, "step": 1435 }, { "epoch": 0.5490420360308836, "grad_norm": 0.2501155138015747, "learning_rate": 4.4577116100128735e-05, "loss": 1.317795181274414, "step": 1440 }, { "epoch": 0.5509484319893242, "grad_norm": 0.2776888608932495, "learning_rate": 4.427031688151321e-05, "loss": 1.2918581008911132, "step": 1445 }, { "epoch": 0.5528548279477647, "grad_norm": 0.2992541193962097, "learning_rate": 4.396373610420362e-05, "loss": 1.329861545562744, "step": 1450 }, { "epoch": 0.5547612239062053, "grad_norm": 0.3052087724208832, "learning_rate": 4.365738545643884e-05, "loss": 1.2998424530029298, "step": 1455 }, { "epoch": 0.5566676198646459, "grad_norm": 0.27905166149139404, "learning_rate": 4.335127661768429e-05, "loss": 1.3324199676513673, "step": 1460 }, { "epoch": 0.5585740158230864, "grad_norm": 0.28347963094711304, "learning_rate": 4.304542125818648e-05, "loss": 1.3317461967468263, "step": 1465 }, { "epoch": 0.5604804117815271, "grad_norm": 0.29316428303718567, "learning_rate": 4.273983103852815e-05, "loss": 1.3193351745605468, "step": 1470 }, { "epoch": 0.5623868077399676, "grad_norm": 0.29219284653663635, "learning_rate": 4.243451760918375e-05, "loss": 1.328935146331787, "step": 1475 }, { "epoch": 0.5642932036984082, "grad_norm": 0.34995195269584656, "learning_rate": 4.212949261007519e-05, "loss": 1.2937623977661132, "step": 1480 }, { "epoch": 0.5661995996568487, "grad_norm": 0.2483871728181839, "learning_rate": 4.1824767670128154e-05, "loss": 1.3481175422668457, "step": 1485 }, { "epoch": 0.5681059956152893, "grad_norm": 0.2733031213283539, "learning_rate": 4.1520354406828736e-05, "loss": 1.27366304397583, "step": 1490 }, { "epoch": 0.5700123915737298, "grad_norm": 0.3554569482803345, "learning_rate": 4.121626442578045e-05, "loss": 1.3291565895080566, "step": 1495 }, { "epoch": 0.5719187875321704, "grad_norm": 0.2724780738353729, "learning_rate": 4.0912509320261914e-05, "loss": 1.3142485618591309, "step": 1500 }, { "epoch": 0.573825183490611, "grad_norm": 0.2626362442970276, "learning_rate": 4.060910067078475e-05, "loss": 1.2978642463684082, "step": 1505 }, { "epoch": 0.5757315794490516, "grad_norm": 0.277729868888855, "learning_rate": 4.030605004465207e-05, "loss": 1.2920963287353515, "step": 1510 }, { "epoch": 0.5776379754074922, "grad_norm": 0.28084853291511536, "learning_rate": 4.000336899551759e-05, "loss": 1.2903416633605957, "step": 1515 }, { "epoch": 0.5795443713659327, "grad_norm": 0.3141873776912689, "learning_rate": 3.970106906294509e-05, "loss": 1.300405788421631, "step": 1520 }, { "epoch": 0.5814507673243733, "grad_norm": 0.34942084550857544, "learning_rate": 3.939916177196841e-05, "loss": 1.325791358947754, "step": 1525 }, { "epoch": 0.5833571632828138, "grad_norm": 0.3157213032245636, "learning_rate": 3.909765863265219e-05, "loss": 1.2976320266723633, "step": 1530 }, { "epoch": 0.5852635592412544, "grad_norm": 0.29693111777305603, "learning_rate": 3.879657113965294e-05, "loss": 1.2306509971618653, "step": 1535 }, { "epoch": 0.587169955199695, "grad_norm": 0.30891987681388855, "learning_rate": 3.84959107717809e-05, "loss": 1.3545056343078614, "step": 1540 }, { "epoch": 0.5890763511581355, "grad_norm": 0.3011731207370758, "learning_rate": 3.819568899156236e-05, "loss": 1.307596778869629, "step": 1545 }, { "epoch": 0.5909827471165762, "grad_norm": 0.29167380928993225, "learning_rate": 3.7895917244802656e-05, "loss": 1.3272083282470704, "step": 1550 }, { "epoch": 0.5928891430750167, "grad_norm": 0.263597697019577, "learning_rate": 3.759660696014987e-05, "loss": 1.33306827545166, "step": 1555 }, { "epoch": 0.5947955390334573, "grad_norm": 0.25330621004104614, "learning_rate": 3.729776954865905e-05, "loss": 1.2714315414428712, "step": 1560 }, { "epoch": 0.5967019349918978, "grad_norm": 0.2821616530418396, "learning_rate": 3.699941640335716e-05, "loss": 1.3136507034301759, "step": 1565 }, { "epoch": 0.5986083309503384, "grad_norm": 0.2773730158805847, "learning_rate": 3.670155889880881e-05, "loss": 1.3050535202026368, "step": 1570 }, { "epoch": 0.6005147269087789, "grad_norm": 0.24520425498485565, "learning_rate": 3.64042083906825e-05, "loss": 1.3005794525146483, "step": 1575 }, { "epoch": 0.6024211228672195, "grad_norm": 0.28279751539230347, "learning_rate": 3.6107376215317815e-05, "loss": 1.2946210861206056, "step": 1580 }, { "epoch": 0.60432751882566, "grad_norm": 0.268442302942276, "learning_rate": 3.5811073689293084e-05, "loss": 1.320157814025879, "step": 1585 }, { "epoch": 0.6062339147841006, "grad_norm": 0.2854236364364624, "learning_rate": 3.551531210899406e-05, "loss": 1.3783449172973632, "step": 1590 }, { "epoch": 0.6081403107425413, "grad_norm": 0.2724571228027344, "learning_rate": 3.522010275018322e-05, "loss": 1.2988112449645997, "step": 1595 }, { "epoch": 0.6100467067009818, "grad_norm": 0.24997997283935547, "learning_rate": 3.492545686756986e-05, "loss": 1.282177734375, "step": 1600 }, { "epoch": 0.6119531026594224, "grad_norm": 0.2501998543739319, "learning_rate": 3.4631385694381e-05, "loss": 1.2766773223876953, "step": 1605 }, { "epoch": 0.6138594986178629, "grad_norm": 0.26247185468673706, "learning_rate": 3.433790044193323e-05, "loss": 1.3106462478637695, "step": 1610 }, { "epoch": 0.6157658945763035, "grad_norm": 0.27473998069763184, "learning_rate": 3.40450122992051e-05, "loss": 1.271501350402832, "step": 1615 }, { "epoch": 0.617672290534744, "grad_norm": 0.30904969573020935, "learning_rate": 3.375273243241071e-05, "loss": 1.2359012603759765, "step": 1620 }, { "epoch": 0.6195786864931846, "grad_norm": 0.27315428853034973, "learning_rate": 3.3461071984573986e-05, "loss": 1.304299545288086, "step": 1625 }, { "epoch": 0.6214850824516251, "grad_norm": 0.3226105570793152, "learning_rate": 3.317004207510369e-05, "loss": 1.3027402877807617, "step": 1630 }, { "epoch": 0.6233914784100658, "grad_norm": 0.2585526406764984, "learning_rate": 3.287965379936974e-05, "loss": 1.2923802375793456, "step": 1635 }, { "epoch": 0.6252978743685064, "grad_norm": 0.32294324040412903, "learning_rate": 3.258991822828007e-05, "loss": 1.356869888305664, "step": 1640 }, { "epoch": 0.6272042703269469, "grad_norm": 0.29488036036491394, "learning_rate": 3.230084640785851e-05, "loss": 1.3255125045776368, "step": 1645 }, { "epoch": 0.6291106662853875, "grad_norm": 0.3081420660018921, "learning_rate": 3.2012449358823796e-05, "loss": 1.311000442504883, "step": 1650 }, { "epoch": 0.631017062243828, "grad_norm": 0.2720779776573181, "learning_rate": 3.172473807616931e-05, "loss": 1.2965307235717773, "step": 1655 }, { "epoch": 0.6329234582022686, "grad_norm": 0.28681716322898865, "learning_rate": 3.1437723528743934e-05, "loss": 1.3056275367736816, "step": 1660 }, { "epoch": 0.6348298541607091, "grad_norm": 0.29165732860565186, "learning_rate": 3.11514166588339e-05, "loss": 1.3133922576904298, "step": 1665 }, { "epoch": 0.6367362501191497, "grad_norm": 0.25299572944641113, "learning_rate": 3.086582838174551e-05, "loss": 1.2984167098999024, "step": 1670 }, { "epoch": 0.6386426460775904, "grad_norm": 0.24326911568641663, "learning_rate": 3.058096958538917e-05, "loss": 1.3146974563598632, "step": 1675 }, { "epoch": 0.6405490420360309, "grad_norm": 0.2539363503456116, "learning_rate": 3.0296851129864168e-05, "loss": 1.2391217231750489, "step": 1680 }, { "epoch": 0.6424554379944715, "grad_norm": 0.25005969405174255, "learning_rate": 3.001348384704461e-05, "loss": 1.2616147994995117, "step": 1685 }, { "epoch": 0.644361833952912, "grad_norm": 0.2587001323699951, "learning_rate": 2.9730878540166585e-05, "loss": 1.2715343475341796, "step": 1690 }, { "epoch": 0.6462682299113526, "grad_norm": 0.24096567928791046, "learning_rate": 2.9449045983416207e-05, "loss": 1.314798927307129, "step": 1695 }, { "epoch": 0.6481746258697931, "grad_norm": 0.2563248574733734, "learning_rate": 2.9167996921518848e-05, "loss": 1.3071712493896483, "step": 1700 }, { "epoch": 0.6500810218282337, "grad_norm": 0.22646738588809967, "learning_rate": 2.8887742069329606e-05, "loss": 1.2838253021240233, "step": 1705 }, { "epoch": 0.6519874177866742, "grad_norm": 0.28143811225891113, "learning_rate": 2.860829211142466e-05, "loss": 1.2992055892944336, "step": 1710 }, { "epoch": 0.6538938137451149, "grad_norm": 0.28922876715660095, "learning_rate": 2.8329657701694013e-05, "loss": 1.33804349899292, "step": 1715 }, { "epoch": 0.6558002097035555, "grad_norm": 0.3674686849117279, "learning_rate": 2.805184946293532e-05, "loss": 1.281188678741455, "step": 1720 }, { "epoch": 0.657706605661996, "grad_norm": 0.3004717528820038, "learning_rate": 2.7774877986448856e-05, "loss": 1.2528301239013673, "step": 1725 }, { "epoch": 0.6596130016204366, "grad_norm": 0.2616945207118988, "learning_rate": 2.7498753831633773e-05, "loss": 1.2314598083496093, "step": 1730 }, { "epoch": 0.6615193975788771, "grad_norm": 0.31714972853660583, "learning_rate": 2.722348752558552e-05, "loss": 1.2884645462036133, "step": 1735 }, { "epoch": 0.6634257935373177, "grad_norm": 0.32175734639167786, "learning_rate": 2.6949089562694435e-05, "loss": 1.3210320472717285, "step": 1740 }, { "epoch": 0.6653321894957582, "grad_norm": 0.274068146944046, "learning_rate": 2.667557040424578e-05, "loss": 1.2970300674438477, "step": 1745 }, { "epoch": 0.6672385854541988, "grad_norm": 0.2562931478023529, "learning_rate": 2.6402940478020767e-05, "loss": 1.3085933685302735, "step": 1750 }, { "epoch": 0.6691449814126395, "grad_norm": 0.31347551941871643, "learning_rate": 2.6131210177899113e-05, "loss": 1.3006364822387695, "step": 1755 }, { "epoch": 0.67105137737108, "grad_norm": 0.3195972740650177, "learning_rate": 2.5860389863462765e-05, "loss": 1.2757848739624023, "step": 1760 }, { "epoch": 0.6729577733295206, "grad_norm": 0.26257574558258057, "learning_rate": 2.559048985960084e-05, "loss": 1.3114376068115234, "step": 1765 }, { "epoch": 0.6748641692879611, "grad_norm": 0.27884575724601746, "learning_rate": 2.532152045611615e-05, "loss": 1.2742648124694824, "step": 1770 }, { "epoch": 0.6767705652464017, "grad_norm": 0.26600757241249084, "learning_rate": 2.5053491907332815e-05, "loss": 1.3461550712585448, "step": 1775 }, { "epoch": 0.6786769612048422, "grad_norm": 0.23416565358638763, "learning_rate": 2.4786414431705302e-05, "loss": 1.2992279052734375, "step": 1780 }, { "epoch": 0.6805833571632828, "grad_norm": 0.2441694587469101, "learning_rate": 2.4520298211428945e-05, "loss": 1.3232810020446777, "step": 1785 }, { "epoch": 0.6824897531217233, "grad_norm": 0.27872809767723083, "learning_rate": 2.4255153392051655e-05, "loss": 1.2967830657958985, "step": 1790 }, { "epoch": 0.684396149080164, "grad_norm": 0.31921660900115967, "learning_rate": 2.3990990082087166e-05, "loss": 1.3162948608398437, "step": 1795 }, { "epoch": 0.6863025450386046, "grad_norm": 0.2605992555618286, "learning_rate": 2.3727818352629712e-05, "loss": 1.2798006057739257, "step": 1800 }, { "epoch": 0.6882089409970451, "grad_norm": 0.2766391634941101, "learning_rate": 2.3465648236969938e-05, "loss": 1.248784637451172, "step": 1805 }, { "epoch": 0.6901153369554857, "grad_norm": 0.2724340558052063, "learning_rate": 2.320448973021252e-05, "loss": 1.267018985748291, "step": 1810 }, { "epoch": 0.6920217329139262, "grad_norm": 0.269867867231369, "learning_rate": 2.2944352788895064e-05, "loss": 1.2623897552490235, "step": 1815 }, { "epoch": 0.6939281288723668, "grad_norm": 0.2870424687862396, "learning_rate": 2.2685247330608417e-05, "loss": 1.2856816291809081, "step": 1820 }, { "epoch": 0.6958345248308073, "grad_norm": 0.34039217233657837, "learning_rate": 2.242718323361876e-05, "loss": 1.3209775924682616, "step": 1825 }, { "epoch": 0.6977409207892479, "grad_norm": 0.2975488007068634, "learning_rate": 2.21701703364908e-05, "loss": 1.3308780670166016, "step": 1830 }, { "epoch": 0.6996473167476885, "grad_norm": 0.2922642230987549, "learning_rate": 2.1914218437712824e-05, "loss": 1.2677643775939942, "step": 1835 }, { "epoch": 0.7015537127061291, "grad_norm": 0.30045410990715027, "learning_rate": 2.1659337295323118e-05, "loss": 1.2900771141052245, "step": 1840 }, { "epoch": 0.7034601086645696, "grad_norm": 0.2769049406051636, "learning_rate": 2.1405536626537825e-05, "loss": 1.2788096427917481, "step": 1845 }, { "epoch": 0.7053665046230102, "grad_norm": 0.3026473820209503, "learning_rate": 2.1152826107380653e-05, "loss": 1.348760223388672, "step": 1850 }, { "epoch": 0.7072729005814508, "grad_norm": 0.3524516224861145, "learning_rate": 2.0901215372313888e-05, "loss": 1.2741279602050781, "step": 1855 }, { "epoch": 0.7091792965398913, "grad_norm": 0.29180601239204407, "learning_rate": 2.065071401387105e-05, "loss": 1.283041000366211, "step": 1860 }, { "epoch": 0.7110856924983319, "grad_norm": 0.24817217886447906, "learning_rate": 2.0401331582291257e-05, "loss": 1.261880111694336, "step": 1865 }, { "epoch": 0.7129920884567724, "grad_norm": 0.25220730900764465, "learning_rate": 2.015307758515513e-05, "loss": 1.2523793220520019, "step": 1870 }, { "epoch": 0.7148984844152131, "grad_norm": 0.2991998493671417, "learning_rate": 1.9905961487022222e-05, "loss": 1.2672356605529784, "step": 1875 }, { "epoch": 0.7168048803736536, "grad_norm": 0.27264538407325745, "learning_rate": 1.9659992709070345e-05, "loss": 1.2976717948913574, "step": 1880 }, { "epoch": 0.7187112763320942, "grad_norm": 0.2786688804626465, "learning_rate": 1.941518062873621e-05, "loss": 1.2084770202636719, "step": 1885 }, { "epoch": 0.7206176722905347, "grad_norm": 0.2885562479496002, "learning_rate": 1.9171534579358075e-05, "loss": 1.2393610000610351, "step": 1890 }, { "epoch": 0.7225240682489753, "grad_norm": 0.23934251070022583, "learning_rate": 1.8929063849819845e-05, "loss": 1.2703269004821778, "step": 1895 }, { "epoch": 0.7244304642074159, "grad_norm": 0.27533578872680664, "learning_rate": 1.8687777684196882e-05, "loss": 1.2818480491638184, "step": 1900 }, { "epoch": 0.7263368601658564, "grad_norm": 0.2798852324485779, "learning_rate": 1.8447685281403714e-05, "loss": 1.2778390884399413, "step": 1905 }, { "epoch": 0.728243256124297, "grad_norm": 0.2818307876586914, "learning_rate": 1.8208795794843247e-05, "loss": 1.302980899810791, "step": 1910 }, { "epoch": 0.7301496520827376, "grad_norm": 0.24400120973587036, "learning_rate": 1.7971118332057746e-05, "loss": 1.3045165061950683, "step": 1915 }, { "epoch": 0.7320560480411782, "grad_norm": 0.27064794301986694, "learning_rate": 1.7734661954381754e-05, "loss": 1.2538033485412599, "step": 1920 }, { "epoch": 0.7339624439996187, "grad_norm": 0.27026423811912537, "learning_rate": 1.749943567659648e-05, "loss": 1.3045284271240234, "step": 1925 }, { "epoch": 0.7358688399580593, "grad_norm": 0.26858365535736084, "learning_rate": 1.726544846658626e-05, "loss": 1.2713985443115234, "step": 1930 }, { "epoch": 0.7377752359164998, "grad_norm": 0.2613442838191986, "learning_rate": 1.703270924499656e-05, "loss": 1.243505096435547, "step": 1935 }, { "epoch": 0.7396816318749404, "grad_norm": 0.4013001024723053, "learning_rate": 1.6801226884893896e-05, "loss": 1.296872043609619, "step": 1940 }, { "epoch": 0.741588027833381, "grad_norm": 0.25249019265174866, "learning_rate": 1.6571010211427564e-05, "loss": 1.2743738174438477, "step": 1945 }, { "epoch": 0.7434944237918215, "grad_norm": 0.30830514430999756, "learning_rate": 1.6342068001493234e-05, "loss": 1.347235107421875, "step": 1950 }, { "epoch": 0.7454008197502622, "grad_norm": 0.25204187631607056, "learning_rate": 1.611440898339824e-05, "loss": 1.3047658920288085, "step": 1955 }, { "epoch": 0.7473072157087027, "grad_norm": 0.23890092968940735, "learning_rate": 1.5888041836528915e-05, "loss": 1.3173834800720214, "step": 1960 }, { "epoch": 0.7492136116671433, "grad_norm": 0.27674582600593567, "learning_rate": 1.5662975191019598e-05, "loss": 1.2952470779418945, "step": 1965 }, { "epoch": 0.7511200076255838, "grad_norm": 0.24614043533802032, "learning_rate": 1.5439217627423697e-05, "loss": 1.2403566360473632, "step": 1970 }, { "epoch": 0.7530264035840244, "grad_norm": 0.21446549892425537, "learning_rate": 1.5216777676386534e-05, "loss": 1.268918228149414, "step": 1975 }, { "epoch": 0.754932799542465, "grad_norm": 0.3373437821865082, "learning_rate": 1.4995663818320072e-05, "loss": 1.2323001861572265, "step": 1980 }, { "epoch": 0.7568391955009055, "grad_norm": 0.24887199699878693, "learning_rate": 1.4775884483079666e-05, "loss": 1.2946328163146972, "step": 1985 }, { "epoch": 0.7587455914593461, "grad_norm": 0.3030349910259247, "learning_rate": 1.455744804964268e-05, "loss": 1.2589397430419922, "step": 1990 }, { "epoch": 0.7606519874177867, "grad_norm": 0.28345075249671936, "learning_rate": 1.4340362845788958e-05, "loss": 1.25282564163208, "step": 1995 }, { "epoch": 0.7625583833762273, "grad_norm": 0.2806551456451416, "learning_rate": 1.4124637147783432e-05, "loss": 1.2873175621032715, "step": 2000 }, { "epoch": 0.7644647793346678, "grad_norm": 0.26797688007354736, "learning_rate": 1.391027918006057e-05, "loss": 1.3533535957336427, "step": 2005 }, { "epoch": 0.7663711752931084, "grad_norm": 0.30630385875701904, "learning_rate": 1.3697297114910768e-05, "loss": 1.319953727722168, "step": 2010 }, { "epoch": 0.7682775712515489, "grad_norm": 0.21564672887325287, "learning_rate": 1.348569907216881e-05, "loss": 1.266263771057129, "step": 2015 }, { "epoch": 0.7701839672099895, "grad_norm": 0.31971731781959534, "learning_rate": 1.3275493118904386e-05, "loss": 1.2573046684265137, "step": 2020 }, { "epoch": 0.77209036316843, "grad_norm": 0.26772141456604004, "learning_rate": 1.3066687269114398e-05, "loss": 1.2881788253784179, "step": 2025 }, { "epoch": 0.7739967591268706, "grad_norm": 0.2569355368614197, "learning_rate": 1.2859289483417558e-05, "loss": 1.275874137878418, "step": 2030 }, { "epoch": 0.7759031550853113, "grad_norm": 0.27180615067481995, "learning_rate": 1.2653307668750786e-05, "loss": 1.3089826583862305, "step": 2035 }, { "epoch": 0.7778095510437518, "grad_norm": 0.2430656999349594, "learning_rate": 1.2448749678067856e-05, "loss": 1.2678367614746093, "step": 2040 }, { "epoch": 0.7797159470021924, "grad_norm": 0.23877812922000885, "learning_rate": 1.2245623310039973e-05, "loss": 1.3602535247802734, "step": 2045 }, { "epoch": 0.7816223429606329, "grad_norm": 0.26600319147109985, "learning_rate": 1.204393630875838e-05, "loss": 1.2801698684692382, "step": 2050 }, { "epoch": 0.7835287389190735, "grad_norm": 0.30729660391807556, "learning_rate": 1.1843696363439261e-05, "loss": 1.23919677734375, "step": 2055 }, { "epoch": 0.785435134877514, "grad_norm": 0.227600559592247, "learning_rate": 1.1644911108130435e-05, "loss": 1.3255355834960938, "step": 2060 }, { "epoch": 0.7873415308359546, "grad_norm": 0.3176155686378479, "learning_rate": 1.1447588121420461e-05, "loss": 1.2895964622497558, "step": 2065 }, { "epoch": 0.7892479267943951, "grad_norm": 0.3035479187965393, "learning_rate": 1.125173492614961e-05, "loss": 1.2202783584594727, "step": 2070 }, { "epoch": 0.7911543227528358, "grad_norm": 0.24790754914283752, "learning_rate": 1.1057358989123073e-05, "loss": 1.2362918853759766, "step": 2075 }, { "epoch": 0.7930607187112764, "grad_norm": 0.27740412950515747, "learning_rate": 1.0864467720826343e-05, "loss": 1.3022624969482421, "step": 2080 }, { "epoch": 0.7949671146697169, "grad_norm": 0.2983035743236542, "learning_rate": 1.0673068475142612e-05, "loss": 1.2851173400878906, "step": 2085 }, { "epoch": 0.7968735106281575, "grad_norm": 0.28451427817344666, "learning_rate": 1.0483168549072519e-05, "loss": 1.2093828201293946, "step": 2090 }, { "epoch": 0.798779906586598, "grad_norm": 0.31136924028396606, "learning_rate": 1.029477518245584e-05, "loss": 1.2966349601745606, "step": 2095 }, { "epoch": 0.8006863025450386, "grad_norm": 0.2705349028110504, "learning_rate": 1.0107895557695523e-05, "loss": 1.27640380859375, "step": 2100 }, { "epoch": 0.8025926985034791, "grad_norm": 0.32963642477989197, "learning_rate": 9.922536799483901e-06, "loss": 1.304217529296875, "step": 2105 }, { "epoch": 0.8044990944619197, "grad_norm": 0.30048057436943054, "learning_rate": 9.738705974531026e-06, "loss": 1.2751550674438477, "step": 2110 }, { "epoch": 0.8064054904203604, "grad_norm": 0.2719151973724365, "learning_rate": 9.556410091295215e-06, "loss": 1.310124397277832, "step": 2115 }, { "epoch": 0.8083118863788009, "grad_norm": 0.3245067000389099, "learning_rate": 9.375656099715934e-06, "loss": 1.3070714950561524, "step": 2120 }, { "epoch": 0.8102182823372415, "grad_norm": 0.29382047057151794, "learning_rate": 9.196450890948816e-06, "loss": 1.2848482131958008, "step": 2125 }, { "epoch": 0.812124678295682, "grad_norm": 0.2974618971347809, "learning_rate": 9.01880129710287e-06, "loss": 1.3063250541687013, "step": 2130 }, { "epoch": 0.8140310742541226, "grad_norm": 0.28922203183174133, "learning_rate": 8.84271409098012e-06, "loss": 1.3028696060180665, "step": 2135 }, { "epoch": 0.8159374702125631, "grad_norm": 0.2505742311477661, "learning_rate": 8.66819598581729e-06, "loss": 1.2682609558105469, "step": 2140 }, { "epoch": 0.8178438661710037, "grad_norm": 0.30349427461624146, "learning_rate": 8.495253635029943e-06, "loss": 1.2464805603027345, "step": 2145 }, { "epoch": 0.8197502621294442, "grad_norm": 0.2700892388820648, "learning_rate": 8.323893631958806e-06, "loss": 1.2069608688354492, "step": 2150 }, { "epoch": 0.8216566580878849, "grad_norm": 0.34289395809173584, "learning_rate": 8.154122509618346e-06, "loss": 1.3153762817382812, "step": 2155 }, { "epoch": 0.8235630540463255, "grad_norm": 0.3248732388019562, "learning_rate": 7.985946740447791e-06, "loss": 1.2754580497741699, "step": 2160 }, { "epoch": 0.825469450004766, "grad_norm": 0.2394816279411316, "learning_rate": 7.81937273606429e-06, "loss": 1.2874581336975097, "step": 2165 }, { "epoch": 0.8273758459632066, "grad_norm": 0.25531205534935, "learning_rate": 7.654406847018541e-06, "loss": 1.3131428718566895, "step": 2170 }, { "epoch": 0.8292822419216471, "grad_norm": 0.28492212295532227, "learning_rate": 7.491055362552624e-06, "loss": 1.2674978256225586, "step": 2175 }, { "epoch": 0.8311886378800877, "grad_norm": 0.3087736666202545, "learning_rate": 7.329324510360269e-06, "loss": 1.2896101951599122, "step": 2180 }, { "epoch": 0.8330950338385282, "grad_norm": 0.24922163784503937, "learning_rate": 7.1692204563493956e-06, "loss": 1.2613224029541015, "step": 2185 }, { "epoch": 0.8350014297969688, "grad_norm": 0.23499475419521332, "learning_rate": 7.010749304407077e-06, "loss": 1.2360116004943849, "step": 2190 }, { "epoch": 0.8369078257554095, "grad_norm": 0.3109460771083832, "learning_rate": 6.853917096166768e-06, "loss": 1.264583206176758, "step": 2195 }, { "epoch": 0.83881422171385, "grad_norm": 0.2958238422870636, "learning_rate": 6.698729810778065e-06, "loss": 1.2924345970153808, "step": 2200 }, { "epoch": 0.8407206176722906, "grad_norm": 0.28373780846595764, "learning_rate": 6.5451933646786865e-06, "loss": 1.2855048179626465, "step": 2205 }, { "epoch": 0.8426270136307311, "grad_norm": 0.29589641094207764, "learning_rate": 6.3933136113689e-06, "loss": 1.278209114074707, "step": 2210 }, { "epoch": 0.8445334095891717, "grad_norm": 0.28071531653404236, "learning_rate": 6.2430963411884205e-06, "loss": 1.2841176986694336, "step": 2215 }, { "epoch": 0.8464398055476122, "grad_norm": 0.321755051612854, "learning_rate": 6.09454728109562e-06, "loss": 1.2955687522888184, "step": 2220 }, { "epoch": 0.8483462015060528, "grad_norm": 0.240579292178154, "learning_rate": 5.947672094449169e-06, "loss": 1.2783164978027344, "step": 2225 }, { "epoch": 0.8502525974644933, "grad_norm": 0.2967662513256073, "learning_rate": 5.802476380792194e-06, "loss": 1.2826072692871093, "step": 2230 }, { "epoch": 0.852158993422934, "grad_norm": 0.2595486640930176, "learning_rate": 5.658965675638706e-06, "loss": 1.3454477310180664, "step": 2235 }, { "epoch": 0.8540653893813746, "grad_norm": 0.26660287380218506, "learning_rate": 5.51714545026264e-06, "loss": 1.3258867263793945, "step": 2240 }, { "epoch": 0.8559717853398151, "grad_norm": 0.31178662180900574, "learning_rate": 5.377021111489222e-06, "loss": 1.243789291381836, "step": 2245 }, { "epoch": 0.8578781812982557, "grad_norm": 0.3128054738044739, "learning_rate": 5.238598001488842e-06, "loss": 1.2453927040100097, "step": 2250 }, { "epoch": 0.8597845772566962, "grad_norm": 0.28166258335113525, "learning_rate": 5.101881397573416e-06, "loss": 1.2805182456970214, "step": 2255 }, { "epoch": 0.8616909732151368, "grad_norm": 0.29216358065605164, "learning_rate": 4.96687651199515e-06, "loss": 1.2676274299621582, "step": 2260 }, { "epoch": 0.8635973691735773, "grad_norm": 0.2604143023490906, "learning_rate": 4.8335884917478365e-06, "loss": 1.2538568496704101, "step": 2265 }, { "epoch": 0.8655037651320179, "grad_norm": 0.28287389874458313, "learning_rate": 4.702022418370672e-06, "loss": 1.2607022285461427, "step": 2270 }, { "epoch": 0.8674101610904585, "grad_norm": 0.2540261745452881, "learning_rate": 4.57218330775443e-06, "loss": 1.2899112701416016, "step": 2275 }, { "epoch": 0.8693165570488991, "grad_norm": 0.3204768896102905, "learning_rate": 4.4440761099503455e-06, "loss": 1.2618412017822265, "step": 2280 }, { "epoch": 0.8712229530073397, "grad_norm": 0.24816618859767914, "learning_rate": 4.3177057089813285e-06, "loss": 1.2558921813964843, "step": 2285 }, { "epoch": 0.8731293489657802, "grad_norm": 0.32940608263015747, "learning_rate": 4.193076922655759e-06, "loss": 1.255124568939209, "step": 2290 }, { "epoch": 0.8750357449242208, "grad_norm": 0.32961541414260864, "learning_rate": 4.070194502383839e-06, "loss": 1.228334617614746, "step": 2295 }, { "epoch": 0.8769421408826613, "grad_norm": 0.30504852533340454, "learning_rate": 3.949063132996455e-06, "loss": 1.2398731231689453, "step": 2300 }, { "epoch": 0.8788485368411019, "grad_norm": 0.2569536864757538, "learning_rate": 3.829687432566525e-06, "loss": 1.3019656181335448, "step": 2305 }, { "epoch": 0.8807549327995424, "grad_norm": 0.27825555205345154, "learning_rate": 3.7120719522329873e-06, "loss": 1.2222501754760742, "step": 2310 }, { "epoch": 0.8826613287579831, "grad_norm": 0.2801966667175293, "learning_rate": 3.596221176027248e-06, "loss": 1.226343822479248, "step": 2315 }, { "epoch": 0.8845677247164236, "grad_norm": 0.27791348099708557, "learning_rate": 3.4821395207022766e-06, "loss": 1.2490703582763671, "step": 2320 }, { "epoch": 0.8864741206748642, "grad_norm": 0.30703672766685486, "learning_rate": 3.369831335564172e-06, "loss": 1.1726917266845702, "step": 2325 }, { "epoch": 0.8883805166333048, "grad_norm": 0.25407636165618896, "learning_rate": 3.259300902306367e-06, "loss": 1.259549903869629, "step": 2330 }, { "epoch": 0.8902869125917453, "grad_norm": 0.2748848795890808, "learning_rate": 3.15055243484641e-06, "loss": 1.3021918296813966, "step": 2335 }, { "epoch": 0.8921933085501859, "grad_norm": 0.3162597715854645, "learning_rate": 3.0435900791652816e-06, "loss": 1.2593650817871094, "step": 2340 }, { "epoch": 0.8940997045086264, "grad_norm": 0.3766025900840759, "learning_rate": 2.938417913149344e-06, "loss": 1.2838375091552734, "step": 2345 }, { "epoch": 0.896006100467067, "grad_norm": 0.2617952227592468, "learning_rate": 2.83503994643487e-06, "loss": 1.2173202514648438, "step": 2350 }, { "epoch": 0.8979124964255075, "grad_norm": 0.32625946402549744, "learning_rate": 2.733460120255199e-06, "loss": 1.2620113372802735, "step": 2355 }, { "epoch": 0.8998188923839482, "grad_norm": 0.2758268713951111, "learning_rate": 2.6336823072904304e-06, "loss": 1.3287481307983398, "step": 2360 }, { "epoch": 0.9017252883423887, "grad_norm": 0.30779194831848145, "learning_rate": 2.53571031151984e-06, "loss": 1.2549450874328614, "step": 2365 }, { "epoch": 0.9036316843008293, "grad_norm": 0.2871108651161194, "learning_rate": 2.4395478680768023e-06, "loss": 1.184624195098877, "step": 2370 }, { "epoch": 0.9055380802592699, "grad_norm": 0.2998097538948059, "learning_rate": 2.345198643106428e-06, "loss": 1.1927226066589356, "step": 2375 }, { "epoch": 0.9074444762177104, "grad_norm": 0.31913626194000244, "learning_rate": 2.252666233625783e-06, "loss": 1.2860239028930665, "step": 2380 }, { "epoch": 0.909350872176151, "grad_norm": 0.32737797498703003, "learning_rate": 2.161954167386726e-06, "loss": 1.2646794319152832, "step": 2385 }, { "epoch": 0.9112572681345915, "grad_norm": 0.34339675307273865, "learning_rate": 2.073065902741472e-06, "loss": 1.2995262145996094, "step": 2390 }, { "epoch": 0.9131636640930321, "grad_norm": 0.2388019859790802, "learning_rate": 1.986004828510685e-06, "loss": 1.2607707977294922, "step": 2395 }, { "epoch": 0.9150700600514727, "grad_norm": 0.2666759192943573, "learning_rate": 1.9007742638543102e-06, "loss": 1.3214723587036132, "step": 2400 }, { "epoch": 0.9169764560099133, "grad_norm": 0.2996501326560974, "learning_rate": 1.8173774581450588e-06, "loss": 1.3515162467956543, "step": 2405 }, { "epoch": 0.9188828519683538, "grad_norm": 0.2618994116783142, "learning_rate": 1.7358175908444574e-06, "loss": 1.2994682312011718, "step": 2410 }, { "epoch": 0.9207892479267944, "grad_norm": 0.33215808868408203, "learning_rate": 1.6560977713816982e-06, "loss": 1.289261817932129, "step": 2415 }, { "epoch": 0.922695643885235, "grad_norm": 0.29186832904815674, "learning_rate": 1.5782210390350716e-06, "loss": 1.2653358459472657, "step": 2420 }, { "epoch": 0.9246020398436755, "grad_norm": 0.28440016508102417, "learning_rate": 1.5021903628160804e-06, "loss": 1.254986572265625, "step": 2425 }, { "epoch": 0.9265084358021161, "grad_norm": 0.2949380576610565, "learning_rate": 1.42800864135626e-06, "loss": 1.336177444458008, "step": 2430 }, { "epoch": 0.9284148317605566, "grad_norm": 0.2676756978034973, "learning_rate": 1.3556787027966866e-06, "loss": 1.2899702072143555, "step": 2435 }, { "epoch": 0.9303212277189973, "grad_norm": 0.2686278522014618, "learning_rate": 1.2852033046801104e-06, "loss": 1.2718887329101562, "step": 2440 }, { "epoch": 0.9322276236774378, "grad_norm": 0.2600155174732208, "learning_rate": 1.2165851338458821e-06, "loss": 1.2679462432861328, "step": 2445 }, { "epoch": 0.9341340196358784, "grad_norm": 0.29629039764404297, "learning_rate": 1.1498268063274697e-06, "loss": 1.274935531616211, "step": 2450 }, { "epoch": 0.9360404155943189, "grad_norm": 0.32085058093070984, "learning_rate": 1.0849308672527591e-06, "loss": 1.2384976387023925, "step": 2455 }, { "epoch": 0.9379468115527595, "grad_norm": 0.2750713527202606, "learning_rate": 1.0218997907469941e-06, "loss": 1.290949821472168, "step": 2460 }, { "epoch": 0.9398532075112, "grad_norm": 0.334941029548645, "learning_rate": 9.607359798384785e-07, "loss": 1.269826316833496, "step": 2465 }, { "epoch": 0.9417596034696406, "grad_norm": 0.30846548080444336, "learning_rate": 9.014417663669339e-07, "loss": 1.2838249206542969, "step": 2470 }, { "epoch": 0.9436659994280812, "grad_norm": 0.25176286697387695, "learning_rate": 8.440194108946253e-07, "loss": 1.2833518028259276, "step": 2475 }, { "epoch": 0.9455723953865218, "grad_norm": 0.324649453163147, "learning_rate": 7.884711026201585e-07, "loss": 1.2897378921508789, "step": 2480 }, { "epoch": 0.9474787913449624, "grad_norm": 0.2945902347564697, "learning_rate": 7.347989592950355e-07, "loss": 1.2712274551391602, "step": 2485 }, { "epoch": 0.9493851873034029, "grad_norm": 0.26208600401878357, "learning_rate": 6.830050271429023e-07, "loss": 1.2482695579528809, "step": 2490 }, { "epoch": 0.9512915832618435, "grad_norm": 0.41000497341156006, "learning_rate": 6.330912807815336e-07, "loss": 1.2295034408569336, "step": 2495 }, { "epoch": 0.953197979220284, "grad_norm": 0.2501354217529297, "learning_rate": 5.850596231475769e-07, "loss": 1.2919734001159668, "step": 2500 }, { "epoch": 0.9551043751787246, "grad_norm": 0.27073603868484497, "learning_rate": 5.389118854239705e-07, "loss": 1.2957923889160157, "step": 2505 }, { "epoch": 0.9570107711371652, "grad_norm": 0.3306446671485901, "learning_rate": 4.946498269701616e-07, "loss": 1.2615965843200683, "step": 2510 }, { "epoch": 0.9589171670956057, "grad_norm": 0.32333266735076904, "learning_rate": 4.522751352550203e-07, "loss": 1.2839290618896484, "step": 2515 }, { "epoch": 0.9608235630540464, "grad_norm": 0.31210148334503174, "learning_rate": 4.1178942579248036e-07, "loss": 1.223864459991455, "step": 2520 }, { "epoch": 0.9627299590124869, "grad_norm": 0.281080037355423, "learning_rate": 3.7319424207999385e-07, "loss": 1.312656784057617, "step": 2525 }, { "epoch": 0.9646363549709275, "grad_norm": 0.28866586089134216, "learning_rate": 3.3649105553965055e-07, "loss": 1.2236149787902832, "step": 2530 }, { "epoch": 0.966542750929368, "grad_norm": 0.34519168734550476, "learning_rate": 3.016812654621004e-07, "loss": 1.2471606254577636, "step": 2535 }, { "epoch": 0.9684491468878086, "grad_norm": 0.29924488067626953, "learning_rate": 2.687661989531964e-07, "loss": 1.2718618392944336, "step": 2540 }, { "epoch": 0.9703555428462491, "grad_norm": 0.30336493253707886, "learning_rate": 2.3774711088340173e-07, "loss": 1.256441879272461, "step": 2545 }, { "epoch": 0.9722619388046897, "grad_norm": 0.32538875937461853, "learning_rate": 2.0862518383995e-07, "loss": 1.29504337310791, "step": 2550 }, { "epoch": 0.9741683347631303, "grad_norm": 0.31382668018341064, "learning_rate": 1.814015280817538e-07, "loss": 1.245374870300293, "step": 2555 }, { "epoch": 0.9760747307215709, "grad_norm": 0.2408931404352188, "learning_rate": 1.560771814970885e-07, "loss": 1.3099851608276367, "step": 2560 }, { "epoch": 0.9779811266800115, "grad_norm": 0.2902478277683258, "learning_rate": 1.3265310956401268e-07, "loss": 1.258431625366211, "step": 2565 }, { "epoch": 0.979887522638452, "grad_norm": 0.279956191778183, "learning_rate": 1.1113020531357543e-07, "loss": 1.2262717247009278, "step": 2570 }, { "epoch": 0.9817939185968926, "grad_norm": 0.3357672095298767, "learning_rate": 9.1509289295727e-08, "loss": 1.257904052734375, "step": 2575 }, { "epoch": 0.9837003145553331, "grad_norm": 0.2751654386520386, "learning_rate": 7.379110954810475e-08, "loss": 1.1847064018249511, "step": 2580 }, { "epoch": 0.9856067105137737, "grad_norm": 0.2778809070587158, "learning_rate": 5.797634156744502e-08, "loss": 1.2715692520141602, "step": 2585 }, { "epoch": 0.9875131064722142, "grad_norm": 0.28509262204170227, "learning_rate": 4.406558828388141e-08, "loss": 1.2061580657958983, "step": 2590 }, { "epoch": 0.9894195024306548, "grad_norm": 0.2964514493942261, "learning_rate": 3.2059380037929856e-08, "loss": 1.284592628479004, "step": 2595 }, { "epoch": 0.9913258983890955, "grad_norm": 0.27075910568237305, "learning_rate": 2.1958174560282595e-08, "loss": 1.2388830184936523, "step": 2600 }, { "epoch": 0.993232294347536, "grad_norm": 0.2943772077560425, "learning_rate": 1.376235695434991e-08, "loss": 1.2309008598327638, "step": 2605 }, { "epoch": 0.9951386903059766, "grad_norm": 0.2736813426017761, "learning_rate": 7.472239681582949e-09, "loss": 1.2411253929138184, "step": 2610 }, { "epoch": 0.9970450862644171, "grad_norm": 0.2683391273021698, "learning_rate": 3.088062549555515e-09, "loss": 1.2596145629882813, "step": 2615 }, { "epoch": 0.9989514822228577, "grad_norm": 0.26884642243385315, "learning_rate": 6.099927028380137e-10, "loss": 1.316823673248291, "step": 2620 } ], "logging_steps": 5, "max_steps": 2623, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.043371813447926e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }