{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 3284, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0015226494099733537, "grad_norm": 1.743401050567627, "learning_rate": 4.040404040404041e-06, "loss": 2.8924530029296873, "step": 5 }, { "epoch": 0.0030452988199467074, "grad_norm": 1.2171194553375244, "learning_rate": 9.090909090909091e-06, "loss": 2.909554290771484, "step": 10 }, { "epoch": 0.004567948229920061, "grad_norm": 0.7534424066543579, "learning_rate": 1.4141414141414141e-05, "loss": 2.762582015991211, "step": 15 }, { "epoch": 0.006090597639893415, "grad_norm": 0.4503587484359741, "learning_rate": 1.919191919191919e-05, "loss": 2.7832099914550783, "step": 20 }, { "epoch": 0.007613247049866768, "grad_norm": 0.27066150307655334, "learning_rate": 2.4242424242424244e-05, "loss": 2.548894500732422, "step": 25 }, { "epoch": 0.009135896459840122, "grad_norm": 0.3686508536338806, "learning_rate": 2.9292929292929294e-05, "loss": 2.4201244354248046, "step": 30 }, { "epoch": 0.010658545869813475, "grad_norm": 0.3332791328430176, "learning_rate": 3.434343434343435e-05, "loss": 2.4746280670166017, "step": 35 }, { "epoch": 0.01218119527978683, "grad_norm": 0.3030345141887665, "learning_rate": 3.939393939393939e-05, "loss": 2.3972661972045897, "step": 40 }, { "epoch": 0.013703844689760183, "grad_norm": 0.19423909485340118, "learning_rate": 4.4444444444444447e-05, "loss": 2.2275766372680663, "step": 45 }, { "epoch": 0.015226494099733536, "grad_norm": 0.17889733612537384, "learning_rate": 4.94949494949495e-05, "loss": 2.2540813446044923, "step": 50 }, { "epoch": 0.01674914350970689, "grad_norm": 0.23615150153636932, "learning_rate": 5.4545454545454546e-05, "loss": 2.309238052368164, "step": 55 }, { "epoch": 0.018271792919680244, "grad_norm": 0.22650840878486633, "learning_rate": 5.959595959595959e-05, "loss": 2.1594886779785156, "step": 60 }, { "epoch": 0.0197944423296536, "grad_norm": 0.19858449697494507, "learning_rate": 6.464646464646466e-05, "loss": 2.094899559020996, "step": 65 }, { "epoch": 0.02131709173962695, "grad_norm": 0.22562797367572784, "learning_rate": 6.96969696969697e-05, "loss": 2.010164260864258, "step": 70 }, { "epoch": 0.022839741149600305, "grad_norm": 0.19623544812202454, "learning_rate": 7.474747474747475e-05, "loss": 2.0846214294433594, "step": 75 }, { "epoch": 0.02436239055957366, "grad_norm": 0.20719760656356812, "learning_rate": 7.97979797979798e-05, "loss": 1.9295326232910157, "step": 80 }, { "epoch": 0.02588503996954701, "grad_norm": 0.1923799216747284, "learning_rate": 8.484848484848486e-05, "loss": 1.979888916015625, "step": 85 }, { "epoch": 0.027407689379520365, "grad_norm": 0.19953864812850952, "learning_rate": 8.98989898989899e-05, "loss": 1.8587387084960938, "step": 90 }, { "epoch": 0.02893033878949372, "grad_norm": 0.3826952278614044, "learning_rate": 9.494949494949495e-05, "loss": 1.9173080444335937, "step": 95 }, { "epoch": 0.03045298819946707, "grad_norm": 0.2548823058605194, "learning_rate": 0.0001, "loss": 1.7950099945068358, "step": 100 }, { "epoch": 0.03197563760944042, "grad_norm": 0.267904669046402, "learning_rate": 9.99993919209947e-05, "loss": 1.8805675506591797, "step": 105 }, { "epoch": 0.03349828701941378, "grad_norm": 0.2776813209056854, "learning_rate": 9.99975676987692e-05, "loss": 1.7674415588378907, "step": 110 }, { "epoch": 0.03502093642938713, "grad_norm": 0.2339249700307846, "learning_rate": 9.999452737769436e-05, "loss": 1.736286735534668, "step": 115 }, { "epoch": 0.03654358583936049, "grad_norm": 0.21776463091373444, "learning_rate": 9.999027103172038e-05, "loss": 1.7391990661621093, "step": 120 }, { "epoch": 0.03806623524933384, "grad_norm": 0.2632898986339569, "learning_rate": 9.998479876437505e-05, "loss": 1.7017946243286133, "step": 125 }, { "epoch": 0.0395888846593072, "grad_norm": 0.2742399275302887, "learning_rate": 9.997811070876122e-05, "loss": 1.703371810913086, "step": 130 }, { "epoch": 0.041111534069280545, "grad_norm": 0.26463785767555237, "learning_rate": 9.997020702755353e-05, "loss": 1.7433647155761718, "step": 135 }, { "epoch": 0.0426341834792539, "grad_norm": 0.2810317575931549, "learning_rate": 9.996108791299447e-05, "loss": 1.8044513702392577, "step": 140 }, { "epoch": 0.044156832889227254, "grad_norm": 0.28534260392189026, "learning_rate": 9.995075358688974e-05, "loss": 1.7296686172485352, "step": 145 }, { "epoch": 0.04567948229920061, "grad_norm": 0.2629799246788025, "learning_rate": 9.993920430060281e-05, "loss": 1.8390384674072267, "step": 150 }, { "epoch": 0.047202131709173964, "grad_norm": 0.23989032208919525, "learning_rate": 9.992644033504881e-05, "loss": 1.7192668914794922, "step": 155 }, { "epoch": 0.04872478111914732, "grad_norm": 0.3158107101917267, "learning_rate": 9.991246200068772e-05, "loss": 1.6415214538574219, "step": 160 }, { "epoch": 0.05024743052912067, "grad_norm": 0.353024959564209, "learning_rate": 9.989726963751682e-05, "loss": 1.6634071350097657, "step": 165 }, { "epoch": 0.05177007993909402, "grad_norm": 0.34465649724006653, "learning_rate": 9.98808636150624e-05, "loss": 1.6077117919921875, "step": 170 }, { "epoch": 0.053292729349067376, "grad_norm": 0.26966795325279236, "learning_rate": 9.986324433237073e-05, "loss": 1.6946924209594727, "step": 175 }, { "epoch": 0.05481537875904073, "grad_norm": 0.3428654670715332, "learning_rate": 9.984441221799848e-05, "loss": 1.749506378173828, "step": 180 }, { "epoch": 0.056338028169014086, "grad_norm": 0.28879040479660034, "learning_rate": 9.982436773000218e-05, "loss": 1.6236579895019532, "step": 185 }, { "epoch": 0.05786067757898744, "grad_norm": 0.25999364256858826, "learning_rate": 9.980311135592713e-05, "loss": 1.6690912246704102, "step": 190 }, { "epoch": 0.05938332698896079, "grad_norm": 0.35241764783859253, "learning_rate": 9.978064361279549e-05, "loss": 1.7511703491210937, "step": 195 }, { "epoch": 0.06090597639893414, "grad_norm": 0.34807926416397095, "learning_rate": 9.975696504709382e-05, "loss": 1.5743136405944824, "step": 200 }, { "epoch": 0.0624286258089075, "grad_norm": 0.2592833936214447, "learning_rate": 9.973207623475965e-05, "loss": 1.616415023803711, "step": 205 }, { "epoch": 0.06395127521888085, "grad_norm": 0.2669435143470764, "learning_rate": 9.970597778116752e-05, "loss": 1.590099048614502, "step": 210 }, { "epoch": 0.06547392462885421, "grad_norm": 0.25957730412483215, "learning_rate": 9.967867032111435e-05, "loss": 1.6146507263183594, "step": 215 }, { "epoch": 0.06699657403882756, "grad_norm": 0.2507680058479309, "learning_rate": 9.965015451880382e-05, "loss": 1.614912986755371, "step": 220 }, { "epoch": 0.06851922344880092, "grad_norm": 0.27994081377983093, "learning_rate": 9.962043106783038e-05, "loss": 1.587266731262207, "step": 225 }, { "epoch": 0.07004187285877427, "grad_norm": 0.22382144629955292, "learning_rate": 9.95895006911623e-05, "loss": 1.5750970840454102, "step": 230 }, { "epoch": 0.07156452226874763, "grad_norm": 0.2456839233636856, "learning_rate": 9.955736414112408e-05, "loss": 1.605685043334961, "step": 235 }, { "epoch": 0.07308717167872097, "grad_norm": 0.3846738338470459, "learning_rate": 9.952402219937816e-05, "loss": 1.6009376525878907, "step": 240 }, { "epoch": 0.07460982108869432, "grad_norm": 0.2694767117500305, "learning_rate": 9.948947567690594e-05, "loss": 1.6845123291015625, "step": 245 }, { "epoch": 0.07613247049866768, "grad_norm": 0.2731744945049286, "learning_rate": 9.945372541398803e-05, "loss": 1.5459847450256348, "step": 250 }, { "epoch": 0.07765511990864103, "grad_norm": 0.24335195124149323, "learning_rate": 9.941677228018378e-05, "loss": 1.625588607788086, "step": 255 }, { "epoch": 0.0791777693186144, "grad_norm": 0.2586669325828552, "learning_rate": 9.937861717431022e-05, "loss": 1.6278593063354492, "step": 260 }, { "epoch": 0.08070041872858774, "grad_norm": 0.3470463454723358, "learning_rate": 9.933926102442007e-05, "loss": 1.5964099884033203, "step": 265 }, { "epoch": 0.08222306813856109, "grad_norm": 0.2824432849884033, "learning_rate": 9.929870478777928e-05, "loss": 1.5261369705200196, "step": 270 }, { "epoch": 0.08374571754853445, "grad_norm": 0.2779291570186615, "learning_rate": 9.92569494508437e-05, "loss": 1.5765350341796875, "step": 275 }, { "epoch": 0.0852683669585078, "grad_norm": 0.25763219594955444, "learning_rate": 9.921399602923507e-05, "loss": 1.581442165374756, "step": 280 }, { "epoch": 0.08679101636848116, "grad_norm": 0.29013440012931824, "learning_rate": 9.916984556771634e-05, "loss": 1.6473859786987304, "step": 285 }, { "epoch": 0.08831366577845451, "grad_norm": 0.28086087107658386, "learning_rate": 9.912449914016626e-05, "loss": 1.5918754577636718, "step": 290 }, { "epoch": 0.08983631518842787, "grad_norm": 0.31514450907707214, "learning_rate": 9.907795784955327e-05, "loss": 1.656451416015625, "step": 295 }, { "epoch": 0.09135896459840122, "grad_norm": 0.28868040442466736, "learning_rate": 9.903022282790864e-05, "loss": 1.5072600364685058, "step": 300 }, { "epoch": 0.09288161400837457, "grad_norm": 0.2932286560535431, "learning_rate": 9.898129523629892e-05, "loss": 1.5358075141906737, "step": 305 }, { "epoch": 0.09440426341834793, "grad_norm": 0.25252214074134827, "learning_rate": 9.893117626479777e-05, "loss": 1.5700132369995117, "step": 310 }, { "epoch": 0.09592691282832128, "grad_norm": 0.3809182047843933, "learning_rate": 9.887986713245697e-05, "loss": 1.573440170288086, "step": 315 }, { "epoch": 0.09744956223829464, "grad_norm": 0.317973256111145, "learning_rate": 9.882736908727678e-05, "loss": 1.5587141036987304, "step": 320 }, { "epoch": 0.09897221164826799, "grad_norm": 0.29717665910720825, "learning_rate": 9.877368340617555e-05, "loss": 1.5330610275268555, "step": 325 }, { "epoch": 0.10049486105824133, "grad_norm": 0.3083358407020569, "learning_rate": 9.87188113949587e-05, "loss": 1.5888717651367188, "step": 330 }, { "epoch": 0.1020175104682147, "grad_norm": 0.287901908159256, "learning_rate": 9.866275438828693e-05, "loss": 1.5876055717468263, "step": 335 }, { "epoch": 0.10354015987818804, "grad_norm": 0.2509470582008362, "learning_rate": 9.860551374964381e-05, "loss": 1.5873381614685058, "step": 340 }, { "epoch": 0.1050628092881614, "grad_norm": 0.22488534450531006, "learning_rate": 9.85470908713026e-05, "loss": 1.5889583587646485, "step": 345 }, { "epoch": 0.10658545869813475, "grad_norm": 0.2785811126232147, "learning_rate": 9.84874871742923e-05, "loss": 1.4751785278320313, "step": 350 }, { "epoch": 0.10810810810810811, "grad_norm": 0.22356157004833221, "learning_rate": 9.842670410836316e-05, "loss": 1.5838739395141601, "step": 355 }, { "epoch": 0.10963075751808146, "grad_norm": 0.2423107922077179, "learning_rate": 9.836474315195147e-05, "loss": 1.5520424842834473, "step": 360 }, { "epoch": 0.11115340692805481, "grad_norm": 0.2960359752178192, "learning_rate": 9.830160581214349e-05, "loss": 1.51832914352417, "step": 365 }, { "epoch": 0.11267605633802817, "grad_norm": 0.23912076652050018, "learning_rate": 9.823729362463883e-05, "loss": 1.5534074783325196, "step": 370 }, { "epoch": 0.11419870574800152, "grad_norm": 0.26240867376327515, "learning_rate": 9.817180815371315e-05, "loss": 1.5208246231079101, "step": 375 }, { "epoch": 0.11572135515797488, "grad_norm": 0.26089468598365784, "learning_rate": 9.810515099218003e-05, "loss": 1.6538705825805664, "step": 380 }, { "epoch": 0.11724400456794823, "grad_norm": 0.25654566287994385, "learning_rate": 9.803732376135232e-05, "loss": 1.5265024185180665, "step": 385 }, { "epoch": 0.11876665397792158, "grad_norm": 0.2372649908065796, "learning_rate": 9.796832811100261e-05, "loss": 1.513921070098877, "step": 390 }, { "epoch": 0.12028930338789494, "grad_norm": 0.25683122873306274, "learning_rate": 9.789816571932313e-05, "loss": 1.475426483154297, "step": 395 }, { "epoch": 0.12181195279786829, "grad_norm": 0.3001111149787903, "learning_rate": 9.782683829288501e-05, "loss": 1.5762993812561035, "step": 400 }, { "epoch": 0.12333460220784165, "grad_norm": 0.2704727351665497, "learning_rate": 9.775434756659666e-05, "loss": 1.5549912452697754, "step": 405 }, { "epoch": 0.124857251617815, "grad_norm": 0.31351470947265625, "learning_rate": 9.768069530366164e-05, "loss": 1.4764289855957031, "step": 410 }, { "epoch": 0.12637990102778834, "grad_norm": 0.24154245853424072, "learning_rate": 9.760588329553571e-05, "loss": 1.5097975730895996, "step": 415 }, { "epoch": 0.1279025504377617, "grad_norm": 0.2566833794116974, "learning_rate": 9.752991336188335e-05, "loss": 1.4876442909240724, "step": 420 }, { "epoch": 0.12942519984773507, "grad_norm": 0.2466706782579422, "learning_rate": 9.745278735053343e-05, "loss": 1.4416645050048829, "step": 425 }, { "epoch": 0.13094784925770842, "grad_norm": 0.3321710526943207, "learning_rate": 9.737450713743428e-05, "loss": 1.4886734008789062, "step": 430 }, { "epoch": 0.13247049866768176, "grad_norm": 0.3044130802154541, "learning_rate": 9.729507462660807e-05, "loss": 1.4812179565429688, "step": 435 }, { "epoch": 0.1339931480776551, "grad_norm": 0.21007977426052094, "learning_rate": 9.721449175010446e-05, "loss": 1.5150707244873047, "step": 440 }, { "epoch": 0.1355157974876285, "grad_norm": 0.2695784270763397, "learning_rate": 9.71327604679537e-05, "loss": 1.4663991928100586, "step": 445 }, { "epoch": 0.13703844689760183, "grad_norm": 0.27966949343681335, "learning_rate": 9.704988276811883e-05, "loss": 1.555038070678711, "step": 450 }, { "epoch": 0.13856109630757518, "grad_norm": 0.25070658326148987, "learning_rate": 9.696586066644744e-05, "loss": 1.6597448348999024, "step": 455 }, { "epoch": 0.14008374571754853, "grad_norm": 0.29249563813209534, "learning_rate": 9.688069620662255e-05, "loss": 1.6423145294189454, "step": 460 }, { "epoch": 0.14160639512752188, "grad_norm": 0.27136632800102234, "learning_rate": 9.6794391460113e-05, "loss": 1.4472129821777344, "step": 465 }, { "epoch": 0.14312904453749525, "grad_norm": 0.24730591475963593, "learning_rate": 9.670694852612293e-05, "loss": 1.5789676666259767, "step": 470 }, { "epoch": 0.1446516939474686, "grad_norm": 0.26245319843292236, "learning_rate": 9.661836953154084e-05, "loss": 1.5081109046936034, "step": 475 }, { "epoch": 0.14617434335744195, "grad_norm": 0.2713843882083893, "learning_rate": 9.652865663088783e-05, "loss": 1.5884946823120116, "step": 480 }, { "epoch": 0.1476969927674153, "grad_norm": 0.2706565856933594, "learning_rate": 9.643781200626511e-05, "loss": 1.4721956253051758, "step": 485 }, { "epoch": 0.14921964217738864, "grad_norm": 0.26984086632728577, "learning_rate": 9.63458378673011e-05, "loss": 1.4924152374267579, "step": 490 }, { "epoch": 0.15074229158736202, "grad_norm": 0.2726004719734192, "learning_rate": 9.625273645109746e-05, "loss": 1.5511323928833007, "step": 495 }, { "epoch": 0.15226494099733537, "grad_norm": 0.23182183504104614, "learning_rate": 9.615851002217488e-05, "loss": 1.4804168701171876, "step": 500 }, { "epoch": 0.15378759040730872, "grad_norm": 0.25415918231010437, "learning_rate": 9.606316087241789e-05, "loss": 1.5412309646606446, "step": 505 }, { "epoch": 0.15531023981728206, "grad_norm": 0.29364013671875, "learning_rate": 9.596669132101912e-05, "loss": 1.4650883674621582, "step": 510 }, { "epoch": 0.1568328892272554, "grad_norm": 0.2685583233833313, "learning_rate": 9.586910371442294e-05, "loss": 1.4664419174194336, "step": 515 }, { "epoch": 0.1583555386372288, "grad_norm": 0.2645435929298401, "learning_rate": 9.577040042626833e-05, "loss": 1.4759710311889649, "step": 520 }, { "epoch": 0.15987818804720214, "grad_norm": 0.29622793197631836, "learning_rate": 9.567058385733117e-05, "loss": 1.4932428359985352, "step": 525 }, { "epoch": 0.16140083745717548, "grad_norm": 0.2304457277059555, "learning_rate": 9.556965643546589e-05, "loss": 1.5823408126831056, "step": 530 }, { "epoch": 0.16292348686714883, "grad_norm": 0.2859705686569214, "learning_rate": 9.546762061554631e-05, "loss": 1.4450604438781738, "step": 535 }, { "epoch": 0.16444613627712218, "grad_norm": 0.22525323927402496, "learning_rate": 9.536447887940605e-05, "loss": 1.5858987808227538, "step": 540 }, { "epoch": 0.16596878568709555, "grad_norm": 0.2804889976978302, "learning_rate": 9.526023373577808e-05, "loss": 1.4853877067565917, "step": 545 }, { "epoch": 0.1674914350970689, "grad_norm": 0.23136599361896515, "learning_rate": 9.515488772023371e-05, "loss": 1.4586395263671874, "step": 550 }, { "epoch": 0.16901408450704225, "grad_norm": 0.23829296231269836, "learning_rate": 9.504844339512095e-05, "loss": 1.5025575637817383, "step": 555 }, { "epoch": 0.1705367339170156, "grad_norm": 0.29148998856544495, "learning_rate": 9.494090334950221e-05, "loss": 1.4311025619506836, "step": 560 }, { "epoch": 0.17205938332698897, "grad_norm": 0.25189658999443054, "learning_rate": 9.483227019909123e-05, "loss": 1.5207475662231444, "step": 565 }, { "epoch": 0.17358203273696232, "grad_norm": 0.299384742975235, "learning_rate": 9.472254658618952e-05, "loss": 1.4167113304138184, "step": 570 }, { "epoch": 0.17510468214693567, "grad_norm": 0.2680567502975464, "learning_rate": 9.46117351796221e-05, "loss": 1.5478759765625, "step": 575 }, { "epoch": 0.17662733155690902, "grad_norm": 0.2474081963300705, "learning_rate": 9.449983867467257e-05, "loss": 1.4865997314453125, "step": 580 }, { "epoch": 0.17814998096688237, "grad_norm": 0.2504813075065613, "learning_rate": 9.438685979301757e-05, "loss": 1.473835563659668, "step": 585 }, { "epoch": 0.17967263037685574, "grad_norm": 0.23168018460273743, "learning_rate": 9.42728012826605e-05, "loss": 1.5235390663146973, "step": 590 }, { "epoch": 0.1811952797868291, "grad_norm": 0.24396871030330658, "learning_rate": 9.41576659178648e-05, "loss": 1.5169439315795898, "step": 595 }, { "epoch": 0.18271792919680244, "grad_norm": 0.2807561755180359, "learning_rate": 9.404145649908639e-05, "loss": 1.4731966018676759, "step": 600 }, { "epoch": 0.18424057860677578, "grad_norm": 0.28449010848999023, "learning_rate": 9.392417585290558e-05, "loss": 1.3757762908935547, "step": 605 }, { "epoch": 0.18576322801674913, "grad_norm": 0.2893643379211426, "learning_rate": 9.380582683195832e-05, "loss": 1.4945030212402344, "step": 610 }, { "epoch": 0.1872858774267225, "grad_norm": 0.2784397006034851, "learning_rate": 9.368641231486682e-05, "loss": 1.4249692916870118, "step": 615 }, { "epoch": 0.18880852683669586, "grad_norm": 0.3239067494869232, "learning_rate": 9.356593520616948e-05, "loss": 1.447311019897461, "step": 620 }, { "epoch": 0.1903311762466692, "grad_norm": 0.27936220169067383, "learning_rate": 9.344439843625034e-05, "loss": 1.5492066383361816, "step": 625 }, { "epoch": 0.19185382565664255, "grad_norm": 0.26635825634002686, "learning_rate": 9.332180496126771e-05, "loss": 1.4516194343566895, "step": 630 }, { "epoch": 0.1933764750666159, "grad_norm": 0.31049951910972595, "learning_rate": 9.319815776308234e-05, "loss": 1.565488338470459, "step": 635 }, { "epoch": 0.19489912447658927, "grad_norm": 0.22772887349128723, "learning_rate": 9.307345984918483e-05, "loss": 1.6091934204101563, "step": 640 }, { "epoch": 0.19642177388656262, "grad_norm": 0.2732234001159668, "learning_rate": 9.294771425262254e-05, "loss": 1.5081945419311524, "step": 645 }, { "epoch": 0.19794442329653597, "grad_norm": 0.2492133527994156, "learning_rate": 9.282092403192573e-05, "loss": 1.4335723876953126, "step": 650 }, { "epoch": 0.19946707270650932, "grad_norm": 0.24314217269420624, "learning_rate": 9.269309227103328e-05, "loss": 1.4828542709350585, "step": 655 }, { "epoch": 0.20098972211648267, "grad_norm": 0.2893550992012024, "learning_rate": 9.256422207921757e-05, "loss": 1.588583755493164, "step": 660 }, { "epoch": 0.20251237152645604, "grad_norm": 0.25101926922798157, "learning_rate": 9.243431659100892e-05, "loss": 1.6308202743530273, "step": 665 }, { "epoch": 0.2040350209364294, "grad_norm": 0.24984188377857208, "learning_rate": 9.230337896611934e-05, "loss": 1.469271469116211, "step": 670 }, { "epoch": 0.20555767034640274, "grad_norm": 0.304371178150177, "learning_rate": 9.217141238936567e-05, "loss": 1.4192601203918458, "step": 675 }, { "epoch": 0.20708031975637609, "grad_norm": 0.26368117332458496, "learning_rate": 9.203842007059207e-05, "loss": 1.635411834716797, "step": 680 }, { "epoch": 0.20860296916634946, "grad_norm": 0.23114755749702454, "learning_rate": 9.190440524459203e-05, "loss": 1.4334131240844727, "step": 685 }, { "epoch": 0.2101256185763228, "grad_norm": 0.3051200807094574, "learning_rate": 9.176937117102966e-05, "loss": 1.5119773864746093, "step": 690 }, { "epoch": 0.21164826798629616, "grad_norm": 0.2679291069507599, "learning_rate": 9.163332113436032e-05, "loss": 1.4243457794189454, "step": 695 }, { "epoch": 0.2131709173962695, "grad_norm": 0.22732114791870117, "learning_rate": 9.149625844375088e-05, "loss": 1.4386891365051269, "step": 700 }, { "epoch": 0.21469356680624285, "grad_norm": 0.2432618886232376, "learning_rate": 9.135818643299911e-05, "loss": 1.4286434173583984, "step": 705 }, { "epoch": 0.21621621621621623, "grad_norm": 0.27945658564567566, "learning_rate": 9.121910846045266e-05, "loss": 1.4616294860839845, "step": 710 }, { "epoch": 0.21773886562618958, "grad_norm": 0.2410106658935547, "learning_rate": 9.107902790892733e-05, "loss": 1.4381277084350585, "step": 715 }, { "epoch": 0.21926151503616292, "grad_norm": 0.3209807574748993, "learning_rate": 9.093794818562481e-05, "loss": 1.446068286895752, "step": 720 }, { "epoch": 0.22078416444613627, "grad_norm": 0.29423707723617554, "learning_rate": 9.079587272204982e-05, "loss": 1.3654844284057617, "step": 725 }, { "epoch": 0.22230681385610962, "grad_norm": 0.2853640913963318, "learning_rate": 9.065280497392663e-05, "loss": 1.4238947868347167, "step": 730 }, { "epoch": 0.223829463266083, "grad_norm": 0.2294941246509552, "learning_rate": 9.050874842111498e-05, "loss": 1.4642324447631836, "step": 735 }, { "epoch": 0.22535211267605634, "grad_norm": 0.2794053554534912, "learning_rate": 9.03637065675255e-05, "loss": 1.4611818313598632, "step": 740 }, { "epoch": 0.2268747620860297, "grad_norm": 0.2210826426744461, "learning_rate": 9.021768294103443e-05, "loss": 1.456018829345703, "step": 745 }, { "epoch": 0.22839741149600304, "grad_norm": 0.24113371968269348, "learning_rate": 9.007068109339784e-05, "loss": 1.3719515800476074, "step": 750 }, { "epoch": 0.2299200609059764, "grad_norm": 0.2668301463127136, "learning_rate": 8.99227046001652e-05, "loss": 1.3636157989501954, "step": 755 }, { "epoch": 0.23144271031594976, "grad_norm": 0.36948826909065247, "learning_rate": 8.977375706059247e-05, "loss": 1.5281941413879394, "step": 760 }, { "epoch": 0.2329653597259231, "grad_norm": 0.2943294942378998, "learning_rate": 8.962384209755452e-05, "loss": 1.4288201332092285, "step": 765 }, { "epoch": 0.23448800913589646, "grad_norm": 0.3026641309261322, "learning_rate": 8.947296335745703e-05, "loss": 1.4038793563842773, "step": 770 }, { "epoch": 0.2360106585458698, "grad_norm": 0.20848454535007477, "learning_rate": 8.932112451014774e-05, "loss": 1.459784698486328, "step": 775 }, { "epoch": 0.23753330795584315, "grad_norm": 0.27259698510169983, "learning_rate": 8.916832924882728e-05, "loss": 1.4209893226623536, "step": 780 }, { "epoch": 0.23905595736581653, "grad_norm": 0.25965791940689087, "learning_rate": 8.901458128995927e-05, "loss": 1.378855323791504, "step": 785 }, { "epoch": 0.24057860677578988, "grad_norm": 0.305719792842865, "learning_rate": 8.885988437317992e-05, "loss": 1.4595756530761719, "step": 790 }, { "epoch": 0.24210125618576323, "grad_norm": 0.29244890809059143, "learning_rate": 8.870424226120714e-05, "loss": 1.4551380157470704, "step": 795 }, { "epoch": 0.24362390559573657, "grad_norm": 0.2980535328388214, "learning_rate": 8.854765873974898e-05, "loss": 1.4264792442321776, "step": 800 }, { "epoch": 0.24514655500570995, "grad_norm": 0.3499586284160614, "learning_rate": 8.839013761741148e-05, "loss": 1.467721652984619, "step": 805 }, { "epoch": 0.2466692044156833, "grad_norm": 0.2993587553501129, "learning_rate": 8.823168272560615e-05, "loss": 1.346705436706543, "step": 810 }, { "epoch": 0.24819185382565664, "grad_norm": 0.23189038038253784, "learning_rate": 8.807229791845673e-05, "loss": 1.4903203010559083, "step": 815 }, { "epoch": 0.24971450323563, "grad_norm": 0.2743084132671356, "learning_rate": 8.791198707270538e-05, "loss": 1.548980712890625, "step": 820 }, { "epoch": 0.25123715264560337, "grad_norm": 0.2221740335226059, "learning_rate": 8.775075408761851e-05, "loss": 1.4531554222106933, "step": 825 }, { "epoch": 0.2527598020555767, "grad_norm": 0.29099658131599426, "learning_rate": 8.758860288489183e-05, "loss": 1.4426555633544922, "step": 830 }, { "epoch": 0.25428245146555006, "grad_norm": 0.2629263401031494, "learning_rate": 8.742553740855506e-05, "loss": 1.4071794509887696, "step": 835 }, { "epoch": 0.2558051008755234, "grad_norm": 0.28747856616973877, "learning_rate": 8.726156162487587e-05, "loss": 1.5133395195007324, "step": 840 }, { "epoch": 0.25732775028549676, "grad_norm": 0.262517511844635, "learning_rate": 8.709667952226353e-05, "loss": 1.3573564529418944, "step": 845 }, { "epoch": 0.25885039969547013, "grad_norm": 0.22183161973953247, "learning_rate": 8.693089511117183e-05, "loss": 1.5251442909240722, "step": 850 }, { "epoch": 0.26037304910544345, "grad_norm": 0.21905767917633057, "learning_rate": 8.676421242400156e-05, "loss": 1.503794002532959, "step": 855 }, { "epoch": 0.26189569851541683, "grad_norm": 0.36307400465011597, "learning_rate": 8.659663551500246e-05, "loss": 1.3685101509094237, "step": 860 }, { "epoch": 0.2634183479253902, "grad_norm": 0.2499055415391922, "learning_rate": 8.642816846017449e-05, "loss": 1.3180089950561524, "step": 865 }, { "epoch": 0.2649409973353635, "grad_norm": 0.27423790097236633, "learning_rate": 8.625881535716883e-05, "loss": 1.50178804397583, "step": 870 }, { "epoch": 0.2664636467453369, "grad_norm": 0.23046822845935822, "learning_rate": 8.608858032518814e-05, "loss": 1.4345687866210937, "step": 875 }, { "epoch": 0.2679862961553102, "grad_norm": 0.32026252150535583, "learning_rate": 8.591746750488639e-05, "loss": 1.4084321975708007, "step": 880 }, { "epoch": 0.2695089455652836, "grad_norm": 0.2778593599796295, "learning_rate": 8.574548105826809e-05, "loss": 1.414495086669922, "step": 885 }, { "epoch": 0.271031594975257, "grad_norm": 0.3236066699028015, "learning_rate": 8.557262516858717e-05, "loss": 1.4425021171569825, "step": 890 }, { "epoch": 0.2725542443852303, "grad_norm": 0.2763606905937195, "learning_rate": 8.539890404024511e-05, "loss": 1.6016029357910155, "step": 895 }, { "epoch": 0.27407689379520367, "grad_norm": 0.2556283473968506, "learning_rate": 8.522432189868874e-05, "loss": 1.372022533416748, "step": 900 }, { "epoch": 0.275599543205177, "grad_norm": 0.2730630934238434, "learning_rate": 8.504888299030747e-05, "loss": 1.4496212005615234, "step": 905 }, { "epoch": 0.27712219261515036, "grad_norm": 0.22414790093898773, "learning_rate": 8.487259158232998e-05, "loss": 1.557776927947998, "step": 910 }, { "epoch": 0.27864484202512374, "grad_norm": 0.25023847818374634, "learning_rate": 8.469545196272042e-05, "loss": 1.3323833465576171, "step": 915 }, { "epoch": 0.28016749143509706, "grad_norm": 0.3127973973751068, "learning_rate": 8.451746844007416e-05, "loss": 1.5026471138000488, "step": 920 }, { "epoch": 0.28169014084507044, "grad_norm": 0.2822777330875397, "learning_rate": 8.43386453435129e-05, "loss": 1.3067480087280274, "step": 925 }, { "epoch": 0.28321279025504376, "grad_norm": 0.3239530920982361, "learning_rate": 8.415898702257949e-05, "loss": 1.458646583557129, "step": 930 }, { "epoch": 0.28473543966501713, "grad_norm": 0.27216675877571106, "learning_rate": 8.397849784713205e-05, "loss": 1.3857210159301758, "step": 935 }, { "epoch": 0.2862580890749905, "grad_norm": 0.3790968954563141, "learning_rate": 8.379718220723773e-05, "loss": 1.3885436058044434, "step": 940 }, { "epoch": 0.2877807384849638, "grad_norm": 0.35693275928497314, "learning_rate": 8.361504451306585e-05, "loss": 1.3546630859375, "step": 945 }, { "epoch": 0.2893033878949372, "grad_norm": 0.23096509277820587, "learning_rate": 8.343208919478074e-05, "loss": 1.4413816452026367, "step": 950 }, { "epoch": 0.2908260373049105, "grad_norm": 0.23972415924072266, "learning_rate": 8.324832070243393e-05, "loss": 1.5359551429748535, "step": 955 }, { "epoch": 0.2923486867148839, "grad_norm": 0.2613072693347931, "learning_rate": 8.30637435058559e-05, "loss": 1.6116878509521484, "step": 960 }, { "epoch": 0.2938713361248573, "grad_norm": 0.29908230900764465, "learning_rate": 8.287836209454735e-05, "loss": 1.3728031158447265, "step": 965 }, { "epoch": 0.2953939855348306, "grad_norm": 0.30336692929267883, "learning_rate": 8.269218097757008e-05, "loss": 1.371476173400879, "step": 970 }, { "epoch": 0.29691663494480397, "grad_norm": 0.2792283892631531, "learning_rate": 8.250520468343722e-05, "loss": 1.3788311004638671, "step": 975 }, { "epoch": 0.2984392843547773, "grad_norm": 0.3094034194946289, "learning_rate": 8.231743776000311e-05, "loss": 1.4456854820251466, "step": 980 }, { "epoch": 0.29996193376475067, "grad_norm": 0.2532956898212433, "learning_rate": 8.212888477435272e-05, "loss": 1.4226778030395508, "step": 985 }, { "epoch": 0.30148458317472404, "grad_norm": 0.2680925130844116, "learning_rate": 8.193955031269053e-05, "loss": 1.393292236328125, "step": 990 }, { "epoch": 0.30300723258469736, "grad_norm": 0.26347461342811584, "learning_rate": 8.1749438980229e-05, "loss": 1.4531295776367188, "step": 995 }, { "epoch": 0.30452988199467074, "grad_norm": 0.25980401039123535, "learning_rate": 8.155855540107648e-05, "loss": 1.4095684051513673, "step": 1000 }, { "epoch": 0.30605253140464406, "grad_norm": 0.25571075081825256, "learning_rate": 8.136690421812492e-05, "loss": 1.342782688140869, "step": 1005 }, { "epoch": 0.30757518081461743, "grad_norm": 0.23701255023479462, "learning_rate": 8.117449009293668e-05, "loss": 1.4156591415405273, "step": 1010 }, { "epoch": 0.3090978302245908, "grad_norm": 0.2656676173210144, "learning_rate": 8.09813177056314e-05, "loss": 1.3227380752563476, "step": 1015 }, { "epoch": 0.31062047963456413, "grad_norm": 0.30956336855888367, "learning_rate": 8.078739175477197e-05, "loss": 1.3795610427856446, "step": 1020 }, { "epoch": 0.3121431290445375, "grad_norm": 0.29831424355506897, "learning_rate": 8.059271695725038e-05, "loss": 1.5078824043273926, "step": 1025 }, { "epoch": 0.3136657784545108, "grad_norm": 0.3009597361087799, "learning_rate": 8.039729804817293e-05, "loss": 1.3122706413269043, "step": 1030 }, { "epoch": 0.3151884278644842, "grad_norm": 0.28154706954956055, "learning_rate": 8.020113978074504e-05, "loss": 1.2648576736450194, "step": 1035 }, { "epoch": 0.3167110772744576, "grad_norm": 0.25861454010009766, "learning_rate": 8.000424692615567e-05, "loss": 1.30448637008667, "step": 1040 }, { "epoch": 0.3182337266844309, "grad_norm": 0.23444527387619019, "learning_rate": 7.980662427346127e-05, "loss": 1.3907661437988281, "step": 1045 }, { "epoch": 0.31975637609440427, "grad_norm": 0.2578740417957306, "learning_rate": 7.96082766294693e-05, "loss": 1.395310115814209, "step": 1050 }, { "epoch": 0.3212790255043776, "grad_norm": 0.26323646306991577, "learning_rate": 7.940920881862126e-05, "loss": 1.5015592575073242, "step": 1055 }, { "epoch": 0.32280167491435097, "grad_norm": 0.24181155860424042, "learning_rate": 7.920942568287543e-05, "loss": 1.5405632972717285, "step": 1060 }, { "epoch": 0.32432432432432434, "grad_norm": 0.2329670935869217, "learning_rate": 7.9008932081589e-05, "loss": 1.3958099365234375, "step": 1065 }, { "epoch": 0.32584697373429766, "grad_norm": 0.23964090645313263, "learning_rate": 7.880773289139997e-05, "loss": 1.4673625946044921, "step": 1070 }, { "epoch": 0.32736962314427104, "grad_norm": 0.31865817308425903, "learning_rate": 7.860583300610849e-05, "loss": 1.541058349609375, "step": 1075 }, { "epoch": 0.32889227255424436, "grad_norm": 0.3059067130088806, "learning_rate": 7.840323733655778e-05, "loss": 1.4876275062561035, "step": 1080 }, { "epoch": 0.33041492196421773, "grad_norm": 0.2325078248977661, "learning_rate": 7.819995081051482e-05, "loss": 1.4936686515808106, "step": 1085 }, { "epoch": 0.3319375713741911, "grad_norm": 0.33646270632743835, "learning_rate": 7.799597837255032e-05, "loss": 1.3444353103637696, "step": 1090 }, { "epoch": 0.33346022078416443, "grad_norm": 0.29305240511894226, "learning_rate": 7.779132498391856e-05, "loss": 1.3916387557983398, "step": 1095 }, { "epoch": 0.3349828701941378, "grad_norm": 0.3107070326805115, "learning_rate": 7.758599562243673e-05, "loss": 1.4865869522094726, "step": 1100 }, { "epoch": 0.3365055196041112, "grad_norm": 0.2474549114704132, "learning_rate": 7.737999528236376e-05, "loss": 1.5631649971008301, "step": 1105 }, { "epoch": 0.3380281690140845, "grad_norm": 0.30205830931663513, "learning_rate": 7.717332897427893e-05, "loss": 1.351798152923584, "step": 1110 }, { "epoch": 0.3395508184240579, "grad_norm": 0.330427885055542, "learning_rate": 7.696600172495997e-05, "loss": 1.4060184478759765, "step": 1115 }, { "epoch": 0.3410734678340312, "grad_norm": 0.26146936416625977, "learning_rate": 7.675801857726077e-05, "loss": 1.396233367919922, "step": 1120 }, { "epoch": 0.34259611724400457, "grad_norm": 0.29280221462249756, "learning_rate": 7.654938458998875e-05, "loss": 1.323391056060791, "step": 1125 }, { "epoch": 0.34411876665397795, "grad_norm": 0.25476574897766113, "learning_rate": 7.634010483778184e-05, "loss": 1.3525615692138673, "step": 1130 }, { "epoch": 0.34564141606395127, "grad_norm": 0.2968114912509918, "learning_rate": 7.613018441098494e-05, "loss": 1.3722482681274415, "step": 1135 }, { "epoch": 0.34716406547392464, "grad_norm": 0.3112095594406128, "learning_rate": 7.591962841552627e-05, "loss": 1.4872213363647462, "step": 1140 }, { "epoch": 0.34868671488389796, "grad_norm": 0.24868836998939514, "learning_rate": 7.570844197279299e-05, "loss": 1.367682933807373, "step": 1145 }, { "epoch": 0.35020936429387134, "grad_norm": 0.3044701814651489, "learning_rate": 7.54966302195068e-05, "loss": 1.344968605041504, "step": 1150 }, { "epoch": 0.3517320137038447, "grad_norm": 0.283758282661438, "learning_rate": 7.528419830759892e-05, "loss": 1.3539758682250977, "step": 1155 }, { "epoch": 0.35325466311381803, "grad_norm": 0.31524917483329773, "learning_rate": 7.507115140408477e-05, "loss": 1.3392753601074219, "step": 1160 }, { "epoch": 0.3547773125237914, "grad_norm": 0.2978060841560364, "learning_rate": 7.485749469093834e-05, "loss": 1.383751678466797, "step": 1165 }, { "epoch": 0.35629996193376473, "grad_norm": 0.24903981387615204, "learning_rate": 7.464323336496606e-05, "loss": 1.4401054382324219, "step": 1170 }, { "epoch": 0.3578226113437381, "grad_norm": 0.2903728485107422, "learning_rate": 7.442837263768049e-05, "loss": 1.3851556777954102, "step": 1175 }, { "epoch": 0.3593452607537115, "grad_norm": 0.3136855661869049, "learning_rate": 7.421291773517354e-05, "loss": 1.3426216125488282, "step": 1180 }, { "epoch": 0.3608679101636848, "grad_norm": 0.2400982528924942, "learning_rate": 7.399687389798933e-05, "loss": 1.4459614753723145, "step": 1185 }, { "epoch": 0.3623905595736582, "grad_norm": 0.2520941495895386, "learning_rate": 7.37802463809967e-05, "loss": 1.370910930633545, "step": 1190 }, { "epoch": 0.3639132089836315, "grad_norm": 0.3427690863609314, "learning_rate": 7.356304045326147e-05, "loss": 1.335260009765625, "step": 1195 }, { "epoch": 0.3654358583936049, "grad_norm": 0.3588770925998688, "learning_rate": 7.33452613979182e-05, "loss": 1.3373279571533203, "step": 1200 }, { "epoch": 0.36695850780357825, "grad_norm": 0.3317570090293884, "learning_rate": 7.312691451204178e-05, "loss": 1.385964298248291, "step": 1205 }, { "epoch": 0.36848115721355157, "grad_norm": 0.2783828675746918, "learning_rate": 7.290800510651845e-05, "loss": 1.4141164779663087, "step": 1210 }, { "epoch": 0.37000380662352494, "grad_norm": 0.26642730832099915, "learning_rate": 7.268853850591679e-05, "loss": 1.3404644012451172, "step": 1215 }, { "epoch": 0.37152645603349826, "grad_norm": 0.25768765807151794, "learning_rate": 7.246852004835807e-05, "loss": 1.4136226654052735, "step": 1220 }, { "epoch": 0.37304910544347164, "grad_norm": 0.27597010135650635, "learning_rate": 7.22479550853865e-05, "loss": 1.426306915283203, "step": 1225 }, { "epoch": 0.374571754853445, "grad_norm": 0.24865882098674774, "learning_rate": 7.202684898183898e-05, "loss": 1.3518117904663085, "step": 1230 }, { "epoch": 0.37609440426341834, "grad_norm": 0.2266913801431656, "learning_rate": 7.180520711571471e-05, "loss": 1.4690813064575194, "step": 1235 }, { "epoch": 0.3776170536733917, "grad_norm": 0.2647339403629303, "learning_rate": 7.158303487804432e-05, "loss": 1.3690889358520508, "step": 1240 }, { "epoch": 0.37913970308336503, "grad_norm": 0.2828558087348938, "learning_rate": 7.136033767275871e-05, "loss": 1.334241771697998, "step": 1245 }, { "epoch": 0.3806623524933384, "grad_norm": 0.2561446726322174, "learning_rate": 7.113712091655772e-05, "loss": 1.3273275375366211, "step": 1250 }, { "epoch": 0.3821850019033118, "grad_norm": 0.2407621294260025, "learning_rate": 7.091339003877826e-05, "loss": 1.3427747726440429, "step": 1255 }, { "epoch": 0.3837076513132851, "grad_norm": 0.25592970848083496, "learning_rate": 7.068915048126231e-05, "loss": 1.3133956909179687, "step": 1260 }, { "epoch": 0.3852303007232585, "grad_norm": 0.24890656769275665, "learning_rate": 7.046440769822454e-05, "loss": 1.401773738861084, "step": 1265 }, { "epoch": 0.3867529501332318, "grad_norm": 0.2707661986351013, "learning_rate": 7.023916715611969e-05, "loss": 1.3378002166748046, "step": 1270 }, { "epoch": 0.3882755995432052, "grad_norm": 0.24935978651046753, "learning_rate": 7.001343433350956e-05, "loss": 1.3258022308349608, "step": 1275 }, { "epoch": 0.38979824895317855, "grad_norm": 0.31505095958709717, "learning_rate": 6.978721472092973e-05, "loss": 1.384083366394043, "step": 1280 }, { "epoch": 0.39132089836315187, "grad_norm": 0.2736486792564392, "learning_rate": 6.956051382075608e-05, "loss": 1.3886921882629395, "step": 1285 }, { "epoch": 0.39284354777312525, "grad_norm": 0.29390108585357666, "learning_rate": 6.933333714707094e-05, "loss": 1.406876564025879, "step": 1290 }, { "epoch": 0.39436619718309857, "grad_norm": 0.2984534502029419, "learning_rate": 6.910569022552895e-05, "loss": 1.3138214111328126, "step": 1295 }, { "epoch": 0.39588884659307194, "grad_norm": 0.2528838515281677, "learning_rate": 6.887757859322265e-05, "loss": 1.3129400253295898, "step": 1300 }, { "epoch": 0.3974114960030453, "grad_norm": 0.27338773012161255, "learning_rate": 6.86490077985478e-05, "loss": 1.356154441833496, "step": 1305 }, { "epoch": 0.39893414541301864, "grad_norm": 0.2755977213382721, "learning_rate": 6.841998340106847e-05, "loss": 1.370241928100586, "step": 1310 }, { "epoch": 0.400456794822992, "grad_norm": 0.3948673605918884, "learning_rate": 6.819051097138178e-05, "loss": 1.3480887413024902, "step": 1315 }, { "epoch": 0.40197944423296533, "grad_norm": 0.2611674964427948, "learning_rate": 6.79605960909824e-05, "loss": 1.474497413635254, "step": 1320 }, { "epoch": 0.4035020936429387, "grad_norm": 0.23646868765354156, "learning_rate": 6.773024435212678e-05, "loss": 1.4527637481689453, "step": 1325 }, { "epoch": 0.4050247430529121, "grad_norm": 0.22140051424503326, "learning_rate": 6.74994613576972e-05, "loss": 1.315192699432373, "step": 1330 }, { "epoch": 0.4065473924628854, "grad_norm": 0.30312591791152954, "learning_rate": 6.726825272106538e-05, "loss": 1.266726016998291, "step": 1335 }, { "epoch": 0.4080700418728588, "grad_norm": 0.26451852917671204, "learning_rate": 6.703662406595606e-05, "loss": 1.3504931449890136, "step": 1340 }, { "epoch": 0.40959269128283216, "grad_norm": 0.2913320064544678, "learning_rate": 6.680458102631009e-05, "loss": 1.4232087135314941, "step": 1345 }, { "epoch": 0.4111153406928055, "grad_norm": 0.31301552057266235, "learning_rate": 6.657212924614754e-05, "loss": 1.4294262886047364, "step": 1350 }, { "epoch": 0.41263799010277885, "grad_norm": 0.25427505373954773, "learning_rate": 6.633927437943028e-05, "loss": 1.479306411743164, "step": 1355 }, { "epoch": 0.41416063951275217, "grad_norm": 0.2708263397216797, "learning_rate": 6.610602208992454e-05, "loss": 1.3483418464660644, "step": 1360 }, { "epoch": 0.41568328892272555, "grad_norm": 0.3349183201789856, "learning_rate": 6.587237805106312e-05, "loss": 1.3606966018676758, "step": 1365 }, { "epoch": 0.4172059383326989, "grad_norm": 0.2648729383945465, "learning_rate": 6.563834794580742e-05, "loss": 1.4106568336486816, "step": 1370 }, { "epoch": 0.41872858774267224, "grad_norm": 0.24680568277835846, "learning_rate": 6.540393746650919e-05, "loss": 1.4123987197875976, "step": 1375 }, { "epoch": 0.4202512371526456, "grad_norm": 0.264300674200058, "learning_rate": 6.516915231477207e-05, "loss": 1.3612893104553223, "step": 1380 }, { "epoch": 0.42177388656261894, "grad_norm": 0.2791481018066406, "learning_rate": 6.49339982013129e-05, "loss": 1.6163249969482423, "step": 1385 }, { "epoch": 0.4232965359725923, "grad_norm": 0.23818041384220123, "learning_rate": 6.469848084582289e-05, "loss": 1.4644305229187011, "step": 1390 }, { "epoch": 0.4248191853825657, "grad_norm": 0.2435709536075592, "learning_rate": 6.446260597682839e-05, "loss": 1.3428779602050782, "step": 1395 }, { "epoch": 0.426341834792539, "grad_norm": 0.2401343584060669, "learning_rate": 6.422637933155162e-05, "loss": 1.3154414176940918, "step": 1400 }, { "epoch": 0.4278644842025124, "grad_norm": 0.2605147063732147, "learning_rate": 6.398980665577115e-05, "loss": 1.3638551712036133, "step": 1405 }, { "epoch": 0.4293871336124857, "grad_norm": 0.20154057443141937, "learning_rate": 6.375289370368204e-05, "loss": 1.4641175270080566, "step": 1410 }, { "epoch": 0.4309097830224591, "grad_norm": 0.2590329945087433, "learning_rate": 6.351564623775602e-05, "loss": 1.3620439529418946, "step": 1415 }, { "epoch": 0.43243243243243246, "grad_norm": 0.35539114475250244, "learning_rate": 6.327807002860116e-05, "loss": 1.302149772644043, "step": 1420 }, { "epoch": 0.4339550818424058, "grad_norm": 0.2675325274467468, "learning_rate": 6.304017085482171e-05, "loss": 1.306181049346924, "step": 1425 }, { "epoch": 0.43547773125237915, "grad_norm": 0.2589367926120758, "learning_rate": 6.280195450287736e-05, "loss": 1.3961198806762696, "step": 1430 }, { "epoch": 0.4370003806623525, "grad_norm": 0.27876636385917664, "learning_rate": 6.256342676694262e-05, "loss": 1.3006193161010742, "step": 1435 }, { "epoch": 0.43852303007232585, "grad_norm": 0.28582078218460083, "learning_rate": 6.23245934487658e-05, "loss": 1.3782499313354493, "step": 1440 }, { "epoch": 0.4400456794822992, "grad_norm": 0.2538052201271057, "learning_rate": 6.208546035752798e-05, "loss": 1.4886381149291992, "step": 1445 }, { "epoch": 0.44156832889227254, "grad_norm": 0.2826031446456909, "learning_rate": 6.184603330970165e-05, "loss": 1.3341392517089843, "step": 1450 }, { "epoch": 0.4430909783022459, "grad_norm": 0.25157082080841064, "learning_rate": 6.160631812890925e-05, "loss": 1.368797779083252, "step": 1455 }, { "epoch": 0.44461362771221924, "grad_norm": 0.21295174956321716, "learning_rate": 6.136632064578153e-05, "loss": 1.2691965103149414, "step": 1460 }, { "epoch": 0.4461362771221926, "grad_norm": 0.3233494460582733, "learning_rate": 6.112604669781572e-05, "loss": 1.308966064453125, "step": 1465 }, { "epoch": 0.447658926532166, "grad_norm": 0.34750598669052124, "learning_rate": 6.088550212923356e-05, "loss": 1.3082576751708985, "step": 1470 }, { "epoch": 0.4491815759421393, "grad_norm": 0.2640896439552307, "learning_rate": 6.064469279083912e-05, "loss": 1.3189506530761719, "step": 1475 }, { "epoch": 0.4507042253521127, "grad_norm": 0.240287646651268, "learning_rate": 6.040362453987651e-05, "loss": 1.363023567199707, "step": 1480 }, { "epoch": 0.452226874762086, "grad_norm": 0.2811414897441864, "learning_rate": 6.016230323988745e-05, "loss": 1.3733488082885743, "step": 1485 }, { "epoch": 0.4537495241720594, "grad_norm": 0.3292579650878906, "learning_rate": 5.992073476056854e-05, "loss": 1.4585867881774903, "step": 1490 }, { "epoch": 0.45527217358203276, "grad_norm": 0.26900094747543335, "learning_rate": 5.967892497762866e-05, "loss": 1.3601048469543457, "step": 1495 }, { "epoch": 0.4567948229920061, "grad_norm": 0.2594233751296997, "learning_rate": 5.943687977264584e-05, "loss": 1.3416101455688476, "step": 1500 }, { "epoch": 0.45831747240197945, "grad_norm": 0.2663646936416626, "learning_rate": 5.919460503292442e-05, "loss": 1.3562856674194337, "step": 1505 }, { "epoch": 0.4598401218119528, "grad_norm": 0.28269708156585693, "learning_rate": 5.895210665135169e-05, "loss": 1.3688299179077148, "step": 1510 }, { "epoch": 0.46136277122192615, "grad_norm": 0.2857932150363922, "learning_rate": 5.870939052625465e-05, "loss": 1.3016630172729493, "step": 1515 }, { "epoch": 0.4628854206318995, "grad_norm": 0.2867497205734253, "learning_rate": 5.8466462561256495e-05, "loss": 1.4517138481140137, "step": 1520 }, { "epoch": 0.46440807004187284, "grad_norm": 0.2611059844493866, "learning_rate": 5.8223328665133034e-05, "loss": 1.3801733016967774, "step": 1525 }, { "epoch": 0.4659307194518462, "grad_norm": 0.26675674319267273, "learning_rate": 5.7979994751668964e-05, "loss": 1.3979923248291015, "step": 1530 }, { "epoch": 0.46745336886181954, "grad_norm": 0.24703533947467804, "learning_rate": 5.773646673951406e-05, "loss": 1.4024689674377442, "step": 1535 }, { "epoch": 0.4689760182717929, "grad_norm": 0.36429521441459656, "learning_rate": 5.749275055203918e-05, "loss": 1.3610652923583983, "step": 1540 }, { "epoch": 0.4704986676817663, "grad_norm": 0.2706835865974426, "learning_rate": 5.724885211719221e-05, "loss": 1.3411127090454102, "step": 1545 }, { "epoch": 0.4720213170917396, "grad_norm": 0.2288634479045868, "learning_rate": 5.700477736735382e-05, "loss": 1.2600469589233398, "step": 1550 }, { "epoch": 0.473543966501713, "grad_norm": 0.25470563769340515, "learning_rate": 5.6760532239193275e-05, "loss": 1.3977832794189453, "step": 1555 }, { "epoch": 0.4750666159116863, "grad_norm": 0.2892740070819855, "learning_rate": 5.6516122673523967e-05, "loss": 1.378653335571289, "step": 1560 }, { "epoch": 0.4765892653216597, "grad_norm": 0.2725992202758789, "learning_rate": 5.6271554615158904e-05, "loss": 1.4045576095581054, "step": 1565 }, { "epoch": 0.47811191473163306, "grad_norm": 0.2719159722328186, "learning_rate": 5.602683401276615e-05, "loss": 1.2868476867675782, "step": 1570 }, { "epoch": 0.4796345641416064, "grad_norm": 0.27898305654525757, "learning_rate": 5.578196681872415e-05, "loss": 1.4293672561645507, "step": 1575 }, { "epoch": 0.48115721355157975, "grad_norm": 0.34255102276802063, "learning_rate": 5.5536958988976864e-05, "loss": 1.326737117767334, "step": 1580 }, { "epoch": 0.48267986296155313, "grad_norm": 0.231376513838768, "learning_rate": 5.529181648288901e-05, "loss": 1.3015432357788086, "step": 1585 }, { "epoch": 0.48420251237152645, "grad_norm": 0.3345688581466675, "learning_rate": 5.504654526310102e-05, "loss": 1.4542757034301759, "step": 1590 }, { "epoch": 0.4857251617814998, "grad_norm": 0.30328232049942017, "learning_rate": 5.480115129538409e-05, "loss": 1.398010540008545, "step": 1595 }, { "epoch": 0.48724781119147315, "grad_norm": 0.3044515550136566, "learning_rate": 5.455564054849501e-05, "loss": 1.4142882347106933, "step": 1600 }, { "epoch": 0.4887704606014465, "grad_norm": 0.31157538294792175, "learning_rate": 5.431001899403098e-05, "loss": 1.3000102996826173, "step": 1605 }, { "epoch": 0.4902931100114199, "grad_norm": 0.31317242980003357, "learning_rate": 5.406429260628444e-05, "loss": 1.3200332641601562, "step": 1610 }, { "epoch": 0.4918157594213932, "grad_norm": 0.2634436786174774, "learning_rate": 5.381846736209769e-05, "loss": 1.3754449844360352, "step": 1615 }, { "epoch": 0.4933384088313666, "grad_norm": 0.2267792522907257, "learning_rate": 5.357254924071754e-05, "loss": 1.4365095138549804, "step": 1620 }, { "epoch": 0.4948610582413399, "grad_norm": 0.27569952607154846, "learning_rate": 5.332654422364983e-05, "loss": 1.388918685913086, "step": 1625 }, { "epoch": 0.4963837076513133, "grad_norm": 0.24842625856399536, "learning_rate": 5.308045829451403e-05, "loss": 1.3314464569091797, "step": 1630 }, { "epoch": 0.49790635706128666, "grad_norm": 0.2644146680831909, "learning_rate": 5.28342974388976e-05, "loss": 1.2916046142578126, "step": 1635 }, { "epoch": 0.49942900647126, "grad_norm": 0.22177313268184662, "learning_rate": 5.258806764421048e-05, "loss": 1.3917448043823242, "step": 1640 }, { "epoch": 0.5009516558812334, "grad_norm": 0.2361970990896225, "learning_rate": 5.23417748995394e-05, "loss": 1.376643180847168, "step": 1645 }, { "epoch": 0.5024743052912067, "grad_norm": 0.321374773979187, "learning_rate": 5.2095425195502256e-05, "loss": 1.3032066345214843, "step": 1650 }, { "epoch": 0.50399695470118, "grad_norm": 0.27355530858039856, "learning_rate": 5.184902452410237e-05, "loss": 1.2973228454589845, "step": 1655 }, { "epoch": 0.5055196041111534, "grad_norm": 0.2462250292301178, "learning_rate": 5.1602578878582776e-05, "loss": 1.308804988861084, "step": 1660 }, { "epoch": 0.5070422535211268, "grad_norm": 0.19962942600250244, "learning_rate": 5.135609425328033e-05, "loss": 1.3739556312561034, "step": 1665 }, { "epoch": 0.5085649029311001, "grad_norm": 0.26053565740585327, "learning_rate": 5.1109576643480105e-05, "loss": 1.362898826599121, "step": 1670 }, { "epoch": 0.5100875523410735, "grad_norm": 0.2830159068107605, "learning_rate": 5.086303204526943e-05, "loss": 1.2908313751220704, "step": 1675 }, { "epoch": 0.5116102017510468, "grad_norm": 0.3163045644760132, "learning_rate": 5.061646645539205e-05, "loss": 1.3349504470825195, "step": 1680 }, { "epoch": 0.5131328511610201, "grad_norm": 0.26570799946784973, "learning_rate": 5.0369885871102296e-05, "loss": 1.2985321044921876, "step": 1685 }, { "epoch": 0.5146555005709935, "grad_norm": 0.23638826608657837, "learning_rate": 5.012329629001924e-05, "loss": 1.2784423828125, "step": 1690 }, { "epoch": 0.5161781499809669, "grad_norm": 0.23448485136032104, "learning_rate": 4.987670370998078e-05, "loss": 1.423243236541748, "step": 1695 }, { "epoch": 0.5177007993909403, "grad_norm": 0.2314259111881256, "learning_rate": 4.963011412889773e-05, "loss": 1.3492928504943849, "step": 1700 }, { "epoch": 0.5192234488009136, "grad_norm": 0.2584417760372162, "learning_rate": 4.9383533544607974e-05, "loss": 1.3226016998291015, "step": 1705 }, { "epoch": 0.5207460982108869, "grad_norm": 0.2770603597164154, "learning_rate": 4.913696795473058e-05, "loss": 1.6151105880737304, "step": 1710 }, { "epoch": 0.5222687476208603, "grad_norm": 0.30756762623786926, "learning_rate": 4.88904233565199e-05, "loss": 1.2907414436340332, "step": 1715 }, { "epoch": 0.5237913970308337, "grad_norm": 0.3000791072845459, "learning_rate": 4.864390574671968e-05, "loss": 1.3248751640319825, "step": 1720 }, { "epoch": 0.525314046440807, "grad_norm": 0.27256903052330017, "learning_rate": 4.839742112141724e-05, "loss": 1.2656379699707032, "step": 1725 }, { "epoch": 0.5268366958507804, "grad_norm": 0.24658766388893127, "learning_rate": 4.815097547589763e-05, "loss": 1.3495702743530273, "step": 1730 }, { "epoch": 0.5283593452607537, "grad_norm": 0.343595951795578, "learning_rate": 4.790457480449775e-05, "loss": 1.4066032409667968, "step": 1735 }, { "epoch": 0.529881994670727, "grad_norm": 0.2558363676071167, "learning_rate": 4.76582251004606e-05, "loss": 1.3326688766479493, "step": 1740 }, { "epoch": 0.5314046440807004, "grad_norm": 0.2858749032020569, "learning_rate": 4.741193235578952e-05, "loss": 1.2113912582397461, "step": 1745 }, { "epoch": 0.5329272934906738, "grad_norm": 0.2679879069328308, "learning_rate": 4.7165702561102414e-05, "loss": 1.310260009765625, "step": 1750 }, { "epoch": 0.5344499429006472, "grad_norm": 0.32227835059165955, "learning_rate": 4.6919541705485985e-05, "loss": 1.2331014633178712, "step": 1755 }, { "epoch": 0.5359725923106204, "grad_norm": 0.39187365770339966, "learning_rate": 4.667345577635018e-05, "loss": 1.2413177490234375, "step": 1760 }, { "epoch": 0.5374952417205938, "grad_norm": 0.26487377285957336, "learning_rate": 4.642745075928247e-05, "loss": 1.3207042694091797, "step": 1765 }, { "epoch": 0.5390178911305672, "grad_norm": 0.23867976665496826, "learning_rate": 4.618153263790232e-05, "loss": 1.339517307281494, "step": 1770 }, { "epoch": 0.5405405405405406, "grad_norm": 0.32078996300697327, "learning_rate": 4.5935707393715565e-05, "loss": 1.2735256195068358, "step": 1775 }, { "epoch": 0.542063189950514, "grad_norm": 0.2798478305339813, "learning_rate": 4.568998100596903e-05, "loss": 1.47486572265625, "step": 1780 }, { "epoch": 0.5435858393604872, "grad_norm": 0.2683444917201996, "learning_rate": 4.5444359451505006e-05, "loss": 1.329602336883545, "step": 1785 }, { "epoch": 0.5451084887704606, "grad_norm": 0.23403924703598022, "learning_rate": 4.5198848704615914e-05, "loss": 1.3003073692321778, "step": 1790 }, { "epoch": 0.546631138180434, "grad_norm": 0.30789533257484436, "learning_rate": 4.4953454736898976e-05, "loss": 1.3623156547546387, "step": 1795 }, { "epoch": 0.5481537875904073, "grad_norm": 0.31680822372436523, "learning_rate": 4.4708183517110985e-05, "loss": 1.3261301040649414, "step": 1800 }, { "epoch": 0.5496764370003807, "grad_norm": 0.27970680594444275, "learning_rate": 4.446304101102314e-05, "loss": 1.35093994140625, "step": 1805 }, { "epoch": 0.551199086410354, "grad_norm": 0.32643061876296997, "learning_rate": 4.421803318127587e-05, "loss": 1.3861387252807618, "step": 1810 }, { "epoch": 0.5527217358203274, "grad_norm": 0.3180871307849884, "learning_rate": 4.397316598723385e-05, "loss": 1.3708114624023438, "step": 1815 }, { "epoch": 0.5542443852303007, "grad_norm": 0.2863382399082184, "learning_rate": 4.372844538484111e-05, "loss": 1.3640021324157714, "step": 1820 }, { "epoch": 0.5557670346402741, "grad_norm": 0.2550867795944214, "learning_rate": 4.348387732647605e-05, "loss": 1.3122490882873534, "step": 1825 }, { "epoch": 0.5572896840502475, "grad_norm": 0.3103955388069153, "learning_rate": 4.3239467760806736e-05, "loss": 1.2464099884033204, "step": 1830 }, { "epoch": 0.5588123334602207, "grad_norm": 0.2745635509490967, "learning_rate": 4.299522263264619e-05, "loss": 1.3070437431335449, "step": 1835 }, { "epoch": 0.5603349828701941, "grad_norm": 0.2566152513027191, "learning_rate": 4.27511478828078e-05, "loss": 1.2702374458312988, "step": 1840 }, { "epoch": 0.5618576322801675, "grad_norm": 0.32568952441215515, "learning_rate": 4.250724944796082e-05, "loss": 1.2957048416137695, "step": 1845 }, { "epoch": 0.5633802816901409, "grad_norm": 0.32877373695373535, "learning_rate": 4.226353326048593e-05, "loss": 1.2834630012512207, "step": 1850 }, { "epoch": 0.5649029311001142, "grad_norm": 0.28231871128082275, "learning_rate": 4.2020005248331054e-05, "loss": 1.3048977851867676, "step": 1855 }, { "epoch": 0.5664255805100875, "grad_norm": 0.24540714919567108, "learning_rate": 4.1776671334866985e-05, "loss": 1.3459823608398438, "step": 1860 }, { "epoch": 0.5679482299200609, "grad_norm": 0.3710729479789734, "learning_rate": 4.153353743874352e-05, "loss": 1.270101261138916, "step": 1865 }, { "epoch": 0.5694708793300343, "grad_norm": 0.2750590443611145, "learning_rate": 4.1290609473745363e-05, "loss": 1.3107969284057617, "step": 1870 }, { "epoch": 0.5709935287400076, "grad_norm": 0.2705315947532654, "learning_rate": 4.1047893348648314e-05, "loss": 1.4802775382995605, "step": 1875 }, { "epoch": 0.572516178149981, "grad_norm": 0.3106956481933594, "learning_rate": 4.0805394967075586e-05, "loss": 1.3171422958374024, "step": 1880 }, { "epoch": 0.5740388275599543, "grad_norm": 0.28099218010902405, "learning_rate": 4.056312022735417e-05, "loss": 1.32993803024292, "step": 1885 }, { "epoch": 0.5755614769699277, "grad_norm": 0.3052349090576172, "learning_rate": 4.032107502237136e-05, "loss": 1.2898494720458984, "step": 1890 }, { "epoch": 0.577084126379901, "grad_norm": 0.27192485332489014, "learning_rate": 4.007926523943145e-05, "loss": 1.26883544921875, "step": 1895 }, { "epoch": 0.5786067757898744, "grad_norm": 0.3369957506656647, "learning_rate": 3.983769676011256e-05, "loss": 1.3386381149291993, "step": 1900 }, { "epoch": 0.5801294251998478, "grad_norm": 0.3373662531375885, "learning_rate": 3.959637546012349e-05, "loss": 1.274648952484131, "step": 1905 }, { "epoch": 0.581652074609821, "grad_norm": 0.26808416843414307, "learning_rate": 3.93553072091609e-05, "loss": 1.3046018600463867, "step": 1910 }, { "epoch": 0.5831747240197944, "grad_norm": 0.29087021946907043, "learning_rate": 3.9114497870766456e-05, "loss": 1.2680070877075196, "step": 1915 }, { "epoch": 0.5846973734297678, "grad_norm": 0.3326050043106079, "learning_rate": 3.887395330218429e-05, "loss": 1.2655141830444336, "step": 1920 }, { "epoch": 0.5862200228397412, "grad_norm": 0.26732727885246277, "learning_rate": 3.8633679354218484e-05, "loss": 1.347468376159668, "step": 1925 }, { "epoch": 0.5877426722497145, "grad_norm": 0.26580217480659485, "learning_rate": 3.8393681871090756e-05, "loss": 1.561385154724121, "step": 1930 }, { "epoch": 0.5892653216596878, "grad_norm": 0.32778772711753845, "learning_rate": 3.815396669029836e-05, "loss": 1.2461229324340821, "step": 1935 }, { "epoch": 0.5907879710696612, "grad_norm": 0.27303579449653625, "learning_rate": 3.7914539642472035e-05, "loss": 1.2675182342529296, "step": 1940 }, { "epoch": 0.5923106204796346, "grad_norm": 0.30458420515060425, "learning_rate": 3.767540655123421e-05, "loss": 1.3039443969726563, "step": 1945 }, { "epoch": 0.5938332698896079, "grad_norm": 0.32060548663139343, "learning_rate": 3.7436573233057395e-05, "loss": 1.3895456314086914, "step": 1950 }, { "epoch": 0.5953559192995813, "grad_norm": 0.32158687710762024, "learning_rate": 3.719804549712265e-05, "loss": 1.3140850067138672, "step": 1955 }, { "epoch": 0.5968785687095546, "grad_norm": 0.2586275637149811, "learning_rate": 3.6959829145178294e-05, "loss": 1.2419183731079102, "step": 1960 }, { "epoch": 0.598401218119528, "grad_norm": 0.3412674069404602, "learning_rate": 3.672192997139885e-05, "loss": 1.305590534210205, "step": 1965 }, { "epoch": 0.5999238675295013, "grad_norm": 0.3197862505912781, "learning_rate": 3.6484353762244005e-05, "loss": 1.2525906562805176, "step": 1970 }, { "epoch": 0.6014465169394747, "grad_norm": 0.23176339268684387, "learning_rate": 3.624710629631796e-05, "loss": 1.3585104942321777, "step": 1975 }, { "epoch": 0.6029691663494481, "grad_norm": 0.32459062337875366, "learning_rate": 3.601019334422887e-05, "loss": 1.4005154609680175, "step": 1980 }, { "epoch": 0.6044918157594213, "grad_norm": 0.2904948592185974, "learning_rate": 3.5773620668448384e-05, "loss": 1.3235326766967774, "step": 1985 }, { "epoch": 0.6060144651693947, "grad_norm": 0.3084491789340973, "learning_rate": 3.553739402317162e-05, "loss": 1.3596025466918946, "step": 1990 }, { "epoch": 0.6075371145793681, "grad_norm": 0.2687482237815857, "learning_rate": 3.530151915417712e-05, "loss": 1.3798536300659179, "step": 1995 }, { "epoch": 0.6090597639893415, "grad_norm": 0.34662067890167236, "learning_rate": 3.50660017986871e-05, "loss": 1.3232461929321289, "step": 2000 }, { "epoch": 0.6105824133993148, "grad_norm": 0.26509180665016174, "learning_rate": 3.4830847685227944e-05, "loss": 1.2550721168518066, "step": 2005 }, { "epoch": 0.6121050628092881, "grad_norm": 0.30758926272392273, "learning_rate": 3.4596062533490815e-05, "loss": 1.237048053741455, "step": 2010 }, { "epoch": 0.6136277122192615, "grad_norm": 0.2841697931289673, "learning_rate": 3.436165205419258e-05, "loss": 1.2388126373291015, "step": 2015 }, { "epoch": 0.6151503616292349, "grad_norm": 0.31586602330207825, "learning_rate": 3.41276219489369e-05, "loss": 1.2853063583374023, "step": 2020 }, { "epoch": 0.6166730110392082, "grad_norm": 0.354833722114563, "learning_rate": 3.389397791007548e-05, "loss": 1.4346676826477052, "step": 2025 }, { "epoch": 0.6181956604491816, "grad_norm": 0.277838796377182, "learning_rate": 3.3660725620569733e-05, "loss": 1.3268421173095704, "step": 2030 }, { "epoch": 0.6197183098591549, "grad_norm": 0.2964206039905548, "learning_rate": 3.3427870753852476e-05, "loss": 1.2526841163635254, "step": 2035 }, { "epoch": 0.6212409592691283, "grad_norm": 0.31251513957977295, "learning_rate": 3.319541897368991e-05, "loss": 1.3913281440734864, "step": 2040 }, { "epoch": 0.6227636086791016, "grad_norm": 0.2911834418773651, "learning_rate": 3.296337593404395e-05, "loss": 1.304744815826416, "step": 2045 }, { "epoch": 0.624286258089075, "grad_norm": 0.24373088777065277, "learning_rate": 3.273174727893463e-05, "loss": 1.3184202194213868, "step": 2050 }, { "epoch": 0.6258089074990484, "grad_norm": 0.25820231437683105, "learning_rate": 3.250053864230281e-05, "loss": 1.303819179534912, "step": 2055 }, { "epoch": 0.6273315569090216, "grad_norm": 0.28526636958122253, "learning_rate": 3.226975564787322e-05, "loss": 1.2755561828613282, "step": 2060 }, { "epoch": 0.628854206318995, "grad_norm": 0.26332443952560425, "learning_rate": 3.2039403909017604e-05, "loss": 1.2744020462036132, "step": 2065 }, { "epoch": 0.6303768557289684, "grad_norm": 0.26798829436302185, "learning_rate": 3.1809489028618225e-05, "loss": 1.2746036529541016, "step": 2070 }, { "epoch": 0.6318995051389418, "grad_norm": 0.32245302200317383, "learning_rate": 3.1580016598931545e-05, "loss": 1.193479633331299, "step": 2075 }, { "epoch": 0.6334221545489152, "grad_norm": 0.2814018428325653, "learning_rate": 3.1350992201452214e-05, "loss": 1.342749786376953, "step": 2080 }, { "epoch": 0.6349448039588884, "grad_norm": 0.25612759590148926, "learning_rate": 3.1122421406777364e-05, "loss": 1.2896506309509277, "step": 2085 }, { "epoch": 0.6364674533688618, "grad_norm": 0.2602790892124176, "learning_rate": 3.089430977447106e-05, "loss": 1.5544681549072266, "step": 2090 }, { "epoch": 0.6379901027788352, "grad_norm": 0.31517425179481506, "learning_rate": 3.066666285292906e-05, "loss": 1.3094079971313477, "step": 2095 }, { "epoch": 0.6395127521888085, "grad_norm": 0.303256094455719, "learning_rate": 3.0439486179243926e-05, "loss": 1.2833490371704102, "step": 2100 }, { "epoch": 0.6410354015987819, "grad_norm": 0.2497071474790573, "learning_rate": 3.0212785279070287e-05, "loss": 1.57401762008667, "step": 2105 }, { "epoch": 0.6425580510087552, "grad_norm": 0.24763460457324982, "learning_rate": 2.9986565666490463e-05, "loss": 1.277338409423828, "step": 2110 }, { "epoch": 0.6440807004187286, "grad_norm": 0.3681677281856537, "learning_rate": 2.976083284388031e-05, "loss": 1.2738154411315918, "step": 2115 }, { "epoch": 0.6456033498287019, "grad_norm": 0.3086223900318146, "learning_rate": 2.953559230177545e-05, "loss": 1.2444513320922852, "step": 2120 }, { "epoch": 0.6471259992386753, "grad_norm": 0.25953373312950134, "learning_rate": 2.9310849518737703e-05, "loss": 1.296909713745117, "step": 2125 }, { "epoch": 0.6486486486486487, "grad_norm": 0.2607947587966919, "learning_rate": 2.9086609961221755e-05, "loss": 1.3309907913208008, "step": 2130 }, { "epoch": 0.650171298058622, "grad_norm": 0.35296371579170227, "learning_rate": 2.8862879083442273e-05, "loss": 1.3392168998718261, "step": 2135 }, { "epoch": 0.6516939474685953, "grad_norm": 0.255947470664978, "learning_rate": 2.863966232724129e-05, "loss": 1.2578866958618165, "step": 2140 }, { "epoch": 0.6532165968785687, "grad_norm": 0.34403857588768005, "learning_rate": 2.8416965121955695e-05, "loss": 1.3971917152404785, "step": 2145 }, { "epoch": 0.6547392462885421, "grad_norm": 0.2608356773853302, "learning_rate": 2.819479288428529e-05, "loss": 1.2825126647949219, "step": 2150 }, { "epoch": 0.6562618956985155, "grad_norm": 0.30656731128692627, "learning_rate": 2.797315101816103e-05, "loss": 1.4668644905090331, "step": 2155 }, { "epoch": 0.6577845451084887, "grad_norm": 0.29252496361732483, "learning_rate": 2.775204491461353e-05, "loss": 1.3426076889038085, "step": 2160 }, { "epoch": 0.6593071945184621, "grad_norm": 0.2919674217700958, "learning_rate": 2.7531479951641924e-05, "loss": 1.3578786849975586, "step": 2165 }, { "epoch": 0.6608298439284355, "grad_norm": 0.27810409665107727, "learning_rate": 2.7311461494083213e-05, "loss": 1.2733769416809082, "step": 2170 }, { "epoch": 0.6623524933384088, "grad_norm": 0.38064339756965637, "learning_rate": 2.709199489348156e-05, "loss": 1.315932846069336, "step": 2175 }, { "epoch": 0.6638751427483822, "grad_norm": 0.2880454361438751, "learning_rate": 2.687308548795825e-05, "loss": 1.4902687072753906, "step": 2180 }, { "epoch": 0.6653977921583555, "grad_norm": 0.34167200326919556, "learning_rate": 2.6654738602081818e-05, "loss": 1.4305374145507812, "step": 2185 }, { "epoch": 0.6669204415683289, "grad_norm": 0.2812774181365967, "learning_rate": 2.643695954673855e-05, "loss": 1.2832210540771485, "step": 2190 }, { "epoch": 0.6684430909783022, "grad_norm": 0.3423842489719391, "learning_rate": 2.6219753619003317e-05, "loss": 1.2647760391235352, "step": 2195 }, { "epoch": 0.6699657403882756, "grad_norm": 0.29617008566856384, "learning_rate": 2.6003126102010695e-05, "loss": 1.3261732101440429, "step": 2200 }, { "epoch": 0.671488389798249, "grad_norm": 0.2799670398235321, "learning_rate": 2.5787082264826464e-05, "loss": 1.3618677139282227, "step": 2205 }, { "epoch": 0.6730110392082224, "grad_norm": 0.34016603231430054, "learning_rate": 2.5571627362319524e-05, "loss": 1.2981189727783202, "step": 2210 }, { "epoch": 0.6745336886181956, "grad_norm": 0.2911815941333771, "learning_rate": 2.5356766635033968e-05, "loss": 1.273648166656494, "step": 2215 }, { "epoch": 0.676056338028169, "grad_norm": 0.2776961028575897, "learning_rate": 2.514250530906167e-05, "loss": 1.300809669494629, "step": 2220 }, { "epoch": 0.6775789874381424, "grad_norm": 0.25458282232284546, "learning_rate": 2.4928848595915226e-05, "loss": 1.2465097427368164, "step": 2225 }, { "epoch": 0.6791016368481158, "grad_norm": 0.34107667207717896, "learning_rate": 2.4715801692401087e-05, "loss": 1.3140758514404296, "step": 2230 }, { "epoch": 0.6806242862580891, "grad_norm": 0.30480700731277466, "learning_rate": 2.450336978049322e-05, "loss": 1.2527847290039062, "step": 2235 }, { "epoch": 0.6821469356680624, "grad_norm": 0.2863146960735321, "learning_rate": 2.429155802720704e-05, "loss": 1.2418293952941895, "step": 2240 }, { "epoch": 0.6836695850780358, "grad_norm": 0.2734138071537018, "learning_rate": 2.4080371584473748e-05, "loss": 1.2698816299438476, "step": 2245 }, { "epoch": 0.6851922344880091, "grad_norm": 0.2867834270000458, "learning_rate": 2.3869815589015064e-05, "loss": 1.266134548187256, "step": 2250 }, { "epoch": 0.6867148838979825, "grad_norm": 0.27337172627449036, "learning_rate": 2.3659895162218183e-05, "loss": 1.3900789260864257, "step": 2255 }, { "epoch": 0.6882375333079559, "grad_norm": 0.3269335925579071, "learning_rate": 2.3450615410011245e-05, "loss": 1.253995132446289, "step": 2260 }, { "epoch": 0.6897601827179292, "grad_norm": 0.3106987178325653, "learning_rate": 2.324198142273924e-05, "loss": 1.2283190727233886, "step": 2265 }, { "epoch": 0.6912828321279025, "grad_norm": 0.2846229672431946, "learning_rate": 2.3033998275040046e-05, "loss": 1.4368681907653809, "step": 2270 }, { "epoch": 0.6928054815378759, "grad_norm": 0.3190728724002838, "learning_rate": 2.282667102572107e-05, "loss": 1.2534235954284667, "step": 2275 }, { "epoch": 0.6943281309478493, "grad_norm": 0.3506607413291931, "learning_rate": 2.2620004717636245e-05, "loss": 1.2582056999206543, "step": 2280 }, { "epoch": 0.6958507803578227, "grad_norm": 0.31820976734161377, "learning_rate": 2.241400437756328e-05, "loss": 1.253010368347168, "step": 2285 }, { "epoch": 0.6973734297677959, "grad_norm": 0.3363837003707886, "learning_rate": 2.2208675016081447e-05, "loss": 1.3797335624694824, "step": 2290 }, { "epoch": 0.6988960791777693, "grad_norm": 0.2566366195678711, "learning_rate": 2.20040216274497e-05, "loss": 1.30718936920166, "step": 2295 }, { "epoch": 0.7004187285877427, "grad_norm": 0.25630056858062744, "learning_rate": 2.1800049189485182e-05, "loss": 1.2806304931640624, "step": 2300 }, { "epoch": 0.701941377997716, "grad_norm": 0.3117572069168091, "learning_rate": 2.1596762663442218e-05, "loss": 1.2796730041503905, "step": 2305 }, { "epoch": 0.7034640274076894, "grad_norm": 0.296891987323761, "learning_rate": 2.139416699389153e-05, "loss": 1.2582951545715333, "step": 2310 }, { "epoch": 0.7049866768176627, "grad_norm": 0.22488300502300262, "learning_rate": 2.119226710860003e-05, "loss": 1.2564146995544434, "step": 2315 }, { "epoch": 0.7065093262276361, "grad_norm": 0.2817855477333069, "learning_rate": 2.099106791841101e-05, "loss": 1.257526969909668, "step": 2320 }, { "epoch": 0.7080319756376094, "grad_norm": 0.28889355063438416, "learning_rate": 2.0790574317124588e-05, "loss": 1.2911022186279297, "step": 2325 }, { "epoch": 0.7095546250475828, "grad_norm": 0.24301740527153015, "learning_rate": 2.0590791181378738e-05, "loss": 1.2999372482299805, "step": 2330 }, { "epoch": 0.7110772744575562, "grad_norm": 0.3573141098022461, "learning_rate": 2.0391723370530707e-05, "loss": 1.2373428344726562, "step": 2335 }, { "epoch": 0.7125999238675295, "grad_norm": 0.27264028787612915, "learning_rate": 2.0193375726538737e-05, "loss": 1.2649499893188476, "step": 2340 }, { "epoch": 0.7141225732775028, "grad_norm": 0.28385934233665466, "learning_rate": 1.9995753073844347e-05, "loss": 1.3323958396911622, "step": 2345 }, { "epoch": 0.7156452226874762, "grad_norm": 0.31522929668426514, "learning_rate": 1.979886021925499e-05, "loss": 1.2727210998535157, "step": 2350 }, { "epoch": 0.7171678720974496, "grad_norm": 0.3457392454147339, "learning_rate": 1.9602701951827078e-05, "loss": 1.2966115951538086, "step": 2355 }, { "epoch": 0.718690521507423, "grad_norm": 0.3633219301700592, "learning_rate": 1.940728304274963e-05, "loss": 1.2634574890136718, "step": 2360 }, { "epoch": 0.7202131709173962, "grad_norm": 0.2844873070716858, "learning_rate": 1.9212608245228047e-05, "loss": 1.3942211151123047, "step": 2365 }, { "epoch": 0.7217358203273696, "grad_norm": 0.267837792634964, "learning_rate": 1.901868229436861e-05, "loss": 1.2552343368530274, "step": 2370 }, { "epoch": 0.723258469737343, "grad_norm": 0.27028533816337585, "learning_rate": 1.8825509907063327e-05, "loss": 1.2847795486450195, "step": 2375 }, { "epoch": 0.7247811191473164, "grad_norm": 0.24411892890930176, "learning_rate": 1.86330957818751e-05, "loss": 1.3301410675048828, "step": 2380 }, { "epoch": 0.7263037685572897, "grad_norm": 0.27910399436950684, "learning_rate": 1.844144459892351e-05, "loss": 1.3585662841796875, "step": 2385 }, { "epoch": 0.727826417967263, "grad_norm": 0.24504560232162476, "learning_rate": 1.825056101977101e-05, "loss": 1.2342955589294433, "step": 2390 }, { "epoch": 0.7293490673772364, "grad_norm": 0.3044109046459198, "learning_rate": 1.8060449687309477e-05, "loss": 1.2734466552734376, "step": 2395 }, { "epoch": 0.7308717167872097, "grad_norm": 0.29212686419487, "learning_rate": 1.7871115225647294e-05, "loss": 1.2420330047607422, "step": 2400 }, { "epoch": 0.7323943661971831, "grad_norm": 0.29025325179100037, "learning_rate": 1.7682562239996914e-05, "loss": 1.3065637588500976, "step": 2405 }, { "epoch": 0.7339170156071565, "grad_norm": 0.3286866545677185, "learning_rate": 1.749479531656279e-05, "loss": 1.2894063949584962, "step": 2410 }, { "epoch": 0.7354396650171298, "grad_norm": 0.3037058115005493, "learning_rate": 1.7307819022429926e-05, "loss": 1.3009160995483398, "step": 2415 }, { "epoch": 0.7369623144271031, "grad_norm": 0.28537967801094055, "learning_rate": 1.7121637905452657e-05, "loss": 1.295482063293457, "step": 2420 }, { "epoch": 0.7384849638370765, "grad_norm": 0.2656344473361969, "learning_rate": 1.693625649414411e-05, "loss": 1.291648769378662, "step": 2425 }, { "epoch": 0.7400076132470499, "grad_norm": 0.27123740315437317, "learning_rate": 1.675167929756608e-05, "loss": 1.3669890403747558, "step": 2430 }, { "epoch": 0.7415302626570233, "grad_norm": 0.24127206206321716, "learning_rate": 1.6567910805219273e-05, "loss": 1.2923422813415528, "step": 2435 }, { "epoch": 0.7430529120669965, "grad_norm": 0.3503820598125458, "learning_rate": 1.6384955486934156e-05, "loss": 1.3577987670898437, "step": 2440 }, { "epoch": 0.7445755614769699, "grad_norm": 0.2909773588180542, "learning_rate": 1.6202817792762282e-05, "loss": 1.285128688812256, "step": 2445 }, { "epoch": 0.7460982108869433, "grad_norm": 0.30610406398773193, "learning_rate": 1.602150215286795e-05, "loss": 1.2521181106567383, "step": 2450 }, { "epoch": 0.7476208602969167, "grad_norm": 0.32047051191329956, "learning_rate": 1.5841012977420516e-05, "loss": 1.34920654296875, "step": 2455 }, { "epoch": 0.74914350970689, "grad_norm": 0.2548268139362335, "learning_rate": 1.5661354656487115e-05, "loss": 1.2425745010375977, "step": 2460 }, { "epoch": 0.7506661591168633, "grad_norm": 0.2816760838031769, "learning_rate": 1.548253155992585e-05, "loss": 1.3260144233703612, "step": 2465 }, { "epoch": 0.7521888085268367, "grad_norm": 0.31639087200164795, "learning_rate": 1.530454803727958e-05, "loss": 1.2803930282592773, "step": 2470 }, { "epoch": 0.75371145793681, "grad_norm": 0.3307602107524872, "learning_rate": 1.512740841767003e-05, "loss": 1.326441764831543, "step": 2475 }, { "epoch": 0.7552341073467834, "grad_norm": 0.29831141233444214, "learning_rate": 1.4951117009692528e-05, "loss": 1.2716846466064453, "step": 2480 }, { "epoch": 0.7567567567567568, "grad_norm": 0.25659698247909546, "learning_rate": 1.477567810131127e-05, "loss": 1.249176025390625, "step": 2485 }, { "epoch": 0.7582794061667301, "grad_norm": 0.3631456792354584, "learning_rate": 1.4601095959754895e-05, "loss": 1.3151137351989746, "step": 2490 }, { "epoch": 0.7598020555767034, "grad_norm": 0.3281640410423279, "learning_rate": 1.4427374831412832e-05, "loss": 1.3102104187011718, "step": 2495 }, { "epoch": 0.7613247049866768, "grad_norm": 0.28020521998405457, "learning_rate": 1.4254518941731915e-05, "loss": 1.3195404052734374, "step": 2500 }, { "epoch": 0.7628473543966502, "grad_norm": 0.3130980134010315, "learning_rate": 1.4082532495113626e-05, "loss": 1.3403669357299806, "step": 2505 }, { "epoch": 0.7643700038066236, "grad_norm": 0.2850790023803711, "learning_rate": 1.3911419674811871e-05, "loss": 1.2424325942993164, "step": 2510 }, { "epoch": 0.7658926532165968, "grad_norm": 0.2870088219642639, "learning_rate": 1.3741184642831189e-05, "loss": 1.219760799407959, "step": 2515 }, { "epoch": 0.7674153026265702, "grad_norm": 0.24264056980609894, "learning_rate": 1.3571831539825525e-05, "loss": 1.273961353302002, "step": 2520 }, { "epoch": 0.7689379520365436, "grad_norm": 0.285765677690506, "learning_rate": 1.340336448499756e-05, "loss": 1.2167375564575196, "step": 2525 }, { "epoch": 0.770460601446517, "grad_norm": 0.330020934343338, "learning_rate": 1.3235787575998432e-05, "loss": 1.3481666564941406, "step": 2530 }, { "epoch": 0.7719832508564903, "grad_norm": 0.2715141177177429, "learning_rate": 1.3069104888828176e-05, "loss": 1.2984214782714845, "step": 2535 }, { "epoch": 0.7735059002664636, "grad_norm": 0.30174824595451355, "learning_rate": 1.2903320477736486e-05, "loss": 1.293179702758789, "step": 2540 }, { "epoch": 0.775028549676437, "grad_norm": 0.26991936564445496, "learning_rate": 1.2738438375124128e-05, "loss": 1.3253463745117187, "step": 2545 }, { "epoch": 0.7765511990864103, "grad_norm": 0.288265585899353, "learning_rate": 1.257446259144494e-05, "loss": 1.335153579711914, "step": 2550 }, { "epoch": 0.7780738484963837, "grad_norm": 0.29971587657928467, "learning_rate": 1.2411397115108164e-05, "loss": 1.235035514831543, "step": 2555 }, { "epoch": 0.7795964979063571, "grad_norm": 0.28376299142837524, "learning_rate": 1.2249245912381501e-05, "loss": 1.3113859176635743, "step": 2560 }, { "epoch": 0.7811191473163304, "grad_norm": 0.28060537576675415, "learning_rate": 1.2088012927294635e-05, "loss": 1.3378479957580567, "step": 2565 }, { "epoch": 0.7826417967263037, "grad_norm": 0.2617148756980896, "learning_rate": 1.1927702081543279e-05, "loss": 1.2342710494995117, "step": 2570 }, { "epoch": 0.7841644461362771, "grad_norm": 0.33613044023513794, "learning_rate": 1.1768317274393847e-05, "loss": 1.4422916412353515, "step": 2575 }, { "epoch": 0.7856870955462505, "grad_norm": 0.2812279760837555, "learning_rate": 1.1609862382588526e-05, "loss": 1.2711676597595214, "step": 2580 }, { "epoch": 0.7872097449562239, "grad_norm": 0.27217966318130493, "learning_rate": 1.145234126025102e-05, "loss": 1.2133594512939454, "step": 2585 }, { "epoch": 0.7887323943661971, "grad_norm": 0.2533910274505615, "learning_rate": 1.129575773879285e-05, "loss": 1.22855224609375, "step": 2590 }, { "epoch": 0.7902550437761705, "grad_norm": 0.2904157042503357, "learning_rate": 1.1140115626820086e-05, "loss": 1.3134843826293945, "step": 2595 }, { "epoch": 0.7917776931861439, "grad_norm": 0.32231220602989197, "learning_rate": 1.098541871004074e-05, "loss": 1.2486653327941895, "step": 2600 }, { "epoch": 0.7933003425961173, "grad_norm": 0.2749153673648834, "learning_rate": 1.0831670751172724e-05, "loss": 1.3006187438964845, "step": 2605 }, { "epoch": 0.7948229920060906, "grad_norm": 0.33127519488334656, "learning_rate": 1.0678875489852264e-05, "loss": 1.3799485206604003, "step": 2610 }, { "epoch": 0.7963456414160639, "grad_norm": 0.30147868394851685, "learning_rate": 1.0527036642542981e-05, "loss": 1.1725423812866211, "step": 2615 }, { "epoch": 0.7978682908260373, "grad_norm": 0.2505415678024292, "learning_rate": 1.0376157902445488e-05, "loss": 1.2644968032836914, "step": 2620 }, { "epoch": 0.7993909402360106, "grad_norm": 0.3706868290901184, "learning_rate": 1.0226242939407532e-05, "loss": 1.3067378997802734, "step": 2625 }, { "epoch": 0.800913589645984, "grad_norm": 0.3061469793319702, "learning_rate": 1.0077295399834814e-05, "loss": 1.3681838035583496, "step": 2630 }, { "epoch": 0.8024362390559574, "grad_norm": 0.27597686648368835, "learning_rate": 9.929318906602175e-06, "loss": 1.240310001373291, "step": 2635 }, { "epoch": 0.8039588884659307, "grad_norm": 0.24040164053440094, "learning_rate": 9.782317058965563e-06, "loss": 1.2518142700195312, "step": 2640 }, { "epoch": 0.805481537875904, "grad_norm": 0.2953890264034271, "learning_rate": 9.636293432474496e-06, "loss": 1.2341477394104003, "step": 2645 }, { "epoch": 0.8070041872858774, "grad_norm": 0.27737826108932495, "learning_rate": 9.491251578885024e-06, "loss": 1.227541160583496, "step": 2650 }, { "epoch": 0.8085268366958508, "grad_norm": 0.2581453323364258, "learning_rate": 9.347195026073369e-06, "loss": 1.3648658752441407, "step": 2655 }, { "epoch": 0.8100494861058242, "grad_norm": 0.30326032638549805, "learning_rate": 9.204127277950181e-06, "loss": 1.2833121299743653, "step": 2660 }, { "epoch": 0.8115721355157974, "grad_norm": 0.3057585656642914, "learning_rate": 9.062051814375194e-06, "loss": 1.2374212265014648, "step": 2665 }, { "epoch": 0.8130947849257708, "grad_norm": 0.33398017287254333, "learning_rate": 8.920972091072683e-06, "loss": 1.3803279876708985, "step": 2670 }, { "epoch": 0.8146174343357442, "grad_norm": 0.3035026788711548, "learning_rate": 8.780891539547353e-06, "loss": 1.270256805419922, "step": 2675 }, { "epoch": 0.8161400837457176, "grad_norm": 0.39098060131073, "learning_rate": 8.64181356700089e-06, "loss": 1.1794437408447265, "step": 2680 }, { "epoch": 0.8176627331556909, "grad_norm": 0.2681921422481537, "learning_rate": 8.503741556249123e-06, "loss": 1.263898754119873, "step": 2685 }, { "epoch": 0.8191853825656643, "grad_norm": 0.23838332295417786, "learning_rate": 8.366678865639688e-06, "loss": 1.2420608520507812, "step": 2690 }, { "epoch": 0.8207080319756376, "grad_norm": 0.3182808756828308, "learning_rate": 8.23062882897035e-06, "loss": 1.3469913482666016, "step": 2695 }, { "epoch": 0.822230681385611, "grad_norm": 0.36649560928344727, "learning_rate": 8.09559475540797e-06, "loss": 1.3983057975769042, "step": 2700 }, { "epoch": 0.8237533307955843, "grad_norm": 0.30097055435180664, "learning_rate": 7.961579929407943e-06, "loss": 1.264115333557129, "step": 2705 }, { "epoch": 0.8252759802055577, "grad_norm": 0.29677602648735046, "learning_rate": 7.828587610634342e-06, "loss": 1.3132007598876954, "step": 2710 }, { "epoch": 0.8267986296155311, "grad_norm": 0.29389283061027527, "learning_rate": 7.696621033880663e-06, "loss": 1.2865530014038087, "step": 2715 }, { "epoch": 0.8283212790255043, "grad_norm": 0.2582851052284241, "learning_rate": 7.565683408991092e-06, "loss": 1.314607810974121, "step": 2720 }, { "epoch": 0.8298439284354777, "grad_norm": 0.3167085647583008, "learning_rate": 7.435777920782444e-06, "loss": 1.2856945037841796, "step": 2725 }, { "epoch": 0.8313665778454511, "grad_norm": 0.25633320212364197, "learning_rate": 7.3069077289667335e-06, "loss": 1.2432159423828124, "step": 2730 }, { "epoch": 0.8328892272554245, "grad_norm": 0.37266212701797485, "learning_rate": 7.179075968074267e-06, "loss": 1.2832864761352538, "step": 2735 }, { "epoch": 0.8344118766653978, "grad_norm": 0.279058575630188, "learning_rate": 7.052285747377463e-06, "loss": 1.4640315055847168, "step": 2740 }, { "epoch": 0.8359345260753711, "grad_norm": 0.3403592109680176, "learning_rate": 6.926540150815169e-06, "loss": 1.2649270057678224, "step": 2745 }, { "epoch": 0.8374571754853445, "grad_norm": 0.259685754776001, "learning_rate": 6.80184223691766e-06, "loss": 1.283864974975586, "step": 2750 }, { "epoch": 0.8389798248953179, "grad_norm": 0.2971239984035492, "learning_rate": 6.678195038732294e-06, "loss": 1.2932071685791016, "step": 2755 }, { "epoch": 0.8405024743052912, "grad_norm": 0.31440332531929016, "learning_rate": 6.555601563749675e-06, "loss": 1.2181373596191407, "step": 2760 }, { "epoch": 0.8420251237152646, "grad_norm": 0.3210045397281647, "learning_rate": 6.43406479383053e-06, "loss": 1.2896718978881836, "step": 2765 }, { "epoch": 0.8435477731252379, "grad_norm": 0.2855500280857086, "learning_rate": 6.313587685133199e-06, "loss": 1.2174463272094727, "step": 2770 }, { "epoch": 0.8450704225352113, "grad_norm": 0.30069130659103394, "learning_rate": 6.194173168041689e-06, "loss": 1.357069206237793, "step": 2775 }, { "epoch": 0.8465930719451846, "grad_norm": 0.27656683325767517, "learning_rate": 6.075824147094433e-06, "loss": 1.2149724960327148, "step": 2780 }, { "epoch": 0.848115721355158, "grad_norm": 0.26682960987091064, "learning_rate": 5.958543500913627e-06, "loss": 1.3242107391357423, "step": 2785 }, { "epoch": 0.8496383707651314, "grad_norm": 0.2493298351764679, "learning_rate": 5.842334082135209e-06, "loss": 1.1792052268981934, "step": 2790 }, { "epoch": 0.8511610201751046, "grad_norm": 0.5055561661720276, "learning_rate": 5.727198717339511e-06, "loss": 1.2989743232727051, "step": 2795 }, { "epoch": 0.852683669585078, "grad_norm": 0.28792136907577515, "learning_rate": 5.613140206982442e-06, "loss": 1.320375633239746, "step": 2800 }, { "epoch": 0.8542063189950514, "grad_norm": 0.26852816343307495, "learning_rate": 5.5001613253274185e-06, "loss": 1.272132110595703, "step": 2805 }, { "epoch": 0.8557289684050248, "grad_norm": 0.32533007860183716, "learning_rate": 5.388264820377897e-06, "loss": 1.185745620727539, "step": 2810 }, { "epoch": 0.8572516178149981, "grad_norm": 0.28336215019226074, "learning_rate": 5.2774534138104904e-06, "loss": 1.3922807693481445, "step": 2815 }, { "epoch": 0.8587742672249714, "grad_norm": 0.33650097250938416, "learning_rate": 5.167729800908772e-06, "loss": 1.202780818939209, "step": 2820 }, { "epoch": 0.8602969166349448, "grad_norm": 0.29009220004081726, "learning_rate": 5.059096650497791e-06, "loss": 1.3895336151123048, "step": 2825 }, { "epoch": 0.8618195660449182, "grad_norm": 0.30722734332084656, "learning_rate": 4.951556604879048e-06, "loss": 1.2125556945800782, "step": 2830 }, { "epoch": 0.8633422154548915, "grad_norm": 0.3415650427341461, "learning_rate": 4.845112279766306e-06, "loss": 1.2632791519165039, "step": 2835 }, { "epoch": 0.8648648648648649, "grad_norm": 0.2834647297859192, "learning_rate": 4.73976626422194e-06, "loss": 1.22496337890625, "step": 2840 }, { "epoch": 0.8663875142748382, "grad_norm": 0.2926689386367798, "learning_rate": 4.63552112059395e-06, "loss": 1.339862060546875, "step": 2845 }, { "epoch": 0.8679101636848116, "grad_norm": 0.3083512485027313, "learning_rate": 4.532379384453688e-06, "loss": 1.2591231346130372, "step": 2850 }, { "epoch": 0.8694328130947849, "grad_norm": 0.310629278421402, "learning_rate": 4.430343564534123e-06, "loss": 1.333138656616211, "step": 2855 }, { "epoch": 0.8709554625047583, "grad_norm": 0.29025742411613464, "learning_rate": 4.32941614266883e-06, "loss": 1.3068903923034667, "step": 2860 }, { "epoch": 0.8724781119147317, "grad_norm": 0.3099145293235779, "learning_rate": 4.229599573731685e-06, "loss": 1.307637596130371, "step": 2865 }, { "epoch": 0.874000761324705, "grad_norm": 0.2442350834608078, "learning_rate": 4.130896285577074e-06, "loss": 1.2528931617736816, "step": 2870 }, { "epoch": 0.8755234107346783, "grad_norm": 0.2551295757293701, "learning_rate": 4.033308678980885e-06, "loss": 1.2361909866333007, "step": 2875 }, { "epoch": 0.8770460601446517, "grad_norm": 0.2731325030326843, "learning_rate": 3.93683912758212e-06, "loss": 1.2393997192382813, "step": 2880 }, { "epoch": 0.8785687095546251, "grad_norm": 0.35319268703460693, "learning_rate": 3.841489977825124e-06, "loss": 1.4020925521850587, "step": 2885 }, { "epoch": 0.8800913589645984, "grad_norm": 0.3271200954914093, "learning_rate": 3.747263548902552e-06, "loss": 1.27468843460083, "step": 2890 }, { "epoch": 0.8816140083745717, "grad_norm": 0.329540878534317, "learning_rate": 3.654162132698918e-06, "loss": 1.2445775985717773, "step": 2895 }, { "epoch": 0.8831366577845451, "grad_norm": 0.29114851355552673, "learning_rate": 3.5621879937348836e-06, "loss": 1.2536260604858398, "step": 2900 }, { "epoch": 0.8846593071945185, "grad_norm": 0.30914902687072754, "learning_rate": 3.4713433691121842e-06, "loss": 1.2808460235595702, "step": 2905 }, { "epoch": 0.8861819566044918, "grad_norm": 0.2827509939670563, "learning_rate": 3.3816304684591625e-06, "loss": 1.5088340759277343, "step": 2910 }, { "epoch": 0.8877046060144652, "grad_norm": 0.2379717081785202, "learning_rate": 3.2930514738770733e-06, "loss": 1.2922815322875976, "step": 2915 }, { "epoch": 0.8892272554244385, "grad_norm": 0.28089186549186707, "learning_rate": 3.205608539887006e-06, "loss": 1.2616600036621093, "step": 2920 }, { "epoch": 0.8907499048344119, "grad_norm": 0.3219889998435974, "learning_rate": 3.119303793377448e-06, "loss": 1.384989070892334, "step": 2925 }, { "epoch": 0.8922725542443852, "grad_norm": 0.3581083118915558, "learning_rate": 3.034139333552566e-06, "loss": 1.1470108032226562, "step": 2930 }, { "epoch": 0.8937952036543586, "grad_norm": 0.34060409665107727, "learning_rate": 2.950117231881183e-06, "loss": 1.302926254272461, "step": 2935 }, { "epoch": 0.895317853064332, "grad_norm": 0.30753132700920105, "learning_rate": 2.867239532046312e-06, "loss": 1.2407123565673828, "step": 2940 }, { "epoch": 0.8968405024743052, "grad_norm": 0.2871759533882141, "learning_rate": 2.7855082498955463e-06, "loss": 1.3781506538391113, "step": 2945 }, { "epoch": 0.8983631518842786, "grad_norm": 0.3360864520072937, "learning_rate": 2.7049253733919477e-06, "loss": 1.2938009262084962, "step": 2950 }, { "epoch": 0.899885801294252, "grad_norm": 0.2475963830947876, "learning_rate": 2.6254928625657204e-06, "loss": 1.1924603462219239, "step": 2955 }, { "epoch": 0.9014084507042254, "grad_norm": 0.32613176107406616, "learning_rate": 2.547212649466568e-06, "loss": 1.2345569610595704, "step": 2960 }, { "epoch": 0.9029311001141987, "grad_norm": 0.31767550110816956, "learning_rate": 2.4700866381166533e-06, "loss": 1.2061976432800292, "step": 2965 }, { "epoch": 0.904453749524172, "grad_norm": 0.30944669246673584, "learning_rate": 2.3941167044642944e-06, "loss": 1.7115396499633788, "step": 2970 }, { "epoch": 0.9059763989341454, "grad_norm": 0.25255152583122253, "learning_rate": 2.3193046963383702e-06, "loss": 1.2787339210510253, "step": 2975 }, { "epoch": 0.9074990483441188, "grad_norm": 0.3011283874511719, "learning_rate": 2.2456524334033335e-06, "loss": 1.2116592407226563, "step": 2980 }, { "epoch": 0.9090216977540921, "grad_norm": 0.3232909142971039, "learning_rate": 2.17316170711499e-06, "loss": 1.2717010498046875, "step": 2985 }, { "epoch": 0.9105443471640655, "grad_norm": 0.2687841057777405, "learning_rate": 2.1018342806768786e-06, "loss": 1.260712242126465, "step": 2990 }, { "epoch": 0.9120669965740388, "grad_norm": 0.35367563366889954, "learning_rate": 2.0316718889974106e-06, "loss": 1.2292938232421875, "step": 2995 }, { "epoch": 0.9135896459840122, "grad_norm": 0.34155890345573425, "learning_rate": 1.9626762386476925e-06, "loss": 1.2325470924377442, "step": 3000 }, { "epoch": 0.9151122953939855, "grad_norm": 0.29538673162460327, "learning_rate": 1.8948490078199764e-06, "loss": 1.1699304580688477, "step": 3005 }, { "epoch": 0.9166349448039589, "grad_norm": 0.2917913794517517, "learning_rate": 1.8281918462868642e-06, "loss": 1.3423567771911622, "step": 3010 }, { "epoch": 0.9181575942139323, "grad_norm": 0.35648229718208313, "learning_rate": 1.762706375361184e-06, "loss": 1.2389792442321776, "step": 3015 }, { "epoch": 0.9196802436239055, "grad_norm": 0.270595520734787, "learning_rate": 1.6983941878565224e-06, "loss": 1.2809268951416015, "step": 3020 }, { "epoch": 0.9212028930338789, "grad_norm": 0.33881306648254395, "learning_rate": 1.6352568480485276e-06, "loss": 1.2500165939331054, "step": 3025 }, { "epoch": 0.9227255424438523, "grad_norm": 0.2933228313922882, "learning_rate": 1.5732958916368335e-06, "loss": 1.2259369850158692, "step": 3030 }, { "epoch": 0.9242481918538257, "grad_norm": 0.22616733610630035, "learning_rate": 1.512512825707707e-06, "loss": 1.3729585647583007, "step": 3035 }, { "epoch": 0.925770841263799, "grad_norm": 0.3254220187664032, "learning_rate": 1.4529091286973995e-06, "loss": 1.4288372993469238, "step": 3040 }, { "epoch": 0.9272934906737723, "grad_norm": 0.3164454996585846, "learning_rate": 1.394486250356186e-06, "loss": 1.3193117141723634, "step": 3045 }, { "epoch": 0.9288161400837457, "grad_norm": 0.2773168087005615, "learning_rate": 1.3372456117130838e-06, "loss": 1.240021324157715, "step": 3050 }, { "epoch": 0.9303387894937191, "grad_norm": 0.329457551240921, "learning_rate": 1.281188605041328e-06, "loss": 1.2704096794128419, "step": 3055 }, { "epoch": 0.9318614389036924, "grad_norm": 0.24929700791835785, "learning_rate": 1.2263165938244669e-06, "loss": 1.3053118705749511, "step": 3060 }, { "epoch": 0.9333840883136658, "grad_norm": 0.34899425506591797, "learning_rate": 1.1726309127232271e-06, "loss": 1.416067123413086, "step": 3065 }, { "epoch": 0.9349067377236391, "grad_norm": 0.2927889823913574, "learning_rate": 1.1201328675430334e-06, "loss": 1.3098114013671875, "step": 3070 }, { "epoch": 0.9364293871336125, "grad_norm": 0.28060853481292725, "learning_rate": 1.0688237352022345e-06, "loss": 1.2341123580932618, "step": 3075 }, { "epoch": 0.9379520365435858, "grad_norm": 0.30672842264175415, "learning_rate": 1.018704763701095e-06, "loss": 1.2040374755859375, "step": 3080 }, { "epoch": 0.9394746859535592, "grad_norm": 0.30028146505355835, "learning_rate": 9.697771720913796e-07, "loss": 1.4019268035888672, "step": 3085 }, { "epoch": 0.9409973353635326, "grad_norm": 0.2995659410953522, "learning_rate": 9.220421504467281e-07, "loss": 1.2597471237182618, "step": 3090 }, { "epoch": 0.9425199847735058, "grad_norm": 0.33338701725006104, "learning_rate": 8.755008598337388e-07, "loss": 1.1991617202758789, "step": 3095 }, { "epoch": 0.9440426341834792, "grad_norm": 0.30137255787849426, "learning_rate": 8.301544322836751e-07, "loss": 1.192647933959961, "step": 3100 }, { "epoch": 0.9455652835934526, "grad_norm": 0.27424514293670654, "learning_rate": 7.86003970764948e-07, "loss": 1.2623826026916505, "step": 3105 }, { "epoch": 0.947087933003426, "grad_norm": 0.29633086919784546, "learning_rate": 7.4305054915631e-07, "loss": 1.3140138626098632, "step": 3110 }, { "epoch": 0.9486105824133994, "grad_norm": 0.31470903754234314, "learning_rate": 7.012952122207205e-07, "loss": 1.3920550346374512, "step": 3115 }, { "epoch": 0.9501332318233726, "grad_norm": 0.2626113295555115, "learning_rate": 6.607389755799332e-07, "loss": 1.1867645263671875, "step": 3120 }, { "epoch": 0.951655881233346, "grad_norm": 0.31831568479537964, "learning_rate": 6.213828256897869e-07, "loss": 1.192923355102539, "step": 3125 }, { "epoch": 0.9531785306433194, "grad_norm": 0.26954421401023865, "learning_rate": 5.832277198162095e-07, "loss": 1.379690933227539, "step": 3130 }, { "epoch": 0.9547011800532927, "grad_norm": 0.2589176297187805, "learning_rate": 5.462745860119745e-07, "loss": 1.2484930038452149, "step": 3135 }, { "epoch": 0.9562238294632661, "grad_norm": 0.26862773299217224, "learning_rate": 5.105243230940582e-07, "loss": 1.3305438995361327, "step": 3140 }, { "epoch": 0.9577464788732394, "grad_norm": 0.29442742466926575, "learning_rate": 4.7597780062184073e-07, "loss": 1.244651985168457, "step": 3145 }, { "epoch": 0.9592691282832128, "grad_norm": 0.31116199493408203, "learning_rate": 4.4263585887592276e-07, "loss": 1.2518585205078125, "step": 3150 }, { "epoch": 0.9607917776931861, "grad_norm": 0.2776123583316803, "learning_rate": 4.104993088376974e-07, "loss": 1.1839612007141114, "step": 3155 }, { "epoch": 0.9623144271031595, "grad_norm": 0.46439167857170105, "learning_rate": 3.7956893216961056e-07, "loss": 1.3894214630126953, "step": 3160 }, { "epoch": 0.9638370765131329, "grad_norm": 0.26693403720855713, "learning_rate": 3.4984548119618156e-07, "loss": 1.3106496810913086, "step": 3165 }, { "epoch": 0.9653597259231063, "grad_norm": 0.3090190589427948, "learning_rate": 3.213296788856568e-07, "loss": 1.2332918167114257, "step": 3170 }, { "epoch": 0.9668823753330795, "grad_norm": 0.31082960963249207, "learning_rate": 2.9402221883247926e-07, "loss": 1.240164852142334, "step": 3175 }, { "epoch": 0.9684050247430529, "grad_norm": 0.317879319190979, "learning_rate": 2.6792376524036877e-07, "loss": 1.4019231796264648, "step": 3180 }, { "epoch": 0.9699276741530263, "grad_norm": 0.36246249079704285, "learning_rate": 2.4303495290618485e-07, "loss": 1.2991714477539062, "step": 3185 }, { "epoch": 0.9714503235629997, "grad_norm": 0.27653399109840393, "learning_rate": 2.1935638720451123e-07, "loss": 1.2915735244750977, "step": 3190 }, { "epoch": 0.972972972972973, "grad_norm": 0.2911188304424286, "learning_rate": 1.9688864407288455e-07, "loss": 1.6792026519775392, "step": 3195 }, { "epoch": 0.9744956223829463, "grad_norm": 0.3008953034877777, "learning_rate": 1.7563226999782746e-07, "loss": 1.2785528182983399, "step": 3200 }, { "epoch": 0.9760182717929197, "grad_norm": 0.281717985868454, "learning_rate": 1.5558778200153168e-07, "loss": 1.28317289352417, "step": 3205 }, { "epoch": 0.977540921202893, "grad_norm": 0.35190004110336304, "learning_rate": 1.3675566762927917e-07, "loss": 1.3041015625, "step": 3210 }, { "epoch": 0.9790635706128664, "grad_norm": 0.2680605351924896, "learning_rate": 1.191363849376237e-07, "loss": 1.2247698783874512, "step": 3215 }, { "epoch": 0.9805862200228398, "grad_norm": 0.4276309907436371, "learning_rate": 1.0273036248318324e-07, "loss": 1.327359104156494, "step": 3220 }, { "epoch": 0.9821088694328131, "grad_norm": 0.2858787775039673, "learning_rate": 8.753799931228157e-08, "loss": 1.2513601303100585, "step": 3225 }, { "epoch": 0.9836315188427864, "grad_norm": 0.3357711732387543, "learning_rate": 7.355966495119494e-08, "loss": 1.2300790786743163, "step": 3230 }, { "epoch": 0.9851541682527598, "grad_norm": 0.25023162364959717, "learning_rate": 6.079569939719809e-08, "loss": 1.2293546676635743, "step": 3235 }, { "epoch": 0.9866768176627332, "grad_norm": 0.25940120220184326, "learning_rate": 4.924641311026546e-08, "loss": 1.251792049407959, "step": 3240 }, { "epoch": 0.9881994670727066, "grad_norm": 0.3243073523044586, "learning_rate": 3.8912087005532617e-08, "loss": 1.3878284454345704, "step": 3245 }, { "epoch": 0.9897221164826798, "grad_norm": 0.30321285128593445, "learning_rate": 2.9792972446479605e-08, "loss": 1.3268937110900878, "step": 3250 }, { "epoch": 0.9912447658926532, "grad_norm": 0.24456371366977692, "learning_rate": 2.188929123878025e-08, "loss": 1.39693603515625, "step": 3255 }, { "epoch": 0.9927674153026266, "grad_norm": 0.3350147604942322, "learning_rate": 1.5201235624945352e-08, "loss": 1.323414421081543, "step": 3260 }, { "epoch": 0.9942900647126, "grad_norm": 0.262965589761734, "learning_rate": 9.728968279620887e-09, "loss": 1.207941722869873, "step": 3265 }, { "epoch": 0.9958127141225733, "grad_norm": 0.24838848412036896, "learning_rate": 5.472622305646713e-09, "loss": 1.2328048706054688, "step": 3270 }, { "epoch": 0.9973353635325466, "grad_norm": 0.26840853691101074, "learning_rate": 2.4323012307980732e-09, "loss": 1.3296034812927247, "step": 3275 }, { "epoch": 0.99885801294252, "grad_norm": 0.30611881613731384, "learning_rate": 6.080790052986896e-10, "loss": 1.3041069030761718, "step": 3280 } ], "logging_steps": 5, "max_steps": 3284, "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": 3.599912117731328e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }