{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1896,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005276348766653476,
      "grad_norm": 3.469287395477295,
      "learning_rate": 4.736842105263159e-06,
      "loss": 2.102787208557129,
      "step": 10
    },
    {
      "epoch": 0.010552697533306952,
      "grad_norm": 0.3188445270061493,
      "learning_rate": 1e-05,
      "loss": 1.1864237785339355,
      "step": 20
    },
    {
      "epoch": 0.015829046299960427,
      "grad_norm": 0.14540567994117737,
      "learning_rate": 1.5263157894736842e-05,
      "loss": 0.6990499496459961,
      "step": 30
    },
    {
      "epoch": 0.021105395066613904,
      "grad_norm": 0.12763352692127228,
      "learning_rate": 2.0526315789473685e-05,
      "loss": 0.624098825454712,
      "step": 40
    },
    {
      "epoch": 0.026381743833267378,
      "grad_norm": 0.10226941853761673,
      "learning_rate": 2.578947368421053e-05,
      "loss": 0.5758195877075195,
      "step": 50
    },
    {
      "epoch": 0.031658092599920855,
      "grad_norm": 0.08121254295110703,
      "learning_rate": 3.105263157894737e-05,
      "loss": 0.5796430110931396,
      "step": 60
    },
    {
      "epoch": 0.03693444136657433,
      "grad_norm": 0.09573270380496979,
      "learning_rate": 3.6315789473684214e-05,
      "loss": 0.5682391166687012,
      "step": 70
    },
    {
      "epoch": 0.04221079013322781,
      "grad_norm": 0.10452360659837723,
      "learning_rate": 4.157894736842106e-05,
      "loss": 0.5779275894165039,
      "step": 80
    },
    {
      "epoch": 0.04748713889988128,
      "grad_norm": 0.09806756675243378,
      "learning_rate": 4.68421052631579e-05,
      "loss": 0.5625697135925293,
      "step": 90
    },
    {
      "epoch": 0.052763487666534756,
      "grad_norm": 0.08259418606758118,
      "learning_rate": 4.9999391443993295e-05,
      "loss": 0.5687247753143311,
      "step": 100
    },
    {
      "epoch": 0.05803983643318823,
      "grad_norm": 0.06800932437181473,
      "learning_rate": 4.99925455291635e-05,
      "loss": 0.5552473068237305,
      "step": 110
    },
    {
      "epoch": 0.06331618519984171,
      "grad_norm": 0.1364605873823166,
      "learning_rate": 4.997809509445635e-05,
      "loss": 0.5500987052917481,
      "step": 120
    },
    {
      "epoch": 0.06859253396649519,
      "grad_norm": 0.10689603537321091,
      "learning_rate": 4.995604453672762e-05,
      "loss": 0.5492524623870849,
      "step": 130
    },
    {
      "epoch": 0.07386888273314866,
      "grad_norm": 0.09057933837175369,
      "learning_rate": 4.992640056533407e-05,
      "loss": 0.5506837368011475,
      "step": 140
    },
    {
      "epoch": 0.07914523149980214,
      "grad_norm": 0.07902150601148605,
      "learning_rate": 4.9889172200092025e-05,
      "loss": 0.5636777877807617,
      "step": 150
    },
    {
      "epoch": 0.08442158026645562,
      "grad_norm": 0.0903806984424591,
      "learning_rate": 4.984437076853283e-05,
      "loss": 0.5428320884704589,
      "step": 160
    },
    {
      "epoch": 0.0896979290331091,
      "grad_norm": 0.08734392374753952,
      "learning_rate": 4.97920099024563e-05,
      "loss": 0.5517108917236329,
      "step": 170
    },
    {
      "epoch": 0.09497427779976256,
      "grad_norm": 0.06031898781657219,
      "learning_rate": 4.9732105533782835e-05,
      "loss": 0.5496417045593261,
      "step": 180
    },
    {
      "epoch": 0.10025062656641603,
      "grad_norm": 0.09410607069730759,
      "learning_rate": 4.966467588970592e-05,
      "loss": 0.5374730110168457,
      "step": 190
    },
    {
      "epoch": 0.10552697533306951,
      "grad_norm": 0.07396216690540314,
      "learning_rate": 4.958974148714601e-05,
      "loss": 0.5567604064941406,
      "step": 200
    },
    {
      "epoch": 0.11080332409972299,
      "grad_norm": 0.07383996248245239,
      "learning_rate": 4.9507325126507855e-05,
      "loss": 0.5542710304260254,
      "step": 210
    },
    {
      "epoch": 0.11607967286637647,
      "grad_norm": 0.05645842105150223,
      "learning_rate": 4.941745188474296e-05,
      "loss": 0.5580495834350586,
      "step": 220
    },
    {
      "epoch": 0.12135602163302994,
      "grad_norm": 0.14618708193302155,
      "learning_rate": 4.9320149107719446e-05,
      "loss": 0.5517265319824218,
      "step": 230
    },
    {
      "epoch": 0.12663237039968342,
      "grad_norm": 0.05914875119924545,
      "learning_rate": 4.92154464019014e-05,
      "loss": 0.5488170146942138,
      "step": 240
    },
    {
      "epoch": 0.1319087191663369,
      "grad_norm": 0.08373779058456421,
      "learning_rate": 4.9103375625340525e-05,
      "loss": 0.5490285873413085,
      "step": 250
    },
    {
      "epoch": 0.13718506793299037,
      "grad_norm": 0.07514908164739609,
      "learning_rate": 4.8983970877982625e-05,
      "loss": 0.549438190460205,
      "step": 260
    },
    {
      "epoch": 0.14246141669964385,
      "grad_norm": 0.060127828270196915,
      "learning_rate": 4.885726849129196e-05,
      "loss": 0.5483094692230225,
      "step": 270
    },
    {
      "epoch": 0.14773776546629733,
      "grad_norm": 0.07561356574296951,
      "learning_rate": 4.872330701719664e-05,
      "loss": 0.5502414226531982,
      "step": 280
    },
    {
      "epoch": 0.1530141142329508,
      "grad_norm": 0.06535837054252625,
      "learning_rate": 4.858212721635831e-05,
      "loss": 0.5522649765014649,
      "step": 290
    },
    {
      "epoch": 0.15829046299960428,
      "grad_norm": 0.07079112529754639,
      "learning_rate": 4.8433772045769914e-05,
      "loss": 0.5517202377319336,
      "step": 300
    },
    {
      "epoch": 0.16356681176625776,
      "grad_norm": 0.06277041882276535,
      "learning_rate": 4.827828664568508e-05,
      "loss": 0.5449066638946534,
      "step": 310
    },
    {
      "epoch": 0.16884316053291124,
      "grad_norm": 0.08924835920333862,
      "learning_rate": 4.811571832588318e-05,
      "loss": 0.5504207134246826,
      "step": 320
    },
    {
      "epoch": 0.1741195092995647,
      "grad_norm": 0.06925670057535172,
      "learning_rate": 4.79461165512744e-05,
      "loss": 0.5323378562927246,
      "step": 330
    },
    {
      "epoch": 0.1793958580662182,
      "grad_norm": 0.061691220849752426,
      "learning_rate": 4.77695329268489e-05,
      "loss": 0.54117431640625,
      "step": 340
    },
    {
      "epoch": 0.18467220683287167,
      "grad_norm": 0.05556100606918335,
      "learning_rate": 4.758602118197491e-05,
      "loss": 0.5371489524841309,
      "step": 350
    },
    {
      "epoch": 0.18994855559952512,
      "grad_norm": 0.08767969906330109,
      "learning_rate": 4.739563715405043e-05,
      "loss": 0.5342073440551758,
      "step": 360
    },
    {
      "epoch": 0.1952249043661786,
      "grad_norm": 0.161908358335495,
      "learning_rate": 4.71984387715135e-05,
      "loss": 0.536596155166626,
      "step": 370
    },
    {
      "epoch": 0.20050125313283207,
      "grad_norm": 0.06090890243649483,
      "learning_rate": 4.6994486036216155e-05,
      "loss": 0.552540636062622,
      "step": 380
    },
    {
      "epoch": 0.20577760189948555,
      "grad_norm": 0.08050890266895294,
      "learning_rate": 4.6783841005167704e-05,
      "loss": 0.5407903671264649,
      "step": 390
    },
    {
      "epoch": 0.21105395066613902,
      "grad_norm": 0.07033147662878036,
      "learning_rate": 4.6566567771652414e-05,
      "loss": 0.5586882114410401,
      "step": 400
    },
    {
      "epoch": 0.2163302994327925,
      "grad_norm": 0.08096320927143097,
      "learning_rate": 4.6342732445727826e-05,
      "loss": 0.531796646118164,
      "step": 410
    },
    {
      "epoch": 0.22160664819944598,
      "grad_norm": 0.057998862117528915,
      "learning_rate": 4.611240313410934e-05,
      "loss": 0.5306080341339111,
      "step": 420
    },
    {
      "epoch": 0.22688299696609945,
      "grad_norm": 0.058919817209243774,
      "learning_rate": 4.5875649919447263e-05,
      "loss": 0.5491554737091064,
      "step": 430
    },
    {
      "epoch": 0.23215934573275293,
      "grad_norm": 0.0594005212187767,
      "learning_rate": 4.563254483900265e-05,
      "loss": 0.5564260482788086,
      "step": 440
    },
    {
      "epoch": 0.2374356944994064,
      "grad_norm": 0.07155212759971619,
      "learning_rate": 4.5383161862728443e-05,
      "loss": 0.5302485466003418,
      "step": 450
    },
    {
      "epoch": 0.24271204326605988,
      "grad_norm": 0.055488333106040955,
      "learning_rate": 4.5127576870762486e-05,
      "loss": 0.5283378601074219,
      "step": 460
    },
    {
      "epoch": 0.24798839203271336,
      "grad_norm": 0.09895630925893784,
      "learning_rate": 4.486586763033941e-05,
      "loss": 0.5365806579589844,
      "step": 470
    },
    {
      "epoch": 0.25326474079936684,
      "grad_norm": 0.11615749448537827,
      "learning_rate": 4.459811377212822e-05,
      "loss": 0.5435856819152832,
      "step": 480
    },
    {
      "epoch": 0.2585410895660203,
      "grad_norm": 0.10437575727701187,
      "learning_rate": 4.4324396766003e-05,
      "loss": 0.5505838394165039,
      "step": 490
    },
    {
      "epoch": 0.2638174383326738,
      "grad_norm": 0.05472215637564659,
      "learning_rate": 4.4044799896253896e-05,
      "loss": 0.5423807144165039,
      "step": 500
    },
    {
      "epoch": 0.2638174383326738,
      "eval_loss": 0.5382053256034851,
      "eval_runtime": 41.1844,
      "eval_samples_per_second": 24.281,
      "eval_steps_per_second": 1.53,
      "step": 500
    },
    {
      "epoch": 0.26909378709932724,
      "grad_norm": 0.08025655895471573,
      "learning_rate": 4.3759408236246144e-05,
      "loss": 0.5385940551757813,
      "step": 510
    },
    {
      "epoch": 0.27437013586598075,
      "grad_norm": 0.053745437413454056,
      "learning_rate": 4.346830862253462e-05,
      "loss": 0.5528010368347168,
      "step": 520
    },
    {
      "epoch": 0.2796464846326342,
      "grad_norm": 0.053886476904153824,
      "learning_rate": 4.317158962844196e-05,
      "loss": 0.5308220863342286,
      "step": 530
    },
    {
      "epoch": 0.2849228333992877,
      "grad_norm": 0.06355541944503784,
      "learning_rate": 4.286934153710824e-05,
      "loss": 0.5384160995483398,
      "step": 540
    },
    {
      "epoch": 0.29019918216594115,
      "grad_norm": 0.08518887311220169,
      "learning_rate": 4.2561656314020344e-05,
      "loss": 0.5471887588500977,
      "step": 550
    },
    {
      "epoch": 0.29547553093259465,
      "grad_norm": 0.06389608979225159,
      "learning_rate": 4.224862757902953e-05,
      "loss": 0.5393133640289307,
      "step": 560
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.06710658967494965,
      "learning_rate": 4.193035057786557e-05,
      "loss": 0.5529976844787597,
      "step": 570
    },
    {
      "epoch": 0.3060282284659016,
      "grad_norm": 0.07694882899522781,
      "learning_rate": 4.160692215315615e-05,
      "loss": 0.5469122886657715,
      "step": 580
    },
    {
      "epoch": 0.31130457723255506,
      "grad_norm": 0.05047694966197014,
      "learning_rate": 4.127844071496044e-05,
      "loss": 0.5348247528076172,
      "step": 590
    },
    {
      "epoch": 0.31658092599920856,
      "grad_norm": 0.049118828028440475,
      "learning_rate": 4.094500621082575e-05,
      "loss": 0.5302189826965332,
      "step": 600
    },
    {
      "epoch": 0.321857274765862,
      "grad_norm": 0.06266016513109207,
      "learning_rate": 4.060672009537626e-05,
      "loss": 0.5458699226379394,
      "step": 610
    },
    {
      "epoch": 0.3271336235325155,
      "grad_norm": 0.05073148384690285,
      "learning_rate": 4.026368529944334e-05,
      "loss": 0.5527192115783691,
      "step": 620
    },
    {
      "epoch": 0.33240997229916897,
      "grad_norm": 0.06172562763094902,
      "learning_rate": 3.99160061987466e-05,
      "loss": 0.5287604331970215,
      "step": 630
    },
    {
      "epoch": 0.33768632106582247,
      "grad_norm": 0.07408280670642853,
      "learning_rate": 3.956378858213531e-05,
      "loss": 0.5468239784240723,
      "step": 640
    },
    {
      "epoch": 0.3429626698324759,
      "grad_norm": 0.061289943754673004,
      "learning_rate": 3.920713961939991e-05,
      "loss": 0.5272168636322021,
      "step": 650
    },
    {
      "epoch": 0.3482390185991294,
      "grad_norm": 0.04709945246577263,
      "learning_rate": 3.8846167828663246e-05,
      "loss": 0.5315431594848633,
      "step": 660
    },
    {
      "epoch": 0.3535153673657829,
      "grad_norm": 0.0591881163418293,
      "learning_rate": 3.848098304336166e-05,
      "loss": 0.5342112064361573,
      "step": 670
    },
    {
      "epoch": 0.3587917161324364,
      "grad_norm": 0.05472363159060478,
      "learning_rate": 3.811169637882573e-05,
      "loss": 0.5415730476379395,
      "step": 680
    },
    {
      "epoch": 0.3640680648990898,
      "grad_norm": 0.06319098174571991,
      "learning_rate": 3.773842019847108e-05,
      "loss": 0.5399191856384278,
      "step": 690
    },
    {
      "epoch": 0.36934441366574333,
      "grad_norm": 0.05035176873207092,
      "learning_rate": 3.736126807960939e-05,
      "loss": 0.5387386798858642,
      "step": 700
    },
    {
      "epoch": 0.3746207624323968,
      "grad_norm": 0.05229403078556061,
      "learning_rate": 3.6980354778890065e-05,
      "loss": 0.5388267517089844,
      "step": 710
    },
    {
      "epoch": 0.37989711119905023,
      "grad_norm": 0.05852624028921127,
      "learning_rate": 3.6595796197383005e-05,
      "loss": 0.5488125801086425,
      "step": 720
    },
    {
      "epoch": 0.38517345996570374,
      "grad_norm": 0.07255620509386063,
      "learning_rate": 3.6207709345313276e-05,
      "loss": 0.5299371719360352,
      "step": 730
    },
    {
      "epoch": 0.3904498087323572,
      "grad_norm": 0.08135049045085907,
      "learning_rate": 3.581621230645819e-05,
      "loss": 0.5405550479888916,
      "step": 740
    },
    {
      "epoch": 0.3957261574990107,
      "grad_norm": 0.0674319937825203,
      "learning_rate": 3.5421424202217785e-05,
      "loss": 0.5353422164916992,
      "step": 750
    },
    {
      "epoch": 0.40100250626566414,
      "grad_norm": 0.04660019651055336,
      "learning_rate": 3.502346515536957e-05,
      "loss": 0.5405518054962158,
      "step": 760
    },
    {
      "epoch": 0.40627885503231764,
      "grad_norm": 0.05615897849202156,
      "learning_rate": 3.462245625351858e-05,
      "loss": 0.5442234992980957,
      "step": 770
    },
    {
      "epoch": 0.4115552037989711,
      "grad_norm": 0.06428555399179459,
      "learning_rate": 3.4218519512253905e-05,
      "loss": 0.5265057563781739,
      "step": 780
    },
    {
      "epoch": 0.4168315525656246,
      "grad_norm": 0.07791760563850403,
      "learning_rate": 3.3811777838022764e-05,
      "loss": 0.5301748752593994,
      "step": 790
    },
    {
      "epoch": 0.42210790133227805,
      "grad_norm": 0.05744130536913872,
      "learning_rate": 3.3402354990733596e-05,
      "loss": 0.5446225166320801,
      "step": 800
    },
    {
      "epoch": 0.42738425009893155,
      "grad_norm": 0.05177663266658783,
      "learning_rate": 3.2990375546099475e-05,
      "loss": 0.5553675651550293,
      "step": 810
    },
    {
      "epoch": 0.432660598865585,
      "grad_norm": 0.05629579722881317,
      "learning_rate": 3.2575964857733226e-05,
      "loss": 0.5151557922363281,
      "step": 820
    },
    {
      "epoch": 0.4379369476322385,
      "grad_norm": 0.08680254220962524,
      "learning_rate": 3.215924901900589e-05,
      "loss": 0.5444235801696777,
      "step": 830
    },
    {
      "epoch": 0.44321329639889195,
      "grad_norm": 0.06883590668439865,
      "learning_rate": 3.174035482468016e-05,
      "loss": 0.521091365814209,
      "step": 840
    },
    {
      "epoch": 0.44848964516554546,
      "grad_norm": 0.05226761847734451,
      "learning_rate": 3.131940973233025e-05,
      "loss": 0.5454280376434326,
      "step": 850
    },
    {
      "epoch": 0.4537659939321989,
      "grad_norm": 0.0586739256978035,
      "learning_rate": 3.0896541823560286e-05,
      "loss": 0.5278735160827637,
      "step": 860
    },
    {
      "epoch": 0.4590423426988524,
      "grad_norm": 0.053351663053035736,
      "learning_rate": 3.0471879765032634e-05,
      "loss": 0.5304369449615478,
      "step": 870
    },
    {
      "epoch": 0.46431869146550586,
      "grad_norm": 0.11204632371664047,
      "learning_rate": 3.004555276931837e-05,
      "loss": 0.5195335388183594,
      "step": 880
    },
    {
      "epoch": 0.46959504023215937,
      "grad_norm": 0.05228094384074211,
      "learning_rate": 2.9617690555581533e-05,
      "loss": 0.5469107627868652,
      "step": 890
    },
    {
      "epoch": 0.4748713889988128,
      "grad_norm": 0.06409309059381485,
      "learning_rate": 2.9188423310109275e-05,
      "loss": 0.5274860382080078,
      "step": 900
    },
    {
      "epoch": 0.4801477377654663,
      "grad_norm": 0.054898325353860855,
      "learning_rate": 2.8757881646699897e-05,
      "loss": 0.5422440528869629,
      "step": 910
    },
    {
      "epoch": 0.48542408653211977,
      "grad_norm": 0.061062734574079514,
      "learning_rate": 2.8326196566920804e-05,
      "loss": 0.5353840827941895,
      "step": 920
    },
    {
      "epoch": 0.4907004352987733,
      "grad_norm": 0.0813838317990303,
      "learning_rate": 2.7893499420248414e-05,
      "loss": 0.542230224609375,
      "step": 930
    },
    {
      "epoch": 0.4959767840654267,
      "grad_norm": 0.09550558775663376,
      "learning_rate": 2.7459921864102306e-05,
      "loss": 0.5415503501892089,
      "step": 940
    },
    {
      "epoch": 0.5012531328320802,
      "grad_norm": 0.057921476662158966,
      "learning_rate": 2.702559582378556e-05,
      "loss": 0.536198616027832,
      "step": 950
    },
    {
      "epoch": 0.5065294815987337,
      "grad_norm": 0.058088093996047974,
      "learning_rate": 2.6590653452343706e-05,
      "loss": 0.5298252582550049,
      "step": 960
    },
    {
      "epoch": 0.5118058303653872,
      "grad_norm": 0.06566216796636581,
      "learning_rate": 2.6155227090354262e-05,
      "loss": 0.5259271621704101,
      "step": 970
    },
    {
      "epoch": 0.5170821791320406,
      "grad_norm": 0.07102049887180328,
      "learning_rate": 2.571944922565929e-05,
      "loss": 0.5335311889648438,
      "step": 980
    },
    {
      "epoch": 0.5223585278986941,
      "grad_norm": 0.06666040420532227,
      "learning_rate": 2.5283452453053124e-05,
      "loss": 0.5286438941955567,
      "step": 990
    },
    {
      "epoch": 0.5276348766653476,
      "grad_norm": 0.045802127569913864,
      "learning_rate": 2.4847369433937534e-05,
      "loss": 0.5388987064361572,
      "step": 1000
    },
    {
      "epoch": 0.5276348766653476,
      "eval_loss": 0.5275899767875671,
      "eval_runtime": 41.1227,
      "eval_samples_per_second": 24.317,
      "eval_steps_per_second": 1.532,
      "step": 1000
    },
    {
      "epoch": 0.5329112254320011,
      "grad_norm": 0.04900917783379555,
      "learning_rate": 2.441133285595665e-05,
      "loss": 0.5343585014343262,
      "step": 1010
    },
    {
      "epoch": 0.5381875741986545,
      "grad_norm": 0.0664224922657013,
      "learning_rate": 2.3975475392623874e-05,
      "loss": 0.5367018699645996,
      "step": 1020
    },
    {
      "epoch": 0.543463922965308,
      "grad_norm": 0.0700535774230957,
      "learning_rate": 2.3539929662953153e-05,
      "loss": 0.5292112350463867,
      "step": 1030
    },
    {
      "epoch": 0.5487402717319615,
      "grad_norm": 0.06185878813266754,
      "learning_rate": 2.310482819110673e-05,
      "loss": 0.5412003040313721,
      "step": 1040
    },
    {
      "epoch": 0.554016620498615,
      "grad_norm": 0.04651407152414322,
      "learning_rate": 2.2670303366071838e-05,
      "loss": 0.5272247314453125,
      "step": 1050
    },
    {
      "epoch": 0.5592929692652684,
      "grad_norm": 0.06412776559591293,
      "learning_rate": 2.223648740137854e-05,
      "loss": 0.522367000579834,
      "step": 1060
    },
    {
      "epoch": 0.5645693180319219,
      "grad_norm": 0.05411660671234131,
      "learning_rate": 2.1803512294870856e-05,
      "loss": 0.5501831531524658,
      "step": 1070
    },
    {
      "epoch": 0.5698456667985754,
      "grad_norm": 0.05362454429268837,
      "learning_rate": 2.1371509788543613e-05,
      "loss": 0.5526459217071533,
      "step": 1080
    },
    {
      "epoch": 0.5751220155652289,
      "grad_norm": 0.0568089559674263,
      "learning_rate": 2.09406113284571e-05,
      "loss": 0.5334463596343995,
      "step": 1090
    },
    {
      "epoch": 0.5803983643318823,
      "grad_norm": 0.05569031089544296,
      "learning_rate": 2.051094802474178e-05,
      "loss": 0.5427632331848145,
      "step": 1100
    },
    {
      "epoch": 0.5856747130985358,
      "grad_norm": 0.05014703422784805,
      "learning_rate": 2.0082650611705195e-05,
      "loss": 0.5325045585632324,
      "step": 1110
    },
    {
      "epoch": 0.5909510618651893,
      "grad_norm": 0.059223148971796036,
      "learning_rate": 1.9655849408053274e-05,
      "loss": 0.5336161613464355,
      "step": 1120
    },
    {
      "epoch": 0.5962274106318428,
      "grad_norm": 0.05466364696621895,
      "learning_rate": 1.923067427723801e-05,
      "loss": 0.5291933059692383,
      "step": 1130
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.05338220298290253,
      "learning_rate": 1.8807254587943766e-05,
      "loss": 0.5188746452331543,
      "step": 1140
    },
    {
      "epoch": 0.6067801081651497,
      "grad_norm": 0.05897964537143707,
      "learning_rate": 1.8385719174724013e-05,
      "loss": 0.5332316875457763,
      "step": 1150
    },
    {
      "epoch": 0.6120564569318032,
      "grad_norm": 0.04754431173205376,
      "learning_rate": 1.7966196298800698e-05,
      "loss": 0.5355251789093017,
      "step": 1160
    },
    {
      "epoch": 0.6173328056984567,
      "grad_norm": 0.06868181377649307,
      "learning_rate": 1.7548813609037952e-05,
      "loss": 0.5467939376831055,
      "step": 1170
    },
    {
      "epoch": 0.6226091544651101,
      "grad_norm": 0.1633625328540802,
      "learning_rate": 1.713369810310224e-05,
      "loss": 0.5276923179626465,
      "step": 1180
    },
    {
      "epoch": 0.6278855032317636,
      "grad_norm": 0.06620930880308151,
      "learning_rate": 1.672097608882052e-05,
      "loss": 0.5377791404724122,
      "step": 1190
    },
    {
      "epoch": 0.6331618519984171,
      "grad_norm": 0.07543770968914032,
      "learning_rate": 1.631077314574842e-05,
      "loss": 0.5569764137268066,
      "step": 1200
    },
    {
      "epoch": 0.6384382007650705,
      "grad_norm": 0.04613097757101059,
      "learning_rate": 1.590321408695994e-05,
      "loss": 0.5391340255737305,
      "step": 1210
    },
    {
      "epoch": 0.643714549531724,
      "grad_norm": 0.06107720360159874,
      "learning_rate": 1.5498422921070356e-05,
      "loss": 0.5338814735412598,
      "step": 1220
    },
    {
      "epoch": 0.6489908982983775,
      "grad_norm": 0.05765867978334427,
      "learning_rate": 1.509652281450399e-05,
      "loss": 0.5291410923004151,
      "step": 1230
    },
    {
      "epoch": 0.654267247065031,
      "grad_norm": 0.0857892706990242,
      "learning_rate": 1.4697636054018118e-05,
      "loss": 0.5374494552612304,
      "step": 1240
    },
    {
      "epoch": 0.6595435958316844,
      "grad_norm": 0.12835045158863068,
      "learning_rate": 1.4301884009494637e-05,
      "loss": 0.5271646499633789,
      "step": 1250
    },
    {
      "epoch": 0.6648199445983379,
      "grad_norm": 0.09761949628591537,
      "learning_rate": 1.3909387097010628e-05,
      "loss": 0.5366055488586425,
      "step": 1260
    },
    {
      "epoch": 0.6700962933649914,
      "grad_norm": 0.07090764492750168,
      "learning_rate": 1.352026474219921e-05,
      "loss": 0.5464098453521729,
      "step": 1270
    },
    {
      "epoch": 0.6753726421316449,
      "grad_norm": 0.0528789721429348,
      "learning_rate": 1.3134635343911669e-05,
      "loss": 0.5253230094909668,
      "step": 1280
    },
    {
      "epoch": 0.6806489908982983,
      "grad_norm": 0.0640147402882576,
      "learning_rate": 1.2752616238192127e-05,
      "loss": 0.5387689590454101,
      "step": 1290
    },
    {
      "epoch": 0.6859253396649518,
      "grad_norm": 0.07622914761304855,
      "learning_rate": 1.2374323662575483e-05,
      "loss": 0.5357081413269043,
      "step": 1300
    },
    {
      "epoch": 0.6912016884316053,
      "grad_norm": 0.0576150007545948,
      "learning_rate": 1.1999872720719622e-05,
      "loss": 0.5213495254516601,
      "step": 1310
    },
    {
      "epoch": 0.6964780371982588,
      "grad_norm": 0.05063485726714134,
      "learning_rate": 1.16293773473827e-05,
      "loss": 0.5175722122192383,
      "step": 1320
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.08525495231151581,
      "learning_rate": 1.1262950273756026e-05,
      "loss": 0.5198213577270507,
      "step": 1330
    },
    {
      "epoch": 0.7070307347315657,
      "grad_norm": 0.058000899851322174,
      "learning_rate": 1.0900702993163123e-05,
      "loss": 0.5448369026184082,
      "step": 1340
    },
    {
      "epoch": 0.7123070834982193,
      "grad_norm": 0.0543798953294754,
      "learning_rate": 1.0542745727135584e-05,
      "loss": 0.5294485092163086,
      "step": 1350
    },
    {
      "epoch": 0.7175834322648728,
      "grad_norm": 0.0631227120757103,
      "learning_rate": 1.0189187391875677e-05,
      "loss": 0.5257573127746582,
      "step": 1360
    },
    {
      "epoch": 0.7228597810315261,
      "grad_norm": 0.05980793386697769,
      "learning_rate": 9.840135565116345e-06,
      "loss": 0.530888843536377,
      "step": 1370
    },
    {
      "epoch": 0.7281361297981797,
      "grad_norm": 0.05870359018445015,
      "learning_rate": 9.495696453388334e-06,
      "loss": 0.5263881206512451,
      "step": 1380
    },
    {
      "epoch": 0.7334124785648332,
      "grad_norm": 0.13112448155879974,
      "learning_rate": 9.155974859704527e-06,
      "loss": 0.5317092895507812,
      "step": 1390
    },
    {
      "epoch": 0.7386888273314867,
      "grad_norm": 0.0716542899608612,
      "learning_rate": 8.821074151671446e-06,
      "loss": 0.5289976596832275,
      "step": 1400
    },
    {
      "epoch": 0.7439651760981401,
      "grad_norm": 0.04715152084827423,
      "learning_rate": 8.491096230037392e-06,
      "loss": 0.5213170051574707,
      "step": 1410
    },
    {
      "epoch": 0.7492415248647936,
      "grad_norm": 0.08359207212924957,
      "learning_rate": 8.166141497686932e-06,
      "loss": 0.5287568092346191,
      "step": 1420
    },
    {
      "epoch": 0.7545178736314471,
      "grad_norm": 0.06184040755033493,
      "learning_rate": 7.8463088290912e-06,
      "loss": 0.5355735778808594,
      "step": 1430
    },
    {
      "epoch": 0.7597942223981005,
      "grad_norm": 0.04950764775276184,
      "learning_rate": 7.531695540223202e-06,
      "loss": 0.5518941879272461,
      "step": 1440
    },
    {
      "epoch": 0.765070571164754,
      "grad_norm": 0.060244061052799225,
      "learning_rate": 7.222397358947297e-06,
      "loss": 0.5383299827575684,
      "step": 1450
    },
    {
      "epoch": 0.7703469199314075,
      "grad_norm": 0.08535024523735046,
      "learning_rate": 6.918508395892001e-06,
      "loss": 0.5432676315307617,
      "step": 1460
    },
    {
      "epoch": 0.775623268698061,
      "grad_norm": 0.04657880216836929,
      "learning_rate": 6.620121115814734e-06,
      "loss": 0.5283122062683105,
      "step": 1470
    },
    {
      "epoch": 0.7808996174647144,
      "grad_norm": 0.05936064198613167,
      "learning_rate": 6.327326309467488e-06,
      "loss": 0.5149470329284668,
      "step": 1480
    },
    {
      "epoch": 0.7861759662313679,
      "grad_norm": 0.04747183620929718,
      "learning_rate": 6.040213065971748e-06,
      "loss": 0.5176490783691406,
      "step": 1490
    },
    {
      "epoch": 0.7914523149980214,
      "grad_norm": 0.05526433140039444,
      "learning_rate": 5.7588687457112075e-06,
      "loss": 0.5165718078613282,
      "step": 1500
    },
    {
      "epoch": 0.7914523149980214,
      "eval_loss": 0.5238120555877686,
      "eval_runtime": 41.2166,
      "eval_samples_per_second": 24.262,
      "eval_steps_per_second": 1.529,
      "step": 1500
    },
    {
      "epoch": 0.7967286637646749,
      "grad_norm": 0.05318671837449074,
      "learning_rate": 5.483378953750529e-06,
      "loss": 0.5067502975463867,
      "step": 1510
    },
    {
      "epoch": 0.8020050125313283,
      "grad_norm": 0.07793046534061432,
      "learning_rate": 5.2138275137881245e-06,
      "loss": 0.5287394523620605,
      "step": 1520
    },
    {
      "epoch": 0.8072813612979818,
      "grad_norm": 0.04804445430636406,
      "learning_rate": 4.9502964426509925e-06,
      "loss": 0.5188559055328369,
      "step": 1530
    },
    {
      "epoch": 0.8125577100646353,
      "grad_norm": 0.06349748373031616,
      "learning_rate": 4.692865925339357e-06,
      "loss": 0.5132348537445068,
      "step": 1540
    },
    {
      "epoch": 0.8178340588312888,
      "grad_norm": 0.04600077122449875,
      "learning_rate": 4.441614290628648e-06,
      "loss": 0.5240598678588867,
      "step": 1550
    },
    {
      "epoch": 0.8231104075979422,
      "grad_norm": 0.06124558672308922,
      "learning_rate": 4.196617987236248e-06,
      "loss": 0.5394316196441651,
      "step": 1560
    },
    {
      "epoch": 0.8283867563645957,
      "grad_norm": 0.04623348265886307,
      "learning_rate": 3.957951560560408e-06,
      "loss": 0.5506006240844726,
      "step": 1570
    },
    {
      "epoch": 0.8336631051312492,
      "grad_norm": 0.04951977729797363,
      "learning_rate": 3.725687629998098e-06,
      "loss": 0.536842155456543,
      "step": 1580
    },
    {
      "epoch": 0.8389394538979027,
      "grad_norm": 0.09644008427858353,
      "learning_rate": 3.499896866849084e-06,
      "loss": 0.5277879238128662,
      "step": 1590
    },
    {
      "epoch": 0.8442158026645561,
      "grad_norm": 0.05169585719704628,
      "learning_rate": 3.2806479728126226e-06,
      "loss": 0.5180648326873779,
      "step": 1600
    },
    {
      "epoch": 0.8494921514312096,
      "grad_norm": 0.0778173953294754,
      "learning_rate": 3.0680076590834828e-06,
      "loss": 0.5346675395965577,
      "step": 1610
    },
    {
      "epoch": 0.8547685001978631,
      "grad_norm": 0.07879842072725296,
      "learning_rate": 2.8620406260536554e-06,
      "loss": 0.5449596405029297,
      "step": 1620
    },
    {
      "epoch": 0.8600448489645166,
      "grad_norm": 0.05487416312098503,
      "learning_rate": 2.662809543625852e-06,
      "loss": 0.5100914001464844,
      "step": 1630
    },
    {
      "epoch": 0.86532119773117,
      "grad_norm": 0.04877998307347298,
      "learning_rate": 2.4703750321448284e-06,
      "loss": 0.5349862575531006,
      "step": 1640
    },
    {
      "epoch": 0.8705975464978235,
      "grad_norm": 0.053301483392715454,
      "learning_rate": 2.2847956439523616e-06,
      "loss": 0.5335394859313964,
      "step": 1650
    },
    {
      "epoch": 0.875873895264477,
      "grad_norm": 0.05360141023993492,
      "learning_rate": 2.1061278455714374e-06,
      "loss": 0.5380747795104981,
      "step": 1660
    },
    {
      "epoch": 0.8811502440311304,
      "grad_norm": 0.07707633078098297,
      "learning_rate": 1.934426000525064e-06,
      "loss": 0.5185709476470948,
      "step": 1670
    },
    {
      "epoch": 0.8864265927977839,
      "grad_norm": 0.07253004610538483,
      "learning_rate": 1.7697423527950396e-06,
      "loss": 0.5232056617736817,
      "step": 1680
    },
    {
      "epoch": 0.8917029415644374,
      "grad_norm": 0.04856908321380615,
      "learning_rate": 1.6121270109255848e-06,
      "loss": 0.5326048851013183,
      "step": 1690
    },
    {
      "epoch": 0.8969792903310909,
      "grad_norm": 0.06653986126184464,
      "learning_rate": 1.4616279327767157e-06,
      "loss": 0.5569762706756591,
      "step": 1700
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.048405617475509644,
      "learning_rate": 1.318290910932074e-06,
      "loss": 0.5244148254394532,
      "step": 1710
    },
    {
      "epoch": 0.9075319878643978,
      "grad_norm": 0.0537782683968544,
      "learning_rate": 1.1821595587655055e-06,
      "loss": 0.5292432308197021,
      "step": 1720
    },
    {
      "epoch": 0.9128083366310513,
      "grad_norm": 0.0459461435675621,
      "learning_rate": 1.0532752971707887e-06,
      "loss": 0.5301027297973633,
      "step": 1730
    },
    {
      "epoch": 0.9180846853977048,
      "grad_norm": 0.05908653512597084,
      "learning_rate": 9.316773419584202e-07,
      "loss": 0.5406010150909424,
      "step": 1740
    },
    {
      "epoch": 0.9233610341643582,
      "grad_norm": 0.05751330778002739,
      "learning_rate": 8.174026919233468e-07,
      "loss": 0.5126451015472412,
      "step": 1750
    },
    {
      "epoch": 0.9286373829310117,
      "grad_norm": 0.05343455448746681,
      "learning_rate": 7.10486117587314e-07,
      "loss": 0.5294478416442872,
      "step": 1760
    },
    {
      "epoch": 0.9339137316976652,
      "grad_norm": 0.08664143830537796,
      "learning_rate": 6.109601506191665e-07,
      "loss": 0.5246481418609619,
      "step": 1770
    },
    {
      "epoch": 0.9391900804643187,
      "grad_norm": 0.05929280072450638,
      "learning_rate": 5.188550739363917e-07,
      "loss": 0.538542652130127,
      "step": 1780
    },
    {
      "epoch": 0.9444664292309721,
      "grad_norm": 0.08840236067771912,
      "learning_rate": 4.3419891249089904e-07,
      "loss": 0.52940993309021,
      "step": 1790
    },
    {
      "epoch": 0.9497427779976256,
      "grad_norm": 0.05445009842514992,
      "learning_rate": 3.5701742474180957e-07,
      "loss": 0.5254480361938476,
      "step": 1800
    },
    {
      "epoch": 0.9550191267642791,
      "grad_norm": 0.04973360151052475,
      "learning_rate": 2.873340948179065e-07,
      "loss": 0.5389321327209473,
      "step": 1810
    },
    {
      "epoch": 0.9602954755309326,
      "grad_norm": 0.07387353479862213,
      "learning_rate": 2.251701253720706e-07,
      "loss": 0.5427006721496582,
      "step": 1820
    },
    {
      "epoch": 0.965571824297586,
      "grad_norm": 0.06027231737971306,
      "learning_rate": 1.7054443112992924e-07,
      "loss": 0.5303158760070801,
      "step": 1830
    },
    {
      "epoch": 0.9708481730642395,
      "grad_norm": 0.08982621133327484,
      "learning_rate": 1.23473633134627e-07,
      "loss": 0.5218575954437256,
      "step": 1840
    },
    {
      "epoch": 0.976124521830893,
      "grad_norm": 0.0555257573723793,
      "learning_rate": 8.397205368953776e-08,
      "loss": 0.5326569557189942,
      "step": 1850
    },
    {
      "epoch": 0.9814008705975465,
      "grad_norm": 0.046967435628175735,
      "learning_rate": 5.205171200036996e-08,
      "loss": 0.5277679920196533,
      "step": 1860
    },
    {
      "epoch": 0.9866772193641999,
      "grad_norm": 0.06941176950931549,
      "learning_rate": 2.7722320518092094e-08,
      "loss": 0.542722511291504,
      "step": 1870
    },
    {
      "epoch": 0.9919535681308534,
      "grad_norm": 0.06871765851974487,
      "learning_rate": 1.0991281983688263e-08,
      "loss": 0.53226637840271,
      "step": 1880
    },
    {
      "epoch": 0.997229916897507,
      "grad_norm": 0.05399344116449356,
      "learning_rate": 1.8636871757238274e-09,
      "loss": 0.5319315433502197,
      "step": 1890
    },
    {
      "epoch": 1.0,
      "step": 1896,
      "total_flos": 9.997813601634615e+18,
      "train_loss": 0.5505562032325358,
      "train_runtime": 14451.8624,
      "train_samples_per_second": 8.393,
      "train_steps_per_second": 0.131
    }
  ],
  "logging_steps": 10,
  "max_steps": 1896,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.997813601634615e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}