{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.035045057931626,
  "eval_steps": 400,
  "global_step": 17600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014304105278214848,
      "grad_norm": 4.381897472506865,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 4.333,
      "step": 50
    },
    {
      "epoch": 0.028608210556429696,
      "grad_norm": 5.747764242911294,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 3.5701,
      "step": 100
    },
    {
      "epoch": 0.04291231583464454,
      "grad_norm": 5.963549459328992,
      "learning_rate": 5e-06,
      "loss": 2.7847,
      "step": 150
    },
    {
      "epoch": 0.05721642111285939,
      "grad_norm": 11.127446150543912,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.5742,
      "step": 200
    },
    {
      "epoch": 0.07152052639107424,
      "grad_norm": 3.9613017534642814,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.4695,
      "step": 250
    },
    {
      "epoch": 0.08582463166928908,
      "grad_norm": 3.641857826346019,
      "learning_rate": 1e-05,
      "loss": 2.3974,
      "step": 300
    },
    {
      "epoch": 0.10012873694750393,
      "grad_norm": 5.994311420384253,
      "learning_rate": 9.999953760295448e-06,
      "loss": 2.2789,
      "step": 350
    },
    {
      "epoch": 0.11443284222571878,
      "grad_norm": 2.3599387781179795,
      "learning_rate": 9.999815042132062e-06,
      "loss": 2.2133,
      "step": 400
    },
    {
      "epoch": 0.11443284222571878,
      "eval_loss": 2.138951301574707,
      "eval_runtime": 13.19,
      "eval_samples_per_second": 75.815,
      "eval_steps_per_second": 2.426,
      "step": 400
    },
    {
      "epoch": 0.12873694750393364,
      "grad_norm": 5.356575743204386,
      "learning_rate": 9.999583848360633e-06,
      "loss": 2.1596,
      "step": 450
    },
    {
      "epoch": 0.1430410527821485,
      "grad_norm": 3.842440081655673,
      "learning_rate": 9.999260183732424e-06,
      "loss": 2.1221,
      "step": 500
    },
    {
      "epoch": 0.1573451580603633,
      "grad_norm": 2.3704079011821495,
      "learning_rate": 9.998844054899058e-06,
      "loss": 2.0815,
      "step": 550
    },
    {
      "epoch": 0.17164926333857816,
      "grad_norm": 1.8440320920841848,
      "learning_rate": 9.998335470412393e-06,
      "loss": 2.0687,
      "step": 600
    },
    {
      "epoch": 0.185953368616793,
      "grad_norm": 6.305609267274029,
      "learning_rate": 9.997734440724333e-06,
      "loss": 2.0513,
      "step": 650
    },
    {
      "epoch": 0.20025747389500786,
      "grad_norm": 2.1140529899847054,
      "learning_rate": 9.997040978186633e-06,
      "loss": 2.0241,
      "step": 700
    },
    {
      "epoch": 0.21456157917322272,
      "grad_norm": 3.884579646553787,
      "learning_rate": 9.996255097050624e-06,
      "loss": 2.0084,
      "step": 750
    },
    {
      "epoch": 0.22886568445143757,
      "grad_norm": 3.1240890876667695,
      "learning_rate": 9.995376813466934e-06,
      "loss": 1.9989,
      "step": 800
    },
    {
      "epoch": 0.22886568445143757,
      "eval_loss": 1.9693105220794678,
      "eval_runtime": 13.1024,
      "eval_samples_per_second": 76.322,
      "eval_steps_per_second": 2.442,
      "step": 800
    },
    {
      "epoch": 0.24316978972965242,
      "grad_norm": 2.3200436251519827,
      "learning_rate": 9.994406145485151e-06,
      "loss": 1.9917,
      "step": 850
    },
    {
      "epoch": 0.25747389500786727,
      "grad_norm": 2.6496743450852738,
      "learning_rate": 9.993343113053454e-06,
      "loss": 1.9746,
      "step": 900
    },
    {
      "epoch": 0.2717780002860821,
      "grad_norm": 2.536170754608615,
      "learning_rate": 9.992187738018203e-06,
      "loss": 1.9737,
      "step": 950
    },
    {
      "epoch": 0.286082105564297,
      "grad_norm": 1.6713049324071942,
      "learning_rate": 9.99094004412348e-06,
      "loss": 1.9602,
      "step": 1000
    },
    {
      "epoch": 0.3003862108425118,
      "grad_norm": 2.9333959535896064,
      "learning_rate": 9.989600057010625e-06,
      "loss": 1.9535,
      "step": 1050
    },
    {
      "epoch": 0.3146903161207266,
      "grad_norm": 1.8676266291905814,
      "learning_rate": 9.988167804217682e-06,
      "loss": 1.9416,
      "step": 1100
    },
    {
      "epoch": 0.3289944213989415,
      "grad_norm": 1.2680641471071183,
      "learning_rate": 9.986643315178848e-06,
      "loss": 1.9307,
      "step": 1150
    },
    {
      "epoch": 0.3432985266771563,
      "grad_norm": 2.9062506982476073,
      "learning_rate": 9.98502662122387e-06,
      "loss": 1.9378,
      "step": 1200
    },
    {
      "epoch": 0.3432985266771563,
      "eval_loss": 1.9051591157913208,
      "eval_runtime": 13.1019,
      "eval_samples_per_second": 76.325,
      "eval_steps_per_second": 2.442,
      "step": 1200
    },
    {
      "epoch": 0.3576026319553712,
      "grad_norm": 2.156043900815843,
      "learning_rate": 9.983317755577392e-06,
      "loss": 1.9187,
      "step": 1250
    },
    {
      "epoch": 0.371906737233586,
      "grad_norm": 2.8852879306242203,
      "learning_rate": 9.981516753358274e-06,
      "loss": 1.9251,
      "step": 1300
    },
    {
      "epoch": 0.3862108425118009,
      "grad_norm": 1.6778445737708942,
      "learning_rate": 9.979623651578881e-06,
      "loss": 1.9058,
      "step": 1350
    },
    {
      "epoch": 0.40051494779001573,
      "grad_norm": 1.4368646478597216,
      "learning_rate": 9.977638489144308e-06,
      "loss": 1.9119,
      "step": 1400
    },
    {
      "epoch": 0.4148190530682306,
      "grad_norm": 1.466116857478951,
      "learning_rate": 9.975561306851585e-06,
      "loss": 1.9036,
      "step": 1450
    },
    {
      "epoch": 0.42912315834644543,
      "grad_norm": 1.4471173596729103,
      "learning_rate": 9.973392147388847e-06,
      "loss": 1.9058,
      "step": 1500
    },
    {
      "epoch": 0.4434272636246603,
      "grad_norm": 1.015831804058714,
      "learning_rate": 9.971131055334445e-06,
      "loss": 1.8931,
      "step": 1550
    },
    {
      "epoch": 0.45773136890287514,
      "grad_norm": 1.6593036538850372,
      "learning_rate": 9.968778077156035e-06,
      "loss": 1.8928,
      "step": 1600
    },
    {
      "epoch": 0.45773136890287514,
      "eval_loss": 1.8654637336730957,
      "eval_runtime": 13.1276,
      "eval_samples_per_second": 76.176,
      "eval_steps_per_second": 2.438,
      "step": 1600
    },
    {
      "epoch": 0.47203547418109,
      "grad_norm": 1.2836506785865125,
      "learning_rate": 9.966333261209625e-06,
      "loss": 1.8886,
      "step": 1650
    },
    {
      "epoch": 0.48633957945930484,
      "grad_norm": 1.2135189666496888,
      "learning_rate": 9.96379665773858e-06,
      "loss": 1.8866,
      "step": 1700
    },
    {
      "epoch": 0.5006436847375196,
      "grad_norm": 1.274525834510866,
      "learning_rate": 9.961168318872583e-06,
      "loss": 1.8786,
      "step": 1750
    },
    {
      "epoch": 0.5149477900157345,
      "grad_norm": 1.3030666538156304,
      "learning_rate": 9.958448298626576e-06,
      "loss": 1.8803,
      "step": 1800
    },
    {
      "epoch": 0.5292518952939493,
      "grad_norm": 1.9481826276041598,
      "learning_rate": 9.95563665289964e-06,
      "loss": 1.8661,
      "step": 1850
    },
    {
      "epoch": 0.5435560005721642,
      "grad_norm": 1.184161907280642,
      "learning_rate": 9.952733439473847e-06,
      "loss": 1.8717,
      "step": 1900
    },
    {
      "epoch": 0.557860105850379,
      "grad_norm": 2.035585736840807,
      "learning_rate": 9.94973871801308e-06,
      "loss": 1.8696,
      "step": 1950
    },
    {
      "epoch": 0.572164211128594,
      "grad_norm": 1.0097164190087617,
      "learning_rate": 9.946652550061798e-06,
      "loss": 1.8525,
      "step": 2000
    },
    {
      "epoch": 0.572164211128594,
      "eval_loss": 1.8354862928390503,
      "eval_runtime": 13.0943,
      "eval_samples_per_second": 76.369,
      "eval_steps_per_second": 2.444,
      "step": 2000
    },
    {
      "epoch": 0.5864683164068087,
      "grad_norm": 2.0497282273050517,
      "learning_rate": 9.943474999043775e-06,
      "loss": 1.8572,
      "step": 2050
    },
    {
      "epoch": 0.6007724216850236,
      "grad_norm": 1.4485387654596187,
      "learning_rate": 9.9402061302608e-06,
      "loss": 1.8557,
      "step": 2100
    },
    {
      "epoch": 0.6150765269632384,
      "grad_norm": 1.4726888297829959,
      "learning_rate": 9.93684601089133e-06,
      "loss": 1.8476,
      "step": 2150
    },
    {
      "epoch": 0.6293806322414532,
      "grad_norm": 1.2546088847317722,
      "learning_rate": 9.933394709989109e-06,
      "loss": 1.8535,
      "step": 2200
    },
    {
      "epoch": 0.6436847375196681,
      "grad_norm": 1.442306090060256,
      "learning_rate": 9.92985229848175e-06,
      "loss": 1.8383,
      "step": 2250
    },
    {
      "epoch": 0.657988842797883,
      "grad_norm": 1.3986536095496256,
      "learning_rate": 9.926218849169284e-06,
      "loss": 1.8468,
      "step": 2300
    },
    {
      "epoch": 0.6722929480760979,
      "grad_norm": 1.3568137487712886,
      "learning_rate": 9.922494436722653e-06,
      "loss": 1.8376,
      "step": 2350
    },
    {
      "epoch": 0.6865970533543126,
      "grad_norm": 1.2996414194536055,
      "learning_rate": 9.91867913768218e-06,
      "loss": 1.8272,
      "step": 2400
    },
    {
      "epoch": 0.6865970533543126,
      "eval_loss": 1.8150951862335205,
      "eval_runtime": 13.1089,
      "eval_samples_per_second": 76.284,
      "eval_steps_per_second": 2.441,
      "step": 2400
    },
    {
      "epoch": 0.7009011586325276,
      "grad_norm": 1.2871997517148228,
      "learning_rate": 9.914773030456001e-06,
      "loss": 1.8317,
      "step": 2450
    },
    {
      "epoch": 0.7152052639107424,
      "grad_norm": 1.200976481369304,
      "learning_rate": 9.910776195318448e-06,
      "loss": 1.8392,
      "step": 2500
    },
    {
      "epoch": 0.7295093691889573,
      "grad_norm": 1.4537260955148985,
      "learning_rate": 9.906688714408396e-06,
      "loss": 1.8414,
      "step": 2550
    },
    {
      "epoch": 0.743813474467172,
      "grad_norm": 1.3619012866591573,
      "learning_rate": 9.902510671727583e-06,
      "loss": 1.8243,
      "step": 2600
    },
    {
      "epoch": 0.758117579745387,
      "grad_norm": 1.468758050868889,
      "learning_rate": 9.898242153138882e-06,
      "loss": 1.8208,
      "step": 2650
    },
    {
      "epoch": 0.7724216850236018,
      "grad_norm": 1.5941916432437884,
      "learning_rate": 9.89388324636453e-06,
      "loss": 1.8274,
      "step": 2700
    },
    {
      "epoch": 0.7867257903018167,
      "grad_norm": 1.4358813545146656,
      "learning_rate": 9.889434040984333e-06,
      "loss": 1.815,
      "step": 2750
    },
    {
      "epoch": 0.8010298955800315,
      "grad_norm": 1.0044194890872669,
      "learning_rate": 9.88489462843382e-06,
      "loss": 1.8204,
      "step": 2800
    },
    {
      "epoch": 0.8010298955800315,
      "eval_loss": 1.7972140312194824,
      "eval_runtime": 13.1016,
      "eval_samples_per_second": 76.326,
      "eval_steps_per_second": 2.442,
      "step": 2800
    },
    {
      "epoch": 0.8153340008582464,
      "grad_norm": 1.0780986139085367,
      "learning_rate": 9.880265102002369e-06,
      "loss": 1.8027,
      "step": 2850
    },
    {
      "epoch": 0.8296381061364612,
      "grad_norm": 0.7267417717678716,
      "learning_rate": 9.875545556831283e-06,
      "loss": 1.8156,
      "step": 2900
    },
    {
      "epoch": 0.843942211414676,
      "grad_norm": 1.1249209768789774,
      "learning_rate": 9.870736089911836e-06,
      "loss": 1.8149,
      "step": 2950
    },
    {
      "epoch": 0.8582463166928909,
      "grad_norm": 1.183808055306546,
      "learning_rate": 9.865836800083291e-06,
      "loss": 1.8158,
      "step": 3000
    },
    {
      "epoch": 0.8725504219711057,
      "grad_norm": 0.9727019343602256,
      "learning_rate": 9.860847788030852e-06,
      "loss": 1.8101,
      "step": 3050
    },
    {
      "epoch": 0.8868545272493206,
      "grad_norm": 1.229205403976205,
      "learning_rate": 9.855769156283604e-06,
      "loss": 1.8122,
      "step": 3100
    },
    {
      "epoch": 0.9011586325275354,
      "grad_norm": 1.2130780208525513,
      "learning_rate": 9.850601009212408e-06,
      "loss": 1.8064,
      "step": 3150
    },
    {
      "epoch": 0.9154627378057503,
      "grad_norm": 1.093239130702269,
      "learning_rate": 9.845343453027747e-06,
      "loss": 1.8103,
      "step": 3200
    },
    {
      "epoch": 0.9154627378057503,
      "eval_loss": 1.7855333089828491,
      "eval_runtime": 13.1799,
      "eval_samples_per_second": 75.873,
      "eval_steps_per_second": 2.428,
      "step": 3200
    },
    {
      "epoch": 0.9297668430839651,
      "grad_norm": 1.0418651496232376,
      "learning_rate": 9.839996595777552e-06,
      "loss": 1.8023,
      "step": 3250
    },
    {
      "epoch": 0.94407094836218,
      "grad_norm": 1.2712498822645788,
      "learning_rate": 9.83456054734498e-06,
      "loss": 1.7953,
      "step": 3300
    },
    {
      "epoch": 0.9583750536403948,
      "grad_norm": 0.984132611369419,
      "learning_rate": 9.829035419446156e-06,
      "loss": 1.8015,
      "step": 3350
    },
    {
      "epoch": 0.9726791589186097,
      "grad_norm": 1.0418825994644219,
      "learning_rate": 9.823421325627865e-06,
      "loss": 1.8054,
      "step": 3400
    },
    {
      "epoch": 0.9869832641968245,
      "grad_norm": 1.336436926729505,
      "learning_rate": 9.81771838126524e-06,
      "loss": 1.7937,
      "step": 3450
    },
    {
      "epoch": 1.0012873694750393,
      "grad_norm": 1.0819159062735473,
      "learning_rate": 9.811926703559374e-06,
      "loss": 1.7868,
      "step": 3500
    },
    {
      "epoch": 1.0155914747532542,
      "grad_norm": 1.2714689918837065,
      "learning_rate": 9.806046411534916e-06,
      "loss": 1.7731,
      "step": 3550
    },
    {
      "epoch": 1.029895580031469,
      "grad_norm": 1.0129411367063064,
      "learning_rate": 9.800077626037633e-06,
      "loss": 1.7834,
      "step": 3600
    },
    {
      "epoch": 1.029895580031469,
      "eval_loss": 1.7756215333938599,
      "eval_runtime": 13.1841,
      "eval_samples_per_second": 75.849,
      "eval_steps_per_second": 2.427,
      "step": 3600
    },
    {
      "epoch": 1.044199685309684,
      "grad_norm": 0.8678146485976415,
      "learning_rate": 9.794020469731915e-06,
      "loss": 1.7858,
      "step": 3650
    },
    {
      "epoch": 1.0585037905878987,
      "grad_norm": 1.1072231200441955,
      "learning_rate": 9.787875067098257e-06,
      "loss": 1.7873,
      "step": 3700
    },
    {
      "epoch": 1.0728078958661136,
      "grad_norm": 0.8959989844152632,
      "learning_rate": 9.781641544430703e-06,
      "loss": 1.7928,
      "step": 3750
    },
    {
      "epoch": 1.0871120011443285,
      "grad_norm": 1.6994487358359982,
      "learning_rate": 9.775320029834255e-06,
      "loss": 1.7729,
      "step": 3800
    },
    {
      "epoch": 1.1014161064225432,
      "grad_norm": 1.1169687397960077,
      "learning_rate": 9.76891065322223e-06,
      "loss": 1.7814,
      "step": 3850
    },
    {
      "epoch": 1.115720211700758,
      "grad_norm": 1.0104167054836963,
      "learning_rate": 9.762413546313597e-06,
      "loss": 1.7783,
      "step": 3900
    },
    {
      "epoch": 1.130024316978973,
      "grad_norm": 0.8241889545988433,
      "learning_rate": 9.755828842630269e-06,
      "loss": 1.7716,
      "step": 3950
    },
    {
      "epoch": 1.144328422257188,
      "grad_norm": 1.0453927825295828,
      "learning_rate": 9.749156677494357e-06,
      "loss": 1.787,
      "step": 4000
    },
    {
      "epoch": 1.144328422257188,
      "eval_loss": 1.7660154104232788,
      "eval_runtime": 13.0607,
      "eval_samples_per_second": 76.566,
      "eval_steps_per_second": 2.45,
      "step": 4000
    },
    {
      "epoch": 1.1586325275354026,
      "grad_norm": 1.5781005025322197,
      "learning_rate": 9.742397188025394e-06,
      "loss": 1.777,
      "step": 4050
    },
    {
      "epoch": 1.1729366328136175,
      "grad_norm": 0.6663813498785218,
      "learning_rate": 9.735550513137513e-06,
      "loss": 1.7627,
      "step": 4100
    },
    {
      "epoch": 1.1872407380918324,
      "grad_norm": 1.16263114208236,
      "learning_rate": 9.728616793536588e-06,
      "loss": 1.7706,
      "step": 4150
    },
    {
      "epoch": 1.2015448433700473,
      "grad_norm": 0.8049406818849929,
      "learning_rate": 9.721596171717352e-06,
      "loss": 1.7732,
      "step": 4200
    },
    {
      "epoch": 1.215848948648262,
      "grad_norm": 1.1897294605157323,
      "learning_rate": 9.714488791960463e-06,
      "loss": 1.7785,
      "step": 4250
    },
    {
      "epoch": 1.230153053926477,
      "grad_norm": 0.7890939227616143,
      "learning_rate": 9.707294800329536e-06,
      "loss": 1.7743,
      "step": 4300
    },
    {
      "epoch": 1.2444571592046918,
      "grad_norm": 1.0535327717977379,
      "learning_rate": 9.700014344668152e-06,
      "loss": 1.7655,
      "step": 4350
    },
    {
      "epoch": 1.2587612644829065,
      "grad_norm": 1.0253301557877903,
      "learning_rate": 9.692647574596803e-06,
      "loss": 1.7695,
      "step": 4400
    },
    {
      "epoch": 1.2587612644829065,
      "eval_loss": 1.7592908143997192,
      "eval_runtime": 13.0236,
      "eval_samples_per_second": 76.784,
      "eval_steps_per_second": 2.457,
      "step": 4400
    },
    {
      "epoch": 1.2730653697611214,
      "grad_norm": 1.1457150793499635,
      "learning_rate": 9.685194641509837e-06,
      "loss": 1.7741,
      "step": 4450
    },
    {
      "epoch": 1.2873694750393363,
      "grad_norm": 1.1289748771161727,
      "learning_rate": 9.677655698572326e-06,
      "loss": 1.7613,
      "step": 4500
    },
    {
      "epoch": 1.3016735803175512,
      "grad_norm": 1.2805821960586556,
      "learning_rate": 9.670030900716941e-06,
      "loss": 1.7608,
      "step": 4550
    },
    {
      "epoch": 1.3159776855957661,
      "grad_norm": 1.116003748141364,
      "learning_rate": 9.662320404640743e-06,
      "loss": 1.7623,
      "step": 4600
    },
    {
      "epoch": 1.3302817908739808,
      "grad_norm": 0.915054519499902,
      "learning_rate": 9.654524368801982e-06,
      "loss": 1.7684,
      "step": 4650
    },
    {
      "epoch": 1.3445858961521957,
      "grad_norm": 1.158670382611452,
      "learning_rate": 9.646642953416835e-06,
      "loss": 1.7587,
      "step": 4700
    },
    {
      "epoch": 1.3588900014304106,
      "grad_norm": 0.6334518545999203,
      "learning_rate": 9.638676320456109e-06,
      "loss": 1.7666,
      "step": 4750
    },
    {
      "epoch": 1.3731941067086253,
      "grad_norm": 0.7291754825374577,
      "learning_rate": 9.630624633641918e-06,
      "loss": 1.759,
      "step": 4800
    },
    {
      "epoch": 1.3731941067086253,
      "eval_loss": 1.7522927522659302,
      "eval_runtime": 13.0698,
      "eval_samples_per_second": 76.512,
      "eval_steps_per_second": 2.448,
      "step": 4800
    },
    {
      "epoch": 1.3874982119868402,
      "grad_norm": 0.8676602094607595,
      "learning_rate": 9.622488058444313e-06,
      "loss": 1.7585,
      "step": 4850
    },
    {
      "epoch": 1.401802317265055,
      "grad_norm": 0.6268701284946427,
      "learning_rate": 9.614266762077891e-06,
      "loss": 1.758,
      "step": 4900
    },
    {
      "epoch": 1.4161064225432698,
      "grad_norm": 0.7954138791876184,
      "learning_rate": 9.605960913498342e-06,
      "loss": 1.7528,
      "step": 4950
    },
    {
      "epoch": 1.4304105278214847,
      "grad_norm": 0.9805674870268231,
      "learning_rate": 9.597570683398996e-06,
      "loss": 1.7652,
      "step": 5000
    },
    {
      "epoch": 1.4447146330996996,
      "grad_norm": 1.2416998933826209,
      "learning_rate": 9.5890962442073e-06,
      "loss": 1.7497,
      "step": 5050
    },
    {
      "epoch": 1.4590187383779145,
      "grad_norm": 0.9438154318623259,
      "learning_rate": 9.580537770081285e-06,
      "loss": 1.7486,
      "step": 5100
    },
    {
      "epoch": 1.4733228436561294,
      "grad_norm": 0.7575703670207814,
      "learning_rate": 9.57189543690598e-06,
      "loss": 1.7557,
      "step": 5150
    },
    {
      "epoch": 1.487626948934344,
      "grad_norm": 0.8709256334977673,
      "learning_rate": 9.563169422289798e-06,
      "loss": 1.7493,
      "step": 5200
    },
    {
      "epoch": 1.487626948934344,
      "eval_loss": 1.746894359588623,
      "eval_runtime": 13.0332,
      "eval_samples_per_second": 76.727,
      "eval_steps_per_second": 2.455,
      "step": 5200
    },
    {
      "epoch": 1.501931054212559,
      "grad_norm": 0.990313135807005,
      "learning_rate": 9.554359905560887e-06,
      "loss": 1.7526,
      "step": 5250
    },
    {
      "epoch": 1.516235159490774,
      "grad_norm": 1.3585589462134218,
      "learning_rate": 9.54546706776345e-06,
      "loss": 1.7477,
      "step": 5300
    },
    {
      "epoch": 1.5305392647689886,
      "grad_norm": 1.0080284138615836,
      "learning_rate": 9.536491091654018e-06,
      "loss": 1.7398,
      "step": 5350
    },
    {
      "epoch": 1.5448433700472035,
      "grad_norm": 0.6122020478330652,
      "learning_rate": 9.527432161697696e-06,
      "loss": 1.7556,
      "step": 5400
    },
    {
      "epoch": 1.5591474753254184,
      "grad_norm": 0.8555908841043908,
      "learning_rate": 9.518290464064365e-06,
      "loss": 1.7402,
      "step": 5450
    },
    {
      "epoch": 1.573451580603633,
      "grad_norm": 0.7605282500535738,
      "learning_rate": 9.509066186624872e-06,
      "loss": 1.7433,
      "step": 5500
    },
    {
      "epoch": 1.5877556858818482,
      "grad_norm": 0.7684854850117561,
      "learning_rate": 9.499759518947156e-06,
      "loss": 1.7447,
      "step": 5550
    },
    {
      "epoch": 1.602059791160063,
      "grad_norm": 1.2011176682075966,
      "learning_rate": 9.490370652292357e-06,
      "loss": 1.7461,
      "step": 5600
    },
    {
      "epoch": 1.602059791160063,
      "eval_loss": 1.7409335374832153,
      "eval_runtime": 13.0714,
      "eval_samples_per_second": 76.503,
      "eval_steps_per_second": 2.448,
      "step": 5600
    },
    {
      "epoch": 1.6163638964382778,
      "grad_norm": 0.9371628453607871,
      "learning_rate": 9.480899779610883e-06,
      "loss": 1.7541,
      "step": 5650
    },
    {
      "epoch": 1.6306680017164927,
      "grad_norm": 0.7143343954612081,
      "learning_rate": 9.471347095538448e-06,
      "loss": 1.7392,
      "step": 5700
    },
    {
      "epoch": 1.6449721069947074,
      "grad_norm": 0.9557461607608252,
      "learning_rate": 9.461712796392067e-06,
      "loss": 1.7476,
      "step": 5750
    },
    {
      "epoch": 1.6592762122729223,
      "grad_norm": 0.9598758061093912,
      "learning_rate": 9.45199708016603e-06,
      "loss": 1.747,
      "step": 5800
    },
    {
      "epoch": 1.6735803175511372,
      "grad_norm": 1.1359595669153315,
      "learning_rate": 9.442200146527824e-06,
      "loss": 1.7379,
      "step": 5850
    },
    {
      "epoch": 1.687884422829352,
      "grad_norm": 0.7961067517193703,
      "learning_rate": 9.432322196814032e-06,
      "loss": 1.7371,
      "step": 5900
    },
    {
      "epoch": 1.7021885281075668,
      "grad_norm": 0.9958451010134263,
      "learning_rate": 9.422363434026205e-06,
      "loss": 1.7404,
      "step": 5950
    },
    {
      "epoch": 1.7164926333857817,
      "grad_norm": 0.9090957659949102,
      "learning_rate": 9.41232406282667e-06,
      "loss": 1.7392,
      "step": 6000
    },
    {
      "epoch": 1.7164926333857817,
      "eval_loss": 1.7344313859939575,
      "eval_runtime": 13.0691,
      "eval_samples_per_second": 76.516,
      "eval_steps_per_second": 2.449,
      "step": 6000
    },
    {
      "epoch": 1.7307967386639964,
      "grad_norm": 1.1213090245292214,
      "learning_rate": 9.402204289534344e-06,
      "loss": 1.7302,
      "step": 6050
    },
    {
      "epoch": 1.7451008439422115,
      "grad_norm": 0.8031846181876277,
      "learning_rate": 9.392004322120484e-06,
      "loss": 1.734,
      "step": 6100
    },
    {
      "epoch": 1.7594049492204262,
      "grad_norm": 0.8951992445159495,
      "learning_rate": 9.381724370204414e-06,
      "loss": 1.7271,
      "step": 6150
    },
    {
      "epoch": 1.7737090544986411,
      "grad_norm": 0.6356844624225287,
      "learning_rate": 9.371364645049216e-06,
      "loss": 1.7343,
      "step": 6200
    },
    {
      "epoch": 1.788013159776856,
      "grad_norm": 0.9354771107489174,
      "learning_rate": 9.360925359557397e-06,
      "loss": 1.7213,
      "step": 6250
    },
    {
      "epoch": 1.8023172650550707,
      "grad_norm": 0.8683866672638255,
      "learning_rate": 9.3504067282665e-06,
      "loss": 1.7456,
      "step": 6300
    },
    {
      "epoch": 1.8166213703332856,
      "grad_norm": 0.7256479046632077,
      "learning_rate": 9.339808967344701e-06,
      "loss": 1.7334,
      "step": 6350
    },
    {
      "epoch": 1.8309254756115005,
      "grad_norm": 0.9100891545758867,
      "learning_rate": 9.329132294586374e-06,
      "loss": 1.7305,
      "step": 6400
    },
    {
      "epoch": 1.8309254756115005,
      "eval_loss": 1.7306665182113647,
      "eval_runtime": 13.0681,
      "eval_samples_per_second": 76.522,
      "eval_steps_per_second": 2.449,
      "step": 6400
    },
    {
      "epoch": 1.8452295808897152,
      "grad_norm": 0.7131708711024103,
      "learning_rate": 9.318376929407606e-06,
      "loss": 1.7262,
      "step": 6450
    },
    {
      "epoch": 1.8595336861679304,
      "grad_norm": 0.6762253904995256,
      "learning_rate": 9.307543092841688e-06,
      "loss": 1.7263,
      "step": 6500
    },
    {
      "epoch": 1.873837791446145,
      "grad_norm": 0.8848356010504166,
      "learning_rate": 9.296631007534576e-06,
      "loss": 1.7291,
      "step": 6550
    },
    {
      "epoch": 1.8881418967243597,
      "grad_norm": 0.8254328432524617,
      "learning_rate": 9.285640897740316e-06,
      "loss": 1.7248,
      "step": 6600
    },
    {
      "epoch": 1.9024460020025749,
      "grad_norm": 0.8328557115282507,
      "learning_rate": 9.27457298931643e-06,
      "loss": 1.7379,
      "step": 6650
    },
    {
      "epoch": 1.9167501072807895,
      "grad_norm": 0.6959225186429033,
      "learning_rate": 9.263427509719287e-06,
      "loss": 1.7217,
      "step": 6700
    },
    {
      "epoch": 1.9310542125590044,
      "grad_norm": 0.7948142001263543,
      "learning_rate": 9.252204687999401e-06,
      "loss": 1.7348,
      "step": 6750
    },
    {
      "epoch": 1.9453583178372194,
      "grad_norm": 0.9097813983094877,
      "learning_rate": 9.240904754796767e-06,
      "loss": 1.7323,
      "step": 6800
    },
    {
      "epoch": 1.9453583178372194,
      "eval_loss": 1.7259055376052856,
      "eval_runtime": 13.0454,
      "eval_samples_per_second": 76.656,
      "eval_steps_per_second": 2.453,
      "step": 6800
    },
    {
      "epoch": 1.959662423115434,
      "grad_norm": 0.9853743080642359,
      "learning_rate": 9.22952794233608e-06,
      "loss": 1.7367,
      "step": 6850
    },
    {
      "epoch": 1.973966528393649,
      "grad_norm": 0.7062853621991527,
      "learning_rate": 9.218074484421977e-06,
      "loss": 1.7222,
      "step": 6900
    },
    {
      "epoch": 1.9882706336718639,
      "grad_norm": 0.7105578463978743,
      "learning_rate": 9.206544616434249e-06,
      "loss": 1.7214,
      "step": 6950
    },
    {
      "epoch": 2.0025747389500785,
      "grad_norm": 0.9464929135027466,
      "learning_rate": 9.194938575322973e-06,
      "loss": 1.7175,
      "step": 7000
    },
    {
      "epoch": 2.0168788442282937,
      "grad_norm": 0.7023281633842239,
      "learning_rate": 9.183256599603672e-06,
      "loss": 1.7088,
      "step": 7050
    },
    {
      "epoch": 2.0311829495065084,
      "grad_norm": 0.6102272480325144,
      "learning_rate": 9.171498929352388e-06,
      "loss": 1.7067,
      "step": 7100
    },
    {
      "epoch": 2.045487054784723,
      "grad_norm": 0.855210847731902,
      "learning_rate": 9.159665806200766e-06,
      "loss": 1.7069,
      "step": 7150
    },
    {
      "epoch": 2.059791160062938,
      "grad_norm": 0.6906731860604268,
      "learning_rate": 9.147757473331082e-06,
      "loss": 1.7066,
      "step": 7200
    },
    {
      "epoch": 2.059791160062938,
      "eval_loss": 1.722530722618103,
      "eval_runtime": 13.0737,
      "eval_samples_per_second": 76.489,
      "eval_steps_per_second": 2.448,
      "step": 7200
    },
    {
      "epoch": 2.074095265341153,
      "grad_norm": 1.0171875730793354,
      "learning_rate": 9.135774175471244e-06,
      "loss": 1.7112,
      "step": 7250
    },
    {
      "epoch": 2.088399370619368,
      "grad_norm": 0.718919260784006,
      "learning_rate": 9.123716158889765e-06,
      "loss": 1.6947,
      "step": 7300
    },
    {
      "epoch": 2.1027034758975827,
      "grad_norm": 0.8725712344270407,
      "learning_rate": 9.111583671390697e-06,
      "loss": 1.6921,
      "step": 7350
    },
    {
      "epoch": 2.1170075811757973,
      "grad_norm": 0.9117880050064536,
      "learning_rate": 9.09937696230855e-06,
      "loss": 1.7062,
      "step": 7400
    },
    {
      "epoch": 2.1313116864540125,
      "grad_norm": 0.816392919836334,
      "learning_rate": 9.087096282503152e-06,
      "loss": 1.6993,
      "step": 7450
    },
    {
      "epoch": 2.145615791732227,
      "grad_norm": 0.7035389418244336,
      "learning_rate": 9.074741884354507e-06,
      "loss": 1.7022,
      "step": 7500
    },
    {
      "epoch": 2.159919897010442,
      "grad_norm": 0.7867250841208043,
      "learning_rate": 9.062314021757603e-06,
      "loss": 1.7022,
      "step": 7550
    },
    {
      "epoch": 2.174224002288657,
      "grad_norm": 0.5829241671744307,
      "learning_rate": 9.049812950117191e-06,
      "loss": 1.6875,
      "step": 7600
    },
    {
      "epoch": 2.174224002288657,
      "eval_loss": 1.7198066711425781,
      "eval_runtime": 13.1757,
      "eval_samples_per_second": 75.897,
      "eval_steps_per_second": 2.429,
      "step": 7600
    },
    {
      "epoch": 2.1885281075668717,
      "grad_norm": 1.1249011702012237,
      "learning_rate": 9.037238926342544e-06,
      "loss": 1.7058,
      "step": 7650
    },
    {
      "epoch": 2.2028322128450863,
      "grad_norm": 1.004023688704636,
      "learning_rate": 9.02459220884217e-06,
      "loss": 1.6977,
      "step": 7700
    },
    {
      "epoch": 2.2171363181233015,
      "grad_norm": 0.9785901369627025,
      "learning_rate": 9.011873057518503e-06,
      "loss": 1.7067,
      "step": 7750
    },
    {
      "epoch": 2.231440423401516,
      "grad_norm": 0.7641084413348023,
      "learning_rate": 8.999081733762568e-06,
      "loss": 1.7038,
      "step": 7800
    },
    {
      "epoch": 2.2457445286797313,
      "grad_norm": 0.7283443537665686,
      "learning_rate": 8.986218500448598e-06,
      "loss": 1.713,
      "step": 7850
    },
    {
      "epoch": 2.260048633957946,
      "grad_norm": 0.9539540219253599,
      "learning_rate": 8.973283621928644e-06,
      "loss": 1.706,
      "step": 7900
    },
    {
      "epoch": 2.2743527392361607,
      "grad_norm": 0.8106080829599567,
      "learning_rate": 8.96027736402713e-06,
      "loss": 1.6958,
      "step": 7950
    },
    {
      "epoch": 2.288656844514376,
      "grad_norm": 0.8882476907898474,
      "learning_rate": 8.947199994035402e-06,
      "loss": 1.6901,
      "step": 8000
    },
    {
      "epoch": 2.288656844514376,
      "eval_loss": 1.7156543731689453,
      "eval_runtime": 13.0298,
      "eval_samples_per_second": 76.747,
      "eval_steps_per_second": 2.456,
      "step": 8000
    },
    {
      "epoch": 2.3029609497925905,
      "grad_norm": 0.9762766790404122,
      "learning_rate": 8.934051780706226e-06,
      "loss": 1.6917,
      "step": 8050
    },
    {
      "epoch": 2.317265055070805,
      "grad_norm": 0.6971489481173876,
      "learning_rate": 8.920832994248268e-06,
      "loss": 1.6994,
      "step": 8100
    },
    {
      "epoch": 2.3315691603490203,
      "grad_norm": 0.5820566152621507,
      "learning_rate": 8.907543906320542e-06,
      "loss": 1.7065,
      "step": 8150
    },
    {
      "epoch": 2.345873265627235,
      "grad_norm": 0.645459754550139,
      "learning_rate": 8.894184790026823e-06,
      "loss": 1.6908,
      "step": 8200
    },
    {
      "epoch": 2.3601773709054497,
      "grad_norm": 1.0593884241082467,
      "learning_rate": 8.880755919910048e-06,
      "loss": 1.692,
      "step": 8250
    },
    {
      "epoch": 2.374481476183665,
      "grad_norm": 0.6598732077733668,
      "learning_rate": 8.867257571946646e-06,
      "loss": 1.7046,
      "step": 8300
    },
    {
      "epoch": 2.3887855814618795,
      "grad_norm": 0.8135828323323933,
      "learning_rate": 8.853690023540898e-06,
      "loss": 1.6983,
      "step": 8350
    },
    {
      "epoch": 2.4030896867400946,
      "grad_norm": 0.6292103166156576,
      "learning_rate": 8.840053553519216e-06,
      "loss": 1.6911,
      "step": 8400
    },
    {
      "epoch": 2.4030896867400946,
      "eval_loss": 1.7090901136398315,
      "eval_runtime": 13.0474,
      "eval_samples_per_second": 76.644,
      "eval_steps_per_second": 2.453,
      "step": 8400
    },
    {
      "epoch": 2.4173937920183093,
      "grad_norm": 0.8817911559963482,
      "learning_rate": 8.82634844212442e-06,
      "loss": 1.6933,
      "step": 8450
    },
    {
      "epoch": 2.431697897296524,
      "grad_norm": 0.7934805421221099,
      "learning_rate": 8.81257497100998e-06,
      "loss": 1.6895,
      "step": 8500
    },
    {
      "epoch": 2.446002002574739,
      "grad_norm": 0.855182243732375,
      "learning_rate": 8.79873342323422e-06,
      "loss": 1.6945,
      "step": 8550
    },
    {
      "epoch": 2.460306107852954,
      "grad_norm": 0.6125900217722975,
      "learning_rate": 8.78482408325451e-06,
      "loss": 1.6906,
      "step": 8600
    },
    {
      "epoch": 2.4746102131311685,
      "grad_norm": 0.6660364707065795,
      "learning_rate": 8.770847236921412e-06,
      "loss": 1.6922,
      "step": 8650
    },
    {
      "epoch": 2.4889143184093836,
      "grad_norm": 0.7819064185488933,
      "learning_rate": 8.756803171472817e-06,
      "loss": 1.6927,
      "step": 8700
    },
    {
      "epoch": 2.5032184236875983,
      "grad_norm": 0.6307439119404958,
      "learning_rate": 8.742692175528027e-06,
      "loss": 1.6989,
      "step": 8750
    },
    {
      "epoch": 2.517522528965813,
      "grad_norm": 0.6293488618510799,
      "learning_rate": 8.728514539081837e-06,
      "loss": 1.6837,
      "step": 8800
    },
    {
      "epoch": 2.517522528965813,
      "eval_loss": 1.7051697969436646,
      "eval_runtime": 13.0509,
      "eval_samples_per_second": 76.623,
      "eval_steps_per_second": 2.452,
      "step": 8800
    },
    {
      "epoch": 2.531826634244028,
      "grad_norm": 0.7311550336703251,
      "learning_rate": 8.714270553498567e-06,
      "loss": 1.6836,
      "step": 8850
    },
    {
      "epoch": 2.546130739522243,
      "grad_norm": 0.560283624336398,
      "learning_rate": 8.699960511506077e-06,
      "loss": 1.6977,
      "step": 8900
    },
    {
      "epoch": 2.560434844800458,
      "grad_norm": 0.6106667827565102,
      "learning_rate": 8.685584707189749e-06,
      "loss": 1.6904,
      "step": 8950
    },
    {
      "epoch": 2.5747389500786726,
      "grad_norm": 0.7552955271738838,
      "learning_rate": 8.671143435986447e-06,
      "loss": 1.69,
      "step": 9000
    },
    {
      "epoch": 2.5890430553568873,
      "grad_norm": 0.6855807066717469,
      "learning_rate": 8.656636994678447e-06,
      "loss": 1.6995,
      "step": 9050
    },
    {
      "epoch": 2.6033471606351024,
      "grad_norm": 0.8814483730904599,
      "learning_rate": 8.642065681387329e-06,
      "loss": 1.6919,
      "step": 9100
    },
    {
      "epoch": 2.617651265913317,
      "grad_norm": 0.6710277536844194,
      "learning_rate": 8.627429795567858e-06,
      "loss": 1.6862,
      "step": 9150
    },
    {
      "epoch": 2.6319553711915322,
      "grad_norm": 0.887320880133999,
      "learning_rate": 8.61272963800183e-06,
      "loss": 1.6859,
      "step": 9200
    },
    {
      "epoch": 2.6319553711915322,
      "eval_loss": 1.7010042667388916,
      "eval_runtime": 13.0596,
      "eval_samples_per_second": 76.572,
      "eval_steps_per_second": 2.45,
      "step": 9200
    },
    {
      "epoch": 2.646259476469747,
      "grad_norm": 0.6062615724604773,
      "learning_rate": 8.597965510791883e-06,
      "loss": 1.6957,
      "step": 9250
    },
    {
      "epoch": 2.6605635817479616,
      "grad_norm": 0.9356074049979478,
      "learning_rate": 8.5831377173553e-06,
      "loss": 1.6811,
      "step": 9300
    },
    {
      "epoch": 2.6748676870261763,
      "grad_norm": 0.905579588189196,
      "learning_rate": 8.568246562417762e-06,
      "loss": 1.6879,
      "step": 9350
    },
    {
      "epoch": 2.6891717923043914,
      "grad_norm": 0.7739005916322703,
      "learning_rate": 8.553292352007096e-06,
      "loss": 1.6879,
      "step": 9400
    },
    {
      "epoch": 2.703475897582606,
      "grad_norm": 0.8473371714356891,
      "learning_rate": 8.538275393446976e-06,
      "loss": 1.6907,
      "step": 9450
    },
    {
      "epoch": 2.717780002860821,
      "grad_norm": 0.6586208831165219,
      "learning_rate": 8.523195995350613e-06,
      "loss": 1.6886,
      "step": 9500
    },
    {
      "epoch": 2.732084108139036,
      "grad_norm": 0.827548888966318,
      "learning_rate": 8.508054467614417e-06,
      "loss": 1.6855,
      "step": 9550
    },
    {
      "epoch": 2.7463882134172506,
      "grad_norm": 0.702203100476128,
      "learning_rate": 8.492851121411614e-06,
      "loss": 1.6832,
      "step": 9600
    },
    {
      "epoch": 2.7463882134172506,
      "eval_loss": 1.6964640617370605,
      "eval_runtime": 13.1004,
      "eval_samples_per_second": 76.334,
      "eval_steps_per_second": 2.443,
      "step": 9600
    },
    {
      "epoch": 2.7606923186954657,
      "grad_norm": 0.7172738684998019,
      "learning_rate": 8.477586269185868e-06,
      "loss": 1.6824,
      "step": 9650
    },
    {
      "epoch": 2.7749964239736804,
      "grad_norm": 0.6634870837445137,
      "learning_rate": 8.462260224644848e-06,
      "loss": 1.6821,
      "step": 9700
    },
    {
      "epoch": 2.7893005292518955,
      "grad_norm": 0.6916121607750829,
      "learning_rate": 8.446873302753783e-06,
      "loss": 1.6909,
      "step": 9750
    },
    {
      "epoch": 2.80360463453011,
      "grad_norm": 0.7324116907371762,
      "learning_rate": 8.431425819728998e-06,
      "loss": 1.6909,
      "step": 9800
    },
    {
      "epoch": 2.817908739808325,
      "grad_norm": 0.6843560320392789,
      "learning_rate": 8.415918093031403e-06,
      "loss": 1.6786,
      "step": 9850
    },
    {
      "epoch": 2.8322128450865396,
      "grad_norm": 0.752892823321002,
      "learning_rate": 8.400350441359976e-06,
      "loss": 1.6728,
      "step": 9900
    },
    {
      "epoch": 2.8465169503647547,
      "grad_norm": 0.9700342755779745,
      "learning_rate": 8.384723184645211e-06,
      "loss": 1.6783,
      "step": 9950
    },
    {
      "epoch": 2.8608210556429694,
      "grad_norm": 0.7767564698368711,
      "learning_rate": 8.369036644042546e-06,
      "loss": 1.6675,
      "step": 10000
    },
    {
      "epoch": 2.8608210556429694,
      "eval_loss": 1.693839192390442,
      "eval_runtime": 13.0504,
      "eval_samples_per_second": 76.626,
      "eval_steps_per_second": 2.452,
      "step": 10000
    },
    {
      "epoch": 2.8751251609211845,
      "grad_norm": 0.6772095075860332,
      "learning_rate": 8.353291141925763e-06,
      "loss": 1.6721,
      "step": 10050
    },
    {
      "epoch": 2.889429266199399,
      "grad_norm": 0.6382340661083454,
      "learning_rate": 8.337487001880353e-06,
      "loss": 1.6842,
      "step": 10100
    },
    {
      "epoch": 2.903733371477614,
      "grad_norm": 0.7870530454186793,
      "learning_rate": 8.32162454869688e-06,
      "loss": 1.6764,
      "step": 10150
    },
    {
      "epoch": 2.918037476755829,
      "grad_norm": 0.7725000837437397,
      "learning_rate": 8.305704108364301e-06,
      "loss": 1.6795,
      "step": 10200
    },
    {
      "epoch": 2.9323415820340437,
      "grad_norm": 0.6068764021560474,
      "learning_rate": 8.289726008063265e-06,
      "loss": 1.6783,
      "step": 10250
    },
    {
      "epoch": 2.946645687312259,
      "grad_norm": 0.9395553539153366,
      "learning_rate": 8.273690576159383e-06,
      "loss": 1.68,
      "step": 10300
    },
    {
      "epoch": 2.9609497925904735,
      "grad_norm": 0.7531796928086886,
      "learning_rate": 8.257598142196496e-06,
      "loss": 1.6669,
      "step": 10350
    },
    {
      "epoch": 2.975253897868688,
      "grad_norm": 0.6247104825883635,
      "learning_rate": 8.241449036889892e-06,
      "loss": 1.6718,
      "step": 10400
    },
    {
      "epoch": 2.975253897868688,
      "eval_loss": 1.6905415058135986,
      "eval_runtime": 13.0826,
      "eval_samples_per_second": 76.438,
      "eval_steps_per_second": 2.446,
      "step": 10400
    },
    {
      "epoch": 2.989558003146903,
      "grad_norm": 0.546997508440891,
      "learning_rate": 8.225243592119501e-06,
      "loss": 1.6805,
      "step": 10450
    },
    {
      "epoch": 3.003862108425118,
      "grad_norm": 0.7776889636138464,
      "learning_rate": 8.208982140923095e-06,
      "loss": 1.6707,
      "step": 10500
    },
    {
      "epoch": 3.0181662137033327,
      "grad_norm": 0.7998275166017301,
      "learning_rate": 8.192665017489431e-06,
      "loss": 1.6397,
      "step": 10550
    },
    {
      "epoch": 3.032470318981548,
      "grad_norm": 0.7459803419055197,
      "learning_rate": 8.17629255715138e-06,
      "loss": 1.6611,
      "step": 10600
    },
    {
      "epoch": 3.0467744242597625,
      "grad_norm": 0.6817944157156409,
      "learning_rate": 8.159865096379046e-06,
      "loss": 1.6375,
      "step": 10650
    },
    {
      "epoch": 3.061078529537977,
      "grad_norm": 0.6959338742861377,
      "learning_rate": 8.14338297277284e-06,
      "loss": 1.6392,
      "step": 10700
    },
    {
      "epoch": 3.0753826348161923,
      "grad_norm": 0.7388183617279478,
      "learning_rate": 8.126846525056555e-06,
      "loss": 1.6424,
      "step": 10750
    },
    {
      "epoch": 3.089686740094407,
      "grad_norm": 0.6981074857483759,
      "learning_rate": 8.110256093070393e-06,
      "loss": 1.6592,
      "step": 10800
    },
    {
      "epoch": 3.089686740094407,
      "eval_loss": 1.6885778903961182,
      "eval_runtime": 13.0832,
      "eval_samples_per_second": 76.434,
      "eval_steps_per_second": 2.446,
      "step": 10800
    },
    {
      "epoch": 3.103990845372622,
      "grad_norm": 0.7805391928889925,
      "learning_rate": 8.093612017763986e-06,
      "loss": 1.6437,
      "step": 10850
    },
    {
      "epoch": 3.118294950650837,
      "grad_norm": 0.7246045663324853,
      "learning_rate": 8.076914641189388e-06,
      "loss": 1.6557,
      "step": 10900
    },
    {
      "epoch": 3.1325990559290515,
      "grad_norm": 0.7387863523438669,
      "learning_rate": 8.060164306494052e-06,
      "loss": 1.6397,
      "step": 10950
    },
    {
      "epoch": 3.1469031612072667,
      "grad_norm": 0.6210712373332249,
      "learning_rate": 8.043361357913763e-06,
      "loss": 1.6413,
      "step": 11000
    },
    {
      "epoch": 3.1612072664854813,
      "grad_norm": 0.9802329165310913,
      "learning_rate": 8.026506140765581e-06,
      "loss": 1.6453,
      "step": 11050
    },
    {
      "epoch": 3.175511371763696,
      "grad_norm": 0.6431933255522037,
      "learning_rate": 8.009599001440733e-06,
      "loss": 1.6499,
      "step": 11100
    },
    {
      "epoch": 3.189815477041911,
      "grad_norm": 0.6689757471837987,
      "learning_rate": 7.992640287397498e-06,
      "loss": 1.6464,
      "step": 11150
    },
    {
      "epoch": 3.204119582320126,
      "grad_norm": 0.5745449183320485,
      "learning_rate": 7.975630347154062e-06,
      "loss": 1.6458,
      "step": 11200
    },
    {
      "epoch": 3.204119582320126,
      "eval_loss": 1.68647038936615,
      "eval_runtime": 13.0514,
      "eval_samples_per_second": 76.62,
      "eval_steps_per_second": 2.452,
      "step": 11200
    },
    {
      "epoch": 3.2184236875983405,
      "grad_norm": 0.7776825101072233,
      "learning_rate": 7.958569530281369e-06,
      "loss": 1.6423,
      "step": 11250
    },
    {
      "epoch": 3.2327277928765557,
      "grad_norm": 0.7074657527331386,
      "learning_rate": 7.941458187395918e-06,
      "loss": 1.6402,
      "step": 11300
    },
    {
      "epoch": 3.2470318981547703,
      "grad_norm": 0.6882685901776942,
      "learning_rate": 7.924296670152573e-06,
      "loss": 1.6413,
      "step": 11350
    },
    {
      "epoch": 3.2613360034329855,
      "grad_norm": 0.7352534174047116,
      "learning_rate": 7.907085331237328e-06,
      "loss": 1.6535,
      "step": 11400
    },
    {
      "epoch": 3.2756401087112,
      "grad_norm": 0.6752564589976222,
      "learning_rate": 7.889824524360058e-06,
      "loss": 1.6502,
      "step": 11450
    },
    {
      "epoch": 3.289944213989415,
      "grad_norm": 0.7781753735420677,
      "learning_rate": 7.872514604247261e-06,
      "loss": 1.6503,
      "step": 11500
    },
    {
      "epoch": 3.30424831926763,
      "grad_norm": 0.7069554958978874,
      "learning_rate": 7.855155926634755e-06,
      "loss": 1.6521,
      "step": 11550
    },
    {
      "epoch": 3.3185524245458446,
      "grad_norm": 0.8017576198027669,
      "learning_rate": 7.837748848260372e-06,
      "loss": 1.6518,
      "step": 11600
    },
    {
      "epoch": 3.3185524245458446,
      "eval_loss": 1.6823465824127197,
      "eval_runtime": 13.0525,
      "eval_samples_per_second": 76.614,
      "eval_steps_per_second": 2.452,
      "step": 11600
    },
    {
      "epoch": 3.3328565298240593,
      "grad_norm": 0.7088855521224748,
      "learning_rate": 7.820293726856625e-06,
      "loss": 1.6422,
      "step": 11650
    },
    {
      "epoch": 3.3471606351022745,
      "grad_norm": 0.6674161498231996,
      "learning_rate": 7.802790921143367e-06,
      "loss": 1.6477,
      "step": 11700
    },
    {
      "epoch": 3.361464740380489,
      "grad_norm": 0.7617355475219582,
      "learning_rate": 7.785240790820403e-06,
      "loss": 1.6424,
      "step": 11750
    },
    {
      "epoch": 3.375768845658704,
      "grad_norm": 0.5922876479830514,
      "learning_rate": 7.767643696560103e-06,
      "loss": 1.6286,
      "step": 11800
    },
    {
      "epoch": 3.390072950936919,
      "grad_norm": 0.6014516421402848,
      "learning_rate": 7.75e-06,
      "loss": 1.6507,
      "step": 11850
    },
    {
      "epoch": 3.4043770562151336,
      "grad_norm": 0.623953970052767,
      "learning_rate": 7.732310063735346e-06,
      "loss": 1.6348,
      "step": 11900
    },
    {
      "epoch": 3.4186811614933488,
      "grad_norm": 0.8360426729514715,
      "learning_rate": 7.71457425131166e-06,
      "loss": 1.6276,
      "step": 11950
    },
    {
      "epoch": 3.4329852667715635,
      "grad_norm": 0.6464266491022174,
      "learning_rate": 7.696792927217266e-06,
      "loss": 1.6391,
      "step": 12000
    },
    {
      "epoch": 3.4329852667715635,
      "eval_loss": 1.678931474685669,
      "eval_runtime": 13.0631,
      "eval_samples_per_second": 76.551,
      "eval_steps_per_second": 2.45,
      "step": 12000
    },
    {
      "epoch": 3.447289372049778,
      "grad_norm": 0.6126546460094165,
      "learning_rate": 7.6789664568758e-06,
      "loss": 1.6287,
      "step": 12050
    },
    {
      "epoch": 3.4615934773279933,
      "grad_norm": 0.5960230832976515,
      "learning_rate": 7.661095206638688e-06,
      "loss": 1.6433,
      "step": 12100
    },
    {
      "epoch": 3.475897582606208,
      "grad_norm": 0.6761717944619002,
      "learning_rate": 7.643179543777636e-06,
      "loss": 1.649,
      "step": 12150
    },
    {
      "epoch": 3.4902016878844226,
      "grad_norm": 0.9634933236219494,
      "learning_rate": 7.625219836477073e-06,
      "loss": 1.6417,
      "step": 12200
    },
    {
      "epoch": 3.5045057931626378,
      "grad_norm": 0.7034969394806604,
      "learning_rate": 7.607216453826575e-06,
      "loss": 1.6393,
      "step": 12250
    },
    {
      "epoch": 3.5188098984408525,
      "grad_norm": 0.6731018596913478,
      "learning_rate": 7.589169765813298e-06,
      "loss": 1.647,
      "step": 12300
    },
    {
      "epoch": 3.533114003719067,
      "grad_norm": 0.6118854498537465,
      "learning_rate": 7.571080143314362e-06,
      "loss": 1.6309,
      "step": 12350
    },
    {
      "epoch": 3.5474181089972823,
      "grad_norm": 0.5833382042357486,
      "learning_rate": 7.552947958089234e-06,
      "loss": 1.6261,
      "step": 12400
    },
    {
      "epoch": 3.5474181089972823,
      "eval_loss": 1.6743122339248657,
      "eval_runtime": 13.0457,
      "eval_samples_per_second": 76.653,
      "eval_steps_per_second": 2.453,
      "step": 12400
    },
    {
      "epoch": 3.561722214275497,
      "grad_norm": 0.6661614205378471,
      "learning_rate": 7.534773582772087e-06,
      "loss": 1.6351,
      "step": 12450
    },
    {
      "epoch": 3.576026319553712,
      "grad_norm": 0.714289109336214,
      "learning_rate": 7.51655739086414e-06,
      "loss": 1.6422,
      "step": 12500
    },
    {
      "epoch": 3.5903304248319268,
      "grad_norm": 0.6101362453032799,
      "learning_rate": 7.498299756725984e-06,
      "loss": 1.6447,
      "step": 12550
    },
    {
      "epoch": 3.6046345301101415,
      "grad_norm": 0.5358085065496345,
      "learning_rate": 7.480001055569892e-06,
      "loss": 1.6356,
      "step": 12600
    },
    {
      "epoch": 3.6189386353883566,
      "grad_norm": 0.5759734399751635,
      "learning_rate": 7.4616616634521e-06,
      "loss": 1.64,
      "step": 12650
    },
    {
      "epoch": 3.6332427406665713,
      "grad_norm": 0.7053847123624982,
      "learning_rate": 7.443281957265086e-06,
      "loss": 1.6335,
      "step": 12700
    },
    {
      "epoch": 3.6475468459447864,
      "grad_norm": 0.6269316120083251,
      "learning_rate": 7.424862314729819e-06,
      "loss": 1.6359,
      "step": 12750
    },
    {
      "epoch": 3.661850951223001,
      "grad_norm": 0.7414178784729023,
      "learning_rate": 7.406403114388003e-06,
      "loss": 1.6344,
      "step": 12800
    },
    {
      "epoch": 3.661850951223001,
      "eval_loss": 1.67084538936615,
      "eval_runtime": 13.0507,
      "eval_samples_per_second": 76.624,
      "eval_steps_per_second": 2.452,
      "step": 12800
    },
    {
      "epoch": 3.6761550565012158,
      "grad_norm": 0.739429421422803,
      "learning_rate": 7.387904735594291e-06,
      "loss": 1.6338,
      "step": 12850
    },
    {
      "epoch": 3.6904591617794305,
      "grad_norm": 0.6194546733603346,
      "learning_rate": 7.36936755850849e-06,
      "loss": 1.644,
      "step": 12900
    },
    {
      "epoch": 3.7047632670576456,
      "grad_norm": 0.5969848608399483,
      "learning_rate": 7.3507919640877535e-06,
      "loss": 1.64,
      "step": 12950
    },
    {
      "epoch": 3.7190673723358603,
      "grad_norm": 0.6934857883840727,
      "learning_rate": 7.332178334078746e-06,
      "loss": 1.6384,
      "step": 13000
    },
    {
      "epoch": 3.7333714776140754,
      "grad_norm": 0.635352435508875,
      "learning_rate": 7.313527051009803e-06,
      "loss": 1.6367,
      "step": 13050
    },
    {
      "epoch": 3.74767558289229,
      "grad_norm": 0.6676277653287923,
      "learning_rate": 7.2948384981830655e-06,
      "loss": 1.6332,
      "step": 13100
    },
    {
      "epoch": 3.7619796881705048,
      "grad_norm": 0.5981093667238178,
      "learning_rate": 7.2761130596666045e-06,
      "loss": 1.6243,
      "step": 13150
    },
    {
      "epoch": 3.77628379344872,
      "grad_norm": 0.6546784259139526,
      "learning_rate": 7.25735112028653e-06,
      "loss": 1.6331,
      "step": 13200
    },
    {
      "epoch": 3.77628379344872,
      "eval_loss": 1.6657731533050537,
      "eval_runtime": 13.0681,
      "eval_samples_per_second": 76.522,
      "eval_steps_per_second": 2.449,
      "step": 13200
    },
    {
      "epoch": 3.7905878987269346,
      "grad_norm": 1.1022867143082844,
      "learning_rate": 7.2385530656190785e-06,
      "loss": 1.6221,
      "step": 13250
    },
    {
      "epoch": 3.8048920040051497,
      "grad_norm": 0.7046788263112277,
      "learning_rate": 7.219719281982694e-06,
      "loss": 1.6263,
      "step": 13300
    },
    {
      "epoch": 3.8191961092833644,
      "grad_norm": 0.7089454605909015,
      "learning_rate": 7.20085015643008e-06,
      "loss": 1.6245,
      "step": 13350
    },
    {
      "epoch": 3.833500214561579,
      "grad_norm": 0.7801822159411739,
      "learning_rate": 7.181946076740257e-06,
      "loss": 1.6231,
      "step": 13400
    },
    {
      "epoch": 3.8478043198397938,
      "grad_norm": 0.6644382304711074,
      "learning_rate": 7.163007431410583e-06,
      "loss": 1.632,
      "step": 13450
    },
    {
      "epoch": 3.862108425118009,
      "grad_norm": 0.7162696862257913,
      "learning_rate": 7.144034609648779e-06,
      "loss": 1.6379,
      "step": 13500
    },
    {
      "epoch": 3.8764125303962236,
      "grad_norm": 0.66835417830248,
      "learning_rate": 7.125028001364918e-06,
      "loss": 1.6265,
      "step": 13550
    },
    {
      "epoch": 3.8907166356744387,
      "grad_norm": 0.8073668698442618,
      "learning_rate": 7.105987997163424e-06,
      "loss": 1.6305,
      "step": 13600
    },
    {
      "epoch": 3.8907166356744387,
      "eval_loss": 1.6642513275146484,
      "eval_runtime": 13.0315,
      "eval_samples_per_second": 76.737,
      "eval_steps_per_second": 2.456,
      "step": 13600
    },
    {
      "epoch": 3.9050207409526534,
      "grad_norm": 0.8129075896081209,
      "learning_rate": 7.086914988335039e-06,
      "loss": 1.6334,
      "step": 13650
    },
    {
      "epoch": 3.919324846230868,
      "grad_norm": 0.6722996060245693,
      "learning_rate": 7.0678093668487836e-06,
      "loss": 1.6378,
      "step": 13700
    },
    {
      "epoch": 3.933628951509083,
      "grad_norm": 0.6234556338573759,
      "learning_rate": 7.048671525343898e-06,
      "loss": 1.6157,
      "step": 13750
    },
    {
      "epoch": 3.947933056787298,
      "grad_norm": 0.674127005602253,
      "learning_rate": 7.029501857121776e-06,
      "loss": 1.6237,
      "step": 13800
    },
    {
      "epoch": 3.962237162065513,
      "grad_norm": 0.6848190186027889,
      "learning_rate": 7.010300756137882e-06,
      "loss": 1.6167,
      "step": 13850
    },
    {
      "epoch": 3.9765412673437277,
      "grad_norm": 0.7866991878129077,
      "learning_rate": 6.991068616993655e-06,
      "loss": 1.6264,
      "step": 13900
    },
    {
      "epoch": 3.9908453726219424,
      "grad_norm": 0.6764477676367477,
      "learning_rate": 6.971805834928399e-06,
      "loss": 1.6198,
      "step": 13950
    },
    {
      "epoch": 4.005149477900157,
      "grad_norm": 0.561303007679291,
      "learning_rate": 6.952512805811156e-06,
      "loss": 1.6281,
      "step": 14000
    },
    {
      "epoch": 4.005149477900157,
      "eval_loss": 1.6613872051239014,
      "eval_runtime": 13.0547,
      "eval_samples_per_second": 76.601,
      "eval_steps_per_second": 2.451,
      "step": 14000
    },
    {
      "epoch": 4.019453583178372,
      "grad_norm": 0.8593165537427608,
      "learning_rate": 6.933189926132581e-06,
      "loss": 1.5957,
      "step": 14050
    },
    {
      "epoch": 4.033757688456587,
      "grad_norm": 0.7007147184136575,
      "learning_rate": 6.913837592996783e-06,
      "loss": 1.5881,
      "step": 14100
    },
    {
      "epoch": 4.048061793734802,
      "grad_norm": 0.770003508592736,
      "learning_rate": 6.894456204113167e-06,
      "loss": 1.605,
      "step": 14150
    },
    {
      "epoch": 4.062365899013017,
      "grad_norm": 0.6226702180817224,
      "learning_rate": 6.875046157788267e-06,
      "loss": 1.5911,
      "step": 14200
    },
    {
      "epoch": 4.076670004291231,
      "grad_norm": 0.7639202802814479,
      "learning_rate": 6.855607852917555e-06,
      "loss": 1.604,
      "step": 14250
    },
    {
      "epoch": 4.090974109569446,
      "grad_norm": 0.882721244152998,
      "learning_rate": 6.836141688977238e-06,
      "loss": 1.6012,
      "step": 14300
    },
    {
      "epoch": 4.105278214847662,
      "grad_norm": 0.6636212731955713,
      "learning_rate": 6.816648066016059e-06,
      "loss": 1.6104,
      "step": 14350
    },
    {
      "epoch": 4.119582320125876,
      "grad_norm": 0.600373299209649,
      "learning_rate": 6.7971273846470696e-06,
      "loss": 1.5809,
      "step": 14400
    },
    {
      "epoch": 4.119582320125876,
      "eval_loss": 1.6590399742126465,
      "eval_runtime": 13.0488,
      "eval_samples_per_second": 76.635,
      "eval_steps_per_second": 2.452,
      "step": 14400
    },
    {
      "epoch": 4.133886425404091,
      "grad_norm": 0.5838739816681767,
      "learning_rate": 6.777580046039399e-06,
      "loss": 1.5936,
      "step": 14450
    },
    {
      "epoch": 4.148190530682306,
      "grad_norm": 0.8054046294072329,
      "learning_rate": 6.758006451910008e-06,
      "loss": 1.5943,
      "step": 14500
    },
    {
      "epoch": 4.16249463596052,
      "grad_norm": 0.6586960505758862,
      "learning_rate": 6.738407004515434e-06,
      "loss": 1.5972,
      "step": 14550
    },
    {
      "epoch": 4.176798741238736,
      "grad_norm": 0.614285360390926,
      "learning_rate": 6.718782106643524e-06,
      "loss": 1.5987,
      "step": 14600
    },
    {
      "epoch": 4.191102846516951,
      "grad_norm": 0.7672522315210418,
      "learning_rate": 6.699132161605158e-06,
      "loss": 1.5989,
      "step": 14650
    },
    {
      "epoch": 4.205406951795165,
      "grad_norm": 0.6095862804856478,
      "learning_rate": 6.679457573225961e-06,
      "loss": 1.5927,
      "step": 14700
    },
    {
      "epoch": 4.21971105707338,
      "grad_norm": 0.5725548623370728,
      "learning_rate": 6.659758745837998e-06,
      "loss": 1.5944,
      "step": 14750
    },
    {
      "epoch": 4.234015162351595,
      "grad_norm": 0.6763995208415444,
      "learning_rate": 6.640036084271477e-06,
      "loss": 1.5856,
      "step": 14800
    },
    {
      "epoch": 4.234015162351595,
      "eval_loss": 1.6558407545089722,
      "eval_runtime": 13.0633,
      "eval_samples_per_second": 76.55,
      "eval_steps_per_second": 2.45,
      "step": 14800
    },
    {
      "epoch": 4.248319267629809,
      "grad_norm": 0.5816921920934364,
      "learning_rate": 6.620289993846416e-06,
      "loss": 1.5894,
      "step": 14850
    },
    {
      "epoch": 4.262623372908025,
      "grad_norm": 0.5963950247380321,
      "learning_rate": 6.600520880364318e-06,
      "loss": 1.5877,
      "step": 14900
    },
    {
      "epoch": 4.27692747818624,
      "grad_norm": 0.7244641422220082,
      "learning_rate": 6.5807291500998385e-06,
      "loss": 1.5984,
      "step": 14950
    },
    {
      "epoch": 4.291231583464454,
      "grad_norm": 0.6891578076550495,
      "learning_rate": 6.560915209792424e-06,
      "loss": 1.5811,
      "step": 15000
    },
    {
      "epoch": 4.305535688742669,
      "grad_norm": 0.6285344026946775,
      "learning_rate": 6.541079466637962e-06,
      "loss": 1.5963,
      "step": 15050
    },
    {
      "epoch": 4.319839794020884,
      "grad_norm": 0.6315690680101345,
      "learning_rate": 6.52122232828041e-06,
      "loss": 1.5957,
      "step": 15100
    },
    {
      "epoch": 4.334143899299098,
      "grad_norm": 0.5748378429144894,
      "learning_rate": 6.501344202803415e-06,
      "loss": 1.5931,
      "step": 15150
    },
    {
      "epoch": 4.348448004577314,
      "grad_norm": 0.7552352391145764,
      "learning_rate": 6.4814454987219355e-06,
      "loss": 1.5945,
      "step": 15200
    },
    {
      "epoch": 4.348448004577314,
      "eval_loss": 1.6537083387374878,
      "eval_runtime": 13.0367,
      "eval_samples_per_second": 76.707,
      "eval_steps_per_second": 2.455,
      "step": 15200
    },
    {
      "epoch": 4.362752109855529,
      "grad_norm": 0.6302273947646538,
      "learning_rate": 6.461526624973836e-06,
      "loss": 1.5949,
      "step": 15250
    },
    {
      "epoch": 4.377056215133743,
      "grad_norm": 0.7279773630417031,
      "learning_rate": 6.441587990911489e-06,
      "loss": 1.5955,
      "step": 15300
    },
    {
      "epoch": 4.391360320411958,
      "grad_norm": 0.7564493394180175,
      "learning_rate": 6.421630006293359e-06,
      "loss": 1.5784,
      "step": 15350
    },
    {
      "epoch": 4.405664425690173,
      "grad_norm": 0.6547475070066977,
      "learning_rate": 6.401653081275586e-06,
      "loss": 1.5815,
      "step": 15400
    },
    {
      "epoch": 4.419968530968388,
      "grad_norm": 0.6231989802641532,
      "learning_rate": 6.38165762640355e-06,
      "loss": 1.5898,
      "step": 15450
    },
    {
      "epoch": 4.434272636246603,
      "grad_norm": 0.6634320872185652,
      "learning_rate": 6.361644052603445e-06,
      "loss": 1.5857,
      "step": 15500
    },
    {
      "epoch": 4.448576741524818,
      "grad_norm": 0.585640805907106,
      "learning_rate": 6.341612771173817e-06,
      "loss": 1.5944,
      "step": 15550
    },
    {
      "epoch": 4.462880846803032,
      "grad_norm": 0.6816841693204327,
      "learning_rate": 6.321564193777129e-06,
      "loss": 1.5847,
      "step": 15600
    },
    {
      "epoch": 4.462880846803032,
      "eval_loss": 1.6510008573532104,
      "eval_runtime": 13.0513,
      "eval_samples_per_second": 76.621,
      "eval_steps_per_second": 2.452,
      "step": 15600
    },
    {
      "epoch": 4.477184952081247,
      "grad_norm": 0.6053048902545912,
      "learning_rate": 6.301498732431287e-06,
      "loss": 1.595,
      "step": 15650
    },
    {
      "epoch": 4.491489057359463,
      "grad_norm": 0.5846349328081588,
      "learning_rate": 6.281416799501188e-06,
      "loss": 1.5829,
      "step": 15700
    },
    {
      "epoch": 4.505793162637677,
      "grad_norm": 0.6663370815014324,
      "learning_rate": 6.261318807690223e-06,
      "loss": 1.5913,
      "step": 15750
    },
    {
      "epoch": 4.520097267915892,
      "grad_norm": 0.6707807397421404,
      "learning_rate": 6.24120517003182e-06,
      "loss": 1.5855,
      "step": 15800
    },
    {
      "epoch": 4.534401373194107,
      "grad_norm": 0.6936942245291033,
      "learning_rate": 6.221076299880939e-06,
      "loss": 1.5836,
      "step": 15850
    },
    {
      "epoch": 4.548705478472321,
      "grad_norm": 0.5972670709526067,
      "learning_rate": 6.200932610905584e-06,
      "loss": 1.5983,
      "step": 15900
    },
    {
      "epoch": 4.563009583750537,
      "grad_norm": 0.7073631469228808,
      "learning_rate": 6.180774517078301e-06,
      "loss": 1.5801,
      "step": 15950
    },
    {
      "epoch": 4.577313689028752,
      "grad_norm": 0.6700094336440139,
      "learning_rate": 6.160602432667668e-06,
      "loss": 1.5788,
      "step": 16000
    },
    {
      "epoch": 4.577313689028752,
      "eval_loss": 1.6471811532974243,
      "eval_runtime": 13.0567,
      "eval_samples_per_second": 76.589,
      "eval_steps_per_second": 2.451,
      "step": 16000
    },
    {
      "epoch": 4.591617794306966,
      "grad_norm": 0.6135192274092318,
      "learning_rate": 6.140416772229785e-06,
      "loss": 1.59,
      "step": 16050
    },
    {
      "epoch": 4.605921899585181,
      "grad_norm": 0.6341044144664583,
      "learning_rate": 6.12021795059975e-06,
      "loss": 1.5846,
      "step": 16100
    },
    {
      "epoch": 4.620226004863396,
      "grad_norm": 0.724534964828596,
      "learning_rate": 6.10000638288314e-06,
      "loss": 1.59,
      "step": 16150
    },
    {
      "epoch": 4.63453011014161,
      "grad_norm": 0.6113074334486132,
      "learning_rate": 6.079782484447475e-06,
      "loss": 1.575,
      "step": 16200
    },
    {
      "epoch": 4.648834215419825,
      "grad_norm": 0.6386331564571069,
      "learning_rate": 6.059546670913684e-06,
      "loss": 1.5872,
      "step": 16250
    },
    {
      "epoch": 4.663138320698041,
      "grad_norm": 0.7261941546202135,
      "learning_rate": 6.03929935814756e-06,
      "loss": 1.5784,
      "step": 16300
    },
    {
      "epoch": 4.677442425976255,
      "grad_norm": 0.6351322658943287,
      "learning_rate": 6.01904096225122e-06,
      "loss": 1.5765,
      "step": 16350
    },
    {
      "epoch": 4.69174653125447,
      "grad_norm": 0.5996478129830516,
      "learning_rate": 5.998771899554551e-06,
      "loss": 1.58,
      "step": 16400
    },
    {
      "epoch": 4.69174653125447,
      "eval_loss": 1.6419577598571777,
      "eval_runtime": 13.0531,
      "eval_samples_per_second": 76.61,
      "eval_steps_per_second": 2.452,
      "step": 16400
    },
    {
      "epoch": 4.706050636532685,
      "grad_norm": 0.8110729150452963,
      "learning_rate": 5.978492586606647e-06,
      "loss": 1.5815,
      "step": 16450
    },
    {
      "epoch": 4.720354741810899,
      "grad_norm": 0.7079172508860698,
      "learning_rate": 5.958203440167261e-06,
      "loss": 1.5735,
      "step": 16500
    },
    {
      "epoch": 4.734658847089115,
      "grad_norm": 0.7437188489635005,
      "learning_rate": 5.93790487719823e-06,
      "loss": 1.5816,
      "step": 16550
    },
    {
      "epoch": 4.74896295236733,
      "grad_norm": 0.6429721202094572,
      "learning_rate": 5.917597314854914e-06,
      "loss": 1.5735,
      "step": 16600
    },
    {
      "epoch": 4.763267057645544,
      "grad_norm": 0.7341831677461502,
      "learning_rate": 5.897281170477614e-06,
      "loss": 1.5851,
      "step": 16650
    },
    {
      "epoch": 4.777571162923759,
      "grad_norm": 0.6108465449546007,
      "learning_rate": 5.876956861583007e-06,
      "loss": 1.5671,
      "step": 16700
    },
    {
      "epoch": 4.791875268201974,
      "grad_norm": 0.6989820941323435,
      "learning_rate": 5.856624805855548e-06,
      "loss": 1.5844,
      "step": 16750
    },
    {
      "epoch": 4.806179373480189,
      "grad_norm": 0.697409967231527,
      "learning_rate": 5.83628542113891e-06,
      "loss": 1.5913,
      "step": 16800
    },
    {
      "epoch": 4.806179373480189,
      "eval_loss": 1.640140175819397,
      "eval_runtime": 13.0618,
      "eval_samples_per_second": 76.559,
      "eval_steps_per_second": 2.45,
      "step": 16800
    },
    {
      "epoch": 4.820483478758404,
      "grad_norm": 0.7126977088350184,
      "learning_rate": 5.815939125427373e-06,
      "loss": 1.5789,
      "step": 16850
    },
    {
      "epoch": 4.834787584036619,
      "grad_norm": 0.6711423839732361,
      "learning_rate": 5.795586336857253e-06,
      "loss": 1.569,
      "step": 16900
    },
    {
      "epoch": 4.849091689314833,
      "grad_norm": 0.6873244551411083,
      "learning_rate": 5.775227473698294e-06,
      "loss": 1.5836,
      "step": 16950
    },
    {
      "epoch": 4.863395794593048,
      "grad_norm": 0.6568926452793338,
      "learning_rate": 5.754862954345081e-06,
      "loss": 1.5768,
      "step": 17000
    },
    {
      "epoch": 4.8776998998712635,
      "grad_norm": 0.6866802641183569,
      "learning_rate": 5.734493197308442e-06,
      "loss": 1.5818,
      "step": 17050
    },
    {
      "epoch": 4.892004005149478,
      "grad_norm": 0.7569171940676707,
      "learning_rate": 5.714118621206843e-06,
      "loss": 1.5744,
      "step": 17100
    },
    {
      "epoch": 4.906308110427693,
      "grad_norm": 0.7437917330435557,
      "learning_rate": 5.693739644757781e-06,
      "loss": 1.5871,
      "step": 17150
    },
    {
      "epoch": 4.920612215705908,
      "grad_norm": 0.6919341126692011,
      "learning_rate": 5.673356686769194e-06,
      "loss": 1.5653,
      "step": 17200
    },
    {
      "epoch": 4.920612215705908,
      "eval_loss": 1.637027382850647,
      "eval_runtime": 13.0268,
      "eval_samples_per_second": 76.765,
      "eval_steps_per_second": 2.456,
      "step": 17200
    },
    {
      "epoch": 4.934916320984122,
      "grad_norm": 0.7285248772831358,
      "learning_rate": 5.6529701661308415e-06,
      "loss": 1.5756,
      "step": 17250
    },
    {
      "epoch": 4.949220426262337,
      "grad_norm": 0.8182466871622013,
      "learning_rate": 5.632580501805692e-06,
      "loss": 1.5798,
      "step": 17300
    },
    {
      "epoch": 4.9635245315405525,
      "grad_norm": 0.6755432735906193,
      "learning_rate": 5.612188112821328e-06,
      "loss": 1.5854,
      "step": 17350
    },
    {
      "epoch": 4.977828636818767,
      "grad_norm": 0.7612962134476555,
      "learning_rate": 5.591793418261326e-06,
      "loss": 1.5812,
      "step": 17400
    },
    {
      "epoch": 4.992132742096982,
      "grad_norm": 0.7563925945387832,
      "learning_rate": 5.571396837256637e-06,
      "loss": 1.5806,
      "step": 17450
    },
    {
      "epoch": 5.006436847375197,
      "grad_norm": 0.7029518743960665,
      "learning_rate": 5.550998788976988e-06,
      "loss": 1.5687,
      "step": 17500
    },
    {
      "epoch": 5.020740952653411,
      "grad_norm": 0.7224515281262691,
      "learning_rate": 5.530599692622257e-06,
      "loss": 1.5522,
      "step": 17550
    },
    {
      "epoch": 5.035045057931626,
      "grad_norm": 0.8254883333638792,
      "learning_rate": 5.510199967413862e-06,
      "loss": 1.5572,
      "step": 17600
    },
    {
      "epoch": 5.035045057931626,
      "eval_loss": 1.63729989528656,
      "eval_runtime": 13.0559,
      "eval_samples_per_second": 76.594,
      "eval_steps_per_second": 2.451,
      "step": 17600
    }
  ],
  "logging_steps": 50,
  "max_steps": 34950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 800,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5651465548791808e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}